From d5501f2ff80d30d615d59531825d3a5f0bb0d35d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:24 +0200 Subject: [PATCH 0001/2093] init: Provide arch_cpu_finalize_init() commit 7725acaa4f0c04fbefb0e0d342635b967bb7d414 upstream check_bugs() has become a dumping ground for all sorts of activities to finalize the CPU initialization before running the rest of the init code. Most are empty, a few do actual bug checks, some do alternative patching and some cobble a CPU advertisement string together.... Aside of that the current implementation requires duplicated function declaration and mostly empty header files for them. Provide a new function arch_cpu_finalize_init(). Provide a generic declaration if CONFIG_ARCH_HAS_CPU_FINALIZE_INIT is selected and a stub inline otherwise. This requires a temporary #ifdef in start_kernel() which will be removed along with check_bugs() once the architectures are converted over. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224544.957805717@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/Kconfig | 3 +++ include/linux/cpu.h | 6 ++++++ init/main.c | 5 +++++ 3 files changed, 14 insertions(+) diff --git a/arch/Kconfig b/arch/Kconfig index 81599f5c17b0..b60d271bf76a 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -285,6 +285,9 @@ config ARCH_HAS_DMA_SET_UNCACHED config ARCH_HAS_DMA_CLEAR_UNCACHED bool +config ARCH_HAS_CPU_FINALIZE_INIT + bool + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 314802f98b9d..43b0b7950e33 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -187,6 +187,12 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void arch_cpu_idle_dead(void); +#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT +void arch_cpu_finalize_init(void); +#else +static inline void arch_cpu_finalize_init(void) { } +#endif + int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); diff --git a/init/main.c b/init/main.c index aa21add5f7c5..8c720c5bd7cb 100644 --- a/init/main.c +++ b/init/main.c @@ -1135,7 +1135,12 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) delayacct_init(); poking_init(); + + arch_cpu_finalize_init(); + /* Temporary conditional until everything has been converted */ +#ifndef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT check_bugs(); +#endif acpi_subsystem_init(); arch_post_acpi_subsys_init(); From 7918a3555a2502a4d86b831da089f3b985d1bca9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:24 +0200 Subject: [PATCH 0002/2093] x86/cpu: Switch to arch_cpu_finalize_init() commit 7c7077a72674402654f3291354720cd73cdf649e upstream check_bugs() is a dumping ground for finalizing the CPU bringup. Only parts of it has to do with actual CPU bugs. Split it apart into arch_cpu_finalize_init() and cpu_select_mitigations(). Fixup the bogus 32bit comments while at it. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230613224545.019583869@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/Kconfig | 1 + arch/x86/include/asm/bugs.h | 2 -- arch/x86/kernel/cpu/bugs.c | 51 +--------------------------------- arch/x86/kernel/cpu/common.c | 53 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/cpu.h | 1 + 5 files changed, 56 insertions(+), 52 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b3d5706579d4..3867f102cde1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,6 +69,7 @@ config X86 select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CACHE_LINE_SIZE + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 92ae28389940..f25ca2d709d4 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -4,8 +4,6 @@ #include -extern void check_bugs(void); - #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) int ppro_with_ram_bug(void); #else diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f54992887491..d3732e97ad14 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,7 +9,6 @@ * - Andrew D. Balsa (code cleanup). */ #include -#include #include #include #include @@ -27,8 +26,6 @@ #include #include #include -#include -#include #include #include #include @@ -124,21 +121,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); -void __init check_bugs(void) +void __init cpu_select_mitigations(void) { - identify_boot_cpu(); - - /* - * identify_boot_cpu() initialized SMT support information, let the - * core code know. - */ - cpu_smt_check_topology(); - - if (!IS_ENABLED(CONFIG_SMP)) { - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); - } - /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD @@ -175,39 +159,6 @@ void __init check_bugs(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); - - arch_smt_update(); - -#ifdef CONFIG_X86_32 - /* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); - - init_utsname()->machine[1] = - '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); - - fpu__init_check_bugs(); -#else /* CONFIG_X86_64 */ - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -#endif } /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d298d70f74ce..20c3c3ea6976 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -19,10 +19,13 @@ #include #include #include +#include #include #include #include +#include +#include #include #include #include @@ -58,6 +61,7 @@ #include #include #include +#include #include #include #include @@ -2369,3 +2373,52 @@ void arch_smt_update(void) /* Check whether IPI broadcasting can be enabled */ apic_smt_update(); } + +void __init arch_cpu_finalize_init(void) +{ + identify_boot_cpu(); + + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + cpu_select_mitigations(); + + arch_smt_update(); + + if (IS_ENABLED(CONFIG_X86_32)) { + /* + * Check whether this is a real i386 which is not longer + * supported and fixup the utsname. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + } + + alternative_instructions(); + + if (IS_ENABLED(CONFIG_X86_64)) { + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); + } else { + fpu__init_check_bugs(); + } +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 7c9b5893c30a..61dbb9b216e6 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -79,6 +79,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); From e2e06240ae4780977387906e2e11774283ca7997 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0003/2093] ARM: cpu: Switch to arch_cpu_finalize_init() commit ee31bb0524a2e7c99b03f50249a411cc1eaa411f upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.078124882@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/arm/Kconfig | 1 + arch/arm/include/asm/bugs.h | 4 ---- arch/arm/kernel/bugs.c | 3 ++- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0202e48e7a20..6d5afe2e6ba3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,7 @@ config ARM select ARCH_32BIT_OFF_T select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h index 97a312ba0840..fe385551edec 100644 --- a/arch/arm/include/asm/bugs.h +++ b/arch/arm/include/asm/bugs.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * arch/arm/include/asm/bugs.h - * * Copyright (C) 1995-2003 Russell King */ #ifndef __ASM_BUGS_H @@ -10,10 +8,8 @@ extern void check_writebuffer_bugs(void); #ifdef CONFIG_MMU -extern void check_bugs(void); extern void check_other_bugs(void); #else -#define check_bugs() do { } while (0) #define check_other_bugs() do { } while (0) #endif diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c index 14c8dbbb7d2d..087bce6ec8e9 100644 --- a/arch/arm/kernel/bugs.c +++ b/arch/arm/kernel/bugs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include @@ -11,7 +12,7 @@ void check_other_bugs(void) #endif } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { check_writebuffer_bugs(); check_other_bugs(); From 403e4cc67e4cf9226c57a7cb27c7f4365d2143b7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0004/2093] ia64/cpu: Switch to arch_cpu_finalize_init() commit 6c38e3005621800263f117fb00d6787a76e16de7 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.137045745@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/ia64/Kconfig | 1 + arch/ia64/include/asm/bugs.h | 20 -------------------- arch/ia64/kernel/setup.c | 3 +-- 3 files changed, 2 insertions(+), 22 deletions(-) delete mode 100644 arch/ia64/include/asm/bugs.h diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index c6e06cdc738f..283b751cbf6a 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -9,6 +9,7 @@ menu "Processor type and features" config IA64 bool select ARCH_BINFMT_ELF_EXTRA_PHDRS + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_DMA_MARK_CLEAN select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER diff --git a/arch/ia64/include/asm/bugs.h b/arch/ia64/include/asm/bugs.h deleted file mode 100644 index 0d6b9bded56c..000000000000 --- a/arch/ia64/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - * - * Based on . - * - * Modified 1998, 1999, 2003 - * David Mosberger-Tang , Hewlett-Packard Co. - */ -#ifndef _ASM_IA64_BUGS_H -#define _ASM_IA64_BUGS_H - -#include - -extern void check_bugs (void); - -#endif /* _ASM_IA64_BUGS_H */ diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index c05728044272..9009f1871e3b 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1067,8 +1067,7 @@ cpu_init (void) } } -void __init -check_bugs (void) +void __init arch_cpu_finalize_init(void) { ia64_patch_mckinley_e9((unsigned long) __start___mckinley_e9_bundles, (unsigned long) __end___mckinley_e9_bundles); From 08e86d42e2c916e362d124e3bc6c824eb1862498 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0005/2093] loongarch/cpu: Switch to arch_cpu_finalize_init() commit 9841c423164787feb8f1442f922b7d80a70c82f1 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.195288218@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/Kconfig | 1 + arch/loongarch/kernel/setup.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e737dc8cd660..270742cc3ca4 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -10,6 +10,7 @@ config LOONGARCH select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index ae436def7ee9..29725b37b35c 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -12,6 +12,7 @@ */ #include #include +#include #include #include #include @@ -80,6 +81,11 @@ const char *get_system_type(void) return "generic-loongson-machine"; } +void __init arch_cpu_finalize_init(void) +{ + alternative_instructions(); +} + static const char *dmi_string_parse(const struct dmi_header *dm, u8 s) { const u8 *bp = ((u8 *) dm) + dm->length; From 489ae02c89936c7e40f04191e8c160ac53649526 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0006/2093] m68k/cpu: Switch to arch_cpu_finalize_init() commit 9ceecc2589b9d7cef6b321339ed8de484eac4b20 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Acked-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230613224545.254342916@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/m68k/Kconfig | 1 + arch/m68k/include/asm/bugs.h | 21 --------------------- arch/m68k/kernel/setup_mm.c | 3 ++- 3 files changed, 3 insertions(+), 22 deletions(-) delete mode 100644 arch/m68k/include/asm/bugs.h diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 7bff88118507..1fe5b2018745 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -4,6 +4,7 @@ config M68K default y select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA diff --git a/arch/m68k/include/asm/bugs.h b/arch/m68k/include/asm/bugs.h deleted file mode 100644 index 745530651e0b..000000000000 --- a/arch/m68k/include/asm/bugs.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-m68k/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#ifdef CONFIG_MMU -extern void check_bugs(void); /* in arch/m68k/kernel/setup.c */ -#else -static void check_bugs(void) -{ -} -#endif diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index fbff1cea62ca..6f1ae01f322c 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -10,6 +10,7 @@ */ #include +#include #include #include #include @@ -504,7 +505,7 @@ static int __init proc_hardware_init(void) module_init(proc_hardware_init); #endif -void check_bugs(void) +void __init arch_cpu_finalize_init(void) { #if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU) if (m68k_fputype == 0) { From 6a90583dbd9b794071b8b54d8c36f40a459d1051 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0007/2093] mips/cpu: Switch to arch_cpu_finalize_init() commit 7f066a22fe353a827a402ee2835e81f045b1574d upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.312438573@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/mips/Kconfig | 1 + arch/mips/include/asm/bugs.h | 17 ----------------- arch/mips/kernel/setup.c | 13 +++++++++++++ 3 files changed, 14 insertions(+), 17 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 7b0856c76c9a..cf1fbf4eaa8a 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,6 +4,7 @@ config MIPS default y select ARCH_32BIT_OFF_T if !64BIT select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER if !CC_IS_CLANG || CLANG_VERSION >= 140000 select ARCH_HAS_DEBUG_VIRTUAL if !64BIT select ARCH_HAS_FORTIFY_SOURCE diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d72dc6e1cf3c..8d4cf29861b8 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -1,17 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * This is included by init/main.c to check for architecture-dependent bugs. - * * Copyright (C) 2007 Maciej W. Rozycki - * - * Needs: - * void check_bugs(void); */ #ifndef _ASM_BUGS_H #define _ASM_BUGS_H #include -#include #include #include @@ -30,17 +24,6 @@ static inline void check_bugs_early(void) check_bugs64_early(); } -static inline void check_bugs(void) -{ - unsigned int cpu = smp_processor_id(); - - cpu_data[cpu].udelay_val = loops_per_jiffy; - check_bugs32(); - - if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) - check_bugs64(); -} - static inline int r4k_daddiu_bug(void) { if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 81dbb4ef5231..7c540572f1f7 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -11,6 +11,8 @@ * Copyright (C) 2000, 2001, 2002, 2007 Maciej W. Rozycki */ #include +#include +#include #include #include #include @@ -840,3 +842,14 @@ static int __init setnocoherentio(char *str) } early_param("nocoherentio", setnocoherentio); #endif + +void __init arch_cpu_finalize_init(void) +{ + unsigned int cpu = smp_processor_id(); + + cpu_data[cpu].udelay_val = loops_per_jiffy; + check_bugs32(); + + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64(); +} From 84f585542ec69226311be5a4500a4b3cbad6fb5b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0008/2093] sh/cpu: Switch to arch_cpu_finalize_init() commit 01eb454e9bfe593f320ecbc9aaec60bf87cd453d upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.371697797@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/sh/Kconfig | 1 + arch/sh/include/asm/bugs.h | 74 --------------------------------- arch/sh/include/asm/processor.h | 2 + arch/sh/kernel/idle.c | 1 + arch/sh/kernel/setup.c | 55 ++++++++++++++++++++++++ 5 files changed, 59 insertions(+), 74 deletions(-) delete mode 100644 arch/sh/include/asm/bugs.h diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 8e4d1f757bcc..a0593f6ce0e0 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -7,6 +7,7 @@ config SUPERH select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_BINFMT_FLAT if !MMU + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h deleted file mode 100644 index fe52abb69cea..000000000000 --- a/arch/sh/include/asm/bugs.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_SH_BUGS_H -#define __ASM_SH_BUGS_H - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any Super-H bugs yet. - */ - -#include - -extern void select_idle_routine(void); - -static void __init check_bugs(void) -{ - extern unsigned long loops_per_jiffy; - char *p = &init_utsname()->machine[2]; /* "sh" */ - - select_idle_routine(); - - current_cpu_data.loops_per_jiffy = loops_per_jiffy; - - switch (current_cpu_data.family) { - case CPU_FAMILY_SH2: - *p++ = '2'; - break; - case CPU_FAMILY_SH2A: - *p++ = '2'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH3: - *p++ = '3'; - break; - case CPU_FAMILY_SH4: - *p++ = '4'; - break; - case CPU_FAMILY_SH4A: - *p++ = '4'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH4AL_DSP: - *p++ = '4'; - *p++ = 'a'; - *p++ = 'l'; - *p++ = '-'; - *p++ = 'd'; - *p++ = 's'; - *p++ = 'p'; - break; - case CPU_FAMILY_UNKNOWN: - /* - * Specifically use CPU_FAMILY_UNKNOWN rather than - * default:, so we're able to have the compiler whine - * about unhandled enumerations. - */ - break; - } - - printk("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); - -#ifndef __LITTLE_ENDIAN__ - /* 'eb' means 'Endian Big' */ - *p++ = 'e'; - *p++ = 'b'; -#endif - *p = '\0'; -} -#endif /* __ASM_SH_BUGS_H */ diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 85a6c1c3c16e..73fba7c922f9 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -166,6 +166,8 @@ extern unsigned int instruction_size(unsigned int insn); #define instruction_size(insn) (2) #endif +void select_idle_routine(void); + #endif /* __ASSEMBLY__ */ #include diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index f59814983bd5..a80b2a5b25c7 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index af977ec4ca5e..cf7c0f72f293 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -354,3 +355,57 @@ int test_mode_pin(int pin) { return sh_mv.mv_mode_pins() & pin; } + +void __init arch_cpu_finalize_init(void) +{ + char *p = &init_utsname()->machine[2]; /* "sh" */ + + select_idle_routine(); + + current_cpu_data.loops_per_jiffy = loops_per_jiffy; + + switch (current_cpu_data.family) { + case CPU_FAMILY_SH2: + *p++ = '2'; + break; + case CPU_FAMILY_SH2A: + *p++ = '2'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH3: + *p++ = '3'; + break; + case CPU_FAMILY_SH4: + *p++ = '4'; + break; + case CPU_FAMILY_SH4A: + *p++ = '4'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH4AL_DSP: + *p++ = '4'; + *p++ = 'a'; + *p++ = 'l'; + *p++ = '-'; + *p++ = 'd'; + *p++ = 's'; + *p++ = 'p'; + break; + case CPU_FAMILY_UNKNOWN: + /* + * Specifically use CPU_FAMILY_UNKNOWN rather than + * default:, so we're able to have the compiler whine + * about unhandled enumerations. + */ + break; + } + + pr_info("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); + +#ifndef __LITTLE_ENDIAN__ + /* 'eb' means 'Endian Big' */ + *p++ = 'e'; + *p++ = 'b'; +#endif + *p = '\0'; +} From ce97072e10cc844fac8176681b2cb17bf3eaaa7b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0009/2093] sparc/cpu: Switch to arch_cpu_finalize_init() commit 44ade508e3bfac45ae97864587de29eb1a881ec0 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Sam Ravnborg Link: https://lore.kernel.org/r/20230613224545.431995857@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/sparc/Kconfig | 1 + arch/sparc/include/asm/bugs.h | 18 ------------------ arch/sparc/kernel/setup_32.c | 7 +++++++ 3 files changed, 8 insertions(+), 18 deletions(-) delete mode 100644 arch/sparc/include/asm/bugs.h diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index dbb1760cbe8c..b67d96e3392e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -51,6 +51,7 @@ config SPARC config SPARC32 def_bool !64BIT select ARCH_32BIT_OFF_T + select ARCH_HAS_CPU_FINALIZE_INIT if !SMP select ARCH_HAS_SYNC_DMA_FOR_CPU select CLZ_TAB select DMA_DIRECT_REMAP diff --git a/arch/sparc/include/asm/bugs.h b/arch/sparc/include/asm/bugs.h deleted file mode 100644 index 02fa369b9c21..000000000000 --- a/arch/sparc/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include/asm/bugs.h: Sparc probes for various bugs. - * - * Copyright (C) 1996, 2007 David S. Miller (davem@davemloft.net) - */ - -#ifdef CONFIG_SPARC32 -#include -#endif - -extern unsigned long loops_per_jiffy; - -static void __init check_bugs(void) -{ -#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) - cpu_data(0).udelay_val = loops_per_jiffy; -#endif -} diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index c8e0dd99f370..c9d1ba4f311b 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -412,3 +412,10 @@ static int __init topology_init(void) } subsys_initcall(topology_init); + +#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) +void __init arch_cpu_finalize_init(void) +{ + cpu_data(0).udelay_val = loops_per_jiffy; +} +#endif From 8beabde0ed8d31e45a3d9484f0591a18c0c94cc7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0010/2093] um/cpu: Switch to arch_cpu_finalize_init() commit 9349b5cd0908f8afe95529fc7a8cbb1417df9b0c upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Acked-by: Richard Weinberger Link: https://lore.kernel.org/r/20230613224545.493148694@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/um/Kconfig | 1 + arch/um/include/asm/bugs.h | 7 ------- arch/um/kernel/um_arch.c | 3 ++- 3 files changed, 3 insertions(+), 8 deletions(-) delete mode 100644 arch/um/include/asm/bugs.h diff --git a/arch/um/Kconfig b/arch/um/Kconfig index ad4ff3b0e91e..82709bc36df7 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -6,6 +6,7 @@ config UML bool default y select ARCH_EPHEMERAL_INODES + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h deleted file mode 100644 index 4473942a0839..000000000000 --- a/arch/um/include/asm/bugs.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_BUGS_H -#define __UM_BUGS_H - -void check_bugs(void); - -#endif diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8adf8e89b255..334c91191b31 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -3,6 +3,7 @@ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ +#include #include #include #include @@ -426,7 +427,7 @@ void __init setup_arch(char **cmdline_p) } } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { arch_check_bugs(); os_check_bugs(); From a3342c60dcc58007cc14b2cf1ebc7e2b563423a8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0011/2093] init: Remove check_bugs() leftovers commit 61235b24b9cb37c13fcad5b9596d59a1afdcec30 upstream Everything is converted over to arch_cpu_finalize_init(). Remove the check_bugs() leftovers including the empty stubs in asm-generic, alpha, parisc, powerpc and xtensa. Signed-off-by: Thomas Gleixner Reviewed-by: Richard Henderson Link: https://lore.kernel.org/r/20230613224545.553215951@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/bugs.h | 20 -------------------- arch/parisc/include/asm/bugs.h | 20 -------------------- arch/powerpc/include/asm/bugs.h | 15 --------------- arch/xtensa/include/asm/bugs.h | 18 ------------------ include/asm-generic/bugs.h | 11 ----------- init/main.c | 5 ----- 6 files changed, 89 deletions(-) delete mode 100644 arch/alpha/include/asm/bugs.h delete mode 100644 arch/parisc/include/asm/bugs.h delete mode 100644 arch/powerpc/include/asm/bugs.h delete mode 100644 arch/xtensa/include/asm/bugs.h delete mode 100644 include/asm-generic/bugs.h diff --git a/arch/alpha/include/asm/bugs.h b/arch/alpha/include/asm/bugs.h deleted file mode 100644 index 78030d1c7e7e..000000000000 --- a/arch/alpha/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * include/asm-alpha/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any alpha bugs yet.. Nice chip - */ - -static void check_bugs(void) -{ -} diff --git a/arch/parisc/include/asm/bugs.h b/arch/parisc/include/asm/bugs.h deleted file mode 100644 index 0a7f9db6bd1c..000000000000 --- a/arch/parisc/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-parisc/bugs.h - * - * Copyright (C) 1999 Mike Shaver - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#include - -static inline void check_bugs(void) -{ -// identify_cpu(&boot_cpu_data); -} diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h deleted file mode 100644 index 01b8f6ca4dbb..000000000000 --- a/arch/powerpc/include/asm/bugs.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_BUGS_H -#define _ASM_POWERPC_BUGS_H - -/* - */ - -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* _ASM_POWERPC_BUGS_H */ diff --git a/arch/xtensa/include/asm/bugs.h b/arch/xtensa/include/asm/bugs.h deleted file mode 100644 index 69b29d198249..000000000000 --- a/arch/xtensa/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-xtensa/bugs.h - * - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Xtensa processors don't have any bugs. :) - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file "COPYING" in the main directory of - * this archive for more details. - */ - -#ifndef _XTENSA_BUGS_H -#define _XTENSA_BUGS_H - -static void check_bugs(void) { } - -#endif /* _XTENSA_BUGS_H */ diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h deleted file mode 100644 index 69021830f078..000000000000 --- a/include/asm-generic/bugs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_BUGS_H -#define __ASM_GENERIC_BUGS_H -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* __ASM_GENERIC_BUGS_H */ diff --git a/init/main.c b/init/main.c index 8c720c5bd7cb..fa3b4c99616e 100644 --- a/init/main.c +++ b/init/main.c @@ -104,7 +104,6 @@ #include #include -#include #include #include #include @@ -1137,10 +1136,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) poking_init(); arch_cpu_finalize_init(); - /* Temporary conditional until everything has been converted */ -#ifndef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT - check_bugs(); -#endif acpi_subsystem_init(); arch_post_acpi_subsys_init(); From 8183a89caf67a1f56f1da1d6081e26a0ae7a5fdf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0012/2093] init: Invoke arch_cpu_finalize_init() earlier commit 9df9d2f0471b4c4702670380b8d8a45b40b23a7d upstream X86 is reworking the boot process so that initializations which are not required during early boot can be moved into the late boot process and out of the fragile and restricted initial boot phase. arch_cpu_finalize_init() is the obvious place to do such initializations, but arch_cpu_finalize_init() is invoked too late in start_kernel() e.g. for initializing the FPU completely. fork_init() requires that the FPU is initialized as the size of task_struct on X86 depends on the size of the required FPU register buffer. Fortunately none of the init calls between calibrate_delay() and arch_cpu_finalize_init() is relevant for the functionality of arch_cpu_finalize_init(). Invoke it right after calibrate_delay() where everything which is relevant for arch_cpu_finalize_init() has been set up already. No functional change intended. Signed-off-by: Thomas Gleixner Reviewed-by: Rick Edgecombe Link: https://lore.kernel.org/r/20230613224545.612182854@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- init/main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/init/main.c b/init/main.c index fa3b4c99616e..3ad2400e7aa4 100644 --- a/init/main.c +++ b/init/main.c @@ -1107,6 +1107,9 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) late_time_init(); sched_clock_init(); calibrate_delay(); + + arch_cpu_finalize_init(); + pid_idr_init(); anon_vma_init(); #ifdef CONFIG_X86 @@ -1135,8 +1138,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) poking_init(); - arch_cpu_finalize_init(); - acpi_subsystem_init(); arch_post_acpi_subsys_init(); kcsan_init(); From b0837880fa65fa4a6dc407b42e9b33e18f7b44e3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0013/2093] init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init() commit 439e17576eb47f26b78c5bbc72e344d4206d2327 upstream Invoke the X86ism mem_encrypt_init() from X86 arch_cpu_finalize_init() and remove the weak fallback from the core code. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.670360645@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mem_encrypt.h | 7 ++++--- arch/x86/kernel/cpu/common.c | 11 +++++++++++ init/main.c | 11 ----------- 3 files changed, 15 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 72ca90552b6a..a95914f479b8 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -51,6 +51,8 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +void __init mem_encrypt_init(void); + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -82,13 +84,12 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline void mem_encrypt_init(void) { } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void add_encrypt_protection_map(void); /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 20c3c3ea6976..d750115e8fff 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -2421,4 +2422,14 @@ void __init arch_cpu_finalize_init(void) } else { fpu__init_check_bugs(); } + + /* + * This needs to be called before any devices perform DMA + * operations that might use the SWIOTLB bounce buffers. It will + * mark the bounce buffers as decrypted so that their usage will + * not cause "plain-text" data to be decrypted when accessed. It + * must be called after late_time_init() so that Hyper-V x86/x64 + * hypercalls work when the SWIOTLB bounce buffers are decrypted. + */ + mem_encrypt_init(); } diff --git a/init/main.c b/init/main.c index 3ad2400e7aa4..5b53f04571bb 100644 --- a/init/main.c +++ b/init/main.c @@ -96,7 +96,6 @@ #include #include #include -#include #include #include #include @@ -780,8 +779,6 @@ void __init __weak thread_stack_cache_init(void) } #endif -void __init __weak mem_encrypt_init(void) { } - void __init __weak poking_init(void) { } void __init __weak pgtable_cache_init(void) { } @@ -1083,14 +1080,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) */ locking_selftest(); - /* - * This needs to be called before any devices perform DMA - * operations that might use the SWIOTLB bounce buffers. It will - * mark the bounce buffers as decrypted so that their usage will - * not cause "plain-text" data to be decrypted when accessed. - */ - mem_encrypt_init(); - #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start && !initrd_below_start_ok && page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) { From c956807d8462e94a1450dc0737728c25917b1d67 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0014/2093] x86/init: Initialize signal frame size late commit 54d9a91a3d6713d1332e93be13b4eaf0fa54349d upstream No point in doing this during really early boot. Move it to an early initcall so that it is set up before possible user mode helpers are started during device initialization. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.727330699@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/sigframe.h | 2 -- arch/x86/kernel/cpu/common.c | 3 --- arch/x86/kernel/signal.c | 4 +++- 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 5b1ed650b124..84eab2724875 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -85,6 +85,4 @@ struct rt_sigframe_x32 { #endif /* CONFIG_X86_64 */ -void __init init_sigframe_size(void); - #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d750115e8fff..678dc12b2f1c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -63,7 +63,6 @@ #include #include #include -#include #include #include @@ -1578,8 +1577,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) fpu__init_system(c); - init_sigframe_size(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 82c562e2cc98..55ed638cb3fd 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -724,7 +724,7 @@ SYSCALL_DEFINE0(rt_sigreturn) static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; -void __init init_sigframe_size(void) +static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); @@ -736,7 +736,9 @@ void __init init_sigframe_size(void) max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); + return 0; } +early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { From 9e8d9d399094dd911059ff337dd8a104f052e1ca Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0015/2093] x86/fpu: Remove cpuinfo argument from init functions commit 1f34bb2a24643e0087652d81078e4f616562738d upstream Nothing in the call chain requires it Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.783704297@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/fpu/api.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/fpu/init.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 503a577814b2..b475d9a582b8 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -109,7 +109,7 @@ extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); -extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 678dc12b2f1c..6f7310efb671 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1575,7 +1575,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(c); + fpu__init_system(); #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 851eb13edc01..5001df943828 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static void fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { @@ -211,10 +211,10 @@ static void __init fpu__init_system_xstate_size_legacy(void) * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ -void __init fpu__init_system(struct cpuinfo_x86 *c) +void __init fpu__init_system(void) { fpstate_reset(¤t->thread.fpu); - fpu__init_system_early_generic(c); + fpu__init_system_early_generic(); /* * The FPU has to be operational for some of the From e26932942b2c505d5e8a9f263cbe66de4fab1b24 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0016/2093] x86/fpu: Mark init functions __init commit 1703db2b90c91b2eb2d699519fc505fe431dde0e upstream No point in keeping them around. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.841685728@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/fpu/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 5001df943828..998a08f17e33 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -53,7 +53,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -static bool fpu__probe_without_cpuid(void) +static bool __init fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(void) +static void __init fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { From f25ad76d92176f41a543a812972e9937ce4f7d08 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0017/2093] x86/fpu: Move FPU initialization into arch_cpu_finalize_init() commit b81fac906a8f9e682e513ddd95697ec7a20878d4 upstream Initializing the FPU during the early boot process is a pointless exercise. Early boot is convoluted and fragile enough. Nothing requires that the FPU is set up early. It has to be initialized before fork_init() because the task_struct size depends on the FPU register buffer size. Move the initialization to arch_cpu_finalize_init() which is the perfect place to do so. No functional change. This allows to remove quite some of the custom early command line parsing, but that's subject to the next installment. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.902376621@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/common.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6f7310efb671..2bab14d5115c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1575,8 +1575,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says @@ -2292,8 +2290,6 @@ void cpu_init(void) doublefault_init_cpu_tss(); - fpu__init_cpu(); - if (is_uv_system()) uv_cpu_init(); @@ -2309,6 +2305,7 @@ void cpu_init_secondary(void) */ cpu_init_exception_handling(); cpu_init(); + fpu__init_cpu(); } #endif @@ -2403,6 +2400,13 @@ void __init arch_cpu_finalize_init(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); } + /* + * Must be before alternatives because it might set or clear + * feature bits. + */ + fpu__init_system(); + fpu__init_cpu(); + alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { From c66ebe070d9641c9339e42e1c2d707a5052e9904 Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Tue, 1 Aug 2023 16:36:25 +0200 Subject: [PATCH 0018/2093] x86/speculation: Add Gather Data Sampling mitigation commit 8974eb588283b7d44a7c91fa09fcbaf380339f3a upstream Gather Data Sampling (GDS) is a hardware vulnerability which allows unprivileged speculative access to data which was previously stored in vector registers. Intel processors that support AVX2 and AVX512 have gather instructions that fetch non-contiguous data elements from memory. On vulnerable hardware, when a gather instruction is transiently executed and encounters a fault, stale data from architectural or internal vector registers may get transiently stored to the destination vector register allowing an attacker to infer the stale data using typical side channel techniques like cache timing attacks. This mitigation is different from many earlier ones for two reasons. First, it is enabled by default and a bit must be set to *DISABLE* it. This is the opposite of normal mitigation polarity. This means GDS can be mitigated simply by updating microcode and leaving the new control bit alone. Second, GDS has a "lock" bit. This lock bit is there because the mitigation affects the hardware security features KeyLocker and SGX. It needs to be enabled and *STAY* enabled for these features to be mitigated against GDS. The mitigation is enabled in the microcode by default. Disable it by setting gather_data_sampling=off or by disabling all mitigations with mitigations=off. The mitigation status can be checked by reading: /sys/devices/system/cpu/vulnerabilities/gather_data_sampling Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-devices-system-cpu | 15 +- .../hw-vuln/gather_data_sampling.rst | 99 ++++++++++++++ Documentation/admin-guide/hw-vuln/index.rst | 1 + .../admin-guide/kernel-parameters.txt | 41 ++++-- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr-index.h | 11 ++ arch/x86/kernel/cpu/bugs.c | 129 ++++++++++++++++++ arch/x86/kernel/cpu/common.c | 34 +++-- arch/x86/kernel/cpu/cpu.h | 1 + drivers/base/cpu.c | 8 ++ 10 files changed, 311 insertions(+), 29 deletions(-) create mode 100644 Documentation/admin-guide/hw-vuln/gather_data_sampling.rst diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index f54867cadb0f..13c01b641dc7 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -513,17 +513,18 @@ Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpuX. What: /sys/devices/system/cpu/vulnerabilities - /sys/devices/system/cpu/vulnerabilities/meltdown - /sys/devices/system/cpu/vulnerabilities/spectre_v1 - /sys/devices/system/cpu/vulnerabilities/spectre_v2 - /sys/devices/system/cpu/vulnerabilities/spec_store_bypass + /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds - /sys/devices/system/cpu/vulnerabilities/srbds - /sys/devices/system/cpu/vulnerabilities/tsx_async_abort - /sys/devices/system/cpu/vulnerabilities/itlb_multihit + /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data /sys/devices/system/cpu/vulnerabilities/retbleed + /sys/devices/system/cpu/vulnerabilities/spec_store_bypass + /sys/devices/system/cpu/vulnerabilities/spectre_v1 + /sys/devices/system/cpu/vulnerabilities/spectre_v2 + /sys/devices/system/cpu/vulnerabilities/srbds + /sys/devices/system/cpu/vulnerabilities/tsx_async_abort Date: January 2018 Contact: Linux kernel mailing list Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst new file mode 100644 index 000000000000..74dab6af7fe1 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -0,0 +1,99 @@ +.. SPDX-License-Identifier: GPL-2.0 + +GDS - Gather Data Sampling +========================== + +Gather Data Sampling is a hardware vulnerability which allows unprivileged +speculative access to data which was previously stored in vector registers. + +Problem +------- +When a gather instruction performs loads from memory, different data elements +are merged into the destination vector register. However, when a gather +instruction that is transiently executed encounters a fault, stale data from +architectural or internal vector registers may get transiently forwarded to the +destination vector register instead. This will allow a malicious attacker to +infer stale data using typical side channel techniques like cache timing +attacks. GDS is a purely sampling-based attack. + +The attacker uses gather instructions to infer the stale vector register data. +The victim does not need to do anything special other than use the vector +registers. The victim does not need to use gather instructions to be +vulnerable. + +Because the buffers are shared between Hyper-Threads cross Hyper-Thread attacks +are possible. + +Attack scenarios +---------------- +Without mitigation, GDS can infer stale data across virtually all +permission boundaries: + + Non-enclaves can infer SGX enclave data + Userspace can infer kernel data + Guests can infer data from hosts + Guest can infer guest from other guests + Users can infer data from other users + +Because of this, it is important to ensure that the mitigation stays enabled in +lower-privilege contexts like guests and when running outside SGX enclaves. + +The hardware enforces the mitigation for SGX. Likewise, VMMs should ensure +that guests are not allowed to disable the GDS mitigation. If a host erred and +allowed this, a guest could theoretically disable GDS mitigation, mount an +attack, and re-enable it. + +Mitigation mechanism +-------------------- +This issue is mitigated in microcode. The microcode defines the following new +bits: + + ================================ === ============================ + IA32_ARCH_CAPABILITIES[GDS_CTRL] R/O Enumerates GDS vulnerability + and mitigation support. + IA32_ARCH_CAPABILITIES[GDS_NO] R/O Processor is not vulnerable. + IA32_MCU_OPT_CTRL[GDS_MITG_DIS] R/W Disables the mitigation + 0 by default. + IA32_MCU_OPT_CTRL[GDS_MITG_LOCK] R/W Locks GDS_MITG_DIS=0. Writes + to GDS_MITG_DIS are ignored + Can't be cleared once set. + ================================ === ============================ + +GDS can also be mitigated on systems that don't have updated microcode by +disabling AVX. This can be done by setting "clearcpuid=avx" on the kernel +command-line. + +Mitigation control on the kernel command line +--------------------------------------------- +The mitigation can be disabled by setting "gather_data_sampling=off" or +"mitigations=off" on the kernel command line. Not specifying either will +default to the mitigation being enabled. + +GDS System Information +------------------------ +The kernel provides vulnerability status information through sysfs. For +GDS this can be accessed by the following sysfs file: + +/sys/devices/system/cpu/vulnerabilities/gather_data_sampling + +The possible values contained in this file are: + + ============================== ============================================= + Not affected Processor not vulnerable. + Vulnerable Processor vulnerable and mitigation disabled. + Vulnerable: No microcode Processor vulnerable and microcode is missing + mitigation. + Mitigation: Microcode Processor is vulnerable and mitigation is in + effect. + Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in + effect and cannot be disabled. + Unknown: Dependent on + hypervisor status Running on a virtual guest processor that is + affected but with no way to know if host + processor is mitigated or vulnerable. + ============================== ============================================= + +GDS Default mitigation +---------------------- +The updated microcode will enable the mitigation by default. The kernel's +default action is to leave the mitigation enabled. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index e0614760a99e..436fac0bd9c3 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -19,3 +19,4 @@ are configurable at compile, boot or run time. l1d_flush.rst processor_mmio_stale_data.rst cross-thread-rsb.rst + gather_data_sampling.rst diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6b838869554b..4f946c7be54c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1593,6 +1593,20 @@ Format: off | on default: on + gather_data_sampling= + [X86,INTEL] Control the Gather Data Sampling (GDS) + mitigation. + + Gather Data Sampling is a hardware vulnerability which + allows unprivileged speculative access to data which was + previously stored in vector registers. + + This issue is mitigated by default in updated microcode. + The mitigation may have a performance impact but can be + disabled. + + off: Disable GDS mitigation. + gcov_persist= [GCOV] When non-zero (default), profiling data for kernel modules is saved and remains accessible via debugfs, even when the module is unloaded/reloaded. @@ -3228,24 +3242,25 @@ Disable all optional CPU mitigations. This improves system performance, but it may also expose users to several CPU vulnerabilities. - Equivalent to: nopti [X86,PPC] - if nokaslr then kpti=0 [ARM64] - nospectre_v1 [X86,PPC] - nobp=0 [S390] - nospectre_v2 [X86,PPC,S390,ARM64] - spectre_v2_user=off [X86] - spec_store_bypass_disable=off [X86,PPC] - ssbd=force-off [ARM64] - nospectre_bhb [ARM64] + Equivalent to: if nokaslr then kpti=0 [ARM64] + gather_data_sampling=off [X86] + kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] - tsx_async_abort=off [X86] - kvm.nx_huge_pages=off [X86] - srbds=off [X86,INTEL] + mmio_stale_data=off [X86] no_entry_flush [PPC] no_uaccess_flush [PPC] - mmio_stale_data=off [X86] + nobp=0 [S390] + nopti [X86,PPC] + nospectre_bhb [ARM64] + nospectre_v1 [X86,PPC] + nospectre_v2 [X86,PPC,S390,ARM64] retbleed=off [X86] + spec_store_bypass_disable=off [X86,PPC] + spectre_v2_user=off [X86] + srbds=off [X86,INTEL] + ssbd=force-off [ARM64] + tsx_async_abort=off [X86] Exceptions: This does not have any effect on diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 92729c38853d..9a3d6bdf3b9f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -464,5 +464,6 @@ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 846067e1ee8b..a070e55ba441 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -158,6 +158,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -181,6 +190,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d3732e97ad14..62e67922d340 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -46,6 +46,7 @@ static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); +static void __init gds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -159,6 +160,7 @@ void __init cpu_select_mitigations(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); + gds_select_mitigation(); } /* @@ -644,6 +646,120 @@ static int __init l1d_flush_parse_cmdline(char *str) } early_param("l1d_flush", l1d_flush_parse_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "GDS: " fmt + +enum gds_mitigations { + GDS_MITIGATION_OFF, + GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FULL, + GDS_MITIGATION_FULL_LOCKED, + GDS_MITIGATION_HYPERVISOR, +}; + +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; + +static const char * const gds_strings[] = { + [GDS_MITIGATION_OFF] = "Vulnerable", + [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FULL] = "Mitigation: Microcode", + [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", + [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +void update_gds_msr(void) +{ + u64 mcu_ctrl_after; + u64 mcu_ctrl; + + switch (gds_mitigation) { + case GDS_MITIGATION_OFF: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl |= GDS_MITG_DIS; + break; + case GDS_MITIGATION_FULL_LOCKED: + /* + * The LOCKED state comes from the boot CPU. APs might not have + * the same state. Make sure the mitigation is enabled on all + * CPUs. + */ + case GDS_MITIGATION_FULL: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl &= ~GDS_MITG_DIS; + break; + case GDS_MITIGATION_UCODE_NEEDED: + case GDS_MITIGATION_HYPERVISOR: + return; + }; + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + /* + * Check to make sure that the WRMSR value was not ignored. Writes to + * GDS_MITG_DIS will be ignored if this processor is locked but the boot + * processor was not. + */ + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); + WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); +} + +static void __init gds_select_mitigation(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + gds_mitigation = GDS_MITIGATION_HYPERVISOR; + goto out; + } + + if (cpu_mitigations_off()) + gds_mitigation = GDS_MITIGATION_OFF; + /* Will verify below that mitigation _can_ be disabled */ + + /* No microcode */ + if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + goto out; + } + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + if (mcu_ctrl & GDS_MITG_LOCKED) { + if (gds_mitigation == GDS_MITIGATION_OFF) + pr_warn("Mitigation locked. Disable failed.\n"); + + /* + * The mitigation is selected from the boot CPU. All other CPUs + * _should_ have the same state. If the boot CPU isn't locked + * but others are then update_gds_msr() will WARN() of the state + * mismatch. If the boot CPU is locked update_gds_msr() will + * ensure the other CPUs have the mitigation enabled. + */ + gds_mitigation = GDS_MITIGATION_FULL_LOCKED; + } + + update_gds_msr(); +out: + pr_info("%s\n", gds_strings[gds_mitigation]); +} + +static int __init gds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return 0; + + if (!strcmp(str, "off")) + gds_mitigation = GDS_MITIGATION_OFF; + + return 0; +} +early_param("gather_data_sampling", gds_parse_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt @@ -2356,6 +2472,11 @@ static ssize_t retbleed_show_state(char *buf) return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } +static ssize_t gds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2405,6 +2526,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RETBLEED: return retbleed_show_state(buf); + case X86_BUG_GDS: + return gds_show_state(buf); + default: break; } @@ -2469,4 +2593,9 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } + +ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_GDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2bab14d5115c..98ae37cdba47 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1241,6 +1241,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by SMT (cross-thread) return predictions */ #define SMT_RSB BIT(4) +/* CPU is affected by GDS */ +#define GDS BIT(5) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1253,19 +1255,21 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), @@ -1394,6 +1398,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_matches(cpu_vuln_blacklist, SMT_RSB)) setup_force_cpu_bug(X86_BUG_SMT_RSB); + /* + * Check if CPU is vulnerable to GDS. If running in a virtual machine on + * an affected processor, the VMM may have disabled the use of GATHER by + * disabling AVX2. The only way to do this in HW is to clear XCR0[2], + * which means that AVX will be disabled. + */ + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + boot_cpu_has(X86_FEATURE_AVX)) + setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1957,6 +1971,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + if (boot_cpu_has_bug(X86_BUG_GDS)) + update_gds_msr(); tsx_ap_init(); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 61dbb9b216e6..d9aeb335002d 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -83,6 +83,7 @@ void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); +extern void update_gds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 7af8e33735a3..cc6cf06ce88e 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -577,6 +577,12 @@ ssize_t __weak cpu_show_retbleed(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -588,6 +594,7 @@ static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); +static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -601,6 +608,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, &dev_attr_retbleed.attr, + &dev_attr_gather_data_sampling.attr, NULL }; From 92fc27c79bc7f3e2bfd2b88e197762566daf02a1 Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Tue, 1 Aug 2023 16:36:26 +0200 Subject: [PATCH 0019/2093] x86/speculation: Add force option to GDS mitigation commit 553a5c03e90a6087e88f8ff878335ef0621536fb upstream The Gather Data Sampling (GDS) vulnerability allows malicious software to infer stale data previously stored in vector registers. This may include sensitive data such as cryptographic keys. GDS is mitigated in microcode, and systems with up-to-date microcode are protected by default. However, any affected system that is running with older microcode will still be vulnerable to GDS attacks. Since the gather instructions used by the attacker are part of the AVX2 and AVX512 extensions, disabling these extensions prevents gather instructions from being executed, thereby mitigating the system from GDS. Disabling AVX2 is sufficient, but we don't have the granularity to do this. The XCR0[2] disables AVX, with no option to just disable AVX2. Add a kernel parameter gather_data_sampling=force that will enable the microcode mitigation if available, otherwise it will disable AVX on affected systems. This option will be ignored if cmdline mitigations=off. This is a *big* hammer. It is known to break buggy userspace that uses incomplete, buggy AVX enumeration. Unfortunately, such userspace does exist in the wild: https://www.mail-archive.com/bug-coreutils@gnu.org/msg33046.html [ dhansen: add some more ominous warnings about disabling AVX ] Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- .../hw-vuln/gather_data_sampling.rst | 18 +++++++++++++---- .../admin-guide/kernel-parameters.txt | 8 +++++++- arch/x86/kernel/cpu/bugs.c | 20 ++++++++++++++++++- 3 files changed, 40 insertions(+), 6 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst index 74dab6af7fe1..40b7a6260010 100644 --- a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -60,14 +60,21 @@ bits: ================================ === ============================ GDS can also be mitigated on systems that don't have updated microcode by -disabling AVX. This can be done by setting "clearcpuid=avx" on the kernel -command-line. +disabling AVX. This can be done by setting gather_data_sampling="force" or +"clearcpuid=avx" on the kernel command-line. + +If used, these options will disable AVX use by turning on XSAVE YMM support. +However, the processor will still enumerate AVX support. Userspace that +does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM +support will break. Mitigation control on the kernel command line --------------------------------------------- The mitigation can be disabled by setting "gather_data_sampling=off" or -"mitigations=off" on the kernel command line. Not specifying either will -default to the mitigation being enabled. +"mitigations=off" on the kernel command line. Not specifying either will default +to the mitigation being enabled. Specifying "gather_data_sampling=force" will +use the microcode mitigation when available or disable AVX on affected systems +where the microcode hasn't been updated to include the mitigation. GDS System Information ------------------------ @@ -83,6 +90,9 @@ The possible values contained in this file are: Vulnerable Processor vulnerable and mitigation disabled. Vulnerable: No microcode Processor vulnerable and microcode is missing mitigation. + Mitigation: AVX disabled, + no microcode Processor is vulnerable and microcode is missing + mitigation. AVX disabled as mitigation. Mitigation: Microcode Processor is vulnerable and mitigation is in effect. Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 4f946c7be54c..7f89a185665f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1603,7 +1603,13 @@ This issue is mitigated by default in updated microcode. The mitigation may have a performance impact but can be - disabled. + disabled. On systems without the microcode mitigation + disabling AVX serves as a mitigation. + + force: Disable AVX to mitigate systems without + microcode mitigation. No effect if the microcode + mitigation is present. Known to cause crashes in + userspace with buggy AVX enumeration. off: Disable GDS mitigation. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 62e67922d340..9de9b61cbb71 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -652,6 +652,7 @@ early_param("l1d_flush", l1d_flush_parse_cmdline); enum gds_mitigations { GDS_MITIGATION_OFF, GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FORCE, GDS_MITIGATION_FULL, GDS_MITIGATION_FULL_LOCKED, GDS_MITIGATION_HYPERVISOR, @@ -662,6 +663,7 @@ static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL static const char * const gds_strings[] = { [GDS_MITIGATION_OFF] = "Vulnerable", [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", [GDS_MITIGATION_FULL] = "Mitigation: Microcode", [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", @@ -687,6 +689,7 @@ void update_gds_msr(void) rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); mcu_ctrl &= ~GDS_MITG_DIS; break; + case GDS_MITIGATION_FORCE: case GDS_MITIGATION_UCODE_NEEDED: case GDS_MITIGATION_HYPERVISOR: return; @@ -721,10 +724,23 @@ static void __init gds_select_mitigation(void) /* No microcode */ if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { - gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + if (gds_mitigation == GDS_MITIGATION_FORCE) { + /* + * This only needs to be done on the boot CPU so do it + * here rather than in update_gds_msr() + */ + setup_clear_cpu_cap(X86_FEATURE_AVX); + pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); + } else { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + } goto out; } + /* Microcode has mitigation, use it */ + if (gds_mitigation == GDS_MITIGATION_FORCE) + gds_mitigation = GDS_MITIGATION_FULL; + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); if (mcu_ctrl & GDS_MITG_LOCKED) { if (gds_mitigation == GDS_MITIGATION_OFF) @@ -755,6 +771,8 @@ static int __init gds_parse_cmdline(char *str) if (!strcmp(str, "off")) gds_mitigation = GDS_MITIGATION_OFF; + else if (!strcmp(str, "force")) + gds_mitigation = GDS_MITIGATION_FORCE; return 0; } From c04579e95492dff342cb4976dd2f5728c0f87eee Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Tue, 1 Aug 2023 16:36:26 +0200 Subject: [PATCH 0020/2093] x86/speculation: Add Kconfig option for GDS commit 53cf5797f114ba2bd86d23a862302119848eff19 upstream Gather Data Sampling (GDS) is mitigated in microcode. However, on systems that haven't received the updated microcode, disabling AVX can act as a mitigation. Add a Kconfig option that uses the microcode mitigation if available and disables AVX otherwise. Setting this option has no effect on systems not affected by GDS. This is the equivalent of setting gather_data_sampling=force. Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/Kconfig | 19 +++++++++++++++++++ arch/x86/kernel/cpu/bugs.c | 4 ++++ 2 files changed, 23 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3867f102cde1..884fd1bd82c9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2522,6 +2522,25 @@ config SLS against straight line speculation. The kernel image might be slightly larger. +config GDS_FORCE_MITIGATION + bool "Force GDS Mitigation" + depends on CPU_SUP_INTEL + default n + help + Gather Data Sampling (GDS) is a hardware vulnerability which allows + unprivileged speculative access to data which was previously stored in + vector registers. + + This option is equivalent to setting gather_data_sampling=force on the + command line. The microcode mitigation is used if present, otherwise + AVX is disabled as a mitigation. On affected systems that are missing + the microcode any userspace code that unconditionally uses AVX will + break with this option set. + + Setting this option on systems not vulnerable to GDS has no effect. + + If in doubt, say N. + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9de9b61cbb71..077480506312 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -658,7 +658,11 @@ enum gds_mitigations { GDS_MITIGATION_HYPERVISOR, }; +#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; +#else static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; +#endif static const char * const gds_strings[] = { [GDS_MITIGATION_OFF] = "Vulnerable", From b6fd07c41b4c64faff368728cef13439ee62860d Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Tue, 1 Aug 2023 16:36:26 +0200 Subject: [PATCH 0021/2093] KVM: Add GDS_NO support to KVM commit 81ac7e5d741742d650b4ed6186c4826c1a0631a7 upstream Gather Data Sampling (GDS) is a transient execution attack using gather instructions from the AVX2 and AVX512 extensions. This attack allows malicious code to infer data that was previously stored in vector registers. Systems that are not vulnerable to GDS will set the GDS_NO bit of the IA32_ARCH_CAPABILITIES MSR. This is useful for VM guests that may think they are on vulnerable systems that are, in fact, not affected. Guests that are running on affected hosts where the mitigation is enabled are protected as if they were running on an unaffected system. On all hosts that are not affected or that are mitigated, set the GDS_NO bit. Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 7 +++++++ arch/x86/kvm/x86.c | 7 ++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 077480506312..cf1e6e842f6f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -673,6 +673,13 @@ static const char * const gds_strings[] = { [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", }; +bool gds_ucode_mitigated(void) +{ + return (gds_mitigation == GDS_MITIGATION_FULL || + gds_mitigation == GDS_MITIGATION_FULL_LOCKED); +} +EXPORT_SYMBOL_GPL(gds_ucode_mitigated); + void update_gds_msr(void) { u64 mcu_ctrl_after; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 32f589b96d99..f4b12c3c30a0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -311,6 +311,8 @@ u64 __read_mostly host_xcr0; static struct kmem_cache *x86_emulator_cache; +extern bool gds_ucode_mitigated(void); + /* * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. @@ -1613,7 +1615,7 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1670,6 +1672,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } From baa7b7501e41344f95da0bd3042dd04110d58edb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 16 Jun 2023 22:15:31 +0200 Subject: [PATCH 0022/2093] x86/mem_encrypt: Unbreak the AMD_MEM_ENCRYPT=n build commit 0a9567ac5e6a40cdd9c8cd15b19a62a15250f450 upstream. Moving mem_encrypt_init() broke the AMD_MEM_ENCRYPT=n because the declaration of that function was under #ifdef CONFIG_AMD_MEM_ENCRYPT and the obvious placement for the inline stub was the #else path. This is a leftover of commit 20f07a044a76 ("x86/sev: Move common memory encryption code to mem_encrypt.c") which made mem_encrypt_init() depend on X86_MEM_ENCRYPT without moving the prototype. That did not fail back then because there was no stub inline as the core init code had a weak function. Move both the declaration and the stub out of the CONFIG_AMD_MEM_ENCRYPT section and guard it with CONFIG_X86_MEM_ENCRYPT. Fixes: 439e17576eb4 ("init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init()") Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Closes: https://lore.kernel.org/oe-kbuild-all/202306170247.eQtCJPE8-lkp@intel.com/ Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mem_encrypt.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index a95914f479b8..8f513372cd8d 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -17,6 +17,12 @@ #include +#ifdef CONFIG_X86_MEM_ENCRYPT +void __init mem_encrypt_init(void); +#else +static inline void mem_encrypt_init(void) { } +#endif + #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; @@ -51,8 +57,6 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); -void __init mem_encrypt_init(void); - #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -84,8 +88,6 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } -static inline void mem_encrypt_init(void) { } - #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ From 7f3982de36c6620c2faae6fd960fa4021d71e16a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 3 Jul 2023 15:00:32 +0200 Subject: [PATCH 0023/2093] x86/xen: Fix secondary processors' FPU initialization commit fe3e0a13e597c1c8617814bf9b42ab732db5c26e upstream. Moving the call of fpu__init_cpu() from cpu_init() to start_secondary() broke Xen PV guests, as those don't call start_secondary() for APs. Call fpu__init_cpu() in Xen's cpu_bringup(), which is the Xen PV replacement of start_secondary(). Fixes: b81fac906a8f ("x86/fpu: Move FPU initialization into arch_cpu_finalize_init()") Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Boris Ostrovsky Acked-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230703130032.22916-1-jgross@suse.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/xen/smp_pv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6175f2c5c822..e97bab7b0010 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -63,6 +63,7 @@ static void cpu_bringup(void) cr4_init(); cpu_init(); + fpu__init_cpu(); touch_softlockup_watchdog(); /* PVH runs in ring 0 and allows us to do native syscalls. Yay! */ From d972c8c08f96518ff02efd87c4fef594a833f6ea Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 9 Jan 2023 16:09:22 +0100 Subject: [PATCH 0024/2093] x86/mm: fix poking_init() for Xen PV guests commit 26ce6ec364f18d2915923bc05784084e54a5c4cc upstream. Commit 3f4c8211d982 ("x86/mm: Use mm_alloc() in poking_init()") broke the kernel for running as Xen PV guest. It seems as if the new address space is never activated before being used, resulting in Xen rejecting to accept the new CR3 value (the PGD isn't pinned). Fix that by adding the now missing call of paravirt_arch_dup_mmap() to poking_init(). That call was previously done by dup_mm()->dup_mmap() and it is a NOP for all cases but for Xen PV, where it is just doing the pinning of the PGD. Fixes: 3f4c8211d982 ("x86/mm: Use mm_alloc() in poking_init()") Signed-off-by: Juergen Gross Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230109150922.10578-1-jgross@suse.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/init.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 0d5ccea2538f..d0563830cffa 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * We need to define the tracepoints somewhere, and tlb.c @@ -829,6 +830,9 @@ void __init poking_init(void) poking_mm = copy_init_mm(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, From 9ae15aaff39c831e2f9d8b029e85a2d70c7c8a68 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Oct 2022 21:38:21 +0200 Subject: [PATCH 0025/2093] x86/mm: Use mm_alloc() in poking_init() commit 3f4c8211d982099be693be9aa7d6fc4607dff290 upstream. Instead of duplicating init_mm, allocate a fresh mm. The advantage is that mm_alloc() has much simpler dependencies. Additionally it makes more conceptual sense, init_mm has no (and must not have) user state to duplicate. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221025201057.816175235@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/init.c | 2 +- include/linux/sched/task.h | 1 - kernel/fork.c | 5 ----- 3 files changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d0563830cffa..913287b9340c 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -827,7 +827,7 @@ void __init poking_init(void) spinlock_t *ptl; pte_t *ptep; - poking_mm = copy_init_mm(); + poking_mm = mm_alloc(); BUG_ON(!poking_mm); /* Xen PV guests need the PGD to be pinned. */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index d6c48163c6de..f0441efd1586 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -90,7 +90,6 @@ extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); -struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); diff --git a/kernel/fork.c b/kernel/fork.c index 6bb91fbbf73c..ab4def837607 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2600,11 +2600,6 @@ struct task_struct * __init fork_idle(int cpu) return task; } -struct mm_struct *copy_init_mm(void) -{ - return dup_mm(NULL, &init_mm); -} - /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. From e0fd83a193c530fdeced8b2e2ec83039ffdb884b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Oct 2022 21:38:18 +0200 Subject: [PATCH 0026/2093] mm: Move mm_cachep initialization to mm_init() commit af80602799681c78f14fbe20b6185a56020dedee upstream. In order to allow using mm_alloc() much earlier, move initializing mm_cachep into mm_init(). Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221025201057.751153381@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/task.h | 1 + init/main.c | 1 + kernel/fork.c | 32 ++++++++++++++++++-------------- 3 files changed, 20 insertions(+), 14 deletions(-) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index f0441efd1586..357e0068497c 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -65,6 +65,7 @@ extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); +extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); diff --git a/init/main.c b/init/main.c index 5b53f04571bb..20e2d1d05973 100644 --- a/init/main.c +++ b/init/main.c @@ -856,6 +856,7 @@ static void __init mm_init(void) /* Should be run after espfix64 is set up. */ pti_init(); kmsan_init_runtime(); + mm_cache_init(); } #ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET diff --git a/kernel/fork.c b/kernel/fork.c index ab4def837607..41950ff90aa3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -3018,10 +3018,27 @@ static void sighand_ctor(void *data) init_waitqueue_head(&sighand->signalfd_wqh); } -void __init proc_caches_init(void) +void __init mm_cache_init(void) { unsigned int mm_size; + /* + * The mm_cpumask is located at the end of mm_struct, and is + * dynamically sized based on the maximum CPU number this system + * can have, taking hotplug into account (nr_cpu_ids). + */ + mm_size = sizeof(struct mm_struct) + cpumask_size(); + + mm_cachep = kmem_cache_create_usercopy("mm_struct", + mm_size, ARCH_MIN_MMSTRUCT_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, + offsetof(struct mm_struct, saved_auxv), + sizeof_field(struct mm_struct, saved_auxv), + NULL); +} + +void __init proc_caches_init(void) +{ sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -3039,19 +3056,6 @@ void __init proc_caches_init(void) SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); - /* - * The mm_cpumask is located at the end of mm_struct, and is - * dynamically sized based on the maximum CPU number this system - * can have, taking hotplug into account (nr_cpu_ids). - */ - mm_size = sizeof(struct mm_struct) + cpumask_size(); - - mm_cachep = kmem_cache_create_usercopy("mm_struct", - mm_size, ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, - offsetof(struct mm_struct, saved_auxv), - sizeof_field(struct mm_struct, saved_auxv), - NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); From 051f5dcf144aa7659c4f4be04c66c3eda9b1bad3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Oct 2022 21:38:25 +0200 Subject: [PATCH 0027/2093] x86/mm: Initialize text poking earlier commit 5b93a83649c7cba3a15eb7e8959b250841acb1b1 upstream. Move poking_init() up a bunch; specifically move it right after mm_init() which is right before ftrace_init(). This will allow simplifying ftrace text poking which currently has a bunch of exceptions for early boot. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221025201057.881703081@infradead.org Signed-off-by: Greg Kroah-Hartman --- init/main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/init/main.c b/init/main.c index 20e2d1d05973..fe378351e8a9 100644 --- a/init/main.c +++ b/init/main.c @@ -992,7 +992,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) sort_main_extable(); trap_init(); mm_init(); - + poking_init(); ftrace_init(); /* trace_printk can be enabled here */ @@ -1126,8 +1126,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) taskstats_init_early(); delayacct_init(); - poking_init(); - acpi_subsystem_init(); arch_post_acpi_subsys_init(); kcsan_init(); From dacb0bac2edb649ce01c25da9f8898769516d716 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 1 Aug 2023 07:31:07 -0700 Subject: [PATCH 0028/2093] Documentation/x86: Fix backwards on/off logic about YMM support commit 1b0fc0345f2852ffe54fb9ae0e12e2ee69ad6a20 upstream These options clearly turn *off* XSAVE YMM support. Correct the typo. Reported-by: Ben Hutchings Fixes: 553a5c03e90a ("x86/speculation: Add force option to GDS mitigation") Signed-off-by: Dave Hansen Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/gather_data_sampling.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst index 40b7a6260010..264bfa937f7d 100644 --- a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -63,7 +63,7 @@ GDS can also be mitigated on systems that don't have updated microcode by disabling AVX. This can be done by setting gather_data_sampling="force" or "clearcpuid=avx" on the kernel command-line. -If used, these options will disable AVX use by turning on XSAVE YMM support. +If used, these options will disable AVX use by turning off XSAVE YMM support. However, the processor will still enumerate AVX support. Userspace that does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM support will break. From dfede4cb8ef732039b7a479d260bd89d3b474f14 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sat, 8 Jul 2023 10:21:35 +0200 Subject: [PATCH 0029/2093] x86/bugs: Increase the x86 bugs vector size to two u32s Upstream commit: 0e52740ffd10c6c316837c6c128f460f1aaba1ea There was never a doubt in my mind that they would not fit into a single u32 eventually. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 2 +- tools/arch/x86/include/asm/cpufeatures.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 9a3d6bdf3b9f..fbb5451af302 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 20 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b71f4f2ecdd5..9ecc62861194 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 20 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used From dec3b91f2c4b2c9b24d933e2c3f17493e30149ac Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Tue, 10 Jan 2023 16:46:37 -0600 Subject: [PATCH 0030/2093] x86/cpu, kvm: Add support for CPUID_80000021_EAX commit 8415a74852d7c24795007ee9862d25feb519007c upstream. Add support for CPUID leaf 80000021, EAX. The majority of the features will be used in the kernel and thus a separate leaf is appropriate. Include KVM's reverse_cpuid entry because features are used by VM guests, too. [ bp: Massage commit message. ] Signed-off-by: Kim Phillips Signed-off-by: Borislav Petkov (AMD) Acked-by: Sean Christopherson Link: https://lore.kernel.org/r/20230124163319.2277355-2-kim.phillips@amd.com [bwh: Backported to 6.1: adjust context] Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeature.h | 7 +++++-- arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/disabled-features.h | 3 ++- arch/x86/include/asm/required-features.h | 3 ++- arch/x86/kernel/cpu/common.c | 3 +++ arch/x86/kvm/reverse_cpuid.h | 1 + 6 files changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1a85e1fb0922..ce0c8f7d3218 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -32,6 +32,7 @@ enum cpuid_leafs CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, + CPUID_8000_0021_EAX, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -94,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -118,8 +120,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index fbb5451af302..4e363f24b3c8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 20 /* N 32-bit words worth of info */ +#define NCAPINTS 21 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 33d2cd04d254..000037078db4 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -111,6 +111,7 @@ #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define DISABLED_MASK20 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index aff774775c67..7ba1726b71c7 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -98,6 +98,7 @@ #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define REQUIRED_MASK20 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 98ae37cdba47..082e3da3de0d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1076,6 +1076,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000001f) c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + if (c->extended_cpuid_level >= 0x80000021) + c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021); + init_scattered_cpuid_features(c); init_speculation_control(c); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index a19d473d0184..7eeade35a425 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -48,6 +48,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, + [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; /* From ac41e90d8daa8815d8bee774a1975435fbfe1ae7 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Wed, 28 Jun 2023 11:02:39 +0200 Subject: [PATCH 0031/2093] x86/srso: Add a Speculative RAS Overflow mitigation Upstream commit: fb3bd914b3ec28f5fb697ac55c4846ac2d542855 Add a mitigation for the speculative return address stack overflow vulnerability found on AMD processors. The mitigation works by ensuring all RET instructions speculate to a controlled location, similar to how speculation is controlled in the retpoline sequence. To accomplish this, the __x86_return_thunk forces the CPU to mispredict every function return using a 'safe return' sequence. To ensure the safety of this mitigation, the kernel must ensure that the safe return sequence is itself free from attacker interference. In Zen3 and Zen4, this is accomplished by creating a BTB alias between the untraining function srso_untrain_ret_alias() and the safe return function srso_safe_ret_alias() which results in evicting a potentially poisoned BTB entry and using that safe one for all function returns. In older Zen1 and Zen2, this is accomplished using a reinterpretation technique similar to Retbleed one: srso_untrain_ret() and srso_safe_ret(). Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/index.rst | 1 + Documentation/admin-guide/hw-vuln/srso.rst | 133 ++++++++++++++++++ .../admin-guide/kernel-parameters.txt | 11 ++ arch/x86/Kconfig | 7 + arch/x86/include/asm/cpufeatures.h | 5 + arch/x86/include/asm/nospec-branch.h | 9 +- arch/x86/include/asm/processor.h | 2 + arch/x86/kernel/alternative.c | 4 +- arch/x86/kernel/cpu/amd.c | 14 ++ arch/x86/kernel/cpu/bugs.c | 106 ++++++++++++++ arch/x86/kernel/cpu/common.c | 8 +- arch/x86/kernel/vmlinux.lds.S | 32 ++++- arch/x86/lib/retpoline.S | 82 ++++++++++- drivers/base/cpu.c | 8 ++ include/linux/cpu.h | 2 + tools/objtool/arch/x86/decode.c | 5 +- 16 files changed, 420 insertions(+), 9 deletions(-) create mode 100644 Documentation/admin-guide/hw-vuln/srso.rst diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 436fac0bd9c3..6828102baaa7 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -20,3 +20,4 @@ are configurable at compile, boot or run time. processor_mmio_stale_data.rst cross-thread-rsb.rst gather_data_sampling.rst + srso diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst new file mode 100644 index 000000000000..2f923c805802 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -0,0 +1,133 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Speculative Return Stack Overflow (SRSO) +======================================== + +This is a mitigation for the speculative return stack overflow (SRSO) +vulnerability found on AMD processors. The mechanism is by now the well +known scenario of poisoning CPU functional units - the Branch Target +Buffer (BTB) and Return Address Predictor (RAP) in this case - and then +tricking the elevated privilege domain (the kernel) into leaking +sensitive data. + +AMD CPUs predict RET instructions using a Return Address Predictor (aka +Return Address Stack/Return Stack Buffer). In some cases, a non-architectural +CALL instruction (i.e., an instruction predicted to be a CALL but is +not actually a CALL) can create an entry in the RAP which may be used +to predict the target of a subsequent RET instruction. + +The specific circumstances that lead to this varies by microarchitecture +but the concern is that an attacker can mis-train the CPU BTB to predict +non-architectural CALL instructions in kernel space and use this to +control the speculative target of a subsequent kernel RET, potentially +leading to information disclosure via a speculative side-channel. + +The issue is tracked under CVE-2023-20569. + +Affected processors +------------------- + +AMD Zen, generations 1-4. That is, all families 0x17 and 0x19. Older +processors have not been investigated. + +System information and options +------------------------------ + +First of all, it is required that the latest microcode be loaded for +mitigations to be effective. + +The sysfs file showing SRSO mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/spec_rstack_overflow + +The possible values in this file are: + + - 'Not affected' The processor is not vulnerable + + - 'Vulnerable: no microcode' The processor is vulnerable, no + microcode extending IBPB functionality + to address the vulnerability has been + applied. + + - 'Mitigation: microcode' Extended IBPB functionality microcode + patch has been applied. It does not + address User->Kernel and Guest->Host + transitions protection but it does + address User->User and VM->VM attack + vectors. + + (spec_rstack_overflow=microcode) + + - 'Mitigation: safe RET' Software-only mitigation. It complements + the extended IBPB microcode patch + functionality by addressing User->Kernel + and Guest->Host transitions protection. + + Selected by default or by + spec_rstack_overflow=safe-ret + + - 'Mitigation: IBPB' Similar protection as "safe RET" above + but employs an IBPB barrier on privilege + domain crossings (User->Kernel, + Guest->Host). + + (spec_rstack_overflow=ibpb) + + - 'Mitigation: IBPB on VMEXIT' Mitigation addressing the cloud provider + scenario - the Guest->Host transitions + only. + + (spec_rstack_overflow=ibpb-vmexit) + +In order to exploit vulnerability, an attacker needs to: + + - gain local access on the machine + + - break kASLR + + - find gadgets in the running kernel in order to use them in the exploit + + - potentially create and pin an additional workload on the sibling + thread, depending on the microarchitecture (not necessary on fam 0x19) + + - run the exploit + +Considering the performance implications of each mitigation type, the +default one is 'Mitigation: safe RET' which should take care of most +attack vectors, including the local User->Kernel one. + +As always, the user is advised to keep her/his system up-to-date by +applying software updates regularly. + +The default setting will be reevaluated when needed and especially when +new attack vectors appear. + +As one can surmise, 'Mitigation: safe RET' does come at the cost of some +performance depending on the workload. If one trusts her/his userspace +and does not want to suffer the performance impact, one can always +disable the mitigation with spec_rstack_overflow=off. + +Similarly, 'Mitigation: IBPB' is another full mitigation type employing +an indrect branch prediction barrier after having applied the required +microcode patch for one's system. This mitigation comes also at +a performance cost. + +Mitigation: safe RET +-------------------- + +The mitigation works by ensuring all RET instructions speculate to +a controlled location, similar to how speculation is controlled in the +retpoline sequence. To accomplish this, the __x86_return_thunk forces +the CPU to mispredict every function return using a 'safe return' +sequence. + +To ensure the safety of this mitigation, the kernel must ensure that the +safe return sequence is itself free from attacker interference. In Zen3 +and Zen4, this is accomplished by creating a BTB alias between the +untraining function srso_untrain_ret_alias() and the safe return +function srso_safe_ret_alias() which results in evicting a potentially +poisoned BTB entry and using that safe one for all function returns. + +In older Zen1 and Zen2, this is accomplished using a reinterpretation +technique similar to Retbleed one: srso_untrain_ret() and +srso_safe_ret(). diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 7f89a185665f..286be425f3bf 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5785,6 +5785,17 @@ Not specifying this option is equivalent to spectre_v2_user=auto. + spec_rstack_overflow= + [X86] Control RAS overflow mitigation on AMD Zen CPUs + + off - Disable mitigation + microcode - Enable microcode mitigation only + safe-ret - Enable sw-only safe RET mitigation (default) + ibpb - Enable mitigation by issuing IBPB on + kernel entry + ibpb-vmexit - Issue IBPB only on VMEXIT + (cloud-specific mitigation) + spec_store_bypass_disable= [HW] Control Speculative Store Bypass (SSB) Disable mitigation (Speculative Store Bypass vulnerability) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 884fd1bd82c9..4c9bfc4be58d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2512,6 +2512,13 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. +config CPU_SRSO + bool "Mitigate speculative RAS overflow on AMD" + depends on CPU_SUP_AMD && X86_64 && RETHUNK + default y + help + Enable the SRSO mitigation needed on AMD Zen1-4 machines. + config SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4e363f24b3c8..b37563e53df8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -308,6 +308,9 @@ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -466,4 +469,6 @@ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +/* BUG word 2 */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index dfdb103ae4f6..690b9f983e41 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -112,7 +112,7 @@ * eventually turn into it's own annotation. */ .macro ANNOTATE_UNRET_END -#ifdef CONFIG_DEBUG_ENTRY +#if (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -191,6 +191,11 @@ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif + +#ifdef CONFIG_CPU_SRSO + ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ + "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS +#endif .endm #else /* __ASSEMBLY__ */ @@ -206,6 +211,8 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); +extern void srso_untrain_ret(void); +extern void srso_untrain_ret_alias(void); extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d8277eec1bcd..c13e4ff8ec70 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -800,9 +800,11 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); +extern bool cpu_has_ibpb_brtype_microcode(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } +static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } #endif #define for_each_possible_hypervisor_cpuid_base(function) \ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index d1d92897ed6b..f8a6062f6ae3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -538,7 +538,9 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_feature_enabled(X86_FEATURE_RETHUNK) || + cpu_feature_enabled(X86_FEATURE_SRSO) || + cpu_feature_enabled(X86_FEATURE_SRSO_ALIAS)) return -1; bytes[i++] = RET_INSN_OPCODE; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7f4eb8b027cc..04249047df86 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1245,6 +1245,20 @@ u32 amd_get_highest_perf(void) } EXPORT_SYMBOL_GPL(amd_get_highest_perf); +bool cpu_has_ibpb_brtype_microcode(void) +{ + u8 fam = boot_cpu_data.x86; + + if (fam == 0x17) { + /* Zen1/2 IBPB flushes branch type predictions too. */ + return boot_cpu_has(X86_FEATURE_AMD_IBPB); + } else if (fam == 0x19) { + return false; + } + + return false; +} + static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cf1e6e842f6f..d691abd65ed7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -47,6 +47,7 @@ static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init srso_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -161,6 +162,7 @@ void __init cpu_select_mitigations(void) srbds_select_mitigation(); l1d_flush_select_mitigation(); gds_select_mitigation(); + srso_select_mitigation(); } /* @@ -2303,6 +2305,95 @@ static int __init l1tf_cmdline(char *str) } early_param("l1tf", l1tf_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt + +enum srso_mitigation { + SRSO_MITIGATION_NONE, + SRSO_MITIGATION_MICROCODE, + SRSO_MITIGATION_SAFE_RET, +}; + +enum srso_mitigation_cmd { + SRSO_CMD_OFF, + SRSO_CMD_MICROCODE, + SRSO_CMD_SAFE_RET, +}; + +static const char * const srso_strings[] = { + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", +}; + +static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; +static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; + +static int __init srso_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + srso_cmd = SRSO_CMD_OFF; + else if (!strcmp(str, "microcode")) + srso_cmd = SRSO_CMD_MICROCODE; + else if (!strcmp(str, "safe-ret")) + srso_cmd = SRSO_CMD_SAFE_RET; + else + pr_err("Ignoring unknown SRSO option (%s).", str); + + return 0; +} +early_param("spec_rstack_overflow", srso_parse_cmdline); + +#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." + +static void __init srso_select_mitigation(void) +{ + bool has_microcode; + + if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) + return; + + has_microcode = cpu_has_ibpb_brtype_microcode(); + if (!has_microcode) { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + } + + switch (srso_cmd) { + case SRSO_CMD_OFF: + return; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; + pr_warn(SRSO_NOTICE); + } + break; + + case SRSO_CMD_SAFE_RET: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (boot_cpu_data.x86 == 0x19) + setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); + else + setup_force_cpu_cap(X86_FEATURE_SRSO); + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + return; + } + break; + + default: + break; + + } + + pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); +} + #undef pr_fmt #define pr_fmt(fmt) fmt @@ -2506,6 +2597,13 @@ static ssize_t gds_show_state(char *buf) return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } +static ssize_t srso_show_state(char *buf) +{ + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], + (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2558,6 +2656,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_GDS: return gds_show_state(buf); + case X86_BUG_SRSO: + return srso_show_state(buf); + default: break; } @@ -2627,4 +2728,9 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } + +ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 082e3da3de0d..44dcb2c83ba4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1246,6 +1246,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SMT_RSB BIT(4) /* CPU is affected by GDS */ #define GDS BIT(5) +/* CPU is affected by SRSO */ +#define SRSO BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1279,8 +1281,9 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_AMD(0x19, SRSO), {} }; @@ -1411,6 +1414,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 15f29053cec4..fd03f5a1f0ef 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -133,7 +133,20 @@ SECTIONS LOCK_TEXT KPROBES_TEXT ALIGN_ENTRY_TEXT_BEGIN +#ifdef CONFIG_CPU_SRSO + *(.text.__x86.rethunk_untrain) +#endif + ENTRY_TEXT + +#ifdef CONFIG_CPU_SRSO + /* + * See the comment above srso_untrain_ret_alias()'s + * definition. + */ + . = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + *(.text.__x86.rethunk_safe) +#endif ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT STATIC_CALL_TEXT @@ -141,13 +154,15 @@ SECTIONS #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.*) + *(.text.__x86.indirect_thunk) + *(.text.__x86.return_thunk) __indirect_thunk_end = .; #endif } :text =0xcccc /* End of text section, which should occupy whole number of pages */ _etext = .; + . = ALIGN(PAGE_SIZE); X86_ALIGN_RODATA_BEGIN @@ -492,6 +507,21 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif + #ifdef CONFIG_RETHUNK +. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned"); +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); +#endif + +#ifdef CONFIG_CPU_SRSO +/* + * GNU ld cannot do XOR so do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: + */ +. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) - + (srso_untrain_ret_alias & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), + "SRSO function pair won't alias"); +#endif + #endif /* CONFIG_X86_64 */ #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 841955dc2573..764c7ed079f2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,6 +9,7 @@ #include #include #include +#include .section .text.__x86.indirect_thunk @@ -74,6 +75,45 @@ SYM_CODE_END(__x86_indirect_thunk_array) */ #ifdef CONFIG_RETHUNK +/* + * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at + * special addresses: + * + * - srso_untrain_ret_alias() is 2M aligned + * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14 + * and 20 in its virtual address are set (while those bits in the + * srso_untrain_ret_alias() function are cleared). + * + * This guarantees that those two addresses will alias in the branch + * target buffer of Zen3/4 generations, leading to any potential + * poisoned entries at that BTB slot to get evicted. + * + * As a result, srso_safe_ret_alias() becomes a safe return. + */ +#ifdef CONFIG_CPU_SRSO + .section .text.__x86.rethunk_untrain + +SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + ASM_NOP2 + lfence + jmp __x86_return_thunk +SYM_FUNC_END(srso_untrain_ret_alias) +__EXPORT_THUNK(srso_untrain_ret_alias) + + .section .text.__x86.rethunk_safe +#endif + +/* Needs a definition for the __x86_return_thunk alternative below. */ +SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +#ifdef CONFIG_CPU_SRSO + add $8, %_ASM_SP + UNWIND_HINT_FUNC +#endif + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_safe_ret_alias) + .section .text.__x86.return_thunk /* @@ -86,7 +126,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) * from re-poisioning the BTB prediction. */ .align 64 - .skip 63, 0xcc + .skip 64 - (__ret - zen_untrain_ret), 0xcc SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR /* @@ -118,10 +158,10 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * evicted, __x86_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) +SYM_INNER_LABEL(__ret, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(__x86_return_thunk) +SYM_CODE_END(__ret) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -132,11 +172,45 @@ SYM_CODE_END(__x86_return_thunk) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp __x86_return_thunk + jmp __ret int3 SYM_FUNC_END(zen_untrain_ret) __EXPORT_THUNK(zen_untrain_ret) +/* + * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccccc308c48348,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + add $8, %_ASM_SP + ret + int3 + int3 + int3 + lfence + call srso_safe_ret + int3 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) +__EXPORT_THUNK(srso_untrain_ret) + +SYM_FUNC_START(__x86_return_thunk) + ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ + "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS + int3 +SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) #endif /* CONFIG_RETHUNK */ diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index cc6cf06ce88e..dab70a65377c 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -583,6 +583,12 @@ ssize_t __weak cpu_show_gds(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -595,6 +601,7 @@ static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); +static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -609,6 +616,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_mmio_stale_data.attr, &dev_attr_retbleed.attr, &dev_attr_gather_data_sampling.attr, + &dev_attr_spec_rstack_overflow.attr, NULL }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 43b0b7950e33..f98cfe9f188f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,8 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev, char *buf); extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 1c253b4b7ce0..a60c5efe34b3 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -796,5 +796,8 @@ bool arch_is_retpoline(struct symbol *sym) bool arch_is_rethunk(struct symbol *sym) { - return !strcmp(sym->name, "__x86_return_thunk"); + return !strcmp(sym->name, "__x86_return_thunk") || + !strcmp(sym->name, "srso_untrain_ret") || + !strcmp(sym->name, "srso_safe_ret") || + !strcmp(sym->name, "__ret"); } From 9139f4b6dd4fe1003ba79ab317d1a9f48849b369 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 18 Jul 2023 11:13:40 +0200 Subject: [PATCH 0032/2093] x86/srso: Add IBPB_BRTYPE support Upstream commit: 79113e4060aba744787a81edb9014f2865193854 Add support for the synthetic CPUID flag which "if this bit is 1, it indicates that MSR 49h (PRED_CMD) bit 0 (IBPB) flushes all branch type predictions from the CPU branch predictor." This flag is there so that this capability in guests can be detected easily (otherwise one would have to track microcode revisions which is impossible for guests). It is also needed only for Zen3 and -4. The other two (Zen1 and -2) always flush branch type predictions by default. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 2 ++ arch/x86/kernel/cpu/bugs.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b37563e53df8..1c330be12824 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -426,6 +426,8 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ + /* * BUG word(s) */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d691abd65ed7..137565e7f7de 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2356,10 +2356,20 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) return; - has_microcode = cpu_has_ibpb_brtype_microcode(); + /* + * The first check is for the kernel running as a guest in order + * for guests to verify whether IBPB is a viable mitigation. + */ + has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); if (!has_microcode) { pr_warn("IBPB-extending microcode not applied!\n"); pr_warn(SRSO_NOTICE); + } else { + /* + * Enable the synthetic (even if in a real CPUID leaf) + * flag for guests. + */ + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); } switch (srso_cmd) { From 98f62883e7519011bf63f85381d637f65d7f180e Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 29 Jun 2023 17:43:40 +0200 Subject: [PATCH 0033/2093] x86/srso: Add SRSO_NO support Upstream commit: 1b5277c0ea0b247393a9c426769fde18cff5e2f6 Add support for the CPUID flag which denotes that the CPU is not affected by SRSO. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 2 ++ arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/nospec-branch.h | 6 +++--- arch/x86/kernel/cpu/amd.c | 12 ++++++------ arch/x86/kernel/cpu/bugs.c | 24 ++++++++++++++++++++---- arch/x86/kernel/cpu/common.c | 6 ++++-- arch/x86/kvm/cpuid.c | 3 +++ 7 files changed, 39 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1c330be12824..a8c2733c816c 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -426,7 +426,9 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* * BUG word(s) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a070e55ba441..52d8c67d9308 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -60,6 +60,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 690b9f983e41..573a137f5ac3 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -318,11 +318,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +extern u64 x86_pred_cmd; + static inline void indirect_branch_prediction_barrier(void) { - u64 val = PRED_CMD_IBPB; - - alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); + alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 04249047df86..9842f2402978 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1249,14 +1249,14 @@ bool cpu_has_ibpb_brtype_microcode(void) { u8 fam = boot_cpu_data.x86; - if (fam == 0x17) { - /* Zen1/2 IBPB flushes branch type predictions too. */ + /* Zen1/2 IBPB flushes branch type predictions too. */ + if (fam == 0x17) return boot_cpu_has(X86_FEATURE_AMD_IBPB); - } else if (fam == 0x19) { + /* Poke the MSR bit on Zen3/4 to check its presence. */ + else if (fam == 0x19) + return !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB); + else return false; - } - - return false; } static void zenbleed_check_cpu(void *unused) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 137565e7f7de..1be4f7186ba8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -57,6 +57,9 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; +EXPORT_SYMBOL_GPL(x86_pred_cmd); + static DEFINE_MUTEX(spec_ctrl_mutex); /* Update SPEC_CTRL MSR and its cached copy unconditionally */ @@ -2354,7 +2357,7 @@ static void __init srso_select_mitigation(void) bool has_microcode; if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) - return; + goto pred_cmd; /* * The first check is for the kernel running as a guest in order @@ -2367,9 +2370,18 @@ static void __init srso_select_mitigation(void) } else { /* * Enable the synthetic (even if in a real CPUID leaf) - * flag for guests. + * flags for guests. */ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + setup_force_cpu_cap(X86_FEATURE_SBPB); + + /* + * Zen1/2 with SMT off aren't vulnerable after the right + * IBPB microcode has been applied. + */ + if ((boot_cpu_data.x86 < 0x19) && + (cpu_smt_control == CPU_SMT_DISABLED)) + setup_force_cpu_cap(X86_FEATURE_SRSO_NO); } switch (srso_cmd) { @@ -2392,16 +2404,20 @@ static void __init srso_select_mitigation(void) srso_mitigation = SRSO_MITIGATION_SAFE_RET; } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); - return; + goto pred_cmd; } break; default: break; - } pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); + +pred_cmd: + if (boot_cpu_has(X86_FEATURE_SRSO_NO) || + srso_cmd == SRSO_CMD_OFF) + x86_pred_cmd = PRED_CMD_SBPB; } #undef pr_fmt diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 44dcb2c83ba4..f63c8427cf63 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1414,8 +1414,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); - if (cpu_matches(cpu_vuln_blacklist, SRSO)) - setup_force_cpu_bug(X86_BUG_SRSO); + if (!cpu_has(c, X86_FEATURE_SRSO_NO)) { + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + } if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6047dbe04880..7b4224f5ee2d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -736,6 +736,9 @@ void kvm_set_cpu_caps(void) F(PMM) | F(PMM_EN) ); + if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) + kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + /* * Hide RDTSCP and RDPID if either feature is reported as supported but * probing MSR_TSC_AUX failed. This is purely a sanity check and From 79c8091888ef61aac79ef72122d1e6cd0b620669 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 6 Jul 2023 15:04:35 +0200 Subject: [PATCH 0034/2093] x86/srso: Add IBPB Upstream commit: 233d6f68b98d480a7c42ebe78c38f79d44741ca9 Add the option to mitigate using IBPB on a kernel entry. Pull in the Retbleed alternative so that the IBPB call from there can be used. Also, if Retbleed mitigation is done using IBPB, the same mitigation can and must be used here. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 3 ++- arch/x86/kernel/cpu/bugs.c | 23 +++++++++++++++++++++++ 2 files changed, 25 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 573a137f5ac3..31fa631c8587 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -185,7 +185,8 @@ * where we have a stack but before any RET instruction. */ .macro UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ + defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1be4f7186ba8..82417ce310cc 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2315,18 +2315,21 @@ enum srso_mitigation { SRSO_MITIGATION_NONE, SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, + SRSO_MITIGATION_IBPB, }; enum srso_mitigation_cmd { SRSO_CMD_OFF, SRSO_CMD_MICROCODE, SRSO_CMD_SAFE_RET, + SRSO_CMD_IBPB, }; static const char * const srso_strings[] = { [SRSO_MITIGATION_NONE] = "Vulnerable", [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2343,6 +2346,8 @@ static int __init srso_parse_cmdline(char *str) srso_cmd = SRSO_CMD_MICROCODE; else if (!strcmp(str, "safe-ret")) srso_cmd = SRSO_CMD_SAFE_RET; + else if (!strcmp(str, "ibpb")) + srso_cmd = SRSO_CMD_IBPB; else pr_err("Ignoring unknown SRSO option (%s).", str); @@ -2384,6 +2389,14 @@ static void __init srso_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_SRSO_NO); } + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { + if (has_microcode) { + pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + srso_mitigation = SRSO_MITIGATION_IBPB; + goto pred_cmd; + } + } + switch (srso_cmd) { case SRSO_CMD_OFF: return; @@ -2408,6 +2421,16 @@ static void __init srso_select_mitigation(void) } break; + case SRSO_CMD_IBPB: + if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (has_microcode) { + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + srso_mitigation = SRSO_MITIGATION_IBPB; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto pred_cmd; + } default: break; } From c9ae63d773ca182c4ef63fbdd22cdf090d9c1cd7 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 7 Jul 2023 13:53:41 +0200 Subject: [PATCH 0035/2093] x86/srso: Add IBPB on VMEXIT Upstream commit: d893832d0e1ef41c72cdae444268c1d64a2be8ad Add the option to flush IBPB only on VMEXIT in order to protect from malicious guests but one otherwise trusts the software that runs on the hypervisor. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/bugs.c | 19 +++++++++++++++++++ arch/x86/kvm/svm/svm.c | 4 +++- arch/x86/kvm/svm/vmenter.S | 3 +++ 4 files changed, 26 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index a8c2733c816c..e721b8426c24 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -310,6 +310,7 @@ #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 82417ce310cc..af612778a328 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2316,6 +2316,7 @@ enum srso_mitigation { SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, SRSO_MITIGATION_IBPB, + SRSO_MITIGATION_IBPB_ON_VMEXIT, }; enum srso_mitigation_cmd { @@ -2323,6 +2324,7 @@ enum srso_mitigation_cmd { SRSO_CMD_MICROCODE, SRSO_CMD_SAFE_RET, SRSO_CMD_IBPB, + SRSO_CMD_IBPB_ON_VMEXIT, }; static const char * const srso_strings[] = { @@ -2330,6 +2332,7 @@ static const char * const srso_strings[] = { [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2348,6 +2351,8 @@ static int __init srso_parse_cmdline(char *str) srso_cmd = SRSO_CMD_SAFE_RET; else if (!strcmp(str, "ibpb")) srso_cmd = SRSO_CMD_IBPB; + else if (!strcmp(str, "ibpb-vmexit")) + srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; else pr_err("Ignoring unknown SRSO option (%s).", str); @@ -2431,6 +2436,20 @@ static void __init srso_select_mitigation(void) pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); goto pred_cmd; } + break; + + case SRSO_CMD_IBPB_ON_VMEXIT: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + default: break; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0a212fe2cd39..fdb6007f2eb8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1485,7 +1485,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; - indirect_branch_prediction_barrier(); + + if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT)) + indirect_branch_prediction_barrier(); } if (kvm_vcpu_apicv_active(vcpu)) avic_vcpu_load(vcpu, cpu); diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 34367dc203f2..5be9a63f09ff 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -223,6 +223,9 @@ SYM_FUNC_START(__svm_vcpu_run) */ UNTRAIN_RET + /* SRSO */ + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded From c7f2cd04554259c2474c4f9fa134528bc2826b22 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 28 Jul 2023 17:28:43 -0500 Subject: [PATCH 0036/2093] x86/srso: Fix return thunks in generated code Upstream commit: 238ec850b95a02dcdff3edc86781aa913549282f Set X86_FEATURE_RETHUNK when enabling the SRSO mitigation so that generated code (e.g., ftrace, static call, eBPF) generates "jmp __x86_return_thunk" instead of RET. [ bp: Add a comment. ] Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Josh Poimboeuf Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/alternative.c | 4 +--- arch/x86/kernel/cpu/bugs.c | 6 ++++++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f8a6062f6ae3..d1d92897ed6b 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -538,9 +538,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK) || - cpu_feature_enabled(X86_FEATURE_SRSO) || - cpu_feature_enabled(X86_FEATURE_SRSO_ALIAS)) + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) return -1; bytes[i++] = RET_INSN_OPCODE; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index af612778a328..b4ac1f3d41b3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2415,6 +2415,12 @@ static void __init srso_select_mitigation(void) case SRSO_CMD_SAFE_RET: if (IS_ENABLED(CONFIG_CPU_SRSO)) { + /* + * Enable the return thunk for generated code + * like ftrace, static_call, etc. + */ + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + if (boot_cpu_data.x86 == 0x19) setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); else From 77cf32d0dbfbf575fe66561e069228c532dc1da9 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 28 Jul 2023 23:03:22 +0200 Subject: [PATCH 0037/2093] x86/srso: Add a forgotten NOENDBR annotation Upstream commit: 3bbbe97ad83db8d9df06daf027b0840188de625d Fix: vmlinux.o: warning: objtool: .export_symbol+0x29e40: data relocation to !ENDBR: srso_untrain_ret_alias+0x0 Reported-by: Linus Torvalds Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/retpoline.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 764c7ed079f2..30e76fab678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -94,6 +94,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) .section .text.__x86.rethunk_untrain SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR ASM_NOP2 lfence jmp __x86_return_thunk From 4f25355540ad4d40dd3445f66159a321dad29cc8 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Mon, 7 Aug 2023 10:46:04 +0200 Subject: [PATCH 0038/2093] x86/srso: Tie SBPB bit setting to microcode patch detection commit 5a15d8348881e9371afdf9f5357a135489496955 upstream. The SBPB bit in MSR_IA32_PRED_CMD is supported only after a microcode patch has been applied so set X86_FEATURE_SBPB only then. Otherwise, guests would attempt to set that bit and #GP on the MSR write. While at it, make SMT detection more robust as some guests - depending on how and what CPUID leafs their report - lead to cpu_smt_control getting set to CPU_SMT_NOT_SUPPORTED but SRSO_NO should be set for any guest incarnation where one simply cannot do SMT, for whatever reason. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Reported-by: Konrad Rzeszutek Wilk Reported-by: Salvatore Bonaccorso Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/amd.c | 19 ++++++++++++------- arch/x86/kernel/cpu/bugs.c | 7 +++---- 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9842f2402978..7f0cf4a959c0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1247,16 +1247,21 @@ EXPORT_SYMBOL_GPL(amd_get_highest_perf); bool cpu_has_ibpb_brtype_microcode(void) { - u8 fam = boot_cpu_data.x86; - + switch (boot_cpu_data.x86) { /* Zen1/2 IBPB flushes branch type predictions too. */ - if (fam == 0x17) + case 0x17: return boot_cpu_has(X86_FEATURE_AMD_IBPB); - /* Poke the MSR bit on Zen3/4 to check its presence. */ - else if (fam == 0x19) - return !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB); - else + case 0x19: + /* Poke the MSR bit on Zen3/4 to check its presence. */ + if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_SBPB); + return true; + } else { + return false; + } + default: return false; + } } static void zenbleed_check_cpu(void *unused) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b4ac1f3d41b3..d98f33ea57e4 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2383,14 +2383,13 @@ static void __init srso_select_mitigation(void) * flags for guests. */ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); - setup_force_cpu_cap(X86_FEATURE_SBPB); /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. */ if ((boot_cpu_data.x86 < 0x19) && - (cpu_smt_control == CPU_SMT_DISABLED)) + (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) setup_force_cpu_cap(X86_FEATURE_SRSO_NO); } @@ -2463,8 +2462,8 @@ static void __init srso_select_mitigation(void) pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); pred_cmd: - if (boot_cpu_has(X86_FEATURE_SRSO_NO) || - srso_cmd == SRSO_CMD_OFF) + if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; } From fa5b932b77c815d0e416612859d5899424bb4212 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Thu, 3 Aug 2023 08:41:22 +0200 Subject: [PATCH 0039/2093] xen/netback: Fix buffer overrun triggered by unusual packet commit 534fc31d09b706a16d83533e16b5dc855caf7576 upstream. It is possible that a guest can send a packet that contains a head + 18 slots and yet has a len <= XEN_NETBACK_TX_COPY_LEN. This causes nr_slots to underflow in xenvif_get_requests() which then causes the subsequent loop's termination condition to be wrong, causing a buffer overrun of queue->tx_map_ops. Rework the code to account for the extra frag_overflow slots. This is CVE-2023-34319 / XSA-432. Fixes: ad7f402ae4f4 ("xen/netback: Ensure protocol headers don't fall in the non-linear area") Signed-off-by: Ross Lagerwall Reviewed-by: Paul Durrant Reviewed-by: Wei Liu Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netback/netback.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c35c085dbc87..c3a8d78a41a7 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -396,7 +396,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; struct xen_netif_tx_request *txp = first; - nr_slots = shinfo->nr_frags + 1; + nr_slots = shinfo->nr_frags + frag_overflow + 1; copy_count(skb) = 0; XENVIF_TX_CB(skb)->split_mask = 0; @@ -462,8 +462,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } } - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, gop++) { + for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; + shinfo->nr_frags++, gop++, nr_slots--) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, @@ -476,12 +476,12 @@ static void xenvif_get_requests(struct xenvif_queue *queue, txp++; } - if (frag_overflow) { + if (nr_slots > 0) { shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; shinfo->nr_frags++, txp++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; @@ -492,6 +492,11 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } skb_shinfo(skb)->frag_list = nskb; + } else if (nskb) { + /* A frag_list skb was allocated but it is no longer needed + * because enough slots were converted to copy ops above. + */ + kfree_skb(nskb); } (*copy_ops) = cop - queue->tx_copy_ops; From dd5f2ef16e3c6b83f14b5e620f51f42bc05a5d47 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 8 Aug 2023 19:20:48 +0200 Subject: [PATCH 0040/2093] x86: fix backwards merge of GDS/SRSO bit Stable-tree-only change. Due to the way the GDS and SRSO patches flowed into the stable tree, it was a 50% chance that the merge of the which value GDS and SRSO should be. Of course, I lost that bet, and chose the opposite of what Linus chose in commit 64094e7e3118 ("Merge tag 'gds-for-linus-2023-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") Fix this up by switching the values to match what is now in Linus's tree as that is the correct value to mirror. Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/common.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f63c8427cf63..d38ae25e7c01 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1244,10 +1244,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by SMT (cross-thread) return predictions */ #define SMT_RSB BIT(4) -/* CPU is affected by GDS */ -#define GDS BIT(5) /* CPU is affected by SRSO */ -#define SRSO BIT(6) +#define SRSO BIT(5) +/* CPU is affected by GDS */ +#define GDS BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), From 0a4a7855302d56a1d75cec3aa9a6914a3af9c6af Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 8 Aug 2023 20:03:51 +0200 Subject: [PATCH 0041/2093] Linux 6.1.44 Tested-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 69cdd0d2946c..612f3d83629b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 43 +SUBLEVEL = 44 EXTRAVERSION = NAME = Curry Ramen From c7920f992840779383cbff15a2e860515eec7644 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Aug 2023 08:42:37 -0600 Subject: [PATCH 0042/2093] io_uring: gate iowait schedule on having pending requests Commit 7b72d661f1f2f950ab8c12de7e2bc48bdac8ed69 upstream. A previous commit made all cqring waits marked as iowait, as a way to improve performance for short schedules with pending IO. However, for use cases that have a special reaper thread that does nothing but wait on events on the ring, this causes a cosmetic issue where we know have one core marked as being "busy" with 100% iowait. While this isn't a grave issue, it is confusing to users. Rather than always mark us as being in iowait, gate setting of current->in_iowait to 1 by whether or not the waiting task has pending requests. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/io-uring/CAMEGJJ2RxopfNQ7GNLhr7X9=bHXKo+G5OOe0LUq=+UgLXsv1Xg@mail.gmail.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=217699 Link: https://bugzilla.kernel.org/show_bug.cgi?id=217700 Reported-by: Oleksandr Natalenko Reported-by: Phil Elwell Tested-by: Andres Freund Fixes: 8a796565cec3 ("io_uring: Use io_schedule* in cqring wait") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f091153bc854..ed8e9deae284 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2349,12 +2349,21 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) return 0; } +static bool current_pending_io(void) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx) + return false; + return percpu_counter_read_positive(&tctx->inflight); +} + /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, ktime_t *timeout) { - int token, ret; + int io_wait, ret; unsigned long check_cq; /* make sure we run task_work before checking for signals */ @@ -2372,15 +2381,17 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, } /* - * Use io_schedule_prepare/finish, so cpufreq can take into account - * that the task is waiting for IO - turns out to be important for low - * QD IO. + * Mark us as being in io_wait if we have pending requests, so cpufreq + * can take into account that the task is waiting for IO - turns out + * to be important for low QD IO. */ - token = io_schedule_prepare(); + io_wait = current->in_iowait; + if (current_pending_io()) + current->in_iowait = 1; ret = 1; if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) ret = -ETIME; - io_schedule_finish(token); + current->in_iowait = io_wait; return ret; } From 15c22cd1de50f9489f9f1fd9cd5ec6eaccedc918 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Nov 2022 22:40:17 +0100 Subject: [PATCH 0043/2093] perf: Fix function pointer case commit 1af6239d1d3e61d33fd2f0ba53d3d1a67cc50574 upstream. With the advent of CFI it is no longer acceptible to cast function pointers. The robot complains thusly: kernel-events-core.c:warning:cast-from-int-(-)(struct-perf_cpu_pmu_context-)-to-remote_function_f-(aka-int-(-)(void-)-)-converts-to-incompatible-function-type Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Cixi Geng Signed-off-by: Greg Kroah-Hartman --- kernel/events/core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 934332b3eb54..db1065daabb6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1133,6 +1133,11 @@ static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) return 0; } +static int perf_mux_hrtimer_restart_ipi(void *arg) +{ + return perf_mux_hrtimer_restart(arg); +} + void perf_pmu_disable(struct pmu *pmu) { int *count = this_cpu_ptr(pmu->pmu_disable_count); @@ -11155,8 +11160,7 @@ perf_event_mux_interval_ms_store(struct device *dev, cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); - cpu_function_call(cpu, - (remote_function_f)perf_mux_hrtimer_restart, cpuctx); + cpu_function_call(cpu, perf_mux_hrtimer_restart_ipi, cpuctx); } cpus_read_unlock(); mutex_unlock(&mux_interval_mutex); From 93f5b881125e6514c9bcd225fd86703da533136b Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 13 Apr 2023 22:15:31 +0300 Subject: [PATCH 0044/2093] net/mlx5: Free irqs only on shutdown callback commit 9c2d08010963a61a171e8cb2852d3ce015b60cb4 upstream. Whenever a shutdown is invoked, free irqs only and keep mlx5_irq synthetic wrapper intact in order to avoid use-after-free on system shutdown. for example: ================================================================== BUG: KASAN: use-after-free in _find_first_bit+0x66/0x80 Read of size 8 at addr ffff88823fc0d318 by task kworker/u192:0/13608 CPU: 25 PID: 13608 Comm: kworker/u192:0 Tainted: G B W O 6.1.21-cloudflare-kasan-2023.3.21 #1 Hardware name: GIGABYTE R162-R2-GEN0/MZ12-HD2-CD, BIOS R14 05/03/2021 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core] Call Trace: dump_stack_lvl+0x34/0x48 print_report+0x170/0x473 ? _find_first_bit+0x66/0x80 kasan_report+0xad/0x130 ? _find_first_bit+0x66/0x80 _find_first_bit+0x66/0x80 mlx5e_open_channels+0x3c5/0x3a10 [mlx5_core] ? console_unlock+0x2fa/0x430 ? _raw_spin_lock_irqsave+0x8d/0xf0 ? _raw_spin_unlock_irqrestore+0x42/0x80 ? preempt_count_add+0x7d/0x150 ? __wake_up_klogd.part.0+0x7d/0xc0 ? vprintk_emit+0xfe/0x2c0 ? mlx5e_trigger_napi_sched+0x40/0x40 [mlx5_core] ? dev_attr_show.cold+0x35/0x35 ? devlink_health_do_dump.part.0+0x174/0x340 ? devlink_health_report+0x504/0x810 ? mlx5e_reporter_tx_timeout+0x29d/0x3a0 [mlx5_core] ? mlx5e_tx_timeout_work+0x17c/0x230 [mlx5_core] ? process_one_work+0x680/0x1050 mlx5e_safe_switch_params+0x156/0x220 [mlx5_core] ? mlx5e_switch_priv_channels+0x310/0x310 [mlx5_core] ? mlx5_eq_poll_irq_disabled+0xb6/0x100 [mlx5_core] mlx5e_tx_reporter_timeout_recover+0x123/0x240 [mlx5_core] ? __mutex_unlock_slowpath.constprop.0+0x2b0/0x2b0 devlink_health_reporter_recover+0xa6/0x1f0 devlink_health_report+0x2f7/0x810 ? vsnprintf+0x854/0x15e0 mlx5e_reporter_tx_timeout+0x29d/0x3a0 [mlx5_core] ? mlx5e_reporter_tx_err_cqe+0x1a0/0x1a0 [mlx5_core] ? mlx5e_tx_reporter_timeout_dump+0x50/0x50 [mlx5_core] ? mlx5e_tx_reporter_dump_sq+0x260/0x260 [mlx5_core] ? newidle_balance+0x9b7/0xe30 ? psi_group_change+0x6a7/0xb80 ? mutex_lock+0x96/0xf0 ? __mutex_lock_slowpath+0x10/0x10 mlx5e_tx_timeout_work+0x17c/0x230 [mlx5_core] process_one_work+0x680/0x1050 worker_thread+0x5a0/0xeb0 ? process_one_work+0x1050/0x1050 kthread+0x2a2/0x340 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 Freed by task 1: kasan_save_stack+0x23/0x50 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x40 ____kasan_slab_free+0x169/0x1d0 slab_free_freelist_hook+0xd2/0x190 __kmem_cache_free+0x1a1/0x2f0 irq_pool_free+0x138/0x200 [mlx5_core] mlx5_irq_table_destroy+0xf6/0x170 [mlx5_core] mlx5_core_eq_free_irqs+0x74/0xf0 [mlx5_core] shutdown+0x194/0x1aa [mlx5_core] pci_device_shutdown+0x75/0x120 device_shutdown+0x35c/0x620 kernel_restart+0x60/0xa0 __do_sys_reboot+0x1cb/0x2c0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x4b/0xb5 The buggy address belongs to the object at ffff88823fc0d300 which belongs to the cache kmalloc-192 of size 192 The buggy address is located 24 bytes inside of 192-byte region [ffff88823fc0d300, ffff88823fc0d3c0) The buggy address belongs to the physical page: page:0000000010139587 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x23fc0c head:0000000010139587 order:1 compound_mapcount:0 compound_pincount:0 flags: 0x2ffff800010200(slab|head|node=0|zone=2|lastcpupid=0x1ffff) raw: 002ffff800010200 0000000000000000 dead000000000122 ffff88810004ca00 raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88823fc0d200: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88823fc0d280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc >ffff88823fc0d300: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88823fc0d380: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff88823fc0d400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== general protection fault, probably for non-canonical address 0xdffffc005c40d7ac: 0000 [#1] PREEMPT SMP KASAN NOPTI KASAN: probably user-memory-access in range [0x00000002e206bd60-0x00000002e206bd67] CPU: 25 PID: 13608 Comm: kworker/u192:0 Tainted: G B W O 6.1.21-cloudflare-kasan-2023.3.21 #1 Hardware name: GIGABYTE R162-R2-GEN0/MZ12-HD2-CD, BIOS R14 05/03/2021 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core] RIP: 0010:__alloc_pages+0x141/0x5c0 Call Trace: ? sysvec_apic_timer_interrupt+0xa0/0xc0 ? asm_sysvec_apic_timer_interrupt+0x16/0x20 ? __alloc_pages_slowpath.constprop.0+0x1ec0/0x1ec0 ? _raw_spin_unlock_irqrestore+0x3d/0x80 __kmalloc_large_node+0x80/0x120 ? kvmalloc_node+0x4e/0x170 __kmalloc_node+0xd4/0x150 kvmalloc_node+0x4e/0x170 mlx5e_open_channels+0x631/0x3a10 [mlx5_core] ? console_unlock+0x2fa/0x430 ? _raw_spin_lock_irqsave+0x8d/0xf0 ? _raw_spin_unlock_irqrestore+0x42/0x80 ? preempt_count_add+0x7d/0x150 ? __wake_up_klogd.part.0+0x7d/0xc0 ? vprintk_emit+0xfe/0x2c0 ? mlx5e_trigger_napi_sched+0x40/0x40 [mlx5_core] ? dev_attr_show.cold+0x35/0x35 ? devlink_health_do_dump.part.0+0x174/0x340 ? devlink_health_report+0x504/0x810 ? mlx5e_reporter_tx_timeout+0x29d/0x3a0 [mlx5_core] ? mlx5e_tx_timeout_work+0x17c/0x230 [mlx5_core] ? process_one_work+0x680/0x1050 mlx5e_safe_switch_params+0x156/0x220 [mlx5_core] ? mlx5e_switch_priv_channels+0x310/0x310 [mlx5_core] ? mlx5_eq_poll_irq_disabled+0xb6/0x100 [mlx5_core] mlx5e_tx_reporter_timeout_recover+0x123/0x240 [mlx5_core] ? __mutex_unlock_slowpath.constprop.0+0x2b0/0x2b0 devlink_health_reporter_recover+0xa6/0x1f0 devlink_health_report+0x2f7/0x810 ? vsnprintf+0x854/0x15e0 mlx5e_reporter_tx_timeout+0x29d/0x3a0 [mlx5_core] ? mlx5e_reporter_tx_err_cqe+0x1a0/0x1a0 [mlx5_core] ? mlx5e_tx_reporter_timeout_dump+0x50/0x50 [mlx5_core] ? mlx5e_tx_reporter_dump_sq+0x260/0x260 [mlx5_core] ? newidle_balance+0x9b7/0xe30 ? psi_group_change+0x6a7/0xb80 ? mutex_lock+0x96/0xf0 ? __mutex_lock_slowpath+0x10/0x10 mlx5e_tx_timeout_work+0x17c/0x230 [mlx5_core] process_one_work+0x680/0x1050 worker_thread+0x5a0/0xeb0 ? process_one_work+0x1050/0x1050 kthread+0x2a2/0x340 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 ---[ end trace 0000000000000000 ]--- RIP: 0010:__alloc_pages+0x141/0x5c0 Code: e0 39 a3 96 89 e9 b8 22 01 32 01 83 e1 0f 48 89 fa 01 c9 48 c1 ea 03 d3 f8 83 e0 03 89 44 24 6c 48 b8 00 00 00 00 00 fc ff df <80> 3c 02 00 0f 85 fc 03 00 00 89 e8 4a 8b 14 f5 e0 39 a3 96 4c 89 RSP: 0018:ffff888251f0f438 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 1ffff1104a3e1e8b RCX: 0000000000000000 RDX: 000000005c40d7ac RSI: 0000000000000003 RDI: 00000002e206bd60 RBP: 0000000000052dc0 R08: ffff8882b0044218 R09: ffff8882b0045e8a R10: fffffbfff300fefc R11: ffff888167af4000 R12: 0000000000000003 R13: 0000000000000000 R14: 00000000696c7070 R15: ffff8882373f4380 FS: 0000000000000000(0000) GS:ffff88bf2be80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005641d031eee8 CR3: 0000002e7ca14000 CR4: 0000000000350ee0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x11000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]---] Reported-by: Frederick Lawler Link: https://lore.kernel.org/netdev/be5b9271-7507-19c5-ded1-fa78f1980e69@cloudflare.com Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed [hardik: Refer to the irqn member of the mlx5_irq struct, instead of the msi_map, since we don't have upstream v6.4 commit 235a25fe28de ("net/mlx5: Modify struct mlx5_irq to use struct msi_map")]. [hardik: Refer to the pf_pool member of the mlx5_irq_table struct, instead of pcif_pool, since we don't have upstream v6.4 commit 8bebfd767909 ("net/mlx5: Improve naming of pci function vectors")]. Signed-off-by: Hardik Garg Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +- .../ethernet/mellanox/mlx5/core/mlx5_irq.h | 1 + .../net/ethernet/mellanox/mlx5/core/pci_irq.c | 29 +++++++++++++++++++ 3 files changed, 31 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index a0242dc15741..e112b5685b02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -1061,7 +1061,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) mutex_lock(&table->lock); /* sync with create/destroy_async_eq */ if (!mlx5_core_is_sf(dev)) clear_rmap(dev); - mlx5_irq_table_destroy(dev); + mlx5_irq_table_free_irqs(dev); mutex_unlock(&table->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index 23cb63fa4588..2e728e4e81fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -14,6 +14,7 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); int mlx5_irq_table_create(struct mlx5_core_dev *dev); void mlx5_irq_table_destroy(struct mlx5_core_dev *dev); +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev); int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table); int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table); struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 662f1d55e30e..5e0f7d96aac5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -591,6 +591,24 @@ static void irq_pools_destroy(struct mlx5_irq_table *table) irq_pool_free(table->pf_pool); } +static void mlx5_irq_pool_free_irqs(struct mlx5_irq_pool *pool) +{ + struct mlx5_irq *irq; + unsigned long index; + + xa_for_each(&pool->irqs, index, irq) + free_irq(irq->irqn, &irq->nh); +} + +static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table) +{ + if (table->sf_ctrl_pool) { + mlx5_irq_pool_free_irqs(table->sf_comp_pool); + mlx5_irq_pool_free_irqs(table->sf_ctrl_pool); + } + mlx5_irq_pool_free_irqs(table->pf_pool); +} + /* irq_table API */ int mlx5_irq_table_init(struct mlx5_core_dev *dev) @@ -670,6 +688,17 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) pci_free_irq_vectors(dev->pdev); } +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev) +{ + struct mlx5_irq_table *table = dev->priv.irq_table; + + if (mlx5_core_is_sf(dev)) + return; + + mlx5_irq_pools_free_irqs(table); + pci_free_irq_vectors(dev->pdev); +} + int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table) { if (table->sf_comp_pool) From 50c24f0c940728792c8bdf65c1eaf6b91b3b0dcd Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 24 Jul 2023 17:40:55 -0500 Subject: [PATCH 0045/2093] net: ipa: only reset hashed tables when supported commit e11ec2b868af2b351c6c1e2e50eb711cc5423a10 upstream. Last year, the code that manages GSI channel transactions switched from using spinlock-protected linked lists to using indexes into the ring buffer used for a channel. Recently, Google reported seeing transaction reference count underflows occasionally during shutdown. Doug Anderson found a way to reproduce the issue reliably, and bisected the issue to the commit that eliminated the linked lists and the lock. The root cause was ultimately determined to be related to unused transactions being committed as part of the modem shutdown cleanup activity. Unused transactions are not normally expected (except in error cases). The modem uses some ranges of IPA-resident memory, and whenever it shuts down we zero those ranges. In ipa_filter_reset_table() a transaction is allocated to zero modem filter table entries. If hashing is not supported, hashed table memory should not be zeroed. But currently nothing prevents that, and the result is an unused transaction. Something similar occurs when we zero routing table entries for the modem. By preventing any attempt to clear hashed tables when hashing is not supported, the reference count underflow is avoided in this case. Note that there likely remains an issue with properly freeing unused transactions (if they occur due to errors). This patch addresses only the underflows that Google originally reported. Cc: # 6.1.x Fixes: d338ae28d8a8 ("net: ipa: kill all other transaction lists") Tested-by: Douglas Anderson Signed-off-by: Alex Elder Link: https://lore.kernel.org/r/20230724224055.1688854-1-elder@linaro.org Signed-off-by: Jakub Kicinski Signed-off-by: Alex Elder Signed-off-by: Greg Kroah-Hartman --- drivers/net/ipa/ipa_table.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 510ff2dc8999..cd81dd916c29 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -311,16 +311,15 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem) if (ret) return ret; + ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem); + if (ret || !ipa_table_hash_support(ipa)) + return ret; + ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER_HASHED, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem); - if (ret) - return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem); - - return ret; + return ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem); } /* The AP routes and modem routes are each contiguous within the @@ -329,11 +328,12 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem) * */ static int ipa_route_reset(struct ipa *ipa, bool modem) { + bool hash_support = ipa_table_hash_support(ipa); struct gsi_trans *trans; u16 first; u16 count; - trans = ipa_cmd_trans_alloc(ipa, 4); + trans = ipa_cmd_trans_alloc(ipa, hash_support ? 4 : 2); if (!trans) { dev_err(&ipa->pdev->dev, "no transaction for %s route reset\n", @@ -350,12 +350,14 @@ static int ipa_route_reset(struct ipa *ipa, bool modem) } ipa_table_reset_add(trans, false, first, count, IPA_MEM_V4_ROUTE); - ipa_table_reset_add(trans, false, first, count, - IPA_MEM_V4_ROUTE_HASHED); - ipa_table_reset_add(trans, false, first, count, IPA_MEM_V6_ROUTE); - ipa_table_reset_add(trans, false, first, count, - IPA_MEM_V6_ROUTE_HASHED); + + if (hash_support) { + ipa_table_reset_add(trans, false, first, count, + IPA_MEM_V4_ROUTE_HASHED); + ipa_table_reset_add(trans, false, first, count, + IPA_MEM_V6_ROUTE_HASHED); + } gsi_trans_commit_wait(trans); From e3399bd014e9f2faedb66c8660b7f81ef20aa44f Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 2 Aug 2023 17:20:57 +0000 Subject: [PATCH 0046/2093] iommu/arm-smmu-v3: Work around MMU-600 erratum 1076982 commit f322e8af35c7f23a8c08b595c38d6c855b2d836f upstream MMU-600 versions prior to r1p0 fail to correctly generate a WFE wakeup event when the command queue transitions fom full to non-full. We can easily work around this by simply hiding the SEV capability such that we fall back to polling for space in the queue - since MMU-600 implements MSIs we wouldn't expect to need SEV for sync completion either, so this should have little to no impact. Signed-off-by: Robin Murphy Reviewed-by: Nicolin Chen Tested-by: Nicolin Chen Link: https://lore.kernel.org/r/08adbe3d01024d8382a478325f73b56851f76e49.1683731256.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Easwar Hariharan Signed-off-by: Greg Kroah-Hartman --- Documentation/arm64/silicon-errata.rst | 2 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 29 +++++++++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 6 +++++ 3 files changed, 37 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index bbc80eff03f9..9f94afe2fc17 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -141,6 +141,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | MMU-600 | #1076982 | N/A | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index d4d8bfee9feb..c12b57910c51 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3410,6 +3410,33 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) return 0; } +#define IIDR_IMPLEMENTER_ARM 0x43b +#define IIDR_PRODUCTID_ARM_MMU_600 0x483 + +static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu) +{ + u32 reg; + unsigned int implementer, productid, variant, revision; + + reg = readl_relaxed(smmu->base + ARM_SMMU_IIDR); + implementer = FIELD_GET(IIDR_IMPLEMENTER, reg); + productid = FIELD_GET(IIDR_PRODUCTID, reg); + variant = FIELD_GET(IIDR_VARIANT, reg); + revision = FIELD_GET(IIDR_REVISION, reg); + + switch (implementer) { + case IIDR_IMPLEMENTER_ARM: + switch (productid) { + case IIDR_PRODUCTID_ARM_MMU_600: + /* Arm erratum 1076982 */ + if (variant == 0 && revision <= 2) + smmu->features &= ~ARM_SMMU_FEAT_SEV; + break; + } + break; + } +} + static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) { u32 reg; @@ -3615,6 +3642,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) smmu->ias = max(smmu->ias, smmu->oas); + arm_smmu_device_iidr_probe(smmu); + if (arm_smmu_sva_supported(smmu)) smmu->features |= ARM_SMMU_FEAT_SVA; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index cd48590ada30..ce5e44a13d84 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -69,6 +69,12 @@ #define IDR5_VAX GENMASK(11, 10) #define IDR5_VAX_52_BIT 1 +#define ARM_SMMU_IIDR 0x18 +#define IIDR_PRODUCTID GENMASK(31, 20) +#define IIDR_VARIANT GENMASK(19, 16) +#define IIDR_REVISION GENMASK(15, 12) +#define IIDR_IMPLEMENTER GENMASK(11, 0) + #define ARM_SMMU_CR0 0x20 #define CR0_ATSCHK (1 << 4) #define CR0_CMDQEN (1 << 3) From 57ae3671ece5380ab0e7b948c508797a77632a1e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 2 Aug 2023 17:20:58 +0000 Subject: [PATCH 0047/2093] iommu/arm-smmu-v3: Document MMU-700 erratum 2812531 commit 309a15cb16bb075da1c99d46fb457db6a1a2669e upstream To work around MMU-700 erratum 2812531 we need to ensure that certain sequences of commands cannot be issued without an intervening sync. In practice this falls out of our current command-batching machinery anyway - each batch only contains a single type of invalidation command, and ends with a sync. The only exception is when a batch is sufficiently large to need issuing across multiple command queue slots, wherein the earlier slots will not contain a sync and thus may in theory interleave with another batch being issued in parallel to create an affected sequence across the slot boundary. Since MMU-700 supports range invalidate commands and thus we will prefer to use them (which also happens to avoid conditions for other errata), I'm not entirely sure it's even possible for a single high-level invalidate call to generate a batch of more than 63 commands, but for the sake of robustness and documentation, wire up an option to enforce that a sync is always inserted for every slot issued. The other aspect is that the relative order of DVM commands cannot be controlled, so DVM cannot be used. Again that is already the status quo, but since we have at least defined ARM_SMMU_FEAT_BTM, we can explicitly disable it for documentation purposes even if it's not wired up anywhere yet. Signed-off-by: Robin Murphy Reviewed-by: Nicolin Chen Link: https://lore.kernel.org/r/330221cdfd0003cd51b6c04e7ff3566741ad8374.1683731256.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Easwar Hariharan Signed-off-by: Greg Kroah-Hartman --- Documentation/arm64/silicon-errata.rst | 2 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 12 ++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1 + 3 files changed, 15 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 9f94afe2fc17..40405cf79794 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -143,6 +143,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-600 | #1076982 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | MMU-700 | #2812531 | N/A | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index c12b57910c51..aed038f7d66c 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -882,6 +882,12 @@ static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu, { int index; + if (cmds->num == CMDQ_BATCH_ENTRIES - 1 && + (smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC)) { + arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true); + cmds->num = 0; + } + if (cmds->num == CMDQ_BATCH_ENTRIES) { arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false); cmds->num = 0; @@ -3412,6 +3418,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) #define IIDR_IMPLEMENTER_ARM 0x43b #define IIDR_PRODUCTID_ARM_MMU_600 0x483 +#define IIDR_PRODUCTID_ARM_MMU_700 0x487 static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu) { @@ -3432,6 +3439,11 @@ static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu) if (variant == 0 && revision <= 2) smmu->features &= ~ARM_SMMU_FEAT_SEV; break; + case IIDR_PRODUCTID_ARM_MMU_700: + /* Arm erratum 2812531 */ + smmu->features &= ~ARM_SMMU_FEAT_BTM; + smmu->options |= ARM_SMMU_OPT_CMDQ_FORCE_SYNC; + break; } break; } diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index ce5e44a13d84..d9e4357c6869 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -650,6 +650,7 @@ struct arm_smmu_device { #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) #define ARM_SMMU_OPT_PAGE0_REGS_ONLY (1 << 1) #define ARM_SMMU_OPT_MSIPOLL (1 << 2) +#define ARM_SMMU_OPT_CMDQ_FORCE_SYNC (1 << 3) u32 options; struct arm_smmu_cmdq cmdq; From 42d04acf1d9b78c07f9a29d6093b638ccf21c175 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 2 Aug 2023 17:20:59 +0000 Subject: [PATCH 0048/2093] iommu/arm-smmu-v3: Add explicit feature for nesting commit 1d9777b9f3d55b4b6faf186ba4f1d6fb560c0523 upstream In certain cases we may want to refuse to allow nested translation even when both stages are implemented, so let's add an explicit feature for nesting support which we can control in its own right. For now this merely serves as documentation, but it means a nice convenient check will be ready and waiting for the future nesting code. Signed-off-by: Robin Murphy Reviewed-by: Nicolin Chen Link: https://lore.kernel.org/r/136c3f4a3a84cc14a5a1978ace57dfd3ed67b688.1683731256.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Easwar Hariharan Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 4 ++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index aed038f7d66c..330f909a29de 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3654,6 +3654,10 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) smmu->ias = max(smmu->ias, smmu->oas); + if ((smmu->features & ARM_SMMU_FEAT_TRANS_S1) && + (smmu->features & ARM_SMMU_FEAT_TRANS_S2)) + smmu->features |= ARM_SMMU_FEAT_NESTING; + arm_smmu_device_iidr_probe(smmu); if (arm_smmu_sva_supported(smmu)) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index d9e4357c6869..d0b207cae107 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -645,6 +645,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_BTM (1 << 16) #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_E2H (1 << 18) +#define ARM_SMMU_FEAT_NESTING (1 << 19) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) From 8ddb3183c439bec96c6fb244b4449486405d6c3b Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 2 Aug 2023 17:21:00 +0000 Subject: [PATCH 0049/2093] iommu/arm-smmu-v3: Document nesting-related errata commit 0bfbfc526c70606bf0fad302e4821087cbecfaf4 upstream Both MMU-600 and MMU-700 have similar errata around TLB invalidation while both stages of translation are active, which will need some consideration once nesting support is implemented. For now, though, it's very easy to make our implicit lack of nesting support explicit for those cases, so they're less likely to be missed in future. Signed-off-by: Robin Murphy Reviewed-by: Nicolin Chen Link: https://lore.kernel.org/r/696da78d32bb4491f898f11b0bb4d850a8aa7c6a.1683731256.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Easwar Hariharan Signed-off-by: Greg Kroah-Hartman --- Documentation/arm64/silicon-errata.rst | 4 ++-- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 40405cf79794..b3c8ac6a2c38 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -141,9 +141,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ -| ARM | MMU-600 | #1076982 | N/A | +| ARM | MMU-600 | #1076982,1209401| N/A | +----------------+-----------------+-----------------+-----------------------------+ -| ARM | MMU-700 | #2812531 | N/A | +| ARM | MMU-700 | #2268618,2812531| N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 330f909a29de..db33dc87f69e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3438,11 +3438,16 @@ static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu) /* Arm erratum 1076982 */ if (variant == 0 && revision <= 2) smmu->features &= ~ARM_SMMU_FEAT_SEV; + /* Arm erratum 1209401 */ + if (variant < 2) + smmu->features &= ~ARM_SMMU_FEAT_NESTING; break; case IIDR_PRODUCTID_ARM_MMU_700: /* Arm erratum 2812531 */ smmu->features &= ~ARM_SMMU_FEAT_BTM; smmu->options |= ARM_SMMU_OPT_CMDQ_FORCE_SYNC; + /* Arm errata 2268618, 2812531 */ + smmu->features &= ~ARM_SMMU_FEAT_NESTING; break; } break; From d060bbb2fed8afa3509614a6057f0792a5c71d0a Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Tue, 6 Jun 2023 08:39:45 -0700 Subject: [PATCH 0050/2093] arm64: dts: imx8mm-venice-gw7903: disable disp_blk_ctrl [ Upstream commit 3e7d3c5e13b05dda9db92d98803a626378e75438 ] The GW7903 does not connect the VDD_MIPI power rails thus MIPI is disabled. However we must also disable disp_blk_ctrl as it uses the pgc_mipi power domain and without it being disabled imx8m-blk-ctrl will fail to probe: imx8m-blk-ctrl 32e28000.blk-ctrl: error -ETIMEDOUT: failed to attach power domain "mipi-dsi" imx8m-blk-ctrl: probe of 32e28000.blk-ctrl failed with error -110 Fixes: a72ba91e5bc7 ("arm64: dts: imx: Add i.mx8mm Gateworks gw7903 dts support") Signed-off-by: Tim Harvey Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts index 8e861b920d09..7c9b60f4da92 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts @@ -559,6 +559,10 @@ &pcie0 { status = "okay"; }; +&disp_blk_ctrl { + status = "disabled"; +}; + &pgc_mipi { status = "disabled"; }; From 608ac7ea5f057dca02df0f6fec70cdadf4aa47b3 Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Tue, 6 Jun 2023 08:40:30 -0700 Subject: [PATCH 0051/2093] arm64: dts: imx8mm-venice-gw7904: disable disp_blk_ctrl [ Upstream commit f7a0b57524cf811ac06257a5099f1b7c19ee7310 ] The GW7904 does not connect the VDD_MIPI power rails thus MIPI is disabled. However we must also disable disp_blk_ctrl as it uses the pgc_mipi power domain and without it being disabled imx8m-blk-ctrl will fail to probe: imx8m-blk-ctrl 32e28000.blk-ctrl: error -ETIMEDOUT: failed to attach power domain "mipi-dsi" imx8m-blk-ctrl: probe of 32e28000.blk-ctrl failed with error -110 Fixes: b999bdaf0597 ("arm64: dts: imx: Add i.mx8mm Gateworks gw7904 dts support") Signed-off-by: Tim Harvey Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts index a67771d02146..46a07dfc0086 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7904.dts @@ -617,6 +617,10 @@ &pcie0 { status = "okay"; }; +&disp_blk_ctrl { + status = "disabled"; +}; + &pgc_mipi { status = "disabled"; }; From 753a927c58412a8510ff5933c948d259df9058c3 Mon Sep 17 00:00:00 2001 From: Yashwanth Varakala Date: Fri, 16 Jun 2023 11:50:07 +0200 Subject: [PATCH 0052/2093] arm64: dts: phycore-imx8mm: Label typo-fix of VPU [ Upstream commit cddeefc1663294fb74b31ff5029a83c0e819ff3a ] Corrected the label of the VPU regulator node (buck 3) from reg_vdd_gpu to reg_vdd_vpu. Fixes: ae6847f26ac9 ("arm64: dts: freescale: Add phyBOARD-Polis-i.MX8MM support") Signed-off-by: Yashwanth Varakala Signed-off-by: Cem Tenruh Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi index 995b44efb1b6..3e5e7d861882 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi @@ -210,7 +210,7 @@ regulator-state-mem { }; }; - reg_vdd_gpu: buck3 { + reg_vdd_vpu: buck3 { regulator-always-on; regulator-boot-on; regulator-max-microvolt = <1000000>; From a24f67b71ad265e4008ae88f09e5bc039afb49df Mon Sep 17 00:00:00 2001 From: Yashwanth Varakala Date: Fri, 16 Jun 2023 11:50:09 +0200 Subject: [PATCH 0053/2093] arm64: dts: phycore-imx8mm: Correction in gpio-line-names [ Upstream commit 1ef0aa137a96c5f0564f2db0c556a4f0f60ce8f5 ] Remove unused nINT_ETHPHY entry from gpio-line-names in gpio1 nodes of phyCORE-i.MX8MM and phyBOARD-Polis-i.MX8MM devicetrees. Fixes: ae6847f26ac9 ("arm64: dts: freescale: Add phyBOARD-Polis-i.MX8MM support") Signed-off-by: Yashwanth Varakala Signed-off-by: Cem Tenruh Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts | 2 +- arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts index 4a3df2b77b0b..6720ddf59783 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-phyboard-polis-rdk.dts @@ -141,7 +141,7 @@ can0: can@0 { }; &gpio1 { - gpio-line-names = "nINT_ETHPHY", "LED_RED", "WDOG_INT", "X_RTC_INT", + gpio-line-names = "", "LED_RED", "WDOG_INT", "X_RTC_INT", "", "", "", "RESET_ETHPHY", "CAN_nINT", "CAN_EN", "nENABLE_FLATLINK", "", "USB_OTG_VBUS_EN", "", "LED_GREEN", "LED_BLUE"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi index 3e5e7d861882..9d9b103c79c7 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-phycore-som.dtsi @@ -111,7 +111,7 @@ som_flash: flash@0 { }; &gpio1 { - gpio-line-names = "nINT_ETHPHY", "", "WDOG_INT", "X_RTC_INT", + gpio-line-names = "", "", "WDOG_INT", "X_RTC_INT", "", "", "", "RESET_ETHPHY", "", "", "nENABLE_FLATLINK"; }; From 5841d3d0c3525e699c2eb60cce0bfa3eb03eccc0 Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Tue, 4 Jul 2023 09:48:00 -0400 Subject: [PATCH 0054/2093] arm64: dts: imx8mn-var-som: add missing pull-up for onboard PHY reset pinmux [ Upstream commit 253be5b53c2792fb4384f8005b05421e6f040ee3 ] For SOMs with an onboard PHY, the RESET_N pull-up resistor is currently deactivated in the pinmux configuration. When the pinmux code selects the GPIO function for this pin, with a default direction of input, this prevents the RESET_N pin from being taken to the proper 3.3V level (deasserted), and this results in the PHY being not detected since it is held in reset. Taken from RESET_N pin description in ADIN13000 datasheet: This pin requires a 1K pull-up resistor to AVDD_3P3. Activate the pull-up resistor to fix the issue. Fixes: ade0176dd8a0 ("arm64: dts: imx8mn-var-som: Add Variscite VAR-SOM-MX8MN System on Module") Signed-off-by: Hugo Villeneuve Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index d053ef302fb8..faafefe562e4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -351,7 +351,7 @@ MX8MN_IOMUXC_ENET_TXC_ENET1_RGMII_TXC 0x1f MX8MN_IOMUXC_ENET_RXC_ENET1_RGMII_RXC 0x91 MX8MN_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL 0x91 MX8MN_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL 0x1f - MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x19 + MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x159 >; }; From 7b0582dddd7eaa005ed895049db400da5dd54dda Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Fri, 7 Jul 2023 11:42:00 +0200 Subject: [PATCH 0055/2093] arm64: dts: freescale: Fix VPU G2 clock [ Upstream commit b27bfc5103c72f84859bd32731b6a09eafdeda05 ] Set VPU G2 clock to 300MHz like described in documentation. This fixes pixels error occurring with large resolution ( >= 2560x1600) HEVC test stream when using the postprocessor to produce NV12. Fixes: 4ac7e4a81272 ("arm64: dts: imx8mq: Enable both G1 and G2 VPU's with vpu-blk-ctrl") Signed-off-by: Benjamin Gaignard Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mq.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 4724ed0cbff9..bf8f02c1535c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -756,7 +756,7 @@ pgc_vpu: power-domain@6 { <&clk IMX8MQ_SYS1_PLL_800M>, <&clk IMX8MQ_VPU_PLL>; assigned-clock-rates = <600000000>, - <600000000>, + <300000000>, <800000000>, <0>; }; From 0ca5de8309f9942cf59190732a37fd251cc60ad1 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Mon, 17 Jul 2023 18:17:02 +0100 Subject: [PATCH 0056/2093] firmware: smccc: Fix use of uninitialised results structure [ Upstream commit d05799d7b4a39fa71c65aa277128ac7c843ffcdc ] Commit 35727af2b15d ("irqchip/gicv3: Workaround for NVIDIA erratum T241-FABRIC-4") moved the initialisation of the SoC version to arm_smccc_version_init() but forgot to update the results structure and it's usage. Fix the use of the uninitialised results structure and update the error strings. Fixes: 35727af2b15d ("irqchip/gicv3: Workaround for NVIDIA erratum T241-FABRIC-4") Signed-off-by: Punit Agrawal Cc: Sudeep Holla Cc: Marc Zyngier Cc: Vikram Sethi Cc: Shanker Donthineni Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20230717171702.424253-1-punit.agrawal@bytedance.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/smccc/soc_id.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c index 890eb454599a..1990263fbba0 100644 --- a/drivers/firmware/smccc/soc_id.c +++ b/drivers/firmware/smccc/soc_id.c @@ -34,7 +34,6 @@ static struct soc_device_attribute *soc_dev_attr; static int __init smccc_soc_init(void) { - struct arm_smccc_res res; int soc_id_rev, soc_id_version; static char soc_id_str[20], soc_id_rev_str[12]; static char soc_id_jep106_id_str[12]; @@ -49,13 +48,13 @@ static int __init smccc_soc_init(void) } if (soc_id_version < 0) { - pr_err("ARCH_SOC_ID(0) returned error: %lx\n", res.a0); + pr_err("Invalid SoC Version: %x\n", soc_id_version); return -EINVAL; } soc_id_rev = arm_smccc_get_soc_id_revision(); if (soc_id_rev < 0) { - pr_err("ARCH_SOC_ID(1) returned error: %lx\n", res.a0); + pr_err("Invalid SoC Revision: %x\n", soc_id_rev); return -EINVAL; } From 6289d5486d36d6294a16eaeae1d31045dda14eee Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 17 Jul 2023 12:17:03 -0700 Subject: [PATCH 0057/2093] lib/bitmap: workaround const_eval test build failure [ Upstream commit 2356d198d2b4ddec24efea98271cb3be230bc787 ] When building with Clang, and when KASAN and GCOV_PROFILE_ALL are both enabled, the test fails to build [1]: >> lib/test_bitmap.c:920:2: error: call to '__compiletime_assert_239' declared with 'error' attribute: BUILD_BUG_ON failed: !__builtin_constant_p(res) BUILD_BUG_ON(!__builtin_constant_p(res)); ^ include/linux/build_bug.h:50:2: note: expanded from macro 'BUILD_BUG_ON' BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) ^ include/linux/build_bug.h:39:37: note: expanded from macro 'BUILD_BUG_ON_MSG' #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) ^ include/linux/compiler_types.h:352:2: note: expanded from macro 'compiletime_assert' _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) ^ include/linux/compiler_types.h:340:2: note: expanded from macro '_compiletime_assert' __compiletime_assert(condition, msg, prefix, suffix) ^ include/linux/compiler_types.h:333:4: note: expanded from macro '__compiletime_assert' prefix ## suffix(); \ ^ :185:1: note: expanded from here __compiletime_assert_239 Originally it was attributed to s390, which now looks seemingly wrong. The issue is not related to bitmap code itself, but it breaks build for a given configuration. Disabling the const_eval test under that config may potentially hide other bugs. Instead, workaround it by disabling GCOV for the test_bitmap unless the compiler will get fixed. [1] https://github.com/ClangBuiltLinux/linux/issues/1874 Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202307171254.yFcH97ej-lkp@intel.com/ Fixes: dc34d5036692 ("lib: test_bitmap: add compile-time optimization/evaluations assertions") Co-developed-by: Nathan Chancellor Signed-off-by: Nathan Chancellor Signed-off-by: Yury Norov Reviewed-by: Nick Desaulniers Reviewed-by: Alexander Lobakin Signed-off-by: Sasha Levin --- lib/Makefile | 6 ++++++ lib/test_bitmap.c | 8 ++++---- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/lib/Makefile b/lib/Makefile index 59bd7c2f793a..5ffe72ec9979 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -81,8 +81,14 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o obj-$(CONFIG_TEST_PRINTF) += test_printf.o obj-$(CONFIG_TEST_SCANF) += test_scanf.o + obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o obj-$(CONFIG_TEST_STRSCPY) += test_strscpy.o +ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_KASAN),yy) +# FIXME: Clang breaks test_bitmap_const_eval when KASAN and GCOV are enabled +GCOV_PROFILE_test_bitmap.o := n +endif + obj-$(CONFIG_TEST_UUID) += test_uuid.o obj-$(CONFIG_TEST_XARRAY) += test_xarray.o obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index a8005ad3bd58..37a9108c4f58 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -1149,6 +1149,10 @@ static void __init test_bitmap_print_buf(void) } } +/* + * FIXME: Clang breaks compile-time evaluations when KASAN and GCOV are enabled. + * To workaround it, GCOV is force-disabled in Makefile for this configuration. + */ static void __init test_bitmap_const_eval(void) { DECLARE_BITMAP(bitmap, BITS_PER_LONG); @@ -1174,11 +1178,7 @@ static void __init test_bitmap_const_eval(void) * the compiler is fixed. */ bitmap_clear(bitmap, 0, BITS_PER_LONG); -#if defined(__s390__) && defined(__clang__) - if (!const_test_bit(7, bitmap)) -#else if (!test_bit(7, bitmap)) -#endif bitmap_set(bitmap, 5, 2); /* Equals to `unsigned long bitopvar = BIT(20)` */ From 5b53b2b44f0cf5e77bc6e4ac22685ba23eafe94a Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 19 Jul 2023 18:35:33 +0100 Subject: [PATCH 0058/2093] firmware: arm_scmi: Fix chan_free cleanup on SMC [ Upstream commit d1ff11d7ad8704f8d615f6446041c221b2d2ec4d ] SCMI transport based on SMC can optionally use an additional IRQ to signal message completion. The associated interrupt handler is currently allocated using devres but on shutdown the core SCMI stack will call .chan_free() well before any managed cleanup is invoked by devres. As a consequence, the arrival of a late reply to an in-flight pending transaction could still trigger the interrupt handler well after the SCMI core has cleaned up the channels, with unpleasant results. Inhibit further message processing on the IRQ path by explicitly freeing the IRQ inside .chan_free() callback itself. Fixes: dd820ee21d5e ("firmware: arm_scmi: Augment SMC/HVC to allow optional interrupt") Reported-by: Bjorn Andersson Signed-off-by: Cristian Marussi Link: https://lore.kernel.org/r/20230719173533.2739319-1-cristian.marussi@arm.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_scmi/smc.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index 87a7b13cf868..dc383d874ee3 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -23,6 +23,7 @@ /** * struct scmi_smc - Structure representing a SCMI smc transport * + * @irq: An optional IRQ for completion * @cinfo: SCMI channel info * @shmem: Transmit/Receive shared memory area * @shmem_lock: Lock to protect access to Tx/Rx shared memory area. @@ -33,6 +34,7 @@ */ struct scmi_smc { + int irq; struct scmi_chan_info *cinfo; struct scmi_shared_mem __iomem *shmem; /* Protect access to shmem area */ @@ -106,7 +108,7 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, struct resource res; struct device_node *np; u32 func_id; - int ret, irq; + int ret; if (!tx) return -ENODEV; @@ -142,11 +144,10 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, * completion of a message is signaled by an interrupt rather than by * the return of the SMC call. */ - irq = of_irq_get_byname(cdev->of_node, "a2p"); - if (irq > 0) { - ret = devm_request_irq(dev, irq, smc_msg_done_isr, - IRQF_NO_SUSPEND, - dev_name(dev), scmi_info); + scmi_info->irq = of_irq_get_byname(cdev->of_node, "a2p"); + if (scmi_info->irq > 0) { + ret = request_irq(scmi_info->irq, smc_msg_done_isr, + IRQF_NO_SUSPEND, dev_name(dev), scmi_info); if (ret) { dev_err(dev, "failed to setup SCMI smc irq\n"); return ret; @@ -168,6 +169,10 @@ static int smc_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_smc *scmi_info = cinfo->transport_info; + /* Ignore any possible further reception on the IRQ path */ + if (scmi_info->irq > 0) + free_irq(scmi_info->irq, scmi_info); + cinfo->transport_info = NULL; scmi_info->cinfo = NULL; From f168188174b3ec24f54b1d79811ebeb1c00d3df0 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Tue, 1 Aug 2023 15:22:17 -0700 Subject: [PATCH 0059/2093] word-at-a-time: use the same return type for has_zero regardless of endianness [ Upstream commit 79e8328e5acbe691bbde029a52c89d70dcbc22f3 ] Compiling big-endian targets with Clang produces the diagnostic: fs/namei.c:2173:13: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical] } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); ~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ || fs/namei.c:2173:13: note: cast one or both operands to int to silence this warning It appears that when has_zero was introduced, two definitions were produced with different signatures (in particular different return types). Looking at the usage in hash_name() in fs/namei.c, I suspect that has_zero() is meant to be invoked twice per while loop iteration; using logical-or would not update `bdata` when `a` did not have zeros. So I think it's preferred to always return an unsigned long rather than a bool than update the while loop in hash_name() to use a logical-or rather than bitwise-or. [ Also changed powerpc version to do the same - Linus ] Link: https://github.com/ClangBuiltLinux/linux/issues/1832 Link: https://lore.kernel.org/lkml/20230801-bitwise-v1-1-799bec468dc4@google.com/ Fixes: 36126f8f2ed8 ("word-at-a-time: make the interfaces truly generic") Debugged-by: Nathan Chancellor Signed-off-by: Nick Desaulniers Acked-by: Heiko Carstens Cc: Arnd Bergmann Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/word-at-a-time.h | 2 +- include/asm-generic/word-at-a-time.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index 46c31fb8748d..30a12d208687 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -34,7 +34,7 @@ static inline long find_zero(unsigned long mask) return leading_zero_bits >> 3; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h index 20c93f08c993..95a1d214108a 100644 --- a/include/asm-generic/word-at-a-time.h +++ b/include/asm-generic/word-at-a-time.h @@ -38,7 +38,7 @@ static inline long find_zero(unsigned long mask) return (mask >> 8) ? byte : byte + 1; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; From a759972d254901fa8066676caef6e4cc3a48d52e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 27 Jul 2023 20:29:39 +0200 Subject: [PATCH 0060/2093] KVM: s390: fix sthyi error handling [ Upstream commit 0c02cc576eac161601927b41634f80bfd55bfa9e ] Commit 9fb6c9b3fea1 ("s390/sthyi: add cache to store hypervisor info") added cache handling for store hypervisor info. This also changed the possible return code for sthyi_fill(). Instead of only returning a condition code like the sthyi instruction would do, it can now also return a negative error value (-ENOMEM). handle_styhi() was not changed accordingly. In case of an error, the negative error value would incorrectly injected into the guest PSW. Add proper error handling to prevent this, and update the comment which describes the possible return values of sthyi_fill(). Fixes: 9fb6c9b3fea1 ("s390/sthyi: add cache to store hypervisor info") Reviewed-by: Christian Borntraeger Link: https://lore.kernel.org/r/20230727182939.2050744-1-hca@linux.ibm.com Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/kernel/sthyi.c | 6 +++--- arch/s390/kvm/intercept.c | 9 ++++++--- 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c index 4d141e2c132e..2ea7f208f0e7 100644 --- a/arch/s390/kernel/sthyi.c +++ b/arch/s390/kernel/sthyi.c @@ -459,9 +459,9 @@ static int sthyi_update_cache(u64 *rc) * * Fills the destination with system information returned by the STHYI * instruction. The data is generated by emulation or execution of STHYI, - * if available. The return value is the condition code that would be - * returned, the rc parameter is the return code which is passed in - * register R2 + 1. + * if available. The return value is either a negative error value or + * the condition code that would be returned, the rc parameter is the + * return code which is passed in register R2 + 1. */ int sthyi_fill(void *dst, u64 *rc) { diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index ee7478a60144..b37bb960bfaf 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -389,8 +389,8 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu) */ int handle_sthyi(struct kvm_vcpu *vcpu) { - int reg1, reg2, r = 0; - u64 code, addr, cc = 0, rc = 0; + int reg1, reg2, cc = 0, r = 0; + u64 code, addr, rc = 0; struct sthyi_sctns *sctns = NULL; if (!test_kvm_facility(vcpu->kvm, 74)) @@ -421,7 +421,10 @@ int handle_sthyi(struct kvm_vcpu *vcpu) return -ENOMEM; cc = sthyi_fill(sctns, &rc); - + if (cc < 0) { + free_page((unsigned long)sctns); + return cc; + } out: if (!cc) { if (kvm_s390_pv_cpu_is_protected(vcpu)) { From 05e0952ddb75abef20cdb585060584f8d8f0bc4a Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Wed, 19 Jul 2023 14:54:59 +0800 Subject: [PATCH 0061/2093] erofs: fix wrong primary bvec selection on deduplicated extents [ Upstream commit 94c43de73521d8ed7ebcfc6191d9dace1cbf7caa ] When handling deduplicated compressed data, there can be multiple decompressed extents pointing to the same compressed data in one shot. In such cases, the bvecs which belong to the longest extent will be selected as the primary bvecs for real decompressors to decode and the other duplicated bvecs will be directly copied from the primary bvecs. Previously, only relative offsets of the longest extent were checked to decompress the primary bvecs. On rare occasions, it can be incorrect if there are several extents with the same start relative offset. As a result, some short bvecs could be selected for decompression and then cause data corruption. For example, as Shijie Sun reported off-list, considering the following extents of a file: 117: 903345.. 915250 | 11905 : 385024.. 389120 | 4096 ... 119: 919729.. 930323 | 10594 : 385024.. 389120 | 4096 ... 124: 968881.. 980786 | 11905 : 385024.. 389120 | 4096 The start relative offset is the same: 2225, but extent 119 (919729.. 930323) is shorter than the others. Let's restrict the bvec length in addition to the start offset if bvecs are not full. Reported-by: Shijie Sun Fixes: 5c2a64252c5d ("erofs: introduce partial-referenced pclusters") Tested-by Shijie Sun Reviewed-by: Yue Hu Reviewed-by: Chao Yu Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20230719065459.60083-1-hsiangkao@linux.alibaba.com Signed-off-by: Sasha Levin --- fs/erofs/zdata.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 533e612b6a48..361f3c29897e 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -989,10 +989,11 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, struct z_erofs_bvec *bvec) { struct z_erofs_bvec_item *item; + unsigned int pgnr; - if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { - unsigned int pgnr; - + if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) && + (bvec->end == PAGE_SIZE || + bvec->offset + bvec->end == be->pcl->length)) { pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; DBG_BUGON(pgnr >= be->nr_pages); if (!be->decompressed_pages[pgnr]) { From 7a6fad03f54c3fd007a075fa58b75789ff12f227 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Sun, 23 Jul 2023 23:10:43 +0300 Subject: [PATCH 0062/2093] wifi: cfg80211: Fix return value in scan logic [ Upstream commit fd7f08d92fcd7cc3eca0dd6c853f722a4c6176df ] The reporter noticed a warning when running iwlwifi: WARNING: CPU: 8 PID: 659 at mm/page_alloc.c:4453 __alloc_pages+0x329/0x340 As cfg80211_parse_colocated_ap() is not expected to return a negative value return 0 and not a negative value if cfg80211_calc_short_ssid() fails. Fixes: c8cb5b854b40f ("nl80211/cfg80211: support 6 GHz scanning") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217675 Signed-off-by: Ilan Peer Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230723201043.3007430-1-ilan.peer@intel.com Signed-off-by: Sasha Levin --- net/wireless/scan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index efe9283e9893..e5c1510c098f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -643,7 +643,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); if (ret) - return ret; + return 0; /* RNR IE may contain more than one NEIGHBOR_AP_INFO */ while (pos + sizeof(*ap_info) <= end) { From c818fff3b6cb1a8d5216e4974c4b5f2d11ebf005 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 4 Jul 2023 15:06:40 +0800 Subject: [PATCH 0063/2093] net/mlx5e: fix double free in macsec_fs_tx_create_crypto_table_groups [ Upstream commit aeb660171b0663847fa04806a96302ac6112ad26 ] In function macsec_fs_tx_create_crypto_table_groups(), when the ft->g memory is successfully allocated but the 'in' memory fails to be allocated, the memory pointed to by ft->g is released once. And in function macsec_fs_tx_create(), macsec_fs_tx_destroy() is called to release the memory pointed to by ft->g again. This will cause double free problem. Fixes: e467b283ffd5 ("net/mlx5e: Add MACsec TX steering rules") Signed-off-by: Zhengchao Shao Reviewed-by: Simon Horman Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c index 5b658a5588c6..6ecf0bf2366a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c @@ -160,6 +160,7 @@ static int macsec_fs_tx_create_crypto_table_groups(struct mlx5e_flow_table *ft) if (!in) { kfree(ft->g); + ft->g = NULL; return -ENOMEM; } From 3169c3854397f3070a63b1b772db16dcb8cba7b4 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 5 Jul 2023 20:15:27 +0800 Subject: [PATCH 0064/2093] net/mlx5: DR, fix memory leak in mlx5dr_cmd_create_reformat_ctx [ Upstream commit 5dd77585dd9d0e03dd1bceb95f0269a7eaf6b936 ] when mlx5_cmd_exec failed in mlx5dr_cmd_create_reformat_ctx, the memory pointed by 'in' is not released, which will cause memory leak. Move memory release after mlx5_cmd_exec. Fixes: 1d9186476e12 ("net/mlx5: DR, Add direct rule command utilities") Signed-off-by: Zhengchao Shao Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 84364691a379..d7b1a230b59e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -538,11 +538,12 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); if (err) - return err; + goto err_free_in; *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); - kvfree(in); +err_free_in: + kvfree(in); return err; } From 0582a3caaa3e2f7b80bcb113ad3c910eac15a63e Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Sat, 8 Jul 2023 15:13:07 +0800 Subject: [PATCH 0065/2093] net/mlx5: fix potential memory leak in mlx5e_init_rep_rx [ Upstream commit c6cf0b6097bf1bf1b2a89b521e9ecd26b581a93a ] The memory pointed to by the priv->rx_res pointer is not freed in the error path of mlx5e_init_rep_rx, which can lead to a memory leak. Fix by freeing the memory in the error path, thereby making the error path identical to mlx5e_cleanup_rep_rx(). Fixes: af8bbf730068 ("net/mlx5e: Convert mlx5e_flow_steering member of mlx5e_priv to pointer") Signed-off-by: Zhengchao Shao Reviewed-by: Simon Horman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 9bd1a93a512d..ff0c025db140 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -912,7 +912,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err = mlx5e_open_drop_rq(priv, &priv->drop_rq); if (err) { mlx5_core_err(mdev, "open drop rq failed, %d\n", err); - return err; + goto err_rx_res_free; } err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, @@ -946,6 +946,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) mlx5e_rx_res_destroy(priv->rx_res); err_close_drop_rq: mlx5e_close_drop_rq(&priv->drop_rq); +err_rx_res_free: mlx5e_rx_res_free(priv->rx_res); priv->rx_res = NULL; err_free_fs: From a7b5f001004c2fe0d2e3ea8d21d498e38a61d9eb Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Tue, 25 Jul 2023 14:56:55 +0800 Subject: [PATCH 0066/2093] net/mlx5e: fix return value check in mlx5e_ipsec_remove_trailer() [ Upstream commit e5bcb7564d3bd0c88613c76963c5349be9c511c5 ] mlx5e_ipsec_remove_trailer() should return an error code if function pskb_trim() returns an unexpected value. Fixes: 2ac9cfe78223 ("net/mlx5e: IPSec, Add Innova IPSec offload TX data path") Signed-off-by: Yuanjun Gong Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 6859f1c1a831..c4a84f0a3b73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -58,7 +58,9 @@ static int mlx5e_ipsec_remove_trailer(struct sk_buff *skb, struct xfrm_state *x) trailer_len = alen + plen + 2; - pskb_trim(skb, skb->len - trailer_len); + ret = pskb_trim(skb, skb->len - trailer_len); + if (unlikely(ret)) + return ret; if (skb->protocol == htons(ETH_P_IP)) { ipv4hdr->tot_len = htons(ntohs(ipv4hdr->tot_len) - trailer_len); ip_send_check(ipv4hdr); From 94a0eb9c12be737d91bd84bf7f395f197d076628 Mon Sep 17 00:00:00 2001 From: Amir Tzin Date: Tue, 30 May 2023 20:11:14 +0300 Subject: [PATCH 0067/2093] net/mlx5e: Fix crash moving to switchdev mode when ntuple offload is set [ Upstream commit 3ec43c1b082a8804472430e1253544d75f4b540e ] Moving to switchdev mode with ntuple offload on causes the kernel to crash since fs->arfs is freed during nic profile cleanup flow. Ntuple offload is not supported in switchdev mode and it is already unset by mlx5 fix feature ndo in switchdev mode. Verify fs->arfs is valid before disabling it. trace: [] RIP: 0010:_raw_spin_lock_bh+0x17/0x30 [] arfs_del_rules+0x44/0x1a0 [mlx5_core] [] mlx5e_arfs_disable+0xe/0x20 [mlx5_core] [] mlx5e_handle_feature+0x3d/0xb0 [mlx5_core] [] ? __rtnl_unlock+0x25/0x50 [] mlx5e_set_features+0xfe/0x160 [mlx5_core] [] __netdev_update_features+0x278/0xa50 [] ? netdev_run_todo+0x5e/0x2a0 [] netdev_update_features+0x22/0x70 [] ? _cond_resched+0x15/0x30 [] mlx5e_attach_netdev+0x12a/0x1e0 [mlx5_core] [] mlx5e_netdev_attach_profile+0xa1/0xc0 [mlx5_core] [] mlx5e_netdev_change_profile+0x77/0xe0 [mlx5_core] [] mlx5e_vport_rep_load+0x1ed/0x290 [mlx5_core] [] mlx5_esw_offloads_rep_load+0x88/0xd0 [mlx5_core] [] esw_offloads_load_rep.part.38+0x31/0x50 [mlx5_core] [] esw_offloads_enable+0x6c5/0x710 [mlx5_core] [] mlx5_eswitch_enable_locked+0x1bb/0x290 [mlx5_core] [] mlx5_devlink_eswitch_mode_set+0x14f/0x320 [mlx5_core] [] devlink_nl_cmd_eswitch_set_doit+0x94/0x120 [] genl_family_rcv_msg_doit.isra.17+0x113/0x150 [] genl_family_rcv_msg+0xb7/0x170 [] ? devlink_nl_cmd_port_split_doit+0x100/0x100 [] genl_rcv_msg+0x47/0xa0 [] ? genl_family_rcv_msg+0x170/0x170 [] netlink_rcv_skb+0x4c/0x130 [] genl_rcv+0x24/0x40 [] netlink_unicast+0x19a/0x230 [] netlink_sendmsg+0x204/0x3d0 [] sock_sendmsg+0x50/0x60 Fixes: 90b22b9bcd24 ("net/mlx5e: Disable Rx ntuple offload for uplink representor") Signed-off-by: Amir Tzin Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 0ae1865086ff..dc0a0a27ac84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -136,6 +136,16 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs); int mlx5e_arfs_disable(struct mlx5e_flow_steering *fs) { + /* Moving to switchdev mode, fs->arfs is freed by mlx5e_nic_profile + * cleanup_rx callback and it is not recreated when + * mlx5e_uplink_rep_profile is loaded as mlx5e_create_flow_steering() + * is not called by the uplink_rep profile init_rx callback. Thus, if + * ntuple is set, moving to switchdev flow will enter this function + * with fs->arfs nullified. + */ + if (!mlx5e_fs_get_arfs(fs)) + return 0; + arfs_del_rules(fs); return arfs_disable(fs); From d628ba98eb1637acce44001e04c718d8dbb1f7ce Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 3 Jul 2023 08:28:16 +0000 Subject: [PATCH 0068/2093] net/mlx5e: Move representor neigh cleanup to profile cleanup_tx [ Upstream commit d03b6e6f31820b84f7449cca022047f36c42bc3f ] For IP tunnel encapsulation in ECMP (Equal-Cost Multipath) mode, as the flow is duplicated to the peer eswitch, the related neighbour information on the peer uplink representor is created as well. In the cited commit, eswitch devcom unpair is moved to uplink unload API, specifically the profile->cleanup_tx. If there is a encap rule offloaded in ECMP mode, when one eswitch does unpair (because of unloading the driver, for instance), and the peer rule from the peer eswitch is going to be deleted, the use-after-free error is triggered while accessing neigh info, as it is already cleaned up in uplink's profile->disable, which is before its profile->cleanup_tx. To fix this issue, move the neigh cleanup to profile's cleanup_tx callback, and after mlx5e_cleanup_uplink_rep_tx is called. The neigh init is moved to init_tx for symmeter. [ 2453.376299] BUG: KASAN: slab-use-after-free in mlx5e_rep_neigh_entry_release+0x109/0x3a0 [mlx5_core] [ 2453.379125] Read of size 4 at addr ffff888127af9008 by task modprobe/2496 [ 2453.381542] CPU: 7 PID: 2496 Comm: modprobe Tainted: G B 6.4.0-rc7+ #15 [ 2453.383386] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 2453.384335] Call Trace: [ 2453.384625] [ 2453.384891] dump_stack_lvl+0x33/0x50 [ 2453.385285] print_report+0xc2/0x610 [ 2453.385667] ? __virt_addr_valid+0xb1/0x130 [ 2453.386091] ? mlx5e_rep_neigh_entry_release+0x109/0x3a0 [mlx5_core] [ 2453.386757] kasan_report+0xae/0xe0 [ 2453.387123] ? mlx5e_rep_neigh_entry_release+0x109/0x3a0 [mlx5_core] [ 2453.387798] mlx5e_rep_neigh_entry_release+0x109/0x3a0 [mlx5_core] [ 2453.388465] mlx5e_rep_encap_entry_detach+0xa6/0xe0 [mlx5_core] [ 2453.389111] mlx5e_encap_dealloc+0xa7/0x100 [mlx5_core] [ 2453.389706] mlx5e_tc_tun_encap_dests_unset+0x61/0xb0 [mlx5_core] [ 2453.390361] mlx5_free_flow_attr_actions+0x11e/0x340 [mlx5_core] [ 2453.391015] ? complete_all+0x43/0xd0 [ 2453.391398] ? free_flow_post_acts+0x38/0x120 [mlx5_core] [ 2453.392004] mlx5e_tc_del_fdb_flow+0x4ae/0x690 [mlx5_core] [ 2453.392618] mlx5e_tc_del_fdb_peers_flow+0x308/0x370 [mlx5_core] [ 2453.393276] mlx5e_tc_clean_fdb_peer_flows+0xf5/0x140 [mlx5_core] [ 2453.393925] mlx5_esw_offloads_unpair+0x86/0x540 [mlx5_core] [ 2453.394546] ? mlx5_esw_offloads_set_ns_peer.isra.0+0x180/0x180 [mlx5_core] [ 2453.395268] ? down_write+0xaa/0x100 [ 2453.395652] mlx5_esw_offloads_devcom_event+0x203/0x530 [mlx5_core] [ 2453.396317] mlx5_devcom_send_event+0xbb/0x190 [mlx5_core] [ 2453.396917] mlx5_esw_offloads_devcom_cleanup+0xb0/0xd0 [mlx5_core] [ 2453.397582] mlx5e_tc_esw_cleanup+0x42/0x120 [mlx5_core] [ 2453.398182] mlx5e_rep_tc_cleanup+0x15/0x30 [mlx5_core] [ 2453.398768] mlx5e_cleanup_rep_tx+0x6c/0x80 [mlx5_core] [ 2453.399367] mlx5e_detach_netdev+0xee/0x120 [mlx5_core] [ 2453.399957] mlx5e_netdev_change_profile+0x84/0x170 [mlx5_core] [ 2453.400598] mlx5e_vport_rep_unload+0xe0/0xf0 [mlx5_core] [ 2453.403781] mlx5_eswitch_unregister_vport_reps+0x15e/0x190 [mlx5_core] [ 2453.404479] ? mlx5_eswitch_register_vport_reps+0x200/0x200 [mlx5_core] [ 2453.405170] ? up_write+0x39/0x60 [ 2453.405529] ? kernfs_remove_by_name_ns+0xb7/0xe0 [ 2453.405985] auxiliary_bus_remove+0x2e/0x40 [ 2453.406405] device_release_driver_internal+0x243/0x2d0 [ 2453.406900] ? kobject_put+0x42/0x2d0 [ 2453.407284] bus_remove_device+0x128/0x1d0 [ 2453.407687] device_del+0x240/0x550 [ 2453.408053] ? waiting_for_supplier_show+0xe0/0xe0 [ 2453.408511] ? kobject_put+0xfa/0x2d0 [ 2453.408889] ? __kmem_cache_free+0x14d/0x280 [ 2453.409310] mlx5_rescan_drivers_locked.part.0+0xcd/0x2b0 [mlx5_core] [ 2453.409973] mlx5_unregister_device+0x40/0x50 [mlx5_core] [ 2453.410561] mlx5_uninit_one+0x3d/0x110 [mlx5_core] [ 2453.411111] remove_one+0x89/0x130 [mlx5_core] [ 2453.411628] pci_device_remove+0x59/0xf0 [ 2453.412026] device_release_driver_internal+0x243/0x2d0 [ 2453.412511] ? parse_option_str+0x14/0x90 [ 2453.412915] driver_detach+0x7b/0xf0 [ 2453.413289] bus_remove_driver+0xb5/0x160 [ 2453.413685] pci_unregister_driver+0x3f/0xf0 [ 2453.414104] mlx5_cleanup+0xc/0x20 [mlx5_core] Fixes: 2be5bd42a5bb ("net/mlx5: Handle pairing of E-switch via uplink un/load APIs") Signed-off-by: Jianbo Liu Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ff0c025db140..bd895ef341a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1040,6 +1040,10 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } + err = mlx5e_rep_neigh_init(rpriv); + if (err) + goto err_neigh_init; + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_init_uplink_rep_tx(rpriv); if (err) @@ -1056,6 +1060,8 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); err_init_tx: + mlx5e_rep_neigh_cleanup(rpriv); +err_neigh_init: mlx5e_destroy_tises(priv); return err; } @@ -1069,22 +1075,17 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); + mlx5e_rep_neigh_cleanup(rpriv); mlx5e_destroy_tises(priv); } static void mlx5e_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - mlx5e_set_netdev_mtu_boundaries(priv); - mlx5e_rep_neigh_init(rpriv); } static void mlx5e_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - mlx5e_rep_neigh_cleanup(rpriv); } static int mlx5e_update_rep_rx(struct mlx5e_priv *priv) @@ -1119,7 +1120,6 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; u16 max_mtu; @@ -1139,7 +1139,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5_notifier_register(mdev, &priv->events_nb); mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); - mlx5e_rep_neigh_init(rpriv); mlx5e_rep_bridge_init(priv); netdev->wanted_features |= NETIF_F_HW_TC; @@ -1154,7 +1153,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; rtnl_lock(); @@ -1164,7 +1162,6 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) rtnl_unlock(); mlx5e_rep_bridge_cleanup(priv); - mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); mlx5e_rep_tc_disable(priv); From 24772cc31f0074fb8dbb9f3f2733784dc8bd6673 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 25 Jul 2023 10:33:30 +0800 Subject: [PATCH 0069/2093] bpf: Add length check for SK_DIAG_BPF_STORAGE_REQ_MAP_FD parsing [ Upstream commit bcc29b7f5af6797702c2306a7aacb831fc5ce9cb ] The nla_for_each_nested parsing in function bpf_sk_storage_diag_alloc does not check the length of the nested attribute. This can lead to an out-of-attribute read and allow a malformed nlattr (e.g., length 0) to be viewed as a 4 byte integer. This patch adds an additional check when the nlattr is getting counted. This makes sure the latter nla_get_u32 can access the attributes with the correct length. Fixes: 1ed4d92458a9 ("bpf: INET_DIAG support in bpf_sk_storage") Suggested-by: Jakub Kicinski Signed-off-by: Lin Ma Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230725023330.422856-1-linma@zju.edu.cn Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- net/core/bpf_sk_storage.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94374d529ea4..ad01b1bea52e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -531,8 +531,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); nr_maps++; + } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); From 8dfac8071d58447e5cace4c4c6fe493ce2f615f6 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Wed, 26 Jul 2023 15:53:14 +0800 Subject: [PATCH 0070/2093] rtnetlink: let rtnl_bridge_setlink checks IFLA_BRIDGE_MODE length [ Upstream commit d73ef2d69c0dba5f5a1cb9600045c873bab1fb7f ] There are totally 9 ndo_bridge_setlink handlers in the current kernel, which are 1) bnxt_bridge_setlink, 2) be_ndo_bridge_setlink 3) i40e_ndo_bridge_setlink 4) ice_bridge_setlink 5) ixgbe_ndo_bridge_setlink 6) mlx5e_bridge_setlink 7) nfp_net_bridge_setlink 8) qeth_l2_bridge_setlink 9) br_setlink. By investigating the code, we find that 1-7 parse and use nlattr IFLA_BRIDGE_MODE but 3 and 4 forget to do the nla_len check. This can lead to an out-of-attribute read and allow a malformed nlattr (e.g., length 0) to be viewed as a 2 byte integer. To avoid such issues, also for other ndo_bridge_setlink handlers in the future. This patch adds the nla_len check in rtnl_bridge_setlink and does an early error return if length mismatches. To make it works, the break is removed from the parsing for IFLA_BRIDGE_FLAGS to make sure this nla_for_each_nested iterates every attribute. Fixes: b1edc14a3fbf ("ice: Implement ice_bridge_getlink and ice_bridge_setlink") Fixes: 51616018dd1b ("i40e: Add support for getlink, setlink ndo ops") Suggested-by: Jakub Kicinski Signed-off-by: Lin Ma Acked-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Link: https://lore.kernel.org/r/20230726075314.1059224-1-linma@zju.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/rtnetlink.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5625ed30a06f..2758b3f7c021 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5030,13 +5030,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; have_flags = true; flags = nla_get_u16(attr); - break; + } + + if (nla_type(attr) == IFLA_BRIDGE_MODE) { + if (nla_len(attr) < sizeof(u16)) + return -EINVAL; } } } From 5ef5b6e9c17be8711d50017626d2897b1c06953a Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Thu, 27 Jul 2023 01:05:06 +0800 Subject: [PATCH 0071/2093] net: dsa: fix value check in bcm_sf2_sw_probe() [ Upstream commit dadc5b86cc9459581f37fe755b431adc399ea393 ] in bcm_sf2_sw_probe(), check the return value of clk_prepare_enable() and return the error code if clk_prepare_enable() returns an unexpected value. Fixes: e9ec5c3bd238 ("net: dsa: bcm_sf2: request and handle clocks") Signed-off-by: Yuanjun Gong Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230726170506.16547-1-ruc_gongyuanjun@163.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/bcm_sf2.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index cde253d27bd0..72374b066f64 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1436,7 +1436,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; priv->clk_mdiv = devm_clk_get_optional(&pdev->dev, "sw_switch_mdiv"); if (IS_ERR(priv->clk_mdiv)) { @@ -1444,7 +1446,9 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) goto out_clk; } - clk_prepare_enable(priv->clk_mdiv); + ret = clk_prepare_enable(priv->clk_mdiv); + if (ret) + goto out_clk; ret = bcm_sf2_sw_rst(priv); if (ret) { From 22709d85373ffc6278c8961dfe43180e66355ecb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Georg=20M=C3=BCller?= Date: Fri, 28 Jul 2023 17:18:12 +0200 Subject: [PATCH 0072/2093] perf test uprobe_from_different_cu: Skip if there is no gcc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 98ce8e4a9dcfb448b30a2d7a16190f4a00382377 ] Without gcc, the test will fail. On cleanup, ignore probe removal errors. Otherwise, in case of an error adding the probe, the temporary directory is not removed. Fixes: 56cbeacf14353057 ("perf probe: Add test for regression introduced by switch to die_get_decl_file()") Signed-off-by: Georg Müller Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Georg Müller Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230728151812.454806-2-georgmueller@gmx.net Link: https://lore.kernel.org/r/CAP-5=fUP6UuLgRty3t2=fQsQi3k4hDMz415vWdp1x88QMvZ8ug@mail.gmail.com/ Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/tests/shell/test_uprobe_from_different_cu.sh | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh index 00d2e0e2e0c2..319f36ebb9a4 100644 --- a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -4,6 +4,12 @@ set -e +# skip if there's no gcc +if ! [ -x "$(command -v gcc)" ]; then + echo "failed: no gcc compiler" + exit 2 +fi + temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) cleanup() @@ -11,7 +17,7 @@ cleanup() trap - EXIT TERM INT if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then echo "--- Cleaning up ---" - perf probe -x ${temp_dir}/testfile -d foo + perf probe -x ${temp_dir}/testfile -d foo || true rm -f "${temp_dir}/"* rmdir "${temp_dir}" fi From d652c080b67caf227adfcf77c03cbaf7d0820cbc Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Wed, 26 Jul 2023 09:51:51 -0400 Subject: [PATCH 0073/2093] net: sched: cls_u32: Fix match key mis-addressing [ Upstream commit e68409db995380d1badacba41ff24996bd396171 ] A match entry is uniquely identified with an "address" or "path" in the form of: hashtable ID(12b):bucketid(8b):nodeid(12b). When creating table match entries all of hash table id, bucket id and node (match entry id) are needed to be either specified by the user or reasonable in-kernel defaults are used. The in-kernel default for a table id is 0x800(omnipresent root table); for bucketid it is 0x0. Prior to this fix there was none for a nodeid i.e. the code assumed that the user passed the correct nodeid and if the user passes a nodeid of 0 (as Mingi Cho did) then that is what was used. But nodeid of 0 is reserved for identifying the table. This is not a problem until we dump. The dump code notices that the nodeid is zero and assumes it is referencing a table and therefore references table struct tc_u_hnode instead of what was created i.e match entry struct tc_u_knode. Ming does an equivalent of: tc filter add dev dummy0 parent 10: prio 1 handle 0x1000 \ protocol ip u32 match ip src 10.0.0.1/32 classid 10:1 action ok Essentially specifying a table id 0, bucketid 1 and nodeid of zero Tableid 0 is remapped to the default of 0x800. Bucketid 1 is ignored and defaults to 0x00. Nodeid was assumed to be what Ming passed - 0x000 dumping before fix shows: ~$ tc filter ls dev dummy0 parent 10: filter protocol ip pref 1 u32 chain 0 filter protocol ip pref 1 u32 chain 0 fh 800: ht divisor 1 filter protocol ip pref 1 u32 chain 0 fh 800: ht divisor -30591 Note that the last line reports a table instead of a match entry (you can tell this because it says "ht divisor..."). As a result of reporting the wrong data type (misinterpretting of struct tc_u_knode as being struct tc_u_hnode) the divisor is reported with value of -30591. Ming identified this as part of the heap address (physmap_base is 0xffff8880 (-30591 - 1)). The fix is to ensure that when table entry matches are added and no nodeid is specified (i.e nodeid == 0) then we get the next available nodeid from the table's pool. After the fix, this is what the dump shows: $ tc filter ls dev dummy0 parent 10: filter protocol ip pref 1 u32 chain 0 filter protocol ip pref 1 u32 chain 0 fh 800: ht divisor 1 filter protocol ip pref 1 u32 chain 0 fh 800::800 order 2048 key ht 800 bkt 0 flowid 10:1 not_in_hw match 0a000001/ffffffff at 12 action order 1: gact action pass random type none pass val 0 index 1 ref 1 bind 1 Reported-by: Mingi Cho Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230726135151.416917-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/cls_u32.c | 56 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 50 insertions(+), 6 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 1280736a7b92..0e3bb1d65be1 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1022,18 +1022,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { + /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } - handle = htid | TC_U32_NODE(handle); - err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, - GFP_KERNEL); - if (err) - return err; - } else + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); From 3c42307abe97c5006f2875d38a896bb448080286 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Thu, 27 Jul 2023 08:56:19 +0000 Subject: [PATCH 0074/2093] mISDN: hfcpci: Fix potential deadlock on &hc->lock [ Upstream commit 56c6be35fcbed54279df0a2c9e60480a61841d6f ] As &hc->lock is acquired by both timer _hfcpci_softirq() and hardirq hfcpci_int(), the timer should disable irq before lock acquisition otherwise deadlock could happen if the timmer is preemtped by the hadr irq. Possible deadlock scenario: hfcpci_softirq() (timer) -> _hfcpci_softirq() -> spin_lock(&hc->lock); -> hfcpci_int() -> spin_lock(&hc->lock); (deadlock here) This flaw was found by an experimental static analysis tool I am developing for irq-related deadlock. The tentative patch fixes the potential deadlock by spin_lock_irq() in timer. Fixes: b36b654a7e82 ("mISDN: Create /sys/class/mISDN") Signed-off-by: Chengfeng Ye Link: https://lore.kernel.org/r/20230727085619.7419-1-dg573847474@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/isdn/hardware/mISDN/hfcpci.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index c0331b268010..fe391de1aba3 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -839,7 +839,7 @@ hfcpci_fill_fifo(struct bchannel *bch) *z1t = cpu_to_le16(new_z1); /* now send data */ if (bch->tx_idx < bch->tx_skb->len) return; - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); if (get_next_bframe(bch)) goto next_t_frame; return; @@ -895,7 +895,7 @@ hfcpci_fill_fifo(struct bchannel *bch) } bz->za[new_f1].z1 = cpu_to_le16(new_z1); /* for next buffer */ bz->f1 = new_f1; /* next frame */ - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); get_next_bframe(bch); } @@ -1119,7 +1119,7 @@ tx_birq(struct bchannel *bch) if (bch->tx_skb && bch->tx_idx < bch->tx_skb->len) hfcpci_fill_fifo(bch); else { - dev_kfree_skb(bch->tx_skb); + dev_kfree_skb_any(bch->tx_skb); if (get_next_bframe(bch)) hfcpci_fill_fifo(bch); } @@ -2277,7 +2277,7 @@ _hfcpci_softirq(struct device *dev, void *unused) return 0; if (hc->hw.int_m2 & HFCPCI_IRQ_ENABLE) { - spin_lock(&hc->lock); + spin_lock_irq(&hc->lock); bch = Sel_BCS(hc, hc->hw.bswapped ? 2 : 1); if (bch && bch->state == ISDN_P_B_RAW) { /* B1 rx&tx */ main_rec_hfcpci(bch); @@ -2288,7 +2288,7 @@ _hfcpci_softirq(struct device *dev, void *unused) main_rec_hfcpci(bch); tx_birq(bch); } - spin_unlock(&hc->lock); + spin_unlock_irq(&hc->lock); } return 0; } From 9da9ea9b132cbb9a5c4ff3d00214bd7064ca1a9a Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Thu, 27 Jul 2023 18:26:09 +0300 Subject: [PATCH 0075/2093] qed: Fix scheduling in a tasklet while getting stats [ Upstream commit e346e231b42bcae6822a6326acfb7b741e9e6026 ] Here we've got to a situation when tasklet called usleep_range() in PTT acquire logic, thus welcome to the "scheduling while atomic" BUG(). BUG: scheduling while atomic: swapper/24/0/0x00000100 [] schedule+0x29/0x70 [] schedule_hrtimeout_range_clock+0xb2/0x150 [] schedule_hrtimeout_range+0x13/0x20 [] usleep_range+0x4f/0x70 [] qed_ptt_acquire+0x38/0x100 [qed] [] _qed_get_vport_stats+0x458/0x580 [qed] [] qed_get_vport_stats+0x1c/0xd0 [qed] [] qed_get_protocol_stats+0x93/0x100 [qed] qed_mcp_send_protocol_stats case MFW_DRV_MSG_GET_LAN_STATS: case MFW_DRV_MSG_GET_FCOE_STATS: case MFW_DRV_MSG_GET_ISCSI_STATS: case MFW_DRV_MSG_GET_RDMA_STATS: [] qed_mcp_handle_events+0x2d8/0x890 [qed] qed_int_assertion qed_int_attentions [] qed_int_sp_dpc+0xa50/0xdc0 [qed] [] tasklet_action+0x83/0x140 [] __do_softirq+0x125/0x2bb [] call_softirq+0x1c/0x30 [] do_softirq+0x65/0xa0 [] irq_exit+0x105/0x110 [] do_IRQ+0x56/0xf0 Fix this by making caller to provide the context whether it could be in atomic context flow or not when getting stats from QED driver. QED driver based on the context provided decide to schedule out or not when acquiring the PTT BAR window. We faced the BUG_ON() while getting vport stats, but according to the code same issue could happen for fcoe and iscsi statistics as well, so fixing them too. Fixes: 6c75424612a7 ("qed: Add support for NCSI statistics.") Fixes: 1e128c81290a ("qed: Add support for hardware offloaded FCoE.") Fixes: 2f2b2614e893 ("qed: Provide iSCSI statistics to management") Cc: Sudarsana Kalluru Cc: David Miller Cc: Manish Chopra Signed-off-by: Konstantin Khorenko Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_dev_api.h | 16 ++++++++++++ drivers/net/ethernet/qlogic/qed/qed_fcoe.c | 19 ++++++++++---- drivers/net/ethernet/qlogic/qed/qed_fcoe.h | 17 ++++++++++-- drivers/net/ethernet/qlogic/qed/qed_hw.c | 26 ++++++++++++++++--- drivers/net/ethernet/qlogic/qed/qed_iscsi.c | 19 ++++++++++---- drivers/net/ethernet/qlogic/qed/qed_iscsi.h | 8 ++++-- drivers/net/ethernet/qlogic/qed/qed_l2.c | 19 ++++++++++---- drivers/net/ethernet/qlogic/qed/qed_l2.h | 24 +++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_main.c | 6 ++--- 9 files changed, 128 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index f8682356d0cf..94d4f9413ab7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -193,6 +193,22 @@ void qed_hw_remove(struct qed_dev *cdev); */ struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn); +/** + * qed_ptt_acquire_context(): Allocate a PTT window honoring the context + * atomicy. + * + * @p_hwfn: HW device data. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: struct qed_ptt. + * + * Should be called at the entry point to the driver + * (at the beginning of an exported function). + */ +struct qed_ptt *qed_ptt_acquire_context(struct qed_hwfn *p_hwfn, + bool is_atomic); + /** * qed_ptt_release(): Release PTT Window. * diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index 3764190b948e..04602ac94708 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -693,13 +693,14 @@ static void _qed_fcoe_get_pstats(struct qed_hwfn *p_hwfn, } static int qed_fcoe_get_stats(struct qed_hwfn *p_hwfn, - struct qed_fcoe_stats *p_stats) + struct qed_fcoe_stats *p_stats, + bool is_atomic) { struct qed_ptt *p_ptt; memset(p_stats, 0, sizeof(*p_stats)); - p_ptt = qed_ptt_acquire(p_hwfn); + p_ptt = qed_ptt_acquire_context(p_hwfn, is_atomic); if (!p_ptt) { DP_ERR(p_hwfn, "Failed to acquire ptt\n"); @@ -973,19 +974,27 @@ static int qed_fcoe_destroy_conn(struct qed_dev *cdev, QED_SPQ_MODE_EBLOCK, NULL); } +static int qed_fcoe_stats_context(struct qed_dev *cdev, + struct qed_fcoe_stats *stats, + bool is_atomic) +{ + return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats, is_atomic); +} + static int qed_fcoe_stats(struct qed_dev *cdev, struct qed_fcoe_stats *stats) { - return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats); + return qed_fcoe_stats_context(cdev, stats, false); } void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats) + struct qed_mcp_fcoe_stats *stats, + bool is_atomic) { struct qed_fcoe_stats proto_stats; /* Retrieve FW statistics */ memset(&proto_stats, 0, sizeof(proto_stats)); - if (qed_fcoe_stats(cdev, &proto_stats)) { + if (qed_fcoe_stats_context(cdev, &proto_stats, is_atomic)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Failed to collect FCoE statistics\n"); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h index 19c85adf4ceb..214e8299ecb4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.h +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.h @@ -28,8 +28,20 @@ int qed_fcoe_alloc(struct qed_hwfn *p_hwfn); void qed_fcoe_setup(struct qed_hwfn *p_hwfn); void qed_fcoe_free(struct qed_hwfn *p_hwfn); +/** + * qed_get_protocol_stats_fcoe(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: Void. + */ void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats); + struct qed_mcp_fcoe_stats *stats, + bool is_atomic); #else /* CONFIG_QED_FCOE */ static inline int qed_fcoe_alloc(struct qed_hwfn *p_hwfn) { @@ -40,7 +52,8 @@ static inline void qed_fcoe_setup(struct qed_hwfn *p_hwfn) {} static inline void qed_fcoe_free(struct qed_hwfn *p_hwfn) {} static inline void qed_get_protocol_stats_fcoe(struct qed_dev *cdev, - struct qed_mcp_fcoe_stats *stats) + struct qed_mcp_fcoe_stats *stats, + bool is_atomic) { } #endif /* CONFIG_QED_FCOE */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c index 554f30b0cfd5..6263f847b6b9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.c +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c @@ -23,7 +23,10 @@ #include "qed_reg_addr.h" #include "qed_sriov.h" -#define QED_BAR_ACQUIRE_TIMEOUT 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_USLEEP_CNT 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_USLEEP 1000 +#define QED_BAR_ACQUIRE_TIMEOUT_UDELAY_CNT 100000 +#define QED_BAR_ACQUIRE_TIMEOUT_UDELAY 10 /* Invalid values */ #define QED_BAR_INVALID_OFFSET (cpu_to_le32(-1)) @@ -84,12 +87,22 @@ void qed_ptt_pool_free(struct qed_hwfn *p_hwfn) } struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn) +{ + return qed_ptt_acquire_context(p_hwfn, false); +} + +struct qed_ptt *qed_ptt_acquire_context(struct qed_hwfn *p_hwfn, bool is_atomic) { struct qed_ptt *p_ptt; - unsigned int i; + unsigned int i, count; + + if (is_atomic) + count = QED_BAR_ACQUIRE_TIMEOUT_UDELAY_CNT; + else + count = QED_BAR_ACQUIRE_TIMEOUT_USLEEP_CNT; /* Take the free PTT from the list */ - for (i = 0; i < QED_BAR_ACQUIRE_TIMEOUT; i++) { + for (i = 0; i < count; i++) { spin_lock_bh(&p_hwfn->p_ptt_pool->lock); if (!list_empty(&p_hwfn->p_ptt_pool->free_list)) { @@ -105,7 +118,12 @@ struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn) } spin_unlock_bh(&p_hwfn->p_ptt_pool->lock); - usleep_range(1000, 2000); + + if (is_atomic) + udelay(QED_BAR_ACQUIRE_TIMEOUT_UDELAY); + else + usleep_range(QED_BAR_ACQUIRE_TIMEOUT_USLEEP, + QED_BAR_ACQUIRE_TIMEOUT_USLEEP * 2); } DP_NOTICE(p_hwfn, "PTT acquire timeout - failed to allocate PTT\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 511ab214eb9c..980e7289b481 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -999,13 +999,14 @@ static void _qed_iscsi_get_pstats(struct qed_hwfn *p_hwfn, } static int qed_iscsi_get_stats(struct qed_hwfn *p_hwfn, - struct qed_iscsi_stats *stats) + struct qed_iscsi_stats *stats, + bool is_atomic) { struct qed_ptt *p_ptt; memset(stats, 0, sizeof(*stats)); - p_ptt = qed_ptt_acquire(p_hwfn); + p_ptt = qed_ptt_acquire_context(p_hwfn, is_atomic); if (!p_ptt) { DP_ERR(p_hwfn, "Failed to acquire ptt\n"); return -EAGAIN; @@ -1336,9 +1337,16 @@ static int qed_iscsi_destroy_conn(struct qed_dev *cdev, QED_SPQ_MODE_EBLOCK, NULL); } +static int qed_iscsi_stats_context(struct qed_dev *cdev, + struct qed_iscsi_stats *stats, + bool is_atomic) +{ + return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats, is_atomic); +} + static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats) { - return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats); + return qed_iscsi_stats_context(cdev, stats, false); } static int qed_iscsi_change_mac(struct qed_dev *cdev, @@ -1358,13 +1366,14 @@ static int qed_iscsi_change_mac(struct qed_dev *cdev, } void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats) + struct qed_mcp_iscsi_stats *stats, + bool is_atomic) { struct qed_iscsi_stats proto_stats; /* Retrieve FW statistics */ memset(&proto_stats, 0, sizeof(proto_stats)); - if (qed_iscsi_stats(cdev, &proto_stats)) { + if (qed_iscsi_stats_context(cdev, &proto_stats, is_atomic)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Failed to collect ISCSI statistics\n"); return; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h index dec2b00259d4..974cb8d26608 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h @@ -39,11 +39,14 @@ void qed_iscsi_free(struct qed_hwfn *p_hwfn); * * @cdev: Qed dev pointer. * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. * + * Context: The function should not sleep in case is_atomic == true. * Return: Void. */ void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats); + struct qed_mcp_iscsi_stats *stats, + bool is_atomic); #else /* IS_ENABLED(CONFIG_QED_ISCSI) */ static inline int qed_iscsi_alloc(struct qed_hwfn *p_hwfn) { @@ -56,7 +59,8 @@ static inline void qed_iscsi_free(struct qed_hwfn *p_hwfn) {} static inline void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, - struct qed_mcp_iscsi_stats *stats) {} + struct qed_mcp_iscsi_stats *stats, + bool is_atomic) {} #endif /* IS_ENABLED(CONFIG_QED_ISCSI) */ #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 7776d3bdd459..970b9aabbc3d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1863,7 +1863,8 @@ static void __qed_get_vport_stats(struct qed_hwfn *p_hwfn, } static void _qed_get_vport_stats(struct qed_dev *cdev, - struct qed_eth_stats *stats) + struct qed_eth_stats *stats, + bool is_atomic) { u8 fw_vport = 0; int i; @@ -1872,10 +1873,11 @@ static void _qed_get_vport_stats(struct qed_dev *cdev, for_each_hwfn(cdev, i) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; - struct qed_ptt *p_ptt = IS_PF(cdev) ? qed_ptt_acquire(p_hwfn) - : NULL; + struct qed_ptt *p_ptt; bool b_get_port_stats; + p_ptt = IS_PF(cdev) ? qed_ptt_acquire_context(p_hwfn, is_atomic) + : NULL; if (IS_PF(cdev)) { /* The main vport index is relative first */ if (qed_fw_vport(p_hwfn, 0, &fw_vport)) { @@ -1900,6 +1902,13 @@ static void _qed_get_vport_stats(struct qed_dev *cdev, } void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) +{ + qed_get_vport_stats_context(cdev, stats, false); +} + +void qed_get_vport_stats_context(struct qed_dev *cdev, + struct qed_eth_stats *stats, + bool is_atomic) { u32 i; @@ -1908,7 +1917,7 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) return; } - _qed_get_vport_stats(cdev, stats); + _qed_get_vport_stats(cdev, stats, is_atomic); if (!cdev->reset_stats) return; @@ -1960,7 +1969,7 @@ void qed_reset_vport_stats(struct qed_dev *cdev) if (!cdev->reset_stats) { DP_INFO(cdev, "Reset stats not allocated\n"); } else { - _qed_get_vport_stats(cdev, cdev->reset_stats); + _qed_get_vport_stats(cdev, cdev->reset_stats, false); cdev->reset_stats->common.link_change_count = 0; } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index a538cf478c14..2d2f82c785ad 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -249,8 +249,32 @@ qed_sp_eth_rx_queues_update(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data); +/** + * qed_get_vport_stats(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * + * Return: Void. + */ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats); +/** + * qed_get_vport_stats_context(): Fills provided statistics + * struct with statistics. + * + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * @is_atomic: Hint from the caller - if the func can sleep or not. + * + * Context: The function should not sleep in case is_atomic == true. + * Return: Void. + */ +void qed_get_vport_stats_context(struct qed_dev *cdev, + struct qed_eth_stats *stats, + bool is_atomic); + void qed_reset_vport_stats(struct qed_dev *cdev); /** diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index c91898be7c03..25d9c254288b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -3101,7 +3101,7 @@ void qed_get_protocol_stats(struct qed_dev *cdev, switch (type) { case QED_MCP_LAN_STATS: - qed_get_vport_stats(cdev, ð_stats); + qed_get_vport_stats_context(cdev, ð_stats, true); stats->lan_stats.ucast_rx_pkts = eth_stats.common.rx_ucast_pkts; stats->lan_stats.ucast_tx_pkts = @@ -3109,10 +3109,10 @@ void qed_get_protocol_stats(struct qed_dev *cdev, stats->lan_stats.fcs_err = -1; break; case QED_MCP_FCOE_STATS: - qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats); + qed_get_protocol_stats_fcoe(cdev, &stats->fcoe_stats, true); break; case QED_MCP_ISCSI_STATS: - qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats); + qed_get_protocol_stats_iscsi(cdev, &stats->iscsi_stats, true); break; default: DP_VERBOSE(cdev, QED_MSG_SP, From 60d92bc9c0940a8492a025b54224b6f063932736 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:08 +0000 Subject: [PATCH 0076/2093] net: annotate data-races around sk->sk_reserved_mem [ Upstream commit fe11fdcb4207907d80cda2e73777465d68131e66 ] sk_getsockopt() runs locklessly. This means sk->sk_reserved_mem can be read while other threads are changing its value. Add missing annotations where they are needed. Fixes: 2bb2f5fb21b0 ("net: add new socket option SO_RESERVE_MEM") Signed-off-by: Eric Dumazet Cc: Wei Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 0c1baa5517f1..9483820833c5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -996,7 +996,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes) bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); - sk->sk_reserved_mem -= bytes; + WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } @@ -1033,7 +1033,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) } sk->sk_forward_alloc += pages << PAGE_SHIFT; - sk->sk_reserved_mem += pages << PAGE_SHIFT; + WRITE_ONCE(sk->sk_reserved_mem, + sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } @@ -1922,7 +1923,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RESERVE_MEM: - v.val = sk->sk_reserved_mem; + v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: From 0317c8322d9ac86a2bf251f94efc7fe96643e0fb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:09 +0000 Subject: [PATCH 0077/2093] net: annotate data-race around sk->sk_txrehash [ Upstream commit c76a0328899bbe226f8adeb88b8da9e4167bd316 ] sk_getsockopt() runs locklessly. This means sk->sk_txrehash can be read while other threads are changing its value. Other locations were handled in commit cb6cd2cec799 ("tcp: Change SYN ACK retransmit behaviour to account for rehash") Fixes: 26859240e4ee ("txhash: Add socket option to control TX hash rethink behavior") Signed-off-by: Eric Dumazet Cc: Akhmat Karakotov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 9483820833c5..77abd69c56dd 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1521,7 +1521,9 @@ int sk_setsockopt(struct sock *sk, int level, int optname, } if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* Paired with READ_ONCE() in tcp_rtx_synack() */ + /* Paired with READ_ONCE() in tcp_rtx_synack() + * and sk_getsockopt(). + */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -1927,7 +1929,8 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_TXREHASH: - v.val = sk->sk_txrehash; + /* Paired with WRITE_ONCE() in sk_setsockopt() */ + v.val = READ_ONCE(sk->sk_txrehash); break; default: From be43c8f1c9164adc14dbcaf06bb5ab921d82586a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:10 +0000 Subject: [PATCH 0078/2093] net: annotate data-races around sk->sk_max_pacing_rate [ Upstream commit ea7f45ef77b39e72244d282e47f6cb1ef4135cd2 ] sk_getsockopt() runs locklessly. This means sk->sk_max_pacing_rate can be read while other threads are changing its value. Fixes: 62748f32d501 ("net: introduce SO_MAX_PACING_RATE") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 77abd69c56dd..86e88de1238b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1426,7 +1426,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname, cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = ulval; + /* Pairs with READ_ONCE() from sk_getsockopt() */ + WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } @@ -1852,12 +1853,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #endif case SO_MAX_PACING_RATE: + /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); - v.ulval = sk->sk_max_pacing_rate; + v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ - v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + v.val = min_t(unsigned long, ~0U, + READ_ONCE(sk->sk_max_pacing_rate)); } break; From 0a40103c9191ed3555d5a656b8df16341f8f43fe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:11 +0000 Subject: [PATCH 0079/2093] net: add missing READ_ONCE(sk->sk_rcvlowat) annotation [ Upstream commit e6d12bdb435d23ff6c1890c852d85408a2f496ee ] In a prior commit, I forgot to change sk_getsockopt() when reading sk->sk_rcvlowat locklessly. Fixes: eac66402d1c3 ("net: annotate sk->sk_rcvlowat lockless reads") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index 86e88de1238b..1b1fe67b94d4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1717,7 +1717,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; + v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: From 10c832159622dafa50029cb2e89781bd547cb1e8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:13 +0000 Subject: [PATCH 0080/2093] net: add missing READ_ONCE(sk->sk_sndbuf) annotation [ Upstream commit 74bc084327c643499474ba75df485607da37dd6e ] In a prior commit, I forgot to change sk_getsockopt() when reading sk->sk_sndbuf locklessly. Fixes: e292f05e0df7 ("tcp: annotate sk->sk_sndbuf lockless reads") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index 1b1fe67b94d4..04306ccdf908 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1624,7 +1624,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_SNDBUF: - v.val = sk->sk_sndbuf; + v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: From c7bb6860645f83134842e27a2fd1c1449edc5d80 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:14 +0000 Subject: [PATCH 0081/2093] net: add missing READ_ONCE(sk->sk_rcvbuf) annotation [ Upstream commit b4b553253091cafe9ec38994acf42795e073bef5 ] In a prior commit, I forgot to change sk_getsockopt() when reading sk->sk_rcvbuf locklessly. Fixes: ebb3b78db7bf ("tcp: annotate sk->sk_rcvbuf lockless reads") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index 04306ccdf908..1a2ec2c4cfe2 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1628,7 +1628,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_RCVBUF: - v.val = sk->sk_rcvbuf; + v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: From b53468041d20177c8b8808d1891c0145718ceadf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:15 +0000 Subject: [PATCH 0082/2093] net: annotate data-races around sk->sk_mark [ Upstream commit 3c5b4d69c358a9275a8de98f87caf6eda644b086 ] sk->sk_mark is often read while another thread could change the value. Fixes: 4a19ec5800fc ("[NET]: Introducing socket mark socket option.") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/inet_sock.h | 7 ++++--- include/net/ip.h | 2 +- include/net/route.h | 4 ++-- net/core/sock.c | 4 ++-- net/dccp/ipv6.c | 4 ++-- net/ipv4/inet_diag.c | 4 ++-- net/ipv4/ip_output.c | 4 ++-- net/ipv4/route.c | 4 ++-- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/ping.c | 2 +- net/ipv6/raw.c | 4 ++-- net/ipv6/route.c | 7 ++++--- net/ipv6/tcp_ipv6.c | 6 +++--- net/ipv6/udp.c | 4 ++-- net/l2tp/l2tp_ip6.c | 2 +- net/mptcp/sockopt.c | 2 +- net/netfilter/nft_socket.c | 2 +- net/netfilter/xt_socket.c | 4 ++-- net/packet/af_packet.c | 6 +++--- net/smc/af_smc.c | 2 +- net/xdp/xsk.c | 2 +- net/xfrm/xfrm_policy.c | 2 +- 22 files changed, 41 insertions(+), 39 deletions(-) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 51857117ac09..c8ef3b881f03 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -107,11 +107,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) + u32 mark = READ_ONCE(sk->sk_mark); + + if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; - return sk->sk_mark; + return mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, diff --git a/include/net/ip.h b/include/net/ip.h index 83a1a9bc3ceb..530e7257e438 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, { ipcm_init(ipcm); - ipcm->sockc.mark = inet->sk.sk_mark; + ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; diff --git a/include/net/route.h b/include/net/route.h index fe00b0a2e475..af8431b25f80 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -171,7 +171,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) { - flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos, + flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos, RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, daddr, saddr, dport, sport, sock_net_uid(net, sk)); @@ -304,7 +304,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk), + flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), protocol, flow_flags, dst, src, dport, sport, sk->sk_uid); } diff --git a/net/core/sock.c b/net/core/sock.c index 1a2ec2c4cfe2..4dd13d34e474 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -977,7 +977,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { - sk->sk_mark = val; + WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } @@ -1796,7 +1796,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len); case SO_MARK: - v.val = sk->sk_mark; + v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c0fd8f5f3b94..b51ce6f8ceba 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -237,8 +237,8 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass, - sk->sk_priority); + err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, + np->tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index b812eb36f0e3..f7426926a104 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, } #endif - if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark))) goto errout; if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || @@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; if (sk_fullsock(sk)) - entry.mark = sk->sk_mark; + entry.mark = READ_ONCE(sk->sk_mark); else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else if (sk->sk_state == TCP_TIME_WAIT) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7b4ab545c06e..99d8cdbfd9ab 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -184,7 +184,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, skb->priority = sk->sk_priority; if (!skb->mark) - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -527,7 +527,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cd1fa9f70f1a..51bd9a50a1d1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; @@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; - flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9a8d59e9303a..23b4f93afb28 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -931,7 +931,7 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(ipv4_tcp_sk); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 4651aaf70db4..4d5a27dd9a4b 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -120,7 +120,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init_sk(&ipc6, np); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 33852fc38ad9..e8675e5b5d00 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -772,12 +772,12 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0b060cb8681f..960ab43a49c4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2952,7 +2952,8 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); - ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid); + ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), + sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || @@ -3173,8 +3174,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark, - sk->sk_uid); + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d9253aa764fa..039aa51390ae 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -567,8 +567,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, - tclass, sk->sk_priority); + err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), + opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -943,7 +943,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else - mark = sk->sk_mark; + mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), true); } if (txhash) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04f1d696503c..27348172b25b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -622,7 +622,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), - sk->sk_mark, sk->sk_uid); + READ_ONCE(sk->sk_mark), sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } @@ -1350,7 +1350,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; - ipc6.sockc.mark = sk->sk_mark; + ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ if (sin6) { diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 5137ea1861ce..bce4132b0a5c 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -519,7 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Get and verify the address */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 696ba398d699..937bd4c55615 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -102,7 +102,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { - ssk->sk_mark = sk->sk_mark; + WRITE_ONCE(ssk->sk_mark, sk->sk_mark); sk_dst_reset(ssk); } break; diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 49a5348a6a14..777561b71fcb 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -107,7 +107,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { - *dest = sk->sk_mark; + *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; return; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 7013f55f05d1..76e01f292aaf 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -77,7 +77,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); @@ -138,7 +138,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) - pskb->mark = sk->sk_mark; + pskb->mark = READ_ONCE(sk->sk_mark); if (sk != skb->sk) sock_gen_put(sk); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6ab9d5b54338..30a28c1ff928 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2053,7 +2053,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); @@ -2576,7 +2576,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; skb->priority = po->sk.sk_priority; - skb->mark = po->sk.sk_mark; + skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -2978,7 +2978,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; sockcm_init(&sockc, sk); - sockc.mark = sk->sk_mark; + sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 02d1daae7739..5ae0a54a823b 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -447,7 +447,7 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, nsk->sk_rcvbuf = osk->sk_rcvbuf; nsk->sk_sndtimeo = osk->sk_sndtimeo; nsk->sk_rcvtimeo = osk->sk_rcvtimeo; - nsk->sk_mark = osk->sk_mark; + nsk->sk_mark = READ_ONCE(osk->sk_mark); nsk->sk_priority = osk->sk_priority; nsk->sk_rcvlowat = osk->sk_rcvlowat; nsk->sk_bound_dev_if = osk->sk_bound_dev_if; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 371d269d22fa..22bf10ffbf2d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -504,7 +504,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->dev = dev; skb->priority = xs->sk.sk_priority; - skb->mark = xs->sk.sk_mark; + skb->mark = READ_ONCE(xs->sk.sk_mark); skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; skb->destructor = xsk_destruct_skb; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7b1b93584bdb..e65de78cb61b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2174,7 +2174,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; From dd7a1ff07c6c741e6d56e65316f57835ed750eca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:16 +0000 Subject: [PATCH 0083/2093] net: add missing data-race annotations around sk->sk_peek_off [ Upstream commit 11695c6e966b0ec7ed1d16777d294cef865a5c91 ] sk_getsockopt() runs locklessly, thus we need to annotate the read of sk->sk_peek_off. While we are at it, add corresponding annotations to sk_set_peek_off() and unix_set_peek_off(). Fixes: b9bb53f3836f ("sock: convert sk_peek_offset functions to WRITE_ONCE") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 4 ++-- net/unix/af_unix.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 4dd13d34e474..61bbe6263f98 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1815,7 +1815,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, if (!sock->ops->set_peek_off) return -EOPNOTSUPP; - v.val = sk->sk_peek_off; + v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); @@ -3119,7 +3119,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5b19b6c53a2c..78fa620a6398 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -779,7 +779,7 @@ static int unix_set_peek_off(struct sock *sk, int val) if (mutex_lock_interruptible(&u->iolock)) return -EINTR; - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); mutex_unlock(&u->iolock); return 0; From 6326c83ee27ef9141ebfe730b7459534d2417870 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:17 +0000 Subject: [PATCH 0084/2093] net: add missing data-race annotation for sk_ll_usec [ Upstream commit e5f0d2dd3c2faa671711dac6d3ff3cef307bcfe3 ] In a prior commit I forgot that sk_getsockopt() reads sk->sk_ll_usec without holding a lock. Fixes: 0dbffbb5335a ("net: annotate data race around sk_ll_usec") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index 61bbe6263f98..ff52d51dfe2c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1845,7 +1845,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: - v.val = sk->sk_ll_usec; + v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); From 12d4ba18142434949977f7de9225847fd7147876 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:18 +0000 Subject: [PATCH 0085/2093] net: annotate data-races around sk->sk_priority [ Upstream commit 8bf43be799d4b242ea552a14db10456446be843e ] sk_getsockopt() runs locklessly. This means sk->sk_priority can be read while other threads are changing its value. Other reads also happen without socket lock being held. Add missing annotations where needed. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 6 +++--- net/ipv4/ip_output.c | 4 ++-- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/tcp_ipv6.c | 3 ++- net/packet/af_packet.c | 6 +++--- 8 files changed, 14 insertions(+), 13 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index ff52d51dfe2c..3b5304f084ef 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -800,7 +800,7 @@ EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); - sk->sk_priority = priority; + WRITE_ONCE(sk->sk_priority, priority); release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); @@ -1203,7 +1203,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname, if ((val >= 0 && val <= 6) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) - sk->sk_priority = val; + WRITE_ONCE(sk->sk_priority, val); else ret = -EPERM; break; @@ -1670,7 +1670,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_PRIORITY: - v.val = sk->sk_priority; + v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 99d8cdbfd9ab..acfe58d2f1dd 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,7 +182,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, ip_options_build(skb, &opt->opt, daddr, rt); } - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) skb->mark = READ_ONCE(sk->sk_mark); @@ -526,7 +526,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index a7fd035b5b4f..63aa52becd88 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -591,7 +591,7 @@ void __ip_sock_set_tos(struct sock *sk, int val) } if (inet_sk(sk)->tos != val) { inet_sk(sk)->tos = val; - sk->sk_priority = rt_tos2priority(val); + WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 86197634dcf5..639aa5abda9d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -346,7 +346,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 23b4f93afb28..08921b96f972 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -933,7 +933,7 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_priority : sk->sk_priority; + inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e8675e5b5d00..df3abd9e5237 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -612,7 +612,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 039aa51390ae..4bdd356bb5c4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1132,7 +1132,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, + ipv6_get_dsfield(ipv6_hdr(skb)), 0, + READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 30a28c1ff928..168106840073 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2052,7 +2052,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; @@ -2575,7 +2575,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; - skb->priority = po->sk.sk_priority; + skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); @@ -3052,7 +3052,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->protocol = proto; skb->dev = dev; - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; From 0b45af982a4df0b14fb8669ee2a871cfdfa6a39c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 28 Jul 2023 17:07:05 -0700 Subject: [PATCH 0086/2093] net/sched: taprio: Limit TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME to INT_MAX. [ Upstream commit e739718444f7bf2fa3d70d101761ad83056ca628 ] syzkaller found zero division error [0] in div_s64_rem() called from get_cycle_time_elapsed(), where sched->cycle_time is the divisor. We have tests in parse_taprio_schedule() so that cycle_time will never be 0, and actually cycle_time is not 0 in get_cycle_time_elapsed(). The problem is that the types of divisor are different; cycle_time is s64, but the argument of div_s64_rem() is s32. syzkaller fed this input and 0x100000000 is cast to s32 to be 0. @TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME={0xc, 0x8, 0x100000000} We use s64 for cycle_time to cast it to ktime_t, so let's keep it and set max for cycle_time. While at it, we prevent overflow in setup_txtime() and add another test in parse_taprio_schedule() to check if cycle_time overflows. Also, we add a new tdc test case for this issue. [0]: divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 1 PID: 103 Comm: kworker/1:3 Not tainted 6.5.0-rc1-00330-g60cc1f7d0605 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:div_s64_rem include/linux/math64.h:42 [inline] RIP: 0010:get_cycle_time_elapsed net/sched/sch_taprio.c:223 [inline] RIP: 0010:find_entry_to_transmit+0x252/0x7e0 net/sched/sch_taprio.c:344 Code: 3c 02 00 0f 85 5e 05 00 00 48 8b 4c 24 08 4d 8b bd 40 01 00 00 48 8b 7c 24 48 48 89 c8 4c 29 f8 48 63 f7 48 99 48 89 74 24 70 <48> f7 fe 48 29 d1 48 8d 04 0f 49 89 cc 48 89 44 24 20 49 8d 85 10 RSP: 0018:ffffc90000acf260 EFLAGS: 00010206 RAX: 177450e0347560cf RBX: 0000000000000000 RCX: 177450e0347560cf RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000100000000 RBP: 0000000000000056 R08: 0000000000000000 R09: ffffed10020a0934 R10: ffff8880105049a7 R11: ffff88806cf3a520 R12: ffff888010504800 R13: ffff88800c00d800 R14: ffff8880105049a0 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88806cf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f0edf84f0e8 CR3: 000000000d73c002 CR4: 0000000000770ee0 PKRU: 55555554 Call Trace: get_packet_txtime net/sched/sch_taprio.c:508 [inline] taprio_enqueue_one+0x900/0xff0 net/sched/sch_taprio.c:577 taprio_enqueue+0x378/0xae0 net/sched/sch_taprio.c:658 dev_qdisc_enqueue+0x46/0x170 net/core/dev.c:3732 __dev_xmit_skb net/core/dev.c:3821 [inline] __dev_queue_xmit+0x1b2f/0x3000 net/core/dev.c:4169 dev_queue_xmit include/linux/netdevice.h:3088 [inline] neigh_resolve_output net/core/neighbour.c:1552 [inline] neigh_resolve_output+0x4a7/0x780 net/core/neighbour.c:1532 neigh_output include/net/neighbour.h:544 [inline] ip6_finish_output2+0x924/0x17d0 net/ipv6/ip6_output.c:135 __ip6_finish_output+0x620/0xaa0 net/ipv6/ip6_output.c:196 ip6_finish_output net/ipv6/ip6_output.c:207 [inline] NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip6_output+0x206/0x410 net/ipv6/ip6_output.c:228 dst_output include/net/dst.h:458 [inline] NF_HOOK.constprop.0+0xea/0x260 include/linux/netfilter.h:303 ndisc_send_skb+0x872/0xe80 net/ipv6/ndisc.c:508 ndisc_send_ns+0xb5/0x130 net/ipv6/ndisc.c:666 addrconf_dad_work+0xc14/0x13f0 net/ipv6/addrconf.c:4175 process_one_work+0x92c/0x13a0 kernel/workqueue.c:2597 worker_thread+0x60f/0x1240 kernel/workqueue.c:2748 kthread+0x2fe/0x3f0 kernel/kthread.c:389 ret_from_fork+0x2c/0x50 arch/x86/entry/entry_64.S:308 Modules linked in: Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Co-developed-by: Eric Dumazet Co-developed-by: Pedro Tammela Acked-by: Vinicius Costa Gomes Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/sch_taprio.c | 15 +++++++++-- .../tc-testing/tc-tests/qdiscs/taprio.json | 25 +++++++++++++++++++ 2 files changed, 38 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index a274a9332f33..8d5eebb2dd1b 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -769,6 +769,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, }; +static struct netlink_range_validation_signed taprio_cycle_time_range = { + .min = 0, + .max = INT_MAX, +}; + static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) @@ -777,7 +782,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, - [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = + NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, @@ -913,6 +919,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, return -EINVAL; } + if (cycle < 0 || cycle > INT_MAX) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); + return -EINVAL; + } + new->cycle_time = cycle; } @@ -1110,7 +1121,7 @@ static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; - u32 interval = 0; + u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index a44455372646..08d4861c2e78 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -131,5 +131,30 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] + }, + { + "id": "3e1e", + "name": "Add taprio Qdisc with an invalid cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle 1: taprio num_tc 3 map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@0 1@0 base-time 1000000000 sched-entry S 01 300000 flags 0x1 clockid CLOCK_TAI cycle-time 4294967296 || /bin/true", + "$IP link set dev $ETH up", + "$IP addr add 10.10.10.10/24 dev $ETH" + ], + "cmdUnderTest": "/bin/true", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] } ] From 4461b2cae3262279f254b3cd0f02d4323b1acc01 Mon Sep 17 00:00:00 2001 From: Rafal Rogalski Date: Fri, 28 Jul 2023 10:12:43 -0700 Subject: [PATCH 0087/2093] ice: Fix RDMA VSI removal during queue rebuild [ Upstream commit 4b31fd4d77ffa430d0b74ba1885ea0a41594f202 ] During qdisc create/delete, it is necessary to rebuild the queue of VSIs. An error occurred because the VSIs created by RDMA were still active. Added check if RDMA is active. If yes, it disallows qdisc changes and writes a message in the system logs. Fixes: 348048e724a0 ("ice: Implement iidc operations") Signed-off-by: Rafal Rogalski Signed-off-by: Mateusz Palczewski Signed-off-by: Kamil Maziarz Tested-by: Bharathi Sreenivas Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230728171243.2446101-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_main.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8f77088900e9..a771e597795d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8777,6 +8777,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_pf *pf = np->vsi->back; + bool locked = false; int err; switch (type) { @@ -8786,10 +8787,27 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, ice_setup_tc_block_cb, np, np, true); case TC_SETUP_QDISC_MQPRIO: + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); + err = -EBUSY; + goto adev_unlock; + } + } + /* setup traffic classifier for receive side */ mutex_lock(&pf->tc_mutex); err = ice_setup_tc_mqprio_qdisc(netdev, type_data); mutex_unlock(&pf->tc_mutex); + +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } return err; default: return -EOPNOTSUPP; From cbd000451885801e9bbfd9cf7a7946806a85cb5e Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Sat, 29 Jul 2023 17:51:07 +0800 Subject: [PATCH 0088/2093] bpf, cpumap: Handle skb as well when clean up ptr_ring [ Upstream commit 7c62b75cd1a792e14b037fa4f61f9b18914e7de1 ] The following warning was reported when running xdp_redirect_cpu with both skb-mode and stress-mode enabled: ------------[ cut here ]------------ Incorrect XDP memory type (-2128176192) usage WARNING: CPU: 7 PID: 1442 at net/core/xdp.c:405 Modules linked in: CPU: 7 PID: 1442 Comm: kworker/7:0 Tainted: G 6.5.0-rc2+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: events __cpu_map_entry_free RIP: 0010:__xdp_return+0x1e4/0x4a0 ...... Call Trace: ? show_regs+0x65/0x70 ? __warn+0xa5/0x240 ? __xdp_return+0x1e4/0x4a0 ...... xdp_return_frame+0x4d/0x150 __cpu_map_entry_free+0xf9/0x230 process_one_work+0x6b0/0xb80 worker_thread+0x96/0x720 kthread+0x1a5/0x1f0 ret_from_fork+0x3a/0x70 ret_from_fork_asm+0x1b/0x30 The reason for the warning is twofold. One is due to the kthread cpu_map_kthread_run() is stopped prematurely. Another one is __cpu_map_ring_cleanup() doesn't handle skb mode and treats skbs in ptr_ring as XDP frames. Prematurely-stopped kthread will be fixed by the preceding patch and ptr_ring will be empty when __cpu_map_ring_cleanup() is called. But as the comments in __cpu_map_ring_cleanup() said, handling and freeing skbs in ptr_ring as well to "catch any broken behaviour gracefully". Fixes: 11941f8a8536 ("bpf: cpumap: Implement generic cpumap") Signed-off-by: Hou Tao Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230729095107.1722450-3-houtao@huaweicloud.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- kernel/bpf/cpumap.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 09141351d545..e5888d401d79 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -134,11 +134,17 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring) * invoked cpu_map_kthread_stop(). Catch any broken behaviour * gracefully and warn once. */ - struct xdp_frame *xdpf; + void *ptr; - while ((xdpf = ptr_ring_consume(ring))) - if (WARN_ON_ONCE(xdpf)) - xdp_return_frame(xdpf); + while ((ptr = ptr_ring_consume(ring))) { + WARN_ON_ONCE(1); + if (unlikely(__ptr_test_bit(0, &ptr))) { + __ptr_clear_bit(0, &ptr); + kfree_skb(ptr); + continue; + } + xdp_return_frame(ptr); + } } static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) From aab2d095ce4dd8d01ca484c0cc641fb497bf74db Mon Sep 17 00:00:00 2001 From: valis Date: Sat, 29 Jul 2023 08:32:00 -0400 Subject: [PATCH 0089/2093] net/sched: cls_u32: No longer copy tcf_result on update to avoid use-after-free [ Upstream commit 3044b16e7c6fe5d24b1cdbcf1bd0a9d92d1ebd81 ] When u32_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. Fix this by no longer copying the tcf_result struct from the old filter. Fixes: de5df63228fc ("net: sched: cls_u32 changes to knode must appear atomic to readers") Reported-by: valis Reported-by: M A Ramdhan Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: M A Ramdhan Link: https://lore.kernel.org/r/20230729123202.72406-2-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/cls_u32.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 0e3bb1d65be1..ba93e2a6bdbb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -824,7 +824,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->ifindex = n->ifindex; new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); From 7f691439b29be0aae68f83ad5eecfddc11007724 Mon Sep 17 00:00:00 2001 From: valis Date: Sat, 29 Jul 2023 08:32:01 -0400 Subject: [PATCH 0090/2093] net/sched: cls_fw: No longer copy tcf_result on update to avoid use-after-free [ Upstream commit 76e42ae831991c828cffa8c37736ebfb831ad5ec ] When fw_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. Fix this by no longer copying the tcf_result struct from the old filter. Fixes: e35a8ee5993b ("net: sched: fw use RCU") Reported-by: valis Reported-by: Bing-Jhong Billy Jheng Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: M A Ramdhan Link: https://lore.kernel.org/r/20230729123202.72406-3-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/cls_fw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 1212b057b129..6160ef7d646a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -265,7 +265,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; fnew->ifindex = f->ifindex; fnew->tp = f->tp; From d4d3b53a4c66004e8e864fea744b3a2b86a73b62 Mon Sep 17 00:00:00 2001 From: valis Date: Sat, 29 Jul 2023 08:32:02 -0400 Subject: [PATCH 0091/2093] net/sched: cls_route: No longer copy tcf_result on update to avoid use-after-free [ Upstream commit b80b829e9e2c1b3f7aae34855e04d8f6ecaf13c8 ] When route4_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. Fix this by no longer copying the tcf_result struct from the old filter. Fixes: 1109c00547fc ("net: sched: RCU cls_route") Reported-by: valis Reported-by: Bing-Jhong Billy Jheng Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: M A Ramdhan Link: https://lore.kernel.org/r/20230729123202.72406-4-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/cls_route.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 9e43b929d4ca..306188bf2d1f 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -511,7 +511,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; From 834422b06c8b932184eb8127f1afd7a7957b764c Mon Sep 17 00:00:00 2001 From: Tomas Glozar Date: Fri, 28 Jul 2023 08:44:11 +0200 Subject: [PATCH 0092/2093] bpf: sockmap: Remove preempt_disable in sock_map_sk_acquire [ Upstream commit 13d2618b48f15966d1adfe1ff6a1985f5eef40ba ] Disabling preemption in sock_map_sk_acquire conflicts with GFP_ATOMIC allocation later in sk_psock_init_link on PREEMPT_RT kernels, since GFP_ATOMIC might sleep on RT (see bpf: Make BPF and PREEMPT_RT co-exist patchset notes for details). This causes calling bpf_map_update_elem on BPF_MAP_TYPE_SOCKMAP maps to BUG (sleeping function called from invalid context) on RT kernels. preempt_disable was introduced together with lock_sk and rcu_read_lock in commit 99ba2b5aba24e ("bpf: sockhash, disallow bpf_tcp_close and update in parallel"), probably to match disabled migration of BPF programs, and is no longer necessary. Remove preempt_disable to fix BUG in sock_map_update_common on RT. Signed-off-by: Tomas Glozar Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/all/20200224140131.461979697@linutronix.de/ Fixes: 99ba2b5aba24 ("bpf: sockhash, disallow bpf_tcp_close and update in parallel") Reviewed-by: John Fastabend Link: https://lore.kernel.org/r/20230728064411.305576-1-tglozar@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/core/sock_map.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d38267201892..c84e5073c0b6 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -117,7 +117,6 @@ static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); - preempt_disable(); rcu_read_lock(); } @@ -125,7 +124,6 @@ static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); - preempt_enable(); release_sock(sk); } From 58660666b46488152ec03dbde8a6e3e12b785fc9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 31 Jul 2023 10:42:32 +0300 Subject: [PATCH 0093/2093] net: ll_temac: fix error checking of irq_of_parse_and_map() [ Upstream commit ef45e8400f5bb66b03cc949f76c80e2a118447de ] Most kernel functions return negative error codes but some irq functions return zero on error. In this code irq_of_parse_and_map(), returns zero and platform_get_irq() returns negative error codes. We need to handle both cases appropriately. Fixes: 8425c41d1ef7 ("net: ll_temac: Extend support to non-device-tree platforms") Signed-off-by: Dan Carpenter Acked-by: Esben Haabendal Reviewed-by: Yang Yingliang Reviewed-by: Harini Katakam Link: https://lore.kernel.org/r/3d0aef75-06e0-45a5-a2a6-2cc4738d4143@moroto.mountain Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/xilinx/ll_temac_main.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 1066420d6a83..6bf5e341c3c1 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1568,12 +1568,16 @@ static int temac_probe(struct platform_device *pdev) } /* Error handle returned DMA RX and TX interrupts */ - if (lp->rx_irq < 0) - return dev_err_probe(&pdev->dev, lp->rx_irq, + if (lp->rx_irq <= 0) { + rc = lp->rx_irq ?: -EINVAL; + return dev_err_probe(&pdev->dev, rc, "could not get DMA RX irq\n"); - if (lp->tx_irq < 0) - return dev_err_probe(&pdev->dev, lp->tx_irq, + } + if (lp->tx_irq <= 0) { + rc = lp->tx_irq ?: -EINVAL; + return dev_err_probe(&pdev->dev, rc, "could not get DMA TX irq\n"); + } if (temac_np) { /* Retrieve the MAC address */ From 8afe27770dea9c4af991253c48db4a4dcc35f1a4 Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Mon, 31 Jul 2023 17:05:35 +0800 Subject: [PATCH 0094/2093] net: korina: handle clk prepare error in korina_probe() [ Upstream commit 0b6291ad1940c403734312d0e453e8dac9148f69 ] in korina_probe(), the return value of clk_prepare_enable() should be checked since it might fail. we can use devm_clk_get_optional_enabled() instead of devm_clk_get_optional() and clk_prepare_enable() to automatically handle the error. Fixes: e4cd854ec487 ("net: korina: Get mdio input clock via common clock framework") Signed-off-by: Yuanjun Gong Link: https://lore.kernel.org/r/20230731090535.21416-1-ruc_gongyuanjun@163.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/korina.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 2b9335cb4bb3..8537578e1cf1 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1302,11 +1302,10 @@ static int korina_probe(struct platform_device *pdev) else if (of_get_ethdev_address(pdev->dev.of_node, dev) < 0) eth_hw_addr_random(dev); - clk = devm_clk_get_optional(&pdev->dev, "mdioclk"); + clk = devm_clk_get_optional_enabled(&pdev->dev, "mdioclk"); if (IS_ERR(clk)) return PTR_ERR(clk); if (clk) { - clk_prepare_enable(clk); lp->mii_clock_freq = clk_get_rate(clk); } else { lp->mii_clock_freq = 200000000; /* max possible input clk */ From 64763dd851faaabb2b28a07878ea59e46734cd73 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 31 Jul 2023 11:48:32 +0100 Subject: [PATCH 0095/2093] net: netsec: Ignore 'phy-mode' on SynQuacer in DT mode [ Upstream commit f3bb7759a924713bc54d15f6d0d70733b5935fad ] As documented in acd7aaf51b20 ("netsec: ignore 'phy-mode' device property on ACPI systems") the SocioNext SynQuacer platform ships with firmware defining the PHY mode as RGMII even though the physical configuration of the PHY is for TX and RX delays. Since bbc4d71d63549bc ("net: phy: realtek: fix rtl8211e rx/tx delay config") this has caused misconfiguration of the PHY, rendering the network unusable. This was worked around for ACPI by ignoring the phy-mode property but the system is also used with DT. For DT instead if we're running on a SynQuacer force a working PHY mode, as well as the standard EDK2 firmware with DT there are also some of these systems that use u-boot and might not initialise the PHY if not netbooting. Newer firmware imagaes for at least EDK2 are available from Linaro so print a warning when doing this. Fixes: 533dd11a12f6 ("net: socionext: Add Synquacer NetSec driver") Signed-off-by: Mark Brown Acked-by: Ard Biesheuvel Acked-by: Ilias Apalodimas Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230731-synquacer-net-v3-1-944be5f06428@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/socionext/netsec.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 9b46579b5a10..b130e978366c 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1851,6 +1851,17 @@ static int netsec_of_probe(struct platform_device *pdev, return err; } + /* + * SynQuacer is physically configured with TX and RX delays + * but the standard firmware claimed otherwise for a long + * time, ignore it. + */ + if (of_machine_is_compatible("socionext,developer-box") && + priv->phy_interface != PHY_INTERFACE_MODE_RGMII_ID) { + dev_warn(&pdev->dev, "Outdated firmware reports incorrect PHY mode, overriding\n"); + priv->phy_interface = PHY_INTERFACE_MODE_RGMII_ID; + } + priv->phy_np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!priv->phy_np) { dev_err(&pdev->dev, "missing required property 'phy-handle'\n"); From e9f11bfc03fb0d3c86f91b8ae945bb10f7e19c16 Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Mon, 31 Jul 2023 07:20:42 -0700 Subject: [PATCH 0096/2093] bnxt_en: Fix page pool logic for page size >= 64K [ Upstream commit f6974b4c2d8e1062b5a52228ee47293c15b4ee1e ] The RXBD length field on all bnxt chips is 16-bit and so we cannot support a full page when the native page size is 64K or greater. The non-XDP (non page pool) code path has logic to handle this but the XDP page pool code path does not handle this. Add the missing logic to use page_pool_dev_alloc_frag() to allocate 32K chunks if the page size is 64K or greater. Fixes: 9f4b28301ce6 ("bnxt: XDP multibuffer enablement") Link: https://lore.kernel.org/netdev/20230728231829.235716-2-michael.chan@broadcom.com/ Reviewed-by: Andy Gospodarek Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Link: https://lore.kernel.org/r/20230731142043.58855-2-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 42 ++++++++++++------- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 6 +-- 2 files changed, 29 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6469fb8a42a8..9bd18c2b10bc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -721,17 +721,24 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, + unsigned int *offset, gfp_t gfp) { struct device *dev = &bp->pdev->dev; struct page *page; - page = page_pool_dev_alloc_pages(rxr->page_pool); + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + page = page_pool_dev_alloc_frag(rxr->page_pool, offset, + BNXT_RX_PAGE_SIZE); + } else { + page = page_pool_dev_alloc_pages(rxr->page_pool); + *offset = 0; + } if (!page) return NULL; - *mapping = dma_map_page_attrs(dev, page, 0, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + *mapping = dma_map_page_attrs(dev, page, *offset, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); if (dma_mapping_error(dev, *mapping)) { page_pool_recycle_direct(rxr->page_pool, page); return NULL; @@ -771,15 +778,16 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, dma_addr_t mapping; if (BNXT_RX_PAGE_MODE(bp)) { + unsigned int offset; struct page *page = - __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp); if (!page) return -ENOMEM; mapping += bp->rx_dma_offset; rx_buf->data = page; - rx_buf->data_ptr = page_address(page) + bp->rx_offset; + rx_buf->data_ptr = page_address(page) + offset + bp->rx_offset; } else { u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, gfp); @@ -839,7 +847,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, unsigned int offset = 0; if (BNXT_RX_PAGE_MODE(bp)) { - page = __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp); + page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp); if (!page) return -ENOMEM; @@ -986,15 +994,15 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp, return NULL; } dma_addr -= bp->rx_dma_offset; - dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - skb = build_skb(page_address(page), PAGE_SIZE); + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); + skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE); if (!skb) { page_pool_recycle_direct(rxr->page_pool, page); return NULL; } skb_mark_for_recycle(skb); - skb_reserve(skb, bp->rx_dma_offset); + skb_reserve(skb, bp->rx_offset); __skb_put(skb, len); return skb; @@ -1020,8 +1028,8 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, return NULL; } dma_addr -= bp->rx_dma_offset; - dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE, + bp->rx_dir, DMA_ATTR_WEAK_ORDERING); if (unlikely(!payload)) payload = eth_get_headlen(bp->dev, data_ptr, len); @@ -1034,7 +1042,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, skb_mark_for_recycle(skb); off = (void *)data_ptr - page_address(page); - skb_add_rx_frag(skb, 0, page, off, len, PAGE_SIZE); + skb_add_rx_frag(skb, 0, page, off, len, BNXT_RX_PAGE_SIZE); memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN, payload + NET_IP_ALIGN); @@ -1169,7 +1177,7 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp, skb->data_len += total_frag_len; skb->len += total_frag_len; - skb->truesize += PAGE_SIZE * agg_bufs; + skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs; return skb; } @@ -2972,8 +2980,8 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) rx_buf->data = NULL; if (BNXT_RX_PAGE_MODE(bp)) { mapping -= bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, PAGE_SIZE, - bp->rx_dir, + dma_unmap_page_attrs(&pdev->dev, mapping, + BNXT_RX_PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); page_pool_recycle_direct(rxr->page_pool, data); } else { @@ -3241,6 +3249,8 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, pp.nid = dev_to_node(&bp->pdev->dev); pp.dev = &bp->pdev->dev; pp.dma_dir = DMA_BIDIRECTIONAL; + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) + pp.flags |= PP_FLAG_PAGE_FRAG; rxr->page_pool = page_pool_create(&pp); if (IS_ERR(rxr->page_pool)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 36d5202c0aee..aa56db138d6b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -180,8 +180,8 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, u8 *data_ptr, unsigned int len, struct xdp_buff *xdp) { + u32 buflen = BNXT_RX_PAGE_SIZE; struct bnxt_sw_rx_bd *rx_buf; - u32 buflen = PAGE_SIZE; struct pci_dev *pdev; dma_addr_t mapping; u32 offset; @@ -297,7 +297,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, rx_buf = &rxr->rx_buf_ring[cons]; mapping = rx_buf->mapping - bp->rx_dma_offset; dma_unmap_page_attrs(&pdev->dev, mapping, - PAGE_SIZE, bp->rx_dir, + BNXT_RX_PAGE_SIZE, bp->rx_dir, DMA_ATTR_WEAK_ORDERING); /* if we are unable to allocate a new buffer, abort and reuse */ @@ -478,7 +478,7 @@ bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags, } xdp_update_skb_shared_info(skb, num_frags, sinfo->xdp_frags_size, - PAGE_SIZE * sinfo->nr_frags, + BNXT_RX_PAGE_SIZE * sinfo->nr_frags, xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } From 421e02bda0570eeb11636544fe97ec3097d1bb92 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 31 Jul 2023 07:20:43 -0700 Subject: [PATCH 0097/2093] bnxt_en: Fix max_mtu setting for multi-buf XDP [ Upstream commit 08450ea98ae98d5a35145b675b76db616046ea11 ] The existing code does not allow the MTU to be set to the maximum even after an XDP program supporting multiple buffers is attached. Fix it to set the netdev->max_mtu to the maximum value if the attached XDP program supports mutiple buffers, regardless of the current MTU value. Also use a local variable dev instead of repeatedly using bp->dev. Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff") Reviewed-by: Somnath Kotur Reviewed-by: Ajit Khaparde Reviewed-by: Andy Gospodarek Signed-off-by: Michael Chan Link: https://lore.kernel.org/r/20230731142043.58855-3-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9bd18c2b10bc..969db3c45d17 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4027,26 +4027,29 @@ void bnxt_set_ring_params(struct bnxt *bp) */ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) { + struct net_device *dev = bp->dev; + if (page_mode) { bp->flags &= ~BNXT_FLAG_AGG_RINGS; bp->flags |= BNXT_FLAG_RX_PAGE_MODE; - if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { + if (bp->xdp_prog->aux->xdp_has_frags) + dev->max_mtu = min_t(u16, bp->max_mtu, BNXT_MAX_MTU); + else + dev->max_mtu = + min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); + if (dev->mtu > BNXT_MAX_PAGE_MODE_MTU) { bp->flags |= BNXT_FLAG_JUMBO; bp->rx_skb_func = bnxt_rx_multi_page_skb; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_MTU); } else { bp->flags |= BNXT_FLAG_NO_AGG_RINGS; bp->rx_skb_func = bnxt_rx_page_skb; - bp->dev->max_mtu = - min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU); } bp->rx_dir = DMA_BIDIRECTIONAL; /* Disable LRO or GRO_HW */ - netdev_update_features(bp->dev); + netdev_update_features(dev); } else { - bp->dev->max_mtu = bp->max_mtu; + dev->max_mtu = bp->max_mtu; bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE; bp->rx_dir = DMA_FROM_DEVICE; bp->rx_skb_func = bnxt_rx_skb; From ecff20e193207b44fdbfe64d7de89890f0a7fe6c Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 1 Aug 2023 09:32:48 +0800 Subject: [PATCH 0098/2093] net: dcb: choose correct policy to parse DCB_ATTR_BCN [ Upstream commit 31d49ba033095f6e8158c60f69714a500922e0c3 ] The dcbnl_bcn_setcfg uses erroneous policy to parse tb[DCB_ATTR_BCN], which is introduced in commit 859ee3c43812 ("DCB: Add support for DCB BCN"). Please see the comment in below code static int dcbnl_bcn_setcfg(...) { ... ret = nla_parse_nested_deprecated(..., dcbnl_pfc_up_nest, .. ) // !!! dcbnl_pfc_up_nest for attributes // DCB_PFC_UP_ATTR_0 to DCB_PFC_UP_ATTR_ALL in enum dcbnl_pfc_up_attrs ... for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { // !!! DCB_BCN_ATTR_RP_0 to DCB_BCN_ATTR_RP_7 in enum dcbnl_bcn_attrs ... value_byte = nla_get_u8(data[i]); ... } ... for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { // !!! DCB_BCN_ATTR_BCNA_0 to DCB_BCN_ATTR_RI in enum dcbnl_bcn_attrs ... value_int = nla_get_u32(data[i]); ... } ... } That is, the nla_parse_nested_deprecated uses dcbnl_pfc_up_nest attributes to parse nlattr defined in dcbnl_pfc_up_attrs. But the following access code fetch each nlattr as dcbnl_bcn_attrs attributes. By looking up the associated nla_policy for dcbnl_bcn_attrs. We can find the beginning part of these two policies are "same". static const struct nla_policy dcbnl_pfc_up_nest[...] = { [DCB_PFC_UP_ATTR_0] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_1] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_2] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_3] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_4] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_5] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_6] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_7] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_ALL] = {.type = NLA_FLAG}, }; static const struct nla_policy dcbnl_bcn_nest[...] = { [DCB_BCN_ATTR_RP_0] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_1] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_2] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_3] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_4] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_5] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_6] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_7] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_ALL] = {.type = NLA_FLAG}, // from here is somewhat different [DCB_BCN_ATTR_BCNA_0] = {.type = NLA_U32}, ... [DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG}, }; Therefore, the current code is buggy and this nla_parse_nested_deprecated could overflow the dcbnl_pfc_up_nest and use the adjacent nla_policy to parse attributes from DCB_BCN_ATTR_BCNA_0. Hence use the correct policy dcbnl_bcn_nest to parse the nested tb[DCB_ATTR_BCN] TLV. Fixes: 859ee3c43812 ("DCB: Add support for DCB BCN") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230801013248.87240-1-linma@zju.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/dcb/dcbnl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index dc4fb699b56c..d2981e89d363 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -946,7 +946,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, - tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; From 86818409f989fee29c38528ed8fb085655603356 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Tue, 1 Aug 2023 10:00:16 +0200 Subject: [PATCH 0099/2093] s390/qeth: Don't call dev_close/dev_open (DOWN/UP) [ Upstream commit 1cfef80d4c2b2c599189f36f36320b205d9447d9 ] dev_close() and dev_open() are issued to change the interface state to DOWN or UP (dev->flags IFF_UP). When the netdev is set DOWN it loses e.g its Ipv6 addresses and routes. We don't want this in cases of device recovery (triggered by hardware or software) or when the qeth device is set offline. Setting a qeth device offline or online and device recovery actions call netif_device_detach() and/or netif_device_attach(). That will reset or set the LOWER_UP indication i.e. change the dev->state Bit __LINK_STATE_PRESENT. That is enough to e.g. cause bond failovers, and still preserves the interface settings that are handled by the network stack. Don't call dev_open() nor dev_close() from the qeth device driver. Let the network stack handle this. Fixes: d4560150cb47 ("s390/qeth: call dev_close() during recovery") Signed-off-by: Alexandra Winter Reviewed-by: Wenjia Zhang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/s390/net/qeth_core.h | 1 - drivers/s390/net/qeth_core_main.c | 2 -- drivers/s390/net/qeth_l2_main.c | 9 ++++++--- drivers/s390/net/qeth_l3_main.c | 8 +++++--- 4 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 1d195429753d..613eab729704 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -716,7 +716,6 @@ struct qeth_card_info { u16 chid; u8 ids_valid:1; /* cssid,iid,chid */ u8 dev_addr_is_registered:1; - u8 open_when_online:1; u8 promisc_mode:1; u8 use_v1_blkt:1; u8 is_vm_nic:1; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8bd9fd51208c..ae4b6d24bc90 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5371,8 +5371,6 @@ int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc, qeth_clear_ipacmd_list(card); rtnl_lock(); - card->info.open_when_online = card->dev->flags & IFF_UP; - dev_close(card->dev); netif_device_detach(card->dev); netif_carrier_off(card->dev); rtnl_unlock(); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index c6ded3fdd715..9ef2118fc7a2 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2387,9 +2387,12 @@ static int qeth_l2_set_online(struct qeth_card *card, bool carrier_ok) qeth_enable_hw_features(dev); qeth_l2_enable_brport_features(card); - if (card->info.open_when_online) { - card->info.open_when_online = 0; - dev_open(dev, NULL); + if (netif_running(dev)) { + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); + qeth_l2_set_rx_mode(dev); } rtnl_unlock(); } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d8487a10cd55..c0f30cefec10 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2017,9 +2017,11 @@ static int qeth_l3_set_online(struct qeth_card *card, bool carrier_ok) netif_device_attach(dev); qeth_enable_hw_features(dev); - if (card->info.open_when_online) { - card->info.open_when_online = 0; - dev_open(dev, NULL); + if (netif_running(dev)) { + local_bh_disable(); + napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } rtnl_unlock(); } From 691a09eecad97e745b9aa0e3918db46d020bdacb Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Tue, 1 Aug 2023 14:43:18 +0800 Subject: [PATCH 0100/2093] ip6mr: Fix skb_under_panic in ip6mr_cache_report() [ Upstream commit 30e0191b16e8a58e4620fa3e2839ddc7b9d4281c ] skbuff: skb_under_panic: text:ffffffff88771f69 len:56 put:-4 head:ffff88805f86a800 data:ffff887f5f86a850 tail:0x88 end:0x2c0 dev:pim6reg ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:192! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 2 PID: 22968 Comm: kworker/2:11 Not tainted 6.5.0-rc3-00044-g0a8db05b571a #236 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:skb_panic+0x152/0x1d0 Call Trace: skb_push+0xc4/0xe0 ip6mr_cache_report+0xd69/0x19b0 reg_vif_xmit+0x406/0x690 dev_hard_start_xmit+0x17e/0x6e0 __dev_queue_xmit+0x2d6a/0x3d20 vlan_dev_hard_start_xmit+0x3ab/0x5c0 dev_hard_start_xmit+0x17e/0x6e0 __dev_queue_xmit+0x2d6a/0x3d20 neigh_connected_output+0x3ed/0x570 ip6_finish_output2+0x5b5/0x1950 ip6_finish_output+0x693/0x11c0 ip6_output+0x24b/0x880 NF_HOOK.constprop.0+0xfd/0x530 ndisc_send_skb+0x9db/0x1400 ndisc_send_rs+0x12a/0x6c0 addrconf_dad_completed+0x3c9/0xea0 addrconf_dad_work+0x849/0x1420 process_one_work+0xa22/0x16e0 worker_thread+0x679/0x10c0 ret_from_fork+0x28/0x60 ret_from_fork_asm+0x11/0x20 When setup a vlan device on dev pim6reg, DAD ns packet may sent on reg_vif_xmit(). reg_vif_xmit() ip6mr_cache_report() skb_push(skb, -skb_network_offset(pkt));//skb_network_offset(pkt) is 4 And skb_push declared as: void *skb_push(struct sk_buff *skb, unsigned int len); skb->data -= len; //0xffff88805f86a84c - 0xfffffffc = 0xffff887f5f86a850 skb->data is set to 0xffff887f5f86a850, which is invalid mem addr, lead to skb_push() fails. Fixes: 14fb64e1f449 ("[IPV6] MROUTE: Support PIM-SM (SSM).") Signed-off-by: Yue Haibing Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/ip6mr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index facdc78a43e5..27fb5479988a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1073,7 +1073,7 @@ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); From 7b8717658dff8b471cbfc124bf9b5ca4229579ed Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Mon, 31 Jul 2023 16:02:08 -0400 Subject: [PATCH 0101/2093] vxlan: Fix nexthop hash size [ Upstream commit 0756384fb1bd38adb2ebcfd1307422f433a1d772 ] The nexthop code expects a 31 bit hash, such as what is returned by fib_multipath_hash() and rt6_multipath_hash(). Passing the 32 bit hash returned by skb_get_hash() can lead to problems related to the fact that 'int hash' is a negative number when the MSB is set. In the case of hash threshold nexthop groups, nexthop_select_path_hthr() will disproportionately select the first nexthop group entry. In the case of resilient nexthop groups, nexthop_select_path_res() may do an out of bounds access in nh_buckets[], for example: hash = -912054133 num_nh_buckets = 2 bucket_index = 65535 which leads to the following panic: BUG: unable to handle page fault for address: ffffc900025910c8 PGD 100000067 P4D 100000067 PUD 10026b067 PMD 0 Oops: 0002 [#1] PREEMPT SMP KASAN NOPTI CPU: 4 PID: 856 Comm: kworker/4:3 Not tainted 6.5.0-rc2+ #34 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:nexthop_select_path+0x197/0xbf0 Code: c1 e4 05 be 08 00 00 00 4c 8b 35 a4 14 7e 01 4e 8d 6c 25 00 4a 8d 7c 25 08 48 01 dd e8 c2 25 15 ff 49 8d 7d 08 e8 39 13 15 ff <4d> 89 75 08 48 89 ef e8 7d 12 15 ff 48 8b 5d 00 e8 14 55 2f 00 85 RSP: 0018:ffff88810c36f260 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 00000000002000c0 RCX: ffffffffaf02dd77 RDX: dffffc0000000000 RSI: 0000000000000008 RDI: ffffc900025910c8 RBP: ffffc900025910c0 R08: 0000000000000001 R09: fffff520004b2219 R10: ffffc900025910cf R11: 31392d2068736168 R12: 00000000002000c0 R13: ffffc900025910c0 R14: 00000000fffef608 R15: ffff88811840e900 FS: 0000000000000000(0000) GS:ffff8881f7000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffc900025910c8 CR3: 0000000129d00000 CR4: 0000000000750ee0 PKRU: 55555554 Call Trace: ? __die+0x23/0x70 ? page_fault_oops+0x1ee/0x5c0 ? __pfx_is_prefetch.constprop.0+0x10/0x10 ? __pfx_page_fault_oops+0x10/0x10 ? search_bpf_extables+0xfe/0x1c0 ? fixup_exception+0x3b/0x470 ? exc_page_fault+0xf6/0x110 ? asm_exc_page_fault+0x26/0x30 ? nexthop_select_path+0x197/0xbf0 ? nexthop_select_path+0x197/0xbf0 ? lock_is_held_type+0xe7/0x140 vxlan_xmit+0x5b2/0x2340 ? __lock_acquire+0x92b/0x3370 ? __pfx_vxlan_xmit+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 ? __pfx_register_lock_class+0x10/0x10 ? skb_network_protocol+0xce/0x2d0 ? dev_hard_start_xmit+0xca/0x350 ? __pfx_vxlan_xmit+0x10/0x10 dev_hard_start_xmit+0xca/0x350 __dev_queue_xmit+0x513/0x1e20 ? __pfx___dev_queue_xmit+0x10/0x10 ? __pfx_lock_release+0x10/0x10 ? mark_held_locks+0x44/0x90 ? skb_push+0x4c/0x80 ? eth_header+0x81/0xe0 ? __pfx_eth_header+0x10/0x10 ? neigh_resolve_output+0x215/0x310 ? ip6_finish_output2+0x2ba/0xc90 ip6_finish_output2+0x2ba/0xc90 ? lock_release+0x236/0x3e0 ? ip6_mtu+0xbb/0x240 ? __pfx_ip6_finish_output2+0x10/0x10 ? find_held_lock+0x83/0xa0 ? lock_is_held_type+0xe7/0x140 ip6_finish_output+0x1ee/0x780 ip6_output+0x138/0x460 ? __pfx_ip6_output+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 ? __pfx_ip6_finish_output+0x10/0x10 NF_HOOK.constprop.0+0xc0/0x420 ? __pfx_NF_HOOK.constprop.0+0x10/0x10 ? ndisc_send_skb+0x2c0/0x960 ? __pfx_lock_release+0x10/0x10 ? __local_bh_enable_ip+0x93/0x110 ? lock_is_held_type+0xe7/0x140 ndisc_send_skb+0x4be/0x960 ? __pfx_ndisc_send_skb+0x10/0x10 ? mark_held_locks+0x65/0x90 ? find_held_lock+0x83/0xa0 ndisc_send_ns+0xb0/0x110 ? __pfx_ndisc_send_ns+0x10/0x10 addrconf_dad_work+0x631/0x8e0 ? lock_acquire+0x180/0x3f0 ? __pfx_addrconf_dad_work+0x10/0x10 ? mark_held_locks+0x24/0x90 process_one_work+0x582/0x9c0 ? __pfx_process_one_work+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? mark_held_locks+0x24/0x90 worker_thread+0x93/0x630 ? __kthread_parkme+0xdc/0x100 ? __pfx_worker_thread+0x10/0x10 kthread+0x1a5/0x1e0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x60 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 RIP: 0000:0x0 Code: Unable to access opcode bytes at 0xffffffffffffffd6. RSP: 0000:0000000000000000 EFLAGS: 00000000 ORIG_RAX: 0000000000000000 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Modules linked in: CR2: ffffc900025910c8 ---[ end trace 0000000000000000 ]--- RIP: 0010:nexthop_select_path+0x197/0xbf0 Code: c1 e4 05 be 08 00 00 00 4c 8b 35 a4 14 7e 01 4e 8d 6c 25 00 4a 8d 7c 25 08 48 01 dd e8 c2 25 15 ff 49 8d 7d 08 e8 39 13 15 ff <4d> 89 75 08 48 89 ef e8 7d 12 15 ff 48 8b 5d 00 e8 14 55 2f 00 85 RSP: 0018:ffff88810c36f260 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 00000000002000c0 RCX: ffffffffaf02dd77 RDX: dffffc0000000000 RSI: 0000000000000008 RDI: ffffc900025910c8 RBP: ffffc900025910c0 R08: 0000000000000001 R09: fffff520004b2219 R10: ffffc900025910cf R11: 31392d2068736168 R12: 00000000002000c0 R13: ffffc900025910c0 R14: 00000000fffef608 R15: ffff88811840e900 FS: 0000000000000000(0000) GS:ffff8881f7000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 0000000129d00000 CR4: 0000000000750ee0 PKRU: 55555554 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0x2ca00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fix this problem by ensuring the MSB of hash is 0 using a right shift - the same approach used in fib_multipath_hash() and rt6_multipath_hash(). Fixes: 1274e1cc4226 ("vxlan: ecmp support for mac fdb entries") Signed-off-by: Benjamin Poirier Reviewed-by: Ido Schimmel Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/vxlan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 03bcc1ef0d61..a46ec889acb7 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -548,12 +548,12 @@ static inline void vxlan_flag_attr_error(int attrtype, } static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh, - int hash, + u32 hash, struct vxlan_rdst *rdst) { struct fib_nh_common *nhc; - nhc = nexthop_path_fdb_result(nh, hash); + nhc = nexthop_path_fdb_result(nh, hash >> 1); if (unlikely(!nhc)) return false; From 1ca50e5de43aa1df6253105790971392a68b111c Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 31 Jul 2023 14:58:40 +0300 Subject: [PATCH 0102/2093] net/mlx5: fs_core: Make find_closest_ft more generic [ Upstream commit 618d28a535a0582617465d14e05f3881736a2962 ] As find_closest_ft_recursive is called to find the closest FT, the first parameter of find_closest_ft can be changed from fs_prio to fs_node. Thus this function is extended to find the closest FT for the nodes of any type, not only prios, but also the sub namespaces. Signed-off-by: Jianbo Liu Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/d3962c2b443ec8dde7a740dc742a1f052d5e256c.1690803944.git.leonro@nvidia.com Signed-off-by: Jakub Kicinski Stable-dep-of: c635ca45a7a2 ("net/mlx5: fs_core: Skip the FTs in the same FS_TYPE_PRIO_CHAINS fs_prio") Signed-off-by: Sasha Levin --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 29 +++++++++---------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d53749248fa0..73ef771d6a4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -876,18 +876,17 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse is false then return the first flow table in next priority of - * prio in the tree, else return the last flow table in the previous priority - * of prio in the tree. +/* If reverse is false then return the first flow table next to the passed node + * in the tree, else return the last flow table before the node in the tree. */ -static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool reverse) +static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool reverse) { struct mlx5_flow_table *ft = NULL; struct fs_node *curr_node; struct fs_node *parent; - parent = prio->node.parent; - curr_node = &prio->node; + parent = node->parent; + curr_node = node; while (!ft && parent) { ft = find_closest_ft_recursive(parent, &curr_node->list, reverse); curr_node = parent; @@ -897,15 +896,15 @@ static struct mlx5_flow_table *find_closest_ft(struct fs_prio *prio, bool revers } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_next_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_next_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, false); + return find_closest_ft(node, false); } /* Assuming all the tree is locked by mutex chain lock */ -static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) +static struct mlx5_flow_table *find_prev_chained_ft(struct fs_node *node) { - return find_closest_ft(prio, true); + return find_closest_ft(node, true); } static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, @@ -917,7 +916,7 @@ static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return find_next_chained_ft(prio); + return find_next_chained_ft(&prio->node); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, @@ -948,7 +947,7 @@ static int connect_prev_fts(struct mlx5_core_dev *dev, { struct mlx5_flow_table *prev_ft; - prev_ft = find_prev_chained_ft(prio); + prev_ft = find_prev_chained_ft(&prio->node); if (prev_ft) { struct fs_prio *prev_prio; @@ -1094,7 +1093,7 @@ static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table if (err) return err; - next_ft = first_ft ? first_ft : find_next_chained_ft(prio); + next_ft = first_ft ? first_ft : find_next_chained_ft(&prio->node); err = connect_fwd_rules(dev, ft, next_ft); if (err) return err; @@ -1169,7 +1168,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); next_ft = unmanaged ? ft_attr->next_ft : - find_next_chained_ft(fs_prio); + find_next_chained_ft(&fs_prio->node); ft->def_miss_action = ns->def_miss_action; ft->ns = ns; err = root->cmds->create_flow_table(root, ft, ft_attr, next_ft); @@ -2163,7 +2162,7 @@ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) if (!list_is_last(&ft->node.list, &prio->node.children)) return list_next_entry(ft, node.list); - return find_next_chained_ft(prio); + return find_next_chained_ft(&prio->node); } static int update_root_ft_destroy(struct mlx5_flow_table *ft) From 72b3aea3450ecd45d42d8adc44d9874e7d5f32f3 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 31 Jul 2023 14:58:41 +0300 Subject: [PATCH 0103/2093] net/mlx5: fs_core: Skip the FTs in the same FS_TYPE_PRIO_CHAINS fs_prio [ Upstream commit c635ca45a7a2023904a1f851e99319af7b87017d ] In the cited commit, new type of FS_TYPE_PRIO_CHAINS fs_prio was added to support multiple parallel namespaces for multi-chains. And we skip all the flow tables under the fs_node of this type unconditionally, when searching for the next or previous flow table to connect for a new table. As this search function is also used for find new root table when the old one is being deleted, it will skip the entire FS_TYPE_PRIO_CHAINS fs_node next to the old root. However, new root table should be chosen from it if there is any table in it. Fix it by skipping only the flow tables in the same FS_TYPE_PRIO_CHAINS fs_node when finding the closest FT for a fs_node. Besides, complete the connecting from FTs of previous priority of prio because there should be multiple prevs after this fs_prio type is introduced. And also the next FT should be chosen from the first flow table next to the prio in the same FS_TYPE_PRIO_CHAINS fs_prio, if this prio is the first child. Fixes: 328edb499f99 ("net/mlx5: Split FDB fast path prio to multiple namespaces") Signed-off-by: Jianbo Liu Reviewed-by: Paul Blakey Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/7a95754df479e722038996c97c97b062b372591f.1690803944.git.leonro@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 80 +++++++++++++++++-- 1 file changed, 72 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 73ef771d6a4a..e6674118bc42 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -860,7 +860,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, struct fs_node *iter = list_entry(start, struct fs_node, list); struct mlx5_flow_table *ft = NULL; - if (!root || root->type == FS_TYPE_PRIO_CHAINS) + if (!root) return NULL; list_for_each_advance_continue(iter, &root->children, reverse) { @@ -876,19 +876,42 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } +static struct fs_node *find_prio_chains_parent(struct fs_node *parent, + struct fs_node **child) +{ + struct fs_node *node = NULL; + + while (parent && parent->type != FS_TYPE_PRIO_CHAINS) { + node = parent; + parent = parent->parent; + } + + if (child) + *child = node; + + return parent; +} + /* If reverse is false then return the first flow table next to the passed node * in the tree, else return the last flow table before the node in the tree. + * If skip is true, skip the flow tables in the same prio_chains prio. */ -static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool reverse) +static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool reverse, + bool skip) { + struct fs_node *prio_chains_parent = NULL; struct mlx5_flow_table *ft = NULL; struct fs_node *curr_node; struct fs_node *parent; + if (skip) + prio_chains_parent = find_prio_chains_parent(node, NULL); parent = node->parent; curr_node = node; while (!ft && parent) { - ft = find_closest_ft_recursive(parent, &curr_node->list, reverse); + if (parent != prio_chains_parent) + ft = find_closest_ft_recursive(parent, &curr_node->list, + reverse); curr_node = parent; parent = curr_node->parent; } @@ -898,13 +921,13 @@ static struct mlx5_flow_table *find_closest_ft(struct fs_node *node, bool revers /* Assuming all the tree is locked by mutex chain lock */ static struct mlx5_flow_table *find_next_chained_ft(struct fs_node *node) { - return find_closest_ft(node, false); + return find_closest_ft(node, false, true); } /* Assuming all the tree is locked by mutex chain lock */ static struct mlx5_flow_table *find_prev_chained_ft(struct fs_node *node) { - return find_closest_ft(node, true); + return find_closest_ft(node, true, true); } static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, @@ -940,21 +963,55 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev, return 0; } +static struct mlx5_flow_table *find_closet_ft_prio_chains(struct fs_node *node, + struct fs_node *parent, + struct fs_node **child, + bool reverse) +{ + struct mlx5_flow_table *ft; + + ft = find_closest_ft(node, reverse, false); + + if (ft && parent == find_prio_chains_parent(&ft->node, child)) + return ft; + + return NULL; +} + /* Connect flow tables from previous priority of prio to ft */ static int connect_prev_fts(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, struct fs_prio *prio) { + struct fs_node *prio_parent, *parent = NULL, *child, *node; struct mlx5_flow_table *prev_ft; + int err = 0; + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + /* return directly if not under the first sub ns of prio_chains prio */ + if (prio_parent && !list_is_first(&child->list, &prio_parent->children)) + return 0; prev_ft = find_prev_chained_ft(&prio->node); - if (prev_ft) { + while (prev_ft) { struct fs_prio *prev_prio; fs_get_obj(prev_prio, prev_ft->node.parent); - return connect_fts_in_prio(dev, prev_prio, ft); + err = connect_fts_in_prio(dev, prev_prio, ft); + if (err) + break; + + if (!parent) { + parent = find_prio_chains_parent(&prev_prio->node, &child); + if (!parent) + break; + } + + node = child; + prev_ft = find_closet_ft_prio_chains(node, parent, &child, true); } - return 0; + return err; } static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio @@ -2156,12 +2213,19 @@ EXPORT_SYMBOL(mlx5_del_flow_rules); /* Assuming prio->node.children(flow tables) is sorted by level */ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) { + struct fs_node *prio_parent, *child; struct fs_prio *prio; fs_get_obj(prio, ft->node.parent); if (!list_is_last(&ft->node.list, &prio->node.children)) return list_next_entry(ft, node.list); + + prio_parent = find_prio_chains_parent(&prio->node, &child); + + if (prio_parent && list_is_first(&child->list, &prio_parent->children)) + return find_closest_ft(&prio->node, false, false); + return find_next_chained_ft(&prio->node); } From afac854f8221aabcbb7fa13b3fbd9e64097658ae Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Wed, 2 Aug 2023 11:23:56 +0200 Subject: [PATCH 0104/2093] prestera: fix fallback to previous version on same major version [ Upstream commit b755c25fbcd568821a3bb0e0d5c2daa5fcb00bba ] When both supported and previous version have the same major version, and the firmwares are missing, the driver ends in a loop requesting the same (previous) version over and over again: [ 76.327413] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.1.img firmware, fall-back to previous 4.0 version [ 76.339802] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.352162] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.364502] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.376848] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.389183] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.401522] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.413860] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version [ 76.426199] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.0.img firmware, fall-back to previous 4.0 version ... Fix this by inverting the check to that we aren't yet at the previous version, and also check the minor version. This also catches the case where both versions are the same, as it was after commit bb5dbf2cc64d ("net: marvell: prestera: add firmware v4.0 support"). With this fix applied: [ 88.499622] Prestera DX 0000:01:00.0: missing latest mrvl/prestera/mvsw_prestera_fw-v4.1.img firmware, fall-back to previous 4.0 version [ 88.511995] Prestera DX 0000:01:00.0: failed to request previous firmware: mrvl/prestera/mvsw_prestera_fw-v4.0.img [ 88.522403] Prestera DX: probe of 0000:01:00.0 failed with error -2 Fixes: 47f26018a414 ("net: marvell: prestera: try to load previous fw version") Signed-off-by: Jonas Gorski Acked-by: Elad Nachman Reviewed-by: Jesse Brandeburg Acked-by: Taras Chornyi Link: https://lore.kernel.org/r/20230802092357.163944-1-jonas.gorski@bisdn.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/prestera/prestera_pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 59470d99f522..a37dbbda8de3 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -702,7 +702,8 @@ static int prestera_fw_get(struct prestera_fw *fw) err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev); if (err) { - if (ver_maj == PRESTERA_SUPP_FW_MAJ_VER) { + if (ver_maj != PRESTERA_PREV_FW_MAJ_VER || + ver_min != PRESTERA_PREV_FW_MIN_VER) { ver_maj = PRESTERA_PREV_FW_MAJ_VER; ver_min = PRESTERA_PREV_FW_MIN_VER; From 71f891a25405001e96e80ef6434aae75075a9363 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Aug 2023 13:14:55 +0000 Subject: [PATCH 0105/2093] tcp_metrics: fix addr_same() helper [ Upstream commit e6638094d7af6c7b9dcca05ad009e79e31b4f670 ] Because v4 and v6 families use separate inetpeer trees (respectively net->ipv4.peers and net->ipv6.peers), inetpeer_addr_cmp(a, b) assumes a & b share the same family. tcp_metrics use a common hash table, where entries can have different families. We must therefore make sure to not call inetpeer_addr_cmp() if the families do not match. Fixes: d39d14ffa24c ("net: Add helper function to compare inetpeer addresses") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230802131500.1478140-2-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_metrics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 82f4575f9cd9..c4daf0aa2d4d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -78,7 +78,7 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - return inetpeer_addr_cmp(a, b) == 0; + return (a->family == b->family) && !inetpeer_addr_cmp(a, b); } struct tcpm_hash_bucket { From 4a77a0f7526c2761b300826b86da92878cfafb98 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Aug 2023 13:14:56 +0000 Subject: [PATCH 0106/2093] tcp_metrics: annotate data-races around tm->tcpm_stamp [ Upstream commit 949ad62a5d5311d36fce2e14fe5fed3f936da51c ] tm->tcpm_stamp can be read or written locklessly. Add needed READ_ONCE()/WRITE_ONCE() to document this. Also constify tcpm_check_stamp() dst argument. Fixes: 51c5d0c4b169 ("tcp: Maintain dynamic metrics in local cache.") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230802131500.1478140-3-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_metrics.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c4daf0aa2d4d..838616588796 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -97,7 +97,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, u32 msval; u32 val; - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); val = 0; if (dst_metric_locked(dst, RTAX_RTT)) @@ -131,9 +131,15 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, #define TCP_METRICS_TIMEOUT (60 * 60 * HZ) -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +static void tcpm_check_stamp(struct tcp_metrics_block *tm, + const struct dst_entry *dst) { - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + unsigned long limit; + + if (!tm) + return; + limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT; + if (unlikely(time_after(jiffies, limit))) tcpm_suck_dst(tm, dst, false); } @@ -174,7 +180,8 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, oldest = deref_locked(tcp_metrics_hash[hash].chain); for (tm = deref_locked(oldest->tcpm_next); tm; tm = deref_locked(tm->tcpm_next)) { - if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + if (time_before(READ_ONCE(tm->tcpm_stamp), + READ_ONCE(oldest->tcpm_stamp))) oldest = tm; } tm = oldest; @@ -434,7 +441,7 @@ void tcp_update_metrics(struct sock *sk) tp->reordering); } } - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); out_unlock: rcu_read_unlock(); } @@ -647,7 +654,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, } if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, - jiffies - tm->tcpm_stamp, + jiffies - READ_ONCE(tm->tcpm_stamp), TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; From fee608e802718649185be76c4478012154a5fe33 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Aug 2023 13:14:57 +0000 Subject: [PATCH 0107/2093] tcp_metrics: annotate data-races around tm->tcpm_lock [ Upstream commit 285ce119a3c6c4502585936650143e54c8692788 ] tm->tcpm_lock can be read or written locklessly. Add needed READ_ONCE()/WRITE_ONCE() to document this. Fixes: 51c5d0c4b169 ("tcp: Maintain dynamic metrics in local cache.") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230802131500.1478140-4-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_metrics.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 838616588796..131fa3004969 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -59,7 +59,8 @@ static inline struct net *tm_net(struct tcp_metrics_block *tm) static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_lock & (1 << idx); + /* Paired with WRITE_ONCE() in tcpm_suck_dst() */ + return READ_ONCE(tm->tcpm_lock) & (1 << idx); } static u32 tcp_metric_get(struct tcp_metrics_block *tm, @@ -110,7 +111,8 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, val |= 1 << TCP_METRIC_CWND; if (dst_metric_locked(dst, RTAX_REORDERING)) val |= 1 << TCP_METRIC_REORDERING; - tm->tcpm_lock = val; + /* Paired with READ_ONCE() in tcp_metric_locked() */ + WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; From 6dea95d8caff9512fbd91bcf0375c046c98c165b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Aug 2023 13:14:58 +0000 Subject: [PATCH 0108/2093] tcp_metrics: annotate data-races around tm->tcpm_vals[] [ Upstream commit 8c4d04f6b443869d25e59822f7cec88d647028a9 ] tm->tcpm_vals[] values can be read or written locklessly. Add needed READ_ONCE()/WRITE_ONCE() to document this, and force use of tcp_metric_get() and tcp_metric_set() Fixes: 51c5d0c4b169 ("tcp: Maintain dynamic metrics in local cache.") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_metrics.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 131fa3004969..fd4ab7a51cef 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -63,17 +63,19 @@ static bool tcp_metric_locked(struct tcp_metrics_block *tm, return READ_ONCE(tm->tcpm_lock) & (1 << idx); } -static u32 tcp_metric_get(struct tcp_metrics_block *tm, +static u32 tcp_metric_get(const struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_vals[idx]; + /* Paired with WRITE_ONCE() in tcp_metric_set() */ + return READ_ONCE(tm->tcpm_vals[idx]); } static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) { - tm->tcpm_vals[idx] = val; + /* Paired with READ_ONCE() in tcp_metric_get() */ + WRITE_ONCE(tm->tcpm_vals[idx], val); } static bool addr_same(const struct inetpeer_addr *a, @@ -115,13 +117,16 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC); msval = dst_metric_raw(dst, RTAX_RTTVAR); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; - tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); - tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); - tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC); + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + dst_metric_raw(dst, RTAX_SSTHRESH)); + tcp_metric_set(tm, TCP_METRIC_CWND, + dst_metric_raw(dst, RTAX_CWND)); + tcp_metric_set(tm, TCP_METRIC_REORDERING, + dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; @@ -667,7 +672,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { - u32 val = tm->tcpm_vals[i]; + u32 val = tcp_metric_get(tm, i); if (!val) continue; From e53917e7efea95b8a10c5d3696e37e4a1e7d47fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Aug 2023 13:14:59 +0000 Subject: [PATCH 0109/2093] tcp_metrics: annotate data-races around tm->tcpm_net [ Upstream commit d5d986ce42c71a7562d32c4e21e026b0f87befec ] tm->tcpm_net can be read or written locklessly. Instead of changing write_pnet() and read_pnet() and potentially hurt performance, add the needed READ_ONCE()/WRITE_ONCE() in tm_net() and tcpm_new(). Fixes: 849e8a0ca8d5 ("tcp_metrics: Add a field tcpm_net and verify it matches on lookup") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230802131500.1478140-6-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_metrics.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index fd4ab7a51cef..4fd274836a48 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -40,7 +40,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - possible_net_t tcpm_net; + struct net *tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -51,9 +51,10 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; -static inline struct net *tm_net(struct tcp_metrics_block *tm) +static inline struct net *tm_net(const struct tcp_metrics_block *tm) { - return read_pnet(&tm->tcpm_net); + /* Paired with the WRITE_ONCE() in tcpm_new() */ + return READ_ONCE(tm->tcpm_net); } static bool tcp_metric_locked(struct tcp_metrics_block *tm, @@ -197,7 +198,9 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, if (!tm) goto out_unlock; } - write_pnet(&tm->tcpm_net, net); + /* Paired with the READ_ONCE() in tm_net() */ + WRITE_ONCE(tm->tcpm_net, net); + tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; From cd4bdf8f98ef88ac9c2df2269c925c857e3af222 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Aug 2023 13:15:00 +0000 Subject: [PATCH 0110/2093] tcp_metrics: fix data-race in tcpm_suck_dst() vs fastopen [ Upstream commit ddf251fa2bc1d3699eec0bae6ed0bc373b8fda79 ] Whenever tcpm_new() reclaims an old entry, tcpm_suck_dst() would overwrite data that could be read from tcp_fastopen_cache_get() or tcp_metrics_fill_info(). We need to acquire fastopen_seqlock to maintain consistency. For newly allocated objects, tcpm_new() can switch to kzalloc() to avoid an extra fastopen_seqlock acquisition. Fixes: 1fe4c481ba63 ("net-tcp: Fast Open client - cookie cache") Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230802131500.1478140-7-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_metrics.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4fd274836a48..99ac5efe244d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -93,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; static unsigned int tcp_metrics_hash_log __read_mostly; static DEFINE_SPINLOCK(tcp_metrics_lock); +static DEFINE_SEQLOCK(fastopen_seqlock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, const struct dst_entry *dst, @@ -129,11 +130,13 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, tcp_metric_set(tm, TCP_METRIC_REORDERING, dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { + write_seqlock(&fastopen_seqlock); tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; tm->tcpm_fastopen.try_exp = 0; tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; + write_sequnlock(&fastopen_seqlock); } } @@ -194,7 +197,7 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, } tm = oldest; } else { - tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + tm = kzalloc(sizeof(*tm), GFP_ATOMIC); if (!tm) goto out_unlock; } @@ -204,7 +207,7 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; - tcpm_suck_dst(tm, dst, true); + tcpm_suck_dst(tm, dst, reclaim); if (likely(!reclaim)) { tm->tcpm_next = tcp_metrics_hash[hash].chain; @@ -556,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) return ret; } -static DEFINE_SEQLOCK(fastopen_seqlock); - void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { From f0618c305b41f1a4df1635c399fe264e8ad676a1 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Sat, 29 Jul 2023 18:29:02 -0700 Subject: [PATCH 0111/2093] rust: allocator: Prevent mis-aligned allocation commit b3d8aa84bbfe9b58ccc5332cacf8ea17200af310 upstream. Currently the rust allocator simply passes the size of the type Layout to krealloc(), and in theory the alignment requirement from the type Layout may be larger than the guarantee provided by SLAB, which means the allocated object is mis-aligned. Fix this by adjusting the allocation size to the nearest power of two, which SLAB always guarantees a size-aligned allocation. And because Rust guarantees that the original size must be a multiple of alignment and the alignment must be a power of two, then the alignment requirement is satisfied. Suggested-by: Vlastimil Babka Co-developed-by: "Andreas Hindborg (Samsung)" Signed-off-by: "Andreas Hindborg (Samsung)" Signed-off-by: Boqun Feng Cc: stable@vger.kernel.org # v6.1+ Acked-by: Vlastimil Babka Fixes: 247b365dc8dc ("rust: add `kernel` crate") Link: https://github.com/Rust-for-Linux/linux/issues/974 Link: https://lore.kernel.org/r/20230730012905.643822-2-boqun.feng@gmail.com [ Applied rewording of comment as discussed in the mailing list. ] Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- rust/bindings/bindings_helper.h | 1 + rust/kernel/allocator.rs | 74 ++++++++++++++++++++++++++------- 2 files changed, 60 insertions(+), 15 deletions(-) diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index c48bc284214a..fdb4e11df3bd 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -9,5 +9,6 @@ #include /* `bindgen` gets confused at certain things. */ +const size_t BINDINGS_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN; const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL; const gfp_t BINDINGS___GFP_ZERO = __GFP_ZERO; diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs index 397a3dd57a9b..9363b527be66 100644 --- a/rust/kernel/allocator.rs +++ b/rust/kernel/allocator.rs @@ -9,6 +9,36 @@ use crate::bindings; struct KernelAllocator; +/// Calls `krealloc` with a proper size to alloc a new object aligned to `new_layout`'s alignment. +/// +/// # Safety +/// +/// - `ptr` can be either null or a pointer which has been allocated by this allocator. +/// - `new_layout` must have a non-zero size. +unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: bindings::gfp_t) -> *mut u8 { + // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first. + let layout = new_layout.pad_to_align(); + + let mut size = layout.size(); + + if layout.align() > bindings::BINDINGS_ARCH_SLAB_MINALIGN { + // The alignment requirement exceeds the slab guarantee, thus try to enlarge the size + // to use the "power-of-two" size/alignment guarantee (see comments in `kmalloc()` for + // more information). + // + // Note that `layout.size()` (after padding) is guaranteed to be a multiple of + // `layout.align()`, so `next_power_of_two` gives enough alignment guarantee. + size = size.next_power_of_two(); + } + + // SAFETY: + // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the + // function safety requirement. + // - `size` is greater than 0 since it's either a `layout.size()` (which cannot be zero + // according to the function safety requirement) or a result from `next_power_of_two()`. + unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags) as *mut u8 } +} + unsafe impl GlobalAlloc for KernelAllocator { unsafe fn alloc(&self, layout: Layout) -> *mut u8 { // `krealloc()` is used instead of `kmalloc()` because the latter is @@ -30,10 +60,20 @@ static ALLOCATOR: KernelAllocator = KernelAllocator; // to extract the object file that has them from the archive. For the moment, // let's generate them ourselves instead. // +// Note: Although these are *safe* functions, they are called by the compiler +// with parameters that obey the same `GlobalAlloc` function safety +// requirements: size and align should form a valid layout, and size is +// greater than 0. +// // Note that `#[no_mangle]` implies exported too, nowadays. #[no_mangle] -fn __rust_alloc(size: usize, _align: usize) -> *mut u8 { - unsafe { bindings::krealloc(core::ptr::null(), size, bindings::GFP_KERNEL) as *mut u8 } +fn __rust_alloc(size: usize, align: usize) -> *mut u8 { + // SAFETY: See assumption above. + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + + // SAFETY: `ptr::null_mut()` is null, per assumption above the size of `layout` is greater + // than 0. + unsafe { krealloc_aligned(ptr::null_mut(), layout, bindings::GFP_KERNEL) } } #[no_mangle] @@ -42,23 +82,27 @@ fn __rust_dealloc(ptr: *mut u8, _size: usize, _align: usize) { } #[no_mangle] -fn __rust_realloc(ptr: *mut u8, _old_size: usize, _align: usize, new_size: usize) -> *mut u8 { - unsafe { - bindings::krealloc( - ptr as *const core::ffi::c_void, - new_size, - bindings::GFP_KERNEL, - ) as *mut u8 - } +fn __rust_realloc(ptr: *mut u8, _old_size: usize, align: usize, new_size: usize) -> *mut u8 { + // SAFETY: See assumption above. + let new_layout = unsafe { Layout::from_size_align_unchecked(new_size, align) }; + + // SAFETY: Per assumption above, `ptr` is allocated by `__rust_*` before, and the size of + // `new_layout` is greater than 0. + unsafe { krealloc_aligned(ptr, new_layout, bindings::GFP_KERNEL) } } #[no_mangle] -fn __rust_alloc_zeroed(size: usize, _align: usize) -> *mut u8 { +fn __rust_alloc_zeroed(size: usize, align: usize) -> *mut u8 { + // SAFETY: See assumption above. + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + + // SAFETY: `ptr::null_mut()` is null, per assumption above the size of `layout` is greater + // than 0. unsafe { - bindings::krealloc( - core::ptr::null(), - size, + krealloc_aligned( + ptr::null_mut(), + layout, bindings::GFP_KERNEL | bindings::__GFP_ZERO, - ) as *mut u8 + ) } } From 645603ab5fa8b8765219016877a3bd797c00b384 Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Mon, 24 Jul 2023 16:51:56 +0200 Subject: [PATCH 0112/2093] scsi: zfcp: Defer fc_rport blocking until after ADISC response commit e65851989001c0c9ba9177564b13b38201c0854c upstream. Storage devices are free to send RSCNs, e.g. for internal state changes. If this happens on all connected paths, zfcp risks temporarily losing all paths at the same time. This has strong requirements on multipath configuration such as "no_path_retry queue". Avoid such situations by deferring fc_rport blocking until after the ADISC response, when any actual state change of the remote port became clear. The already existing port recovery triggers explicitly block the fc_rport. The triggers are: on ADISC reject or timeout (typical cable pull case), and on ADISC indicating that the remote port has changed its WWPN or the port is meanwhile no longer open. As a side effect, this also removes a confusing direct function call to another work item function zfcp_scsi_rport_work() instead of scheduling that other work item. It was probably done that way to have the rport block side effect immediate and synchronous to the caller. Fixes: a2fa0aede07c ("[SCSI] zfcp: Block FC transport rports early on errors") Cc: stable@vger.kernel.org #v2.6.30+ Reviewed-by: Benjamin Block Reviewed-by: Fedor Loshakov Signed-off-by: Steffen Maier Link: https://lore.kernel.org/r/20230724145156.3920244-1-maier@linux.ibm.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/s390/scsi/zfcp_fc.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index 77917b339870..a64def01d824 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -534,8 +534,7 @@ static void zfcp_fc_adisc_handler(void *data) /* re-init to undo drop from zfcp_fc_adisc() */ port->d_id = ntoh24(adisc_resp->adisc_port_id); - /* port is good, unblock rport without going through erp */ - zfcp_scsi_schedule_rport_register(port); + /* port is still good, nothing to do */ out: atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status); put_device(&port->dev); @@ -595,9 +594,6 @@ void zfcp_fc_link_test_work(struct work_struct *work) int retval; set_worker_desc("zadisc%16llx", port->wwpn); /* < WORKER_DESC_LEN=24 */ - get_device(&port->dev); - port->rport_task = RPORT_DEL; - zfcp_scsi_rport_work(&port->rport_work); /* only issue one test command at one time per port */ if (atomic_read(&port->status) & ZFCP_STATUS_PORT_LINK_TEST) From f62faadc791e1d5c06822859cb6b59428727e245 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 20 Jul 2023 14:05:02 -0700 Subject: [PATCH 0113/2093] scsi: storvsc: Limit max_sectors for virtual Fibre Channel devices commit 010c1e1c5741365dbbf44a5a5bb9f30192875c4c upstream. The Hyper-V host is queried to get the max transfer size that it supports, and this value is used to set max_sectors for the synthetic SCSI controller. However, this max transfer size may be too large for virtual Fibre Channel devices, which are limited to 512 Kbytes. If a larger transfer size is used with a vFC device, Hyper-V always returns an error, and storvsc logs a message like this where the SRB status and SCSI status are both zero: hv_storvsc : tag#197 cmd 0x8a status: scsi 0x0 srb 0x0 hv 0xc0000001 Add logic to limit the max transfer size to 512 Kbytes for vFC devices. Fixes: 1d3e0980782f ("scsi: storvsc: Correct reporting of Hyper-V I/O size limits") Cc: stable@vger.kernel.org Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1689887102-32806-1-git-send-email-mikelley@microsoft.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/storvsc_drv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5284f9a0b826..54a1b8514f04 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -365,6 +365,7 @@ static void storvsc_on_channel_callback(void *context); #define STORVSC_FC_MAX_LUNS_PER_TARGET 255 #define STORVSC_FC_MAX_TARGETS 128 #define STORVSC_FC_MAX_CHANNELS 8 +#define STORVSC_FC_MAX_XFER_SIZE ((u32)(512 * 1024)) #define STORVSC_IDE_MAX_LUNS_PER_TARGET 64 #define STORVSC_IDE_MAX_TARGETS 1 @@ -2002,6 +2003,9 @@ static int storvsc_probe(struct hv_device *device, * protecting it from any weird value. */ max_xfer_bytes = round_down(stor_device->max_transfer_bytes, HV_HYP_PAGE_SIZE); + if (is_fc) + max_xfer_bytes = min(max_xfer_bytes, STORVSC_FC_MAX_XFER_SIZE); + /* max_hw_sectors_kb */ host->max_sectors = max_xfer_bytes >> 9; /* From be52667ba24344199990e011cb7819640266799e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 1 Aug 2023 19:14:24 +0200 Subject: [PATCH 0114/2093] libceph: fix potential hang in ceph_osdc_notify() commit e6e2843230799230fc5deb8279728a7218b0d63c upstream. If the cluster becomes unavailable, ceph_osdc_notify() may hang even with osd_request_timeout option set because linger_notify_finish_wait() waits for MWatchNotify NOTIFY_COMPLETE message with no associated OSD request in flight -- it's completely asynchronous. Introduce an additional timeout, derived from the specified notify timeout. While at it, switch both waits to killable which is more correct. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Reviewed-by: Xiubo Li Signed-off-by: Greg Kroah-Hartman --- net/ceph/osd_client.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 4e4f1e4bc265..c22bb06b450e 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3334,17 +3334,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->reg_commit_wait); + ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } -static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq) +static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, + unsigned long timeout) { - int ret; + long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->notify_finish_wait); - return ret ?: lreq->notify_finish_error; + left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, + ceph_timeout_jiffies(timeout)); + if (left <= 0) + left = left ?: -ETIMEDOUT; + else + left = lreq->notify_finish_error; /* completed */ + + return left; } /* @@ -4896,7 +4903,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) - ret = linger_notify_finish_wait(lreq); + ret = linger_notify_finish_wait(lreq, + msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); From ad82aac732c22e043307933e13fe112682bfff0c Mon Sep 17 00:00:00 2001 From: Ross Maynard Date: Mon, 31 Jul 2023 15:42:04 +1000 Subject: [PATCH 0115/2093] USB: zaurus: Add ID for A-300/B-500/C-700 commit b99225b4fe297d07400f9e2332ecd7347b224f8d upstream. The SL-A300, B500/5600, and C700 devices no longer auto-load because of "usbnet: Remove over-broad module alias from zaurus." This patch adds IDs for those 3 devices. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217632 Fixes: 16adf5d07987 ("usbnet: Remove over-broad module alias from zaurus.") Signed-off-by: Ross Maynard Cc: stable@vger.kernel.org Acked-by: Greg Kroah-Hartman Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/69b5423b-2013-9fc9-9569-58e707d9bafb@bigpond.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/cdc_ether.c | 21 +++++++++++++++++++++ drivers/net/usb/zaurus.c | 21 +++++++++++++++++++++ 2 files changed, 42 insertions(+) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index fb5f59d0d55d..f07bfe56ec87 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -618,9 +618,23 @@ static const struct usb_device_id products[] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8005, /* A-300 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8006, /* B-500/SL-5600 */ ZAURUS_MASTER_INTERFACE, .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8006, /* B-500/SL-5600 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, @@ -628,6 +642,13 @@ static const struct usb_device_id products[] = { .idProduct = 0x8007, /* C-700 */ ZAURUS_MASTER_INTERFACE, .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8007, /* C-700 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, diff --git a/drivers/net/usb/zaurus.c b/drivers/net/usb/zaurus.c index 7984f2157d22..df3617c4c44e 100644 --- a/drivers/net/usb/zaurus.c +++ b/drivers/net/usb/zaurus.c @@ -289,9 +289,23 @@ static const struct usb_device_id products [] = { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, + .idProduct = 0x8005, /* A-300 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, .idProduct = 0x8006, /* B-500/SL-5600 */ ZAURUS_MASTER_INTERFACE, .driver_info = ZAURUS_PXA_INFO, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8006, /* B-500/SL-5600 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, @@ -299,6 +313,13 @@ static const struct usb_device_id products [] = { .idProduct = 0x8007, /* C-700 */ ZAURUS_MASTER_INTERFACE, .driver_info = ZAURUS_PXA_INFO, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x8007, /* C-700 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, From a062da58ed97d1f16a564619726e77ba528c5191 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 25 Jul 2023 12:03:59 +0800 Subject: [PATCH 0116/2093] ceph: defer stopping mdsc delayed_work commit e7e607bd00481745550389a29ecabe33e13d67cf upstream. Flushing the dirty buffer may take a long time if the cluster is overloaded or if there is network issue. So we should ping the MDSs periodically to keep alive, else the MDS will blocklist the kclient. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61843 Signed-off-by: Xiubo Li Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/mds_client.c | 4 ++-- fs/ceph/mds_client.h | 5 +++++ fs/ceph/super.c | 10 ++++++++++ 3 files changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1989c8deea55..dcabe2783edf 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4758,7 +4758,7 @@ static void delayed_work(struct work_struct *work) dout("mdsc delayed_work\n"); - if (mdsc->stopping) + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED) return; mutex_lock(&mdsc->mutex); @@ -4937,7 +4937,7 @@ void send_flush_mdlog(struct ceph_mds_session *s) void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) { dout("pre_umount\n"); - mdsc->stopping = 1; + mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN; ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true); ceph_mdsc_iterate_sessions(mdsc, lock_unlock_session, false); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 18b026b1ac63..9a80658f4167 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -380,6 +380,11 @@ struct cap_wait { int want; }; +enum { + CEPH_MDSC_STOPPING_BEGIN = 1, + CEPH_MDSC_STOPPING_FLUSHED = 2, +}; + /* * mds client state */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 3fc48b43cab0..a5f52013314d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1374,6 +1374,16 @@ static void ceph_kill_sb(struct super_block *s) ceph_mdsc_pre_umount(fsc->mdsc); flush_fs_workqueues(fsc); + /* + * Though the kill_anon_super() will finally trigger the + * sync_filesystem() anyway, we still need to do it here + * and then bump the stage of shutdown to stop the work + * queue as earlier as possible. + */ + sync_filesystem(s); + + fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; + kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; From bc41119995e41ca19a06ea464a2d2cab875ac2ad Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 19 Jul 2023 08:16:52 +0200 Subject: [PATCH 0117/2093] firmware: arm_scmi: Drop OF node reference in the transport channel setup commit da042eb4f061a0b54aedadcaa15391490c48e1ad upstream. The OF node reference obtained from of_parse_phandle() should be dropped if node is not compatible with arm,scmi-shmem. Fixes: 507cd4d2c5eb ("firmware: arm_scmi: Add compatibility checks for shmem node") Cc: Signed-off-by: Krzysztof Kozlowski Reviewed-by: Cristian Marussi Link: https://lore.kernel.org/r/20230719061652.8850-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sudeep Holla Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/arm_scmi/mailbox.c | 4 +++- drivers/firmware/arm_scmi/smc.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index a455f3c0e98b..25d31dfdad15 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -106,8 +106,10 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return -ENOMEM; shmem = of_parse_phandle(cdev->of_node, "shmem", idx); - if (!of_device_is_compatible(shmem, "arm,scmi-shmem")) + if (!of_device_is_compatible(shmem, "arm,scmi-shmem")) { + of_node_put(shmem); return -ENXIO; + } ret = of_address_to_resource(shmem, 0, &res); of_node_put(shmem); diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index dc383d874ee3..ac0bd51ef16a 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -118,8 +118,10 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return -ENOMEM; np = of_parse_phandle(cdev->of_node, "shmem", 0); - if (!of_device_is_compatible(np, "arm,scmi-shmem")) + if (!of_device_is_compatible(np, "arm,scmi-shmem")) { + of_node_put(np); return -ENXIO; + } ret = of_address_to_resource(np, 0, &res); of_node_put(np); From 1427a7e96fb90d0896f74f5bcd21feb03cc7c3d0 Mon Sep 17 00:00:00 2001 From: gaoming Date: Wed, 5 Jul 2023 15:15:15 +0800 Subject: [PATCH 0118/2093] exfat: use kvmalloc_array/kvfree instead of kmalloc_array/kfree commit daf60d6cca26e50d65dac374db92e58de745ad26 upstream. The call stack shown below is a scenario in the Linux 4.19 kernel. Allocating memory failed where exfat fs use kmalloc_array due to system memory fragmentation, while the u-disk was inserted without recognition. Devices such as u-disk using the exfat file system are pluggable and may be insert into the system at any time. However, long-term running systems cannot guarantee the continuity of physical memory. Therefore, it's necessary to address this issue. Binder:2632_6: page allocation failure: order:4, mode:0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null) Call trace: [242178.097582] dump_backtrace+0x0/0x4 [242178.097589] dump_stack+0xf4/0x134 [242178.097598] warn_alloc+0xd8/0x144 [242178.097603] __alloc_pages_nodemask+0x1364/0x1384 [242178.097608] kmalloc_order+0x2c/0x510 [242178.097612] kmalloc_order_trace+0x40/0x16c [242178.097618] __kmalloc+0x360/0x408 [242178.097624] load_alloc_bitmap+0x160/0x284 [242178.097628] exfat_fill_super+0xa3c/0xe7c [242178.097635] mount_bdev+0x2e8/0x3a0 [242178.097638] exfat_fs_mount+0x40/0x50 [242178.097643] mount_fs+0x138/0x2e8 [242178.097649] vfs_kern_mount+0x90/0x270 [242178.097655] do_mount+0x798/0x173c [242178.097659] ksys_mount+0x114/0x1ac [242178.097665] __arm64_sys_mount+0x24/0x34 [242178.097671] el0_svc_common+0xb8/0x1b8 [242178.097676] el0_svc_handler+0x74/0x90 [242178.097681] el0_svc+0x8/0x340 By analyzing the exfat code,we found that continuous physical memory is not required here,so kvmalloc_array is used can solve this problem. Cc: stable@vger.kernel.org Signed-off-by: gaoming Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman --- fs/exfat/balloc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 9f42f25fab92..e918decb3735 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -69,7 +69,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, } sbi->map_sectors = ((need_map_size - 1) >> (sb->s_blocksize_bits)) + 1; - sbi->vol_amap = kmalloc_array(sbi->map_sectors, + sbi->vol_amap = kvmalloc_array(sbi->map_sectors, sizeof(struct buffer_head *), GFP_KERNEL); if (!sbi->vol_amap) return -ENOMEM; @@ -84,7 +84,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, while (j < i) brelse(sbi->vol_amap[j++]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); sbi->vol_amap = NULL; return -EIO; } @@ -138,7 +138,7 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi) for (i = 0; i < sbi->map_sectors; i++) __brelse(sbi->vol_amap[i]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); } int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) From 724ce05212d02947d5b0575dc306743ba50a1304 Mon Sep 17 00:00:00 2001 From: Sungjong Seo Date: Fri, 14 Jul 2023 17:43:54 +0900 Subject: [PATCH 0119/2093] exfat: release s_lock before calling dir_emit() commit ff84772fd45d486e4fc78c82e2f70ce5333543e6 upstream. There is a potential deadlock reported by syzbot as below: ====================================================== WARNING: possible circular locking dependency detected 6.4.0-next-20230707-syzkaller #0 Not tainted ------------------------------------------------------ syz-executor330/5073 is trying to acquire lock: ffff8880218527a0 (&mm->mmap_lock){++++}-{3:3}, at: mmap_read_lock_killable include/linux/mmap_lock.h:151 [inline] ffff8880218527a0 (&mm->mmap_lock){++++}-{3:3}, at: get_mmap_lock_carefully mm/memory.c:5293 [inline] ffff8880218527a0 (&mm->mmap_lock){++++}-{3:3}, at: lock_mm_and_find_vma+0x369/0x510 mm/memory.c:5344 but task is already holding lock: ffff888019f760e0 (&sbi->s_lock){+.+.}-{3:3}, at: exfat_iterate+0x117/0xb50 fs/exfat/dir.c:232 which lock already depends on the new lock. Chain exists of: &mm->mmap_lock --> mapping.invalidate_lock#3 --> &sbi->s_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sbi->s_lock); lock(mapping.invalidate_lock#3); lock(&sbi->s_lock); rlock(&mm->mmap_lock); Let's try to avoid above potential deadlock condition by moving dir_emit*() out of sbi->s_lock coverage. Fixes: ca06197382bd ("exfat: add directory operations") Cc: stable@vger.kernel.org #v5.7+ Reported-by: syzbot+1741a5d9b79989c10bdc@syzkaller.appspotmail.com Link: https://lore.kernel.org/lkml/00000000000078ee7e060066270b@google.com/T/#u Tested-by: syzbot+1741a5d9b79989c10bdc@syzkaller.appspotmail.com Signed-off-by: Sungjong Seo Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman --- fs/exfat/dir.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 15c4f901be36..78de6f67f882 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -210,7 +210,10 @@ static void exfat_free_namebuf(struct exfat_dentry_namebuf *nb) exfat_init_namebuf(nb); } -/* skip iterating emit_dots when dir is empty */ +/* + * Before calling dir_emit*(), sbi->s_lock should be released + * because page fault can occur in dir_emit*(). + */ #define ITER_POS_FILLED_DOTS (2) static int exfat_iterate(struct file *file, struct dir_context *ctx) { @@ -225,11 +228,10 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) int err = 0, fake_offset = 0; exfat_init_namebuf(nb); - mutex_lock(&EXFAT_SB(sb)->s_lock); cpos = ctx->pos; if (!dir_emit_dots(file, ctx)) - goto unlock; + goto out; if (ctx->pos == ITER_POS_FILLED_DOTS) { cpos = 0; @@ -241,16 +243,18 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) /* name buffer should be allocated before use */ err = exfat_alloc_namebuf(nb); if (err) - goto unlock; + goto out; get_new: + mutex_lock(&EXFAT_SB(sb)->s_lock); + if (ei->flags == ALLOC_NO_FAT_CHAIN && cpos >= i_size_read(inode)) goto end_of_dir; err = exfat_readdir(inode, &cpos, &de); if (err) { /* - * At least we tried to read a sector. Move cpos to next sector - * position (should be aligned). + * At least we tried to read a sector. + * Move cpos to next sector position (should be aligned). */ if (err == -EIO) { cpos += 1 << (sb->s_blocksize_bits); @@ -273,16 +277,10 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) inum = iunique(sb, EXFAT_ROOT_INO); } - /* - * Before calling dir_emit(), sb_lock should be released. - * Because page fault can occur in dir_emit() when the size - * of buffer given from user is larger than one page size. - */ mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) - goto out_unlocked; - mutex_lock(&EXFAT_SB(sb)->s_lock); + goto out; ctx->pos = cpos; goto get_new; @@ -290,9 +288,8 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) if (!cpos && fake_offset) cpos = ITER_POS_FILLED_DOTS; ctx->pos = cpos; -unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); -out_unlocked: +out: /* * To improve performance, free namebuf after unlock sb_lock. * If namebuf is not allocated, this function do nothing From 67327cadba59d5c78c1a8a979270d175a147e548 Mon Sep 17 00:00:00 2001 From: Olivier Maignial Date: Fri, 23 Jun 2023 17:33:36 +0200 Subject: [PATCH 0120/2093] mtd: spinand: toshiba: Fix ecc_get_status commit 8544cda94dae6be3f1359539079c68bb731428b1 upstream. Reading ECC status is failing. tx58cxgxsxraix_ecc_get_status() is using on-stack buffer for SPINAND_GET_FEATURE_OP() output. It is not suitable for DMA needs of spi-mem. Fix this by using the spi-mem operations dedicated buffer spinand->scratchbuf. See spinand->scratchbuf: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/linux/mtd/spinand.h?h=v6.3#n418 spi_mem_check_op(): https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/spi/spi-mem.c?h=v6.3#n199 Fixes: 10949af1681d ("mtd: spinand: Add initial support for Toshiba TC58CVG2S0H") Cc: stable@vger.kernel.org Signed-off-by: Olivier Maignial Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/DB4P250MB1032553D05FBE36DEE0D311EFE23A@DB4P250MB1032.EURP250.PROD.OUTLOOK.COM Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/spi/toshiba.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c index 7380b1ebaccd..a80427c13121 100644 --- a/drivers/mtd/nand/spi/toshiba.c +++ b/drivers/mtd/nand/spi/toshiba.c @@ -73,7 +73,7 @@ static int tx58cxgxsxraix_ecc_get_status(struct spinand_device *spinand, { struct nand_device *nand = spinand_to_nand(spinand); u8 mbf = 0; - struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, &mbf); + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, spinand->scratchbuf); switch (status & STATUS_ECC_MASK) { case STATUS_ECC_NO_BITFLIPS: @@ -92,7 +92,7 @@ static int tx58cxgxsxraix_ecc_get_status(struct spinand_device *spinand, if (spi_mem_exec_op(spinand->spimem, &op)) return nanddev_get_ecc_conf(nand)->strength; - mbf >>= 4; + mbf = *(spinand->scratchbuf) >> 4; if (WARN_ON(mbf > nanddev_get_ecc_conf(nand)->strength || !mbf)) return nanddev_get_ecc_conf(nand)->strength; From 680f4d8aec1bdc5d2cec2891b162aab20e2bb977 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Wed, 5 Jul 2023 09:52:10 +0300 Subject: [PATCH 0121/2093] mtd: rawnand: meson: fix OOB available bytes for ECC commit 7e6b04f9238eab0f684fafd158c1f32ea65b9eaa upstream. It is incorrect to calculate number of OOB bytes for ECC engine using some "already known" ECC step size (1024 bytes here). Number of such bytes for ECC engine must be whole OOB except 2 bytes for bad block marker, while proper ECC step size and strength will be selected by ECC logic. Fixes: 8fae856c5350 ("mtd: rawnand: meson: add support for Amlogic NAND flash controller") Cc: Signed-off-by: Arseniy Krasnov Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230705065211.293500-1-AVKrasnov@sberdevices.ru Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/meson_nand.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 029a2a302aa6..ac4947f72047 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -1184,7 +1184,6 @@ static int meson_nand_attach_chip(struct nand_chip *nand) struct meson_nfc *nfc = nand_get_controller_data(nand); struct meson_nfc_nand_chip *meson_chip = to_meson_nand(nand); struct mtd_info *mtd = nand_to_mtd(nand); - int nsectors = mtd->writesize / 1024; int ret; if (!mtd->name) { @@ -1202,7 +1201,7 @@ static int meson_nand_attach_chip(struct nand_chip *nand) nand->options |= NAND_NO_SUBPAGE_WRITE; ret = nand_ecc_choose_conf(nand, nfc->data->ecc_caps, - mtd->oobsize - 2 * nsectors); + mtd->oobsize - 2); if (ret) { dev_err(nfc->dev, "failed to ECC init\n"); return -EINVAL; From 3654ed5daf492463c3faa434c7000d45c2da2ace Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Jul 2023 10:42:05 +0200 Subject: [PATCH 0122/2093] bpf: Disable preemption in bpf_perf_event_output commit f2c67a3e60d1071b65848efaa8c3b66c363dd025 upstream. The nesting protection in bpf_perf_event_output relies on disabled preemption, which is guaranteed for kprobes and tracepoints. However bpf_perf_event_output can be also called from uprobes context through bpf_prog_run_array_sleepable function which disables migration, but keeps preemption enabled. This can cause task to be preempted by another one inside the nesting protection and lead eventually to two tasks using same perf_sample_data buffer and cause crashes like: kernel tried to execute NX-protected page - exploit attempt? (uid: 0) BUG: unable to handle page fault for address: ffffffff82be3eea ... Call Trace: ? __die+0x1f/0x70 ? page_fault_oops+0x176/0x4d0 ? exc_page_fault+0x132/0x230 ? asm_exc_page_fault+0x22/0x30 ? perf_output_sample+0x12b/0x910 ? perf_event_output+0xd0/0x1d0 ? bpf_perf_event_output+0x162/0x1d0 ? bpf_prog_c6271286d9a4c938_krava1+0x76/0x87 ? __uprobe_perf_func+0x12b/0x540 ? uprobe_dispatcher+0x2c4/0x430 ? uprobe_notify_resume+0x2da/0xce0 ? atomic_notifier_call_chain+0x7b/0x110 ? exit_to_user_mode_prepare+0x13e/0x290 ? irqentry_exit_to_user_mode+0x5/0x30 ? asm_exc_int3+0x35/0x40 Fixing this by disabling preemption in bpf_perf_event_output. Cc: stable@vger.kernel.org Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps") Acked-by: Hou Tao Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20230725084206.580930-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- kernel/trace/bpf_trace.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1642548892a8..916cffbe4fe7 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -662,8 +662,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); - int nest_level = this_cpu_inc_return(bpf_trace_nest_level); + struct bpf_trace_sample_data *sds; struct perf_raw_record raw = { .frag = { .size = size, @@ -671,7 +670,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, }, }; struct perf_sample_data *sd; - int err; + int nest_level, err; + + preempt_disable(); + sds = this_cpu_ptr(&bpf_trace_sds); + nest_level = this_cpu_inc_return(bpf_trace_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; @@ -690,9 +693,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, sd->sample_flags |= PERF_SAMPLE_RAW; err = __bpf_perf_event_output(regs, map, flags, sd); - out: this_cpu_dec(bpf_trace_nest_level); + preempt_enable(); return err; } From 367fdf369dc79539648db226a942846304c11ed5 Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Tue, 11 Jul 2023 15:44:30 -0500 Subject: [PATCH 0123/2093] arm64: dts: stratix10: fix incorrect I2C property for SCL signal commit db66795f61354c373ecdadbdae1ed253a96c47cb upstream. The correct dts property for the SCL falling time is "i2c-scl-falling-time-ns". Fixes: c8da1d15b8a4 ("arm64: dts: stratix10: i2c clock running out of spec") Cc: stable@vger.kernel.org Signed-off-by: Dinh Nguyen Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts | 2 +- arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index 48424e459f12..15b5651b88d0 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -128,7 +128,7 @@ &i2c1 { status = "okay"; clock-frequency = <100000>; i2c-sda-falling-time-ns = <890>; /* hcnt */ - i2c-sdl-falling-time-ns = <890>; /* lcnt */ + i2c-scl-falling-time-ns = <890>; /* lcnt */ adc@14 { compatible = "lltc,ltc2497"; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index 847a7c01f5af..fcf640de90b6 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -141,7 +141,7 @@ &i2c2 { status = "okay"; clock-frequency = <100000>; i2c-sda-falling-time-ns = <890>; /* hcnt */ - i2c-sdl-falling-time-ns = <890>; /* lcnt */ + i2c-scl-falling-time-ns = <890>; /* lcnt */ adc@14 { compatible = "lltc,ltc2497"; From b6846d7c408b33e4701f4f5ca28932e2a08e0a2e Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Mon, 31 Jul 2023 18:42:36 +0200 Subject: [PATCH 0124/2093] net: tun_chr_open(): set sk_uid from current_fsuid() commit 9bc3047374d5bec163e83e743709e23753376f0c upstream. Commit a096ccca6e50 initializes the "sk_uid" field in the protocol socket (struct sock) from the "/dev/net/tun" device node's owner UID. Per original commit 86741ec25462 ("net: core: Add a UID field to struct sock.", 2016-11-04), that's wrong: the idea is to cache the UID of the userspace process that creates the socket. Commit 86741ec25462 mentions socket() and accept(); with "tun", the action that creates the socket is open("/dev/net/tun"). Therefore the device node's owner UID is irrelevant. In most cases, "/dev/net/tun" will be owned by root, so in practice, commit a096ccca6e50 has no observable effect: - before, "sk_uid" would be zero, due to undefined behavior (CVE-2023-1076), - after, "sk_uid" would be zero, due to "/dev/net/tun" being owned by root. What matters is the (fs)UID of the process performing the open(), so cache that in "sk_uid". Cc: Eric Dumazet Cc: Lorenzo Colitti Cc: Paolo Abeni Cc: Pietro Borrello Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Fixes: a096ccca6e50 ("tun: tun_chr_open(): correctly initialize socket uid") Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2173435 Signed-off-by: Laszlo Ersek Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/tun.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7c8db8f6f661..228f5f9ef1dd 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3457,7 +3457,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); + sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; From 767800fc402deac438c5aed9c82f0e71a70c86fd Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Mon, 31 Jul 2023 18:42:37 +0200 Subject: [PATCH 0125/2093] net: tap_open(): set sk_uid from current_fsuid() commit 5c9241f3ceab3257abe2923a59950db0dc8bb737 upstream. Commit 66b2c338adce initializes the "sk_uid" field in the protocol socket (struct sock) from the "/dev/tapX" device node's owner UID. Per original commit 86741ec25462 ("net: core: Add a UID field to struct sock.", 2016-11-04), that's wrong: the idea is to cache the UID of the userspace process that creates the socket. Commit 86741ec25462 mentions socket() and accept(); with "tap", the action that creates the socket is open("/dev/tapX"). Therefore the device node's owner UID is irrelevant. In most cases, "/dev/tapX" will be owned by root, so in practice, commit 66b2c338adce has no observable effect: - before, "sk_uid" would be zero, due to undefined behavior (CVE-2023-1076), - after, "sk_uid" would be zero, due to "/dev/tapX" being owned by root. What matters is the (fs)UID of the process performing the open(), so cache that in "sk_uid". Cc: Eric Dumazet Cc: Lorenzo Colitti Cc: Paolo Abeni Cc: Pietro Borrello Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 66b2c338adce ("tap: tap_open(): correctly initialize socket uid") Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2173435 Signed-off-by: Laszlo Ersek Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/tap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 3c468ef8f245..8c010857e6d7 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -533,7 +533,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); + sock_init_data_uid(&q->sock, &q->sk, current_fsuid()); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; From 0526119bf59e6729b57535eb52dab28b7fbfe00e Mon Sep 17 00:00:00 2001 From: Paul Fertser Date: Mon, 5 Jun 2023 10:34:07 +0300 Subject: [PATCH 0126/2093] wifi: mt76: mt7615: do not advertise 5 GHz on first phy of MT7615D (DBDC) commit 421033deb91521aa6a9255e495cb106741a52275 upstream. On DBDC devices the first (internal) phy is only capable of using 2.4 GHz band, and the 5 GHz band is exposed via a separate phy object, so avoid the false advertising. Reported-by: Rani Hod Closes: https://github.com/openwrt/openwrt/pull/12361 Fixes: 7660a1bd0c22 ("mt76: mt7615: register ext_phy if DBDC is detected") Cc: stable@vger.kernel.org Signed-off-by: Paul Fertser Reviewed-by: Simon Horman Acked-by: Felix Fietkau Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230605073408.8699-1-fercerpav@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c index 6dbaaf95ee38..2092aa373ab3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c @@ -123,12 +123,12 @@ mt7615_eeprom_parse_hw_band_cap(struct mt7615_dev *dev) case MT_EE_5GHZ: dev->mphy.cap.has_5ghz = true; break; - case MT_EE_2GHZ: - dev->mphy.cap.has_2ghz = true; - break; case MT_EE_DBDC: dev->dbdc_support = true; fallthrough; + case MT_EE_2GHZ: + dev->mphy.cap.has_2ghz = true; + break; default: dev->mphy.cap.has_2ghz = true; dev->mphy.cap.has_5ghz = true; From 98cccbd0a19a161971bc7f7feb10577adc62c400 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 21 Jul 2023 21:51:16 -0700 Subject: [PATCH 0127/2093] x86/hyperv: Disable IBT when hypercall page lacks ENDBR instruction commit d5ace2a776442d80674eff9ed42e737f7dd95056 upstream. On hardware that supports Indirect Branch Tracking (IBT), Hyper-V VMs with ConfigVersion 9.3 or later support IBT in the guest. However, current versions of Hyper-V have a bug in that there's not an ENDBR64 instruction at the beginning of the hypercall page. Since hypercalls are made with an indirect call to the hypercall page, all hypercall attempts fail with an exception and Linux panics. A Hyper-V fix is in progress to add ENDBR64. But guard against the Linux panic by clearing X86_FEATURE_IBT if the hypercall page doesn't start with ENDBR. The VM will boot and run without IBT. If future Linux 32-bit kernels were to support IBT, additional hypercall page hackery would be needed to make IBT work for such kernels in a Hyper-V VM. Cc: stable@vger.kernel.org Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1690001476-98594-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu Signed-off-by: Greg Kroah-Hartman --- arch/x86/hyperv/hv_init.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 85863b9c9e68..189ae92de4d0 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -467,6 +468,26 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); } + /* + * Some versions of Hyper-V that provide IBT in guest VMs have a bug + * in that there's no ENDBR64 instruction at the entry to the + * hypercall page. Because hypercalls are invoked via an indirect call + * to the hypercall page, all hypercall attempts fail when IBT is + * enabled, and Linux panics. For such buggy versions, disable IBT. + * + * Fixed versions of Hyper-V always provide ENDBR64 on the hypercall + * page, so if future Linux kernel versions enable IBT for 32-bit + * builds, additional hypercall page hackery will be required here + * to provide an ENDBR32. + */ +#ifdef CONFIG_X86_KERNEL_IBT + if (cpu_feature_enabled(X86_FEATURE_IBT) && + *(u32 *)hv_hypercall_pg != gen_endbr()) { + setup_clear_cpu_cap(X86_FEATURE_IBT); + pr_warn("Hyper-V: Disabling IBT because of Hyper-V bug\n"); + } +#endif + /* * hyperv_init() is called before LAPIC is initialized: see * apic_intr_mode_init() -> x86_platform.apic_post_init() and From ec062367fa0ce5609b45babbde9360f2f8c460b5 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 1 Aug 2023 19:14:24 +0200 Subject: [PATCH 0128/2093] rbd: prevent busy loop when requesting exclusive lock commit 9d01e07fd1bfb4daae156ab528aa196f5ac2b2bc upstream. Due to rbd_try_acquire_lock() effectively swallowing all but EBLOCKLISTED error from rbd_try_lock() ("request lock anyway") and rbd_request_lock() returning ETIMEDOUT error not only for an actual notify timeout but also when the lock owner doesn't respond, a busy loop inside of rbd_acquire_lock() between rbd_try_acquire_lock() and rbd_request_lock() is possible. Requesting the lock on EBUSY error (returned by get_lock_owner_info() if an incompatible lock or invalid lock owner is detected) makes very little sense. The same goes for ETIMEDOUT error (might pop up pretty much anywhere if osd_request_timeout option is set) and many others. Just fail I/O requests on rbd_dev->acquiring_list immediately on any error from rbd_try_lock(). Cc: stable@vger.kernel.org # 588159009d5b: rbd: retrieve and check lock owner twice before blocklisting Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index daec0321cd76..74ef3da54536 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3676,7 +3676,7 @@ static int rbd_lock(struct rbd_device *rbd_dev) ret = ceph_cls_lock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, RBD_LOCK_NAME, CEPH_CLS_LOCK_EXCLUSIVE, cookie, RBD_LOCK_TAG, "", 0); - if (ret) + if (ret && ret != -EEXIST) return ret; __rbd_lock(rbd_dev, cookie); @@ -3879,7 +3879,7 @@ static struct ceph_locker *get_lock_owner_info(struct rbd_device *rbd_dev) &rbd_dev->header_oloc, RBD_LOCK_NAME, &lock_type, &lock_tag, &lockers, &num_lockers); if (ret) { - rbd_warn(rbd_dev, "failed to retrieve lockers: %d", ret); + rbd_warn(rbd_dev, "failed to get header lockers: %d", ret); return ERR_PTR(ret); } @@ -3941,8 +3941,10 @@ static int find_watcher(struct rbd_device *rbd_dev, ret = ceph_osdc_list_watchers(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, &watchers, &num_watchers); - if (ret) + if (ret) { + rbd_warn(rbd_dev, "failed to get watchers: %d", ret); return ret; + } sscanf(locker->id.cookie, RBD_LOCK_COOKIE_PREFIX " %llu", &cookie); for (i = 0; i < num_watchers; i++) { @@ -3986,8 +3988,12 @@ static int rbd_try_lock(struct rbd_device *rbd_dev) locker = refreshed_locker = NULL; ret = rbd_lock(rbd_dev); - if (ret != -EBUSY) + if (!ret) goto out; + if (ret != -EBUSY) { + rbd_warn(rbd_dev, "failed to lock header: %d", ret); + goto out; + } /* determine if the current lock holder is still alive */ locker = get_lock_owner_info(rbd_dev); @@ -4090,11 +4096,8 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev) ret = rbd_try_lock(rbd_dev); if (ret < 0) { - rbd_warn(rbd_dev, "failed to lock header: %d", ret); - if (ret == -EBLOCKLISTED) - goto out; - - ret = 1; /* request lock anyway */ + rbd_warn(rbd_dev, "failed to acquire lock: %d", ret); + goto out; } if (ret > 0) { up_write(&rbd_dev->lock_rwsem); @@ -6628,12 +6631,11 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) cancel_delayed_work_sync(&rbd_dev->lock_dwork); if (!ret) ret = -ETIMEDOUT; - } - if (ret) { - rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret); - return ret; + rbd_warn(rbd_dev, "failed to acquire lock: %ld", ret); } + if (ret) + return ret; /* * The lock may have been released by now, unless automatic lock From 36dd8ca330b76585640ed32255a3c99f901e1502 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Jul 2023 10:42:06 +0200 Subject: [PATCH 0129/2093] bpf: Disable preemption in bpf_event_output commit d62cc390c2e99ae267ffe4b8d7e2e08b6c758c32 upstream. We received report [1] of kernel crash, which is caused by using nesting protection without disabled preemption. The bpf_event_output can be called by programs executed by bpf_prog_run_array_cg function that disabled migration but keeps preemption enabled. This can cause task to be preempted by another one inside the nesting protection and lead eventually to two tasks using same perf_sample_data buffer and cause crashes like: BUG: kernel NULL pointer dereference, address: 0000000000000001 #PF: supervisor instruction fetch in kernel mode #PF: error_code(0x0010) - not-present page ... ? perf_output_sample+0x12a/0x9a0 ? finish_task_switch.isra.0+0x81/0x280 ? perf_event_output+0x66/0xa0 ? bpf_event_output+0x13a/0x190 ? bpf_event_output_data+0x22/0x40 ? bpf_prog_dfc84bbde731b257_cil_sock4_connect+0x40a/0xacb ? xa_load+0x87/0xe0 ? __cgroup_bpf_run_filter_sock_addr+0xc1/0x1a0 ? release_sock+0x3e/0x90 ? sk_setsockopt+0x1a1/0x12f0 ? udp_pre_connect+0x36/0x50 ? inet_dgram_connect+0x93/0xa0 ? __sys_connect+0xb4/0xe0 ? udp_setsockopt+0x27/0x40 ? __pfx_udp_push_pending_frames+0x10/0x10 ? __sys_setsockopt+0xdf/0x1a0 ? __x64_sys_connect+0xf/0x20 ? do_syscall_64+0x3a/0x90 ? entry_SYSCALL_64_after_hwframe+0x72/0xdc Fixing this by disabling preemption in bpf_event_output. [1] https://github.com/cilium/cilium/issues/26756 Cc: stable@vger.kernel.org Reported-by: Oleg "livelace" Popov Closes: https://github.com/cilium/cilium/issues/26756 Fixes: 2a916f2f546c ("bpf: Use migrate_disable/enable in array macros and cgroup/lirc code.") Acked-by: Hou Tao Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20230725084206.580930-3-jolsa@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- kernel/trace/bpf_trace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 916cffbe4fe7..ad04390883ad 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -720,7 +720,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, @@ -737,8 +736,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, }; struct perf_sample_data *sd; struct pt_regs *regs; + int nest_level; u64 ret; + preempt_disable(); + nest_level = this_cpu_inc_return(bpf_event_output_nest_level); + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; @@ -754,6 +757,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, ret = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_event_output_nest_level); + preempt_enable(); return ret; } From b8ea2a46913bc420b140a009aca02abc85f34242 Mon Sep 17 00:00:00 2001 From: Naveen N Rao Date: Wed, 21 Jun 2023 10:43:49 +0530 Subject: [PATCH 0130/2093] powerpc/ftrace: Create a dummy stackframe to fix stack unwind commit 41a506ef71eb38d94fe133f565c87c3e06ccc072 upstream. With ppc64 -mprofile-kernel and ppc32 -pg, profiling instructions to call into ftrace are emitted right at function entry. The instruction sequence used is minimal to reduce overhead. Crucially, a stackframe is not created for the function being traced. This breaks stack unwinding since the function being traced does not have a stackframe for itself. As such, it never shows up in the backtrace: /sys/kernel/debug/tracing # echo 1 > /proc/sys/kernel/stack_tracer_enabled /sys/kernel/debug/tracing # cat stack_trace Depth Size Location (17 entries) ----- ---- -------- 0) 4144 32 ftrace_call+0x4/0x44 1) 4112 432 get_page_from_freelist+0x26c/0x1ad0 2) 3680 496 __alloc_pages+0x290/0x1280 3) 3184 336 __folio_alloc+0x34/0x90 4) 2848 176 vma_alloc_folio+0xd8/0x540 5) 2672 272 __handle_mm_fault+0x700/0x1cc0 6) 2400 208 handle_mm_fault+0xf0/0x3f0 7) 2192 80 ___do_page_fault+0x3e4/0xbe0 8) 2112 160 do_page_fault+0x30/0xc0 9) 1952 256 data_access_common_virt+0x210/0x220 10) 1696 400 0xc00000000f16b100 11) 1296 384 load_elf_binary+0x804/0x1b80 12) 912 208 bprm_execve+0x2d8/0x7e0 13) 704 64 do_execveat_common+0x1d0/0x2f0 14) 640 160 sys_execve+0x54/0x70 15) 480 64 system_call_exception+0x138/0x350 16) 416 416 system_call_common+0x160/0x2c4 Fix this by having ftrace create a dummy stackframe for the function being traced. With this, backtraces now capture the function being traced: /sys/kernel/debug/tracing # cat stack_trace Depth Size Location (17 entries) ----- ---- -------- 0) 3888 32 _raw_spin_trylock+0x8/0x70 1) 3856 576 get_page_from_freelist+0x26c/0x1ad0 2) 3280 64 __alloc_pages+0x290/0x1280 3) 3216 336 __folio_alloc+0x34/0x90 4) 2880 176 vma_alloc_folio+0xd8/0x540 5) 2704 416 __handle_mm_fault+0x700/0x1cc0 6) 2288 96 handle_mm_fault+0xf0/0x3f0 7) 2192 48 ___do_page_fault+0x3e4/0xbe0 8) 2144 192 do_page_fault+0x30/0xc0 9) 1952 608 data_access_common_virt+0x210/0x220 10) 1344 16 0xc0000000334bbb50 11) 1328 416 load_elf_binary+0x804/0x1b80 12) 912 64 bprm_execve+0x2d8/0x7e0 13) 848 176 do_execveat_common+0x1d0/0x2f0 14) 672 192 sys_execve+0x54/0x70 15) 480 64 system_call_exception+0x138/0x350 16) 416 416 system_call_common+0x160/0x2c4 This results in two additional stores in the ftrace entry code, but produces reliable backtraces. Fixes: 153086644fd1 ("powerpc/ftrace: Add support for -mprofile-kernel ftrace ABI") Cc: stable@vger.kernel.org Signed-off-by: Naveen N Rao Signed-off-by: Michael Ellerman Link: https://msgid.link/20230621051349.759567-1-naveen@kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/trace/ftrace_mprofile.S | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index d031093bc436..6f9c2dea905b 100644 --- a/arch/powerpc/kernel/trace/ftrace_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -33,6 +33,9 @@ * and then arrange for the ftrace function to be called. */ .macro ftrace_regs_entry allregs + /* Create a minimal stack frame for representing B */ + PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1) + /* Create our stack frame + pt_regs */ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) @@ -42,7 +45,7 @@ #ifdef CONFIG_PPC64 /* Save the original return address in A's stack frame */ - std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) + std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 @@ -77,6 +80,8 @@ mflr r7 /* Save it as pt_regs->nip */ PPC_STL r7, _NIP(r1) + /* Also save it in B's stackframe header for proper unwind */ + PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Save the read LR in pt_regs->link */ PPC_STL r0, _LINK(r1) @@ -142,7 +147,7 @@ #endif /* Pop our stack frame */ - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE #ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ From bae353469a282d4a0ac27f07a0ba5137ad1a049d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 Aug 2023 19:33:23 +0100 Subject: [PATCH 0131/2093] arm64/fpsimd: Sync and zero pad FPSIMD state for streaming SVE commit 69af56ae56a48a2522aad906c4461c6c7c092737 upstream. We have a function sve_sync_from_fpsimd_zeropad() which is used by the ptrace code to update the SVE state when the user writes to the the FPSIMD register set. Currently this checks that the task has SVE enabled but this will miss updates for tasks which have streaming SVE enabled if SVE has not been enabled for the thread, also do the conversion if the task has streaming SVE enabled. Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers") Signed-off-by: Mark Brown Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230803-arm64-fix-ptrace-ssve-no-sve-v1-3-49df214bfb3e@kernel.org Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/fpsimd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 59aaf2e68833..8fa9b1fa211a 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -791,7 +791,8 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); From 654c1dd350c746244e4dd4fe1fde577a2dc93d96 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 Aug 2023 00:46:39 +0100 Subject: [PATCH 0132/2093] arm64/fpsimd: Clear SME state in the target task when setting the VL commit c9bb40b7f786662e33d71afe236442b0b61f0446 upstream. When setting SME vector lengths we clear TIF_SME to reenable SME traps, doing a reallocation of the backing storage on next use. We do this using clear_thread_flag() which operates on the current thread, meaning that when setting the vector length via ptrace we may both not force traps for the target task and force a spurious flush of any SME state that the tracing task may have. Clear the flag in the target task. Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers") Reported-by: David Spickett Signed-off-by: Mark Brown Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230803-arm64-fix-ptrace-tif-sme-v1-1-88312fd6fbfd@kernel.org Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/fpsimd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8fa9b1fa211a..f7dbc0074cb0 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -864,7 +864,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, */ task->thread.svcr &= ~(SVCR_SM_MASK | SVCR_ZA_MASK); - clear_thread_flag(TIF_SME); + clear_tsk_thread_flag(task, TIF_SME); free_sme = true; } } From 61f96da37dd4fb166c7d9bdf76016b8340e5f85f Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 Aug 2023 19:33:22 +0100 Subject: [PATCH 0133/2093] arm64/fpsimd: Sync FPSIMD state with SVE for SME only systems commit 507ea5dd92d23fcf10e4d1a68a443c86a49753ed upstream. Currently we guard FPSIMD/SVE state conversions with a check for the system supporting SVE but SME only systems may need to sync streaming mode SVE state so add a check for SME support too. These functions are only used by the ptrace code. Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers") Signed-off-by: Mark Brown Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230803-arm64-fix-ptrace-ssve-no-sve-v1-2-49df214bfb3e@kernel.org Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/fpsimd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f7dbc0074cb0..356036babd09 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -634,7 +634,7 @@ static void fpsimd_to_sve(struct task_struct *task) void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); @@ -660,7 +660,7 @@ static void sve_to_fpsimd(struct task_struct *task) unsigned int i; __uint128_t const *p; - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) return; vl = thread_get_cur_vl(&task->thread); From 4f03b0471ee007b4b26ee7bbbfa7cc289c63da98 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sun, 6 Aug 2023 02:11:58 +1000 Subject: [PATCH 0134/2093] open: make RESOLVE_CACHED correctly test for O_TMPFILE commit a0fc452a5d7fed986205539259df1d60546f536c upstream. O_TMPFILE is actually __O_TMPFILE|O_DIRECTORY. This means that the old fast-path check for RESOLVE_CACHED would reject all users passing O_DIRECTORY with -EAGAIN, when in fact the intended test was to check for __O_TMPFILE. Cc: stable@vger.kernel.org # v5.12+ Fixes: 99668f618062 ("fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED") Signed-off-by: Aleksa Sarai Message-Id: <20230806-resolve_cached-o_tmpfile-v1-1-7ba16308465e@cyphar.com> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/open.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/open.c b/fs/open.c index 9541430ec5b3..51dc46620d03 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1233,7 +1233,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ - if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } From 1fdd16d89c01336d9a942b5f03673c17d401da87 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Mon, 24 Jul 2023 10:42:29 +0800 Subject: [PATCH 0135/2093] drm/ttm: check null pointer before accessing when swapping MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2dedcf414bb01b8d966eb445db1d181d92304fb2 upstream. Add a check to avoid null pointer dereference as below: [ 90.002283] general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN NOPTI [ 90.002292] KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] [ 90.002346] ? exc_general_protection+0x159/0x240 [ 90.002352] ? asm_exc_general_protection+0x26/0x30 [ 90.002357] ? ttm_bo_evict_swapout_allowable+0x322/0x5e0 [ttm] [ 90.002365] ? ttm_bo_evict_swapout_allowable+0x42e/0x5e0 [ttm] [ 90.002373] ttm_bo_swapout+0x134/0x7f0 [ttm] [ 90.002383] ? __pfx_ttm_bo_swapout+0x10/0x10 [ttm] [ 90.002391] ? lock_acquire+0x44d/0x4f0 [ 90.002398] ? ttm_device_swapout+0xa5/0x260 [ttm] [ 90.002412] ? lock_acquired+0x355/0xa00 [ 90.002416] ? do_raw_spin_trylock+0xb6/0x190 [ 90.002421] ? __pfx_lock_acquired+0x10/0x10 [ 90.002426] ? ttm_global_swapout+0x25/0x210 [ttm] [ 90.002442] ttm_device_swapout+0x198/0x260 [ttm] [ 90.002456] ? __pfx_ttm_device_swapout+0x10/0x10 [ttm] [ 90.002472] ttm_global_swapout+0x75/0x210 [ttm] [ 90.002486] ttm_tt_populate+0x187/0x3f0 [ttm] [ 90.002501] ttm_bo_handle_move_mem+0x437/0x590 [ttm] [ 90.002517] ttm_bo_validate+0x275/0x430 [ttm] [ 90.002530] ? __pfx_ttm_bo_validate+0x10/0x10 [ttm] [ 90.002544] ? kasan_save_stack+0x33/0x60 [ 90.002550] ? kasan_set_track+0x25/0x30 [ 90.002554] ? __kasan_kmalloc+0x8f/0xa0 [ 90.002558] ? amdgpu_gtt_mgr_new+0x81/0x420 [amdgpu] [ 90.003023] ? ttm_resource_alloc+0xf6/0x220 [ttm] [ 90.003038] amdgpu_bo_pin_restricted+0x2dd/0x8b0 [amdgpu] [ 90.003210] ? __x64_sys_ioctl+0x131/0x1a0 [ 90.003210] ? do_syscall_64+0x60/0x90 Fixes: a2848d08742c ("drm/ttm: never consider pinned BOs for eviction&swap") Tested-by: Mikhail Gavrilov Signed-off-by: Guchun Chen Reviewed-by: Alex Deucher Reviewed-by: Christian König Cc: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20230724024229.1118444-1-guchun.chen@amd.com Signed-off-by: Christian König Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ttm/ttm_bo.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index f7aeeee6f526..db332de134f1 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -552,7 +552,8 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, if (bo->pin_count) { *locked = false; - *busy = false; + if (busy) + *busy = false; return false; } From 4db8b39418a685179263b7ad895a3182d72be358 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Thu, 20 Jul 2023 11:35:44 +0200 Subject: [PATCH 0136/2093] drm/i915: Fix premature release of request's reusable memory commit a337b64f0d5717248a0c894e2618e658e6a9de9f upstream. Infinite waits for completion of GPU activity have been observed in CI, mostly inside __i915_active_wait(), triggered by igt@gem_barrier_race or igt@perf@stress-open-close. Root cause analysis, based of ftrace dumps generated with a lot of extra trace_printk() calls added to the code, revealed loops of request dependencies being accidentally built, preventing the requests from being processed, each waiting for completion of another one's activity. After we substitute a new request for a last active one tracked on a timeline, we set up a dependency of our new request to wait on completion of current activity of that previous one. While doing that, we must take care of keeping the old request still in memory until we use its attributes for setting up that await dependency, or we can happen to set up the await dependency on an unrelated request that already reuses the memory previously allocated to the old one, already released. Combined with perf adding consecutive kernel context remote requests to different user context timelines, unresolvable loops of await dependencies can be built, leading do infinite waits. We obtain a pointer to the previous request to wait upon when we substitute it with a pointer to our new request in an active tracker, e.g. in intel_timeline.last_request. In some processing paths we protect that old request from being freed before we use it by getting a reference to it under RCU protection, but in others, e.g. __i915_request_commit() -> __i915_request_add_to_timeline() -> __i915_request_ensure_ordering(), we don't. But anyway, since the requests' memory is SLAB_FAILSAFE_BY_RCU, that RCU protection is not sufficient against reuse of memory. We could protect i915_request's memory from being prematurely reused by calling its release function via call_rcu() and using rcu_read_lock() consequently, as proposed in v1. However, that approach leads to significant (up to 10 times) increase of SLAB utilization by i915_request SLAB cache. Another potential approach is to take a reference to the previous active fence. When updating an active fence tracker, we first lock the new fence, substitute a pointer of the current active fence with the new one, then we lock the substituted fence. With this approach, there is a time window after the substitution and before the lock when the request can be concurrently released by an interrupt handler and its memory reused, then we may happen to lock and return a new, unrelated request. Always get a reference to the current active fence first, before replacing it with a new one. Having it protected from premature release and reuse, lock it and then replace with the new one but only if not yet signalled via a potential concurrent interrupt nor replaced with another one by a potential concurrent thread, otherwise retry, starting from getting a reference to the new current one. Adjust users to not get a reference to the previous active fence themselves and always put the reference got by __i915_active_fence_set() when no longer needed. v3: Fix lockdep splat reports and other issues caused by incorrect use of try_cmpxchg() (use (cmpxchg() != prev) instead) v2: Protect request's memory by getting a reference to it in favor of delegating its release to call_rcu() (Chris) Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8211 Fixes: df9f85d8582e ("drm/i915: Serialise i915_active_fence_set() with itself") Suggested-by: Chris Wilson Signed-off-by: Janusz Krzysztofik Cc: # v5.6+ Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20230720093543.832147-2-janusz.krzysztofik@linux.intel.com (cherry picked from commit 946e047a3d88d46d15b5c5af0414098e12b243f7) Signed-off-by: Tvrtko Ursulin Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_active.c | 99 ++++++++++++++++++++--------- drivers/gpu/drm/i915/i915_request.c | 11 ++++ 2 files changed, 81 insertions(+), 29 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 8ef93889061a..5ec293011d99 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -449,8 +449,11 @@ int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) } } while (unlikely(is_barrier(active))); - if (!__i915_active_fence_set(active, fence)) + fence = __i915_active_fence_set(active, fence); + if (!fence) __i915_active_acquire(ref); + else + dma_fence_put(fence); out: i915_active_release(ref); @@ -469,13 +472,9 @@ __i915_active_set_fence(struct i915_active *ref, return NULL; } - rcu_read_lock(); prev = __i915_active_fence_set(active, fence); - if (prev) - prev = dma_fence_get_rcu(prev); - else + if (!prev) __i915_active_acquire(ref); - rcu_read_unlock(); return prev; } @@ -1019,10 +1018,11 @@ void i915_request_add_active_barriers(struct i915_request *rq) * * Records the new @fence as the last active fence along its timeline in * this active tracker, moving the tracking callbacks from the previous - * fence onto this one. Returns the previous fence (if not already completed), - * which the caller must ensure is executed before the new fence. To ensure - * that the order of fences within the timeline of the i915_active_fence is - * understood, it should be locked by the caller. + * fence onto this one. Gets and returns a reference to the previous fence + * (if not already completed), which the caller must put after making sure + * that it is executed before the new fence. To ensure that the order of + * fences within the timeline of the i915_active_fence is understood, it + * should be locked by the caller. */ struct dma_fence * __i915_active_fence_set(struct i915_active_fence *active, @@ -1031,7 +1031,23 @@ __i915_active_fence_set(struct i915_active_fence *active, struct dma_fence *prev; unsigned long flags; - if (fence == rcu_access_pointer(active->fence)) + /* + * In case of fences embedded in i915_requests, their memory is + * SLAB_FAILSAFE_BY_RCU, then it can be reused right after release + * by new requests. Then, there is a risk of passing back a pointer + * to a new, completely unrelated fence that reuses the same memory + * while tracked under a different active tracker. Combined with i915 + * perf open/close operations that build await dependencies between + * engine kernel context requests and user requests from different + * timelines, this can lead to dependency loops and infinite waits. + * + * As a countermeasure, we try to get a reference to the active->fence + * first, so if we succeed and pass it back to our user then it is not + * released and potentially reused by an unrelated request before the + * user has a chance to set up an await dependency on it. + */ + prev = i915_active_fence_get(active); + if (fence == prev) return fence; GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); @@ -1040,27 +1056,56 @@ __i915_active_fence_set(struct i915_active_fence *active, * Consider that we have two threads arriving (A and B), with * C already resident as the active->fence. * - * A does the xchg first, and so it sees C or NULL depending - * on the timing of the interrupt handler. If it is NULL, the - * previous fence must have been signaled and we know that - * we are first on the timeline. If it is still present, - * we acquire the lock on that fence and serialise with the interrupt - * handler, in the process removing it from any future interrupt - * callback. A will then wait on C before executing (if present). - * - * As B is second, it sees A as the previous fence and so waits for - * it to complete its transition and takes over the occupancy for - * itself -- remembering that it needs to wait on A before executing. + * Both A and B have got a reference to C or NULL, depending on the + * timing of the interrupt handler. Let's assume that if A has got C + * then it has locked C first (before B). * * Note the strong ordering of the timeline also provides consistent * nesting rules for the fence->lock; the inner lock is always the * older lock. */ spin_lock_irqsave(fence->lock, flags); - prev = xchg(__active_fence_slot(active), fence); - if (prev) { - GEM_BUG_ON(prev == fence); + if (prev) spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + + /* + * A does the cmpxchg first, and so it sees C or NULL, as before, or + * something else, depending on the timing of other threads and/or + * interrupt handler. If not the same as before then A unlocks C if + * applicable and retries, starting from an attempt to get a new + * active->fence. Meanwhile, B follows the same path as A. + * Once A succeeds with cmpxch, B fails again, retires, gets A from + * active->fence, locks it as soon as A completes, and possibly + * succeeds with cmpxchg. + */ + while (cmpxchg(__active_fence_slot(active), prev, fence) != prev) { + if (prev) { + spin_unlock(prev->lock); + dma_fence_put(prev); + } + spin_unlock_irqrestore(fence->lock, flags); + + prev = i915_active_fence_get(active); + GEM_BUG_ON(prev == fence); + + spin_lock_irqsave(fence->lock, flags); + if (prev) + spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + } + + /* + * If prev is NULL then the previous fence must have been signaled + * and we know that we are first on the timeline. If it is still + * present then, having the lock on that fence already acquired, we + * serialise with the interrupt handler, in the process of removing it + * from any future interrupt callback. A will then wait on C before + * executing (if present). + * + * As B is second, it sees A as the previous fence and so waits for + * it to complete its transition and takes over the occupancy for + * itself -- remembering that it needs to wait on A before executing. + */ + if (prev) { __list_del_entry(&active->cb.node); spin_unlock(prev->lock); /* serialise with prev->cb_list */ } @@ -1077,11 +1122,7 @@ int i915_active_fence_set(struct i915_active_fence *active, int err = 0; /* Must maintain timeline ordering wrt previous active requests */ - rcu_read_lock(); fence = __i915_active_fence_set(active, &rq->fence); - if (fence) /* but the previous fence may not belong to that timeline! */ - fence = dma_fence_get_rcu(fence); - rcu_read_unlock(); if (fence) { err = i915_request_await_dma_fence(rq, fence); dma_fence_put(fence); diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 62fad16a55e8..803cd2ad4deb 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1647,6 +1647,11 @@ __i915_request_ensure_parallel_ordering(struct i915_request *rq, request_to_parent(rq)->parallel.last_rq = i915_request_get(rq); + /* + * Users have to put a reference potentially got by + * __i915_active_fence_set() to the returned request + * when no longer needed + */ return to_request(__i915_active_fence_set(&timeline->last_request, &rq->fence)); } @@ -1693,6 +1698,10 @@ __i915_request_ensure_ordering(struct i915_request *rq, 0); } + /* + * Users have to put the reference to prev potentially got + * by __i915_active_fence_set() when no longer needed + */ return prev; } @@ -1736,6 +1745,8 @@ __i915_request_add_to_timeline(struct i915_request *rq) prev = __i915_request_ensure_ordering(rq, timeline); else prev = __i915_request_ensure_parallel_ordering(rq, timeline); + if (prev) + i915_request_put(prev); /* * Make sure that no request gazumped us - if it was allocated after From 37f6073f7db329c9db4357f82e565958fb64ea16 Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Tue, 25 Jul 2023 02:19:44 +0200 Subject: [PATCH 0137/2093] drm/i915/gt: Cleanup aux invalidation registers commit d14560ac1b595aa2e792365e91fea6aeaee66c2b upstream. Fix the 'NV' definition postfix that is supposed to be INV. Take the chance to also order properly the registers based on their address and call the GEN12_GFX_CCS_AUX_INV address as GEN12_CCS_AUX_INV like all the other similar registers. Remove also VD1, VD3 and VE1 registers that don't exist and add BCS0 and CCS0. Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Nirmoy Das Reviewed-by: Andrzej Hajda Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-2-andi.shyti@linux.intel.com (cherry picked from commit 2f0b927d3ca3440445975ebde27f3df1c3ed6f76) Signed-off-by: Tvrtko Ursulin Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 8 ++++---- drivers/gpu/drm/i915/gt/intel_gt_regs.h | 16 ++++++++-------- drivers/gpu/drm/i915/gt/intel_lrc.c | 6 +++--- 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index e49fa6fa6aee..b2838732ac93 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -256,8 +256,8 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) if (!HAS_FLAT_CCS(rq->engine->i915)) { /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); + cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, + GEN12_CCS_AUX_INV); } *cs++ = preparser_disable(false); @@ -317,10 +317,10 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (aux_inv) { /* hsdes: 1809175790 */ if (rq->engine->class == VIDEO_DECODE_CLASS) cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_NV); + cs, GEN12_VD0_AUX_INV); else cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_NV); + cs, GEN12_VE0_AUX_INV); } if (mode & EMIT_INVALIDATE) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 2275ee47da95..dd006563cc81 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -301,9 +301,11 @@ #define GEN8_PRIVATE_PAT_HI _MMIO(0x40e0 + 4) #define GEN10_PAT_INDEX(index) _MMIO(0x40e0 + (index) * 4) #define BSD_HWS_PGA_GEN7 _MMIO(0x4180) -#define GEN12_GFX_CCS_AUX_NV _MMIO(0x4208) -#define GEN12_VD0_AUX_NV _MMIO(0x4218) -#define GEN12_VD1_AUX_NV _MMIO(0x4228) + +#define GEN12_CCS_AUX_INV _MMIO(0x4208) +#define GEN12_VD0_AUX_INV _MMIO(0x4218) +#define GEN12_VE0_AUX_INV _MMIO(0x4238) +#define GEN12_BCS0_AUX_INV _MMIO(0x4248) #define GEN8_RTCR _MMIO(0x4260) #define GEN8_M1TCR _MMIO(0x4264) @@ -311,14 +313,12 @@ #define GEN8_BTCR _MMIO(0x426c) #define GEN8_VTCR _MMIO(0x4270) -#define GEN12_VD2_AUX_NV _MMIO(0x4298) -#define GEN12_VD3_AUX_NV _MMIO(0x42a8) -#define GEN12_VE0_AUX_NV _MMIO(0x4238) - #define BLT_HWS_PGA_GEN7 _MMIO(0x4280) -#define GEN12_VE1_AUX_NV _MMIO(0x42b8) +#define GEN12_VD2_AUX_INV _MMIO(0x4298) +#define GEN12_CCS0_AUX_INV _MMIO(0x42c8) #define AUX_INV REG_BIT(0) + #define VEBOX_HWS_PGA_GEN7 _MMIO(0x4380) #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 3955292483a6..137e41e37ea5 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1299,7 +1299,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) /* hsdes: 1809175790 */ if (!HAS_FLAT_CCS(ce->engine->i915)) cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); + cs, GEN12_CCS_AUX_INV); /* Wa_16014892111 */ if (IS_DG2(ce->engine->i915)) @@ -1326,10 +1326,10 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) if (!HAS_FLAT_CCS(ce->engine->i915)) { if (ce->engine->class == VIDEO_DECODE_CLASS) cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_NV); + cs, GEN12_VD0_AUX_INV); else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_NV); + cs, GEN12_VE0_AUX_INV); } return cs; From 8a211e9118d5c8f0f2ae8ca16e47f79cd9492a43 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 11 Jul 2023 17:08:12 +0200 Subject: [PATCH 0138/2093] clk: imx93: Propagate correct error in imx93_clocks_probe() commit a29b2fccf5f2689a9637be85ff1f51c834c6fb33 upstream. smatch reports: drivers/clk/imx/clk-imx93.c:294 imx93_clocks_probe() error: uninitialized symbol 'base'. Indeed, in case of an error, the wrong (yet uninitialized) variable is converted to an error code and returned. Fix this by propagating the error code in the correct variable. Fixes: e02ba11b45764705 ("clk: imx93: fix memory leak and missing unwind goto in imx93_clocks_probe") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/9c2acd81-3ad8-485d-819e-9e4201277831@kadam.mountain Reported-by: kernel test robot Closes: https://lore.kernel.org/all/202306161533.4YDmL22b-lkp@intel.com/ Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230711150812.3562221-1-geert+renesas@glider.be Reviewed-by: Peng Fan Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- drivers/clk/imx/clk-imx93.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index 5e3d299190c8..61d9f9bf86e6 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -288,7 +288,7 @@ static int imx93_clocks_probe(struct platform_device *pdev) anatop_base = devm_of_iomap(dev, np, 0, NULL); of_node_put(np); if (WARN_ON(IS_ERR(anatop_base))) { - ret = PTR_ERR(base); + ret = PTR_ERR(anatop_base); goto unregister_hws; } From 7a1178a3671b40746830d355836b72e47ceb2490 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Sat, 29 Jul 2023 17:51:06 +0800 Subject: [PATCH 0139/2093] bpf, cpumap: Make sure kthread is running before map update returns commit 640a604585aa30f93e39b17d4d6ba69fcb1e66c9 upstream. The following warning was reported when running stress-mode enabled xdp_redirect_cpu with some RT threads: ------------[ cut here ]------------ WARNING: CPU: 4 PID: 65 at kernel/bpf/cpumap.c:135 CPU: 4 PID: 65 Comm: kworker/4:1 Not tainted 6.5.0-rc2+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: events cpu_map_kthread_stop RIP: 0010:put_cpu_map_entry+0xda/0x220 ...... Call Trace: ? show_regs+0x65/0x70 ? __warn+0xa5/0x240 ...... ? put_cpu_map_entry+0xda/0x220 cpu_map_kthread_stop+0x41/0x60 process_one_work+0x6b0/0xb80 worker_thread+0x96/0x720 kthread+0x1a5/0x1f0 ret_from_fork+0x3a/0x70 ret_from_fork_asm+0x1b/0x30 The root cause is the same as commit 436901649731 ("bpf: cpumap: Fix memory leak in cpu_map_update_elem"). The kthread is stopped prematurely by kthread_stop() in cpu_map_kthread_stop(), and kthread() doesn't call cpu_map_kthread_run() at all but XDP program has already queued some frames or skbs into ptr_ring. So when __cpu_map_ring_cleanup() checks the ptr_ring, it will find it was not emptied and report a warning. An alternative fix is to use __cpu_map_ring_cleanup() to drop these pending frames or skbs when kthread_stop() returns -EINTR, but it may confuse the user, because these frames or skbs have been handled correctly by XDP program. So instead of dropping these frames or skbs, just make sure the per-cpu kthread is running before __cpu_map_entry_alloc() returns. After apply the fix, the error handle for kthread_stop() will be unnecessary because it will always return 0, so just remove it. Fixes: 6710e1126934 ("bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP") Signed-off-by: Hou Tao Reviewed-by: Pu Lehui Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230729095107.1722450-2-houtao@huaweicloud.com Signed-off-by: Martin KaFai Lau Signed-off-by: Greg Kroah-Hartman --- kernel/bpf/cpumap.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e5888d401d79..08a8e8102728 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -71,6 +72,7 @@ struct bpf_cpu_map_entry { struct rcu_head rcu; struct work_struct kthread_stop_wq; + struct completion kthread_running; }; struct bpf_cpu_map { @@ -164,7 +166,6 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) static void cpu_map_kthread_stop(struct work_struct *work) { struct bpf_cpu_map_entry *rcpu; - int err; rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); @@ -174,14 +175,7 @@ static void cpu_map_kthread_stop(struct work_struct *work) rcu_barrier(); /* kthread_stop will wake_up_process and wait for it to complete */ - err = kthread_stop(rcpu->kthread); - if (err) { - /* kthread_stop may be called before cpu_map_kthread_run - * is executed, so we need to release the memory related - * to rcpu. - */ - put_cpu_map_entry(rcpu); - } + kthread_stop(rcpu->kthread); } static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, @@ -309,11 +303,11 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, return nframes; } - static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); /* When kthread gives stop order, then rcpu have been disconnected @@ -478,6 +472,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, goto free_ptr_ring; /* Setup kthread */ + init_completion(&rcpu->kthread_running); rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, "cpumap/%d/map:%d", cpu, map->id); @@ -491,6 +486,12 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); + /* Make sure kthread has been running, so kthread_stop() will not + * stop the kthread prematurely and all pending frames or skbs + * will be handled by the kthread before kthread_stop() returns. + */ + wait_for_completion(&rcpu->kthread_running); + return rcpu; free_prog: From 4968484ac8efb7b958c938b321c1f4be536babd3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 3 Aug 2023 11:35:53 -0700 Subject: [PATCH 0140/2093] file: reinstate f_pos locking optimization for regular files commit 797964253d358cf8d705614dda394dbe30120223 upstream. In commit 20ea1e7d13c1 ("file: always lock position for FMODE_ATOMIC_POS") we ended up always taking the file pos lock, because pidfd_getfd() could get a reference to the file even when it didn't have an elevated file count due to threading of other sharing cases. But Mateusz Guzik reports that the extra locking is actually measurable, so let's re-introduce the optimization, and only force the locking for directory traversal. Directories need the lock for correctness reasons, while regular files only need it for "POSIX semantics". Since pidfd_getfd() is about debuggers etc special things that are _way_ outside of POSIX, we can relax the rules for that case. Reported-by: Mateusz Guzik Cc: Christian Brauner Link: https://lore.kernel.org/linux-fsdevel/20230803095311.ijpvhx3fyrbkasul@f/ Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/file.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/fs/file.c b/fs/file.c index 35c62b54c9d6..dbca26ef7a01 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1036,12 +1036,28 @@ unsigned long __fdget_raw(unsigned int fd) return __fget_light(fd, 0); } +/* + * Try to avoid f_pos locking. We only need it if the + * file is marked for FMODE_ATOMIC_POS, and it can be + * accessed multiple ways. + * + * Always do it for directories, because pidfd_getfd() + * can make a file accessible even if it otherwise would + * not be, and for directories this is a correctness + * issue, not a "POSIX requirement". + */ +static inline bool file_needs_f_pos_lock(struct file *file) +{ + return (file->f_mode & FMODE_ATOMIC_POS) && + (file_count(file) > 1 || S_ISDIR(file_inode(file)->i_mode)); +} + unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } From 33d9490b27e5d8da4444aefd714a4f50189db978 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 2 May 2023 09:08:38 -0700 Subject: [PATCH 0141/2093] mm: kmem: fix a NULL pointer dereference in obj_stock_flush_required() commit 3b8abb3239530c423c0b97e42af7f7e856e1ee96 upstream. KCSAN found an issue in obj_stock_flush_required(): stock->cached_objcg can be reset between the check and dereference: ================================================================== BUG: KCSAN: data-race in drain_all_stock / drain_obj_stock write to 0xffff888237c2a2f8 of 8 bytes by task 19625 on cpu 0: drain_obj_stock+0x408/0x4e0 mm/memcontrol.c:3306 refill_obj_stock+0x9c/0x1e0 mm/memcontrol.c:3340 obj_cgroup_uncharge+0xe/0x10 mm/memcontrol.c:3408 memcg_slab_free_hook mm/slab.h:587 [inline] __cache_free mm/slab.c:3373 [inline] __do_kmem_cache_free mm/slab.c:3577 [inline] kmem_cache_free+0x105/0x280 mm/slab.c:3602 __d_free fs/dcache.c:298 [inline] dentry_free fs/dcache.c:375 [inline] __dentry_kill+0x422/0x4a0 fs/dcache.c:621 dentry_kill+0x8d/0x1e0 dput+0x118/0x1f0 fs/dcache.c:913 __fput+0x3bf/0x570 fs/file_table.c:329 ____fput+0x15/0x20 fs/file_table.c:349 task_work_run+0x123/0x160 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop+0xcf/0xe0 kernel/entry/common.c:171 exit_to_user_mode_prepare+0x6a/0xa0 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x26/0x140 kernel/entry/common.c:296 do_syscall_64+0x4d/0xc0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888237c2a2f8 of 8 bytes by task 19632 on cpu 1: obj_stock_flush_required mm/memcontrol.c:3319 [inline] drain_all_stock+0x174/0x2a0 mm/memcontrol.c:2361 try_charge_memcg+0x6d0/0xd10 mm/memcontrol.c:2703 try_charge mm/memcontrol.c:2837 [inline] mem_cgroup_charge_skmem+0x51/0x140 mm/memcontrol.c:7290 sock_reserve_memory+0xb1/0x390 net/core/sock.c:1025 sk_setsockopt+0x800/0x1e70 net/core/sock.c:1525 udp_lib_setsockopt+0x99/0x6c0 net/ipv4/udp.c:2692 udp_setsockopt+0x73/0xa0 net/ipv4/udp.c:2817 sock_common_setsockopt+0x61/0x70 net/core/sock.c:3668 __sys_setsockopt+0x1c3/0x230 net/socket.c:2271 __do_sys_setsockopt net/socket.c:2282 [inline] __se_sys_setsockopt net/socket.c:2279 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2279 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0xffff8881382d52c0 -> 0xffff888138893740 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 19632 Comm: syz-executor.0 Not tainted 6.3.0-rc2-syzkaller-00387-g534293368afa #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Fix it by using READ_ONCE()/WRITE_ONCE() for all accesses to stock->cached_objcg. Link: https://lkml.kernel.org/r/20230502160839.361544-1-roman.gushchin@linux.dev Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API") Signed-off-by: Roman Gushchin Reported-by: syzbot+774c29891415ab0fd29d@syzkaller.appspotmail.com Reported-by: Dmitry Vyukov Link: https://lore.kernel.org/linux-mm/CACT4Y+ZfucZhM60YPphWiCLJr6+SGFhT+jjm8k1P-a_8Kkxsjg@mail.gmail.com/T/#t Reviewed-by: Yosry Ahmed Acked-by: Shakeel Butt Reviewed-by: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/memcontrol.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3e8f1ad0fe9d..67b6d8238b3e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3165,12 +3165,12 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, * accumulating over a page of vmstat data or when pgdat or idx * changes. */ - if (stock->cached_objcg != objcg) { + if (READ_ONCE(stock->cached_objcg) != objcg) { old = drain_obj_stock(stock); obj_cgroup_get(objcg); stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; - stock->cached_objcg = objcg; + WRITE_ONCE(stock->cached_objcg, objcg); stock->cached_pgdat = pgdat; } else if (stock->cached_pgdat != pgdat) { /* Flush the existing cached vmstat data */ @@ -3224,7 +3224,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); - if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { + if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) { stock->nr_bytes -= nr_bytes; ret = true; } @@ -3236,7 +3236,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) { - struct obj_cgroup *old = stock->cached_objcg; + struct obj_cgroup *old = READ_ONCE(stock->cached_objcg); if (!old) return NULL; @@ -3289,7 +3289,7 @@ static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) stock->cached_pgdat = NULL; } - stock->cached_objcg = NULL; + WRITE_ONCE(stock->cached_objcg, NULL); /* * The `old' objects needs to be released by the caller via * obj_cgroup_put() outside of memcg_stock_pcp::stock_lock. @@ -3300,10 +3300,11 @@ static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, struct mem_cgroup *root_memcg) { + struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg); struct mem_cgroup *memcg; - if (stock->cached_objcg) { - memcg = obj_cgroup_memcg(stock->cached_objcg); + if (objcg) { + memcg = obj_cgroup_memcg(objcg); if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) return true; } @@ -3322,10 +3323,10 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, local_lock_irqsave(&memcg_stock.stock_lock, flags); stock = this_cpu_ptr(&memcg_stock); - if (stock->cached_objcg != objcg) { /* reset if necessary */ + if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */ old = drain_obj_stock(stock); obj_cgroup_get(objcg); - stock->cached_objcg = objcg; + WRITE_ONCE(stock->cached_objcg, objcg); stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; allow_uncharge = true; /* Allow uncharge when objcg changes */ From ccc6de4d4f3466fb70f17aea4e41b43742b6a979 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 28 Mar 2023 20:05:16 +0900 Subject: [PATCH 0142/2093] fs/ntfs3: Use __GFP_NOWARN allocation at ntfs_load_attr_list() commit ea303f72d70ce2f0b0aa94ab127085289768c5a6 upstream. syzbot is reporting too large allocation at ntfs_load_attr_list(), for a crafted filesystem can have huge data_size. Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=89dbb3a789a5b9711793 Signed-off-by: Tetsuo Handa Signed-off-by: Konstantin Komarov Signed-off-by: Greg Kroah-Hartman --- fs/ntfs3/attrlist.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index c0c6bcbc8c05..81c22df27c72 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -52,7 +52,7 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (!attr->non_res) { lsize = le32_to_cpu(attr->res.data_size); - le = kmalloc(al_aligned(lsize), GFP_NOFS); + le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); if (!le) { err = -ENOMEM; goto out; @@ -80,7 +80,7 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (err < 0) goto out; - le = kmalloc(al_aligned(lsize), GFP_NOFS); + le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); if (!le) { err = -ENOMEM; goto out; From 1416eebaad80bdc85ad9f97f27242011b031e2a9 Mon Sep 17 00:00:00 2001 From: Prince Kumar Maurya Date: Tue, 30 May 2023 18:31:41 -0700 Subject: [PATCH 0143/2093] fs/sysv: Null check to prevent null-ptr-deref bug commit ea2b62f305893992156a798f665847e0663c9f41 upstream. sb_getblk(inode->i_sb, parent) return a null ptr and taking lock on that leads to the null-ptr-deref bug. Reported-by: syzbot+aad58150cbc64ba41bdc@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=aad58150cbc64ba41bdc Signed-off-by: Prince Kumar Maurya Message-Id: <20230531013141.19487-1-princekumarmaurya06@gmail.com> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/sysv/itree.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 3b8567564e7e..9925cfe57159 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -145,6 +145,10 @@ static int alloc_branch(struct inode *inode, */ parent = block_to_cpu(SYSV_SB(inode->i_sb), branch[n-1].key); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + sysv_free_block(inode->i_sb, branch[n].key); + break; + } lock_buffer(bh); memset(bh->b_data, 0, blocksize); branch[n].bh = bh; From 29fac18499332211b2615ade356e2bd8b3269f98 Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Wed, 31 May 2023 01:39:56 -0400 Subject: [PATCH 0144/2093] Bluetooth: L2CAP: Fix use-after-free in l2cap_sock_ready_cb commit 1728137b33c00d5a2b5110ed7aafb42e7c32e4a1 upstream. l2cap_sock_release(sk) frees sk. However, sk's children are still alive and point to the already free'd sk's address. To fix this, l2cap_sock_release(sk) also cleans sk's children. ================================================================== BUG: KASAN: use-after-free in l2cap_sock_ready_cb+0xb7/0x100 net/bluetooth/l2cap_sock.c:1650 Read of size 8 at addr ffff888104617aa8 by task kworker/u3:0/276 CPU: 0 PID: 276 Comm: kworker/u3:0 Not tainted 6.2.0-00001-gef397bd4d5fb-dirty #59 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: hci2 hci_rx_work Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0x95 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:306 [inline] print_report+0x175/0x478 mm/kasan/report.c:417 kasan_report+0xb1/0x130 mm/kasan/report.c:517 l2cap_sock_ready_cb+0xb7/0x100 net/bluetooth/l2cap_sock.c:1650 l2cap_chan_ready+0x10e/0x1e0 net/bluetooth/l2cap_core.c:1386 l2cap_config_req+0x753/0x9f0 net/bluetooth/l2cap_core.c:4480 l2cap_bredr_sig_cmd net/bluetooth/l2cap_core.c:5739 [inline] l2cap_sig_channel net/bluetooth/l2cap_core.c:6509 [inline] l2cap_recv_frame+0xe2e/0x43c0 net/bluetooth/l2cap_core.c:7788 l2cap_recv_acldata+0x6ed/0x7e0 net/bluetooth/l2cap_core.c:8506 hci_acldata_packet net/bluetooth/hci_core.c:3813 [inline] hci_rx_work+0x66e/0xbc0 net/bluetooth/hci_core.c:4048 process_one_work+0x4ea/0x8e0 kernel/workqueue.c:2289 worker_thread+0x364/0x8e0 kernel/workqueue.c:2436 kthread+0x1b9/0x200 kernel/kthread.c:376 ret_from_fork+0x2c/0x50 arch/x86/entry/entry_64.S:308 Allocated by task 288: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0x82/0x90 mm/kasan/common.c:383 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slab_common.c:968 [inline] __kmalloc+0x5a/0x140 mm/slab_common.c:981 kmalloc include/linux/slab.h:584 [inline] sk_prot_alloc+0x113/0x1f0 net/core/sock.c:2040 sk_alloc+0x36/0x3c0 net/core/sock.c:2093 l2cap_sock_alloc.constprop.0+0x39/0x1c0 net/bluetooth/l2cap_sock.c:1852 l2cap_sock_create+0x10d/0x220 net/bluetooth/l2cap_sock.c:1898 bt_sock_create+0x183/0x290 net/bluetooth/af_bluetooth.c:132 __sock_create+0x226/0x380 net/socket.c:1518 sock_create net/socket.c:1569 [inline] __sys_socket_create net/socket.c:1606 [inline] __sys_socket_create net/socket.c:1591 [inline] __sys_socket+0x112/0x200 net/socket.c:1639 __do_sys_socket net/socket.c:1652 [inline] __se_sys_socket net/socket.c:1650 [inline] __x64_sys_socket+0x40/0x50 net/socket.c:1650 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 288: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:523 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10a/0x190 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x88/0x1f0 mm/slub.c:3800 sk_prot_free net/core/sock.c:2076 [inline] __sk_destruct+0x347/0x430 net/core/sock.c:2168 sk_destruct+0x9c/0xb0 net/core/sock.c:2183 __sk_free+0x82/0x220 net/core/sock.c:2194 sk_free+0x7c/0xa0 net/core/sock.c:2205 sock_put include/net/sock.h:1991 [inline] l2cap_sock_kill+0x256/0x2b0 net/bluetooth/l2cap_sock.c:1257 l2cap_sock_release+0x1a7/0x220 net/bluetooth/l2cap_sock.c:1428 __sock_release+0x80/0x150 net/socket.c:650 sock_close+0x19/0x30 net/socket.c:1368 __fput+0x17a/0x5c0 fs/file_table.c:320 task_work_run+0x132/0x1c0 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x113/0x120 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x21/0x50 kernel/entry/common.c:296 do_syscall_64+0x4c/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff888104617800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 680 bytes inside of 1024-byte region [ffff888104617800, ffff888104617c00) The buggy address belongs to the physical page: page:00000000dbca6a80 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888104614000 pfn:0x104614 head:00000000dbca6a80 order:2 compound_mapcount:0 subpages_mapcount:0 compound_pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffff888100041dc0 ffffea0004212c10 ffffea0004234b10 raw: ffff888104614000 0000000000080002 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888104617980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888104617a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888104617a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888104617b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888104617b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Ack: This bug is found by FuzzBT with a modified Syzkaller. Other contributors are Ruoyu Wu and Hui Peng. Signed-off-by: Sungwoo Kim Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/l2cap_sock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index eebe256104bc..947ca580bb9a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -46,6 +46,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -1415,6 +1416,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); From 203d58930d4ac3287fe8a3c7e7be8b86a4dc20de Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 7 Jun 2023 19:19:02 +0900 Subject: [PATCH 0145/2093] debugobjects: Recheck debug_objects_enabled before reporting commit 8b64d420fe2450f82848178506d3e3a0bd195539 upstream. syzbot is reporting false a positive ODEBUG message immediately after ODEBUG was disabled due to OOM. [ 1062.309646][T22911] ODEBUG: Out of memory. ODEBUG disabled [ 1062.886755][ T5171] ------------[ cut here ]------------ [ 1062.892770][ T5171] ODEBUG: assert_init not available (active state 0) object: ffffc900056afb20 object type: timer_list hint: process_timeout+0x0/0x40 CPU 0 [ T5171] CPU 1 [T22911] -------------- -------------- debug_object_assert_init() { if (!debug_objects_enabled) return; db = get_bucket(addr); lookup_object_or_alloc() { debug_objects_enabled = 0; return NULL; } debug_objects_oom() { pr_warn("Out of memory. ODEBUG disabled\n"); // all buckets get emptied here, and } lookup_object_or_alloc(addr, db, descr, false, true) { // this bucket is already empty. return ERR_PTR(-ENOENT); } // Emits false positive warning. debug_print_object(&o, "assert_init"); } Recheck debug_object_enabled in debug_print_object() to avoid that. Reported-by: syzbot Suggested-by: Thomas Gleixner Signed-off-by: Tetsuo Handa Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/492fe2ae-5141-d548-ebd5-62f5fe2e57f7@I-love.SAKURA.ne.jp Closes: https://syzkaller.appspot.com/bug?extid=7937ba6a50bdd00fffdf Signed-off-by: Greg Kroah-Hartman --- lib/debugobjects.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index c46736210363..dacb80c22c4f 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -498,6 +498,15 @@ static void debug_print_object(struct debug_obj *obj, char *msg) const struct debug_obj_descr *descr = obj->descr; static int limit; + /* + * Don't report if lookup_object_or_alloc() by the current thread + * failed because lookup_object_or_alloc()/debug_objects_oom() by a + * concurrent thread turned off debug_objects_enabled and cleared + * the hash buckets. + */ + if (!debug_objects_enabled) + return; + if (limit < 5 && descr != descr_test) { void *hint = descr->debug_hint ? descr->debug_hint(obj->object) : NULL; From 1bebbd9b8037a9cc75984317cb495dec4824c399 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 12 Jul 2023 10:15:10 -0400 Subject: [PATCH 0146/2093] net: usbnet: Fix WARNING in usbnet_start_xmit/usb_submit_urb commit 5e1627cb43ddf1b24b92eb26f8d958a3f5676ccb upstream. The syzbot fuzzer identified a problem in the usbnet driver: usb 1-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 0 PID: 754 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Modules linked in: CPU: 0 PID: 754 Comm: kworker/0:2 Not tainted 6.4.0-rc7-syzkaller-00014-g692b7dc87ca6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Workqueue: mld mld_ifc_work RIP: 0010:usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Code: 7c 24 18 e8 2c b4 5b fb 48 8b 7c 24 18 e8 42 07 f0 fe 41 89 d8 44 89 e1 4c 89 ea 48 89 c6 48 c7 c7 a0 c9 fc 8a e8 5a 6f 23 fb <0f> 0b e9 58 f8 ff ff e8 fe b3 5b fb 48 81 c5 c0 05 00 00 e9 84 f7 RSP: 0018:ffffc9000463f568 EFLAGS: 00010086 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff88801eb28000 RSI: ffffffff814c03b7 RDI: 0000000000000001 RBP: ffff8881443b7190 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000003 R13: ffff88802a77cb18 R14: 0000000000000003 R15: ffff888018262500 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556a99c15a18 CR3: 0000000028c71000 CR4: 0000000000350ef0 Call Trace: usbnet_start_xmit+0xfe5/0x2190 drivers/net/usb/usbnet.c:1453 __netdev_start_xmit include/linux/netdevice.h:4918 [inline] netdev_start_xmit include/linux/netdevice.h:4932 [inline] xmit_one net/core/dev.c:3578 [inline] dev_hard_start_xmit+0x187/0x700 net/core/dev.c:3594 ... This bug is caused by the fact that usbnet trusts the bulk endpoint addresses its probe routine receives in the driver_info structure, and it does not check to see that these endpoints actually exist and have the expected type and directions. The fix is simply to add such a check. Reported-and-tested-by: syzbot+63ee658b9a100ffadbe2@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-usb/000000000000a56e9105d0cec021@google.com/ Signed-off-by: Alan Stern CC: Oliver Neukum Link: https://lore.kernel.org/r/ea152b6d-44df-4f8a-95c6-4db51143dcc1@rowland.harvard.edu Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/usbnet.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 64a9a80b2309..405e588f8a3a 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1770,6 +1770,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) } else if (!info->in || !info->out) status = usbnet_get_endpoints (dev, udev); else { + u8 ep_addrs[3] = { + info->in + USB_DIR_IN, info->out + USB_DIR_OUT, 0 + }; + dev->in = usb_rcvbulkpipe (xdev, info->in); dev->out = usb_sndbulkpipe (xdev, info->out); if (!(info->flags & FLAG_NO_SETINT)) @@ -1779,6 +1783,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) else status = 0; + if (status == 0 && !usb_check_bulk_endpoints(udev, ep_addrs)) + status = -EINVAL; } if (status >= 0 && dev->status) status = init_status (dev, udev); From 295ef44a2abaf97d7a594b1d4c60d4be3738191f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 15 Jun 2023 13:38:48 +0200 Subject: [PATCH 0147/2093] fs: Protect reconfiguration of sb read-write from racing writes commit c541dce86c537714b6761a79a969c1623dfa222b upstream. The reconfigure / remount code takes a lot of effort to protect filesystem's reconfiguration code from racing writes on remounting read-only. However during remounting read-only filesystem to read-write mode userspace writes can start immediately once we clear SB_RDONLY flag. This is inconvenient for example for ext4 because we need to do some writes to the filesystem (such as preparation of quota files) before we can take userspace writes so we are clearing SB_RDONLY flag before we are fully ready to accept userpace writes and syzbot has found a way to exploit this [1]. Also as far as I'm reading the code the filesystem remount code was protected from racing writes in the legacy mount path by the mount's MNT_READONLY flag so this is relatively new problem. It is actually fairly easy to protect remount read-write from racing writes using sb->s_readonly_remount flag so let's just do that instead of having to workaround these races in the filesystem code. [1] https://lore.kernel.org/all/00000000000006a0df05f6667499@google.com/T/ Signed-off-by: Jan Kara Message-Id: <20230615113848.8439-1-jack@suse.cz> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/super.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/super.c b/fs/super.c index 7c140ee60c54..d138332e57a9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -904,6 +904,7 @@ int reconfigure_super(struct fs_context *fc) struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; + bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) @@ -921,7 +922,7 @@ int reconfigure_super(struct fs_context *fc) bdev_read_only(sb->s_bdev)) return -EACCES; #endif - + remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } @@ -951,6 +952,14 @@ int reconfigure_super(struct fs_context *fc) if (retval) return retval; } + } else if (remount_rw) { + /* + * We set s_readonly_remount here to protect filesystem's + * reconfigure code from writes from userspace until + * reconfigure finishes. + */ + sb->s_readonly_remount = 1; + smp_wmb(); } if (fc->ops->reconfigure) { From 56c0d76a97222f4a91912d43814c7129010f4725 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Jun 2023 12:25:52 +0200 Subject: [PATCH 0148/2093] ext2: Drop fragment support commit 404615d7f1dcd4cca200e9a7a9df3a1dcae1dd62 upstream. Ext2 has fields in superblock reserved for subblock allocation support. However that never landed. Drop the many years dead code. Reported-by: syzbot+af5e10f73dbff48f70af@syzkaller.appspotmail.com Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/ext2/ext2.h | 12 ------------ fs/ext2/super.c | 23 ++++------------------- 2 files changed, 4 insertions(+), 31 deletions(-) diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index dc5dcb78bc27..2c95916aead8 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -70,10 +70,7 @@ struct mb_cache; * second extended-fs super-block data in memory */ struct ext2_sb_info { - unsigned long s_frag_size; /* Size of a fragment in bytes */ - unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_frags_per_group;/* Number of fragments in a group */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ @@ -188,15 +185,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_INODE_SIZE(s) (EXT2_SB(s)->s_inode_size) #define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino) -/* - * Macro-instructions used to manage fragments - */ -#define EXT2_MIN_FRAG_SIZE 1024 -#define EXT2_MAX_FRAG_SIZE 4096 -#define EXT2_MIN_FRAG_LOG_SIZE 10 -#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size) -#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block) - /* * Structure of a blocks group descriptor */ diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 3feea4b31fa7..99b26fe20d17 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -668,10 +668,9 @@ static int ext2_setup_super (struct super_block * sb, es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); if (test_opt (sb, DEBUG)) - ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, " + ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, " "bpg=%lu, ipg=%lu, mo=%04lx]", EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, - sbi->s_frag_size, sbi->s_groups_count, EXT2_BLOCKS_PER_GROUP(sb), EXT2_INODES_PER_GROUP(sb), @@ -1012,14 +1011,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } } - sbi->s_frag_size = EXT2_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (sbi->s_frag_size == 0) - goto cantfind_ext2; - sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size; - sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); @@ -1045,11 +1037,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sb->s_blocksize != sbi->s_frag_size) { + if (es->s_log_frag_size != es->s_log_block_size) { ext2_msg(sb, KERN_ERR, - "error: fragsize %lu != blocksize %lu" - "(not supported yet)", - sbi->s_frag_size, sb->s_blocksize); + "error: fragsize log %u != blocksize log %u", + le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits); goto failed_mount; } @@ -1066,12 +1057,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group, sbi->s_inodes_per_group + 3); goto failed_mount; } - if (sbi->s_frags_per_group > sb->s_blocksize * 8) { - ext2_msg(sb, KERN_ERR, - "error: #fragments per group too big: %lu", - sbi->s_frags_per_group); - goto failed_mount; - } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext2_msg(sb, KERN_ERR, From 23e72231f8281505883514b23709076e234d4f27 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 30 Jun 2023 16:03:44 +0100 Subject: [PATCH 0149/2093] btrfs: remove BUG_ON()'s in add_new_free_space() commit d8ccbd21918fd7fa6ce3226cffc22c444228e8ad upstream. At add_new_free_space() we have these BUG_ON()'s that are there to deal with any failure to add free space to the in memory free space cache. Such failures are mostly -ENOMEM that should be very rare. However there's no need to have these BUG_ON()'s, we can just return any error to the caller and all callers and their upper call chain are already dealing with errors. So just make add_new_free_space() return any errors, while removing the BUG_ON()'s, and returning the total amount of added free space to an optional u64 pointer argument. Reported-by: syzbot+3ba856e07b7127889d8c@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/000000000000e9cb8305ff4e8327@google.com/ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/block-group.c | 51 +++++++++++++++++++++++++------------- fs/btrfs/block-group.h | 4 +-- fs/btrfs/free-space-tree.c | 24 ++++++++++++------ 3 files changed, 53 insertions(+), 26 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index d93e8735ab1f..d7aad5e8ee37 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -494,12 +494,16 @@ static void fragment_free_space(struct btrfs_block_group *block_group) * used yet since their free space will be released as soon as the transaction * commits. */ -u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end) +int add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end, + u64 *total_added_ret) { struct btrfs_fs_info *info = block_group->fs_info; - u64 extent_start, extent_end, size, total_added = 0; + u64 extent_start, extent_end, size; int ret; + if (total_added_ret) + *total_added_ret = 0; + while (start < end) { ret = find_first_extent_bit(&info->excluded_extents, start, &extent_start, &extent_end, @@ -512,10 +516,12 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end start = extent_end + 1; } else if (extent_start > start && extent_start < end) { size = extent_start - start; - total_added += size; ret = btrfs_add_free_space_async_trimmed(block_group, start, size); - BUG_ON(ret); /* -ENOMEM or logic error */ + if (ret) + return ret; + if (total_added_ret) + *total_added_ret += size; start = extent_end + 1; } else { break; @@ -524,13 +530,15 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end if (start < end) { size = end - start; - total_added += size; ret = btrfs_add_free_space_async_trimmed(block_group, start, size); - BUG_ON(ret); /* -ENOMEM or logic error */ + if (ret) + return ret; + if (total_added_ret) + *total_added_ret += size; } - return total_added; + return 0; } static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) @@ -637,8 +645,13 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) if (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY) { - total_found += add_new_free_space(block_group, last, - key.objectid); + u64 space_added; + + ret = add_new_free_space(block_group, last, key.objectid, + &space_added); + if (ret) + goto out; + total_found += space_added; if (key.type == BTRFS_METADATA_ITEM_KEY) last = key.objectid + fs_info->nodesize; @@ -653,11 +666,10 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) } path->slots[0]++; } - ret = 0; - - total_found += add_new_free_space(block_group, last, - block_group->start + block_group->length); + ret = add_new_free_space(block_group, last, + block_group->start + block_group->length, + NULL); out: btrfs_free_path(path); return ret; @@ -2101,9 +2113,11 @@ static int read_one_block_group(struct btrfs_fs_info *info, btrfs_free_excluded_extents(cache); } else if (cache->used == 0) { cache->cached = BTRFS_CACHE_FINISHED; - add_new_free_space(cache, cache->start, - cache->start + cache->length); + ret = add_new_free_space(cache, cache->start, + cache->start + cache->length, NULL); btrfs_free_excluded_extents(cache); + if (ret) + goto error; } ret = btrfs_add_block_group_cache(info, cache); @@ -2529,9 +2543,12 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - add_new_free_space(cache, chunk_offset, chunk_offset + size); - + ret = add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL); btrfs_free_excluded_extents(cache); + if (ret) { + btrfs_put_block_group(cache); + return ERR_PTR(ret); + } /* * Ensure the corresponding space_info object is created and diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 8fb14b99a1d1..0a3d38682358 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -284,8 +284,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait); void btrfs_put_caching_control(struct btrfs_caching_control *ctl); struct btrfs_caching_control *btrfs_get_caching_control( struct btrfs_block_group *cache); -u64 add_new_free_space(struct btrfs_block_group *block_group, - u64 start, u64 end); +int add_new_free_space(struct btrfs_block_group *block_group, + u64 start, u64 end, u64 *total_added_ret); struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, const u64 chunk_offset); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index a07450f64abb..a207db932226 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1510,9 +1510,13 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, if (prev_bit == 0 && bit == 1) { extent_start = offset; } else if (prev_bit == 1 && bit == 0) { - total_found += add_new_free_space(block_group, - extent_start, - offset); + u64 space_added; + + ret = add_new_free_space(block_group, extent_start, + offset, &space_added); + if (ret) + goto out; + total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); @@ -1524,8 +1528,9 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, } } if (prev_bit == 1) { - total_found += add_new_free_space(block_group, extent_start, - end); + ret = add_new_free_space(block_group, extent_start, end, NULL); + if (ret) + goto out; extent_count++; } @@ -1564,6 +1569,8 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, end = block_group->start + block_group->length; while (1) { + u64 space_added; + ret = btrfs_next_item(root, path); if (ret < 0) goto out; @@ -1578,8 +1585,11 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY); ASSERT(key.objectid < end && key.objectid + key.offset <= end); - total_found += add_new_free_space(block_group, key.objectid, - key.objectid + key.offset); + ret = add_new_free_space(block_group, key.objectid, + key.objectid + key.offset, &space_added); + if (ret) + goto out; + total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); From a78a8bcdc26de5ef3a0ee27c9c6c512e54a6051c Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 29 Jun 2023 19:11:44 +0800 Subject: [PATCH 0150/2093] f2fs: fix to do sanity check on direct node in truncate_dnode() commit a6ec83786ab9f13f25fb18166dee908845713a95 upstream. syzbot reports below bug: BUG: KASAN: slab-use-after-free in f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 Read of size 4 at addr ffff88802a25c000 by task syz-executor148/5000 CPU: 1 PID: 5000 Comm: syz-executor148 Not tainted 6.4.0-rc7-syzkaller-00041-ge660abd551f1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:351 print_report mm/kasan/report.c:462 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:572 f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 truncate_dnode+0x229/0x2e0 fs/f2fs/node.c:944 f2fs_truncate_inode_blocks+0x64b/0xde0 fs/f2fs/node.c:1154 f2fs_do_truncate_blocks+0x4ac/0xf30 fs/f2fs/file.c:721 f2fs_truncate_blocks+0x7b/0x300 fs/f2fs/file.c:749 f2fs_truncate.part.0+0x4a5/0x630 fs/f2fs/file.c:799 f2fs_truncate include/linux/fs.h:825 [inline] f2fs_setattr+0x1738/0x2090 fs/f2fs/file.c:1006 notify_change+0xb2c/0x1180 fs/attr.c:483 do_truncate+0x143/0x200 fs/open.c:66 handle_truncate fs/namei.c:3295 [inline] do_open fs/namei.c:3640 [inline] path_openat+0x2083/0x2750 fs/namei.c:3791 do_filp_open+0x1ba/0x410 fs/namei.c:3818 do_sys_openat2+0x16d/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_creat fs/open.c:1448 [inline] __se_sys_creat fs/open.c:1442 [inline] __x64_sys_creat+0xcd/0x120 fs/open.c:1442 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is, inodeA references inodeB via inodeB's ino, once inodeA is truncated, it calls truncate_dnode() to truncate data blocks in inodeB's node page, it traverse mapping data from node->i.i_addr[0] to node->i.i_addr[ADDRS_PER_BLOCK() - 1], result in out-of-boundary access. This patch fixes to add sanity check on dnode page in truncate_dnode(), so that, it can help to avoid triggering such issue, and once it encounters such issue, it will record newly introduced ERROR_INVALID_NODE_REFERENCE error into superblock, later fsck can detect such issue and try repairing. Also, it removes f2fs_truncate_data_blocks() for cleanup due to the function has only one caller, and uses f2fs_truncate_data_blocks_range() instead. Reported-and-tested-by: syzbot+12cb4425b22169b52036@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000f3038a05fef867f8@google.com Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/f2fs.h | 1 - fs/f2fs/file.c | 5 ----- fs/f2fs/node.c | 14 ++++++++++++-- include/linux/f2fs_fs.h | 1 + 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 4d1e48c676fa..78f39a78de29 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3431,7 +3431,6 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr) * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); -void f2fs_truncate_data_blocks(struct dnode_of_data *dn); int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 7b94f047cbf7..3ce6da4fac9c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -628,11 +628,6 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) dn->ofs_in_node, nr_free); } -void f2fs_truncate_data_blocks(struct dnode_of_data *dn) -{ - f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); -} - static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a010b4bc36d2..9fe502485930 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -923,6 +923,7 @@ static int truncate_node(struct dnode_of_data *dn) static int truncate_dnode(struct dnode_of_data *dn) { + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *page; int err; @@ -930,16 +931,25 @@ static int truncate_dnode(struct dnode_of_data *dn) return 1; /* get direct node */ - page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(sbi, dn->nid); if (PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); + if (IS_INODE(page) || ino_of_node(page) != dn->inode->i_ino) { + f2fs_err(sbi, "incorrect node reference, ino: %lu, nid: %u, ino_of_node: %u", + dn->inode->i_ino, dn->nid, ino_of_node(page)); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_INVALID_NODE_REFERENCE); + f2fs_put_page(page, 1); + return -EFSCORRUPTED; + } + /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; - f2fs_truncate_data_blocks(dn); + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); err = truncate_node(dn); if (err) { f2fs_put_page(page, 1); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index ee0d75d9a302..77055b239165 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -104,6 +104,7 @@ enum f2fs_error { ERROR_INCONSISTENT_SIT, ERROR_CORRUPTED_VERITY_XATTR, ERROR_CORRUPTED_XATTR, + ERROR_INVALID_NODE_REFERENCE, ERROR_MAX, }; From 88b1958fb57dd99406fd9f4ba4c2daf5e01168b8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 19 May 2023 15:21:16 +0100 Subject: [PATCH 0151/2093] io_uring: annotate offset timeout races commit 5498bf28d8f2bd63a46ad40f4427518615fb793f upstream. It's racy to read ->cached_cq_tail without taking proper measures (usually grabbing ->completion_lock) as timeout requests with CQE offsets do, however they have never had a good semantics for from when they start counting. Annotate racy reads with data_race(). Reported-by: syzbot+cb265db2f3f3468ef436@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/4de3685e185832a92a572df2be2c735d2e21a83d.1684506056.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/timeout.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 4c6a5666541c..b0cf05ebcbcc 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -545,7 +545,7 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags) goto add; } - tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + tail = data_race(ctx->cached_cq_tail) - atomic_read(&ctx->cq_timeouts); timeout->target_seq = tail + off; /* Update the last seq here in case io_flush_timeouts() hasn't. From 6c591fce484ebef302b510b71cd3269f1ca31346 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Sun, 25 Jun 2023 00:10:21 +0530 Subject: [PATCH 0152/2093] mtd: rawnand: omap_elm: Fix incorrect type in assignment [ Upstream commit d8403b9eeee66d5dd81ecb9445800b108c267ce3 ] Once the ECC word endianness is converted to BE32, we force cast it to u32 so we can use elm_write_reg() which in turn uses writel(). Fixes below sparse warnings: drivers/mtd/nand/raw/omap_elm.c:180:37: sparse: expected unsigned int [usertype] val drivers/mtd/nand/raw/omap_elm.c:180:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:185:37: sparse: expected unsigned int [usertype] val drivers/mtd/nand/raw/omap_elm.c:185:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:190:37: sparse: expected unsigned int [usertype] val drivers/mtd/nand/raw/omap_elm.c:190:37: sparse: got restricted __be32 [usertype] >> drivers/mtd/nand/raw/omap_elm.c:200:40: sparse: sparse: restricted __be32 degrades to integer drivers/mtd/nand/raw/omap_elm.c:206:39: sparse: sparse: restricted __be32 degrades to integer drivers/mtd/nand/raw/omap_elm.c:210:37: sparse: expected unsigned int [assigned] [usertype] val drivers/mtd/nand/raw/omap_elm.c:210:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:213:37: sparse: expected unsigned int [assigned] [usertype] val drivers/mtd/nand/raw/omap_elm.c:213:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:216:37: sparse: expected unsigned int [assigned] [usertype] val drivers/mtd/nand/raw/omap_elm.c:216:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:219:37: sparse: expected unsigned int [assigned] [usertype] val drivers/mtd/nand/raw/omap_elm.c:219:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:222:37: sparse: expected unsigned int [assigned] [usertype] val drivers/mtd/nand/raw/omap_elm.c:222:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:225:37: sparse: expected unsigned int [assigned] [usertype] val drivers/mtd/nand/raw/omap_elm.c:225:37: sparse: got restricted __be32 [usertype] drivers/mtd/nand/raw/omap_elm.c:228:39: sparse: sparse: restricted __be32 degrades to integer Fixes: bf22433575ef ("mtd: devices: elm: Add support for ELM error correction") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306212211.WDXokuWh-lkp@intel.com/ Signed-off-by: Roger Quadros Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230624184021.7740-1-rogerq@kernel.org Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/omap_elm.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/mtd/nand/raw/omap_elm.c b/drivers/mtd/nand/raw/omap_elm.c index 4796a48e1012..22d37fc37e98 100644 --- a/drivers/mtd/nand/raw/omap_elm.c +++ b/drivers/mtd/nand/raw/omap_elm.c @@ -177,17 +177,17 @@ static void elm_load_syndrome(struct elm_info *info, switch (info->bch_type) { case BCH8_ECC: /* syndrome fragment 0 = ecc[9-12B] */ - val = cpu_to_be32(*(u32 *) &ecc[9]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[9]); elm_write_reg(info, offset, val); /* syndrome fragment 1 = ecc[5-8B] */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[5]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[5]); elm_write_reg(info, offset, val); /* syndrome fragment 2 = ecc[1-4B] */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[1]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[1]); elm_write_reg(info, offset, val); /* syndrome fragment 3 = ecc[0B] */ @@ -197,35 +197,35 @@ static void elm_load_syndrome(struct elm_info *info, break; case BCH4_ECC: /* syndrome fragment 0 = ecc[20-52b] bits */ - val = (cpu_to_be32(*(u32 *) &ecc[3]) >> 4) | + val = ((__force u32)cpu_to_be32(*(u32 *)&ecc[3]) >> 4) | ((ecc[2] & 0xf) << 28); elm_write_reg(info, offset, val); /* syndrome fragment 1 = ecc[0-20b] bits */ offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[0]) >> 12; + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[0]) >> 12; elm_write_reg(info, offset, val); break; case BCH16_ECC: - val = cpu_to_be32(*(u32 *) &ecc[22]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[22]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[18]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[18]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[14]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[14]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[10]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[10]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[6]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[6]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[2]); + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[2]); elm_write_reg(info, offset, val); offset += 4; - val = cpu_to_be32(*(u32 *) &ecc[0]) >> 16; + val = (__force u32)cpu_to_be32(*(u32 *)&ecc[0]) >> 16; elm_write_reg(info, offset, val); break; default: From 5a8a35b71bd34570983505bcdc16c9456e8970d0 Mon Sep 17 00:00:00 2001 From: Johan Jonker Date: Fri, 14 Jul 2023 17:21:01 +0200 Subject: [PATCH 0153/2093] mtd: rawnand: rockchip: fix oobfree offset and description [ Upstream commit d0ca3b92b7a6f42841ea9da8492aaf649db79780 ] Rockchip boot blocks are written per 4 x 512 byte sectors per page. Each page with boot blocks must have a page address (PA) pointer in OOB to the next page. The currently advertised free OOB area starts at offset 6, like if 4 PA bytes were located right after the BBM. This is wrong as the PA bytes are located right before the ECC bytes. Fix the layout by allowing access to all bytes between the BBM and the PA bytes instead of reserving 4 bytes right after the BBM. This change breaks existing jffs2 users. Fixes: 058e0e847d54 ("mtd: rawnand: rockchip: NFC driver for RK3308, RK2928 and others") Signed-off-by: Johan Jonker Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/d202f12d-188c-20e8-f2c2-9cc874ad4d22@gmail.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/rockchip-nand-controller.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c index f133985cc053..9070dafae9db 100644 --- a/drivers/mtd/nand/raw/rockchip-nand-controller.c +++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c @@ -562,9 +562,10 @@ static int rk_nfc_write_page_raw(struct nand_chip *chip, const u8 *buf, * BBM OOB1 OOB2 OOB3 |......| PA0 PA1 PA2 PA3 * * The rk_nfc_ooblayout_free() function already has reserved - * these 4 bytes with: + * these 4 bytes together with 2 bytes for BBM + * by reducing it's length: * - * oob_region->offset = NFC_SYS_DATA_SIZE + 2; + * oob_region->length = rknand->metadata_size - NFC_SYS_DATA_SIZE - 2; */ if (!i) memcpy(rk_nfc_oob_ptr(chip, i), @@ -933,12 +934,8 @@ static int rk_nfc_ooblayout_free(struct mtd_info *mtd, int section, if (section) return -ERANGE; - /* - * The beginning of the OOB area stores the reserved data for the NFC, - * the size of the reserved data is NFC_SYS_DATA_SIZE bytes. - */ oob_region->length = rknand->metadata_size - NFC_SYS_DATA_SIZE - 2; - oob_region->offset = NFC_SYS_DATA_SIZE + 2; + oob_region->offset = 2; return 0; } From b71c00256da4e1d2f7f9bed31038a152bc40dbf9 Mon Sep 17 00:00:00 2001 From: Johan Jonker Date: Fri, 14 Jul 2023 17:21:21 +0200 Subject: [PATCH 0154/2093] mtd: rawnand: rockchip: Align hwecc vs. raw page helper layouts [ Upstream commit ea690ad78dd611e3906df5b948a516000b05c1cb ] Currently, read/write_page_hwecc() and read/write_page_raw() are not aligned: there is a mismatch in the OOB bytes which are not read/written at the same offset in both cases (raw vs. hwecc). This is a real problem when relying on the presence of the Page Addresses (PA) when using the NAND chip as a boot device, as the BootROM expects additional data in the OOB area at specific locations. Rockchip boot blocks are written per 4 x 512 byte sectors per page. Each page with boot blocks must have a page address (PA) pointer in OOB to the next page. Pages are written in a pattern depending on the NAND chip ID. Generate boot block page address and pattern for hwecc in user space and copy PA data to/from the already reserved last 4 bytes before ECC in the chip->oob_poi data layout. Align the different helpers. This change breaks existing jffs2 users. Fixes: 058e0e847d54 ("mtd: rawnand: rockchip: NFC driver for RK3308, RK2928 and others") Signed-off-by: Johan Jonker Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/5e782c08-862b-51ae-47ff-3299940928ca@gmail.com Signed-off-by: Sasha Levin --- .../mtd/nand/raw/rockchip-nand-controller.c | 34 ++++++++++++------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/drivers/mtd/nand/raw/rockchip-nand-controller.c b/drivers/mtd/nand/raw/rockchip-nand-controller.c index 9070dafae9db..c9c4e9ffcae1 100644 --- a/drivers/mtd/nand/raw/rockchip-nand-controller.c +++ b/drivers/mtd/nand/raw/rockchip-nand-controller.c @@ -598,7 +598,7 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, int pages_per_blk = mtd->erasesize / mtd->writesize; int ret = 0, i, boot_rom_mode = 0; dma_addr_t dma_data, dma_oob; - u32 reg; + u32 tmp; u8 *oob; nand_prog_page_begin_op(chip, page, 0, NULL, 0); @@ -625,6 +625,13 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, * * 0xFF 0xFF 0xFF 0xFF | BBM OOB1 OOB2 OOB3 | ... * + * The code here just swaps the first 4 bytes with the last + * 4 bytes without losing any data. + * + * The chip->oob_poi data layout: + * + * BBM OOB1 OOB2 OOB3 |......| PA0 PA1 PA2 PA3 + * * Configure the ECC algorithm supported by the boot ROM. */ if ((page < (pages_per_blk * rknand->boot_blks)) && @@ -635,21 +642,17 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf, } for (i = 0; i < ecc->steps; i++) { - if (!i) { - reg = 0xFFFFFFFF; - } else { + if (!i) + oob = chip->oob_poi + (ecc->steps - 1) * NFC_SYS_DATA_SIZE; + else oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; - reg = oob[0] | oob[1] << 8 | oob[2] << 16 | - oob[3] << 24; - } - if (!i && boot_rom_mode) - reg = (page & (pages_per_blk - 1)) * 4; + tmp = oob[0] | oob[1] << 8 | oob[2] << 16 | oob[3] << 24; if (nfc->cfg->type == NFC_V9) - nfc->oob_buf[i] = reg; + nfc->oob_buf[i] = tmp; else - nfc->oob_buf[i * (oob_step / 4)] = reg; + nfc->oob_buf[i * (oob_step / 4)] = tmp; } dma_data = dma_map_single(nfc->dev, (void *)nfc->page_buf, @@ -812,12 +815,17 @@ static int rk_nfc_read_page_hwecc(struct nand_chip *chip, u8 *buf, int oob_on, goto timeout_err; } - for (i = 1; i < ecc->steps; i++) { - oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; + for (i = 0; i < ecc->steps; i++) { + if (!i) + oob = chip->oob_poi + (ecc->steps - 1) * NFC_SYS_DATA_SIZE; + else + oob = chip->oob_poi + (i - 1) * NFC_SYS_DATA_SIZE; + if (nfc->cfg->type == NFC_V9) tmp = nfc->oob_buf[i]; else tmp = nfc->oob_buf[i * (oob_step / 4)]; + *oob++ = (u8)tmp; *oob++ = (u8)(tmp >> 8); *oob++ = (u8)(tmp >> 16); From f4b700c71802c81e6f9dce362ee7a0312c8377ba Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 19 Jul 2023 23:55:01 +0200 Subject: [PATCH 0155/2093] mtd: rawnand: fsl_upm: Fix an off-by one test in fun_exec_op() [ Upstream commit c6abce60338aa2080973cd95be0aedad528bb41f ] 'op-cs' is copied in 'fun->mchip_number' which is used to access the 'mchip_offsets' and the 'rnb_gpio' arrays. These arrays have NAND_MAX_CHIPS elements, so the index must be below this limit. Fix the sanity check in order to avoid the NAND_MAX_CHIPS value. This would lead to out-of-bound accesses. Fixes: 54309d657767 ("mtd: rawnand: fsl_upm: Implement exec_op()") Signed-off-by: Christophe JAILLET Reviewed-by: Dan Carpenter Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/cd01cba1c7eda58bdabaae174c78c067325803d2.1689803636.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/fsl_upm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c index b3cc427100a2..636e65328bb3 100644 --- a/drivers/mtd/nand/raw/fsl_upm.c +++ b/drivers/mtd/nand/raw/fsl_upm.c @@ -135,7 +135,7 @@ static int fun_exec_op(struct nand_chip *chip, const struct nand_operation *op, unsigned int i; int ret; - if (op->cs > NAND_MAX_CHIPS) + if (op->cs >= NAND_MAX_CHIPS) return -EINVAL; if (check_only) From a492b8281c3673895a77d9d66d1d5411b50f0072 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 24 Jul 2023 23:43:20 +0530 Subject: [PATCH 0156/2093] powerpc/mm/altmap: Fix altmap boundary check [ Upstream commit 6722b25712054c0f903b839b8f5088438dd04df3 ] altmap->free includes the entire free space from which altmap blocks can be allocated. So when checking whether the kernel is doing altmap block free, compute the boundary correctly, otherwise memory hotunplug can fail. Fixes: 9ef34630a461 ("powerpc/mm: Fallback to RAM if the altmap is unusable") Signed-off-by: "Aneesh Kumar K.V" Reviewed-by: David Hildenbrand Signed-off-by: Michael Ellerman Link: https://msgid.link/20230724181320.471386-1-aneesh.kumar@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/mm/init_64.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index fe1b83020e0d..0ec5b45b1e86 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -314,8 +314,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, start = ALIGN_DOWN(start, page_size); if (altmap) { alt_start = altmap->base_pfn; - alt_end = altmap->base_pfn + altmap->reserve + - altmap->free + altmap->alloc + altmap->align; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; } pr_debug("vmemmap_free %lx...%lx\n", start, end); From 740d4cae248ab532b5e6894a8eb94d117d6aa37a Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Mon, 15 May 2023 09:21:37 +0200 Subject: [PATCH 0157/2093] drm/imx/ipuv3: Fix front porch adjustment upon hactive aligning [ Upstream commit ee31742bf17636da1304af77b2cb1c29b5dda642 ] When hactive is not aligned to 8 pixels, it is aligned accordingly and hfront porch needs to be reduced the same amount. Unfortunately the front porch is set to the difference rather than reducing it. There are some Samsung TVs which can't cope with a front porch of instead of 70. Fixes: 94dfec48fca7 ("drm/imx: Add 8 pixel alignment fix") Signed-off-by: Alexander Stein Reviewed-by: Philipp Zabel Link: https://lore.kernel.org/r/20230515072137.116211-1-alexander.stein@ew.tq-group.com [p.zabel@pengutronix.de: Fixed subject] Signed-off-by: Philipp Zabel Link: https://patchwork.freedesktop.org/patch/msgid/20230515072137.116211-1-alexander.stein@ew.tq-group.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/imx/ipuv3-crtc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 5f26090b0c98..89585b31b985 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -310,7 +310,7 @@ static void ipu_crtc_mode_set_nofb(struct drm_crtc *crtc) dev_warn(ipu_crtc->dev, "8-pixel align hactive %d -> %d\n", sig_cfg.mode.hactive, new_hactive); - sig_cfg.mode.hfront_porch = new_hactive - sig_cfg.mode.hactive; + sig_cfg.mode.hfront_porch -= new_hactive - sig_cfg.mode.hactive; sig_cfg.mode.hactive = new_hactive; } From 63eeb50fa11009cc4c82919b040c361c4ea0f14e Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Thu, 16 Feb 2023 09:49:22 -0700 Subject: [PATCH 0158/2093] drm/amd/display: Ensure that planes are in the same order commit bb46a6a9bab134b9d15043ea8fa9d6c276e938b8 upstream. The function dc_update_planes_and_stream handles multiple cases where DC needs to remove and add planes in the commit tail phase. After Linux started to use this function, some of the IGT kms_plane started to fail; one good example to illustrate why the new sequence regressed IGT is the subtest plane-position-hole which has the following diagram as a template: +--------------------+ +-----------------------+ | +-----+ | | +-----+ | | | | | | | +-----+ | | | +--+ | ==> | | | | | | | |__| | | +-|---+ | | | | | +-----+ | | | | | +--------------------+ +-----------------------+ (a) Final image (b) Composed image IGT expects image (a) as the final result of two plane compositions as described in figure (b). After the migration to the new sequence, the last plane order is changed, and DC generates the following image: +---------------------+ | +-----+ | | | | | | | | | | +-----+ | | | +---------------------+ Notice that the generated image by DC is different because the small square that should be composed on top of the primary plane is below the primary plane. For this reason, the CRC will mismatch with the expected value. Since the function dc_add_all_planes_for_stream re-append all the new planes back to the dc_validation_set, this commit ensures that the original sequence is maintained. After this change, all CI tests in all ASICs start to pass again. Reviewed-by: Harry Wentland Acked-by: Qingqing Zhuo Suggested-by: Melissa Wen Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9b2915764306..86e07cc1d3dc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -351,6 +351,19 @@ static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state, return false; } +static inline void reverse_planes_order(struct dc_surface_update *array_of_surface_update, + int planes_count) +{ + int i, j; + struct dc_surface_update surface_updates_temp; + + for (i = 0, j = planes_count - 1; i < j; i++, j--) { + surface_updates_temp = array_of_surface_update[i]; + array_of_surface_update[i] = array_of_surface_update[j]; + array_of_surface_update[j] = surface_updates_temp; + } +} + /** * update_planes_and_stream_adapter() - Send planes to be updated in DC * @@ -367,6 +380,8 @@ static inline bool update_planes_and_stream_adapter(struct dc *dc, struct dc_stream_update *stream_update, struct dc_surface_update *array_of_surface_update) { + reverse_planes_order(array_of_surface_update, planes_count); + /* * Previous frame finished and HW is ready for optimization. */ From 56562676102e135e7aebada26c2aea146a5b5ad0 Mon Sep 17 00:00:00 2001 From: Peichen Huang Date: Mon, 20 Mar 2023 09:34:23 +0800 Subject: [PATCH 0159/2093] drm/amd/display: skip CLEAR_PAYLOAD_ID_TABLE if device mst_en is 0 commit a1c9a1e27022d13c70a14c4faeab6ce293ad043b upstream. [Why] Some dock and mst monitor don't like to receive CLEAR_PAYLOAD_ID_TABLE when mst_en is set to 0. It doesn't make sense to do so in source side, either. [How] Don't send CLEAR_PAYLOAD_ID_TABLE if mst_en is 0 Reviewed-by: George Shen Acked-by: Qingqing Zhuo Signed-off-by: Peichen Huang Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher [ 6.1.y doesn't have the file rename from 54618888d1ea7 ("drm/amd/display: break down dc_link.c") ] Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 5d53e54ebe90..c2c6c4587a5c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2092,6 +2092,7 @@ static enum dc_status enable_link_dp_mst( struct pipe_ctx *pipe_ctx) { struct dc_link *link = pipe_ctx->stream->link; + unsigned char mstm_cntl; /* sink signal type after MST branch is MST. Multiple MST sinks * share one link. Link DP PHY is enable or training only once. @@ -2100,7 +2101,9 @@ static enum dc_status enable_link_dp_mst( return DC_OK; /* clear payload table */ - dm_helpers_dp_mst_clear_payload_allocation_table(link->ctx, link); + core_link_read_dpcd(link, DP_MSTM_CTRL, &mstm_cntl, 1); + if (mstm_cntl & DP_MST_EN) + dm_helpers_dp_mst_clear_payload_allocation_table(link->ctx, link); /* to make sure the pending down rep can be processed * before enabling the link From e355972affb67aa2e9b6daa6d77008a6b88abcdf Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 21 Jul 2023 15:33:52 -0700 Subject: [PATCH 0160/2093] selftests/rseq: Play nice with binaries statically linked against glibc 2.35+ [ Upstream commit 3bcbc20942db5d738221cca31a928efc09827069 ] To allow running rseq and KVM's rseq selftests as statically linked binaries, initialize the various "trampoline" pointers to point directly at the expect glibc symbols, and skip the dlysm() lookups if the rseq size is non-zero, i.e. the binary is statically linked *and* the libc registered its own rseq. Define weak versions of the symbols so as not to break linking against libc versions that don't support rseq in any capacity. The KVM selftests in particular are often statically linked so that they can be run on targets with very limited runtime environments, i.e. test machines. Fixes: 233e667e1ae3 ("selftests/rseq: Uplift rseq selftests for compatibility with glibc-2.35") Cc: Aaron Lewis Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20230721223352.2333911-1-seanjc@google.com> Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- tools/testing/selftests/rseq/rseq.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 4177f9507bbe..b736a5169aad 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -32,9 +32,17 @@ #include "../kselftest.h" #include "rseq.h" -static const ptrdiff_t *libc_rseq_offset_p; -static const unsigned int *libc_rseq_size_p; -static const unsigned int *libc_rseq_flags_p; +/* + * Define weak versions to play nice with binaries that are statically linked + * against a libc that doesn't support registering its own rseq. + */ +__weak ptrdiff_t __rseq_offset; +__weak unsigned int __rseq_size; +__weak unsigned int __rseq_flags; + +static const ptrdiff_t *libc_rseq_offset_p = &__rseq_offset; +static const unsigned int *libc_rseq_size_p = &__rseq_size; +static const unsigned int *libc_rseq_flags_p = &__rseq_flags; /* Offset from the thread pointer to the rseq area. */ ptrdiff_t rseq_offset; @@ -108,9 +116,17 @@ int rseq_unregister_current_thread(void) static __attribute__((constructor)) void rseq_init(void) { - libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); - libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); - libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + /* + * If the libc's registered rseq size isn't already valid, it may be + * because the binary is dynamically linked and not necessarily due to + * libc not having registered a restartable sequence. Try to find the + * symbols if that's the case. + */ + if (!*libc_rseq_size_p) { + libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); + libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); + libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + } if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p && *libc_rseq_size_p != 0) { /* rseq registration owned by glibc */ From 6ba0594a81f91d6fd8ca9bd4ad23aa1618635a0f Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Thu, 10 Nov 2022 17:15:01 +0800 Subject: [PATCH 0161/2093] f2fs: fix to set flush_merge opt and show noflush_merge [ Upstream commit 967eaad1fed5f6335ea97a47d45214744dc57925 ] Some minor modifications to flush_merge and related parameters: 1.The FLUSH_MERGE opt is set by default only in non-ro mode. 2.When ro and merge are set at the same time, an error is reported. 3.Display noflush_merge mount opt. Suggested-by: Chao Yu Signed-off-by: Yangtao Li Signed-off-by: Jaegeuk Kim Stable-dep-of: 458c15dfbce6 ("f2fs: don't reset unchangable mount option in f2fs_remount()") Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b6dad389fa14..36bb1c969e8b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1347,6 +1347,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) return -EINVAL; } + if ((f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb)) && + test_opt(sbi, FLUSH_MERGE)) { + f2fs_err(sbi, "FLUSH_MERGE not compatible with readonly mode"); + return -EINVAL; + } + if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { f2fs_err(sbi, "Allow to mount readonly mode only"); return -EROFS; @@ -1933,8 +1939,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",inline_dentry"); else seq_puts(seq, ",noinline_dentry"); - if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE)) + if (test_opt(sbi, FLUSH_MERGE)) seq_puts(seq, ",flush_merge"); + else + seq_puts(seq, ",noflush_merge"); if (test_opt(sbi, NOBARRIER)) seq_puts(seq, ",nobarrier"); if (test_opt(sbi, FASTBOOT)) @@ -2063,7 +2071,8 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; - set_opt(sbi, FLUSH_MERGE); + if (!f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) + set_opt(sbi, FLUSH_MERGE); if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi)) { From e2fb24ce37caeaecff08af4e9967c8462624312b Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 23 May 2023 11:58:22 +0800 Subject: [PATCH 0162/2093] f2fs: don't reset unchangable mount option in f2fs_remount() [ Upstream commit 458c15dfbce62c35fefd9ca637b20a051309c9f1 ] syzbot reports a bug as below: general protection fault, probably for non-canonical address 0xdffffc0000000009: 0000 [#1] PREEMPT SMP KASAN RIP: 0010:__lock_acquire+0x69/0x2000 kernel/locking/lockdep.c:4942 Call Trace: lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5691 __raw_write_lock include/linux/rwlock_api_smp.h:209 [inline] _raw_write_lock+0x2e/0x40 kernel/locking/spinlock.c:300 __drop_extent_tree+0x3ac/0x660 fs/f2fs/extent_cache.c:1100 f2fs_drop_extent_tree+0x17/0x30 fs/f2fs/extent_cache.c:1116 f2fs_insert_range+0x2d5/0x3c0 fs/f2fs/file.c:1664 f2fs_fallocate+0x4e4/0x6d0 fs/f2fs/file.c:1838 vfs_fallocate+0x54b/0x6b0 fs/open.c:324 ksys_fallocate fs/open.c:347 [inline] __do_sys_fallocate fs/open.c:355 [inline] __se_sys_fallocate fs/open.c:353 [inline] __x64_sys_fallocate+0xbd/0x100 fs/open.c:353 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is race condition as below: - since it tries to remount rw filesystem, so that do_remount won't call sb_prepare_remount_readonly to block fallocate, there may be race condition in between remount and fallocate. - in f2fs_remount(), default_options() will reset mount option to default one, and then update it based on result of parse_options(), so there is a hole which race condition can happen. Thread A Thread B - f2fs_fill_super - parse_options - clear_opt(READ_EXTENT_CACHE) - f2fs_remount - default_options - set_opt(READ_EXTENT_CACHE) - f2fs_fallocate - f2fs_insert_range - f2fs_drop_extent_tree - __drop_extent_tree - __may_extent_tree - test_opt(READ_EXTENT_CACHE) return true - write_lock(&et->lock) access NULL pointer - parse_options - clear_opt(READ_EXTENT_CACHE) Cc: Reported-by: syzbot+d015b6c2fbb5c383bf08@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/20230522124203.3838360-1-chao@kernel.org Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 36bb1c969e8b..ff47aad636e5 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2040,9 +2040,22 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) return 0; } -static void default_options(struct f2fs_sb_info *sbi) +static void default_options(struct f2fs_sb_info *sbi, bool remount) { /* init some FS parameters */ + if (!remount) { + set_opt(sbi, READ_EXTENT_CACHE); + clear_opt(sbi, DISABLE_CHECKPOINT); + + if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) + set_opt(sbi, DISCARD); + + if (f2fs_sb_has_blkzoned(sbi)) + F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; + else + F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; + } + if (f2fs_sb_has_readonly(sbi)) F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE; else @@ -2065,23 +2078,16 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); - set_opt(sbi, READ_EXTENT_CACHE); set_opt(sbi, NOHEAP); - clear_opt(sbi, DISABLE_CHECKPOINT); set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; if (!f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) set_opt(sbi, FLUSH_MERGE); - if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) - set_opt(sbi, DISCARD); - if (f2fs_sb_has_blkzoned(sbi)) { + if (f2fs_sb_has_blkzoned(sbi)) F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; - F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; - } else { + else F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; - F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; - } #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -2253,7 +2259,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } - default_options(sbi); + default_options(sbi, true); /* parse mount options */ err = parse_options(sb, data, true); @@ -4150,7 +4156,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid, sizeof(raw_super->uuid)); - default_options(sbi); + default_options(sbi, false); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); if (data && !options) { From c2fdf827f8fc6a571e1b7cc38a61041f0321adf5 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 13 Jul 2023 21:59:37 +0900 Subject: [PATCH 0163/2093] exfat: check if filename entries exceeds max filename length [ Upstream commit d42334578eba1390859012ebb91e1e556d51db49 ] exfat_extract_uni_name copies characters from a given file name entry into the 'uniname' variable. This variable is actually defined on the stack of the exfat_readdir() function. According to the definition of the 'exfat_uni_name' type, the file name should be limited 255 characters (+ null teminator space), but the exfat_get_uniname_from_ext_entry() function can write more characters because there is no check if filename entries exceeds max filename length. This patch add the check not to copy filename characters when exceeding max filename length. Cc: stable@vger.kernel.org Cc: Yuezhang Mo Reported-by: Maxim Suhanov Reviewed-by: Sungjong Seo Signed-off-by: Namjae Jeon Signed-off-by: Sasha Levin --- fs/exfat/dir.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 78de6f67f882..51b03b0dd5f7 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -34,6 +34,7 @@ static void exfat_get_uniname_from_ext_entry(struct super_block *sb, { int i; struct exfat_entry_set_cache *es; + unsigned int uni_len = 0, len; es = exfat_get_dentry_set(sb, p_dir, entry, ES_ALL_ENTRIES); if (!es) @@ -52,7 +53,10 @@ static void exfat_get_uniname_from_ext_entry(struct super_block *sb, if (exfat_get_entry_type(ep) != TYPE_EXTEND) break; - exfat_extract_uni_name(ep, uniname); + len = exfat_extract_uni_name(ep, uniname); + uni_len += len; + if (len != EXFAT_FILE_NAME_LEN || uni_len >= MAX_NAME_LENGTH) + break; uniname += EXFAT_FILE_NAME_LEN; } @@ -1024,7 +1028,8 @@ int exfat_find_dir_entry(struct super_block *sb, struct exfat_inode_info *ei, if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; - if (step != DIRENT_STEP_NAME) { + if (step != DIRENT_STEP_NAME || + name_len >= MAX_NAME_LENGTH) { step = DIRENT_STEP_FILE; continue; } From 99255a2b68495d9ada122b6f2e262d967f9ceb61 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 Aug 2023 19:33:21 +0100 Subject: [PATCH 0164/2093] arm64/ptrace: Don't enable SVE when setting streaming SVE commit 045aecdfcb2e060db142d83a0f4082380c465d2c upstream. Systems which implement SME without also implementing SVE are architecturally valid but were not initially supported by the kernel, unfortunately we missed one issue in the ptrace code. The SVE register setting code is shared between SVE and streaming mode SVE. When we set full SVE register state we currently enable TIF_SVE unconditionally, in the case where streaming SVE is being configured on a system that supports vanilla SVE this is not an issue since we always initialise enough state for both vector lengths but on a system which only support SME it will result in us attempting to restore the SVE vector length after having set streaming SVE registers. Fix this by making the enabling of SVE conditional on setting SVE vector state. If we set streaming SVE state and SVE was not already enabled this will result in a SVE access trap on next use of normal SVE, this will cause us to flush our register state but this is fine since the only way to trigger a SVE access trap would be to exit streaming mode which will cause the in register state to be flushed anyway. Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers") Signed-off-by: Mark Brown Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230803-arm64-fix-ptrace-ssve-no-sve-v1-1-49df214bfb3e@kernel.org Signed-off-by: Catalin Marinas [Fix up backport -- broonie] Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/ptrace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 92bc9a2d702c..f19f020ccff9 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -937,11 +937,13 @@ static int sve_set_common(struct task_struct *target, /* * Ensure target->thread.sve_state is up to date with target's * FPSIMD regs, so that a short copyin leaves trailing - * registers unmodified. Always enable SVE even if going into - * streaming mode. + * registers unmodified. Only enable SVE if we are + * configuring normal SVE, a system with streaming SVE may not + * have normal SVE. */ fpsimd_sync_to_sve(target); - set_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SVE) + set_tsk_thread_flag(target, TIF_SVE); BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); start = SVE_PT_SVE_OFFSET; From 526defeec474ea8002b8312b9c88f96fa1f85a48 Mon Sep 17 00:00:00 2001 From: Tong Liu01 Date: Tue, 8 Aug 2023 12:50:53 -0500 Subject: [PATCH 0165/2093] drm/amdgpu: add vram reservation based on vram_usagebyfirmware_v2_2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 4864f2ee9ee2acf4a1009b58fbc62f17fa086d4e upstream Move TMR region from top of FB to 2MB for FFBM, so we need to reserve TMR region firstly to make sure TMR can be allocated at 2MB Signed-off-by: Tong Liu01 Acked-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c | 104 ++++++++++++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 51 +++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 5 + drivers/gpu/drm/amd/include/atomfirmware.h | 63 +++++++++-- 4 files changed, 191 insertions(+), 32 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index b81b77a9efa6..9b97fa39d47a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -101,39 +101,97 @@ void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev) } } +static int amdgpu_atomfirmware_allocate_fb_v2_1(struct amdgpu_device *adev, + struct vram_usagebyfirmware_v2_1 *fw_usage, int *usage_bytes) +{ + uint32_t start_addr, fw_size, drv_size; + + start_addr = le32_to_cpu(fw_usage->start_address_in_kb); + fw_size = le16_to_cpu(fw_usage->used_by_firmware_in_kb); + drv_size = le16_to_cpu(fw_usage->used_by_driver_in_kb); + + DRM_DEBUG("atom firmware v2_1 requested %08x %dkb fw %dkb drv\n", + start_addr, + fw_size, + drv_size); + + if ((start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) == + (uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION << + ATOM_VRAM_OPERATION_FLAGS_SHIFT)) { + /* Firmware request VRAM reservation for SR-IOV */ + adev->mman.fw_vram_usage_start_offset = (start_addr & + (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; + adev->mman.fw_vram_usage_size = fw_size << 10; + /* Use the default scratch size */ + *usage_bytes = 0; + } else { + *usage_bytes = drv_size << 10; + } + return 0; +} + +static int amdgpu_atomfirmware_allocate_fb_v2_2(struct amdgpu_device *adev, + struct vram_usagebyfirmware_v2_2 *fw_usage, int *usage_bytes) +{ + uint32_t fw_start_addr, fw_size, drv_start_addr, drv_size; + + fw_start_addr = le32_to_cpu(fw_usage->fw_region_start_address_in_kb); + fw_size = le16_to_cpu(fw_usage->used_by_firmware_in_kb); + + drv_start_addr = le32_to_cpu(fw_usage->driver_region0_start_address_in_kb); + drv_size = le32_to_cpu(fw_usage->used_by_driver_region0_in_kb); + + DRM_DEBUG("atom requested fw start at %08x %dkb and drv start at %08x %dkb\n", + fw_start_addr, + fw_size, + drv_start_addr, + drv_size); + + if ((fw_start_addr & (ATOM_VRAM_BLOCK_NEEDS_NO_RESERVATION << 30)) == 0) { + /* Firmware request VRAM reservation for SR-IOV */ + adev->mman.fw_vram_usage_start_offset = (fw_start_addr & + (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; + adev->mman.fw_vram_usage_size = fw_size << 10; + } + + if ((drv_start_addr & (ATOM_VRAM_BLOCK_NEEDS_NO_RESERVATION << 30)) == 0) { + /* driver request VRAM reservation for SR-IOV */ + adev->mman.drv_vram_usage_start_offset = (drv_start_addr & + (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; + adev->mman.drv_vram_usage_size = drv_size << 10; + } + + *usage_bytes = 0; + return 0; +} + int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev) { struct atom_context *ctx = adev->mode_info.atom_context; int index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, vram_usagebyfirmware); - struct vram_usagebyfirmware_v2_1 *firmware_usage; - uint32_t start_addr, size; + struct vram_usagebyfirmware_v2_1 *fw_usage_v2_1; + struct vram_usagebyfirmware_v2_2 *fw_usage_v2_2; uint16_t data_offset; + uint8_t frev, crev; int usage_bytes = 0; - if (amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) { - firmware_usage = (struct vram_usagebyfirmware_v2_1 *)(ctx->bios + data_offset); - DRM_DEBUG("atom firmware requested %08x %dkb fw %dkb drv\n", - le32_to_cpu(firmware_usage->start_address_in_kb), - le16_to_cpu(firmware_usage->used_by_firmware_in_kb), - le16_to_cpu(firmware_usage->used_by_driver_in_kb)); - - start_addr = le32_to_cpu(firmware_usage->start_address_in_kb); - size = le16_to_cpu(firmware_usage->used_by_firmware_in_kb); - - if ((uint32_t)(start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) == - (uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION << - ATOM_VRAM_OPERATION_FLAGS_SHIFT)) { - /* Firmware request VRAM reservation for SR-IOV */ - adev->mman.fw_vram_usage_start_offset = (start_addr & - (~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10; - adev->mman.fw_vram_usage_size = size << 10; - /* Use the default scratch size */ - usage_bytes = 0; - } else { - usage_bytes = le16_to_cpu(firmware_usage->used_by_driver_in_kb) << 10; + if (amdgpu_atom_parse_data_header(ctx, index, NULL, &frev, &crev, &data_offset)) { + if (frev == 2 && crev == 1) { + fw_usage_v2_1 = + (struct vram_usagebyfirmware_v2_1 *)(ctx->bios + data_offset); + amdgpu_atomfirmware_allocate_fb_v2_1(adev, + fw_usage_v2_1, + &usage_bytes); + } else if (frev >= 2 && crev >= 2) { + fw_usage_v2_2 = + (struct vram_usagebyfirmware_v2_2 *)(ctx->bios + data_offset); + amdgpu_atomfirmware_allocate_fb_v2_2(adev, + fw_usage_v2_2, + &usage_bytes); } } + ctx->scratch_size_bytes = 0; if (usage_bytes == 0) usage_bytes = 20 * 1024; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b64938ed8cb6..c66e7c79d653 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1537,6 +1537,23 @@ static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev) NULL, &adev->mman.fw_vram_usage_va); } +/* + * Driver Reservation functions + */ +/** + * amdgpu_ttm_drv_reserve_vram_fini - free drv reserved vram + * + * @adev: amdgpu_device pointer + * + * free drv reserved vram if it has been reserved. + */ +static void amdgpu_ttm_drv_reserve_vram_fini(struct amdgpu_device *adev) +{ + amdgpu_bo_free_kernel(&adev->mman.drv_vram_usage_reserved_bo, + NULL, + NULL); +} + /** * amdgpu_ttm_fw_reserve_vram_init - create bo vram reservation from fw * @@ -1563,6 +1580,31 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev) &adev->mman.fw_vram_usage_va); } +/** + * amdgpu_ttm_drv_reserve_vram_init - create bo vram reservation from driver + * + * @adev: amdgpu_device pointer + * + * create bo vram reservation from drv. + */ +static int amdgpu_ttm_drv_reserve_vram_init(struct amdgpu_device *adev) +{ + uint64_t vram_size = adev->gmc.visible_vram_size; + + adev->mman.drv_vram_usage_reserved_bo = NULL; + + if (adev->mman.drv_vram_usage_size == 0 || + adev->mman.drv_vram_usage_size > vram_size) + return 0; + + return amdgpu_bo_create_kernel_at(adev, + adev->mman.drv_vram_usage_start_offset, + adev->mman.drv_vram_usage_size, + AMDGPU_GEM_DOMAIN_VRAM, + &adev->mman.drv_vram_usage_reserved_bo, + NULL); +} + /* * Memoy training reservation functions */ @@ -1730,6 +1772,14 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) return r; } + /* + *The reserved vram for driver must be pinned to the specified + *place on the VRAM, so reserve it early. + */ + r = amdgpu_ttm_drv_reserve_vram_init(adev); + if (r) + return r; + /* * only NAVI10 and onwards ASIC support for IP discovery. * If IP discovery enabled, a block of memory should be @@ -1855,6 +1905,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) amdgpu_bo_free_kernel(&adev->mman.sdma_access_bo, NULL, &adev->mman.sdma_access_ptr); amdgpu_ttm_fw_reserve_vram_fini(adev); + amdgpu_ttm_drv_reserve_vram_fini(adev); if (drm_dev_enter(adev_to_drm(adev), &idx)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index a37207011a69..b391c8d076ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -86,6 +86,11 @@ struct amdgpu_mman { struct amdgpu_bo *fw_vram_usage_reserved_bo; void *fw_vram_usage_va; + /* driver VRAM reservation */ + u64 drv_vram_usage_start_offset; + u64 drv_vram_usage_size; + struct amdgpu_bo *drv_vram_usage_reserved_bo; + /* PAGE_SIZE'd BO for process memory r/w over SDMA. */ struct amdgpu_bo *sdma_access_bo; void *sdma_access_ptr; diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index ff855cb21d3f..bbe1337a8cee 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -705,20 +705,65 @@ struct atom_gpio_pin_lut_v2_1 }; -/* - *************************************************************************** - Data Table vram_usagebyfirmware structure - *************************************************************************** -*/ +/* + * VBIOS/PRE-OS always reserve a FB region at the top of frame buffer. driver should not write + * access that region. driver can allocate their own reservation region as long as it does not + * overlap firwmare's reservation region. + * if (pre-NV1X) atom data table firmwareInfoTable version < 3.3: + * in this case, atom data table vram_usagebyfirmwareTable version always <= 2.1 + * if VBIOS/UEFI GOP is posted: + * VBIOS/UEFIGOP update used_by_firmware_in_kb = total reserved size by VBIOS + * update start_address_in_kb = total_mem_size_in_kb - used_by_firmware_in_kb; + * ( total_mem_size_in_kb = reg(CONFIG_MEMSIZE)<<10) + * driver can allocate driver reservation region under firmware reservation, + * used_by_driver_in_kb = driver reservation size + * driver reservation start address = (start_address_in_kb - used_by_driver_in_kb) + * Comment1[hchan]: There is only one reservation at the beginning of the FB reserved by + * host driver. Host driver would overwrite the table with the following + * used_by_firmware_in_kb = total reserved size for pf-vf info exchange and + * set SRIOV_MSG_SHARE_RESERVATION mask start_address_in_kb = 0 + * else there is no VBIOS reservation region: + * driver must allocate driver reservation region at top of FB. + * driver set used_by_driver_in_kb = driver reservation size + * driver reservation start address = (total_mem_size_in_kb - used_by_driver_in_kb) + * same as Comment1 + * else (NV1X and after): + * if VBIOS/UEFI GOP is posted: + * VBIOS/UEFIGOP update: + * used_by_firmware_in_kb = atom_firmware_Info_v3_3.fw_reserved_size_in_kb; + * start_address_in_kb = total_mem_size_in_kb - used_by_firmware_in_kb; + * (total_mem_size_in_kb = reg(CONFIG_MEMSIZE)<<10) + * if vram_usagebyfirmwareTable version <= 2.1: + * driver can allocate driver reservation region under firmware reservation, + * driver set used_by_driver_in_kb = driver reservation size + * driver reservation start address = start_address_in_kb - used_by_driver_in_kb + * same as Comment1 + * else driver can: + * allocate it reservation any place as long as it does overlap pre-OS FW reservation area + * set used_by_driver_region0_in_kb = driver reservation size + * set driver_region0_start_address_in_kb = driver reservation region start address + * Comment2[hchan]: Host driver can set used_by_firmware_in_kb and start_address_in_kb to + * zero as the reservation for VF as it doesn’t exist. And Host driver should also + * update atom_firmware_Info table to remove the same VBIOS reservation as well. + */ struct vram_usagebyfirmware_v2_1 { - struct atom_common_table_header table_header; - uint32_t start_address_in_kb; - uint16_t used_by_firmware_in_kb; - uint16_t used_by_driver_in_kb; + struct atom_common_table_header table_header; + uint32_t start_address_in_kb; + uint16_t used_by_firmware_in_kb; + uint16_t used_by_driver_in_kb; }; +struct vram_usagebyfirmware_v2_2 { + struct atom_common_table_header table_header; + uint32_t fw_region_start_address_in_kb; + uint16_t used_by_firmware_in_kb; + uint16_t reserved; + uint32_t driver_region0_start_address_in_kb; + uint32_t used_by_driver_region0_in_kb; + uint32_t reserved32[7]; +}; /* *************************************************************************** From 3d0a34c42f0d50c06ca21761d625a823e245118e Mon Sep 17 00:00:00 2001 From: Luben Tuikov Date: Tue, 8 Aug 2023 12:50:54 -0500 Subject: [PATCH 0166/2093] drm/amdgpu: Remove unnecessary domain argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3273f11675ef11959d25a56df3279f712bcd41b7 upstream Remove the "domain" argument to amdgpu_bo_create_kernel_at() since this function takes an "offset" argument which is the offset off of VRAM, and as such allocation always takes place in VRAM. Thus, the "domain" argument is unnecessary. Cc: Alex Deucher Cc: Christian König Cc: AMD Graphics Signed-off-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 10 +++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 7 ------- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 1 - 4 files changed, 6 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index ad8cb9e6d1ab..0ee7c935fba1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -347,17 +347,16 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, * @adev: amdgpu device object * @offset: offset of the BO * @size: size of the BO - * @domain: where to place it * @bo_ptr: used to initialize BOs in structures * @cpu_addr: optional CPU address mapping * - * Creates a kernel BO at a specific offset in the address space of the domain. + * Creates a kernel BO at a specific offset in VRAM. * * Returns: * 0 on success, negative error code otherwise. */ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, - uint64_t offset, uint64_t size, uint32_t domain, + uint64_t offset, uint64_t size, struct amdgpu_bo **bo_ptr, void **cpu_addr) { struct ttm_operation_ctx ctx = { false, false }; @@ -367,8 +366,9 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, offset &= PAGE_MASK; size = ALIGN(size, PAGE_SIZE); - r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, domain, bo_ptr, - NULL, cpu_addr); + r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, bo_ptr, NULL, + cpu_addr); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 147b79c10cbb..93207badf83f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -284,7 +284,7 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, u32 domain, struct amdgpu_bo **bo_ptr, u64 *gpu_addr, void **cpu_addr); int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, - uint64_t offset, uint64_t size, uint32_t domain, + uint64_t offset, uint64_t size, struct amdgpu_bo **bo_ptr, void **cpu_addr); int amdgpu_bo_create_user(struct amdgpu_device *adev, struct amdgpu_bo_param *bp, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index c66e7c79d653..917147dee8a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1575,7 +1575,6 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev) return amdgpu_bo_create_kernel_at(adev, adev->mman.fw_vram_usage_start_offset, adev->mman.fw_vram_usage_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.fw_vram_usage_reserved_bo, &adev->mman.fw_vram_usage_va); } @@ -1600,7 +1599,6 @@ static int amdgpu_ttm_drv_reserve_vram_init(struct amdgpu_device *adev) return amdgpu_bo_create_kernel_at(adev, adev->mman.drv_vram_usage_start_offset, adev->mman.drv_vram_usage_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.drv_vram_usage_reserved_bo, NULL); } @@ -1681,7 +1679,6 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) ret = amdgpu_bo_create_kernel_at(adev, ctx->c2p_train_data_offset, ctx->train_data_size, - AMDGPU_GEM_DOMAIN_VRAM, &ctx->c2p_bo, NULL); if (ret) { @@ -1695,7 +1692,6 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) ret = amdgpu_bo_create_kernel_at(adev, adev->gmc.real_vram_size - adev->mman.discovery_tmr_size, adev->mman.discovery_tmr_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.discovery_memory, NULL); if (ret) { @@ -1796,21 +1792,18 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) * avoid display artifacts while transitioning between pre-OS * and driver. */ r = amdgpu_bo_create_kernel_at(adev, 0, adev->mman.stolen_vga_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.stolen_vga_memory, NULL); if (r) return r; r = amdgpu_bo_create_kernel_at(adev, adev->mman.stolen_vga_size, adev->mman.stolen_extended_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.stolen_extended_memory, NULL); if (r) return r; r = amdgpu_bo_create_kernel_at(adev, adev->mman.stolen_reserved_offset, adev->mman.stolen_reserved_size, - AMDGPU_GEM_DOMAIN_VRAM, &adev->mman.stolen_reserved_memory, NULL); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index c73abe54d974..81549f1edfe0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -391,7 +391,6 @@ static void amdgpu_virt_ras_reserve_bps(struct amdgpu_device *adev) */ if (amdgpu_bo_create_kernel_at(adev, bp << AMDGPU_GPU_PAGE_SHIFT, AMDGPU_GPU_PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM, &bo, NULL)) DRM_DEBUG("RAS WARN: reserve vram for retired page %llx fail\n", bp); From af7215182417c892e09bcb6829377ce5c69f127f Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Tue, 8 Aug 2023 12:50:55 -0500 Subject: [PATCH 0167/2093] drm/amdgpu: Use apt name for FW reserved region commit db3b5cb64a9ca301d14ed027e470834316720e42 upstream Use the generic term fw_reserved_memory for FW reserve region. This region may also hold discovery TMR in addition to other reserve regions. This region size could be larger than discovery tmr size, hence don't change the discovery tmr size based on this. Signed-off-by: Lijo Lazar Reviewed-by: Le Ma Signed-off-by: Alex Deucher [ This change fixes reading IP discovery from debugfs. It needed to be hand modified because: * GC 9.4.3 support isn't introduced in older kernels until 228ce176434b ("drm/amdgpu: Handle VRAM dependencies on GFXIP9.4.3") * It also changed because of 58ab2c08d708 (drm/amdgpu: use VRAM|GTT for a bunch of kernel allocations) not being present. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2748 ] Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 33 ++++++++++++++----------- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 3 ++- 2 files changed, 21 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 917147dee8a2..10469f20a10c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1625,14 +1625,15 @@ static int amdgpu_ttm_training_reserve_vram_fini(struct amdgpu_device *adev) return 0; } -static void amdgpu_ttm_training_data_block_init(struct amdgpu_device *adev) +static void amdgpu_ttm_training_data_block_init(struct amdgpu_device *adev, + uint32_t reserve_size) { struct psp_memory_training_context *ctx = &adev->psp.mem_train_ctx; memset(ctx, 0, sizeof(*ctx)); ctx->c2p_train_data_offset = - ALIGN((adev->gmc.mc_vram_size - adev->mman.discovery_tmr_size - SZ_1M), SZ_1M); + ALIGN((adev->gmc.mc_vram_size - reserve_size - SZ_1M), SZ_1M); ctx->p2c_train_data_offset = (adev->gmc.mc_vram_size - GDDR6_MEM_TRAINING_OFFSET); ctx->train_data_size = @@ -1650,9 +1651,10 @@ static void amdgpu_ttm_training_data_block_init(struct amdgpu_device *adev) */ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) { - int ret; struct psp_memory_training_context *ctx = &adev->psp.mem_train_ctx; bool mem_train_support = false; + uint32_t reserve_size = 0; + int ret; if (!amdgpu_sriov_vf(adev)) { if (amdgpu_atomfirmware_mem_training_supported(adev)) @@ -1668,14 +1670,15 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) * Otherwise, fallback to legacy approach to check and reserve tmr block for ip * discovery data and G6 memory training data respectively */ - adev->mman.discovery_tmr_size = - amdgpu_atomfirmware_get_fw_reserved_fb_size(adev); - if (!adev->mman.discovery_tmr_size) - adev->mman.discovery_tmr_size = DISCOVERY_TMR_OFFSET; + if (adev->bios) + reserve_size = + amdgpu_atomfirmware_get_fw_reserved_fb_size(adev); + if (!reserve_size) + reserve_size = DISCOVERY_TMR_OFFSET; if (mem_train_support) { /* reserve vram for mem train according to TMR location */ - amdgpu_ttm_training_data_block_init(adev); + amdgpu_ttm_training_data_block_init(adev, reserve_size); ret = amdgpu_bo_create_kernel_at(adev, ctx->c2p_train_data_offset, ctx->train_data_size, @@ -1690,13 +1693,14 @@ static int amdgpu_ttm_reserve_tmr(struct amdgpu_device *adev) } ret = amdgpu_bo_create_kernel_at(adev, - adev->gmc.real_vram_size - adev->mman.discovery_tmr_size, - adev->mman.discovery_tmr_size, - &adev->mman.discovery_memory, + adev->gmc.real_vram_size - reserve_size, + reserve_size, + &adev->mman.fw_reserved_memory, NULL); if (ret) { DRM_ERROR("alloc tmr failed(%d)!\n", ret); - amdgpu_bo_free_kernel(&adev->mman.discovery_memory, NULL, NULL); + amdgpu_bo_free_kernel(&adev->mman.fw_reserved_memory, + NULL, NULL); return ret; } @@ -1890,8 +1894,9 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) /* return the stolen vga memory back to VRAM */ amdgpu_bo_free_kernel(&adev->mman.stolen_vga_memory, NULL, NULL); amdgpu_bo_free_kernel(&adev->mman.stolen_extended_memory, NULL, NULL); - /* return the IP Discovery TMR memory back to VRAM */ - amdgpu_bo_free_kernel(&adev->mman.discovery_memory, NULL, NULL); + /* return the FW reserved memory back to VRAM */ + amdgpu_bo_free_kernel(&adev->mman.fw_reserved_memory, NULL, + NULL); if (adev->mman.stolen_reserved_size) amdgpu_bo_free_kernel(&adev->mman.stolen_reserved_memory, NULL, NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index b391c8d076ff..0fefa5e3a524 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -78,7 +78,8 @@ struct amdgpu_mman { /* discovery */ uint8_t *discovery_bin; uint32_t discovery_tmr_size; - struct amdgpu_bo *discovery_memory; + /* fw reserved memory */ + struct amdgpu_bo *fw_reserved_memory; /* firmware VRAM reservation */ u64 fw_vram_usage_start_offset; From 673cdde74fd13fff0acc4c6c41f5f949434156a5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 9 Aug 2023 11:13:22 +0200 Subject: [PATCH 0168/2093] Revert "drm/i915: Disable DC states for all commits" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 0fc6fea41c7122aa5f2088117f50144b507e13d7 which is commit a2b6e99d8a623544f3bdccd28ee35b9c1b00daa5 upstream. It is reported to cause regression issues, so it should be reverted from the 6.1.y tree for now. Reported-by: Thorsten Leemhuis Link: https://lore.kernel.org/r/f0870e8f-0c66-57fd-f95d-18d014a11939@leemhuis.info Link: https://gitlab.freedesktop.org/drm/intel/-/issues/8419 Cc: Manasi Navare Cc: Drew Davenport Cc: Jouni Högander Cc: Imre Deak Cc: Ville Syrjälä Cc: Jani Nikula Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_display.c | 28 +++----------------- 1 file changed, 3 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index da9b995b54c8..96e679a176e9 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -7123,8 +7123,6 @@ static void intel_update_crtc(struct intel_atomic_state *state, intel_fbc_update(state, crtc); - drm_WARN_ON(&i915->drm, !intel_display_power_is_enabled(i915, POWER_DOMAIN_DC_OFF)); - if (!modeset && (new_crtc_state->uapi.color_mgmt_changed || new_crtc_state->update_pipe)) @@ -7501,28 +7499,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) drm_atomic_helper_wait_for_dependencies(&state->base); drm_dp_mst_atomic_wait_for_dependencies(&state->base); - /* - * During full modesets we write a lot of registers, wait - * for PLLs, etc. Doing that while DC states are enabled - * is not a good idea. - * - * During fastsets and other updates we also need to - * disable DC states due to the following scenario: - * 1. DC5 exit and PSR exit happen - * 2. Some or all _noarm() registers are written - * 3. Due to some long delay PSR is re-entered - * 4. DC5 entry -> DMC saves the already written new - * _noarm() registers and the old not yet written - * _arm() registers - * 5. DC5 exit -> DMC restores a mixture of old and - * new register values and arms the update - * 6. PSR exit -> hardware latches a mixture of old and - * new register values -> corrupted frame, or worse - * 7. New _arm() registers are finally written - * 8. Hardware finally latches a complete set of new - * register values, and subsequent frames will be OK again - */ - wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_DC_OFF); + if (state->modeset) + wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET); intel_atomic_prepare_plane_clear_colors(state); @@ -7661,8 +7639,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) * the culprit. */ intel_uncore_arm_unclaimed_mmio_detection(&dev_priv->uncore); + intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET, wakeref); } - intel_display_power_put(dev_priv, POWER_DOMAIN_DC_OFF, wakeref); intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref); /* From f2615bb47be4f53be92c81a6a8aa286c92ef04d9 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sat, 5 Aug 2023 00:06:43 +0200 Subject: [PATCH 0169/2093] x86/CPU/AMD: Do not leak quotient data after a division by 0 commit 77245f1c3c6495521f6a3af082696ee2f8ce3921 upstream. Under certain circumstances, an integer division by 0 which faults, can leave stale quotient data from a previous division operation on Zen1 microarchitectures. Do a dummy division 0/1 before returning from the #DE exception handler in order to avoid any leaks of potentially sensitive data. Signed-off-by: Borislav Petkov (AMD) Cc: Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/cpu/amd.c | 19 +++++++++++++++++++ arch/x86/kernel/traps.c | 2 ++ 4 files changed, 24 insertions(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index e721b8426c24..b122708792c4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -476,4 +476,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c13e4ff8ec70..45bf26862b99 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -801,10 +801,12 @@ extern u16 get_llc_id(unsigned int cpu); extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); extern bool cpu_has_ibpb_brtype_microcode(void); +extern void amd_clear_divider(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } +static inline void amd_clear_divider(void) { } #endif #define for_each_possible_hypervisor_cpuid_base(function) \ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7f0cf4a959c0..43910eb55b2e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -75,6 +75,10 @@ static const int amd_zenbleed[] = AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); +static const int amd_div0[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), + AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -1115,6 +1119,11 @@ static void init_amd(struct cpuinfo_x86 *c) check_null_seg_clears_base(c); zenbleed_check(c); + + if (cpu_has_amd_erratum(c, amd_div0)) { + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); + } } #ifdef CONFIG_X86_32 @@ -1275,3 +1284,13 @@ void amd_check_microcode(void) { on_each_cpu(zenbleed_check_cpu, NULL, 1); } + +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +void noinstr amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c0a5a4f225d9..7e8795d8b0f1 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -206,6 +206,8 @@ DEFINE_IDTENTRY(exc_divide_error) { do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, FPE_INTDIV, error_get_trap_addr(regs)); + + amd_clear_divider(); } DEFINE_IDTENTRY(exc_overflow) From 1321ab403b38366a4cfb283145bb2c005becb1e5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Aug 2023 12:08:27 +0200 Subject: [PATCH 0170/2093] Linux 6.1.45 Link: https://lore.kernel.org/r/20230809103636.615294317@linuxfoundation.org Tested-by: Miguel Ojeda # Rust Tested-by: Conor Dooley Tested-by: Ron Economos Tested-by: Takeshi Ogasawara Tested-by: Bagas Sanjaya Tested-by: SeongJae Park Tested-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 612f3d83629b..82c958299e98 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 44 +SUBLEVEL = 45 EXTRAVERSION = NAME = Curry Ramen From 65383fe06065bea6b40a6e1f309d6a763a7d6357 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 Jan 2023 12:21:35 -0800 Subject: [PATCH 0171/2093] gcc-plugins: Reorganize gimple includes for GCC 13 commit e6a71160cc145e18ab45195abf89884112e02dfb upstream. The gimple-iterator.h header must be included before gimple-fold.h starting with GCC 13. Reorganize gimple headers to work for all GCC versions. Reported-by: Palmer Dabbelt Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/all/20230113173033.4380-1-palmer@rivosinc.com/ Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Cc: Naresh Kamboju Signed-off-by: Greg Kroah-Hartman --- scripts/gcc-plugins/gcc-common.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 9a1895747b15..84c730da36dd 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -71,7 +71,9 @@ #include "varasm.h" #include "stor-layout.h" #include "internal-fn.h" +#include "gimple.h" #include "gimple-expr.h" +#include "gimple-iterator.h" #include "gimple-fold.h" #include "context.h" #include "tree-ssa-alias.h" @@ -85,10 +87,8 @@ #include "tree-eh.h" #include "stmt.h" #include "gimplify.h" -#include "gimple.h" #include "tree-phinodes.h" #include "tree-cfg.h" -#include "gimple-iterator.h" #include "gimple-ssa.h" #include "ssa-iterators.h" From ed2f8701fb9b176b9136140452cfedfb352598b7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Aug 2023 16:26:20 +0200 Subject: [PATCH 0172/2093] Revert "loongarch/cpu: Switch to arch_cpu_finalize_init()" This reverts commit 08e86d42e2c916e362d124e3bc6c824eb1862498 which is commit 9841c423164787feb8f1442f922b7d80a70c82f1 upstream. As Gunter reports: Building loongarch:defconfig ... failed -------------- Error log: :569:2: warning: #warning syscall fstat not implemented [-Wcpp] arch/loongarch/kernel/setup.c: In function 'arch_cpu_finalize_init': arch/loongarch/kernel/setup.c:86:9: error: implicit declaration of function 'alternative_instructions' Actually introduced in v6.1.44 with commit 08e86d42e2c9 ("loongarch/cpu: Switch to arch_cpu_finalize_init()"). Alternative instruction support was only introduced for loongarch in v6.2 with commit 19e5eb15b00c ("LoongArch: Add alternative runtime patching mechanism"). So revert it from 6.1.y. Reported-by: Guenter Roeck Link: https://lore.kernel.org/r/fcd7b764-9047-22ba-a040-41b6ff99959c@roeck-us.net Cc: Thomas Gleixner Cc: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/Kconfig | 1 - arch/loongarch/kernel/setup.c | 6 ------ 2 files changed, 7 deletions(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 270742cc3ca4..e737dc8cd660 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -10,7 +10,6 @@ config LOONGARCH select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI - select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 29725b37b35c..ae436def7ee9 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -12,7 +12,6 @@ */ #include #include -#include #include #include #include @@ -81,11 +80,6 @@ const char *get_system_type(void) return "generic-loongson-machine"; } -void __init arch_cpu_finalize_init(void) -{ - alternative_instructions(); -} - static const char *dmi_string_parse(const struct dmi_header *dm, u8 s) { const u8 *bp = ((u8 *) dm) + dm->length; From d8a7d6136cbf57738e7984b0c4f216cfd2ffbe6e Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 2 Aug 2023 07:25:33 -0500 Subject: [PATCH 0173/2093] tpm: Disable RNG for all AMD fTPMs commit 554b841d470338a3b1d6335b14ee1cd0c8f5d754 upstream. The TPM RNG functionality is not necessary for entropy when the CPU already supports the RDRAND instruction. The TPM RNG functionality was previously disabled on a subset of AMD fTPM series, but reports continue to show problems on some systems causing stutter root caused to TPM RNG functionality. Expand disabling TPM RNG use for all AMD fTPMs whether they have versions that claim to have fixed or not. To accomplish this, move the detection into part of the TPM CRB registration and add a flag indicating that the TPM should opt-out of registration to hwrng. Cc: stable@vger.kernel.org # 6.1.y+ Fixes: b006c439d58d ("hwrng: core - start hwrng kthread also for untrusted sources") Fixes: f1324bbc4011 ("tpm: disable hwrng for fTPM on some AMD designs") Reported-by: daniil.stas@posteo.net Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217719 Reported-by: bitlord0xff@gmail.com Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217212 Signed-off-by: Mario Limonciello Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm-chip.c | 68 ++----------------------------------- drivers/char/tpm/tpm_crb.c | 30 ++++++++++++++++ include/linux/tpm.h | 1 + 3 files changed, 33 insertions(+), 66 deletions(-) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index d7ef4d0a7409..64d3f8887169 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -507,70 +507,6 @@ static int tpm_add_legacy_sysfs(struct tpm_chip *chip) return 0; } -/* - * Some AMD fTPM versions may cause stutter - * https://www.amd.com/en/support/kb/faq/pa-410 - * - * Fixes are available in two series of fTPM firmware: - * 6.x.y.z series: 6.0.18.6 + - * 3.x.y.z series: 3.57.y.5 + - */ -#ifdef CONFIG_X86 -static bool tpm_amd_is_rng_defective(struct tpm_chip *chip) -{ - u32 val1, val2; - u64 version; - int ret; - - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) - return false; - - ret = tpm_request_locality(chip); - if (ret) - return false; - - ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val1, NULL); - if (ret) - goto release; - if (val1 != 0x414D4400U /* AMD */) { - ret = -ENODEV; - goto release; - } - ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_1, &val1, NULL); - if (ret) - goto release; - ret = tpm2_get_tpm_pt(chip, TPM2_PT_FIRMWARE_VERSION_2, &val2, NULL); - -release: - tpm_relinquish_locality(chip); - - if (ret) - return false; - - version = ((u64)val1 << 32) | val2; - if ((version >> 48) == 6) { - if (version >= 0x0006000000180006ULL) - return false; - } else if ((version >> 48) == 3) { - if (version >= 0x0003005700000005ULL) - return false; - } else { - return false; - } - - dev_warn(&chip->dev, - "AMD fTPM version 0x%llx causes system stutter; hwrng disabled\n", - version); - - return true; -} -#else -static inline bool tpm_amd_is_rng_defective(struct tpm_chip *chip) -{ - return false; -} -#endif /* CONFIG_X86 */ - static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); @@ -585,7 +521,7 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) static int tpm_add_hwrng(struct tpm_chip *chip) { if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip) || - tpm_amd_is_rng_defective(chip)) + chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED) return 0; snprintf(chip->hwrng_name, sizeof(chip->hwrng_name), @@ -716,7 +652,7 @@ void tpm_chip_unregister(struct tpm_chip *chip) { tpm_del_legacy_sysfs(chip); if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip) && - !tpm_amd_is_rng_defective(chip)) + !(chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED)) hwrng_unregister(&chip->hwrng); tpm_bios_log_teardown(chip); if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip)) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index cbbedf52607c..7f7f3bded453 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -463,6 +463,28 @@ static bool crb_req_canceled(struct tpm_chip *chip, u8 status) return (cancel & CRB_CANCEL_INVOKE) == CRB_CANCEL_INVOKE; } +static int crb_check_flags(struct tpm_chip *chip) +{ + u32 val; + int ret; + + ret = crb_request_locality(chip, 0); + if (ret) + return ret; + + ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val, NULL); + if (ret) + goto release; + + if (val == 0x414D4400U /* AMD */) + chip->flags |= TPM_CHIP_FLAG_HWRNG_DISABLED; + +release: + crb_relinquish_locality(chip, 0); + + return ret; +} + static const struct tpm_class_ops tpm_crb = { .flags = TPM_OPS_AUTO_STARTUP, .status = crb_status, @@ -800,6 +822,14 @@ static int crb_acpi_add(struct acpi_device *device) chip->acpi_dev_handle = device->handle; chip->flags = TPM_CHIP_FLAG_TPM2; + rc = tpm_chip_bootstrap(chip); + if (rc) + goto out; + + rc = crb_check_flags(chip); + if (rc) + goto out; + rc = tpm_chip_register(chip); out: diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4e22e4f4cec8..df5cd4245f29 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), + TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) From ccb1700ed60653d99bce29f3b62091e7c14858e3 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 7 Aug 2023 23:12:29 -0500 Subject: [PATCH 0174/2093] tpm: Add a helper for checking hwrng enabled commit cacc6e22932f373a91d7be55a9b992dc77f4c59b upstream. The same checks are repeated in three places to decide whether to use hwrng. Consolidate these into a helper. Also this fixes a case that one of them was missing a check in the cleanup path. Fixes: 554b841d4703 ("tpm: Disable RNG for all AMD fTPMs") Signed-off-by: Mario Limonciello Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm-chip.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 64d3f8887169..c0759d49fd14 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -518,10 +518,20 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) return tpm_get_random(chip, data, max); } +static bool tpm_is_hwrng_enabled(struct tpm_chip *chip) +{ + if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM)) + return false; + if (tpm_is_firmware_upgrade(chip)) + return false; + if (chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED) + return false; + return true; +} + static int tpm_add_hwrng(struct tpm_chip *chip) { - if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip) || - chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED) + if (!tpm_is_hwrng_enabled(chip)) return 0; snprintf(chip->hwrng_name, sizeof(chip->hwrng_name), @@ -626,7 +636,7 @@ int tpm_chip_register(struct tpm_chip *chip) return 0; out_hwrng: - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip)) + if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); out_ppi: tpm_bios_log_teardown(chip); @@ -651,8 +661,7 @@ EXPORT_SYMBOL_GPL(tpm_chip_register); void tpm_chip_unregister(struct tpm_chip *chip) { tpm_del_legacy_sysfs(chip); - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip) && - !(chip->flags & TPM_CHIP_FLAG_HWRNG_DISABLED)) + if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); tpm_bios_log_teardown(chip); if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip)) From c6bef3bc30fd4a175aef846b7d928a6c40d091cd Mon Sep 17 00:00:00 2001 From: Long Li Date: Sat, 29 Jul 2023 11:36:18 +0800 Subject: [PATCH 0175/2093] ksmbd: validate command request size commit 5aa4fda5aa9c2a5a7bac67b4a12b089ab81fee3c upstream. In commit 2b9b8f3b68ed ("ksmbd: validate command payload size"), except for SMB2_OPLOCK_BREAK_HE command, the request size of other commands is not checked, it's not expected. Fix it by add check for request size of other commands. Cc: stable@vger.kernel.org Fixes: 2b9b8f3b68ed ("ksmbd: validate command payload size") Acked-by: Namjae Jeon Signed-off-by: Long Li Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/smb2misc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 33b7e6c4ceff..e881df1d10cb 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -380,13 +380,13 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command == SMB2_OPLOCK_BREAK_HE && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (!(command == SMB2_OPLOCK_BREAK_HE && + (le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_20 || + le16_to_cpu(pdu->StructureSize2) == OP_BREAK_STRUCT_SIZE_21))) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, - "Illegal request size %d for oplock break\n", - le16_to_cpu(pdu->StructureSize2)); + "Illegal request size %u for command %d\n", + le16_to_cpu(pdu->StructureSize2), command); return 1; } } From f339d76a3a972601d0738b881b099d49ebbdc3a2 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 6 Aug 2023 08:44:17 +0900 Subject: [PATCH 0176/2093] ksmbd: fix wrong next length validation of ea buffer in smb2_set_ea() commit 79ed288cef201f1f212dfb934bcaac75572fb8f6 upstream. There are multiple smb2_ea_info buffers in FILE_FULL_EA_INFORMATION request from client. ksmbd find next smb2_ea_info using ->NextEntryOffset of current smb2_ea_info. ksmbd need to validate buffer length Before accessing the next ea. ksmbd should check buffer length using buf_len, not next variable. next is the start offset of current ea that got from previous ea. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21598 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/smb2pdu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 26cf73d664f9..f8ca44622d90 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2340,9 +2340,16 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, break; buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); - if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + if (buf_len < sizeof(struct smb2_ea_info)) { + rc = -EINVAL; break; + } + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) { + rc = -EINVAL; + break; + } } while (next != 0); kfree(attr_name); From ec18273e41d9f97a3db47ce8f42019625da646be Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 4 Aug 2023 12:42:45 -0400 Subject: [PATCH 0177/2093] KVM: SEV: snapshot the GHCB before accessing it commit 4e15a0ddc3ff40e8ea84032213976ecf774d7f77 upstream. Validation of the GHCB is susceptible to time-of-check/time-of-use vulnerabilities. To avoid them, we would like to always snapshot the fields that are read in sev_es_validate_vmgexit(), and not use the GHCB anymore after it returns. This means: - invoking sev_es_sync_from_ghcb() before any GHCB access, including before sev_es_validate_vmgexit() - snapshotting all fields including the valid bitmap and the sw_scratch field, which are currently not caching anywhere. The valid bitmap is the first thing to be copied out of the GHCB; then, further accesses will use the copy in svm->sev_es. Fixes: 291bd20d5d88 ("KVM: SVM: Add initial support for a VMGEXIT VMEXIT") Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/sev.c | 69 +++++++++++++++++++++--------------------- arch/x86/kvm/svm/svm.h | 26 ++++++++++++++++ 2 files changed, 61 insertions(+), 34 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4cb2e483db53..38fbe9dc199f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2410,15 +2410,18 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); - vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb); - vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb); + BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap)); + memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap)); - svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb); + vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb); - if (ghcb_xcr0_is_valid(ghcb)) { + svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb); + + if (kvm_ghcb_xcr0_is_valid(svm)) { vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); kvm_update_cpuid_runtime(vcpu); } @@ -2429,6 +2432,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) control->exit_code_hi = upper_32_bits(exit_code); control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); + svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb); /* Clear the valid entries fields */ memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); @@ -2457,56 +2461,56 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) reason = GHCB_ERR_MISSING_INPUT; - if (!ghcb_sw_exit_code_is_valid(ghcb) || - !ghcb_sw_exit_info_1_is_valid(ghcb) || - !ghcb_sw_exit_info_2_is_valid(ghcb)) + if (!kvm_ghcb_sw_exit_code_is_valid(svm) || + !kvm_ghcb_sw_exit_info_1_is_valid(svm) || + !kvm_ghcb_sw_exit_info_2_is_valid(svm)) goto vmgexit_err; switch (ghcb_get_sw_exit_code(ghcb)) { case SVM_EXIT_READ_DR7: break; case SVM_EXIT_WRITE_DR7: - if (!ghcb_rax_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSC: break; case SVM_EXIT_RDPMC: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_CPUID: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; if (ghcb_get_rax(ghcb) == 0xd) - if (!ghcb_xcr0_is_valid(ghcb)) + if (!kvm_ghcb_xcr0_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_INVD: break; case SVM_EXIT_IOIO: if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; } else { if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) - if (!ghcb_rax_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_MSR: - if (!ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; if (ghcb_get_sw_exit_info_1(ghcb)) { - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; } break; case SVM_EXIT_VMMCALL: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_cpl_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_cpl_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_RDTSCP: @@ -2514,19 +2518,19 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_EXIT_WBINVD: break; case SVM_EXIT_MONITOR: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb) || - !ghcb_rdx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_MWAIT: - if (!ghcb_rax_is_valid(ghcb) || - !ghcb_rcx_is_valid(ghcb)) + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_MMIO_READ: case SVM_VMGEXIT_MMIO_WRITE: - if (!ghcb_sw_scratch_is_valid(ghcb)) + if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: @@ -2556,9 +2560,6 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) dump_ghcb(svm); } - /* Clear the valid entries fields */ - memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); - ghcb_set_sw_exit_info_1(ghcb, 2); ghcb_set_sw_exit_info_2(ghcb, reason); @@ -2579,7 +2580,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) */ if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.sw_scratch, svm->sev_es.ghcb_sa, svm->sev_es.ghcb_sa_len); svm->sev_es.ghcb_sa_sync = false; @@ -2630,7 +2631,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; - scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); + scratch_gpa_beg = svm->sev_es.sw_scratch; if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); goto e_scratch; @@ -2846,11 +2847,11 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) exit_code = ghcb_get_sw_exit_code(ghcb); + sev_es_sync_from_ghcb(svm); ret = sev_es_validate_vmgexit(svm); if (ret) return ret; - sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index d0ed3f595229..62f87492763e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -196,10 +196,12 @@ struct vcpu_sev_es_state { /* SEV-ES support */ struct sev_es_save_area *vmsa; struct ghcb *ghcb; + u8 valid_bitmap[16]; struct kvm_host_map ghcb_map; bool received_first_sipi; /* SEV-ES scratch area support */ + u64 sw_scratch; void *ghcb_sa; u32 ghcb_sa_len; bool ghcb_sa_sync; @@ -688,4 +690,28 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm); void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +#define DEFINE_KVM_GHCB_ACCESSORS(field) \ + static __always_inline bool kvm_ghcb_##field##_is_valid(const struct vcpu_svm *svm) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&svm->sev_es.valid_bitmap); \ + } \ + \ + static __always_inline u64 kvm_ghcb_get_##field##_if_valid(struct vcpu_svm *svm, struct ghcb *ghcb) \ + { \ + return kvm_ghcb_##field##_is_valid(svm) ? ghcb->save.field : 0; \ + } \ + +DEFINE_KVM_GHCB_ACCESSORS(cpl) +DEFINE_KVM_GHCB_ACCESSORS(rax) +DEFINE_KVM_GHCB_ACCESSORS(rcx) +DEFINE_KVM_GHCB_ACCESSORS(rdx) +DEFINE_KVM_GHCB_ACCESSORS(rbx) +DEFINE_KVM_GHCB_ACCESSORS(rsi) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_code) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_KVM_GHCB_ACCESSORS(sw_scratch) +DEFINE_KVM_GHCB_ACCESSORS(xcr0) + #endif From 5bdf1c1f346c81996b6e36b5efd5c92aeda4fbe4 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 4 Aug 2023 12:56:36 -0400 Subject: [PATCH 0178/2093] KVM: SEV: only access GHCB fields once commit 7588dbcebcbf0193ab5b76987396d0254270b04a upstream. A KVM guest using SEV-ES or SEV-SNP with multiple vCPUs can trigger a double fetch race condition vulnerability and invoke the VMGEXIT handler recursively. sev_handle_vmgexit() maps the GHCB page using kvm_vcpu_map() and then fetches the exit code using ghcb_get_sw_exit_code(). Soon after, sev_es_validate_vmgexit() fetches the exit code again. Since the GHCB page is shared with the guest, the guest is able to quickly swap the values with another vCPU and hence bypass the validation. One vmexit code that can be rejected by sev_es_validate_vmgexit() is SVM_EXIT_VMGEXIT; if sev_handle_vmgexit() observes it in the second fetch, the call to svm_invoke_exit_handler() will invoke sev_handle_vmgexit() again recursively. To avoid the race, always fetch the GHCB data from the places where sev_es_sync_from_ghcb stores it. Exploiting recursions on linux kernel has been proven feasible in the past, but the impact is mitigated by stack guard pages (CONFIG_VMAP_STACK). Still, if an attacker manages to call the handler multiple times, they can theoretically trigger a stack overflow and cause a denial-of-service, or potentially guest-to-host escape in kernel configurations without stack guard pages. Note that winning the race reliably in every iteration is very tricky due to the very tight window of the fetches; depending on the compiler settings, they are often consecutive because of optimization and inlining. Tested by booting an SEV-ES RHEL9 guest. Fixes: CVE-2023-4155 Fixes: 291bd20d5d88 ("KVM: SVM: Add initial support for a VMGEXIT VMEXIT") Cc: stable@vger.kernel.org Reported-by: Andy Nguyen Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/sev.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 38fbe9dc199f..e0437acb5cf7 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2438,9 +2438,15 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { - struct kvm_vcpu *vcpu; + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; struct ghcb *ghcb; u64 exit_code; u64 reason; @@ -2451,7 +2457,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ - exit_code = ghcb_get_sw_exit_code(ghcb); + exit_code = kvm_ghcb_get_sw_exit_code(control); /* Only GHCB Usage code 0 is supported */ if (ghcb->ghcb_usage) { @@ -2466,7 +2472,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) !kvm_ghcb_sw_exit_info_2_is_valid(svm)) goto vmgexit_err; - switch (ghcb_get_sw_exit_code(ghcb)) { + switch (exit_code) { case SVM_EXIT_READ_DR7: break; case SVM_EXIT_WRITE_DR7: @@ -2483,18 +2489,18 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) if (!kvm_ghcb_rax_is_valid(svm) || !kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_rax(ghcb) == 0xd) + if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd) if (!kvm_ghcb_xcr0_is_valid(svm)) goto vmgexit_err; break; case SVM_EXIT_INVD: break; case SVM_EXIT_IOIO: - if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) { + if (control->exit_info_1 & SVM_IOIO_STR_MASK) { if (!kvm_ghcb_sw_scratch_is_valid(svm)) goto vmgexit_err; } else { - if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK)) + if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK)) if (!kvm_ghcb_rax_is_valid(svm)) goto vmgexit_err; } @@ -2502,7 +2508,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_EXIT_MSR: if (!kvm_ghcb_rcx_is_valid(svm)) goto vmgexit_err; - if (ghcb_get_sw_exit_info_1(ghcb)) { + if (control->exit_info_1) { if (!kvm_ghcb_rax_is_valid(svm) || !kvm_ghcb_rdx_is_valid(svm)) goto vmgexit_err; @@ -2546,8 +2552,6 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) return 0; vmgexit_err: - vcpu = &svm->vcpu; - if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); @@ -2845,8 +2849,6 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); - exit_code = ghcb_get_sw_exit_code(ghcb); - sev_es_sync_from_ghcb(svm); ret = sev_es_validate_vmgexit(svm); if (ret) @@ -2855,6 +2857,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); + exit_code = kvm_ghcb_get_sw_exit_code(control); switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); From e642eb67b8c10dcce758d549cc81564116e0fa49 Mon Sep 17 00:00:00 2001 From: Keith Yeo Date: Mon, 31 Jul 2023 11:47:20 +0800 Subject: [PATCH 0179/2093] wifi: nl80211: fix integer overflow in nl80211_parse_mbssid_elems() commit 6311071a056272e1e761de8d0305e87cc566f734 upstream. nl80211_parse_mbssid_elems() uses a u8 variable num_elems to count the number of MBSSID elements in the nested netlink attribute attrs, which can lead to an integer overflow if a user of the nl80211 interface specifies 256 or more elements in the corresponding attribute in userspace. The integer overflow can lead to a heap buffer overflow as num_elems determines the size of the trailing array in elems, and this array is thereafter written to for each element in attrs. Note that this vulnerability only affects devices with the wiphy->mbssid_max_interfaces member set for the wireless physical device struct in the device driver, and can only be triggered by a process with CAP_NET_ADMIN capabilities. Fix this by checking for a maximum of 255 elements in attrs. Cc: stable@vger.kernel.org Fixes: dc1e3cb8da8b ("nl80211: MBSSID and EMA support in AP mode") Signed-off-by: Keith Yeo Link: https://lore.kernel.org/r/20230731034719.77206-1-keithyjy@gmail.com Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/wireless/nl80211.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 087c0c442e23..c2363d44a1ff 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5378,8 +5378,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) if (!wiphy->mbssid_max_interfaces) return ERR_PTR(-EINVAL); - nla_for_each_nested(nl_elems, attrs, rem_elems) + nla_for_each_nested(nl_elems, attrs, rem_elems) { + if (num_elems >= 255) + return ERR_PTR(-EINVAL); num_elems++; + } elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) From aa4b5895a80fcbd1729b248870b80f9d89ce416e Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Tue, 8 Aug 2023 08:54:26 +0800 Subject: [PATCH 0180/2093] wifi: rtw89: fix 8852AE disconnection caused by RX full flags commit b74bb07cdab6859e1a3fc9fe7351052176322ddf upstream. RX full flags are raised if certain types of RX FIFO are full, and then drop all following MPDU of AMPDU. In order to resume to receive MPDU when RX FIFO becomes available, we clear the register bits by the commit a0d99ebb3ecd ("wifi: rtw89: initialize DMA of CMAC"). But, 8852AE needs more settings to support this. To quickly fix disconnection problem, revert the behavior as before. Fixes: a0d99ebb3ecd ("wifi: rtw89: initialize DMA of CMAC") Reported-by: Damian B Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217710 Cc: Signed-off-by: Ping-Ke Shih Tested-by: Damian B Link: https://lore.kernel.org/r/20230808005426.5327-1-pkshih@realtek.com Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtw89/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 077fddc5fa1e..4a1c9e18c530 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2209,7 +2209,7 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx) u32 reg; int ret; - if (chip_id != RTL8852A && chip_id != RTL8852B) + if (chip_id != RTL8852B) return 0; ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL); From 839aae189e1ff6791e4f5a9a47bcbe5e6543c804 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:51 +0300 Subject: [PATCH 0181/2093] selftests: forwarding: Set default IPv6 traceroute utility commit 38f7c44d6e760a8513557e27340d61b820c91b8f upstream. The test uses the 'TROUTE6' environment variable to encode the name of the IPv6 traceroute utility. By default (without a configuration file), this variable is not set, resulting in failures: # ./ip6_forward_instats_vrf.sh TEST: ping6 [ OK ] TEST: Ip6InTooBigErrors [ OK ] TEST: Ip6InHdrErrors [FAIL] TEST: Ip6InAddrErrors [ OK ] TEST: Ip6InDiscards [ OK ] Fix by setting a default utility name and skip the test if the utility is not present. Fixes: 0857d6f8c759 ("ipv6: When forwarding count rx stats on the orig netdev") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-6-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- .../testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh | 2 ++ tools/testing/selftests/net/forwarding/lib.sh | 1 + 2 files changed, 3 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 9f5b3e2e5e95..49fa94b53a1c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -14,6 +14,8 @@ ALL_TESTS=" NUM_NETIFS=4 source lib.sh +require_command $TROUTE6 + h1_create() { simple_if_init $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index f4721f1b2886..fbe4e37cf26e 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${REQUIRE_MZ:=yes} REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no} STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} +TROUTE6=${TROUTE6:=traceroute6} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then From 260ec73757c1361a61caa83545b0e2165cd64e34 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 7 Aug 2023 15:21:27 +0200 Subject: [PATCH 0182/2093] wireguard: allowedips: expand maximum node depth commit 46622219aae2b67813fe31a7b8cb7da5baff5c8a upstream. In the allowedips self-test, nodes are inserted into the tree, but it generated an even amount of nodes, but for checking maximum node depth, there is of course the root node, which makes the total number necessarily odd. With two few nodes added, it never triggered the maximum depth check like it should have. So, add 129 nodes instead of 128 nodes, and do so with a more straightforward scheme, starting with all the bits set, and shifting over one each time. Then increase the maximum depth to 129, and choose a better name for that variable to make it clear that it represents depth as opposed to bits. Cc: stable@vger.kernel.org Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Jason A. Donenfeld Link: https://lore.kernel.org/r/20230807132146.2191597-2-Jason@zx2c4.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireguard/allowedips.c | 8 ++++---- drivers/net/wireguard/selftest/allowedips.c | 16 ++++++++++------ 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 5bf7822c53f1..0ba714ca5185 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -6,7 +6,7 @@ #include "allowedips.h" #include "peer.h" -enum { MAX_ALLOWEDIPS_BITS = 128 }; +enum { MAX_ALLOWEDIPS_DEPTH = 129 }; static struct kmem_cache *node_cache; @@ -42,7 +42,7 @@ static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) { if (rcu_access_pointer(p)) { - if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS)) + if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_DEPTH)) return; stack[(*len)++] = rcu_dereference_raw(p); } @@ -55,7 +55,7 @@ static void node_free_rcu(struct rcu_head *rcu) static void root_free_rcu(struct rcu_head *rcu) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { container_of(rcu, struct allowedips_node, rcu) }; unsigned int len = 1; @@ -68,7 +68,7 @@ static void root_free_rcu(struct rcu_head *rcu) static void root_remove_peer_lists(struct allowedips_node *root) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root }; + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { root }; unsigned int len = 1; while (len > 0 && (node = stack[--len])) { diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 19eac00b2381..c51c794e70a0 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -593,16 +593,20 @@ bool __init wg_allowedips_selftest(void) wg_allowedips_remove_by_peer(&t, a, &mutex); test_negative(4, a, 192, 168, 0, 1); - /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node + /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_DEPTH) in free_node * if something goes wrong. */ - for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) { - part = cpu_to_be64(~(1LLU << (i % 64))); - memset(&ip, 0xff, 16); - memcpy((u8 *)&ip + (i < 64) * 8, &part, 8); + for (i = 0; i < 64; ++i) { + part = cpu_to_be64(~0LLU << i); + memset(&ip, 0xff, 8); + memcpy((u8 *)&ip + 8, &part, 8); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); + memcpy(&ip, &part, 8); + memset((u8 *)&ip + 8, 0, 8); wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); } - + memset(&ip, 0, 16); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); wg_allowedips_free(&t, &mutex); wg_allowedips_init(&t); From ecab78febff07e57b7546c7b58687596d8b08088 Mon Sep 17 00:00:00 2001 From: Sergei Antonov Date: Tue, 27 Jun 2023 15:05:49 +0300 Subject: [PATCH 0183/2093] mmc: moxart: read scr register without changing byte order commit d44263222134b5635932974c6177a5cba65a07e8 upstream. Conversion from big-endian to native is done in a common function mmc_app_send_scr(). Converting in moxart_transfer_pio() is extra. Double conversion on a LE system returns an incorrect SCR value, leads to errors: mmc0: unrecognised SCR structure version 8 Fixes: 1b66e94e6b99 ("mmc: moxart: Add MOXA ART SD/MMC driver") Signed-off-by: Sergei Antonov Cc: Jonas Jensen Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230627120549.2400325-1-saproj@gmail.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/moxart-mmc.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index 52ed30f2d9f4..94e9a08bc90e 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -338,13 +338,7 @@ static void moxart_transfer_pio(struct moxart_host *host) return; } for (len = 0; len < remain && len < host->fifo_width;) { - /* SCR data must be read in big endian. */ - if (data->mrq->cmd->opcode == SD_APP_SEND_SCR) - *sgp = ioread32be(host->base + - REG_DATA_WINDOW); - else - *sgp = ioread32(host->base + - REG_DATA_WINDOW); + *sgp = ioread32(host->base + REG_DATA_WINDOW); sgp++; len += 4; } From a537fd9096a1d50e5e7c6a3e6dff376049b497af Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Mon, 7 Aug 2023 03:25:32 -0700 Subject: [PATCH 0184/2093] ipv6: adjust ndisc_is_useropt() to also return true for PIO MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 048c796beb6eb4fa3a5a647ee1c81f5c6f0f6a2a upstream. The upcoming (and nearly finalized): https://datatracker.ietf.org/doc/draft-collink-6man-pio-pflag/ will update the IPv6 RA to include a new flag in the PIO field, which will serve as a hint to perform DHCPv6-PD. As we don't want DHCPv6 related logic inside the kernel, this piece of information needs to be exposed to userspace. The simplest option is to simply expose the entire PIO through the already existing mechanism. Even without this new flag, the already existing PIO R (router address) flag (from RFC6275) cannot AFAICT be handled entirely in kernel, and provides useful information that should be exposed to userspace (the router's global address, for use by Mobile IPv6). Also cc'ing stable@ for inclusion in LTS, as while technically this is not quite a bugfix, and instead more of a feature, it is absolutely trivial and the alternative is manually cherrypicking into all Android Common Kernel trees - and I know Greg will ask for it to be sent in via LTS instead... Cc: Jen Linkova Cc: Lorenzo Colitti Cc: David Ahern Cc: YOSHIFUJI Hideaki / 吉藤英明 Cc: stable@vger.kernel.org Signed-off-by: Maciej Żenczykowski Link: https://lore.kernel.org/r/20230807102533.1147559-1-maze@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ndisc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3a553494ff16..a4d43eb45a9d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || From aae988c0965061a9a4a2b1ee25529778c1a03fab Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Thu, 3 Aug 2023 18:27:27 +0200 Subject: [PATCH 0185/2093] selftests: mptcp: join: fix 'delete and re-add' test commit aaf2123a5cf46dbd97f84b6eee80269758064d93 upstream. mptcp_join 'delete and re-add' test fails when using ip mptcp: $ ./mptcp_join.sh -iI 002 delete and re-add before delete[ ok ] mptcp_info subflows=1 [ ok ] Error: argument "ADDRESS" is wrong: invalid for non-zero id address after delete[fail] got 2:2 subflows expected 1 This happens because endpoint delete includes an ip address while id is not 0, contrary to what is indicated in the ip mptcp man page: "When used with the delete id operation, an IFADDR is only included when the ID is 0." This fixes the issue using the $addr variable in pm_nl_del_endpoint() only when id is 0. Fixes: 34aa6e3bccd8 ("selftests: mptcp: add ip mptcp wrappers") Cc: stable@vger.kernel.org Signed-off-by: Andrea Claudi Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-1-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index a3108c3cff47..bd214c47a2c0 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -650,6 +650,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr From d143c736020f8e0c06c1bda91da3ded50b0964ae Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Thu, 3 Aug 2023 18:27:28 +0200 Subject: [PATCH 0186/2093] selftests: mptcp: join: fix 'implicit EP' test commit c8c101ae390a3e817369e94a6f12a1ddea420702 upstream. mptcp_join 'implicit EP' test currently fails when using ip mptcp: $ ./mptcp_join.sh -iI 001 implicit EP creation[fail] expected '10.0.2.2 10.0.2.2 id 1 implicit' found '10.0.2.2 id 1 rawflags 10 ' Error: too many addresses or duplicate one: -22. ID change is prevented[fail] expected '10.0.2.2 10.0.2.2 id 1 implicit' found '10.0.2.2 id 1 rawflags 10 ' modif is allowed[fail] expected '10.0.2.2 10.0.2.2 id 1 signal' found '10.0.2.2 id 1 signal ' This happens because of two reasons: - iproute v6.3.0 does not support the implicit flag, fixed with iproute2-next commit 3a2535a41854 ("mptcp: add support for implicit flag") - pm_nl_check_endpoint wrongly expects the ip address to be repeated two times in iproute output, and does not account for a final whitespace in it. This fixes the issue trimming the whitespace in the output string and removing the double address in the expected string. Fixes: 69c6ce7b6eca ("selftests: mptcp: add implicit endpoint test case") Cc: stable@vger.kernel.org Signed-off-by: Andrea Claudi Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-2-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index bd214c47a2c0..7b20878a1af5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -741,10 +741,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" From 84aa65a5256154591a84f294e60c4622354ca905 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 3 Aug 2023 18:27:29 +0200 Subject: [PATCH 0187/2093] mptcp: avoid bogus reset on fallback close commit ff18f9ef30ee87740f741b964375d0cfb84e1ec2 upstream. Since the blamed commit, the MPTCP protocol unconditionally sends TCP resets on all the subflows on disconnect(). That fits full-blown MPTCP sockets - to implement the fastclose mechanism - but causes unexpected corruption of the data stream, caught as sporadic self-tests failures. Fixes: d21f83485518 ("mptcp: use fastclose on more edge scenarios") Cc: stable@vger.kernel.org Tested-by: Matthieu Baerts Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/419 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-3-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f6f2e6417dcb..6034ea9ad115 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2367,7 +2367,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ From ded9f5551ce5cafa3c41c794428c27a0d0a00542 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 3 Aug 2023 18:27:30 +0200 Subject: [PATCH 0188/2093] mptcp: fix disconnect vs accept race commit 511b90e39250135a7f900f1c3afbce25543018a2 upstream. Despite commit 0ad529d9fd2b ("mptcp: fix possible divide by zero in recvmsg()"), the mptcp protocol is still prone to a race between disconnect() (or shutdown) and accept. The root cause is that the mentioned commit checks the msk-level flag, but mptcp_stream_accept() does acquire the msk-level lock, as it can rely directly on the first subflow lock. As reported by Christoph than can lead to a race where an msk socket is accepted after that mptcp_subflow_queue_clean() releases the listener socket lock and just before it takes destructive actions leading to the following splat: BUG: kernel NULL pointer dereference, address: 0000000000000012 PGD 5a4ca067 P4D 5a4ca067 PUD 37d4c067 PMD 0 Oops: 0000 [#1] PREEMPT SMP CPU: 2 PID: 10955 Comm: syz-executor.5 Not tainted 6.5.0-rc1-gdc7b257ee5dd #37 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 RIP: 0010:mptcp_stream_accept+0x1ee/0x2f0 include/net/inet_sock.h:330 Code: 0a 09 00 48 8b 1b 4c 39 e3 74 07 e8 bc 7c 7f fe eb a1 e8 b5 7c 7f fe 4c 8b 6c 24 08 eb 05 e8 a9 7c 7f fe 49 8b 85 d8 09 00 00 <0f> b6 40 12 88 44 24 07 0f b6 6c 24 07 bf 07 00 00 00 89 ee e8 89 RSP: 0018:ffffc90000d07dc0 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff888037e8d020 RCX: ffff88803b093300 RDX: 0000000000000000 RSI: ffffffff833822c5 RDI: ffffffff8333896a RBP: 0000607f82031520 R08: ffff88803b093300 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000003e83 R12: ffff888037e8d020 R13: ffff888037e8c680 R14: ffff888009af7900 R15: ffff888009af6880 FS: 00007fc26d708640(0000) GS:ffff88807dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000012 CR3: 0000000066bc5001 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: do_accept+0x1ae/0x260 net/socket.c:1872 __sys_accept4+0x9b/0x110 net/socket.c:1913 __do_sys_accept4 net/socket.c:1954 [inline] __se_sys_accept4 net/socket.c:1951 [inline] __x64_sys_accept4+0x20/0x30 net/socket.c:1951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x47/0xa0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Address the issue by temporary removing the pending request socket from the accept queue, so that racing accept() can't touch them. After depleting the msk - the ssk still exists, as plain TCP sockets, re-insert them into the accept queue, so that later inet_csk_listen_stop() will complete the tcp socket disposal. Fixes: 2a6a870e44dd ("mptcp: stops worker on unaccepted sockets at listener close") Cc: stable@vger.kernel.org Reported-by: Christoph Paasch Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/423 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803-upstream-net-20230803-misc-fixes-6-5-v1-4-6671b1ab11cc@tessares.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/protocol.h | 1 - net/mptcp/subflow.c | 60 ++++++++++++++++++++++---------------------- 2 files changed, 30 insertions(+), 31 deletions(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index fc00dd587a29..d77b25636125 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -312,7 +312,6 @@ struct mptcp_sock { u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 047e46dd028d..52a747a80e88 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1724,34 +1724,21 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; - - if (!sk_is_mptcp(ssk)) - continue; - - subflow = mptcp_subflow_ctx(ssk); - if (!subflow || !subflow->conn) - continue; - - /* skip if already in list */ - sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - - sock_hold(sk); - msk->dl_next = head; - head = msk; - } + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; spin_unlock_bh(&queue->rskq_lock); + if (!head) return; @@ -1760,13 +1747,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s */ release_sock(listener_ssk); - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; + for (req = head; req; req = req->dl_next) { + ssk = req->sk; + if (!sk_is_mptcp(ssk)) + continue; + + subflow = mptcp_subflow_ctx(ssk); + if (!subflow || !subflow->conn) + continue; + + sk = subflow->conn; + sock_hold(sk); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1790,6 +1783,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) From aec1ce9a30d454b634a13cabd6a28a49cb5e3927 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 26 May 2023 13:54:34 +0300 Subject: [PATCH 0189/2093] dmaengine: pl330: Return DMA_PAUSED when transaction is paused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8cda3ececf07d374774f6a13e5a94bc2dc04c26c upstream. pl330_pause() does not set anything to indicate paused condition which causes pl330_tx_status() to return DMA_IN_PROGRESS. This breaks 8250 DMA flush after the fix in commit 57e9af7831dc ("serial: 8250_dma: Fix DMA Rx rearm race"). The function comment for pl330_pause() claims pause is supported but resume is not which is enough for 8250 DMA flush to work as long as DMA status reports DMA_PAUSED when appropriate. Add PAUSED state for descriptor and mark BUSY descriptors with PAUSED in pl330_pause(). Return DMA_PAUSED from pl330_tx_status() when the descriptor is PAUSED. Reported-by: Richard Tresidder Tested-by: Richard Tresidder Fixes: 88987d2c7534 ("dmaengine: pl330: add DMA_PAUSE feature") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-serial/f8a86ecd-64b1-573f-c2fa-59f541083f1a@electromag.com.au/ Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230526105434.14959-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/dma/pl330.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index b4731fe6bbc1..3cf0b38387ae 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -403,6 +403,12 @@ enum desc_status { * of a channel can be BUSY at any time. */ BUSY, + /* + * Pause was called while descriptor was BUSY. Due to hardware + * limitations, only termination is possible for descriptors + * that have been paused. + */ + PAUSED, /* * Sitting on the channel work_list but xfer done * by PL330 core @@ -2041,7 +2047,7 @@ static inline void fill_queue(struct dma_pl330_chan *pch) list_for_each_entry(desc, &pch->work_list, node) { /* If already submitted */ - if (desc->status == BUSY) + if (desc->status == BUSY || desc->status == PAUSED) continue; ret = pl330_submit_req(pch->thread, desc); @@ -2326,6 +2332,7 @@ static int pl330_pause(struct dma_chan *chan) { struct dma_pl330_chan *pch = to_pchan(chan); struct pl330_dmac *pl330 = pch->dmac; + struct dma_pl330_desc *desc; unsigned long flags; pm_runtime_get_sync(pl330->ddma.dev); @@ -2335,6 +2342,10 @@ static int pl330_pause(struct dma_chan *chan) _stop(pch->thread); spin_unlock(&pl330->lock); + list_for_each_entry(desc, &pch->work_list, node) { + if (desc->status == BUSY) + desc->status = PAUSED; + } spin_unlock_irqrestore(&pch->lock, flags); pm_runtime_mark_last_busy(pl330->ddma.dev); pm_runtime_put_autosuspend(pl330->ddma.dev); @@ -2425,7 +2436,7 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, else if (running && desc == running) transferred = pl330_get_current_xferred_count(pch, desc); - else if (desc->status == BUSY) + else if (desc->status == BUSY || desc->status == PAUSED) /* * Busy but not running means either just enqueued, * or finished and not yet marked done @@ -2442,6 +2453,9 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, case DONE: ret = DMA_COMPLETE; break; + case PAUSED: + ret = DMA_PAUSED; + break; case PREP: case BUSY: ret = DMA_IN_PROGRESS; From 593615bf14c9122fab73d5773c4179a65cbbcbd4 Mon Sep 17 00:00:00 2001 From: Souradeep Chakrabarti Date: Wed, 9 Aug 2023 03:22:05 -0700 Subject: [PATCH 0190/2093] net: mana: Fix MANA VF unload when hardware is unresponsive commit a7dfeda6fdeccab4c7c3dce9a72c4262b9530c80 upstream. When unloading the MANA driver, mana_dealloc_queues() waits for the MANA hardware to complete any inflight packets and set the pending send count to zero. But if the hardware has failed, mana_dealloc_queues() could wait forever. Fix this by adding a timeout to the wait. Set the timeout to 120 seconds, which is a somewhat arbitrary value that is more than long enough for functional hardware to complete any sends. Cc: stable@vger.kernel.org Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)") Signed-off-by: Souradeep Chakrabarti Link: https://lore.kernel.org/r/1691576525-24271-1-git-send-email-schakrabarti@linux.microsoft.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/microsoft/mana/mana_en.c | 37 +++++++++++++++++-- 1 file changed, 33 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 27a0f3af8aab..4f4204432aaa 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -1972,9 +1973,12 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + unsigned long timeout = jiffies + 120 * HZ; struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; + struct sk_buff *skb; int i, err; + u32 tsleep; if (apc->port_is_up) return -EINVAL; @@ -1990,15 +1994,40 @@ static int mana_dealloc_queues(struct net_device *ndev) * to false, but it doesn't matter since mana_start_xmit() drops any * new packets due to apc->port_is_up being false. * - * Drain all the in-flight TX packets + * Drain all the in-flight TX packets. + * A timeout of 120 seconds for all the queues is used. + * This will break the while loop when h/w is not responding. + * This value of 120 has been decided here considering max + * number of queues. */ + for (i = 0; i < apc->num_queues; i++) { txq = &apc->tx_qp[i].txq; - - while (atomic_read(&txq->pending_sends) > 0) - usleep_range(1000, 2000); + tsleep = 1000; + while (atomic_read(&txq->pending_sends) > 0 && + time_before(jiffies, timeout)) { + usleep_range(tsleep, tsleep + 1000); + tsleep <<= 1; + } + if (atomic_read(&txq->pending_sends)) { + err = pcie_flr(to_pci_dev(gd->gdma_context->dev)); + if (err) { + netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", + err, atomic_read(&txq->pending_sends), + txq->gdma_txq_id); + } + break; + } } + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + while ((skb = skb_dequeue(&txq->pending_skbs))) { + mana_unmap_skb(skb, apc); + dev_kfree_skb_any(skb); + } + atomic_set(&txq->pending_sends, 0); + } /* We're 100% sure the queues can no longer be woken up, because * we're sure now mana_poll_tx_cq() can't be running. */ From 98a34f50c15fa95c1a2264110518dec387c15889 Mon Sep 17 00:00:00 2001 From: Torsten Duwe Date: Wed, 26 Jul 2023 11:54:01 +0200 Subject: [PATCH 0191/2093] riscv/kexec: load initrd high in available memory commit 49af7a2cd5f678217b8b4f86a29411aebebf3e78 upstream. When initrd is loaded low, the secondary kernel fails like this: INITRD: 0xdc581000+0x00eef000 overlaps in-use memory region This initrd load address corresponds to the _end symbol, but the reservation is aligned on PMD_SIZE, as explained by a comment in setup_bootmem(). It is technically possible to align the initrd load address accordingly, leaving a hole between the end of kernel and the initrd, but it is much simpler to allocate the initrd top-down. Fixes: 838b3e28488f ("RISC-V: Load purgatory in kexec_file") Signed-off-by: Torsten Duwe Signed-off-by: Petr Tesarik Cc: stable@vger.kernel.org Reviewed-by: Conor Dooley Link: https://lore.kernel.org/all/67c8eb9eea25717c2c8208d9bfbfaa39e6e2a1c6.1690365011.git.petr.tesarik.ext@huawei.com/ Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/kernel/elf_kexec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..26e19cd17bf1 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) From b374684018e4136c16d98dcaa46f65574d24af99 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Thu, 3 Aug 2023 06:27:38 +0200 Subject: [PATCH 0192/2093] riscv,mmio: Fix readX()-to-delay() ordering commit 4eb2eb1b4c0eb07793c240744843498564a67b83 upstream. Section 2.1 of the Platform Specification [1] states: Unless otherwise specified by a given I/O device, I/O devices are on ordering channel 0 (i.e., they are point-to-point strongly ordered). which is not sufficient to guarantee that a readX() by a hart completes before a subsequent delay() on the same hart (cf. memory-barriers.txt, "Kernel I/O barrier effects"). Set the I(nput) bit in __io_ar() to restore the ordering, align inline comments. [1] https://github.com/riscv/riscv-platform-specs Signed-off-by: Andrea Parri Link: https://lore.kernel.org/r/20230803042738.5937-1-parri.andrea@gmail.com Fixes: fab957c11efe ("RISC-V: Atomic and Locking Code") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/include/asm/mmio.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) From 3fdaa7fbc81b3822a35c65996e3bb3d44a4768d3 Mon Sep 17 00:00:00 2001 From: Torsten Duwe Date: Wed, 26 Jul 2023 11:53:59 +0200 Subject: [PATCH 0193/2093] riscv/kexec: handle R_RISCV_CALL_PLT relocation type commit d0b4f95a51038becce4bdab4789aa7ce59d4ea6e upstream. R_RISCV_CALL has been deprecated and replaced by R_RISCV_CALL_PLT. See Enum 18-19 in Table 3. Relocation types here: https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-elf.adoc It was deprecated in ("Deprecated R_RISCV_CALL, prefer R_RISCV_CALL_PLT"): https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a0dced85018d7a0ec17023c9389cbd70b1dbc1b0 Recent tools (at least GNU binutils-2.40) already use R_RISCV_CALL_PLT. Kernels built with such binutils fail kexec_load_file(2) with: kexec_image: Unknown rela relocation: 19 kexec_image: Error loading purgatory ret=-8 The binary code at the call site remains the same, so tell arch_kexec_apply_relocations_add() to handle _PLT alike. Fixes: 838b3e28488f ("RISC-V: Load purgatory in kexec_file") Signed-off-by: Torsten Duwe Signed-off-by: Petr Tesarik Cc: Li Zhengyu Cc: stable@vger.kernel.org Reviewed-by: Conor Dooley Link: https://lore.kernel.org/all/b046b164af8efd33bbdb7d4003273bdf9196a5b0.1690365011.git.petr.tesarik.ext@huawei.com/ Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/kernel/elf_kexec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 26e19cd17bf1..c08bb5c3b385 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * sym, instead of searching the whole relsec. */ case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: case R_RISCV_CALL: *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | ENCODE_UJTYPE_IMM(val - addr); From 56c79fcae6f344dccc2819384e451d76def35e7f Mon Sep 17 00:00:00 2001 From: August Wikerfors Date: Wed, 16 Nov 2022 18:17:27 +0100 Subject: [PATCH 0194/2093] nvme-pci: add NVME_QUIRK_BOGUS_NID for Samsung PM9B1 256G and 512G commit 688b419c57c13637d95d7879e165fff3dec581eb upstream. The Samsung PM9B1 512G SSD found in some Lenovo Yoga 7 14ARB7 laptop units reports eui as 0001000200030004 when resuming from s2idle, causing the device to be removed with this error in dmesg: nvme nvme0: identifiers changed for nsid 1 To fix this, add a quirk to ignore namespace identifiers for this device. Signed-off-by: August Wikerfors Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/nvme/host/pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ce2e628f94a0..b30269f5e68f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3504,7 +3504,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1d97, 0x2263), /* SPCC */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x144d, 0xa80b), /* Samsung PM9B1 256G and 512G */ - .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x144d, 0xa809), /* Samsung MZALQ256HBJD 256G */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1cc4, 0x6303), /* UMIS RPJTJ512MGE1QDY 512G */ From e179b058d720dfb76f8e35790fed2f0528f8a31e Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Thu, 22 Jun 2023 17:20:17 +0200 Subject: [PATCH 0195/2093] drm/nouveau/gr: enable memory loads on helper invocation on all channels commit 1cb9e2ef66d53b020842b18762e30d0eb4384de8 upstream. We have a lurking bug where Fragment Shader Helper Invocations can't load from memory. But this is actually required in OpenGL and is causing random hangs or failures in random shaders. It is unknown how widespread this issue is, but shaders hitting this can end up with infinite loops. We enable those only on all Kepler and newer GPUs where we use our own Firmware. Nvidia's firmware provides a way to set a kernelspace controlled list of mmio registers in the gr space from push buffers via MME macros. v2: drop code for gm200 and newer. Cc: Ben Skeggs Cc: David Airlie Cc: nouveau@lists.freedesktop.org Cc: stable@vger.kernel.org # 4.19+ Signed-off-by: Karol Herbst Reviewed-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20230622152017.2512101-1-kherbst@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h | 1 + drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c | 4 +++- drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c | 10 ++++++++++ drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c | 1 + drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c | 1 + drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c | 1 + 6 files changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h index 32bbddc0993e..679aff79f4d6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h @@ -123,6 +123,7 @@ void gk104_grctx_generate_r418800(struct gf100_gr *); extern const struct gf100_grctx_func gk110_grctx; void gk110_grctx_generate_r419eb0(struct gf100_gr *); +void gk110_grctx_generate_r419f78(struct gf100_gr *); extern const struct gf100_grctx_func gk110b_grctx; extern const struct gf100_grctx_func gk208_grctx; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c index 304e9d268bad..f894f8254824 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c @@ -916,7 +916,9 @@ static void gk104_grctx_generate_r419f78(struct gf100_gr *gr) { struct nvkm_device *device = gr->base.engine.subdev.device; - nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000); + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c index 86547cfc38dc..e88740d4e54d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c @@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf100_gr *gr) nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000); } +void +gk110_grctx_generate_r419f78(struct gf100_gr *gr) +{ + struct nvkm_device *device = gr->base.engine.subdev.device; + + /* bit 3 set disables loads in fp helper invocations, we need it enabled */ + nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000); +} + const struct gf100_grctx_func gk110_grctx = { .main = gf100_grctx_generate_main, @@ -852,4 +861,5 @@ gk110_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c index ebb947bd1446..086e4d49e112 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c @@ -101,4 +101,5 @@ gk110b_grctx = { .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, .r419eb0 = gk110_grctx_generate_r419eb0, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c index 4d40512b5c99..0bf438c3f7cb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c @@ -566,4 +566,5 @@ gk208_grctx = { .dist_skip_table = gf117_grctx_generate_dist_skip_table, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r418800 = gk104_grctx_generate_r418800, + .r419f78 = gk110_grctx_generate_r419f78, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c index 0b3964e6b36e..acdf0932a99e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c @@ -991,4 +991,5 @@ gm107_grctx = { .r406500 = gm107_grctx_generate_r406500, .gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr, .r419e00 = gm107_grctx_generate_r419e00, + .r419f78 = gk110_grctx_generate_r419f78, }; From a372c3f0db810f76fd65c237147827c7a80020ee Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Fri, 28 Jul 2023 18:58:57 -0400 Subject: [PATCH 0196/2093] drm/nouveau/nvkm/dp: Add workaround to fix DP 1.3+ DPCD issues commit e4060dad253352382b20420d8ef98daab24dbc17 upstream. Currently we use the drm_dp_dpcd_read_caps() helper in the DRM side of nouveau in order to read the DPCD of a DP connector, which makes sure we do the right thing and also check for extended DPCD caps. However, it turns out we're not currently doing this on the nvkm side since we don't have access to the drm_dp_aux structure there - which means that the DRM side of the driver and the NVKM side can end up with different DPCD capabilities for the same connector. Ideally in order to fix this, we just want to use the drm_dp_read_dpcd_caps() helper in nouveau. That's not currently possible though, and is going to depend on having a bunch of the DP code moved out of nvkm and into the DRM side of things as part of the GSP enablement work. Until then however, let's workaround this problem by porting a copy of drm_dp_read_dpcd_caps() into NVKM - which should fix this issue. Signed-off-by: Lyude Paul Reviewed-by: Karol Herbst Link: https://gitlab.freedesktop.org/drm/nouveau/-/issues/211 Link: https://patchwork.freedesktop.org/patch/msgid/20230728225858.350581-1-lyude@redhat.com (cherry picked from commit cc4adf3a7323212f303bc9ff0f96346c44fcba06 in drm-misc-next) Cc: # 6.3+ Signed-off-by: Karol Herbst Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c | 48 ++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index c1b3206f27e6..458f8efb19c6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -26,6 +26,8 @@ #include "head.h" #include "ior.h" +#include + #include #include #include @@ -474,6 +476,50 @@ nvkm_dp_train(struct nvkm_outp *outp, u32 dataKBps) return ret; } +/* XXX: This is a big fat hack, and this is just drm_dp_read_dpcd_caps() + * converted to work inside nvkm. This is a temporary holdover until we start + * passing the drm_dp_aux device through NVKM + */ +static int +nvkm_dp_read_dpcd_caps(struct nvkm_outp *outp) +{ + struct nvkm_i2c_aux *aux = outp->dp.aux; + u8 dpcd_ext[DP_RECEIVER_CAP_SIZE]; + int ret; + + ret = nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, DP_RECEIVER_CAP_SIZE); + if (ret < 0) + return ret; + + /* + * Prior to DP1.3 the bit represented by + * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved. + * If it is set DP_DPCD_REV at 0000h could be at a value less than + * the true capability of the panel. The only way to check is to + * then compare 0000h and 2200h. + */ + if (!(outp->dp.dpcd[DP_TRAINING_AUX_RD_INTERVAL] & + DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT)) + return 0; + + ret = nvkm_rdaux(aux, DP_DP13_DPCD_REV, dpcd_ext, sizeof(dpcd_ext)); + if (ret < 0) + return ret; + + if (outp->dp.dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) { + OUTP_DBG(outp, "Extended DPCD rev less than base DPCD rev (%d > %d)\n", + outp->dp.dpcd[DP_DPCD_REV], dpcd_ext[DP_DPCD_REV]); + return 0; + } + + if (!memcmp(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext))) + return 0; + + memcpy(outp->dp.dpcd, dpcd_ext, sizeof(dpcd_ext)); + + return 0; +} + void nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior) { @@ -630,7 +676,7 @@ nvkm_dp_enable(struct nvkm_outp *outp, bool enable) memset(outp->dp.lttpr, 0x00, sizeof(outp->dp.lttpr)); } - if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, outp->dp.dpcd, sizeof(outp->dp.dpcd))) { + if (!nvkm_dp_read_dpcd_caps(outp)) { const u8 rates[] = { 0x1e, 0x14, 0x0a, 0x06, 0 }; const u8 *rate; int rate_max; From 2322dd8c9d3d89319f222d90f0438a392dfcab9d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 24 Jul 2023 13:26:10 +0200 Subject: [PATCH 0197/2093] drm/shmem-helper: Reset vma->vm_ops before calling dma_buf_mmap() commit 07dd476f6116966cb2006e25fdcf48f0715115ff upstream. The dma-buf backend is supposed to provide its own vm_ops, but some implementation just have nothing special to do and leave vm_ops untouched, probably expecting this field to be zero initialized (this is the case with the system_heap implementation for instance). Let's reset vma->vm_ops to NULL to keep things working with these implementations. Fixes: 26d3ac3cb04d ("drm/shmem-helpers: Redirect mmap for imported dma-buf") Cc: Cc: Daniel Vetter Reported-by: Roman Stratiienko Signed-off-by: Boris Brezillon Tested-by: Roman Stratiienko Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230724112610.60974-1-boris.brezillon@collabora.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gem_shmem_helper.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 5fdc608043e7..e33f06bb66eb 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -622,7 +622,13 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct int ret; if (obj->import_attach) { + /* Reset both vm_ops and vm_private_data, so we don't end up with + * vm_ops pointing to our implementation if the dma-buf backend + * doesn't set those fields. + */ vma->vm_private_data = NULL; + vma->vm_ops = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); /* Drop the reference drm_gem_mmap_obj() acquired.*/ From 9a2393af1f35d1975204fc00035c64a1c792b278 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 28 Jul 2023 11:14:05 -0400 Subject: [PATCH 0198/2093] drm/amdgpu: fix possible UAF in amdgpu_cs_pass1() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 90e065677e0362a777b9db97ea21d43a39211399 upstream. Since the gang_size check is outside of chunk parsing loop, we need to reset i before we free the chunk data. Suggested by Ye Zhang (@VAR10CK) of Baidu Security. Reviewed-by: Guchun Chen Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b60b6e6149bf..fdb53d4394f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -287,7 +287,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, if (!p->gang_size) { ret = -EINVAL; - goto free_partial_kdata; + goto free_all_kdata; } for (i = 0; i < p->gang_size; ++i) { From c3d2d4b02e5e91b465ae85a19c05b00912f79620 Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Mon, 31 Jul 2023 07:35:05 -0100 Subject: [PATCH 0199/2093] drm/amd/display: check attr flag before set cursor degamma on DCN3+ commit 96b020e2163fb2197266b2f71b1007495206e6bb upstream. Don't set predefined degamma curve to cursor plane if the cursor attribute flag is not set. Applying a degamma curve to the cursor by default breaks userspace expectation. Checking the flag before performing any color transformation prevents too dark cursor gamma in DCN3+ on many Linux desktop environment (KDE Plasma, GNOME, wlroots-based, etc.) as reported at: - https://gitlab.freedesktop.org/drm/amd/-/issues/1513 This is the same approach followed by DCN2 drivers where the issue is not present. Fixes: 03f54d7d3448 ("drm/amd/display: Add DCN3 DPP") Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1513 Signed-off-by: Melissa Wen Reviewed-by: Harry Wentland Tested-by: Alex Hung Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index e5b7ef7422b8..50dc83404644 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -357,8 +357,11 @@ void dpp3_set_cursor_attributes( int cur_rom_en = 0; if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA || - color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) - cur_rom_en = 1; + color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) { + if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) { + cur_rom_en = 1; + } + } REG_UPDATE_3(CURSOR0_CONTROL, CUR0_MODE, color_format, From f6166ca452b8687322e6c1f8bac2395abc456aa4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 9 Feb 2023 09:00:02 -0500 Subject: [PATCH 0200/2093] drm/amdgpu: add S/G display parameter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit bf0207e1727031798f300afa17f9bbeceac6da87 upstream. Some users have reported flickerng with S/G display. We've tried extensively to reproduce and debug the issue on a wide variety of platform configurations (DRAM bandwidth, etc.) and a variety of monitors, but so far have not been able to. We disabled S/G display on a number of platforms to address this but that leads to failure to pin framebuffers errors and blank displays when there is memory pressure or no displays at all on systems with limited carveout (e.g., Chromebooks). Add a option to disable this as a debugging option as a way for users to disable this, depending on their use case, and for us to help debug this further. v2: fix typo Reviewed-by: Harry Wentland Acked-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 11 +++++++++++ drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +++ 3 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index c0e782a95e72..e0f146ddc556 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -242,6 +242,7 @@ extern int amdgpu_num_kcq; #define AMDGPU_VCNFW_LOG_SIZE (32 * 1024) extern int amdgpu_vcnfw_log; +extern int amdgpu_sg_display; #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 49a023f59b2f..6e5bc7484695 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -185,6 +185,7 @@ int amdgpu_num_kcq = -1; int amdgpu_smartshift_bias; int amdgpu_use_xgmi_p2p = 1; int amdgpu_vcnfw_log; +int amdgpu_sg_display = -1; /* auto */ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -929,6 +930,16 @@ module_param_named(num_kcq, amdgpu_num_kcq, int, 0444); MODULE_PARM_DESC(vcnfw_log, "Enable vcnfw log(0 = disable (default value), 1 = enable)"); module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444); +/** + * DOC: sg_display (int) + * Disable S/G (scatter/gather) display (i.e., display from system memory). + * This option is only relevant on APUs. Set this option to 0 to disable + * S/G display if you experience flickering or other issues under memory + * pressure and report the issue. + */ +MODULE_PARM_DESC(sg_display, "S/G Display (-1 = auto (default), 0 = disable)"); +module_param_named(sg_display, amdgpu_sg_display, int, 0444); + /** * DOC: smu_pptable_id (int) * Used to override pptable id. id = 0 use VBIOS pptable. diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 86e07cc1d3dc..41dec9eb08f0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1634,6 +1634,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } break; } + if (init_data.flags.gpu_vm_support && + (amdgpu_sg_display == 0)) + init_data.flags.gpu_vm_support = false; if (init_data.flags.gpu_vm_support) adev->mode_info.gpu_vm_support = true; From 10347b115da1029f4a25b69129294b3854144d6a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 27 Jul 2023 10:22:20 -0500 Subject: [PATCH 0201/2093] drm/amd: Disable S/G for APUs when 64GB or more host memory commit 08fffa74d9772d9538338be3f304006c94dde6f0 upstream. Users report a white flickering screen on multiple systems that is tied to having 64GB or more memory. When S/G is enabled pages will get pinned to both VRAM carve out and system RAM leading to this. Until it can be fixed properly, disable S/G when 64GB of memory or more is detected. This will force pages to be pinned into VRAM. This should fix white screen flickers but if VRAM pressure is encountered may lead to black screens. It's a trade-off for now. Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Cc: Hamza Mahfooz Cc: Roman Li Cc: # 6.1.y: bf0207e172703 ("drm/amdgpu: add S/G display parameter") Cc: # 6.4.y Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2735 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354 Signed-off-by: Mario Limonciello Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 +++++++++++++++++++ .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++-- 3 files changed, 29 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index e0f146ddc556..9ecf20169912 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1263,6 +1263,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); +bool amdgpu_sg_display_supported(struct amdgpu_device *adev); bool amdgpu_device_pcie_dynamic_switching_supported(void); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); bool amdgpu_device_aspm_support_quirk(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 30c97ee37563..773383e660e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1333,6 +1333,32 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; } +/* + * On APUs with >= 64GB white flickering has been observed w/ SG enabled. + * Disable S/G on such systems until we have a proper fix. + * https://gitlab.freedesktop.org/drm/amd/-/issues/2354 + * https://gitlab.freedesktop.org/drm/amd/-/issues/2735 + */ +bool amdgpu_sg_display_supported(struct amdgpu_device *adev) +{ + switch (amdgpu_sg_display) { + case -1: + break; + case 0: + return false; + case 1: + return true; + default: + return false; + } + if ((totalram_pages() << (PAGE_SHIFT - 10)) + + (adev->gmc.real_vram_size / 1024) >= 64000000) { + DRM_WARN("Disabling S/G due to >=64GB RAM\n"); + return false; + } + return true; +} + /* * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic * speed switching. Until we have confirmation from Intel that a specific host diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 41dec9eb08f0..9f718b98da1f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1634,9 +1634,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } break; } - if (init_data.flags.gpu_vm_support && - (amdgpu_sg_display == 0)) - init_data.flags.gpu_vm_support = false; + if (init_data.flags.gpu_vm_support) + init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev); if (init_data.flags.gpu_vm_support) adev->mode_info.gpu_vm_support = true; From 3d3fd58bfca151028859cc23757191fa2f65f679 Mon Sep 17 00:00:00 2001 From: Peichen Huang Date: Wed, 31 May 2023 13:36:14 +0800 Subject: [PATCH 0202/2093] drm/amd/display: limit DPIA link rate to HBR3 commit 0e69ef6ea82e8eece7d2b2b45a0da9670eaaefff upstream. [Why] DPIA doesn't support UHBR, driver should not enable UHBR for dp tunneling [How] limit DPIA link rate to HBR3 Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Acked-by: Stylon Wang Signed-off-by: Peichen Huang Reviewed-by: Mustapha Ghaddar Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index c2c6c4587a5c..bbaeb6c567d0 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1141,6 +1141,11 @@ static bool detect_link_and_local_sink(struct dc_link *link, (link->dpcd_caps.dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER)) converter_disable_audio = true; + + /* limited link rate to HBR3 for DPIA until we implement USB4 V2 */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + link->reported_link_cap.link_rate > LINK_RATE_HIGH3) + link->reported_link_cap.link_rate = LINK_RATE_HIGH3; break; } From 088773aaafef55c21c855277bed84d8cef71abeb Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Mon, 3 Jul 2023 14:25:53 +0530 Subject: [PATCH 0203/2093] cpuidle: dt_idle_genpd: Add helper function to remove genpd topology commit 9a8fa00dad3c7b260071f2f220cfb00505372c40 upstream. Genpd parent and child domain topology created using dt_idle_pd_init_topology() needs to be removed during error cases. Add new helper function dt_idle_pd_remove_topology() for same. Cc: stable@vger.kernel.org Reviewed-by: Ulf Hanssson Signed-off-by: Maulik Shah Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/cpuidle/dt_idle_genpd.c | 24 ++++++++++++++++++++++++ drivers/cpuidle/dt_idle_genpd.h | 7 +++++++ 2 files changed, 31 insertions(+) diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c index b37165514d4e..1af63c189039 100644 --- a/drivers/cpuidle/dt_idle_genpd.c +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -152,6 +152,30 @@ int dt_idle_pd_init_topology(struct device_node *np) return 0; } +int dt_idle_pd_remove_topology(struct device_node *np) +{ + struct device_node *node; + struct of_phandle_args child, parent; + int ret; + + for_each_child_of_node(np, node) { + if (of_parse_phandle_with_args(node, "power-domains", + "#power-domain-cells", 0, &parent)) + continue; + + child.np = node; + child.args_count = 0; + ret = of_genpd_remove_subdomain(&parent, &child); + of_node_put(parent.np); + if (ret) { + of_node_put(node); + return ret; + } + } + + return 0; +} + struct device *dt_idle_attach_cpu(int cpu, const char *name) { struct device *dev; diff --git a/drivers/cpuidle/dt_idle_genpd.h b/drivers/cpuidle/dt_idle_genpd.h index a95483d08a02..3be1f70f55b5 100644 --- a/drivers/cpuidle/dt_idle_genpd.h +++ b/drivers/cpuidle/dt_idle_genpd.h @@ -14,6 +14,8 @@ struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, int dt_idle_pd_init_topology(struct device_node *np); +int dt_idle_pd_remove_topology(struct device_node *np); + struct device *dt_idle_attach_cpu(int cpu, const char *name); void dt_idle_detach_cpu(struct device *dev); @@ -36,6 +38,11 @@ static inline int dt_idle_pd_init_topology(struct device_node *np) return 0; } +static inline int dt_idle_pd_remove_topology(struct device_node *np) +{ + return 0; +} + static inline struct device *dt_idle_attach_cpu(int cpu, const char *name) { return NULL; From 0176533f5a398587fe2e42f0be7a78c4d12a987e Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Fri, 4 Aug 2023 15:14:03 -0700 Subject: [PATCH 0204/2093] hwmon: (pmbus/bel-pfe) Enable PMBUS_SKIP_STATUS_CHECK for pfe1100 commit f38963b9cd0645a336cf30c5da2e89e34e34fec3 upstream. Skip status check for both pfe1100 and pfe3000 because the communication error is also observed on pfe1100 devices. Signed-off-by: Tao Ren Fixes: 626bb2f3fb3c hwmon: (pmbus) add driver for BEL PFE1100 and PFE3000 Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230804221403.28931-1-rentao.bupt@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/pmbus/bel-pfe.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/hwmon/pmbus/bel-pfe.c b/drivers/hwmon/pmbus/bel-pfe.c index 4100eefb7ac3..61c195f8fd3b 100644 --- a/drivers/hwmon/pmbus/bel-pfe.c +++ b/drivers/hwmon/pmbus/bel-pfe.c @@ -17,12 +17,13 @@ enum chips {pfe1100, pfe3000}; /* - * Disable status check for pfe3000 devices, because some devices report - * communication error (invalid command) for VOUT_MODE command (0x20) - * although correct VOUT_MODE (0x16) is returned: it leads to incorrect - * exponent in linear mode. + * Disable status check because some devices report communication error + * (invalid command) for VOUT_MODE command (0x20) although the correct + * VOUT_MODE (0x16) is returned: it leads to incorrect exponent in linear + * mode. + * This affects both pfe3000 and pfe1100. */ -static struct pmbus_platform_data pfe3000_plat_data = { +static struct pmbus_platform_data pfe_plat_data = { .flags = PMBUS_SKIP_STATUS_CHECK, }; @@ -94,16 +95,15 @@ static int pfe_pmbus_probe(struct i2c_client *client) int model; model = (int)i2c_match_id(pfe_device_id, client)->driver_data; + client->dev.platform_data = &pfe_plat_data; /* * PFE3000-12-069RA devices may not stay in page 0 during device * probe which leads to probe failure (read status word failed). * So let's set the device to page 0 at the beginning. */ - if (model == pfe3000) { - client->dev.platform_data = &pfe3000_plat_data; + if (model == pfe3000) i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0); - } return pmbus_do_probe(client, &pfe_driver_info[model]); } From 79a96970293befd066fd4dfed52c810a5777b286 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 27 Jul 2023 17:09:30 +0100 Subject: [PATCH 0205/2093] radix tree test suite: fix incorrect allocation size for pthreads commit cac7ea57a06016e4914848b707477fb07ee4ae1c upstream. Currently the pthread allocation for each array item is based on the size of a pthread_t pointer and should be the size of the pthread_t structure, so the allocation is under-allocating the correct size. Fix this by using the size of each element in the pthreads array. Static analysis cppcheck reported: tools/testing/radix-tree/regression1.c:180:2: warning: Size of pointer 'threads' used instead of size of its data. [pointerSize] Link: https://lkml.kernel.org/r/20230727160930.632674-1-colin.i.king@gmail.com Fixes: 1366c37ed84b ("radix tree test harness") Signed-off-by: Colin Ian King Cc: Konstantin Khlebnikov Cc: Matthew Wilcox (Oracle) Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- tools/testing/radix-tree/regression1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index a61c7bcbc72d..63f468bf8245 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -177,7 +177,7 @@ void regression1_test(void) nr_threads = 2; pthread_barrier_init(&worker_barrier, NULL, nr_threads); - threads = malloc(nr_threads * sizeof(pthread_t *)); + threads = malloc(nr_threads * sizeof(*threads)); for (i = 0; i < nr_threads; i++) { arg = i; From 7532ff6edbf5242376b24a95a2fefb59bb653e5a Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 29 Jul 2023 04:13:18 +0900 Subject: [PATCH 0206/2093] nilfs2: fix use-after-free of nilfs_root in dirtying inodes via iput commit f8654743a0e6909dc634cbfad6db6816f10f3399 upstream. During unmount process of nilfs2, nothing holds nilfs_root structure after nilfs2 detaches its writer in nilfs_detach_log_writer(). Previously, nilfs_evict_inode() could cause use-after-free read for nilfs_root if inodes are left in "garbage_list" and released by nilfs_dispose_list at the end of nilfs_detach_log_writer(), and this bug was fixed by commit 9b5a04ac3ad9 ("nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode()"). However, it turned out that there is another possibility of UAF in the call path where mark_inode_dirty_sync() is called from iput(): nilfs_detach_log_writer() nilfs_dispose_list() iput() mark_inode_dirty_sync() __mark_inode_dirty() nilfs_dirty_inode() __nilfs_mark_inode_dirty() nilfs_load_inode_block() --> causes UAF of nilfs_root struct This can happen after commit 0ae45f63d4ef ("vfs: add support for a lazytime mount option"), which changed iput() to call mark_inode_dirty_sync() on its final reference if i_state has I_DIRTY_TIME flag and i_nlink is non-zero. This issue appears after commit 28a65b49eb53 ("nilfs2: do not write dirty data after degenerating to read-only") when using the syzbot reproducer, but the issue has potentially existed before. Fix this issue by adding a "purging flag" to the nilfs structure, setting that flag while disposing the "garbage_list" and checking it in __nilfs_mark_inode_dirty(). Unlike commit 9b5a04ac3ad9 ("nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode()"), this patch does not rely on ns_writer to determine whether to skip operations, so as not to break recovery on mount. The nilfs_salvage_orphan_logs routine dirties the buffer of salvaged data before attaching the log writer, so changing __nilfs_mark_inode_dirty() to skip the operation when ns_writer is NULL will cause recovery write to fail. The purpose of using the cleanup-only flag is to allow for narrowing of such conditions. Link: https://lkml.kernel.org/r/20230728191318.33047-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+74db8b3087f293d3a13a@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/000000000000b4e906060113fd63@google.com Fixes: 0ae45f63d4ef ("vfs: add support for a lazytime mount option") Tested-by: Ryusuke Konishi Cc: # 4.0+ Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/inode.c | 8 ++++++++ fs/nilfs2/segment.c | 2 ++ fs/nilfs2/the_nilfs.h | 2 ++ 3 files changed, 12 insertions(+) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index f6e44efb58e1..d4c0895a8811 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warn(inode->i_sb, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 6cf64023be31..21e8260112c8 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2843,6 +2843,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2855,4 +2856,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 47c7dfbb7ea5..cd4ae1b8ae16 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations From 2368afd60f647889d90fa4a42c7b27548f77dbd9 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 11 Aug 2023 11:40:28 -0500 Subject: [PATCH 0207/2093] drm/amd/pm: fulfill swsmu peak profiling mode shader/memory clock settings commit 975b4b1d90ccf83da252907108f4090fb61b816e upstream Enable peak profiling mode shader/memory clocks reporting for swsmu framework. Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/include/kgd_pp_interface.h | 2 ++ drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 8 ++++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index d18162e9ed1d..f3d64c78feaa 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -139,6 +139,8 @@ enum amd_pp_sensors { AMDGPU_PP_SENSOR_MIN_FAN_RPM, AMDGPU_PP_SENSOR_MAX_FAN_RPM, AMDGPU_PP_SENSOR_VCN_POWER_STATE, + AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK, + AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK, }; enum amd_pp_task { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 91dfc229e34d..6d90ab55cea3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2520,6 +2520,14 @@ static int smu_read_sensor(void *handle, *((uint32_t *)data) = pstate_table->uclk_pstate.standard * 100; *size = 4; break; + case AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK: + *((uint32_t *)data) = pstate_table->gfxclk_pstate.peak * 100; + *size = 4; + break; + case AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK: + *((uint32_t *)data) = pstate_table->uclk_pstate.peak * 100; + *size = 4; + break; case AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK: ret = smu_feature_get_enabled_mask(smu, (uint64_t *)data); *size = 8; From b844033ea813cb028a1961514ef37010fef9f543 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 11 Aug 2023 11:40:29 -0500 Subject: [PATCH 0208/2093] drm/amd/pm: expose swctf threshold setting for legacy powerplay commit 064329c595da56eff6d7a7e7760660c726433139 upstream Preparation for coming optimization which eliminates the influence of GPU temperature momentary fluctuation. Signed-off-by: Evan Quan Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h | 2 ++ .../gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c | 4 +++- drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 2 ++ drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 10 ++++++++++ drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 4 ++++ drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 4 ++++ drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h | 1 + 7 files changed, 26 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index cb5b9df78b4d..338fce249f5a 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -89,6 +89,8 @@ struct amdgpu_dpm_thermal { int max_mem_crit_temp; /* memory max emergency(shutdown) temp */ int max_mem_emergency_temp; + /* SWCTF threshold */ + int sw_ctf_threshold; /* was last interrupt low to high or high to low */ bool high_to_low; /* interrupt source */ diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c index 981dc8c7112d..90452b66e107 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c @@ -241,7 +241,8 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr) TEMP_RANGE_MAX, TEMP_RANGE_MIN, TEMP_RANGE_MAX, - TEMP_RANGE_MAX}; + TEMP_RANGE_MAX, + 0}; struct amdgpu_device *adev = hwmgr->adev; if (!hwmgr->not_vf) @@ -265,6 +266,7 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr) adev->pm.dpm.thermal.min_mem_temp = range.mem_min; adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max; adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max; + adev->pm.dpm.thermal.sw_ctf_threshold = range.sw_ctf_threshold; return ret; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 7ef7e81525a3..b9e6e49ba4f0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -5381,6 +5381,8 @@ static int smu7_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, thermal_data->max = data->thermal_temp_setting.temperature_shutdown * PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + thermal_data->sw_ctf_threshold = thermal_data->max; + return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index c8c9fb827bda..c78f8b2b056d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -5221,6 +5221,9 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, { struct vega10_hwmgr *data = hwmgr->backend; PPTable_t *pp_table = &(data->smc_state_table.pp_table); + struct phm_ppt_v2_information *pp_table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + struct phm_tdp_table *tdp_table = pp_table_info->tdp_table; memcpy(thermal_data, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange)); @@ -5237,6 +5240,13 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)* PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (tdp_table->usSoftwareShutdownTemp > pp_table->ThotspotLimit && + tdp_table->usSoftwareShutdownTemp < VEGA10_THERMAL_MAXIMUM_ALERT_TEMP) + thermal_data->sw_ctf_threshold = tdp_table->usSoftwareShutdownTemp; + else + thermal_data->sw_ctf_threshold = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP; + thermal_data->sw_ctf_threshold *= PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index a2f4d6773d45..0fe821dff0a4 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -2742,6 +2742,8 @@ static int vega12_notify_cac_buffer_info(struct pp_hwmgr *hwmgr, static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *thermal_data) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); PPTable_t *pp_table = &(data->smc_state_table.pp_table); @@ -2760,6 +2762,8 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, PP_TEMPERATURE_UNITS_PER_CENTIGRADES; thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)* PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp * + PP_TEMPERATURE_UNITS_PER_CENTIGRADES; return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index b30684c84e20..8e4743cb7443 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -4213,6 +4213,8 @@ static int vega20_notify_cac_buffer_info(struct pp_hwmgr *hwmgr, static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *thermal_data) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); PPTable_t *pp_table = &(data->smc_state_table.pp_table); @@ -4231,6 +4233,8 @@ static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr, PP_TEMPERATURE_UNITS_PER_CENTIGRADES; thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)* PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp * + PP_TEMPERATURE_UNITS_PER_CENTIGRADES; return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h index a5f2227a3971..0ffc2347829d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h @@ -131,6 +131,7 @@ struct PP_TemperatureRange { int mem_min; int mem_crit_max; int mem_emergency_max; + int sw_ctf_threshold; }; struct PP_StateValidationBlock { From b064f9ccf11cb4008a1f0e3c96099041b121af80 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 11 Aug 2023 11:40:30 -0500 Subject: [PATCH 0209/2093] drm/amd/pm: fulfill powerplay peak profiling mode shader/memory clock settings commit b1a9557a7d00c758ed9e701fbb3445a13a49506f upstream Enable peak profiling mode shader/memory clock reporting for powerplay framework. Signed-off-by: Evan Quan Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/pm/powerplay/amd_powerplay.c | 10 ++- .../drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c | 16 +++- .../drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 76 +++++++++++++++---- .../drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c | 16 +++- .../drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 31 ++++++-- .../drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 22 ++++++ .../drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 20 ++--- drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h | 2 + 8 files changed, 155 insertions(+), 38 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 1159ae114dd0..3f4a476d7802 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -769,10 +769,16 @@ static int pp_dpm_read_sensor(void *handle, int idx, switch (idx) { case AMDGPU_PP_SENSOR_STABLE_PSTATE_SCLK: - *((uint32_t *)value) = hwmgr->pstate_sclk; + *((uint32_t *)value) = hwmgr->pstate_sclk * 100; return 0; case AMDGPU_PP_SENSOR_STABLE_PSTATE_MCLK: - *((uint32_t *)value) = hwmgr->pstate_mclk; + *((uint32_t *)value) = hwmgr->pstate_mclk * 100; + return 0; + case AMDGPU_PP_SENSOR_PEAK_PSTATE_SCLK: + *((uint32_t *)value) = hwmgr->pstate_sclk_peak * 100; + return 0; + case AMDGPU_PP_SENSOR_PEAK_PSTATE_MCLK: + *((uint32_t *)value) = hwmgr->pstate_mclk_peak * 100; return 0; case AMDGPU_PP_SENSOR_MIN_FAN_RPM: *((uint32_t *)value) = hwmgr->thermal_controller.fanInfo.ulMinRPM; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index ede71de2343d..86d6e88c7386 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -375,6 +375,17 @@ static int smu10_enable_gfx_off(struct pp_hwmgr *hwmgr) return 0; } +static void smu10_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) +{ + hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK; + hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK; + + smum_send_msg_to_smc(hwmgr, + PPSMC_MSG_GetMaxGfxclkFrequency, + &hwmgr->pstate_sclk_peak); + hwmgr->pstate_mclk_peak = SMU10_UMD_PSTATE_PEAK_FCLK; +} + static int smu10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { struct amdgpu_device *adev = hwmgr->adev; @@ -398,6 +409,8 @@ static int smu10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) return ret; } + smu10_populate_umdpstate_clocks(hwmgr); + return 0; } @@ -574,9 +587,6 @@ static int smu10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; - hwmgr->pstate_sclk = SMU10_UMD_PSTATE_GFXCLK * 100; - hwmgr->pstate_mclk = SMU10_UMD_PSTATE_FCLK * 100; - /* enable the pp_od_clk_voltage sysfs file */ hwmgr->od_enabled = 1; /* disabled fine grain tuning function by default */ diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index b9e6e49ba4f0..44ec238cfeff 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1501,6 +1501,65 @@ static int smu7_populate_edc_leakage_registers(struct pp_hwmgr *hwmgr) return ret; } +static void smu7_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) +{ + struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); + struct smu7_dpm_table *golden_dpm_table = &data->golden_dpm_table; + struct phm_clock_voltage_dependency_table *vddc_dependency_on_sclk = + hwmgr->dyn_state.vddc_dependency_on_sclk; + struct phm_ppt_v1_information *table_info = + (struct phm_ppt_v1_information *)(hwmgr->pptable); + struct phm_ppt_v1_clock_voltage_dependency_table *vdd_dep_on_sclk = + table_info->vdd_dep_on_sclk; + int32_t tmp_sclk, count, percentage; + + if (golden_dpm_table->mclk_table.count == 1) { + percentage = 70; + hwmgr->pstate_mclk = golden_dpm_table->mclk_table.dpm_levels[0].value; + } else { + percentage = 100 * golden_dpm_table->sclk_table.dpm_levels[golden_dpm_table->sclk_table.count - 1].value / + golden_dpm_table->mclk_table.dpm_levels[golden_dpm_table->mclk_table.count - 1].value; + hwmgr->pstate_mclk = golden_dpm_table->mclk_table.dpm_levels[golden_dpm_table->mclk_table.count - 2].value; + } + + tmp_sclk = hwmgr->pstate_mclk * percentage / 100; + + if (hwmgr->pp_table_version == PP_TABLE_V0) { + for (count = vddc_dependency_on_sclk->count - 1; count >= 0; count--) { + if (tmp_sclk >= vddc_dependency_on_sclk->entries[count].clk) { + hwmgr->pstate_sclk = vddc_dependency_on_sclk->entries[count].clk; + break; + } + } + if (count < 0) + hwmgr->pstate_sclk = vddc_dependency_on_sclk->entries[0].clk; + + hwmgr->pstate_sclk_peak = + vddc_dependency_on_sclk->entries[vddc_dependency_on_sclk->count - 1].clk; + } else if (hwmgr->pp_table_version == PP_TABLE_V1) { + for (count = vdd_dep_on_sclk->count - 1; count >= 0; count--) { + if (tmp_sclk >= vdd_dep_on_sclk->entries[count].clk) { + hwmgr->pstate_sclk = vdd_dep_on_sclk->entries[count].clk; + break; + } + } + if (count < 0) + hwmgr->pstate_sclk = vdd_dep_on_sclk->entries[0].clk; + + hwmgr->pstate_sclk_peak = + vdd_dep_on_sclk->entries[vdd_dep_on_sclk->count - 1].clk; + } + + hwmgr->pstate_mclk_peak = + golden_dpm_table->mclk_table.dpm_levels[golden_dpm_table->mclk_table.count - 1].value; + + /* make sure the output is in Mhz */ + hwmgr->pstate_sclk /= 100; + hwmgr->pstate_mclk /= 100; + hwmgr->pstate_sclk_peak /= 100; + hwmgr->pstate_mclk_peak /= 100; +} + static int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { int tmp_result = 0; @@ -1625,6 +1684,8 @@ static int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((0 == tmp_result), "pcie performance request failed!", result = tmp_result); + smu7_populate_umdpstate_clocks(hwmgr); + return 0; } @@ -3143,15 +3204,12 @@ static int smu7_get_profiling_clk(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_le for (count = hwmgr->dyn_state.vddc_dependency_on_sclk->count-1; count >= 0; count--) { if (tmp_sclk >= hwmgr->dyn_state.vddc_dependency_on_sclk->entries[count].clk) { - tmp_sclk = hwmgr->dyn_state.vddc_dependency_on_sclk->entries[count].clk; *sclk_mask = count; break; } } - if (count < 0 || level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) { + if (count < 0 || level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) *sclk_mask = 0; - tmp_sclk = hwmgr->dyn_state.vddc_dependency_on_sclk->entries[0].clk; - } if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) *sclk_mask = hwmgr->dyn_state.vddc_dependency_on_sclk->count-1; @@ -3161,15 +3219,12 @@ static int smu7_get_profiling_clk(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_le for (count = table_info->vdd_dep_on_sclk->count-1; count >= 0; count--) { if (tmp_sclk >= table_info->vdd_dep_on_sclk->entries[count].clk) { - tmp_sclk = table_info->vdd_dep_on_sclk->entries[count].clk; *sclk_mask = count; break; } } - if (count < 0 || level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) { + if (count < 0 || level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) *sclk_mask = 0; - tmp_sclk = table_info->vdd_dep_on_sclk->entries[0].clk; - } if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) *sclk_mask = table_info->vdd_dep_on_sclk->count - 1; @@ -3181,8 +3236,6 @@ static int smu7_get_profiling_clk(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_le *mclk_mask = golden_dpm_table->mclk_table.count - 1; *pcie_mask = data->dpm_table.pcie_speed_table.count - 1; - hwmgr->pstate_sclk = tmp_sclk; - hwmgr->pstate_mclk = tmp_mclk; return 0; } @@ -3195,9 +3248,6 @@ static int smu7_force_dpm_level(struct pp_hwmgr *hwmgr, uint32_t mclk_mask = 0; uint32_t pcie_mask = 0; - if (hwmgr->pstate_sclk == 0) - smu7_get_profiling_clk(hwmgr, level, &sclk_mask, &mclk_mask, &pcie_mask); - switch (level) { case AMD_DPM_FORCED_LEVEL_HIGH: ret = smu7_force_dpm_highest(hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index b50fd4a4a3d1..b015a601b385 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -1016,6 +1016,18 @@ static void smu8_reset_acp_boot_level(struct pp_hwmgr *hwmgr) data->acp_boot_level = 0xff; } +static void smu8_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) +{ + struct phm_clock_voltage_dependency_table *table = + hwmgr->dyn_state.vddc_dependency_on_sclk; + + hwmgr->pstate_sclk = table->entries[0].clk / 100; + hwmgr->pstate_mclk = 0; + + hwmgr->pstate_sclk_peak = table->entries[table->count - 1].clk / 100; + hwmgr->pstate_mclk_peak = 0; +} + static int smu8_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { smu8_program_voting_clients(hwmgr); @@ -1024,6 +1036,8 @@ static int smu8_enable_dpm_tasks(struct pp_hwmgr *hwmgr) smu8_program_bootup_state(hwmgr); smu8_reset_acp_boot_level(hwmgr); + smu8_populate_umdpstate_clocks(hwmgr); + return 0; } @@ -1167,8 +1181,6 @@ static int smu8_phm_unforce_dpm_levels(struct pp_hwmgr *hwmgr) data->sclk_dpm.soft_min_clk = table->entries[0].clk; data->sclk_dpm.hard_min_clk = table->entries[0].clk; - hwmgr->pstate_sclk = table->entries[0].clk; - hwmgr->pstate_mclk = 0; level = smu8_get_max_sclk_level(hwmgr) - 1; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index c78f8b2b056d..d8cd23438b76 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3008,6 +3008,30 @@ static int vega10_enable_disable_PCC_limit_feature(struct pp_hwmgr *hwmgr, bool return 0; } +static void vega10_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) +{ + struct phm_ppt_v2_information *table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + + if (table_info->vdd_dep_on_sclk->count > VEGA10_UMD_PSTATE_GFXCLK_LEVEL && + table_info->vdd_dep_on_mclk->count > VEGA10_UMD_PSTATE_MCLK_LEVEL) { + hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[VEGA10_UMD_PSTATE_GFXCLK_LEVEL].clk; + hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[VEGA10_UMD_PSTATE_MCLK_LEVEL].clk; + } else { + hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[0].clk; + hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[0].clk; + } + + hwmgr->pstate_sclk_peak = table_info->vdd_dep_on_sclk->entries[table_info->vdd_dep_on_sclk->count - 1].clk; + hwmgr->pstate_mclk_peak = table_info->vdd_dep_on_mclk->entries[table_info->vdd_dep_on_mclk->count - 1].clk; + + /* make sure the output is in Mhz */ + hwmgr->pstate_sclk /= 100; + hwmgr->pstate_mclk /= 100; + hwmgr->pstate_sclk_peak /= 100; + hwmgr->pstate_mclk_peak /= 100; +} + static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { struct vega10_hwmgr *data = hwmgr->backend; @@ -3082,6 +3106,8 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) result = tmp_result); } + vega10_populate_umdpstate_clocks(hwmgr); + return result; } @@ -4169,8 +4195,6 @@ static int vega10_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo *sclk_mask = VEGA10_UMD_PSTATE_GFXCLK_LEVEL; *soc_mask = VEGA10_UMD_PSTATE_SOCCLK_LEVEL; *mclk_mask = VEGA10_UMD_PSTATE_MCLK_LEVEL; - hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[VEGA10_UMD_PSTATE_GFXCLK_LEVEL].clk; - hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[VEGA10_UMD_PSTATE_MCLK_LEVEL].clk; } if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) { @@ -4281,9 +4305,6 @@ static int vega10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, uint32_t mclk_mask = 0; uint32_t soc_mask = 0; - if (hwmgr->pstate_sclk == 0) - vega10_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask); - switch (level) { case AMD_DPM_FORCED_LEVEL_HIGH: ret = vega10_force_dpm_highest(hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 0fe821dff0a4..1069eaaae2f8 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -1026,6 +1026,25 @@ static int vega12_get_all_clock_ranges(struct pp_hwmgr *hwmgr) return 0; } +static void vega12_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) +{ + struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); + struct vega12_single_dpm_table *gfx_dpm_table = &(data->dpm_table.gfx_table); + struct vega12_single_dpm_table *mem_dpm_table = &(data->dpm_table.mem_table); + + if (gfx_dpm_table->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL && + mem_dpm_table->count > VEGA12_UMD_PSTATE_MCLK_LEVEL) { + hwmgr->pstate_sclk = gfx_dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value; + hwmgr->pstate_mclk = mem_dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value; + } else { + hwmgr->pstate_sclk = gfx_dpm_table->dpm_levels[0].value; + hwmgr->pstate_mclk = mem_dpm_table->dpm_levels[0].value; + } + + hwmgr->pstate_sclk_peak = gfx_dpm_table->dpm_levels[gfx_dpm_table->count].value; + hwmgr->pstate_mclk_peak = mem_dpm_table->dpm_levels[mem_dpm_table->count].value; +} + static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { int tmp_result, result = 0; @@ -1077,6 +1096,9 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE(!result, "Failed to setup default DPM tables!", return result); + + vega12_populate_umdpstate_clocks(hwmgr); + return result; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 8e4743cb7443..ff77a3683efd 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -1555,26 +1555,23 @@ static int vega20_set_mclk_od( return 0; } -static int vega20_populate_umdpstate_clocks( - struct pp_hwmgr *hwmgr) +static void vega20_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); struct vega20_single_dpm_table *gfx_table = &(data->dpm_table.gfx_table); struct vega20_single_dpm_table *mem_table = &(data->dpm_table.mem_table); - hwmgr->pstate_sclk = gfx_table->dpm_levels[0].value; - hwmgr->pstate_mclk = mem_table->dpm_levels[0].value; - if (gfx_table->count > VEGA20_UMD_PSTATE_GFXCLK_LEVEL && mem_table->count > VEGA20_UMD_PSTATE_MCLK_LEVEL) { hwmgr->pstate_sclk = gfx_table->dpm_levels[VEGA20_UMD_PSTATE_GFXCLK_LEVEL].value; hwmgr->pstate_mclk = mem_table->dpm_levels[VEGA20_UMD_PSTATE_MCLK_LEVEL].value; + } else { + hwmgr->pstate_sclk = gfx_table->dpm_levels[0].value; + hwmgr->pstate_mclk = mem_table->dpm_levels[0].value; } - hwmgr->pstate_sclk = hwmgr->pstate_sclk * 100; - hwmgr->pstate_mclk = hwmgr->pstate_mclk * 100; - - return 0; + hwmgr->pstate_sclk_peak = gfx_table->dpm_levels[gfx_table->count - 1].value; + hwmgr->pstate_mclk_peak = mem_table->dpm_levels[mem_table->count - 1].value; } static int vega20_get_max_sustainable_clock(struct pp_hwmgr *hwmgr, @@ -1753,10 +1750,7 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "[EnableDPMTasks] Failed to initialize odn settings!", return result); - result = vega20_populate_umdpstate_clocks(hwmgr); - PP_ASSERT_WITH_CODE(!result, - "[EnableDPMTasks] Failed to populate umdpstate clocks!", - return result); + vega20_populate_umdpstate_clocks(hwmgr); result = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetPptLimit, POWER_SOURCE_AC << 16, &hwmgr->default_power_limit); diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index 27f8d0e0e6a8..5ce433e2c16a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -809,6 +809,8 @@ struct pp_hwmgr { uint32_t workload_prority[Workload_Policy_Max]; uint32_t workload_setting[Workload_Policy_Max]; bool gfxoff_state_changed_by_workload; + uint32_t pstate_sclk_peak; + uint32_t pstate_mclk_peak; }; int hwmgr_early_init(struct pp_hwmgr *hwmgr); From 0f19195d639764d68f6f316dda363ba29821e5bc Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 11 Aug 2023 11:40:31 -0500 Subject: [PATCH 0210/2093] drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation commit b75efe88b20c2be28b67e2821a794cc183e32374 upstream An intentional delay is added on soft ctf triggered. Then there will be a double check for the GPU temperature before taking further action. This can avoid unintended shutdown due to temperature momentary fluctuation. Signed-off-by: Evan Quan Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher [ Hand-modified because: * XCP support added to amdgpu.h in kernel 6.5 and is not necessary for this fix. * SMU microcode initialization moved in 32806038aa76 ("drm/amd: Load SMU microcode during early_init") ] Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1267 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2779 Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 ++ .../gpu/drm/amd/pm/powerplay/amd_powerplay.c | 48 +++++++++++++++++++ .../drm/amd/pm/powerplay/hwmgr/smu_helper.c | 27 ++++------- drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h | 2 + drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 34 +++++++++++++ drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h | 2 + .../gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 9 +--- .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 9 +--- 8 files changed, 102 insertions(+), 32 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9ecf20169912..0c962f996aff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -284,6 +284,9 @@ extern int amdgpu_sg_display; #define AMDGPU_SMARTSHIFT_MAX_BIAS (100) #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100) +/* Extra time delay(in ms) to eliminate the influence of temperature momentary fluctuation */ +#define AMDGPU_SWCTF_EXTRA_DELAY 50 + struct amdgpu_device; struct amdgpu_irq_src; struct amdgpu_fpriv; diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 3f4a476d7802..179e1c593a53 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "amd_shared.h" #include "amd_powerplay.h" #include "power_state.h" @@ -91,6 +92,45 @@ static int pp_early_init(void *handle) return 0; } +static void pp_swctf_delayed_work_handler(struct work_struct *work) +{ + struct pp_hwmgr *hwmgr = + container_of(work, struct pp_hwmgr, swctf_delayed_work.work); + struct amdgpu_device *adev = hwmgr->adev; + struct amdgpu_dpm_thermal *range = + &adev->pm.dpm.thermal; + uint32_t gpu_temperature, size; + int ret; + + /* + * If the hotspot/edge temperature is confirmed as below SW CTF setting point + * after the delay enforced, nothing will be done. + * Otherwise, a graceful shutdown will be performed to prevent further damage. + */ + if (range->sw_ctf_threshold && + hwmgr->hwmgr_func->read_sensor) { + ret = hwmgr->hwmgr_func->read_sensor(hwmgr, + AMDGPU_PP_SENSOR_HOTSPOT_TEMP, + &gpu_temperature, + &size); + /* + * For some legacy ASICs, hotspot temperature retrieving might be not + * supported. Check the edge temperature instead then. + */ + if (ret == -EOPNOTSUPP) + ret = hwmgr->hwmgr_func->read_sensor(hwmgr, + AMDGPU_PP_SENSOR_EDGE_TEMP, + &gpu_temperature, + &size); + if (!ret && gpu_temperature / 1000 < range->sw_ctf_threshold) + return; + } + + dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); + dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); + orderly_poweroff(true); +} + static int pp_sw_init(void *handle) { struct amdgpu_device *adev = handle; @@ -101,6 +141,10 @@ static int pp_sw_init(void *handle) pr_debug("powerplay sw init %s\n", ret ? "failed" : "successfully"); + if (!ret) + INIT_DELAYED_WORK(&hwmgr->swctf_delayed_work, + pp_swctf_delayed_work_handler); + return ret; } @@ -136,6 +180,8 @@ static int pp_hw_fini(void *handle) struct amdgpu_device *adev = handle; struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; + cancel_delayed_work_sync(&hwmgr->swctf_delayed_work); + hwmgr_hw_fini(hwmgr); return 0; @@ -222,6 +268,8 @@ static int pp_suspend(void *handle) struct amdgpu_device *adev = handle; struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; + cancel_delayed_work_sync(&hwmgr->swctf_delayed_work); + return hwmgr_suspend(hwmgr); } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c index bfe80ac0ad8c..d0b1ab6c4523 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c @@ -603,21 +603,17 @@ int phm_irq_process(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { + struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; uint32_t client_id = entry->client_id; uint32_t src_id = entry->src_id; if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) { if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH) { - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); - } else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) + schedule_delayed_work(&hwmgr->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); + } else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) { dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n"); - else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) { + } else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) { dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n"); /* * HW CTF just occurred. Shutdown to prevent further damage. @@ -626,15 +622,10 @@ int phm_irq_process(struct amdgpu_device *adev, orderly_poweroff(true); } } else if (client_id == SOC15_IH_CLIENTID_THM) { - if (src_id == 0) { - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); - } else + if (src_id == 0) + schedule_delayed_work(&hwmgr->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); + else dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n"); } else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) { dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n"); diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index 5ce433e2c16a..ec10643edea3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -811,6 +811,8 @@ struct pp_hwmgr { bool gfxoff_state_changed_by_workload; uint32_t pstate_sclk_peak; uint32_t pstate_mclk_peak; + + struct delayed_work swctf_delayed_work; }; int hwmgr_early_init(struct pp_hwmgr *hwmgr); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 6d90ab55cea3..d191ff52d4f0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -24,6 +24,7 @@ #include #include +#include #include "amdgpu.h" #include "amdgpu_smu.h" @@ -1061,6 +1062,34 @@ static void smu_interrupt_work_fn(struct work_struct *work) smu->ppt_funcs->interrupt_work(smu); } +static void smu_swctf_delayed_work_handler(struct work_struct *work) +{ + struct smu_context *smu = + container_of(work, struct smu_context, swctf_delayed_work.work); + struct smu_temperature_range *range = + &smu->thermal_range; + struct amdgpu_device *adev = smu->adev; + uint32_t hotspot_tmp, size; + + /* + * If the hotspot temperature is confirmed as below SW CTF setting point + * after the delay enforced, nothing will be done. + * Otherwise, a graceful shutdown will be performed to prevent further damage. + */ + if (range->software_shutdown_temp && + smu->ppt_funcs->read_sensor && + !smu->ppt_funcs->read_sensor(smu, + AMDGPU_PP_SENSOR_HOTSPOT_TEMP, + &hotspot_tmp, + &size) && + hotspot_tmp / 1000 < range->software_shutdown_temp) + return; + + dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); + dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); + orderly_poweroff(true); +} + static int smu_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1109,6 +1138,9 @@ static int smu_sw_init(void *handle) return ret; } + INIT_DELAYED_WORK(&smu->swctf_delayed_work, + smu_swctf_delayed_work_handler); + ret = smu_smc_table_sw_init(smu); if (ret) { dev_err(adev->dev, "Failed to sw init smc table!\n"); @@ -1581,6 +1613,8 @@ static int smu_smc_hw_cleanup(struct smu_context *smu) return ret; } + cancel_delayed_work_sync(&smu->swctf_delayed_work); + ret = smu_disable_dpms(smu); if (ret) { dev_err(adev->dev, "Fail to disable dpm features!\n"); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 3bc4128a22ac..1ab77a6cdb65 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -573,6 +573,8 @@ struct smu_context u32 debug_param_reg; u32 debug_msg_reg; u32 debug_resp_reg; + + struct delayed_work swctf_delayed_work; }; struct i2c_adapter; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index ad5f6a15a1d7..d490b571c8ff 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1438,13 +1438,8 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); + schedule_delayed_work(&smu->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); break; case THM_11_0__SRCID__THM_DIG_THERM_H2L: dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n"); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 47fafb1fa608..3104d4937909 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1386,13 +1386,8 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); + schedule_delayed_work(&smu->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); break; case THM_11_0__SRCID__THM_DIG_THERM_H2L: dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n"); From 60334c0cba2f7741252960994b1e9b1d6b668d07 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 11 Aug 2023 16:06:59 -0500 Subject: [PATCH 0211/2093] drm/amd/display: Handle virtual hardware detect commit 987b96eb860036ab79051fb271f7fbdc01c9daf5 upstream If virtual hardware is detected, there is no reason to run the full dc_commit_streams process, and DC can return true immediately. Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Co-developed-by: Aurabindo Pillai Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8f9c60ed6f8b..9b7ddd0e10a5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1942,6 +1942,9 @@ enum dc_status dc_commit_streams(struct dc *dc, struct pipe_ctx *pipe; bool handle_exit_odm2to1 = false; + if (dc->ctx->dce_environment == DCE_ENV_VIRTUAL_HW) + return res; + if (!streams_changed(dc, streams, stream_count)) return res; From 9b1a1f168c03787aa6a159f4f1dfbfa398f1d44e Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 11 Aug 2023 16:07:00 -0500 Subject: [PATCH 0212/2093] drm/amd/display: Add function for validate and update new stream commit a5e39ae27c3a305c6aafc0e423b0cb2c677facde upstream DC stream can be seen as a representation of the DCN backend or the data struct that represents the center of the display pipeline. The front end (i.e., planes) is connected to the DC stream, and in its turn, streams are connected to the DC link. Due to this dynamic, DC must handle the following scenarios: 1. A stream is removed; 2. A new stream is created; 3. An unchanged stream had some updates on its planes. These combinations require that the new stream data struct become updated and has a valid global state. For handling multiple corner cases associated with stream operations, this commit introduces a function dedicated to manipulating stream changes and invokes the state validation function after that. Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Co-developed-by: Aurabindo Pillai Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 16 +- .../gpu/drm/amd/display/dc/core/dc_resource.c | 219 +++++++++++++++++- drivers/gpu/drm/amd/display/dc/dc.h | 6 + 3 files changed, 227 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 9b7ddd0e10a5..753c07ab54ed 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1987,21 +1987,17 @@ enum dc_status dc_commit_streams(struct dc *dc, dc_resource_state_copy_construct_current(dc, context); - /* - * Previous validation was perfomred with fast_validation = true and - * the full DML state required for hardware programming was skipped. - * - * Re-validate here to calculate these parameters / watermarks. - */ - res = dc_validate_global_state(dc, context, false); + res = dc_validate_with_context(dc, set, stream_count, context, false); if (res != DC_OK) { - DC_LOG_ERROR("DC commit global validation failure: %s (%d)", - dc_status_to_str(res), res); - return res; + BREAK_TO_DEBUGGER(); + goto fail; } res = dc_commit_state_no_check(dc, context); +fail: + dc_release_state(context); + context_alloc_fail: DC_LOG_DC("%s Finished.\n", __func__); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index a26e52abc989..613db2da353a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -2616,15 +2616,226 @@ bool dc_resource_is_dsc_encoding_supported(const struct dc *dc) return dc->res_pool->res_cap->num_dsc > 0; } +static bool planes_changed_for_existing_stream(struct dc_state *context, + struct dc_stream_state *stream, + const struct dc_validation_set set[], + int set_count) +{ + int i, j; + struct dc_stream_status *stream_status = NULL; + + for (i = 0; i < context->stream_count; i++) { + if (context->streams[i] == stream) { + stream_status = &context->stream_status[i]; + break; + } + } + + if (!stream_status) + ASSERT(0); + + for (i = 0; i < set_count; i++) + if (set[i].stream == stream) + break; + + if (i == set_count) + ASSERT(0); + + if (set[i].plane_count != stream_status->plane_count) + return true; + + for (j = 0; j < set[i].plane_count; j++) + if (set[i].plane_states[j] != stream_status->plane_states[j]) + return true; + + return false; +} /** - * dc_validate_global_state() - Determine if HW can support a given state - * Checks HW resource availability and bandwidth requirement. + * dc_validate_with_context - Validate and update the potential new stream in the context object + * + * @dc: Used to get the current state status + * @set: An array of dc_validation_set with all the current streams reference + * @set_count: Total of streams + * @context: New context + * @fast_validate: Enable or disable fast validation + * + * This function updates the potential new stream in the context object. It + * creates multiple lists for the add, remove, and unchanged streams. In + * particular, if the unchanged streams have a plane that changed, it is + * necessary to remove all planes from the unchanged streams. In summary, this + * function is responsible for validating the new context. + * + * Return: + * In case of success, return DC_OK (1), otherwise, return a DC error. + */ +enum dc_status dc_validate_with_context(struct dc *dc, + const struct dc_validation_set set[], + int set_count, + struct dc_state *context, + bool fast_validate) +{ + struct dc_stream_state *unchanged_streams[MAX_PIPES] = { 0 }; + struct dc_stream_state *del_streams[MAX_PIPES] = { 0 }; + struct dc_stream_state *add_streams[MAX_PIPES] = { 0 }; + int old_stream_count = context->stream_count; + enum dc_status res = DC_ERROR_UNEXPECTED; + int unchanged_streams_count = 0; + int del_streams_count = 0; + int add_streams_count = 0; + bool found = false; + int i, j, k; + + DC_LOGGER_INIT(dc->ctx->logger); + + /* First build a list of streams to be remove from current context */ + for (i = 0; i < old_stream_count; i++) { + struct dc_stream_state *stream = context->streams[i]; + + for (j = 0; j < set_count; j++) { + if (stream == set[j].stream) { + found = true; + break; + } + } + + if (!found) + del_streams[del_streams_count++] = stream; + + found = false; + } + + /* Second, build a list of new streams */ + for (i = 0; i < set_count; i++) { + struct dc_stream_state *stream = set[i].stream; + + for (j = 0; j < old_stream_count; j++) { + if (stream == context->streams[j]) { + found = true; + break; + } + } + + if (!found) + add_streams[add_streams_count++] = stream; + + found = false; + } + + /* Build a list of unchanged streams which is necessary for handling + * planes change such as added, removed, and updated. + */ + for (i = 0; i < set_count; i++) { + /* Check if stream is part of the delete list */ + for (j = 0; j < del_streams_count; j++) { + if (set[i].stream == del_streams[j]) { + found = true; + break; + } + } + + if (!found) { + /* Check if stream is part of the add list */ + for (j = 0; j < add_streams_count; j++) { + if (set[i].stream == add_streams[j]) { + found = true; + break; + } + } + } + + if (!found) + unchanged_streams[unchanged_streams_count++] = set[i].stream; + + found = false; + } + + /* Remove all planes for unchanged streams if planes changed */ + for (i = 0; i < unchanged_streams_count; i++) { + if (planes_changed_for_existing_stream(context, + unchanged_streams[i], + set, + set_count)) { + if (!dc_rem_all_planes_for_stream(dc, + unchanged_streams[i], + context)) { + res = DC_FAIL_DETACH_SURFACES; + goto fail; + } + } + } + + /* Remove all planes for removed streams and then remove the streams */ + for (i = 0; i < del_streams_count; i++) { + /* Need to cpy the dwb data from the old stream in order to efc to work */ + if (del_streams[i]->num_wb_info > 0) { + for (j = 0; j < add_streams_count; j++) { + if (del_streams[i]->sink == add_streams[j]->sink) { + add_streams[j]->num_wb_info = del_streams[i]->num_wb_info; + for (k = 0; k < del_streams[i]->num_wb_info; k++) + add_streams[j]->writeback_info[k] = del_streams[i]->writeback_info[k]; + } + } + } + + if (!dc_rem_all_planes_for_stream(dc, del_streams[i], context)) { + res = DC_FAIL_DETACH_SURFACES; + goto fail; + } + + res = dc_remove_stream_from_ctx(dc, context, del_streams[i]); + if (res != DC_OK) + goto fail; + } + + /* Add new streams and then add all planes for the new stream */ + for (i = 0; i < add_streams_count; i++) { + calculate_phy_pix_clks(add_streams[i]); + res = dc_add_stream_to_ctx(dc, context, add_streams[i]); + if (res != DC_OK) + goto fail; + + if (!add_all_planes_for_stream(dc, add_streams[i], set, set_count, context)) { + res = DC_FAIL_ATTACH_SURFACES; + goto fail; + } + } + + /* Add all planes for unchanged streams if planes changed */ + for (i = 0; i < unchanged_streams_count; i++) { + if (planes_changed_for_existing_stream(context, + unchanged_streams[i], + set, + set_count)) { + if (!add_all_planes_for_stream(dc, unchanged_streams[i], set, set_count, context)) { + res = DC_FAIL_ATTACH_SURFACES; + goto fail; + } + } + } + + res = dc_validate_global_state(dc, context, fast_validate); + +fail: + if (res != DC_OK) + DC_LOG_WARNING("%s:resource validation failed, dc_status:%d\n", + __func__, + res); + + return res; +} + +/** + * dc_validate_global_state() - Determine if hardware can support a given state + * * @dc: dc struct for this driver * @new_ctx: state to be validated * @fast_validate: set to true if only yes/no to support matters * - * Return: DC_OK if the result can be programmed. Otherwise, an error code. + * Checks hardware resource availability and bandwidth requirement. + * + * Return: + * DC_OK if the result can be programmed. Otherwise, an error code. */ enum dc_status dc_validate_global_state( struct dc *dc, @@ -3757,4 +3968,4 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm( } return true; -} \ No newline at end of file +} diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 6409b8d8ff71..a4540f83aae5 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1298,6 +1298,12 @@ enum dc_status dc_validate_plane(struct dc *dc, const struct dc_plane_state *pla void get_clock_requirements_for_state(struct dc_state *state, struct AsicStateEx *info); +enum dc_status dc_validate_with_context(struct dc *dc, + const struct dc_validation_set set[], + int set_count, + struct dc_state *context, + bool fast_validate); + bool dc_set_generic_gpio_for_stereo(bool enable, struct gpio_service *gpio_service); From b2415df0afba5a114cececdb556f74b3d7965aa8 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 11 Aug 2023 16:07:01 -0500 Subject: [PATCH 0213/2093] drm/amd/display: Handle seamless boot stream commit 170390e587a69b2a24abac39eb3ae6ec28a4d7f2 upstream A seamless boot stream has hardware resources assigned to it, and adding a new stream means rebuilding the current assignment. It is desirable to avoid this situation since it may cause light-up issues on the VGA monitor on USB-C. This commit swaps the seamless boot stream to pipe 0 (if necessary) to ensure that the pipe context matches. Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Co-developed-by: Aurabindo Pillai Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 613db2da353a..66923f51037a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -2788,6 +2788,21 @@ enum dc_status dc_validate_with_context(struct dc *dc, goto fail; } + /* Swap seamless boot stream to pipe 0 (if needed) to ensure pipe_ctx + * matches. This may change in the future if seamless_boot_stream can be + * multiple. + */ + for (i = 0; i < add_streams_count; i++) { + mark_seamless_boot_stream(dc, add_streams[i]); + if (add_streams[i]->apply_seamless_boot_optimization && i != 0) { + struct dc_stream_state *temp = add_streams[0]; + + add_streams[0] = add_streams[i]; + add_streams[i] = temp; + break; + } + } + /* Add new streams and then add all planes for the new stream */ for (i = 0; i < add_streams_count; i++) { calculate_phy_pix_clks(add_streams[i]); From 4fe91c51aa936779edcae5943b1e621047fe2c2d Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 11 Aug 2023 16:07:02 -0500 Subject: [PATCH 0214/2093] drm/amd/display: Update OTG instance in the commit stream commit eef019eabc3cd0fddcffefbf67806a4d8cca29bb upstream OTG instance is not updated in dc_commit_state_no_check for newly committed streams because mode_change is not set. Notice that OTG update is part of the software state, and after hardware programming, it must be updated; for this reason, this commit updates the OTG offset right after hardware programming. Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Co-developed-by: Aurabindo Pillai Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 753c07ab54ed..5d0a44e2ef90 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1995,6 +1995,12 @@ enum dc_status dc_commit_streams(struct dc *dc, res = dc_commit_state_no_check(dc, context); + for (i = 0; i < stream_count; i++) { + for (j = 0; j < context->stream_count; j++) + if (streams[i]->stream_id == context->streams[j]->stream_id) + streams[i]->out.otg_offset = context->stream_status[j].primary_otg_inst; + } + fail: dc_release_state(context); From e93ae6e6b6605bfac458950920292311f7cf4a82 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 11 Aug 2023 16:07:03 -0500 Subject: [PATCH 0215/2093] drm/amd/display: Avoid ABM when ODM combine is enabled for eDP commit 7fffb03b4045c862f904a88b852dc509c4e46406 upstream ODM to combine on the eDP panel with ABM causes the color difference to the panel since the ABM module only sets one pipe. Hence, this commit blocks ABM in case of ODM combined on eDP. Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Co-developed-by: Aurabindo Pillai Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 5d0a44e2ef90..8c9843009176 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1996,9 +1996,19 @@ enum dc_status dc_commit_streams(struct dc *dc, res = dc_commit_state_no_check(dc, context); for (i = 0; i < stream_count; i++) { - for (j = 0; j < context->stream_count; j++) + for (j = 0; j < context->stream_count; j++) { if (streams[i]->stream_id == context->streams[j]->stream_id) streams[i]->out.otg_offset = context->stream_status[j].primary_otg_inst; + + if (dc_is_embedded_signal(streams[i]->signal)) { + struct dc_stream_status *status = dc_stream_get_status_from_state(context, streams[i]); + + if (dc->hwss.is_abm_supported) + status->is_abm_supported = dc->hwss.is_abm_supported(dc, context, streams[i]); + else + status->is_abm_supported = true; + } + } } fail: From 9caac2a9f69f58bed2ba35845a13fa7039d2e1d2 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 11 Aug 2023 16:07:04 -0500 Subject: [PATCH 0216/2093] drm/amd/display: Use update plane and stream routine for DCN32x commit dddde627807c22d6f15f4417eb395b13a1ca88f9 upstream Sub-viewport (Subvp) feature is used for changing MCLK without causing any display artifact, requiring special treatment from the plane and stream perspective since DC needs to read data from the cache when using subvp. However, the function dc_commit_updates_for_stream does not provide all the support needed by this feature which will make this function legacy at some point. For this reason, this commit enables dc_update_planes_and_stream for ASICs that support this feature but preserves the old behavior for other ASICs. However, dc_update_planes_and_stream should replace dc_commit_updates_for_stream for all ASICs since it does most of the tasks executed by dc_commit_updates_for_stream with other extra operations, but we need to run tests before making this change. Reviewed-by: Harry Wentland Signed-off-by: Rodrigo Siqueira Co-developed-by: Aurabindo Pillai Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8c9843009176..c9ed0346b88c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -4002,6 +4002,18 @@ void dc_commit_updates_for_stream(struct dc *dc, struct dc_context *dc_ctx = dc->ctx; int i, j; + /* TODO: Since change commit sequence can have a huge impact, + * we decided to only enable it for DCN3x. However, as soon as + * we get more confident about this change we'll need to enable + * the new sequence for all ASICs. + */ + if (dc->ctx->dce_version >= DCN_VERSION_3_2) { + dc_update_planes_and_stream(dc, srf_updates, + surface_count, stream, + stream_update); + return; + } + stream_status = dc_stream_get_status(stream); context = dc->current_state; From e61f0ad73668912feef345e35beeefcce5bbbd63 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Fri, 11 Aug 2023 16:07:05 -0500 Subject: [PATCH 0217/2093] drm/amd/display: Disable phantom OTG after enable for plane disable commit dc55b106ad477c67f969f3432d9070c6846fb557 upstream [Description] - Need to disable phantom OTG after it's enabled in order to restore it to it's original state. - If it's enabled and then an MCLK switch comes in we may not prefetch the correct data since the phantom OTG could already be in the middle of the frame. Reviewed-by: Jun Lei Acked-by: Alan Liu Signed-off-by: Alvin Lee Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 14 +++++++++++++- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c | 8 ++++++++ .../drm/amd/display/dc/inc/hw/timing_generator.h | 1 + 3 files changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index c9ed0346b88c..f16a9e410d16 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1079,6 +1079,7 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) struct dc_state *dangling_context = dc_create_state(dc); struct dc_state *current_ctx; struct pipe_ctx *pipe; + struct timing_generator *tg; if (dangling_context == NULL) return; @@ -1122,6 +1123,7 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) if (should_disable && old_stream) { pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + tg = pipe->stream_res.tg; /* When disabling plane for a phantom pipe, we must turn on the * phantom OTG so the disable programming gets the double buffer * update. Otherwise the pipe will be left in a partially disabled @@ -1129,7 +1131,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) * again for different use. */ if (old_stream->mall_stream_config.type == SUBVP_PHANTOM) { - pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); + if (tg->funcs->enable_crtc) + tg->funcs->enable_crtc(tg); } dc_rem_all_planes_for_stream(dc, old_stream, dangling_context); disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context); @@ -1146,6 +1149,15 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) dc->hwss.interdependent_update_lock(dc, dc->current_state, false); dc->hwss.post_unlock_program_front_end(dc, dangling_context); } + /* We need to put the phantom OTG back into it's default (disabled) state or we + * can get corruption when transition from one SubVP config to a different one. + * The OTG is set to disable on falling edge of VUPDATE so the plane disable + * will still get it's double buffer update. + */ + if (old_stream->mall_stream_config.type == SUBVP_PHANTOM) { + if (tg->funcs->disable_phantom_crtc) + tg->funcs->disable_phantom_crtc(tg); + } } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c index fe941b103de8..a974f86e718a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c @@ -167,6 +167,13 @@ static void optc32_phantom_crtc_post_enable(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); } +static void optc32_disable_phantom_otg(struct timing_generator *optc) +{ + struct optc *optc1 = DCN10TG_FROM_TG(optc); + + REG_UPDATE(OTG_CONTROL, OTG_MASTER_EN, 0); +} + static void optc32_set_odm_bypass(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing) { @@ -260,6 +267,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = { .enable_crtc = optc32_enable_crtc, .disable_crtc = optc32_disable_crtc, .phantom_crtc_post_enable = optc32_phantom_crtc_post_enable, + .disable_phantom_crtc = optc32_disable_phantom_otg, /* used by enable_timing_synchronization. Not need for FPGA */ .is_counter_moving = optc1_is_counter_moving, .get_position = optc1_get_position, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index f96fb425345e..974f2c118a44 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -184,6 +184,7 @@ struct timing_generator_funcs { bool (*disable_crtc)(struct timing_generator *tg); #ifdef CONFIG_DRM_AMD_DC_DCN void (*phantom_crtc_post_enable)(struct timing_generator *tg); + void (*disable_phantom_crtc)(struct timing_generator *tg); #endif bool (*immediate_disable_crtc)(struct timing_generator *tg); bool (*is_counter_moving)(struct timing_generator *tg); From 647e12741e6d16eccb679d2fefa7ec71496b6337 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Fri, 11 Aug 2023 16:07:06 -0500 Subject: [PATCH 0218/2093] drm/amd/display: Retain phantom plane/stream if validation fails commit 9b216b7e38f5381bcc3ad21c5ac614aa577ab8f2 upstream [Description] - If we fail validation, we should retain the phantom stream/planes - Full updates assume that phantom pipes will be fully removed, but if validation fails we keep the phantom pipes - Therefore we have to retain the plane/stream if validation fails (since the refcount is decremented before validation, and the expectation is that it's fully freed when the old dc_state is released) Reviewed-by: Jun Lei Acked-by: Brian Chang Signed-off-by: Alvin Lee Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 13 +++++++++++ .../drm/amd/display/dc/dcn32/dcn32_resource.c | 22 +++++++++++++++++++ .../drm/amd/display/dc/dcn32/dcn32_resource.h | 3 +++ .../amd/display/dc/dcn321/dcn321_resource.c | 1 + .../gpu/drm/amd/display/dc/inc/core_types.h | 1 + 5 files changed, 40 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f16a9e410d16..674ab6d9b31e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3149,6 +3149,19 @@ static bool update_planes_and_stream_state(struct dc *dc, if (update_type == UPDATE_TYPE_FULL) { if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { + /* For phantom pipes we remove and create a new set of phantom pipes + * for each full update (because we don't know if we'll need phantom + * pipes until after the first round of validation). However, if validation + * fails we need to keep the existing phantom pipes (because we don't update + * the dc->current_state). + * + * The phantom stream/plane refcount is decremented for validation because + * we assume it'll be removed (the free comes when the dc_state is freed), + * but if validation fails we have to increment back the refcount so it's + * consistent. + */ + if (dc->res_pool->funcs->retain_phantom_pipes) + dc->res_pool->funcs->retain_phantom_pipes(dc, dc->current_state); BREAK_TO_DEBUGGER(); goto fail; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 814620e6638f..2b8700b291a4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1719,6 +1719,27 @@ static struct dc_stream_state *dcn32_enable_phantom_stream(struct dc *dc, return phantom_stream; } +void dcn32_retain_phantom_pipes(struct dc *dc, struct dc_state *context) +{ + int i; + struct dc_plane_state *phantom_plane = NULL; + struct dc_stream_state *phantom_stream = NULL; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->top_pipe && !pipe->prev_odm_pipe && + pipe->plane_state && pipe->stream && + pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) { + phantom_plane = pipe->plane_state; + phantom_stream = pipe->stream; + + dc_plane_state_retain(phantom_plane); + dc_stream_retain(phantom_stream); + } + } +} + // return true if removed piped from ctx, false otherwise bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context) { @@ -2035,6 +2056,7 @@ static struct resource_funcs dcn32_res_pool_funcs = { .update_soc_for_wm_a = dcn30_update_soc_for_wm_a, .add_phantom_pipes = dcn32_add_phantom_pipes, .remove_phantom_pipes = dcn32_remove_phantom_pipes, + .retain_phantom_pipes = dcn32_retain_phantom_pipes, }; static uint32_t read_pipe_fuses(struct dc_context *ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index 615244a1f95d..026cf13d203f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -83,6 +83,9 @@ bool dcn32_release_post_bldn_3dlut( bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context); +void dcn32_retain_phantom_pipes(struct dc *dc, + struct dc_state *context); + void dcn32_add_phantom_pipes(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index 213ff3672bd5..aed92ced7b76 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -1619,6 +1619,7 @@ static struct resource_funcs dcn321_res_pool_funcs = { .update_soc_for_wm_a = dcn30_update_soc_for_wm_a, .add_phantom_pipes = dcn32_add_phantom_pipes, .remove_phantom_pipes = dcn32_remove_phantom_pipes, + .retain_phantom_pipes = dcn32_retain_phantom_pipes, }; static uint32_t read_pipe_fuses(struct dc_context *ctx) diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 9498105c98ab..5fa7c4772af4 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -234,6 +234,7 @@ struct resource_funcs { unsigned int index); bool (*remove_phantom_pipes)(struct dc *dc, struct dc_state *context); + void (*retain_phantom_pipes)(struct dc *dc, struct dc_state *context); void (*get_panel_config_defaults)(struct dc_panel_config *panel_config); }; From 07152d9e87ef7759955446989693bbf5e8e80b7c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 11 Aug 2023 16:07:07 -0500 Subject: [PATCH 0219/2093] drm/amd/display: fix the build when DRM_AMD_DC_DCN is not set commit 5ca9b33ece9aa048b6ec9411f054e1b781662327 upstream Move the new callback outside of the guard. Fixes: dc55b106ad47 ("drm/amd/display: Disable phantom OTG after enable for plane disable") CC: Alvin Lee CC: Alan Liu Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index 974f2c118a44..789cf9406ca5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -184,8 +184,8 @@ struct timing_generator_funcs { bool (*disable_crtc)(struct timing_generator *tg); #ifdef CONFIG_DRM_AMD_DC_DCN void (*phantom_crtc_post_enable)(struct timing_generator *tg); - void (*disable_phantom_crtc)(struct timing_generator *tg); #endif + void (*disable_phantom_crtc)(struct timing_generator *tg); bool (*immediate_disable_crtc)(struct timing_generator *tg); bool (*is_counter_moving)(struct timing_generator *tg); void (*get_position)(struct timing_generator *tg, From b61a06eca15cc4fd6ff50540ba3bbdea76e52c6b Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Fri, 11 Aug 2023 16:07:08 -0500 Subject: [PATCH 0220/2093] drm/amd/display: trigger timing sync only if TG is running commit 6066aaf74f510fc171dbe9375153aee2d60d37aa upstream [Why&How] If the timing generator isnt running, it does not make sense to trigger a sync on the corresponding OTG. Check this condition before starting. Otherwise, this will cause error like: *ERROR* GSL: Timeout on reset trigger! Fixes: dc55b106ad47 ("drm/amd/display: Disable phantom OTG after enable for plane disable") Signed-off-by: Aurabindo Pillai Reviewed-by: Rodrigo Siqueira Signed-off-by: Alex Deucher [ NOTE: This is also 5f9f97c02dd2 ("drm/amd/display: trigger timing sync only if TG is running") ] Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index a6fde27d1347..394027118963 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2284,6 +2284,12 @@ void dcn10_enable_timing_synchronization( opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); + + if (!tg->funcs->is_tg_enabled(tg)) { + DC_SYNC_INFO("Skipping timing sync on disabled OTG\n"); + return; + } + if (opp->funcs->opp_program_dpg_dimensions) opp->funcs->opp_program_dpg_dimensions(opp, width, 2*(height) + 1); } From 5aac2726b6930f9d5dffb1090ebfc0cdfad6a30c Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 12 Aug 2023 07:16:11 -0600 Subject: [PATCH 0221/2093] io_uring: correct check for O_TMPFILE Commit 72dbde0f2afbe4af8e8595a89c650ae6b9d9c36f upstream. O_TMPFILE is actually __O_TMPFILE|O_DIRECTORY. This means that the old check for whether RESOLVE_CACHED can be used would incorrectly think that O_DIRECTORY could not be used with RESOLVE_CACHED. Cc: stable@vger.kernel.org # v5.12+ Fixes: 3a81fd02045c ("io_uring: enable LOOKUP_CACHED path resolution for filename lookups") Signed-off-by: Aleksa Sarai Link: https://lore.kernel.org/r/20230807-resolve_cached-o_tmpfile-v3-1-e49323e1ef6f@cyphar.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/openclose.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/io_uring/openclose.c b/io_uring/openclose.c index 67178e4bb282..008990e58180 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -110,9 +110,11 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags) if (issue_flags & IO_URING_F_NONBLOCK) { /* * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, - * it'll always -EAGAIN + * it'll always -EAGAIN. Note that we test for __O_TMPFILE + * because O_TMPFILE includes O_DIRECTORY, which isn't a flag + * we need to force async for. */ - if (open->how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + if (open->how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; op.lookup_flags |= LOOKUP_CACHED; op.open_flag |= O_NONBLOCK; From 366563c14f1f8871fcf590d23e2f645fc81340d9 Mon Sep 17 00:00:00 2001 From: Yiyuan Guo Date: Fri, 30 Jun 2023 22:37:19 +0800 Subject: [PATCH 0222/2093] iio: cros_ec: Fix the allocation size for cros_ec_command commit 8a4629055ef55177b5b63dab1ecce676bd8cccdd upstream. The struct cros_ec_command contains several integer fields and a trailing array. An allocation size neglecting the integer fields can lead to buffer overrun. Reviewed-by: Tzung-Bi Shih Signed-off-by: Yiyuan Guo Fixes: 974e6f02e27e ("iio: cros_ec_sensors_core: Add common functions for the ChromeOS EC Sensor Hub.") Link: https://lore.kernel.org/r/20230630143719.1513906-1-yguoaz@gmail.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index 05a28d353e34..d98f7e4d202c 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -253,7 +253,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, platform_set_drvdata(pdev, indio_dev); state->ec = ec->ec_dev; - state->msg = devm_kzalloc(&pdev->dev, + state->msg = devm_kzalloc(&pdev->dev, sizeof(*state->msg) + max((u16)sizeof(struct ec_params_motion_sense), state->ec->max_response), GFP_KERNEL); if (!state->msg) From 5e1ed816a0e1dd71025a8484dfefebf792fcafee Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 18 Jul 2023 10:02:18 +0300 Subject: [PATCH 0223/2093] iio: frequency: admv1013: propagate errors from regulator_get_voltage() commit 507397d19b5a296aa339f7a1bd16284f668a1906 upstream. The regulator_get_voltage() function returns negative error codes. This function saves it to an unsigned int and then does some range checking and, since the error code falls outside the correct range, it returns -EINVAL. Beyond the messiness, this is bad because the regulator_get_voltage() function can return -EPROBE_DEFER and it's important to propagate that back properly so it can be handled. Fixes: da35a7b526d9 ("iio: frequency: admv1013: add support for ADMV1013") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/ce75aac3-2aba-4435-8419-02e59fdd862b@moroto.mountain Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/frequency/admv1013.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index ed8167271358..e6311213f3e8 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -344,9 +344,12 @@ static int admv1013_update_quad_filters(struct admv1013_state *st) static int admv1013_update_mixer_vgate(struct admv1013_state *st) { - unsigned int vcm, mixer_vgate; + unsigned int mixer_vgate; + int vcm; vcm = regulator_get_voltage(st->reg); + if (vcm < 0) + return vcm; if (vcm < 1800000) mixer_vgate = (2389 * vcm / 1000000 + 8100) / 100; From 2f8ebbd0f03e5e494c2ce23ee4a99382da663183 Mon Sep 17 00:00:00 2001 From: Alisa Roman Date: Wed, 14 Jun 2023 18:52:43 +0300 Subject: [PATCH 0224/2093] iio: adc: ad7192: Fix ac excitation feature commit 6bc471b6c3aeaa7b95d1b86a1bb8d91a3c341fa5 upstream. AC excitation enable feature exposed to user on AD7192, allowing a bit which should be 0 to be set. This feature is specific only to AD7195. AC excitation attribute moved accordingly. In the AD7195 documentation, the AC excitation enable bit is on position 22 in the Configuration register. ACX macro changed to match correct register and bit. Note that the fix tag is for the commit that moved the driver out of staging. Fixes: b581f748cce0 ("staging: iio: adc: ad7192: move out of staging") Signed-off-by: Alisa Roman Cc: stable@vger.kernel.org Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230614155242.160296-1-alisa.roman@analog.com Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ad7192.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 8720ac43a4a4..80eff7090f14 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -62,7 +62,6 @@ #define AD7192_MODE_STA_MASK BIT(20) /* Status Register transmission Mask */ #define AD7192_MODE_CLKSRC(x) (((x) & 0x3) << 18) /* Clock Source Select */ #define AD7192_MODE_SINC3 BIT(15) /* SINC3 Filter Select */ -#define AD7192_MODE_ACX BIT(14) /* AC excitation enable(AD7195 only)*/ #define AD7192_MODE_ENPAR BIT(13) /* Parity Enable */ #define AD7192_MODE_CLKDIV BIT(12) /* Clock divide by 2 (AD7190/2 only)*/ #define AD7192_MODE_SCYCLE BIT(11) /* Single cycle conversion */ @@ -91,6 +90,7 @@ /* Configuration Register Bit Designations (AD7192_REG_CONF) */ #define AD7192_CONF_CHOP BIT(23) /* CHOP enable */ +#define AD7192_CONF_ACX BIT(22) /* AC excitation enable(AD7195 only) */ #define AD7192_CONF_REFSEL BIT(20) /* REFIN1/REFIN2 Reference Select */ #define AD7192_CONF_CHAN(x) ((x) << 8) /* Channel select */ #define AD7192_CONF_CHAN_MASK (0x7FF << 8) /* Channel select mask */ @@ -473,7 +473,7 @@ static ssize_t ad7192_show_ac_excitation(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7192_state *st = iio_priv(indio_dev); - return sysfs_emit(buf, "%d\n", !!(st->mode & AD7192_MODE_ACX)); + return sysfs_emit(buf, "%d\n", !!(st->conf & AD7192_CONF_ACX)); } static ssize_t ad7192_show_bridge_switch(struct device *dev, @@ -514,13 +514,13 @@ static ssize_t ad7192_set(struct device *dev, ad_sd_write_reg(&st->sd, AD7192_REG_GPOCON, 1, st->gpocon); break; - case AD7192_REG_MODE: + case AD7192_REG_CONF: if (val) - st->mode |= AD7192_MODE_ACX; + st->conf |= AD7192_CONF_ACX; else - st->mode &= ~AD7192_MODE_ACX; + st->conf &= ~AD7192_CONF_ACX; - ad_sd_write_reg(&st->sd, AD7192_REG_MODE, 3, st->mode); + ad_sd_write_reg(&st->sd, AD7192_REG_CONF, 3, st->conf); break; default: ret = -EINVAL; @@ -580,12 +580,11 @@ static IIO_DEVICE_ATTR(bridge_switch_en, 0644, static IIO_DEVICE_ATTR(ac_excitation_en, 0644, ad7192_show_ac_excitation, ad7192_set, - AD7192_REG_MODE); + AD7192_REG_CONF); static struct attribute *ad7192_attributes[] = { &iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr, &iio_dev_attr_bridge_switch_en.dev_attr.attr, - &iio_dev_attr_ac_excitation_en.dev_attr.attr, NULL }; @@ -596,6 +595,7 @@ static const struct attribute_group ad7192_attribute_group = { static struct attribute *ad7195_attributes[] = { &iio_dev_attr_filter_low_pass_3db_frequency_available.dev_attr.attr, &iio_dev_attr_bridge_switch_en.dev_attr.attr, + &iio_dev_attr_ac_excitation_en.dev_attr.attr, NULL }; From 77b689cc27d489b75d33f1a368356d70eb0ce08c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Mon, 19 Jun 2023 16:12:39 +0200 Subject: [PATCH 0225/2093] iio: adc: ina2xx: avoid NULL pointer dereference on OF device match MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a41e19cc0d6b6a445a4133170b90271e4a2553dc upstream. The affected lines were resulting in a NULL pointer dereference on our platform because the device tree contained the following list of compatible strings: power-sensor@40 { compatible = "ti,ina232", "ti,ina231"; ... }; Since the driver doesn't declare a compatible string "ti,ina232", the OF matching succeeds on "ti,ina231". But the I2C device ID info is populated via the first compatible string, cf. modalias population in of_i2c_get_board_info(). Since there is no "ina232" entry in the legacy I2C device ID table either, the struct i2c_device_id *id pointer in the probe function is NULL. Fix this by using the already populated type variable instead, which points to the proper driver data. Since the name is also wanted, add a generic one to the ina2xx_config table. Signed-off-by: Alvin Šipraga Fixes: c43a102e67db ("iio: ina2xx: add support for TI INA2xx Power Monitors") Link: https://lore.kernel.org/r/20230619141239.2257392-1-alvin@pqrs.dk Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ina2xx-adc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c index 910e7e965fc4..74092f3836b8 100644 --- a/drivers/iio/adc/ina2xx-adc.c +++ b/drivers/iio/adc/ina2xx-adc.c @@ -124,6 +124,7 @@ static const struct regmap_config ina2xx_regmap_config = { enum ina2xx_ids { ina219, ina226 }; struct ina2xx_config { + const char *name; u16 config_default; int calibration_value; int shunt_voltage_lsb; /* nV */ @@ -155,6 +156,7 @@ struct ina2xx_chip_info { static const struct ina2xx_config ina2xx_config[] = { [ina219] = { + .name = "ina219", .config_default = INA219_CONFIG_DEFAULT, .calibration_value = 4096, .shunt_voltage_lsb = 10000, @@ -164,6 +166,7 @@ static const struct ina2xx_config ina2xx_config[] = { .chip_id = ina219, }, [ina226] = { + .name = "ina226", .config_default = INA226_CONFIG_DEFAULT, .calibration_value = 2048, .shunt_voltage_lsb = 2500, @@ -996,7 +999,7 @@ static int ina2xx_probe(struct i2c_client *client, /* Patch the current config register with default. */ val = chip->config->config_default; - if (id->driver_data == ina226) { + if (type == ina226) { ina226_set_average(chip, INA226_DEFAULT_AVG, &val); ina226_set_int_time_vbus(chip, INA226_DEFAULT_IT, &val); ina226_set_int_time_vshunt(chip, INA226_DEFAULT_IT, &val); @@ -1015,7 +1018,7 @@ static int ina2xx_probe(struct i2c_client *client, } indio_dev->modes = INDIO_DIRECT_MODE; - if (id->driver_data == ina226) { + if (type == ina226) { indio_dev->channels = ina226_channels; indio_dev->num_channels = ARRAY_SIZE(ina226_channels); indio_dev->info = &ina226_info; @@ -1024,7 +1027,7 @@ static int ina2xx_probe(struct i2c_client *client, indio_dev->num_channels = ARRAY_SIZE(ina219_channels); indio_dev->info = &ina219_info; } - indio_dev->name = id->name; + indio_dev->name = id ? id->name : chip->config->name; ret = devm_iio_kfifo_buffer_setup(&client->dev, indio_dev, &ina2xx_setup_ops); From f11a26633eb6d3bb24a10b1bacc4e4a9b0c6389f Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Sun, 25 Jun 2023 15:49:37 +0000 Subject: [PATCH 0226/2093] binder: fix memory leak in binder_init() commit adb9743d6a08778b78d62d16b4230346d3508986 upstream. In binder_init(), the destruction of binder_alloc_shrinker_init() is not performed in the wrong path, which will cause memory leaks. So this commit introduces binder_alloc_shrinker_exit() and calls it in the wrong path to fix that. Signed-off-by: Qi Zheng Acked-by: Carlos Llamas Fixes: f2517eb76f1f ("android: binder: Add global lru shrinker to binder") Cc: stable Link: https://lore.kernel.org/r/20230625154937.64316-1-qi.zheng@linux.dev Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 1 + drivers/android/binder_alloc.c | 6 ++++++ drivers/android/binder_alloc.h | 1 + 3 files changed, 8 insertions(+) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index e374a8a2da46..e4a6da81cd4b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -6602,6 +6602,7 @@ static int __init binder_init(void) err_alloc_device_names_failed: debugfs_remove_recursive(binder_debugfs_dir_entry_root); + binder_alloc_shrinker_exit(); return ret; } diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 4fb89ef067d5..cd87f12733f2 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1087,6 +1087,12 @@ int binder_alloc_shrinker_init(void) return ret; } +void binder_alloc_shrinker_exit(void) +{ + unregister_shrinker(&binder_shrinker); + list_lru_destroy(&binder_alloc_lru); +} + /** * check_buffer() - verify that buffer/offset is safe to access * @alloc: binder_alloc for this proc diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 138d1d5af9ce..dc1e2b01dd64 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -129,6 +129,7 @@ extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, int pid); extern void binder_alloc_init(struct binder_alloc *alloc); extern int binder_alloc_shrinker_init(void); +extern void binder_alloc_shrinker_exit(void); extern void binder_alloc_vma_close(struct binder_alloc *alloc); extern struct binder_buffer * binder_alloc_prepare_to_free(struct binder_alloc *alloc, From 8ee39ec479147e29af704639f8e55fce246ed2d9 Mon Sep 17 00:00:00 2001 From: Ricky WU Date: Tue, 25 Jul 2023 09:10:54 +0000 Subject: [PATCH 0227/2093] misc: rtsx: judge ASPM Mode to set PETXCFG Reg commit 101bd907b4244a726980ee67f95ed9cafab6ff7a upstream. ASPM Mode is ASPM_MODE_CFG need to judge the value of clkreq_0 to set HIGH or LOW, if the ASPM Mode is ASPM_MODE_REG always set to HIGH during the initialization. Cc: stable@vger.kernel.org Signed-off-by: Ricky Wu Link: https://lore.kernel.org/r/52906c6836374c8cb068225954c5543a@realtek.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/rts5227.c | 2 +- drivers/misc/cardreader/rts5228.c | 18 ------------------ drivers/misc/cardreader/rts5249.c | 3 +-- drivers/misc/cardreader/rts5260.c | 18 ------------------ drivers/misc/cardreader/rts5261.c | 18 ------------------ drivers/misc/cardreader/rtsx_pcr.c | 5 ++++- 6 files changed, 6 insertions(+), 58 deletions(-) diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index d676cf63a966..3dae5e3a1697 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -195,7 +195,7 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) } } - if (option->force_clkreq_0) + if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index cfebad51d1d8..f4ab09439da7 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -435,17 +435,10 @@ static void rts5228_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1, CD_RESUME_EN_MASK, CD_RESUME_EN_MASK); @@ -476,17 +469,6 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index 91d240dd68fa..47ab72a43256 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -327,12 +327,11 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) } } - /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced * to drive low, and we forcibly request clock. */ - if (option->force_clkreq_0) + if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) rtsx_pci_write_register(pcr, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 9b42b20a3e5a..79b18f6f73a8 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -517,17 +517,10 @@ static void rts5260_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; /* Set mcu_cnt to 7 to ensure data can be sampled properly */ rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07); @@ -546,17 +539,6 @@ static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) rts5260_init_hw(pcr); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00); return 0; diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index b1e76030cafd..94af6bf8a25a 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -498,17 +498,10 @@ static void rts5261_init_from_cfg(struct rtsx_pcr *pcr) option->ltr_enabled = false; } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; } static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) { - struct rtsx_cr_option *option = &pcr->option; u32 val; rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1, @@ -554,17 +547,6 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); - /* - * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced - * to drive low, and we forcibly request clock. - */ - if (option->force_clkreq_0) - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); - else - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 32b7783e9d4f..a3f4b52bb159 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1326,8 +1326,11 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) return err; } - if (pcr->aspm_mode == ASPM_MODE_REG) + if (pcr->aspm_mode == ASPM_MODE_REG) { rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + } /* No CD interrupt if probing driver with card inserted. * So we need to initialize pcr->card_exist here. From 0d2d5282d39aed6f27dfe1ed60a5f3934ebd21cd Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 2 Aug 2023 13:49:02 -0400 Subject: [PATCH 0228/2093] usb-storage: alauda: Fix uninit-value in alauda_check_media() commit a6ff6e7a9dd69364547751db0f626a10a6d628d2 upstream. Syzbot got KMSAN to complain about access to an uninitialized value in the alauda subdriver of usb-storage: BUG: KMSAN: uninit-value in alauda_transport+0x462/0x57f0 drivers/usb/storage/alauda.c:1137 CPU: 0 PID: 12279 Comm: usb-storage Not tainted 5.3.0-rc7+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x191/0x1f0 lib/dump_stack.c:113 kmsan_report+0x13a/0x2b0 mm/kmsan/kmsan_report.c:108 __msan_warning+0x73/0xe0 mm/kmsan/kmsan_instr.c:250 alauda_check_media+0x344/0x3310 drivers/usb/storage/alauda.c:460 The problem is that alauda_check_media() doesn't verify that its USB transfer succeeded before trying to use the received data. What should happen if the transfer fails isn't entirely clear, but a reasonably conservative approach is to pretend that no media is present. A similar problem exists in a usb_stor_dbg() call in alauda_get_media_status(). In this case, when an error occurs the call is redundant, because usb_stor_ctrl_transfer() already will print a debugging message. Finally, unrelated to the uninitialized memory access, is the fact that alauda_check_media() performs DMA to a buffer on the stack. Fortunately usb-storage provides a general purpose DMA-able buffer for uses like this. We'll use it instead. Reported-and-tested-by: syzbot+e7d46eb426883fb97efd@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/0000000000007d25ff059457342d@google.com/T/ Suggested-by: Christophe JAILLET Signed-off-by: Alan Stern Fixes: e80b0fade09e ("[PATCH] USB Storage: add alauda support") Cc: Link: https://lore.kernel.org/r/693d5d5e-f09b-42d0-8ed9-1f96cd30bcce@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/alauda.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 5e912dd29b4c..115f05a6201a 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -318,7 +318,8 @@ static int alauda_get_media_status(struct us_data *us, unsigned char *data) rc = usb_stor_ctrl_transfer(us, us->recv_ctrl_pipe, command, 0xc0, 0, 1, data, 2); - usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]); + if (rc == USB_STOR_XFER_GOOD) + usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]); return rc; } @@ -454,9 +455,14 @@ static int alauda_init_media(struct us_data *us) static int alauda_check_media(struct us_data *us) { struct alauda_info *info = (struct alauda_info *) us->extra; - unsigned char status[2]; + unsigned char *status = us->iobuf; + int rc; - alauda_get_media_status(us, status); + rc = alauda_get_media_status(us, status); + if (rc != USB_STOR_XFER_GOOD) { + status[0] = 0xF0; /* Pretend there's no media */ + status[1] = 0; + } /* Check for no media or door open */ if ((status[0] & 0x80) || ((status[0] & 0x1F) == 0x10) From d2a4ded0ee9902bb62c1f58c6289fbaf1990249c Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Tue, 1 Aug 2023 12:26:58 -0700 Subject: [PATCH 0229/2093] usb: dwc3: Properly handle processing of pending events commit 3ddaa6a274578e23745b7466346fc2650df8f959 upstream. If dwc3 is runtime suspended we defer processing the event buffer until resume, by setting the pending_events flag. Set this flag before triggering resume to avoid race with the runtime resume callback. While handling the pending events, in addition to checking the event buffer we also need to process it. Handle this by explicitly calling dwc3_thread_interrupt(). Also balance the runtime pm get() operation that triggered this processing. Cc: stable@vger.kernel.org Fixes: fc8bb91bc83e ("usb: dwc3: implement runtime PM") Signed-off-by: Elson Roy Serrao Acked-by: Thinh Nguyen Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230801192658.19275-1-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c3590a0c4203..137602d9076f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4342,9 +4342,14 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) u32 count; if (pm_runtime_suspended(dwc->dev)) { + dwc->pending_events = true; + /* + * Trigger runtime resume. The get() function will be balanced + * after processing the pending events in dwc3_process_pending + * events(). + */ pm_runtime_get(dwc->dev); disable_irq_nosync(dwc->irq_gadget); - dwc->pending_events = true; return IRQ_HANDLED; } @@ -4609,6 +4614,8 @@ void dwc3_gadget_process_pending_events(struct dwc3 *dwc) { if (dwc->pending_events) { dwc3_interrupt(dwc->irq_gadget, dwc->ev_buf); + dwc3_thread_interrupt(dwc->irq_gadget, dwc->ev_buf); + pm_runtime_put(dwc->dev); dwc->pending_events = false; enable_irq(dwc->irq_gadget); } From bed19d95fcb9c98dfaa9585922b39a2dfba7898d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 29 Jul 2023 10:59:38 -0400 Subject: [PATCH 0230/2093] USB: Gadget: core: Help prevent panic during UVC unconfigure commit 65dadb2beeb7360232b09ebc4585b54475dfee06 upstream. Avichal Rakesh reported a kernel panic that occurred when the UVC gadget driver was removed from a gadget's configuration. The panic involves a somewhat complicated interaction between the kernel driver and a userspace component (as described in the Link tag below), but the analysis did make one thing clear: The Gadget core should accomodate gadget drivers calling usb_gadget_deactivate() as part of their unbind procedure. Currently this doesn't work. gadget_unbind_driver() calls driver->unbind() while holding the udc->connect_lock mutex, and usb_gadget_deactivate() attempts to acquire that mutex, which will result in a deadlock. The simple fix is for gadget_unbind_driver() to release the mutex when invoking the ->unbind() callback. There is no particular reason for it to be holding the mutex at that time, and the mutex isn't held while the ->bind() callback is invoked. So we'll drop the mutex before performing the unbind callback and reacquire it afterward. We'll also add a couple of comments to usb_gadget_activate() and usb_gadget_deactivate(). Because they run in process context they must not be called from a gadget driver's ->disconnect() callback, which (according to the kerneldoc for struct usb_gadget_driver in include/linux/usb/gadget.h) may run in interrupt context. This may help prevent similar bugs from arising in the future. Reported-and-tested-by: Avichal Rakesh Signed-off-by: Alan Stern Fixes: 286d9975a838 ("usb: gadget: udc: core: Prevent soft_connect_store() race") Link: https://lore.kernel.org/linux-usb/4d7aa3f4-22d9-9f5a-3d70-1bd7148ff4ba@google.com/ Cc: Badhri Jagan Sridharan Cc: Link: https://lore.kernel.org/r/48b2f1f1-0639-46bf-bbfc-98cb05a24914@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 139f471894fb..316e9cc3987b 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -795,6 +795,9 @@ EXPORT_SYMBOL_GPL(usb_gadget_disconnect); * usb_gadget_activate() is called. For example, user mode components may * need to be activated before the system can talk to hosts. * + * This routine may sleep; it must not be called in interrupt context + * (such as from within a gadget driver's disconnect() callback). + * * Returns zero on success, else negative errno. */ int usb_gadget_deactivate(struct usb_gadget *gadget) @@ -833,6 +836,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_deactivate); * This routine activates gadget which was previously deactivated with * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. * + * This routine may sleep; it must not be called in interrupt context. + * * Returns zero on success, else negative errno. */ int usb_gadget_activate(struct usb_gadget *gadget) @@ -1611,7 +1616,11 @@ static void gadget_unbind_driver(struct device *dev) usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); + mutex_unlock(&udc->connect_lock); + udc->driver->unbind(gadget); + + mutex_lock(&udc->connect_lock); usb_gadget_udc_stop_locked(udc); mutex_unlock(&udc->connect_lock); From e3b37754988a228d3443e07c4cc2f2a98cf698f6 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Tue, 1 Aug 2023 14:33:52 +0530 Subject: [PATCH 0231/2093] usb: common: usb-conn-gpio: Prevent bailing out if initial role is none commit 8e21a620c7e6e00347ade1a6ed4967b359eada5a upstream. Currently if we bootup a device without cable connected, then usb-conn-gpio won't call set_role() because last_role is same as current role. This happens since last_role gets initialised to zero during the probe. To avoid this, add a new flag initial_detection into struct usb_conn_info, which prevents bailing out during initial detection. Cc: # 5.4 Fixes: 4602f3bff266 ("usb: common: add USB GPIO based connection detection driver") Signed-off-by: Prashanth K Tested-by: AngeloGioacchino Del Regno Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/1690880632-12588-1-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/usb-conn-gpio.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index e20874caba36..3f5180d64931 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -42,6 +42,7 @@ struct usb_conn_info { struct power_supply_desc desc; struct power_supply *charger; + bool initial_detection; }; /* @@ -86,11 +87,13 @@ static void usb_conn_detect_cable(struct work_struct *work) dev_dbg(info->dev, "role %s -> %s, gpios: id %d, vbus %d\n", usb_role_string(info->last_role), usb_role_string(role), id, vbus); - if (info->last_role == role) { + if (!info->initial_detection && info->last_role == role) { dev_warn(info->dev, "repeated role: %s\n", usb_role_string(role)); return; } + info->initial_detection = false; + if (info->last_role == USB_ROLE_HOST && info->vbus) regulator_disable(info->vbus); @@ -258,6 +261,7 @@ static int usb_conn_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, true); /* Perform initial detection */ + info->initial_detection = true; usb_conn_queue_dwork(info, 0); return 0; From 57b8f5fb8f17e5b32e08ed6e5d136eaea3c7292e Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Wed, 12 Jul 2023 08:57:22 +0000 Subject: [PATCH 0232/2093] usb: typec: tcpm: Fix response to vsafe0V event commit 4270d2b4845e820b274702bfc2a7140f69e4d19d upstream. Do not transition to SNK_UNATTACHED state when receiving vsafe0v event while in SNK_HARD_RESET_WAIT_VBUS. Ignore VBUS off events as well as in some platforms VBUS off can be signalled more than once. [143515.364753] Requesting mux state 1, usb-role 2, orientation 2 [143515.365520] pending state change SNK_HARD_RESET_SINK_OFF -> SNK_HARD_RESET_SINK_ON @ 650 ms [rev3 HARD_RESET] [143515.632281] CC1: 0 -> 0, CC2: 3 -> 0 [state SNK_HARD_RESET_SINK_OFF, polarity 1, disconnected] [143515.637214] VBUS on [143515.664985] VBUS off [143515.664992] state change SNK_HARD_RESET_SINK_OFF -> SNK_HARD_RESET_WAIT_VBUS [rev3 HARD_RESET] [143515.665564] VBUS VSAFE0V [143515.665566] state change SNK_HARD_RESET_WAIT_VBUS -> SNK_UNATTACHED [rev3 HARD_RESET] Fixes: 28b43d3d746b ("usb: typec: tcpm: Introduce vsafe0v for vbus") Cc: Signed-off-by: Badhri Jagan Sridharan Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230712085722.1414743-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 524099634a1d..d5950ef9d1f3 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5322,6 +5322,10 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port) /* Do nothing, vbus drop expected */ break; + case SNK_HARD_RESET_WAIT_VBUS: + /* Do nothing, its OK to receive vbus off events */ + break; + default: if (port->pwr_role == TYPEC_SINK && port->attached) tcpm_set_state(port, SNK_UNATTACHED, tcpm_wait_for_discharge(port)); @@ -5368,6 +5372,9 @@ static void _tcpm_pd_vbus_vsafe0v(struct tcpm_port *port) case SNK_DEBOUNCED: /*Do nothing, still waiting for VSAFE5V for connect */ break; + case SNK_HARD_RESET_WAIT_VBUS: + /* Do nothing, its OK to receive vbus off events */ + break; default: if (port->pwr_role == TYPEC_SINK && port->auto_vbus_discharge_enabled) tcpm_set_state(port, SNK_UNATTACHED, 0); From 6f75e09343549e9908bc88c88890f9a3759c8a04 Mon Sep 17 00:00:00 2001 From: RD Babiera Date: Wed, 26 Jul 2023 02:09:02 +0000 Subject: [PATCH 0233/2093] usb: typec: altmodes/displayport: Signal hpd when configuring pin assignment commit 5a5ccd61cfd76156cb3e0373c300c509d05448ce upstream. When connecting to some DisplayPort partners, the initial status update after entering DisplayPort Alt Mode notifies that the DFP_D/UFP_D is not in the connected state. This leads to sending a configure message that keeps the device in USB mode. The port partner then sets DFP_D/UFP_D to the connected state and HPD to high in the same Attention message. Currently, the HPD signal is dropped in order to handle configuration. This patch saves changes to the HPD signal when the device chooses to configure during dp_altmode_status_update, and invokes sysfs_notify if necessary for HPD after configuring. Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode") Cc: stable@vger.kernel.org Signed-off-by: RD Babiera Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230726020903.1409072-1-rdbabiera@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 7cdf83f4c811..7a3caf556dae 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -60,6 +60,7 @@ struct dp_altmode { enum dp_state state; bool hpd; + bool pending_hpd; struct mutex lock; /* device lock */ struct work_struct work; @@ -144,8 +145,13 @@ static int dp_altmode_status_update(struct dp_altmode *dp) dp->state = DP_STATE_EXIT; } else if (!(con & DP_CONF_CURRENTLY(dp->data.conf))) { ret = dp_altmode_configure(dp, con); - if (!ret) + if (!ret) { dp->state = DP_STATE_CONFIGURE; + if (dp->hpd != hpd) { + dp->hpd = hpd; + dp->pending_hpd = true; + } + } } else { if (dp->hpd != hpd) { drm_connector_oob_hotplug_event(dp->connector_fwnode); @@ -160,6 +166,16 @@ static int dp_altmode_configured(struct dp_altmode *dp) { sysfs_notify(&dp->alt->dev.kobj, "displayport", "configuration"); sysfs_notify(&dp->alt->dev.kobj, "displayport", "pin_assignment"); + /* + * If the DFP_D/UFP_D sends a change in HPD when first notifying the + * DisplayPort driver that it is connected, then we wait until + * configuration is complete to signal HPD. + */ + if (dp->pending_hpd) { + drm_connector_oob_hotplug_event(dp->connector_fwnode); + sysfs_notify(&dp->alt->dev.kobj, "displayport", "hpd"); + dp->pending_hpd = false; + } return dp_altmode_notify(dp); } From d93eeac34e75ccbdbfc90005914d32518624843a Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Wed, 9 Aug 2023 09:40:26 -0700 Subject: [PATCH 0234/2093] x86/srso: Fix build breakage with the LLVM linker commit cbe8ded48b939b9d55d2c5589ab56caa7b530709 upstream. The assertion added to verify the difference in bits set of the addresses of srso_untrain_ret_alias() and srso_safe_ret_alias() would fail to link in LLVM's ld.lld linker with the following error: ld.lld: error: ./arch/x86/kernel/vmlinux.lds:210: at least one side of the expression must be absolute ld.lld: error: ./arch/x86/kernel/vmlinux.lds:211: at least one side of the expression must be absolute Use ABSOLUTE to evaluate the expression referring to at least one of the symbols so that LLD can evaluate the linker script. Also, add linker version info to the comment about XOR being unsupported in either ld.bfd or ld.lld until somewhat recently. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Closes: https://lore.kernel.org/llvm/CA+G9fYsdUeNu-gwbs0+T6XHi4hYYk=Y9725-wFhZ7gJMspLDRA@mail.gmail.com/ Reported-by: Nathan Chancellor Reported-by: Daniel Kolesa Reported-by: Naresh Kamboju Suggested-by: Sven Volkinsfeld Signed-off-by: Nick Desaulniers Signed-off-by: Borislav Petkov (AMD) Link: https://github.com/ClangBuiltLinux/linux/issues/1907 Link: https://lore.kernel.org/r/20230809-gds-v1-1-eaac90b0cbcc@google.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/vmlinux.lds.S | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fd03f5a1f0ef..e6939ebb606a 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -514,11 +514,17 @@ INIT_PER_CPU(irq_stack_backing_store); #ifdef CONFIG_CPU_SRSO /* - * GNU ld cannot do XOR so do: (A | B) - (A & B) in order to compute the XOR + * GNU ld cannot do XOR until 2.41. + * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1 + * + * LLVM lld cannot do XOR until lld-17. + * https://github.com/llvm/llvm-project/commit/fae96104d4378166cbe5c875ef8ed808a356f3fb + * + * Instead do: (A | B) - (A & B) in order to compute the XOR * of the two function addresses: */ -. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) - - (srso_untrain_ret_alias & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), +. = ASSERT(((ABSOLUTE(srso_untrain_ret_alias) | srso_safe_ret_alias) - + (ABSOLUTE(srso_untrain_ret_alias) & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), "SRSO function pair won't alias"); #endif From 25085250a150da4599c3f8dd9db6b76dc864178a Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Fri, 11 Aug 2023 23:37:05 +0300 Subject: [PATCH 0235/2093] x86/cpu/amd: Enable Zenbleed fix for AMD Custom APU 0405 commit 6dbef74aeb090d6bee7d64ef3fa82ae6fa53f271 upstream. Commit 522b1d69219d ("x86/cpu/amd: Add a Zenbleed fix") provided a fix for the Zen2 VZEROUPPER data corruption bug affecting a range of CPU models, but the AMD Custom APU 0405 found on SteamDeck was not listed, although it is clearly affected by the vulnerability. Add this CPU variant to the Zenbleed erratum list, in order to unconditionally enable the fallback fix until a proper microcode update is available. Fixes: 522b1d69219d ("x86/cpu/amd: Add a Zenbleed fix") Signed-off-by: Cristian Ciocaltea Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230811203705.1699914-1-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/amd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 43910eb55b2e..239b302973d7 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -73,6 +73,7 @@ static const int amd_erratum_1054[] = static const int amd_zenbleed[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), + AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); static const int amd_div0[] = From 9ad49178c00a5f20cd97a81cfa87dba8dfa9ff0f Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 3 Aug 2023 18:16:09 +0300 Subject: [PATCH 0236/2093] x86/mm: Fix VDSO and VVAR placement on 5-level paging machines commit 1b8b1aa90c9c0e825b181b98b8d9e249dc395470 upstream. Yingcong has noticed that on the 5-level paging machine, VDSO and VVAR VMAs are placed above the 47-bit border: 8000001a9000-8000001ad000 r--p 00000000 00:00 0 [vvar] 8000001ad000-8000001af000 r-xp 00000000 00:00 0 [vdso] This might confuse users who are not aware of 5-level paging and expect all userspace addresses to be under the 47-bit border. So far problem has only been triggered with ASLR disabled, although it may also occur with ASLR enabled if the layout is randomized in a just right way. The problem happens due to custom placement for the VMAs in the VDSO code: vdso_addr() tries to place them above the stack and checks the result against TASK_SIZE_MAX, which is wrong. TASK_SIZE_MAX is set to the 56-bit border on 5-level paging machines. Use DEFAULT_MAP_WINDOW instead. Fixes: b569bab78d8d ("x86/mm: Prepare to expose larger address space to userspace") Reported-by: Yingcong Wu Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20230803151609.22141-1-kirill.shutemov%40linux.intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/vdso/vma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 311eae30e089..1288661397f0 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -322,8 +322,8 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Round the lowest possible end address up to a PMD boundary. */ end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= TASK_SIZE_MAX) - end = TASK_SIZE_MAX; + if (end >= DEFAULT_MAP_WINDOW) + end = DEFAULT_MAP_WINDOW; end -= len; if (end > start) { From 179430c2aa46a927ce4c01f635a172f851fd15ac Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sun, 16 Jul 2023 20:22:20 +0200 Subject: [PATCH 0237/2093] x86/sev: Do not try to parse for the CC blob on non-AMD hardware commit bee6cf1a80b54548a039e224c651bb15b644a480 upstream. Tao Liu reported a boot hang on an Intel Atom machine due to an unmapped EFI config table. The reason being that the CC blob which contains the CPUID page for AMD SNP guests is parsed for before even checking whether the machine runs on AMD hardware. Usually that's not a problem on !AMD hw - it simply won't find the CC blob's GUID and return. However, if any parts of the config table pointers array is not mapped, the kernel will #PF very early in the decompressor stage without any opportunity to recover. Therefore, do a superficial CPUID check before poking for the CC blob. This will fix the current issue on real hardware. It would also work as a guest on a non-lying hypervisor. For the lying hypervisor, the check is done again, *after* parsing the CC blob as the real CPUID page will be present then. Clear the #VC handler in case SEV-{ES,SNP} hasn't been detected, as a precaution. Fixes: c01fce9cef84 ("x86/compressed: Add SEV-SNP feature detection/setup") Reported-by: Tao Liu Signed-off-by: Borislav Petkov (AMD) Acked-by: Tom Lendacky Tested-by: Tao Liu Cc: Link: https://lore.kernel.org/r/20230601072043.24439-1-ltao@redhat.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/boot/compressed/idt_64.c | 9 ++++++- arch/x86/boot/compressed/sev.c | 39 ++++++++++++++++++++++++++++--- 2 files changed, 44 insertions(+), 4 deletions(-) diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 6debb816e83d..3cdf94b41456 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -63,7 +63,14 @@ void load_stage2_idt(void) set_idt_entry(X86_TRAP_PF, boot_page_fault); #ifdef CONFIG_AMD_MEM_ENCRYPT - set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + /* + * Clear the second stage #VC handler in case guest types + * needing #VC have not been detected. + */ + if (sev_status & BIT(1)) + set_idt_entry(X86_TRAP_VC, boot_stage2_vc); + else + set_idt_entry(X86_TRAP_VC, NULL); #endif load_boot_idt(&boot_idt_desc); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index d63ad8f99f83..e65f0968e0d9 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -355,10 +355,13 @@ void sev_enable(struct boot_params *bp) bp->cc_blob_address = 0; /* - * Setup/preliminary detection of SNP. This will be sanity-checked - * against CPUID/MSR values later. + * Do an initial SEV capability check before snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. */ - snp = snp_init(bp); /* Check for the SME/SEV support leaf */ eax = 0x80000000; @@ -379,6 +382,36 @@ void sev_enable(struct boot_params *bp) ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); /* Check whether SEV is supported */ + if (!(eax & BIT(1))) + return; + + /* + * Setup/preliminary detection of SNP. This will be sanity-checked + * against CPUID/MSR values later. + */ + snp = snp_init(bp); + + /* Now repeat the checks with the SNP CPUID table. */ + + /* Recheck the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Recheck for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ if (!(eax & BIT(1))) { if (snp) error("SEV-SNP support indicated by CC blob, but not CPUID."); From f276899f8dbc882dfa634a384ca86e056088dbde Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 9 Aug 2023 15:04:59 +0200 Subject: [PATCH 0238/2093] x86/speculation: Add cpu_show_gds() prototype commit a57c27c7ad85c420b7de44c6ee56692d51709dda upstream. The newly added function has two definitions but no prototypes: drivers/base/cpu.c:605:16: error: no previous prototype for 'cpu_show_gds' [-Werror=missing-prototypes] Add a declaration next to the other ones for this file to avoid the warning. Fixes: 8974eb588283b ("x86/speculation: Add Gather Data Sampling mitigation") Signed-off-by: Arnd Bergmann Signed-off-by: Dave Hansen Tested-by: Daniel Sneddon Cc: stable@kernel.org Link: https://lore.kernel.org/all/20230809130530.1913368-1-arnd%40kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f98cfe9f188f..008bfa68cfab 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -72,6 +72,8 @@ extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, From 19e7feda89667d01b77e84d6e7a02700106a4ae2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 9 Aug 2023 15:05:00 +0200 Subject: [PATCH 0239/2093] x86: Move gds_ucode_mitigated() declaration to header commit eb3515dc99c7c85f4170b50838136b2a193f8012 upstream. The declaration got placed in the .c file of the caller, but that causes a warning for the definition: arch/x86/kernel/cpu/bugs.c:682:6: error: no previous prototype for 'gds_ucode_mitigated' [-Werror=missing-prototypes] Move it to a header where both sides can observe it instead. Fixes: 81ac7e5d74174 ("KVM: Add GDS_NO support to KVM") Signed-off-by: Arnd Bergmann Signed-off-by: Dave Hansen Tested-by: Daniel Sneddon Cc: stable@kernel.org Link: https://lore.kernel.org/all/20230809130530.1913368-2-arnd%40kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/processor.h | 2 ++ arch/x86/kvm/x86.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 45bf26862b99..94ea13adb724 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -867,4 +867,6 @@ bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif +extern bool gds_ucode_mitigated(void); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f4b12c3c30a0..1931d3fcbbe0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -311,8 +311,6 @@ u64 __read_mostly host_xcr0; static struct kmem_cache *x86_emulator_cache; -extern bool gds_ucode_mitigated(void); - /* * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. From 98e470dc73a9b3539e5a7a3c72f6b7c01c989700 Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Sat, 5 Aug 2023 12:18:13 +0200 Subject: [PATCH 0240/2093] drm/nouveau/disp: Revert a NULL check inside nouveau_connector_get_modes commit d5712cd22b9cf109fded1b7f178f4c1888c8b84b upstream. The original commit adding that check tried to protect the kenrel against a potential invalid NULL pointer access. However we call nouveau_connector_detect_depth once without a native_mode set on purpose for non LVDS connectors and this broke DP support in a few cases. Cc: Olaf Skibbe Cc: Lyude Paul Closes: https://gitlab.freedesktop.org/drm/nouveau/-/issues/238 Closes: https://gitlab.freedesktop.org/drm/nouveau/-/issues/245 Fixes: 20a2ce87fbaf8 ("drm/nouveau/dp: check for NULL nv_connector->native_mode") Signed-off-by: Karol Herbst Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230805101813.2603989-1-kherbst@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/nouveau_connector.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index f40310559d13..49c5451cdfb1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -967,7 +967,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) /* Determine display colour depth for everything except LVDS now, * DP requires this before mode_valid() is called. */ - if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) + if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS) nouveau_connector_detect_depth(connector); /* Find the native mode if this is a digital panel, if we didn't From 312f04ede209f0a186799fe8e64a19b49700d5dc Mon Sep 17 00:00:00 2001 From: Milan Zamazal Date: Wed, 19 Jul 2023 10:32:08 +0200 Subject: [PATCH 0241/2093] iio: core: Prevent invalid memory access when there is no parent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b2a69969908fcaf68596dfc04369af0fe2e1d2f7 upstream. Commit 813665564b3d ("iio: core: Convert to use firmware node handle instead of OF node") switched the kind of nodes to use for label retrieval in device registration. Probably an unwanted change in that commit was that if the device has no parent then NULL pointer is accessed. This is what happens in the stock IIO dummy driver when a new entry is created in configfs: # mkdir /sys/kernel/config/iio/devices/dummy/foo BUG: kernel NULL pointer dereference, address: ... ... Call Trace: __iio_device_register iio_dummy_probe Since there seems to be no reason to make a parent device of an IIO dummy device mandatory, let’s prevent the invalid memory access in __iio_device_register when the parent device is NULL. With this change, the IIO dummy driver works fine with configfs. Fixes: 813665564b3d ("iio: core: Convert to use firmware node handle instead of OF node") Reviewed-by: Andy Shevchenko Signed-off-by: Milan Zamazal Link: https://lore.kernel.org/r/20230719083208.88149-1-mzamazal@redhat.com Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/industrialio-core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 151ff3993354..f3f8392623a4 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1916,7 +1916,7 @@ static const struct iio_buffer_setup_ops noop_ring_setup_ops; int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) { struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode = NULL; int ret; if (!indio_dev->info) @@ -1927,7 +1927,8 @@ int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) /* If the calling driver did not initialize firmware node, do it here */ if (dev_fwnode(&indio_dev->dev)) fwnode = dev_fwnode(&indio_dev->dev); - else + /* The default dummy IIO device has no parent */ + else if (indio_dev->dev.parent) fwnode = dev_fwnode(indio_dev->dev.parent); device_set_node(&indio_dev->dev, fwnode); From 8d0e2802b111da37866c20d7f6b531eb31c72ff5 Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Fri, 23 Jun 2023 14:50:42 +0200 Subject: [PATCH 0242/2093] interconnect: qcom: Add support for mask-based BCMs commit d8630f050d3fd2079f8617dd6c00c6509109c755 upstream. Some BCMs aren't directly associated with the data path (i.e. ACV) and therefore don't communicate using BW. Instead, they are simply enabled/disabled with a simple bit mask. Add support for these. Origin commit retrieved from: https://git.codelinaro.org/clo/la/kernel/msm-5.15/-/commit/2d1573e0206998151b342e6b52a4c0f7234d7e36 Signed-off-by: Mike Tipton [narmstrong: removed copyright change from original commit] Signed-off-by: Neil Armstrong Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230619-topic-sm8550-upstream-interconnect-mask-vote-v2-1-709474b151cc@linaro.org Fixes: fafc114a468e ("interconnect: qcom: Add SM8450 interconnect provider driver") Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- drivers/interconnect/qcom/bcm-voter.c | 5 +++++ drivers/interconnect/qcom/icc-rpmh.h | 2 ++ 2 files changed, 7 insertions(+) diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index 8f385f9c2dd3..d5f2a6b5376b 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -83,6 +83,11 @@ static void bcm_aggregate(struct qcom_icc_bcm *bcm) temp = agg_peak[bucket] * bcm->vote_scale; bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit); + + if (bcm->enable_mask && (bcm->vote_x[bucket] || bcm->vote_y[bucket])) { + bcm->vote_x[bucket] = 0; + bcm->vote_y[bucket] = bcm->enable_mask; + } } if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 && diff --git a/drivers/interconnect/qcom/icc-rpmh.h b/drivers/interconnect/qcom/icc-rpmh.h index 04391c1ba465..7843d8864d6b 100644 --- a/drivers/interconnect/qcom/icc-rpmh.h +++ b/drivers/interconnect/qcom/icc-rpmh.h @@ -81,6 +81,7 @@ struct qcom_icc_node { * @vote_x: aggregated threshold values, represents sum_bw when @type is bw bcm * @vote_y: aggregated threshold values, represents peak_bw when @type is bw bcm * @vote_scale: scaling factor for vote_x and vote_y + * @enable_mask: optional mask to send as vote instead of vote_x/vote_y * @dirty: flag used to indicate whether the bcm needs to be committed * @keepalive: flag used to indicate whether a keepalive is required * @aux_data: auxiliary data used when calculating threshold values and @@ -97,6 +98,7 @@ struct qcom_icc_bcm { u64 vote_x[QCOM_ICC_NUM_BUCKETS]; u64 vote_y[QCOM_ICC_NUM_BUCKETS]; u64 vote_scale; + u32 enable_mask; bool dirty; bool keepalive; struct bcm_db aux_data; From e12b1ebc758a0b5778db1d29181f41f321e6c22c Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Fri, 23 Jun 2023 14:50:43 +0200 Subject: [PATCH 0243/2093] interconnect: qcom: sm8450: add enable_mask for bcm nodes commit be02db24cf840bc0fdfbecc78ad803619dd143e6 upstream. Set the proper enable_mask to nodes requiring such value to be used instead of a bandwidth when voting. The masks were copied from the downstream implementation at [1]. [1] https://git.codelinaro.org/clo/la/kernel/msm-5.10/-/blob/KERNEL.PLATFORM.1.0.r2-05600-WAIPIOLE.0/drivers/interconnect/qcom/waipio.c Signed-off-by: Neil Armstrong Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230619-topic-sm8550-upstream-interconnect-mask-vote-v2-2-709474b151cc@linaro.org Fixes: fafc114a468e ("interconnect: qcom: Add SM8450 interconnect provider driver") Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- drivers/interconnect/qcom/sm8450.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/interconnect/qcom/sm8450.c b/drivers/interconnect/qcom/sm8450.c index 2d7a8e7b85ec..e64c214b4020 100644 --- a/drivers/interconnect/qcom/sm8450.c +++ b/drivers/interconnect/qcom/sm8450.c @@ -1337,6 +1337,7 @@ static struct qcom_icc_node qns_mem_noc_sf_disp = { static struct qcom_icc_bcm bcm_acv = { .name = "ACV", + .enable_mask = 0x8, .num_nodes = 1, .nodes = { &ebi }, }; @@ -1349,6 +1350,7 @@ static struct qcom_icc_bcm bcm_ce0 = { static struct qcom_icc_bcm bcm_cn0 = { .name = "CN0", + .enable_mask = 0x1, .keepalive = true, .num_nodes = 55, .nodes = { &qnm_gemnoc_cnoc, &qnm_gemnoc_pcie, @@ -1383,6 +1385,7 @@ static struct qcom_icc_bcm bcm_cn0 = { static struct qcom_icc_bcm bcm_co0 = { .name = "CO0", + .enable_mask = 0x1, .num_nodes = 2, .nodes = { &qxm_nsp, &qns_nsp_gemnoc }, }; @@ -1403,6 +1406,7 @@ static struct qcom_icc_bcm bcm_mm0 = { static struct qcom_icc_bcm bcm_mm1 = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 12, .nodes = { &qnm_camnoc_hf, &qnm_camnoc_icp, &qnm_camnoc_sf, &qnm_mdp, @@ -1445,6 +1449,7 @@ static struct qcom_icc_bcm bcm_sh0 = { static struct qcom_icc_bcm bcm_sh1 = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 7, .nodes = { &alm_gpu_tcu, &alm_sys_tcu, &qnm_nsp_gemnoc, &qnm_pcie, @@ -1461,6 +1466,7 @@ static struct qcom_icc_bcm bcm_sn0 = { static struct qcom_icc_bcm bcm_sn1 = { .name = "SN1", + .enable_mask = 0x1, .num_nodes = 4, .nodes = { &qhm_gic, &qxm_pimem, &xm_gic, &qns_gemnoc_gc }, @@ -1492,6 +1498,7 @@ static struct qcom_icc_bcm bcm_sn7 = { static struct qcom_icc_bcm bcm_acv_disp = { .name = "ACV", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &ebi_disp }, }; @@ -1510,6 +1517,7 @@ static struct qcom_icc_bcm bcm_mm0_disp = { static struct qcom_icc_bcm bcm_mm1_disp = { .name = "MM1", + .enable_mask = 0x1, .num_nodes = 3, .nodes = { &qnm_mdp_disp, &qnm_rot_disp, &qns_mem_noc_sf_disp }, @@ -1523,6 +1531,7 @@ static struct qcom_icc_bcm bcm_sh0_disp = { static struct qcom_icc_bcm bcm_sh1_disp = { .name = "SH1", + .enable_mask = 0x1, .num_nodes = 1, .nodes = { &qnm_pcie_disp }, }; From e146162dcf2e4d486df8d76f6587b8819cf538bc Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 4 Aug 2023 20:22:11 +0100 Subject: [PATCH 0244/2093] selftests/rseq: Fix build with undefined __weak commit d5ad9aae13dcced333c1a7816ff0a4fbbb052466 upstream. Commit 3bcbc20942db ("selftests/rseq: Play nice with binaries statically linked against glibc 2.35+") which is now in Linus' tree introduced uses of __weak but did nothing to ensure that a definition is provided for it resulting in build failures for the rseq tests: rseq.c:41:1: error: unknown type name '__weak' __weak ptrdiff_t __rseq_offset; ^ rseq.c:41:17: error: expected ';' after top level declarator __weak ptrdiff_t __rseq_offset; ^ ; rseq.c:42:1: error: unknown type name '__weak' __weak unsigned int __rseq_size; ^ rseq.c:43:1: error: unknown type name '__weak' __weak unsigned int __rseq_flags; Fix this by using the definition from tools/include compiler.h. Fixes: 3bcbc20942db ("selftests/rseq: Play nice with binaries statically linked against glibc 2.35+") Signed-off-by: Mark Brown Message-Id: <20230804-kselftest-rseq-build-v1-1-015830b66aa9@kernel.org> Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/rseq/Makefile | 4 +++- tools/testing/selftests/rseq/rseq.c | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 3a173e184566..cb5a9fc629fe 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,8 +4,10 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif +top_srcdir = ../../../.. + CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ - $(CLANG_FLAGS) + $(CLANG_FLAGS) -I$(top_srcdir)/tools/include LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index b736a5169aad..e20191fb40d4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -29,6 +29,8 @@ #include #include +#include + #include "../kselftest.h" #include "rseq.h" From 1455765e28ce78c29c0c92484d394a965d2d1c56 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:52 +0300 Subject: [PATCH 0245/2093] selftests: forwarding: Add a helper to skip test when using veth pairs commit 66e131861ab7bf754b50813216f5c6885cd32d63 upstream. A handful of tests require physical loopbacks to be used instead of veth pairs. Add a helper that these tests will invoke in order to be skipped when executed with veth pairs. Fixes: 64916b57c0b1 ("selftests: forwarding: Add speed and auto-negotiation test") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-7-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/forwarding/lib.sh | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index fbe4e37cf26e..7ca2e07680bd 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -138,6 +138,17 @@ check_locked_port_support() fi } +skip_on_veth() +{ + local kind=$(ip -j -d link show dev ${NETIFS[p1]} | + jq -r '.[].linkinfo.info_kind') + + if [[ $kind == veth ]]; then + echo "SKIP: Test cannot be run with veth pairs" + exit $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip From 10519d0b260d7f738c4774c591e2250a2dbea1c0 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:53 +0300 Subject: [PATCH 0246/2093] selftests: forwarding: ethtool: Skip when using veth pairs commit 60a36e21915c31c0375d9427be9406aa8ce2ec34 upstream. Auto-negotiation cannot be tested with veth pairs, resulting in failures: # ./ethtool.sh TEST: force of same speed autoneg off [FAIL] error in configuration. swp1 speed Not autoneg off [...] Fix by skipping the test when used with veth pairs. Fixes: 64916b57c0b1 ("selftests: forwarding: Add speed and auto-negotiation test") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-8-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/forwarding/ethtool.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index dbb9fcf759e0..aa2eafb7b243 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -286,6 +286,8 @@ different_speeds_autoneg_on() ethtool -s $h1 autoneg on } +skip_on_veth + trap cleanup EXIT setup_prepare From 693c0a5a02e17f997b2897e329ae2744eebb217b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:54 +0300 Subject: [PATCH 0247/2093] selftests: forwarding: ethtool_extended_state: Skip when using veth pairs commit b3d9305e60d121dac20a77b6847c4cf14a4c0001 upstream. Ethtool extended state cannot be tested with veth pairs, resulting in failures: # ./ethtool_extended_state.sh TEST: Autoneg, No partner detected [FAIL] Expected "Autoneg", got "Link detected: no" [...] Fix by skipping the test when used with veth pairs. Fixes: 7d10bcce98cd ("selftests: forwarding: Add tests for ethtool extended state") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-9-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- .../testing/selftests/net/forwarding/ethtool_extended_state.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh index 072faa77f53b..17f89c3b7c02 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -108,6 +108,8 @@ no_cable() ip link set dev $swp3 down } +skip_on_veth + setup_prepare tests_run From 9ff7465b91604f0ad376d11c6948c00ba894fde8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:55 +0300 Subject: [PATCH 0248/2093] selftests: forwarding: hw_stats_l3_gre: Skip when using veth pairs commit 9a711cde07c245a163d95eee5b42ed1871e73236 upstream. Layer 3 hardware stats cannot be used when the underlying interfaces are veth pairs, resulting in failures: # ./hw_stats_l3_gre.sh TEST: ping gre flat [ OK ] TEST: Test rx packets: [FAIL] Traffic not reflected in the counter: 0 -> 0 TEST: Test tx packets: [FAIL] Traffic not reflected in the counter: 0 -> 0 Fix by skipping the test when used with veth pairs. Fixes: 813f97a26860 ("selftests: forwarding: Add a tunnel-based test for L3 HW stats") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-10-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh index eb9ec4a68f84..7594bbb49029 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh @@ -99,6 +99,8 @@ test_stats_rx() test_stats g2a rx } +skip_on_veth + trap cleanup EXIT setup_prepare From 2df0e4373507e0b9cce93229796840f4040d99e9 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:47 +0300 Subject: [PATCH 0249/2093] selftests: forwarding: Skip test when no interfaces are specified commit d72c83b1e4b4a36a38269c77a85ff52f95eb0d08 upstream. As explained in [1], the forwarding selftests are meant to be run with either physical loopbacks or veth pairs. The interfaces are expected to be specified in a user-provided forwarding.config file or as command line arguments. By default, this file is not present and the tests fail: # make -C tools/testing/selftests TARGETS=net/forwarding run_tests [...] TAP version 13 1..102 # timeout set to 45 # selftests: net/forwarding: bridge_igmp.sh # Command line is not complete. Try option "help" # Failed to create netif not ok 1 selftests: net/forwarding: bridge_igmp.sh # exit=1 [...] Fix by skipping a test if interfaces are not provided either via the configuration file or command line arguments. # make -C tools/testing/selftests TARGETS=net/forwarding run_tests [...] TAP version 13 1..102 # timeout set to 45 # selftests: net/forwarding: bridge_igmp.sh # SKIP: Cannot create interface. Name not specified ok 1 selftests: net/forwarding: bridge_igmp.sh # SKIP [1] tools/testing/selftests/net/forwarding/README Fixes: 81573b18f26d ("selftests/net/forwarding: add Makefile to install tests") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/856d454e-f83c-20cf-e166-6dc06cbc1543@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/forwarding/lib.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7ca2e07680bd..06027772cf79 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -211,6 +211,11 @@ create_netif_veth() for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) + if [ -z ${NETIFS[p$i]} ]; then + echo "SKIP: Cannot create interface. Name not specified" + exit $ksft_skip + fi + ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then ip link add ${NETIFS[p$i]} type veth \ From 352dc3ee33c6c37107577b232d64d1fadc0863f4 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:48 +0300 Subject: [PATCH 0250/2093] selftests: forwarding: Switch off timeout commit 0529883ad102f6c04e19fb7018f31e1bda575bbe upstream. The default timeout for selftests is 45 seconds, but it is not enough for forwarding selftests which can takes minutes to finish depending on the number of tests cases: # make -C tools/testing/selftests TARGETS=net/forwarding run_tests TAP version 13 1..102 # timeout set to 45 # selftests: net/forwarding: bridge_igmp.sh # TEST: IGMPv2 report 239.10.10.10 [ OK ] # TEST: IGMPv2 leave 239.10.10.10 [ OK ] # TEST: IGMPv3 report 239.10.10.10 is_include [ OK ] # TEST: IGMPv3 report 239.10.10.10 include -> allow [ OK ] # not ok 1 selftests: net/forwarding: bridge_igmp.sh # TIMEOUT 45 seconds Fix by switching off the timeout and setting it to 0. A similar change was done for BPF selftests in commit 6fc5916cc256 ("selftests: bpf: Switch off timeout"). Fixes: 81573b18f26d ("selftests/net/forwarding: add Makefile to install tests") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/8d149f8c-818e-d141-a0ce-a6bae606bc22@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/forwarding/settings | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/net/forwarding/settings diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/settings @@ -0,0 +1 @@ +timeout=0 From e59a2e5a3123fea60269bda82c9c7e8723f25b71 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:58 +0300 Subject: [PATCH 0251/2093] selftests: forwarding: tc_flower: Relax success criterion commit 9ee37e53e7687654b487fc94e82569377272a7a8 upstream. The test checks that filters that match on source or destination MAC were only hit once. A host can send more than one packet with a given source or destination MAC, resulting in failures. Fix by relaxing the success criterion and instead check that the filters were not hit zero times. Using tc_check_at_least_x_packets() is also an option, but it is not available in older kernels. Fixes: 07e5c75184a1 ("selftests: forwarding: Introduce tc flower matching tests") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-13-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/forwarding/tc_flower.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 683711f41aa9..b1daad19b01e 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -52,8 +52,8 @@ match_dst_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower @@ -78,8 +78,8 @@ match_src_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower From 20acffcdc2b74fb7dcc4e299f7aca173df89d911 Mon Sep 17 00:00:00 2001 From: Andrew Kanner Date: Thu, 3 Aug 2023 21:03:18 +0200 Subject: [PATCH 0252/2093] net: core: remove unnecessary frame_sz check in bpf_xdp_adjust_tail() commit d14eea09edf427fa36bd446f4a3271f99164202f upstream. Syzkaller reported the following issue: ======================================= Too BIG xdp->frame_sz = 131072 WARNING: CPU: 0 PID: 5020 at net/core/filter.c:4121 ____bpf_xdp_adjust_tail net/core/filter.c:4121 [inline] WARNING: CPU: 0 PID: 5020 at net/core/filter.c:4121 bpf_xdp_adjust_tail+0x466/0xa10 net/core/filter.c:4103 ... Call Trace: bpf_prog_4add87e5301a4105+0x1a/0x1c __bpf_prog_run include/linux/filter.h:600 [inline] bpf_prog_run_xdp include/linux/filter.h:775 [inline] bpf_prog_run_generic_xdp+0x57e/0x11e0 net/core/dev.c:4721 netif_receive_generic_xdp net/core/dev.c:4807 [inline] do_xdp_generic+0x35c/0x770 net/core/dev.c:4866 tun_get_user+0x2340/0x3ca0 drivers/net/tun.c:1919 tun_chr_write_iter+0xe8/0x210 drivers/net/tun.c:2043 call_write_iter include/linux/fs.h:1871 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x650/0xe40 fs/read_write.c:584 ksys_write+0x12f/0x250 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd xdp->frame_sz > PAGE_SIZE check was introduced in commit c8741e2bfe87 ("xdp: Allow bpf_xdp_adjust_tail() to grow packet size"). But Jesper Dangaard Brouer noted that after introducing the xdp_init_buff() which all XDP driver use - it's safe to remove this check. The original intend was to catch cases where XDP drivers have not been updated to use xdp.frame_sz, but that is not longer a concern (since xdp_init_buff). Running the initial syzkaller repro it was discovered that the contiguous physical memory allocation is used for both xdp paths in tun_get_user(), e.g. tun_build_skb() and tun_alloc_skb(). It was also stated by Jesper Dangaard Brouer that XDP can work on higher order pages, as long as this is contiguous physical memory (e.g. a page). Reported-and-tested-by: syzbot+f817490f5bd20541b90a@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000774b9205f1d8a80d@google.com/T/ Link: https://syzkaller.appspot.com/bug?extid=f817490f5bd20541b90a Link: https://lore.kernel.org/all/20230725155403.796-1-andrew.kanner@gmail.com/T/ Fixes: 43b5169d8355 ("net, xdp: Introduce xdp_init_buff utility routine") Signed-off-by: Andrew Kanner Acked-by: Jesper Dangaard Brouer Acked-by: Jason Wang Link: https://lore.kernel.org/r/20230803190316.2380231-1-andrew.kanner@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/core/filter.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index da71e6812ab5..419ce7c61bd6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4064,12 +4064,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; From ed90fe7435c573897c2ab7624f24d67c866f94a9 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 4 Aug 2023 03:37:37 -0400 Subject: [PATCH 0253/2093] bpf, sockmap: Fix map type error in sock_map_del_link commit 7e96ec0e6605b69bb21bbf6c0ff9051e656ec2b1 upstream. sock_map_del_link() operates on both SOCKMAP and SOCKHASH, although both types have member named "progs", the offset of "progs" member in these two types is different, so "progs" should be accessed with the real map type. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Xu Kuohai Reviewed-by: John Fastabend Link: https://lore.kernel.org/r/20230804073740.194770-2-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau Signed-off-by: Greg Kroah-Hartman --- net/core/sock_map.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index c84e5073c0b6..96db7409baa1 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -148,13 +148,13 @@ static void sock_map_del_link(struct sock *sk, list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; - struct bpf_stab *stab = container_of(map, struct bpf_stab, - map); - if (psock->saved_data_ready && stab->progs.stream_parser) + struct sk_psock_progs *progs = sock_map_progs(map); + + if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.stream_verdict) + if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); From 6b2824b198a638d5ea45df81fa9acb1699eda8b3 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 4 Aug 2023 03:37:38 -0400 Subject: [PATCH 0254/2093] bpf, sockmap: Fix bug that strp_done cannot be called commit 809e4dc71a0f2b8d2836035d98603694fff11d5d upstream. strp_done is only called when psock->progs.stream_parser is not NULL, but stream_parser was set to NULL by sk_psock_stop_strp(), called by sk_psock_drop() earlier. So, strp_done can never be called. Introduce SK_PSOCK_RX_ENABLED to mark whether there is strp on psock. Change the condition for calling strp_done from judging whether stream_parser is set to judging whether this flag is set. This flag is only set once when strp_init() succeeds, and will never be cleared later. Fixes: c0d95d3380ee ("bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap") Signed-off-by: Xu Kuohai Reviewed-by: John Fastabend Link: https://lore.kernel.org/r/20230804073740.194770-3-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau Signed-off-by: Greg Kroah-Hartman --- include/linux/skmsg.h | 1 + net/core/skmsg.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 054d7911bfc9..c1637515a8a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -62,6 +62,7 @@ struct sk_psock_progs { enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, + SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 65fb6f5b21b2..296e45b6c3c0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1117,13 +1117,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1151,7 +1157,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else From ebceef298c56bb5c898ab497051e99671bc268d8 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Aug 2023 10:40:29 -0700 Subject: [PATCH 0255/2093] mISDN: Update parameter type of dsp_cmx_send() commit 1696ec8654016dad3b1baf6c024303e584400453 upstream. When booting a kernel with CONFIG_MISDN_DSP=y and CONFIG_CFI_CLANG=y, there is a failure when dsp_cmx_send() is called indirectly from call_timer_fn(): [ 0.371412] CFI failure at call_timer_fn+0x2f/0x150 (target: dsp_cmx_send+0x0/0x530; expected type: 0x92ada1e9) The function pointer prototype that call_timer_fn() expects is void (*fn)(struct timer_list *) whereas dsp_cmx_send() has a parameter type of 'void *', which causes the control flow integrity checks to fail because the parameter types do not match. Change dsp_cmx_send()'s parameter type to be 'struct timer_list' to match the expected prototype. The argument is unused anyways, so this has no functional change, aside from avoiding the CFI failure. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202308020936.58787e6c-oliver.sang@intel.com Signed-off-by: Nathan Chancellor Reviewed-by: Sami Tolvanen Reviewed-by: Kees Cook Fixes: e313ac12eb13 ("mISDN: Convert timers to use timer_setup()") Link: https://lore.kernel.org/r/20230802-fix-dsp_cmx_send-cfi-failure-v1-1-2f2e79b0178d@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/isdn/mISDN/dsp.h | 2 +- drivers/isdn/mISDN/dsp_cmx.c | 2 +- drivers/isdn/mISDN/dsp_core.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fa09d511a8ed..baf31258f5c9 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -247,7 +247,7 @@ extern void dsp_cmx_hardware(struct dsp_conf *conf, struct dsp *dsp); extern int dsp_cmx_conf(struct dsp *dsp, u32 conf_id); extern void dsp_cmx_receive(struct dsp *dsp, struct sk_buff *skb); extern void dsp_cmx_hdlc(struct dsp *dsp, struct sk_buff *skb); -extern void dsp_cmx_send(void *arg); +extern void dsp_cmx_send(struct timer_list *arg); extern void dsp_cmx_transmit(struct dsp *dsp, struct sk_buff *skb); extern int dsp_cmx_del_conf_member(struct dsp *dsp); extern int dsp_cmx_del_conf(struct dsp_conf *conf); diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 6d2088fbaf69..1b73af501397 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -1625,7 +1625,7 @@ static u16 dsp_count; /* last sample count */ static int dsp_count_valid; /* if we have last sample count */ void -dsp_cmx_send(void *arg) +dsp_cmx_send(struct timer_list *arg) { struct dsp_conf *conf; struct dsp_conf_member *member; diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 386084530c2f..fae95f166688 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1195,7 +1195,7 @@ static int __init dsp_init(void) } /* set sample timer */ - timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); + timer_setup(&dsp_spl_tl, dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); From fc0b41ac11069c77723bffd4c9c5adb4dcee635f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Aug 2023 17:26:52 +0000 Subject: [PATCH 0256/2093] macsec: use DEV_STATS_INC() commit 32d0a49d36a2a306c2e47fe5659361e424f0ed3f upstream. syzbot/KCSAN reported data-races in macsec whenever dev->stats fields are updated. It appears all of these updates can happen from multiple cpus. Adopt SMP safe DEV_STATS_INC() to update dev->stats fields. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Sabrina Dubroca Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/macsec.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 983cabf9a0f6..6a7965ed6300 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -743,7 +743,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_dropped++; + DEV_STATS_INC(secy->netdev, rx_dropped); return false; } @@ -767,7 +767,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); return false; } @@ -1059,7 +1059,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } @@ -1169,7 +1169,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } @@ -1186,7 +1186,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; @@ -1220,7 +1220,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } @@ -1261,7 +1261,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) if (ret == NET_RX_SUCCESS) count_rx(dev, len); else - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); @@ -1298,7 +1298,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_errors++; + DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } @@ -1317,7 +1317,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } @@ -3418,7 +3418,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, if (!secy->operational) { kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3426,7 +3426,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3663,9 +3663,9 @@ static void macsec_get_stats64(struct net_device *dev, dev_fetch_sw_netstats(s, dev->tstats); - s->rx_dropped = dev->stats.rx_dropped; - s->tx_dropped = dev->stats.tx_dropped; - s->rx_errors = dev->stats.rx_errors; + s->rx_dropped = atomic_long_read(&dev->stats.__rx_dropped); + s->tx_dropped = atomic_long_read(&dev->stats.__tx_dropped); + s->rx_errors = atomic_long_read(&dev->stats.__rx_errors); } static int macsec_get_iflink(const struct net_device *dev) From b249c510b43ea77821fe85cbad2d7faab7510998 Mon Sep 17 00:00:00 2001 From: Xiang Yang Date: Thu, 3 Aug 2023 07:24:38 +0000 Subject: [PATCH 0257/2093] mptcp: fix the incorrect judgment for msk->cb_flags commit 17ebf8a4c38b5481c29623f5e003fdf7583947f9 upstream. Coccicheck reports the error below: net/mptcp/protocol.c:3330:15-28: ERROR: test of a variable/field address Since the address of msk->cb_flags is used in __test_and_clear_bit, the address should not be NULL. The judgment for if (unlikely(msk->cb_flags)) will always be true, we should check the real value of msk->cb_flags here. Fixes: 65a569b03ca8 ("mptcp: optimize release_cb for the common case") Signed-off-by: Xiang Yang Reviewed-by: Matthieu Baerts Link: https://lore.kernel.org/r/20230803072438.1847500-1-xiangyang3@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 6034ea9ad115..61fefa1a82db 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3370,7 +3370,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ From 584a783270c1b1fc83036b570e6d91acfd7d9b6a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Aug 2023 14:56:00 +0000 Subject: [PATCH 0258/2093] net/packet: annotate data-races around tp->status commit 8a9896177784063d01068293caea3f74f6830ff6 upstream. Another syzbot report [1] is about tp->status lockless reads from __packet_get_status() [1] BUG: KCSAN: data-race in __packet_rcv_has_room / __packet_set_status write to 0xffff888117d7c080 of 8 bytes by interrupt on cpu 0: __packet_set_status+0x78/0xa0 net/packet/af_packet.c:407 tpacket_rcv+0x18bb/0x1a60 net/packet/af_packet.c:2483 deliver_skb net/core/dev.c:2173 [inline] __netif_receive_skb_core+0x408/0x1e80 net/core/dev.c:5337 __netif_receive_skb_one_core net/core/dev.c:5491 [inline] __netif_receive_skb+0x57/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x57/0xa0 kernel/softirq.c:650 sysvec_apic_timer_interrupt+0x6d/0x80 arch/x86/kernel/apic/apic.c:1106 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:645 smpboot_thread_fn+0x33c/0x4a0 kernel/smpboot.c:112 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 read to 0xffff888117d7c080 of 8 bytes by interrupt on cpu 1: __packet_get_status net/packet/af_packet.c:436 [inline] packet_lookup_frame net/packet/af_packet.c:524 [inline] __tpacket_has_room net/packet/af_packet.c:1255 [inline] __packet_rcv_has_room+0x3f9/0x450 net/packet/af_packet.c:1298 tpacket_rcv+0x275/0x1a60 net/packet/af_packet.c:2285 deliver_skb net/core/dev.c:2173 [inline] dev_queue_xmit_nit+0x38a/0x5e0 net/core/dev.c:2243 xmit_one net/core/dev.c:3574 [inline] dev_hard_start_xmit+0xcf/0x3f0 net/core/dev.c:3594 __dev_queue_xmit+0xefb/0x1d10 net/core/dev.c:4244 dev_queue_xmit include/linux/netdevice.h:3088 [inline] can_send+0x4eb/0x5d0 net/can/af_can.c:276 bcm_can_tx+0x314/0x410 net/can/bcm.c:302 bcm_tx_timeout_handler+0xdb/0x260 __run_hrtimer kernel/time/hrtimer.c:1685 [inline] __hrtimer_run_queues+0x217/0x700 kernel/time/hrtimer.c:1749 hrtimer_run_softirq+0xd6/0x120 kernel/time/hrtimer.c:1766 __do_softirq+0xc1/0x265 kernel/softirq.c:571 run_ksoftirqd+0x17/0x20 kernel/softirq.c:939 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0000000000000000 -> 0x0000000020000081 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 19 Comm: ksoftirqd/1 Not tainted 6.4.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230803145600.2937518-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 168106840073..451bd8bfafd2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -404,18 +404,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -432,17 +434,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); From ddebdaec1af2913832e511a0650a5300a9dbf3a6 Mon Sep 17 00:00:00 2001 From: Gerd Bayer Date: Fri, 4 Aug 2023 19:06:24 +0200 Subject: [PATCH 0259/2093] net/smc: Use correct buffer sizes when switching between TCP and SMC commit 30c3c4a4497c3765bf6b298f5072c8165aeaf7cc upstream. Tuning of the effective buffer size through setsockopts was working for SMC traffic only but not for TCP fall-back connections even before commit 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and make them tunable"). That change made it apparent that TCP fall-back connections would use net.smc.[rw]mem as buffer size instead of net.ipv4_tcp_[rw]mem. Amend the code that copies attributes between the (TCP) clcsock and the SMC socket and adjust buffer sizes appropriately: - Copy over sk_userlocks so that both sockets agree on whether tuning via setsockopt is active. - When falling back to TCP use sk_sndbuf or sk_rcvbuf as specified with setsockopt. Otherwise, use the sysctl value for TCP/IPv4. - Likewise, use either values from setsockopt or from sysctl for SMC (duplicated) on successful SMC connect. In smc_tcp_listen_work() drop the explicit copy of buffer sizes as that is taken care of by the attribute copy. Fixes: 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and make them tunable") Reviewed-by: Wenjia Zhang Reviewed-by: Tony Lu Signed-off-by: Gerd Bayer Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/smc/af_smc.c | 75 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 52 insertions(+), 23 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5ae0a54a823b..5712a5297bd0 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -438,24 +438,9 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, return rc; } -static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, - unsigned long mask) -{ - /* options we don't get control via setsockopt for */ - nsk->sk_type = osk->sk_type; - nsk->sk_sndbuf = osk->sk_sndbuf; - nsk->sk_rcvbuf = osk->sk_rcvbuf; - nsk->sk_sndtimeo = osk->sk_sndtimeo; - nsk->sk_rcvtimeo = osk->sk_rcvtimeo; - nsk->sk_mark = READ_ONCE(osk->sk_mark); - nsk->sk_priority = osk->sk_priority; - nsk->sk_rcvlowat = osk->sk_rcvlowat; - nsk->sk_bound_dev_if = osk->sk_bound_dev_if; - nsk->sk_err = osk->sk_err; - - nsk->sk_flags &= ~mask; - nsk->sk_flags |= osk->sk_flags & mask; -} +/* copy only relevant settings and flags of SOL_SOCKET level from smc to + * clc socket (since smc is not called for these options from net/core) + */ #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ @@ -472,9 +457,55 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_NOFCS) | \ (1UL << SOCK_FILTER_LOCKED) | \ (1UL << SOCK_TSTAMP_NEW)) -/* copy only relevant settings and flags of SOL_SOCKET level from smc to - * clc socket (since smc is not called for these options from net/core) - */ + +/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ +static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + struct net *nnet = sock_net(nsk); + + nsk->sk_userlocks = osk->sk_userlocks; + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + nsk->sk_sndbuf = osk->sk_sndbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_sndbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); + else + WRITE_ONCE(nsk->sk_sndbuf, + 2 * READ_ONCE(nnet->smc.sysctl_wmem)); + } + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + nsk->sk_rcvbuf = osk->sk_rcvbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_rcvbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); + else + WRITE_ONCE(nsk->sk_rcvbuf, + 2 * READ_ONCE(nnet->smc.sysctl_rmem)); + } +} + +static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + /* options we don't get control via setsockopt for */ + nsk->sk_type = osk->sk_type; + nsk->sk_sndtimeo = osk->sk_sndtimeo; + nsk->sk_rcvtimeo = osk->sk_rcvtimeo; + nsk->sk_mark = READ_ONCE(osk->sk_mark); + nsk->sk_priority = osk->sk_priority; + nsk->sk_rcvlowat = osk->sk_rcvlowat; + nsk->sk_bound_dev_if = osk->sk_bound_dev_if; + nsk->sk_err = osk->sk_err; + + nsk->sk_flags &= ~mask; + nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); +} + static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); @@ -2466,8 +2497,6 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); - new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; - new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); From f20a941bc2c5464ec50ef793fb67d7de68192cbd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Aug 2023 08:49:23 +0000 Subject: [PATCH 0260/2093] tcp: add missing family to tcp_set_ca_state() tracepoint commit 8a70ed9520c5fafaac91053cacdd44625c39e188 upstream. Before this code is copied, add the missing family, as we did in commit 3dd344ea84e1 ("net: tracepoint: exposing sk_family in all tcp:tracepoints") Fixes: 15fcdf6ae116 ("tcp: Add tracepoint for tcp_set_ca_state") Signed-off-by: Eric Dumazet Cc: Ping Gan Cc: Manjusaka Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230808084923.2239142-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/trace/events/tcp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 901b440238d5..0a14c474c6f9 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -381,6 +381,7 @@ TRACE_EVENT(tcp_cong_state_set, __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -396,6 +397,7 @@ TRACE_EVENT(tcp_cong_state_set, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; @@ -409,7 +411,8 @@ TRACE_EVENT(tcp_cong_state_set, __entry->cong_state = ca_state; ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, From da5f42a6e7485fbb7a6dbd6a2b3045e19e4df5cc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 3 Aug 2023 17:26:49 +0200 Subject: [PATCH 0261/2093] tunnels: fix kasan splat when generating ipv4 pmtu error commit 6a7ac3d20593865209dceb554d8b3f094c6bd940 upstream. If we try to emit an icmp error in response to a nonliner skb, we get BUG: KASAN: slab-out-of-bounds in ip_compute_csum+0x134/0x220 Read of size 4 at addr ffff88811c50db00 by task iperf3/1691 CPU: 2 PID: 1691 Comm: iperf3 Not tainted 6.5.0-rc3+ #309 [..] kasan_report+0x105/0x140 ip_compute_csum+0x134/0x220 iptunnel_pmtud_build_icmp+0x554/0x1020 skb_tunnel_check_pmtu+0x513/0xb80 vxlan_xmit_one+0x139e/0x2ef0 vxlan_xmit+0x1867/0x2760 dev_hard_start_xmit+0x1ee/0x4f0 br_dev_queue_push_xmit+0x4d1/0x660 [..] ip_compute_csum() cannot deal with nonlinear skbs, so avoid it. After this change, splat is gone and iperf3 is no longer stuck. Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets") Signed-off-by: Florian Westphal Link: https://lore.kernel.org/r/20230803152653.29535-2-fw@strlen.de Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_tunnel_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); From 15b453cf7348973217558235b9ece2ee5fea6777 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 9 Aug 2023 16:28:43 +0200 Subject: [PATCH 0262/2093] xsk: fix refcount underflow in error path commit 85c2c79a07302fe68a1ad5cc449458cc559e314d upstream. Fix a refcount underflow problem reported by syzbot that can happen when a system is running out of memory. If xp_alloc_tx_descs() fails, and it can only fail due to not having enough memory, then the error path is triggered. In this error path, the refcount of the pool is decremented as it has incremented before. However, the reference to the pool in the socket was not nulled. This means that when the socket is closed later, the socket teardown logic will think that there is a pool attached to the socket and try to decrease the refcount again, leading to a refcount underflow. I chose this fix as it involved adding just a single line. Another option would have been to move xp_get_pool() and the assignment of xs->pool to after the if-statement and using xs_umem->pool instead of xs->pool in the whole if-statement resulting in somewhat simpler code, but this would have led to much more churn in the code base perhaps making it harder to backport. Fixes: ba3beec2ec1d ("xsk: Fix possible crash when multiple sockets are created") Reported-by: syzbot+8ada0057e69293a05fd4@syzkaller.appspotmail.com Signed-off-by: Magnus Karlsson Link: https://lore.kernel.org/r/20230809142843.13944-1-magnus.karlsson@gmail.com Signed-off-by: Martin KaFai Lau Signed-off-by: Greg Kroah-Hartman --- net/xdp/xsk.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 22bf10ffbf2d..f7592638e61d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -994,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } From 00f033d451c4844777aea9164a6b2691f904dd92 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Wed, 2 Aug 2023 19:43:20 +0800 Subject: [PATCH 0263/2093] bonding: Fix incorrect deletion of ETH_P_8021AD protocol vid from slaves commit 01f4fd27087078c90a0e22860d1dfa2cd0510791 upstream. BUG_ON(!vlan_info) is triggered in unregister_vlan_dev() with following testcase: # ip netns add ns1 # ip netns exec ns1 ip link add bond0 type bond mode 0 # ip netns exec ns1 ip link add bond_slave_1 type veth peer veth2 # ip netns exec ns1 ip link set bond_slave_1 master bond0 # ip netns exec ns1 ip link add link bond_slave_1 name vlan10 type vlan id 10 protocol 802.1ad # ip netns exec ns1 ip link add link bond0 name bond0_vlan10 type vlan id 10 protocol 802.1ad # ip netns exec ns1 ip link set bond_slave_1 nomaster # ip netns del ns1 The logical analysis of the problem is as follows: 1. create ETH_P_8021AD protocol vlan10 for bond_slave_1: register_vlan_dev() vlan_vid_add() vlan_info_alloc() __vlan_vid_add() // add [ETH_P_8021AD, 10] vid to bond_slave_1 2. create ETH_P_8021AD protocol bond0_vlan10 for bond0: register_vlan_dev() vlan_vid_add() __vlan_vid_add() vlan_add_rx_filter_info() if (!vlan_hw_filter_capable(dev, proto)) // condition established because bond0 without NETIF_F_HW_VLAN_STAG_FILTER return 0; if (netif_device_present(dev)) return dev->netdev_ops->ndo_vlan_rx_add_vid(dev, proto, vid); // will be never called // The slaves of bond0 will not refer to the [ETH_P_8021AD, 10] vid. 3. detach bond_slave_1 from bond0: __bond_release_one() vlan_vids_del_by_dev() list_for_each_entry(vid_info, &vlan_info->vid_list, list) vlan_vid_del(dev, vid_info->proto, vid_info->vid); // bond_slave_1 [ETH_P_8021AD, 10] vid will be deleted. // bond_slave_1->vlan_info will be assigned NULL. 4. delete vlan10 during delete ns1: default_device_exit_batch() dev->rtnl_link_ops->dellink() // unregister_vlan_dev() for vlan10 vlan_info = rtnl_dereference(real_dev->vlan_info); // real_dev of vlan10 is bond_slave_1 BUG_ON(!vlan_info); // bond_slave_1->vlan_info is NULL now, bug is triggered!!! Add S-VLAN tag related features support to bond driver. So the bond driver will always propagate the VLAN info to its slaves. Fixes: 8ad227ff89a7 ("net: vlan: add 802.1ad support") Suggested-by: Ido Schimmel Signed-off-by: Ziyang Xuan Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/20230802114320.4156068-1-william.xuanziyang@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/bonding/bond_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 576370f89c75..7a3c7a74af04 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5839,7 +5839,9 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; From a6ddc1c774874dc704f96a99d015dc759627bba7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Aug 2023 16:30:21 +0000 Subject: [PATCH 0264/2093] dccp: fix data-race around dp->dccps_mss_cache commit a47e598fbd8617967e49d85c49c22f9fc642704c upstream. dccp_sendmsg() reads dp->dccps_mss_cache before locking the socket. Same thing in do_dccp_getsockopt(). Add READ_ONCE()/WRITE_ONCE() annotations, and change dccp_sendmsg() to check again dccps_mss_cache after socket is locked. Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230803163021.2958262-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/dccp/output.c | 2 +- net/dccp/proto.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a06b5641287a..abc02d25edc1 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -627,7 +627,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -736,7 +736,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -769,6 +769,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) From eeb0e4c1dbdf21896a6d86b7b398e4f88bbdc6e7 Mon Sep 17 00:00:00 2001 From: Andrew Kanner Date: Thu, 3 Aug 2023 20:59:48 +0200 Subject: [PATCH 0265/2093] drivers: net: prevent tun_build_skb() to exceed the packet size limit commit 59eeb232940515590de513b997539ef495faca9a upstream. Using the syzkaller repro with reduced packet size it was discovered that XDP_PACKET_HEADROOM is not checked in tun_can_build_skb(), although pad may be incremented in tun_build_skb(). This may end up with exceeding the PAGE_SIZE limit in tun_build_skb(). Jason Wang proposed to count XDP_PACKET_HEADROOM always (e.g. without rcu_access_pointer(tun->xdp_prog)) in tun_can_build_skb() since there's a window during which XDP program might be attached between tun_can_build_skb() and tun_build_skb(). Fixes: 7df13219d757 ("tun: reserve extra headroom only when XDP is set") Link: https://syzkaller.appspot.com/bug?extid=f817490f5bd20541b90a Signed-off-by: Andrew Kanner Link: https://lore.kernel.org/r/20230803185947.2379988-1-andrew.kanner@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/tun.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 228f5f9ef1dd..7544df1ff50e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1588,7 +1588,7 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) return false; - if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + + if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; From bcbc48b12092b07c9e1c7fcc03a0ceebbfa77bb5 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 4 Aug 2023 18:53:36 +0300 Subject: [PATCH 0266/2093] drivers: vxlan: vnifilter: free percpu vni stats on error path commit b1c936e9af5dd08636d568736fc6075ed9d1d529 upstream. In case rhashtable_lookup_insert_fast() fails inside vxlan_vni_add(), the allocated percpu vni stats are not freed on the error path. Introduce vxlan_vni_free() which would work as a nice wrapper to free vxlan_vni_node resources properly. Found by Linux Verification Center (linuxtesting.org). Fixes: 4095e0e1328a ("drivers: vxlan: vnifilter: per vni stats") Suggested-by: Ido Schimmel Signed-off-by: Fedor Pchelkin Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/vxlan/vxlan_vnifilter.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index 3e04af4c5daa..c5cf55030158 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -713,6 +713,12 @@ static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, return vninode; } +static void vxlan_vni_free(struct vxlan_vni_node *vninode) +{ + free_percpu(vninode->stats); + kfree(vninode); +} + static int vxlan_vni_add(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, union vxlan_addr *group, @@ -740,7 +746,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan, &vninode->vnode, vxlan_vni_rht_params); if (err) { - kfree(vninode); + vxlan_vni_free(vninode); return err; } @@ -763,8 +769,7 @@ static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) struct vxlan_vni_node *v; v = container_of(rcu, struct vxlan_vni_node, rcu); - free_percpu(v->stats); - kfree(v); + vxlan_vni_free(v); } static int vxlan_vni_del(struct vxlan_dev *vxlan, From c2efcaf304fbbcbccfae13907e7dc8e11727b8c3 Mon Sep 17 00:00:00 2001 From: Piotr Gardocki Date: Mon, 7 Aug 2023 13:50:11 -0700 Subject: [PATCH 0267/2093] iavf: fix potential races for FDIR filters commit 0fb1d8eb234b6979d4981d2d385780dd7d8d9771 upstream. Add fdir_fltr_lock locking in unprotected places. The change in iavf_fdir_is_dup_fltr adds a spinlock around a loop which iterates over all filters and looks for a duplicate. The filter can be removed from list and freed from memory at the same time it's being compared. All other places where filters are deleted are already protected with spinlock. The remaining changes protect adapter->fdir_active_fltr variable so now all its uses are under a spinlock. Fixes: 527691bf0682 ("iavf: Support IPv4 Flow Director filters") Signed-off-by: Piotr Gardocki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230807205011.3129224-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 5 ++++- drivers/net/ethernet/intel/iavf/iavf_fdir.c | 11 ++++++++--- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index fd6d6f6263f6..f544d2b0abdb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1401,14 +1401,15 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fsp->flow_type & FLOW_MAC_EXT) return -EINVAL; + spin_lock_bh(&adapter->fdir_fltr_lock); if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { + spin_unlock_bh(&adapter->fdir_fltr_lock); dev_err(&adapter->pdev->dev, "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", IAVF_MAX_FDIR_FILTERS); return -ENOSPC; } - spin_lock_bh(&adapter->fdir_fltr_lock); if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1781,7 +1782,9 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLCNT: if (!FDIR_FLTR_SUPPORT(adapter)) break; + spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; + spin_unlock_bh(&adapter->fdir_fltr_lock); cmd->data = IAVF_MAX_FDIR_FILTERS; ret = 0; break; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 6146203efd84..505e82ebafe4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -722,7 +722,9 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *tmp; + bool ret = false; + spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { if (tmp->flow_type != fltr->flow_type) continue; @@ -732,11 +734,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * !memcmp(&tmp->ip_data, &fltr->ip_data, sizeof(fltr->ip_data)) && !memcmp(&tmp->ext_data, &fltr->ext_data, - sizeof(fltr->ext_data))) - return true; + sizeof(fltr->ext_data))) { + ret = true; + break; + } } + spin_unlock_bh(&adapter->fdir_fltr_lock); - return false; + return ret; } /** From ac6640f4193d0f5b44269a7f08372909f9a18e5c Mon Sep 17 00:00:00 2001 From: Douglas Miller Date: Wed, 2 Aug 2023 13:32:41 -0400 Subject: [PATCH 0268/2093] IB/hfi1: Fix possible panic during hotplug remove commit 4fdfaef71fced490835145631a795497646f4555 upstream. During hotplug remove it is possible that the update counters work might be pending, and may run after memory has been freed. Cancel the update counters work before freeing memory. Fixes: 7724105686e7 ("IB/hfi1: add driver files") Signed-off-by: Douglas Miller Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/169099756100.3927190.15284930454106475280.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/hfi1/chip.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 90b672feed83..194cac40da65 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12307,6 +12307,7 @@ static void free_cntrs(struct hfi1_devdata *dd) if (dd->synth_stats_timer.function) del_timer_sync(&dd->synth_stats_timer); + cancel_work_sync(&dd->update_cntr_work); ppd = (struct hfi1_pportdata *)(dd + 1); for (i = 0; i < dd->num_pports; i++, ppd++) { kfree(ppd->cntrs); From 94916b314861288ebf7ef883ef23df00ac2b94a0 Mon Sep 17 00:00:00 2001 From: Daniel Stone Date: Tue, 8 Aug 2023 11:44:05 +0100 Subject: [PATCH 0269/2093] drm/rockchip: Don't spam logs in atomic check commit 43dae319b50fac075ad864f84501c703ef20eb2b upstream. Userspace should not be able to trigger DRM_ERROR messages to spam the logs; especially not through atomic commit parameters which are completely legitimate for userspace to attempt. Signed-off-by: Daniel Stone Fixes: 7707f7227f09 ("drm/rockchip: Add support for afbc") Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20230808104405.522493-1-daniels@collabora.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 9fea03121247..2e2e08f4359a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -836,12 +836,12 @@ static int vop_plane_atomic_check(struct drm_plane *plane, * need align with 2 pixel. */ if (fb->format->is_yuv && ((new_plane_state->src.x1 >> 16) % 2)) { - DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format not support odd xpos\n"); return -EINVAL; } if (fb->format->is_yuv && new_plane_state->rotation & DRM_MODE_REFLECT_Y) { - DRM_ERROR("Invalid Source: Yuv format does not support this rotation\n"); + DRM_DEBUG_KMS("Invalid Source: Yuv format does not support this rotation\n"); return -EINVAL; } @@ -849,7 +849,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane, struct vop *vop = to_vop(crtc); if (!vop->data->afbc) { - DRM_ERROR("vop does not support AFBC\n"); + DRM_DEBUG_KMS("vop does not support AFBC\n"); return -EINVAL; } @@ -858,15 +858,16 @@ static int vop_plane_atomic_check(struct drm_plane *plane, return ret; if (new_plane_state->src.x1 || new_plane_state->src.y1) { - DRM_ERROR("AFBC does not support offset display, xpos=%d, ypos=%d, offset=%d\n", - new_plane_state->src.x1, - new_plane_state->src.y1, fb->offsets[0]); + DRM_DEBUG_KMS("AFBC does not support offset display, " \ + "xpos=%d, ypos=%d, offset=%d\n", + new_plane_state->src.x1, new_plane_state->src.y1, + fb->offsets[0]); return -EINVAL; } if (new_plane_state->rotation && new_plane_state->rotation != DRM_MODE_ROTATE_0) { - DRM_ERROR("No rotation support in AFBC, rotation=%d\n", - new_plane_state->rotation); + DRM_DEBUG_KMS("No rotation support in AFBC, rotation=%d\n", + new_plane_state->rotation); return -EINVAL; } } From 521860ddf31414a58f2dcd41f04b790603db8c8b Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 22 Jun 2023 18:59:19 +0200 Subject: [PATCH 0270/2093] wifi: cfg80211: fix sband iftype data lookup for AP_VLAN commit 5fb9a9fb71a33be61d7d8e8ba4597bfb18d604d0 upstream. AP_VLAN interfaces are virtual, so doesn't really exist as a type for capabilities. When passed in as a type, AP is the one that's really intended. Fixes: c4cbaf7973a7 ("cfg80211: Add support for HE") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20230622165919.46841-1-nbd@nbd.name Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- include/net/cfg80211.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e09ff87146c1..5976545aa26b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -562,6 +562,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, if (WARN_ON(iftype >= NL80211_IFTYPE_MAX)) return NULL; + if (iftype == NL80211_IFTYPE_AP_VLAN) + iftype = NL80211_IFTYPE_AP; + for (i = 0; i < sband->n_iftype_data; i++) { const struct ieee80211_sband_iftype_data *data = &sband->iftype_data[i]; From 05e6b93da45db981e5586f90c04518880460055b Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Wed, 19 Jul 2023 12:02:41 +0300 Subject: [PATCH 0271/2093] RDMA/umem: Set iova in ODP flow commit 186b169cf1e4be85aa212a893ea783a543400979 upstream. Fixing the ODP registration flow to set the iova correctly. The calculation in ib_umem_num_dma_blocks() function assumes the iova of the umem is set correctly. When iova is not set, the calculation in ib_umem_num_dma_blocks() is equivalent to length/page_size, which is true only when memory is aligned. For unaligned memory, iova must be set for the ALIGN() in the ib_umem_num_dma_blocks() to take effect and return a correct value. mlx5_ib uses ib_umem_num_dma_blocks() to decide the mkey size to use for the MR. Without this fix, when registering unaligned ODP MR, a wrong size mkey might be chosen and this might cause the UMR to fail. UMR would fail over insufficient size to update the mkey translation: infiniband mlx5_0: dump_cqe:273:(pid 0): dump error cqe 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000030: 00 00 00 00 0f 00 78 06 25 00 00 58 00 da ac d2 infiniband mlx5_0: mlx5_ib_post_send_wait:806:(pid 20311): reg umr failed (6) infiniband mlx5_0: pagefault_real_mr:661:(pid 20311): Failed to update mkey page tables Fixes: f0093fb1a7cb ("RDMA/mlx5: Move mlx5_ib_cont_pages() to the creation of the mlx5_ib_mr") Fixes: a665aca89a41 ("RDMA/umem: Split ib_umem_num_pages() into ib_umem_num_dma_blocks()") Signed-off-by: Artemy Kovalyov Signed-off-by: Michael Guralnik Link: https://lore.kernel.org/r/3d4be7ca2155bf239dd8c00a2d25974a92c26ab8.1689757344.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/umem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 86d479772fbc..957634eceba8 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -85,6 +85,8 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, dma_addr_t mask; int i; + umem->iova = va = virt; + if (umem->is_odp) { unsigned int page_size = BIT(to_ib_umem_odp(umem)->page_shift); @@ -100,7 +102,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, */ pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); - umem->iova = va = virt; /* The best result is the smallest page size that results in the minimum * number of required pages. Compute the largest page size that could * work based on VA address bits that don't change. From 059ec8287fd341700c8a93bc029722a6065b4f2f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Aug 2023 15:59:51 -0700 Subject: [PATCH 0272/2093] net: tls: avoid discarding data on record close commit 6b47808f223c70ff564f9b363446d2a5fa1e05b2 upstream. TLS records end with a 16B tag. For TLS device offload we only need to make space for this tag in the stream, the device will generate and replace it with the actual calculated tag. Long time ago the code would just re-reference the head frag which mostly worked but was suboptimal because it prevented TCP from combining the record into a single skb frag. I'm not sure if it was correct as the first frag may be shorter than the tag. The commit under fixes tried to replace that with using the page frag and if the allocation failed rolling back the data, if record was long enough. It achieves better fragment coalescing but is also buggy. We don't roll back the iterator, so unless we're at the end of send we'll skip the data we designated as tag and start the next record as if the rollback never happened. There's also the possibility that the record was constructed with MSG_MORE and the data came from a different syscall and we already told the user space that we "got it". Allocate a single dummy page and use it as fallback. Found by code inspection, and proven by forcing allocation failures. Fixes: e7b159a48ba6 ("net/tls: remove the record tail optimization") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tls/tls_device.c | 64 +++++++++++++++++++++++--------------------- 1 file changed, 33 insertions(+), 31 deletions(-) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bf69c9d6d06c..184982788473 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -313,36 +315,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -535,18 +534,8 @@ static int tls_push_data(struct sock *sk, if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1466,14 +1455,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1482,4 +1483,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } From a3e5f3b7f25d7b90f3b76d98a946fec6e5f79216 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Fri, 4 Aug 2023 12:12:20 +0200 Subject: [PATCH 0273/2093] net: marvell: prestera: fix handling IPv4 routes with nhid commit 2aa71b4b294ee2c3041d085404cea914be9b3225 upstream. Fix handling IPv4 routes referencing a nexthop via its id by replacing calls to fib_info_nh() with fib_info_nhc(). Trying to add an IPv4 route referencing a nextop via nhid: $ ip link set up swp5 $ ip a a 10.0.0.1/24 dev swp5 $ ip nexthop add dev swp5 id 20 via 10.0.0.2 $ ip route add 10.0.1.0/24 nhid 20 triggers warnings when trying to handle the route: [ 528.805763] ------------[ cut here ]------------ [ 528.810437] WARNING: CPU: 3 PID: 53 at include/net/nexthop.h:468 __prestera_fi_is_direct+0x2c/0x68 [prestera] [ 528.820434] Modules linked in: prestera_pci act_gact act_police sch_ingress cls_u32 cls_flower prestera arm64_delta_tn48m_dn_led(O) arm64_delta_tn48m_dn_cpld(O) [last unloaded: prestera_pci] [ 528.837485] CPU: 3 PID: 53 Comm: kworker/u8:3 Tainted: G O 6.4.5 #1 [ 528.845178] Hardware name: delta,tn48m-dn (DT) [ 528.849641] Workqueue: prestera_ordered __prestera_router_fib_event_work [prestera] [ 528.857352] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 528.864347] pc : __prestera_fi_is_direct+0x2c/0x68 [prestera] [ 528.870135] lr : prestera_k_arb_fib_evt+0xb20/0xd50 [prestera] [ 528.876007] sp : ffff80000b20bc90 [ 528.879336] x29: ffff80000b20bc90 x28: 0000000000000000 x27: ffff0001374d3a48 [ 528.886510] x26: ffff000105604000 x25: ffff000134af8a28 x24: ffff0001374d3800 [ 528.893683] x23: ffff000101c89148 x22: ffff000101c89000 x21: ffff000101c89200 [ 528.900855] x20: ffff00013641fda0 x19: ffff800009d01088 x18: 0000000000000059 [ 528.908027] x17: 0000000000000277 x16: 0000000000000000 x15: 0000000000000000 [ 528.915198] x14: 0000000000000003 x13: 00000000000fe400 x12: 0000000000000000 [ 528.922371] x11: 0000000000000002 x10: 0000000000000aa0 x9 : ffff8000013d2020 [ 528.929543] x8 : 0000000000000018 x7 : 000000007b1703f8 x6 : 000000001ca72f86 [ 528.936715] x5 : 0000000033399ea7 x4 : 0000000000000000 x3 : ffff0001374d3acc [ 528.943886] x2 : 0000000000000000 x1 : ffff00010200de00 x0 : ffff000134ae3f80 [ 528.951058] Call trace: [ 528.953516] __prestera_fi_is_direct+0x2c/0x68 [prestera] [ 528.958952] __prestera_router_fib_event_work+0x100/0x158 [prestera] [ 528.965348] process_one_work+0x208/0x488 [ 528.969387] worker_thread+0x4c/0x430 [ 528.973068] kthread+0x120/0x138 [ 528.976313] ret_from_fork+0x10/0x20 [ 528.979909] ---[ end trace 0000000000000000 ]--- [ 528.984998] ------------[ cut here ]------------ [ 528.989645] WARNING: CPU: 3 PID: 53 at include/net/nexthop.h:468 __prestera_fi_is_direct+0x2c/0x68 [prestera] [ 528.999628] Modules linked in: prestera_pci act_gact act_police sch_ingress cls_u32 cls_flower prestera arm64_delta_tn48m_dn_led(O) arm64_delta_tn48m_dn_cpld(O) [last unloaded: prestera_pci] [ 529.016676] CPU: 3 PID: 53 Comm: kworker/u8:3 Tainted: G W O 6.4.5 #1 [ 529.024368] Hardware name: delta,tn48m-dn (DT) [ 529.028830] Workqueue: prestera_ordered __prestera_router_fib_event_work [prestera] [ 529.036539] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 529.043533] pc : __prestera_fi_is_direct+0x2c/0x68 [prestera] [ 529.049318] lr : __prestera_k_arb_fc_apply+0x280/0x2f8 [prestera] [ 529.055452] sp : ffff80000b20bc60 [ 529.058781] x29: ffff80000b20bc60 x28: 0000000000000000 x27: ffff0001374d3a48 [ 529.065953] x26: ffff000105604000 x25: ffff000134af8a28 x24: ffff0001374d3800 [ 529.073126] x23: ffff000101c89148 x22: ffff000101c89148 x21: ffff00013641fda0 [ 529.080299] x20: ffff000101c89000 x19: ffff000101c89020 x18: 0000000000000059 [ 529.087471] x17: 0000000000000277 x16: 0000000000000000 x15: 0000000000000000 [ 529.094642] x14: 0000000000000003 x13: 00000000000fe400 x12: 0000000000000000 [ 529.101814] x11: 0000000000000002 x10: 0000000000000aa0 x9 : ffff8000013cee80 [ 529.108985] x8 : 0000000000000018 x7 : 000000007b1703f8 x6 : 0000000000000018 [ 529.116157] x5 : 00000000d3497eb6 x4 : ffff000105604081 x3 : 000000008e979557 [ 529.123329] x2 : 0000000000000000 x1 : ffff00010200de00 x0 : ffff000134ae3f80 [ 529.130501] Call trace: [ 529.132958] __prestera_fi_is_direct+0x2c/0x68 [prestera] [ 529.138394] prestera_k_arb_fib_evt+0x6b8/0xd50 [prestera] [ 529.143918] __prestera_router_fib_event_work+0x100/0x158 [prestera] [ 529.150313] process_one_work+0x208/0x488 [ 529.154348] worker_thread+0x4c/0x430 [ 529.158030] kthread+0x120/0x138 [ 529.161274] ret_from_fork+0x10/0x20 [ 529.164867] ---[ end trace 0000000000000000 ]--- and results in a non offloaded route: $ ip route 10.0.0.0/24 dev swp5 proto kernel scope link src 10.0.0.1 rt_trap 10.0.1.0/24 nhid 20 via 10.0.0.2 dev swp5 rt_trap When creating a route referencing a nexthop via its ID, the nexthop will be stored in a separate nh pointer instead of the array of nexthops in the fib_info struct. This causes issues since fib_info_nh() only handles the nexthops array, but not the separate nh pointer, and will loudly WARN about it. In contrast fib_info_nhc() handles both, but returns a fib_nh_common pointer instead of a fib_nh pointer. Luckily we only ever access fields from the fib_nh_common parts, so we can just replace all instances of fib_info_nh() with fib_info_nhc() and access the fields via their fib_nh_common names. This allows handling IPv4 routes with an external nexthop, and they now get offloaded as expected: $ ip route 10.0.0.0/24 dev swp5 proto kernel scope link src 10.0.0.1 rt_trap 10.0.1.0/24 nhid 20 via 10.0.0.2 dev swp5 offload rt_offload Fixes: 396b80cb5cc8 ("net: marvell: prestera: Add neighbour cache accounting") Signed-off-by: Jonas Gorski Acked-by: Elad Nachman Link: https://lore.kernel.org/r/20230804101220.247515-1-jonas.gorski@bisdn.de Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- .../ethernet/marvell/prestera/prestera_router.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c index a9a1028cb17b..de317179a7dc 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c @@ -166,11 +166,11 @@ prestera_util_neigh2nc_key(struct prestera_switch *sw, struct neighbour *n, static bool __prestera_fi_is_direct(struct fib_info *fi) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; if (fib_info_num_path(fi) == 1) { - fib_nh = fib_info_nh(fi, 0); - if (fib_nh->fib_nh_gw_family == AF_UNSPEC) + fib_nhc = fib_info_nhc(fi, 0); + if (fib_nhc->nhc_gw_family == AF_UNSPEC) return true; } @@ -261,7 +261,7 @@ static bool __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, struct net_device *dev) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; struct fib_result res; bool reachable; @@ -269,8 +269,8 @@ __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, if (!prestera_util_kern_get_route(&res, tb_id, addr)) if (prestera_fi_is_direct(res.fi)) { - fib_nh = fib_info_nh(res.fi, 0); - if (dev == fib_nh->fib_nh_dev) + fib_nhc = fib_info_nhc(res.fi, 0); + if (dev == fib_nhc->nhc_dev) reachable = true; } @@ -324,7 +324,7 @@ prestera_kern_fib_info_nhc(struct fib_notifier_info *info, int n) if (info->family == AF_INET) { fen4_info = container_of(info, struct fib_entry_notifier_info, info); - return &fib_info_nh(fen4_info->fi, n)->nh_common; + return fib_info_nhc(fen4_info->fi, n); } else if (info->family == AF_INET6) { fen6_info = container_of(info, struct fib6_entry_notifier_info, info); From 001b7d6706e20197b5a53c22bb293812943b696c Mon Sep 17 00:00:00 2001 From: Li Yang Date: Wed, 2 Aug 2023 14:13:47 -0500 Subject: [PATCH 0274/2093] net: phy: at803x: remove set/get wol callbacks for AR8032 commit d7791cec2304aea22eb2ada944e4d467302f5bfe upstream. Since the AR8032 part does not support wol, remove related callbacks from it. Fixes: 5800091a2061 ("net: phy: at803x: add support for AR8032 PHY") Signed-off-by: Li Yang Cc: David Bauer Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/at803x.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index d49965907561..61824a463df8 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -2087,8 +2087,6 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, - .set_wol = at803x_set_wol, - .get_wol = at803x_get_wol, .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ From 758dbcfb257e1aee0a310bae789c2af6ffe35d0f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 3 Aug 2023 16:42:53 +0300 Subject: [PATCH 0275/2093] net: dsa: ocelot: call dsa_tag_8021q_unregister() under rtnl_lock() on driver remove commit a94c16a2fda010866b8858a386a8bfbeba4f72c5 upstream. When the tagging protocol in current use is "ocelot-8021q" and we unbind the driver, we see this splat: $ echo '0000:00:00.2' > /sys/bus/pci/drivers/fsl_enetc/unbind mscc_felix 0000:00:00.5 swp0: left promiscuous mode sja1105 spi2.0: Link is Down DSA: tree 1 torn down mscc_felix 0000:00:00.5 swp2: left promiscuous mode sja1105 spi2.2: Link is Down DSA: tree 3 torn down fsl_enetc 0000:00:00.2 eno2: left promiscuous mode mscc_felix 0000:00:00.5: Link is Down ------------[ cut here ]------------ RTNL: assertion failed at net/dsa/tag_8021q.c (409) WARNING: CPU: 1 PID: 329 at net/dsa/tag_8021q.c:409 dsa_tag_8021q_unregister+0x12c/0x1a0 Modules linked in: CPU: 1 PID: 329 Comm: bash Not tainted 6.5.0-rc3+ #771 pc : dsa_tag_8021q_unregister+0x12c/0x1a0 lr : dsa_tag_8021q_unregister+0x12c/0x1a0 Call trace: dsa_tag_8021q_unregister+0x12c/0x1a0 felix_tag_8021q_teardown+0x130/0x150 felix_teardown+0x3c/0xd8 dsa_tree_teardown_switches+0xbc/0xe0 dsa_unregister_switch+0x168/0x260 felix_pci_remove+0x30/0x60 pci_device_remove+0x4c/0x100 device_release_driver_internal+0x188/0x288 device_links_unbind_consumers+0xfc/0x138 device_release_driver_internal+0xe0/0x288 device_driver_detach+0x24/0x38 unbind_store+0xd8/0x108 drv_attr_store+0x30/0x50 ---[ end trace 0000000000000000 ]--- ------------[ cut here ]------------ RTNL: assertion failed at net/8021q/vlan_core.c (376) WARNING: CPU: 1 PID: 329 at net/8021q/vlan_core.c:376 vlan_vid_del+0x1b8/0x1f0 CPU: 1 PID: 329 Comm: bash Tainted: G W 6.5.0-rc3+ #771 pc : vlan_vid_del+0x1b8/0x1f0 lr : vlan_vid_del+0x1b8/0x1f0 dsa_tag_8021q_unregister+0x8c/0x1a0 felix_tag_8021q_teardown+0x130/0x150 felix_teardown+0x3c/0xd8 dsa_tree_teardown_switches+0xbc/0xe0 dsa_unregister_switch+0x168/0x260 felix_pci_remove+0x30/0x60 pci_device_remove+0x4c/0x100 device_release_driver_internal+0x188/0x288 device_links_unbind_consumers+0xfc/0x138 device_release_driver_internal+0xe0/0x288 device_driver_detach+0x24/0x38 unbind_store+0xd8/0x108 drv_attr_store+0x30/0x50 DSA: tree 0 torn down This was somewhat not so easy to spot, because "ocelot-8021q" is not the default tagging protocol, and thus, not everyone who tests the unbinding path may have switched to it beforehand. The default felix_tag_npi_teardown() does not require rtnl_lock() to be held. Fixes: 7c83a7c539ab ("net: dsa: add a second tagger for Ocelot switches based on tag_8021q") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230803134253.2711124-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/ocelot/felix.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 4faabc4364aa..2d2c6f941272 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1606,8 +1606,10 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); struct dsa_port *dp; + rtnl_lock(); if (felix->tag_proto_ops) felix->tag_proto_ops->teardown(ds); + rtnl_unlock(); dsa_switch_for_each_available_port(dp, ds) ocelot_deinit_port(ocelot, dp->index); From 667ce6a0ff80dddbd56e85d1f6eee7dab6836096 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Mon, 7 Aug 2023 19:34:50 +0800 Subject: [PATCH 0276/2093] net: hns3: refactor hclge_mac_link_status_wait for interface reuse commit 08469dacfad25428b66549716811807203744f4f upstream. Some nic configurations could only be performed after link is down. So this patch refactor this API for reuse. Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230807113452.474224-3-shaojijie@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 50e956d6c3b2..d0d5333b9df4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -72,6 +72,8 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev); static void hclge_sync_promisc_mode(struct hclge_dev *hdev); static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt); static struct hnae3_ae_algo ae_algo; @@ -7656,10 +7658,9 @@ static void hclge_phy_link_status_wait(struct hclge_dev *hdev, } while (++i < HCLGE_PHY_LINK_STATUS_NUM); } -static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt) { -#define HCLGE_MAC_LINK_STATUS_NUM 100 - int link_status; int i = 0; int ret; @@ -7672,13 +7673,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) return 0; msleep(HCLGE_LINK_STATUS_MS); - } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + } while (++i < wait_cnt); return -EBUSY; } static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, bool is_phy) { +#define HCLGE_MAC_LINK_STATUS_NUM 100 + int link_ret; link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; @@ -7686,7 +7689,8 @@ static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, if (is_phy) hclge_phy_link_status_wait(hdev, link_ret); - return hclge_mac_link_status_wait(hdev, link_ret); + return hclge_mac_link_status_wait(hdev, link_ret, + HCLGE_MAC_LINK_STATUS_NUM); } static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) From 59bad9190ac7adbeafa8b90eaa99eba0aa8ebc54 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Mon, 7 Aug 2023 19:34:51 +0800 Subject: [PATCH 0277/2093] net: hns3: add wait until mac link down commit 6265e242f7b95f2c1195b42ec912b84ad161470e upstream. In some configure flow of hns3 driver, for example, change mtu, it will disable MAC through firmware before configuration. But firmware disables MAC asynchronously. The rx traffic may be not stopped in this case. So fixes it by waiting until mac link is down. Fixes: a9775bb64aa7 ("net: hns3: fix set and get link ksettings issue") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230807113452.474224-4-shaojijie@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d0d5333b9df4..6af2273f227c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -7569,6 +7569,8 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { +#define HCLGE_LINK_STATUS_WAIT_CNT 3 + struct hclge_desc desc; struct hclge_config_mac_mode_cmd *req = (struct hclge_config_mac_mode_cmd *)desc.data; @@ -7593,9 +7595,15 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "mac enable fail, ret =%d.\n", ret); + return; + } + + if (!enable) + hclge_mac_link_status_wait(hdev, HCLGE_LINK_STATUS_DOWN, + HCLGE_LINK_STATUS_WAIT_CNT); } static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, From 743f7c1762e098048ede8cdf8c89a118f8d12391 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Mon, 7 Aug 2023 19:34:52 +0800 Subject: [PATCH 0278/2093] net: hns3: fix deadlock issue when externel_lb and reset are executed together commit ac6257a3ae5db5193b1f19c268e4f72d274ddb88 upstream. When externel_lb and reset are executed together, a deadlock may occur: [ 3147.217009] INFO: task kworker/u321:0:7 blocked for more than 120 seconds. [ 3147.230483] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 3147.238999] task:kworker/u321:0 state:D stack: 0 pid: 7 ppid: 2 flags:0x00000008 [ 3147.248045] Workqueue: hclge hclge_service_task [hclge] [ 3147.253957] Call trace: [ 3147.257093] __switch_to+0x7c/0xbc [ 3147.261183] __schedule+0x338/0x6f0 [ 3147.265357] schedule+0x50/0xe0 [ 3147.269185] schedule_preempt_disabled+0x18/0x24 [ 3147.274488] __mutex_lock.constprop.0+0x1d4/0x5dc [ 3147.279880] __mutex_lock_slowpath+0x1c/0x30 [ 3147.284839] mutex_lock+0x50/0x60 [ 3147.288841] rtnl_lock+0x20/0x2c [ 3147.292759] hclge_reset_prepare+0x68/0x90 [hclge] [ 3147.298239] hclge_reset_subtask+0x88/0xe0 [hclge] [ 3147.303718] hclge_reset_service_task+0x84/0x120 [hclge] [ 3147.309718] hclge_service_task+0x2c/0x70 [hclge] [ 3147.315109] process_one_work+0x1d0/0x490 [ 3147.319805] worker_thread+0x158/0x3d0 [ 3147.324240] kthread+0x108/0x13c [ 3147.328154] ret_from_fork+0x10/0x18 In externel_lb process, the hns3 driver call napi_disable() first, then the reset happen, then the restore process of the externel_lb will fail, and will not call napi_enable(). When doing externel_lb again, napi_disable() will be double call, cause a deadlock of rtnl_lock(). This patch use the HNS3_NIC_STATE_DOWN state to protect the calling of napi_disable() and napi_enable() in externel_lb process, just as the usage in ndo_stop() and ndo_start(). Fixes: 04b6ba143521 ("net: hns3: add support for external loopback test") Signed-off-by: Yonglong Liu Signed-off-by: Jijie Shao Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230807113452.474224-5-shaojijie@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 248f15dac86b..61f833d61f58 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5854,6 +5854,9 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running) if (!if_running) return; + if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + netif_carrier_off(ndev); netif_tx_disable(ndev); @@ -5882,7 +5885,16 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running) if (!if_running) return; - hns3_nic_reset_all_ring(priv->ae_handle); + if (hns3_nic_resetting(ndev)) + return; + + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + + if (hns3_nic_reset_all_ring(priv->ae_handle)) + return; + + clear_bit(HNS3_NIC_STATE_DOWN, &priv->state); for (i = 0; i < priv->vector_num; i++) hns3_vector_enable(&priv->tqp_vector[i]); From 0b10d8d1cf85088b42ba5ee2e7bbb6f5a7db0b4f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 10:52:31 +0300 Subject: [PATCH 0279/2093] nexthop: Fix infinite nexthop dump when using maximum nexthop ID commit 913f60cacda73ccac8eead94983e5884c03e04cd upstream. A netlink dump callback can return a positive number to signal that more information needs to be dumped or zero to signal that the dump is complete. In the second case, the core netlink code will append the NLMSG_DONE message to the skb in order to indicate to user space that the dump is complete. The nexthop dump callback always returns a positive number if nexthops were filled in the provided skb, even if the dump is complete. This means that a dump will span at least two recvmsg() calls as long as nexthops are present. In the last recvmsg() call the dump callback will not fill in any nexthops because the previous call indicated that the dump should restart from the last dumped nexthop ID plus one. # ip nexthop add id 1 blackhole # strace -e sendto,recvmsg -s 5 ip nexthop sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOP, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691394315, nlmsg_pid=0}, {nh_family=AF_UNSPEC, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 36 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[{nlmsg_len=36, nlmsg_type=RTM_NEWNEXTHOP, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394315, nlmsg_pid=343}, {nh_family=AF_INET, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}, [[{nla_len=8, nla_type=NHA_ID}, 1], {nla_len=4, nla_type=NHA_BLACKHOLE}]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 36 id 1 blackhole recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 20 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394315, nlmsg_pid=343}, 0], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 20 +++ exited with 0 +++ This behavior is both inefficient and buggy. If the last nexthop to be dumped had the maximum ID of 0xffffffff, then the dump will restart from 0 (0xffffffff + 1) and never end: # ip nexthop add id $((2**32-1)) blackhole # ip nexthop id 4294967295 blackhole id 4294967295 blackhole [...] Fix by adjusting the dump callback to return zero when the dump is complete. After the fix only one recvmsg() call is made and the NLMSG_DONE message is appended to the RTM_NEWNEXTHOP response: # ip nexthop add id $((2**32-1)) blackhole # strace -e sendto,recvmsg -s 5 ip nexthop sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOP, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691394080, nlmsg_pid=0}, {nh_family=AF_UNSPEC, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 56 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[[{nlmsg_len=36, nlmsg_type=RTM_NEWNEXTHOP, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394080, nlmsg_pid=342}, {nh_family=AF_INET, nh_scope=RT_SCOPE_UNIVERSE, nh_protocol=RTPROT_UNSPEC, nh_flags=0}, [[{nla_len=8, nla_type=NHA_ID}, 4294967295], {nla_len=4, nla_type=NHA_BLACKHOLE}]], [{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691394080, nlmsg_pid=342}, 0]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 56 id 4294967295 blackhole +++ exited with 0 +++ Note that if the NLMSG_DONE message cannot be appended because of size limitations, then another recvmsg() will be needed, but the core netlink code will not invoke the dump callback and simply reply with a NLMSG_DONE message since it knows that the callback previously returned zero. Add a test that fails before the fix: # ./fib_nexthops.sh -t basic [...] TEST: Maximum nexthop ID dump [FAIL] [...] And passes after it: # ./fib_nexthops.sh -t basic [...] TEST: Maximum nexthop ID dump [ OK ] [...] Fixes: ab84be7e54fc ("net: Initial nexthop code") Reported-by: Petr Machata Closes: https://lore.kernel.org/netdev/87sf91enuf.fsf@nvidia.com/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230808075233.3337922-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/nexthop.c | 6 +----- tools/testing/selftests/net/fib_nexthops.sh | 5 +++++ 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d8ef05347fd9..cbe6e3ace1da 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0f5e88c8f4ff..10aa059b9f06 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1981,6 +1981,11 @@ basic() run_cmd "$IP link set dev lo up" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) blackhole" + run_cmd "timeout 5 $IP nexthop" + log_test $? 0 "Maximum nexthop ID dump" + # # groups # From 8d6df2c523e22a280ca6cef47a5daf344b69a60e Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 10:52:32 +0300 Subject: [PATCH 0280/2093] nexthop: Make nexthop bucket dump more efficient commit f10d3d9df49d9e6ee244fda6ca264f901a9c5d85 upstream. rtm_dump_nexthop_bucket_nh() is used to dump nexthop buckets belonging to a specific resilient nexthop group. The function returns a positive return code (the skb length) upon both success and failure. The above behavior is problematic. When a complete nexthop bucket dump is requested, the function that walks the different nexthops treats the non-zero return code as an error. This causes buckets belonging to different resilient nexthop groups to be dumped using different buffers even if they can all fit in the same buffer: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id 10 group 1 type resilient buckets 1 # ip nexthop add id 20 group 1 type resilient buckets 1 # strace -e recvmsg -s 0 ip nexthop bucket [...] recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[...], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 64 id 10 index 0 idle_time 10.27 nhid 1 [...] recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[...], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 64 id 20 index 0 idle_time 6.44 nhid 1 [...] Fix by only returning a non-zero return code when an error occurred and restarting the dump from the bucket index we failed to fill in. This allows buckets belonging to different resilient nexthop groups to be dumped using the same buffer: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id 10 group 1 type resilient buckets 1 # ip nexthop add id 20 group 1 type resilient buckets 1 # strace -e recvmsg -s 0 ip nexthop bucket [...] recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[...], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 128 id 10 index 0 idle_time 30.21 nhid 1 id 20 index 0 idle_time 26.7 nhid 1 [...] While this change is more of a performance improvement change than an actual bug fix, it is a prerequisite for a subsequent patch that does fix a bug. Fixes: 8a1bbabb034d ("nexthop: Add netlink handlers for bucket dump") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230808075233.3337922-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/nexthop.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index cbe6e3ace1da..1d1fb180ceda 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3363,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, From 87d7e140081fe97fbf329f7370b18799f1da7de3 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 10:52:33 +0300 Subject: [PATCH 0281/2093] nexthop: Fix infinite nexthop bucket dump when using maximum nexthop ID commit 8743aeff5bc4dcb5b87b43765f48d5ac3ad7dd9f upstream. A netlink dump callback can return a positive number to signal that more information needs to be dumped or zero to signal that the dump is complete. In the second case, the core netlink code will append the NLMSG_DONE message to the skb in order to indicate to user space that the dump is complete. The nexthop bucket dump callback always returns a positive number if nexthop buckets were filled in the provided skb, even if the dump is complete. This means that a dump will span at least two recvmsg() calls as long as nexthop buckets are present. In the last recvmsg() call the dump callback will not fill in any nexthop buckets because the previous call indicated that the dump should restart from the last dumped nexthop ID plus one. # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id 10 group 1 type resilient buckets 2 # strace -e sendto,recvmsg -s 5 ip nexthop bucket sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOPBUCKET, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691396980, nlmsg_pid=0}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 128 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[[{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396980, nlmsg_pid=347}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], [{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396980, nlmsg_pid=347}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 128 id 10 index 0 idle_time 6.66 nhid 1 id 10 index 1 idle_time 6.66 nhid 1 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 20 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396980, nlmsg_pid=347}, 0], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 20 +++ exited with 0 +++ This behavior is both inefficient and buggy. If the last nexthop to be dumped had the maximum ID of 0xffffffff, then the dump will restart from 0 (0xffffffff + 1) and never end: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id $((2**32-1)) group 1 type resilient buckets 2 # ip nexthop bucket id 4294967295 index 0 idle_time 5.55 nhid 1 id 4294967295 index 1 idle_time 5.55 nhid 1 id 4294967295 index 0 idle_time 5.55 nhid 1 id 4294967295 index 1 idle_time 5.55 nhid 1 [...] Fix by adjusting the dump callback to return zero when the dump is complete. After the fix only one recvmsg() call is made and the NLMSG_DONE message is appended to the RTM_NEWNEXTHOPBUCKET responses: # ip link add name dummy1 up type dummy # ip nexthop add id 1 dev dummy1 # ip nexthop add id $((2**32-1)) group 1 type resilient buckets 2 # strace -e sendto,recvmsg -s 5 ip nexthop bucket sendto(3, [[{nlmsg_len=24, nlmsg_type=RTM_GETNEXTHOPBUCKET, nlmsg_flags=NLM_F_REQUEST|NLM_F_DUMP, nlmsg_seq=1691396737, nlmsg_pid=0}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], {nlmsg_len=0, nlmsg_type=0 /* NLMSG_??? */, nlmsg_flags=0, nlmsg_seq=0, nlmsg_pid=0}], 152, 0, NULL, 0) = 152 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=NULL, iov_len=0}], msg_iovlen=1, msg_controllen=0, msg_flags=MSG_TRUNC}, MSG_PEEK|MSG_TRUNC) = 148 recvmsg(3, {msg_name={sa_family=AF_NETLINK, nl_pid=0, nl_groups=00000000}, msg_namelen=12, msg_iov=[{iov_base=[[{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396737, nlmsg_pid=350}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], [{nlmsg_len=64, nlmsg_type=RTM_NEWNEXTHOPBUCKET, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396737, nlmsg_pid=350}, {family=AF_UNSPEC, data="\x00\x00\x00\x00\x00"...}], [{nlmsg_len=20, nlmsg_type=NLMSG_DONE, nlmsg_flags=NLM_F_MULTI, nlmsg_seq=1691396737, nlmsg_pid=350}, 0]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 148 id 4294967295 index 0 idle_time 6.61 nhid 1 id 4294967295 index 1 idle_time 6.61 nhid 1 +++ exited with 0 +++ Note that if the NLMSG_DONE message cannot be appended because of size limitations, then another recvmsg() will be needed, but the core netlink code will not invoke the dump callback and simply reply with a NLMSG_DONE message since it knows that the callback previously returned zero. Add a test that fails before the fix: # ./fib_nexthops.sh -t basic_res [...] TEST: Maximum nexthop ID dump [FAIL] [...] And passes after it: # ./fib_nexthops.sh -t basic_res [...] TEST: Maximum nexthop ID dump [ OK ] [...] Fixes: 8a1bbabb034d ("nexthop: Add netlink handlers for bucket dump") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230808075233.3337922-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/nexthop.c | 6 +----- tools/testing/selftests/net/fib_nexthops.sh | 5 +++++ 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 1d1fb180ceda..9cc287902454 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3424,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 10aa059b9f06..df8d90b51867 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2206,6 +2206,11 @@ basic_res() run_cmd "$IP nexthop bucket list fdb" log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) group 1/2 type resilient buckets 4" + run_cmd "timeout 5 $IP nexthop bucket" + log_test $? 0 "Maximum nexthop ID dump" + # # resilient nexthop buckets get requests # From c4f7de3e8ce1799b12bdd1520e3ebd49d2e12f42 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Wed, 9 Aug 2023 10:09:02 +0800 Subject: [PATCH 0282/2093] net: hns3: fix strscpy causing content truncation issue commit 5e3d20617b055e725e785e0058426368269949f3 upstream. hns3_dbg_fill_content()/hclge_dbg_fill_content() is aim to integrate some items to a string for content, and we add '\n' and '\0' in the last two bytes of content. strscpy() will add '\0' in the last byte of destination buffer(one of items), it result in finishing content print ahead of schedule and some dump content truncation. One Error log shows as below: cat mac_list/uc UC MAC_LIST: Expected: UC MAC_LIST: FUNC_ID MAC_ADDR STATE pf 00:2b:19:05:03:00 ACTIVE The destination buffer is length-bounded and not required to be NUL-terminated, so just change strscpy() to memcpy() to fix it. Fixes: 1cf3d5567f27 ("net: hns3: fix strncpy() not using dest-buf length as length issue") Signed-off-by: Hao Chen Signed-off-by: Jijie Shao Link: https://lore.kernel.org/r/20230809020902.1941471-1-shaojijie@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 4 ++-- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index f6ededec5a4f..69d1549e63a9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -458,9 +458,9 @@ static void hns3_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 726062e51293..5cb8f1818e51 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -110,9 +110,9 @@ static void hclge_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; From dff220037148304571cf78968c1c80488cc2ec91 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 12 Jul 2023 18:26:45 +0530 Subject: [PATCH 0283/2093] dmaengine: mcf-edma: Fix a potential un-allocated memory access commit 0a46781c89dece85386885a407244ca26e5c1c44 upstream. When 'mcf_edma' is allocated, some space is allocated for a flexible array at the end of the struct. 'chans' item are allocated, that is to say 'pdata->dma_channels'. Then, this number of item is stored in 'mcf_edma->n_chans'. A few lines later, if 'mcf_edma->n_chans' is 0, then a default value of 64 is set. This ends to no space allocated by devm_kzalloc() because chans was 0, but 64 items are read and/or written in some not allocated memory. Change the logic to define a default value before allocating the memory. Fixes: e7a3ff92eaf1 ("dmaengine: fsl-edma: add ColdFire mcf5441x edma support") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/f55d914407c900828f6fad3ea5fa791a5f17b9a4.1685172449.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/dma/mcf-edma.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c index e12b754e6398..60d3c5f09ad6 100644 --- a/drivers/dma/mcf-edma.c +++ b/drivers/dma/mcf-edma.c @@ -191,7 +191,13 @@ static int mcf_edma_probe(struct platform_device *pdev) return -EINVAL; } - chans = pdata->dma_channels; + if (!pdata->dma_channels) { + dev_info(&pdev->dev, "setting default channel number to 64"); + chans = 64; + } else { + chans = pdata->dma_channels; + } + len = sizeof(*mcf_edma) + sizeof(*mcf_chan) * chans; mcf_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL); if (!mcf_edma) @@ -203,11 +209,6 @@ static int mcf_edma_probe(struct platform_device *pdev) mcf_edma->drvdata = &mcf_data; mcf_edma->big_endian = 1; - if (!mcf_edma->n_chans) { - dev_info(&pdev->dev, "setting default channel number to 64"); - mcf_edma->n_chans = 64; - } - mutex_init(&mcf_edma->fsl_edma_mutex); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); From ab06983c5bbdacbcc9c03c6d9ae8138620924188 Mon Sep 17 00:00:00 2001 From: Zhang Jianhua Date: Sat, 22 Jul 2023 15:32:44 +0000 Subject: [PATCH 0284/2093] dmaengine: owl-dma: Modify mismatched function name commit 74d7221c1f9c9f3a8c316a3557ca7dca8b99d14c upstream. No functional modification involved. drivers/dma/owl-dma.c:208: warning: expecting prototype for struct owl_dma_pchan. Prototype was for struct owl_dma_vchan instead HDRTEST usr/include/sound/asequencer.h Fixes: 47e20577c24d ("dmaengine: Add Actions Semi Owl family S900 DMA driver") Signed-off-by: Zhang Jianhua Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/20230722153244.2086949-1-chris.zjh@huawei.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/dma/owl-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 95a462a1f511..b6e0ac8314e5 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -192,7 +192,7 @@ struct owl_dma_pchan { }; /** - * struct owl_dma_pchan - Wrapper for DMA ENGINE channel + * struct owl_dma_vchan - Wrapper for DMA ENGINE channel * @vc: wrapped virtual channel * @pchan: the physical channel utilized by this channel * @txd: active transaction on this channel From a824d012ad8f736459398e9c1d5bc0f034c72e5e Mon Sep 17 00:00:00 2001 From: Daniel Jurgens Date: Tue, 11 Jul 2023 00:28:10 +0300 Subject: [PATCH 0285/2093] net/mlx5: Allow 0 for total host VFs commit 2dc2b3922d3c0f52d3a792d15dcacfbc4cc76b8f upstream. When querying eswitch functions 0 is a valid number of host VFs. After introducing ARM SRIOV falling through to getting the max value from PCI results in using the total VFs allowed on the ARM for the host. Fixes: 86eec50beaf3 ("net/mlx5: Support querying max VFs from device"); Signed-off-by: Daniel Jurgens Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 20d7662c10fb..5f2195e65dd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -264,8 +264,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) host_total_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_total_vfs); kvfree(out); - if (host_total_vfs) - return host_total_vfs; + return host_total_vfs; } done: From 4276f3e7ae4a1cfbe01cc807deca680bb9853026 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sun, 30 Jul 2023 09:26:27 +0300 Subject: [PATCH 0286/2093] net/mlx5: LAG, Check correct bucket when modifying LAG commit 86ed7b773c01ba71617538b3b107c33fd9cf90b8 upstream. Cited patch introduced buckets in hash mode, but missed to update the ports/bucket check when modifying LAG. Fix the check. Fixes: 352899f384d4 ("net/mlx5: Lag, use buckets in hash mode") Signed-off-by: Shay Drory Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index d3a3fe4ce670..7d9bbb494d95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -574,7 +574,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, for (i = 0; i < ldev->ports; i++) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; - if (ldev->v2p_map[i] == ports[i]) + if (ldev->v2p_map[idx] == ports[idx]) continue; dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[ports[idx] - 1].dev, From 88ec484ef8e2de7a7819b461ff0bec60fd40e813 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 19 Jul 2023 11:33:44 +0300 Subject: [PATCH 0287/2093] net/mlx5: Skip clock update work when device is in error state commit d006207625657322ba8251b6e7e829f9659755dc upstream. When device is in error state, marked by the flag MLX5_DEVICE_STATE_INTERNAL_ERROR, the HW and PCI may not be accessible and so clock update work should be skipped. Furthermore, such access through PCI in error state, after calling mlx5_pci_disable_device() can result in failing to recover from pci errors. Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support") Reported-and-tested-by: Ganesh G R Closes: https://lore.kernel.org/netdev/9bdb9b9d-140a-7a28-f0de-2e64e873c068@nvidia.com Signed-off-by: Moshe Shemesh Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index d7ddfc489536..2ac255bb918b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -198,10 +198,15 @@ static void mlx5_timestamp_overflow(struct work_struct *work) clock = container_of(timer, struct mlx5_clock, timer); mdev = container_of(clock, struct mlx5_core_dev, clock); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&timer->tc); mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); + +out: schedule_delayed_work(&timer->overflow_work, timer->overflow_period); } From ad0f73cbace470fb087a822fb3dc690980004414 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Sun, 23 Jul 2023 11:03:01 +0300 Subject: [PATCH 0288/2093] net/mlx5: Reload auxiliary devices in pci error handlers commit aab8e1a200b926147db51e3f82fd07bb9edf6a98 upstream. Handling pci errors should fully teardown and load back auxiliary devices, same as done through mlx5 health recovery flow. Fixes: 72ed5d5624af ("net/mlx5: Suspend auxiliary devices only in case of PCI device suspend") Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 077204929fe4..6ab0642e9de7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1794,7 +1794,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); - mlx5_unload_one(dev, true); + mlx5_unload_one(dev, false); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); From 2c5dd8805e6cc11c28de9c5716f205545bdc482a Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 9 Aug 2023 17:10:34 -0500 Subject: [PATCH 0289/2093] ibmvnic: Enforce stronger sanity checks on login response commit db17ba719bceb52f0ae4ebca0e4c17d9a3bebf05 upstream. Ensure that all offsets in a login response buffer are within the size of the allocated response buffer. Any offsets or lengths that surpass the allocation are likely the result of an incomplete response buffer. In these cases, a full reset is necessary. When attempting to login, the ibmvnic device will allocate a response buffer and pass a reference to the VIOS. The VIOS will then send the ibmvnic device a LOGIN_RSP CRQ to signal that the buffer has been filled with data. If the ibmvnic device does not get a response in 20 seconds, the old buffer is freed and a new login request is sent. With 2 outstanding requests, any LOGIN_RSP CRQ's could be for the older login request. If this is the case then the login response buffer (which is for the newer login request) could be incomplete and contain invalid data. Therefore, we must enforce strict sanity checks on the response buffer values. Testing has shown that the `off_rxadd_buff_size` value is filled in last by the VIOS and will be the smoking gun for these circumstances. Until VIOS can implement a mechanism for tracking outstanding response buffers and a method for mapping a LOGIN_RSP CRQ to a particular login response buffer, the best ibmvnic can do in this situation is perform a full reset. Fixes: dff515a3e71d ("ibmvnic: Harden device login requests") Signed-off-by: Nick Child Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809221038.51296-1-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmvnic.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index bc97f24b0827..10a51dd84cd6 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -5192,6 +5192,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, int num_tx_pools; int num_rx_pools; u64 *size_array; + u32 rsp_len; int i; /* CHECK: Test/set of login_pending does not need to be atomic @@ -5243,6 +5244,23 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } + + rsp_len = be32_to_cpu(login_rsp->len); + if (be32_to_cpu(login->login_rsp_len) < rsp_len || + rsp_len <= be32_to_cpu(login_rsp->off_txsubm_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_buff_size) || + rsp_len <= be32_to_cpu(login_rsp->off_supp_tx_desc)) { + /* This can happen if a login request times out and there are + * 2 outstanding login requests sent, the LOGIN_RSP crq + * could have been for the older login request. So we are + * parsing the newer response buffer which may be incomplete + */ + dev_err(dev, "FATAL: Login rsp offsets/lengths invalid\n"); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); + return -EIO; + } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); /* variable buffer sizes are not supported, so just read the From 24556c1cc9dbbf4efc022f932d0860c2f75f4b80 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 9 Aug 2023 17:10:35 -0500 Subject: [PATCH 0290/2093] ibmvnic: Unmap DMA login rsp buffer on send login fail commit 411c565b4bc63e9584a8493882bd566e35a90588 upstream. If the LOGIN CRQ fails to send then we must DMA unmap the response buffer. Previously, if the CRQ failed then the memory was freed without DMA unmapping. Fixes: c98d9cc4170d ("ibmvnic: send_login should check for crq errors") Signed-off-by: Nick Child Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809221038.51296-2-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmvnic.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 10a51dd84cd6..b55c7fc7d2e0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4626,11 +4626,14 @@ static int send_login(struct ibmvnic_adapter *adapter) if (rc) { adapter->login_pending = false; netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); - goto buf_rsp_map_failed; + goto buf_send_failed; } return 0; +buf_send_failed: + dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, + DMA_FROM_DEVICE); buf_rsp_map_failed: kfree(login_rsp_buffer); adapter->login_rsp_buf = NULL; From 31ccd1ba20d8007e13f0b3175b7c394d900759f2 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 9 Aug 2023 17:10:36 -0500 Subject: [PATCH 0291/2093] ibmvnic: Handle DMA unmapping of login buffs in release functions commit d78a671eb8996af19d6311ecdee9790d2fa479f0 upstream. Rather than leaving the DMA unmapping of the login buffers to the login response handler, move this work into the login release functions. Previously, these functions were only used for freeing the allocated buffers. This could lead to issues if there are more than one outstanding login buffer requests, which is possible if a login request times out. If a login request times out, then there is another call to send login. The send login function makes a call to the login buffer release function. In the past, this freed the buffers but did not DMA unmap. Therefore, the VIOS could still write to the old login (now freed) buffer. It is for this reason that it is a good idea to leave the DMA unmap call to the login buffers release function. Since the login buffer release functions now handle DMA unmapping, remove the duplicate DMA unmapping in handle_login_rsp(). Fixes: dff515a3e71d ("ibmvnic: Harden device login requests") Signed-off-by: Nick Child Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809221038.51296-3-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmvnic.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index b55c7fc7d2e0..4dd6c4bfd55e 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1397,12 +1397,22 @@ static int ibmvnic_login(struct net_device *netdev) static void release_login_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_buf_token, + adapter->login_buf_sz, DMA_TO_DEVICE); kfree(adapter->login_buf); adapter->login_buf = NULL; } static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_rsp_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); kfree(adapter->login_rsp_buf); adapter->login_rsp_buf = NULL; } @@ -5207,11 +5217,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, } adapter->login_pending = false; - dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, - DMA_TO_DEVICE); - dma_unmap_single(dev, adapter->login_rsp_buf_token, - adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); - /* If the number of queues requested can't be allocated by the * server, the login response will return with code 1. We will need * to resend the login buffer with fewer queues requested. From 206ccf4f0977a76da38c2c88ba354d7eea9bbf81 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 9 Aug 2023 17:10:37 -0500 Subject: [PATCH 0292/2093] ibmvnic: Do partial reset on login failure commit 23cc5f667453ca7645a24c8d21bf84dbf61107b2 upstream. Perform a partial reset before sending a login request if any of the following are true: 1. If a previous request times out. This can be dangerous because the VIOS could still receive the old login request at any point after the timeout. Therefore, it is best to re-register the CRQ's and sub-CRQ's before retrying. 2. If the previous request returns an error that is not described in PAPR. PAPR provides procedures if the login returns with partial success or aborted return codes (section L.5.1) but other values do not have a defined procedure. Previously, these conditions just returned error from the login function rather than trying to resolve the issue. This can cause further issues since most callers of the login function are not prepared to handle an error when logging in. This improper cleanup can lead to the device being permanently DOWN'd. For example, if the VIOS believes that the device is already logged in then it will return INVALID_STATE (-7). If we never re-register CRQ's then it will always think that the device is already logged in. This leaves the device inoperable. The partial reset involves freeing the sub-CRQs, freeing the CRQ then registering and initializing a new CRQ and sub-CRQs. This essentially restarts all communication with VIOS to allow for a fresh login attempt that will be unhindered by any previous failed attempts. Fixes: dff515a3e71d ("ibmvnic: Harden device login requests") Signed-off-by: Nick Child Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809221038.51296-4-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmvnic.c | 46 ++++++++++++++++++++++++++---- 1 file changed, 40 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4dd6c4bfd55e..a47c1e3a5728 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -96,6 +96,8 @@ static int pending_scrq(struct ibmvnic_adapter *, static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, struct ibmvnic_sub_crq_queue *); static int ibmvnic_poll(struct napi_struct *napi, int data); +static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter); +static inline void reinit_init_done(struct ibmvnic_adapter *adapter); static void send_query_map(struct ibmvnic_adapter *adapter); static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8); static int send_request_unmap(struct ibmvnic_adapter *, u8); @@ -1336,11 +1338,9 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out, retrying...\n"); - retry = true; - adapter->init_done_rc = 0; - retry_count++; - continue; + netdev_warn(netdev, "Login timed out\n"); + adapter->login_pending = false; + goto partial_reset; } if (adapter->init_done_rc == ABORTED) { @@ -1385,7 +1385,41 @@ static int ibmvnic_login(struct net_device *netdev) } else if (adapter->init_done_rc) { netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", adapter->init_done_rc); - return -EIO; + +partial_reset: + /* adapter login failed, so free any CRQs or sub-CRQs + * and register again before attempting to login again. + * If we don't do this then the VIOS may think that + * we are already logged in and reject any subsequent + * attempts + */ + netdev_warn(netdev, + "Freeing and re-registering CRQs before attempting to login again\n"); + retry = true; + adapter->init_done_rc = 0; + retry_count++; + release_sub_crqs(adapter, true); + reinit_init_done(adapter); + release_crq_queue(adapter); + /* If we don't sleep here then we risk an unnecessary + * failover event from the VIOS. This is a known VIOS + * issue caused by a vnic device freeing and registering + * a CRQ too quickly. + */ + msleep(1500); + rc = init_crq_queue(adapter); + if (rc) { + netdev_err(netdev, "login recovery: init CRQ failed %d\n", + rc); + return -EIO; + } + + rc = ibmvnic_reset_init(adapter, false); + if (rc) { + netdev_err(netdev, "login recovery: Reset init failed %d\n", + rc); + return -EIO; + } } } while (retry); From 5e17b8ee64c142c72a33885b51df13e44eb62c5d Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 9 Aug 2023 17:10:38 -0500 Subject: [PATCH 0293/2093] ibmvnic: Ensure login failure recovery is safe from other resets commit 6db541ae279bd4e76dbd939e5fbf298396166242 upstream. If a login request fails, the recovery process should be protected against parallel resets. It is a known issue that freeing and registering CRQ's in quick succession can result in a failover CRQ from the VIOS. Processing a failover during login recovery is dangerous for two reasons: 1. This will result in two parallel initialization processes, this can cause serious issues during login. 2. It is possible that the failover CRQ is received but never executed. We get notified of a pending failover through a transport event CRQ. The reset is not performed until a INIT CRQ request is received. Previously, if CRQ init fails during login recovery, then the ibmvnic irq is freed and the login process returned error. If failover_pending is true (a transport event was received), then the ibmvnic device would never be able to process the reset since it cannot receive the CRQ_INIT request due to the irq being freed. This leaved the device in a inoperable state. Therefore, the login failure recovery process must be hardened against these possible issues. Possible failovers (due to quick CRQ free and init) must be avoided and any issues during re-initialization should be dealt with instead of being propagated up the stack. This logic is similar to that of ibmvnic_probe(). Fixes: dff515a3e71d ("ibmvnic: Harden device login requests") Signed-off-by: Nick Child Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809221038.51296-5-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmvnic.c | 68 +++++++++++++++++++++--------- 1 file changed, 47 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a47c1e3a5728..157be4e9be4b 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -115,6 +115,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); +static void flush_reset_queue(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -1316,8 +1317,8 @@ static const char *adapter_state_to_string(enum vnic_state state) static int ibmvnic_login(struct net_device *netdev) { + unsigned long flags, timeout = msecs_to_jiffies(20000); struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -1382,6 +1383,7 @@ static int ibmvnic_login(struct net_device *netdev) "SCRQ irq initialization failed\n"); return rc; } + /* Default/timeout error handling, reset and start fresh */ } else if (adapter->init_done_rc) { netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", adapter->init_done_rc); @@ -1397,29 +1399,53 @@ static int ibmvnic_login(struct net_device *netdev) "Freeing and re-registering CRQs before attempting to login again\n"); retry = true; adapter->init_done_rc = 0; - retry_count++; release_sub_crqs(adapter, true); - reinit_init_done(adapter); - release_crq_queue(adapter); - /* If we don't sleep here then we risk an unnecessary - * failover event from the VIOS. This is a known VIOS - * issue caused by a vnic device freeing and registering - * a CRQ too quickly. + /* Much of this is similar logic as ibmvnic_probe(), + * we are essentially re-initializing communication + * with the server. We really should not run any + * resets/failovers here because this is already a form + * of reset and we do not want parallel resets occurring */ - msleep(1500); - rc = init_crq_queue(adapter); - if (rc) { - netdev_err(netdev, "login recovery: init CRQ failed %d\n", - rc); - return -EIO; - } + do { + reinit_init_done(adapter); + /* Clear any failovers we got in the previous + * pass since we are re-initializing the CRQ + */ + adapter->failover_pending = false; + release_crq_queue(adapter); + /* If we don't sleep here then we risk an + * unnecessary failover event from the VIOS. + * This is a known VIOS issue caused by a vnic + * device freeing and registering a CRQ too + * quickly. + */ + msleep(1500); + /* Avoid any resets, since we are currently + * resetting. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, + flags); - rc = ibmvnic_reset_init(adapter, false); - if (rc) { - netdev_err(netdev, "login recovery: Reset init failed %d\n", - rc); - return -EIO; - } + rc = init_crq_queue(adapter); + if (rc) { + netdev_err(netdev, "login recovery: init CRQ failed %d\n", + rc); + return -EIO; + } + + rc = ibmvnic_reset_init(adapter, false); + if (rc) + netdev_err(netdev, "login recovery: Reset init failed %d\n", + rc); + /* IBMVNIC_CRQ_INIT will return EAGAIN if it + * fails, since ibmvnic_reset_init will free + * irq's in failure, we won't be able to receive + * new CRQs so we need to keep trying. probe() + * handles this similarly. + */ + } while (rc == -EAGAIN && retry_count++ < retries); } } while (retry); From 227bd2c1eab1d885665d68a803dacb2c47f32617 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 10 Aug 2023 18:00:44 -0400 Subject: [PATCH 0294/2093] gpio: ws16c48: Fix off-by-one error in WS16C48 resource region extent commit 33f83d13ded164cd49ce2a3bd2770115abc64e6f upstream. The WinSystems WS16C48 I/O address region spans offsets 0x0 through 0xA, which is a total of 11 bytes. Fix the WS16C48_EXTENT define to the correct value of 11 so that access to necessary device registers is properly requested in the ws16c48_probe() callback by the devm_request_region() function call. Fixes: 2c05a0f29f41 ("gpio: ws16c48: Implement and utilize register structures") Cc: stable@vger.kernel.org Cc: Paul Demetrotion Signed-off-by: William Breathitt Gray Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpio-ws16c48.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-ws16c48.c b/drivers/gpio/gpio-ws16c48.c index e73885a4dc32..afb42a8e916f 100644 --- a/drivers/gpio/gpio-ws16c48.c +++ b/drivers/gpio/gpio-ws16c48.c @@ -18,7 +18,7 @@ #include #include -#define WS16C48_EXTENT 10 +#define WS16C48_EXTENT 11 #define MAX_NUM_WS16C48 max_num_isa_dev(WS16C48_EXTENT) static unsigned int base[MAX_NUM_WS16C48]; From b8cd871d0a189a0fd8b8839231c73c313cd0d56e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 1 Aug 2023 21:09:51 +0200 Subject: [PATCH 0295/2093] gpio: sim: mark the GPIO chip as a one that can sleep commit 5a78d5db9c90c9dc84212f40a5f2687b7cafc8ec upstream. Simulated chips use a mutex for synchronization in driver callbacks so they must not be called from interrupt context. Set the can_sleep field of the GPIO chip to true to force users to only use threaded irqs. Fixes: cb8c474e79be ("gpio: sim: new testing module") Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpio-sim.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 803676e307d7..fef12e57b1f1 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -425,6 +425,7 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) gc->set_config = gpio_sim_set_config; gc->to_irq = gpio_sim_to_irq; gc->free = gpio_sim_free; + gc->can_sleep = true; ret = devm_gpiochip_add_data(dev, gc, chip); if (ret) From 4e18c827d61b105eacc7e2a65871a92eece8c5af Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 21 Jul 2023 16:09:43 -0400 Subject: [PATCH 0296/2093] btrfs: wait for actual caching progress during allocation commit fc1f91b9231a28fba333f931a031bf776bc6ef0e upstream. Recently we've been having mysterious hangs while running generic/475 on the CI system. This turned out to be something like this: Task 1 dmsetup suspend --nolockfs -> __dm_suspend -> dm_wait_for_completion -> dm_wait_for_bios_completion -> Unable to complete because of IO's on a plug in Task 2 Task 2 wb_workfn -> wb_writeback -> blk_start_plug -> writeback_sb_inodes -> Infinite loop unable to make an allocation Task 3 cache_block_group ->read_extent_buffer_pages ->Waiting for IO to complete that can't be submitted because Task 1 suspended the DM device The problem here is that we need Task 2 to be scheduled completely for the blk plug to flush. Normally this would happen, we normally wait for the block group caching to finish (Task 3), and this schedule would result in the block plug flushing. However if there's enough free space available from the current caching to satisfy the allocation we won't actually wait for the caching to complete. This check however just checks that we have enough space, not that we can make the allocation. In this particular case we were trying to allocate 9MiB, and we had 10MiB of free space, but we didn't have 9MiB of contiguous space to allocate, and thus the allocation failed and we looped. We specifically don't cycle through the FFE loop until we stop finding cached block groups because we don't want to allocate new block groups just because we're caching, so we short circuit the normal loop once we hit LOOP_CACHING_WAIT and we found a caching block group. This is normally fine, except in this particular case where the caching thread can't make progress because the DM device has been suspended. Fix this by not only waiting for free space to >= the amount of space we want to allocate, but also that we make some progress in caching from the time we start waiting. This will keep us from busy looping when the caching is taking a while but still theoretically has enough space for us to allocate from, and fixes this particular case by forcing us to actually sleep and wait for forward progress, which will flush the plug. With this fix we're no longer hanging with generic/475. CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Boris Burkov Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/block-group.c | 17 +++++++++++++++-- fs/btrfs/block-group.h | 2 ++ 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index d7aad5e8ee37..3495bc775afa 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -436,13 +436,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes) { struct btrfs_caching_control *caching_ctl; + int progress; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return; + /* + * We've already failed to allocate from this block group, so even if + * there's enough space in the block group it isn't contiguous enough to + * allow for an allocation, so wait for at least the next wakeup tick, + * or for the thing to be done. + */ + progress = atomic_read(&caching_ctl->progress); + wait_event(caching_ctl->wait, btrfs_block_group_done(cache) || - (cache->free_space_ctl->free_space >= num_bytes)); + (progress != atomic_read(&caching_ctl->progress) && + (cache->free_space_ctl->free_space >= num_bytes))); btrfs_put_caching_control(caching_ctl); } @@ -660,8 +670,10 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; - if (wakeup) + if (wakeup) { + atomic_inc(&caching_ctl->progress); wake_up(&caching_ctl->wait); + } } } path->slots[0]++; @@ -767,6 +779,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; refcount_set(&caching_ctl->count, 2); + atomic_set(&caching_ctl->progress, 0); btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 0a3d38682358..debd42aeae0f 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -70,6 +70,8 @@ struct btrfs_caching_control { wait_queue_head_t wait; struct btrfs_work work; struct btrfs_block_group *block_group; + /* Track progress of caching during allocation. */ + atomic_t progress; refcount_t count; }; From 504d81c512f614ce6aa3d4857e6587580e445a1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jul 2023 06:26:53 -0700 Subject: [PATCH 0297/2093] btrfs: don't stop integrity writeback too early commit effa24f689ce0948f68c754991a445a8d697d3a8 upstream. extent_write_cache_pages stops writing pages as soon as nr_to_write hits zero. That is the right thing for opportunistic writeback, but incorrect for data integrity writeback, which needs to ensure that no dirty pages are left in the range. Thus only stop the writeback for WB_SYNC_NONE if nr_to_write hits 0. This is a port of write_cache_pages changes in commit 05fe478dd04e ("mm: write_cache_pages integrity fix"). Note that I've only trigger the problem with other changes to the btrfs writeback code, but this condition seems worthwhile fixing anyway. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Josef Bacik Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba [ updated comment ] Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent_io.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 58785dc7080a..0ad69041954f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3015,11 +3015,12 @@ int btree_write_cache_pages(struct address_space *mapping, } /* - * the filesystem may choose to bump up nr_to_write. + * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write - * at any time + * at any time. */ - nr_to_write_done = wbc->nr_to_write <= 0; + nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && + wbc->nr_to_write <= 0); } pagevec_release(&pvec); cond_resched(); From 7112abc9e8f2893328cbb2e055c3e21133cc7a3b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jul 2023 06:26:55 -0700 Subject: [PATCH 0298/2093] btrfs: properly clear end of the unreserved range in cow_file_range commit 12b2d64e591652a2d97dd3afa2b062ca7a4ba352 upstream. When the call to btrfs_reloc_clone_csums in cow_file_range returns an error, we jump to the out_unlock label with the extent_reserved variable set to false. The cleanup at the label will then call extent_clear_unlock_delalloc on the range from start to end. But we've already added cur_alloc_size to start before the jump, so there might no range be left from the newly incremented start to end. Move the check for 'start < end' so that it is reached by also for the !extent_reserved case. CC: stable@vger.kernel.org # 6.1+ Fixes: a315e68f6e8b ("Btrfs: fix invalid attempt to free reserved space on failure to cow range") Reviewed-by: Josef Bacik Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/inode.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3c48273cd7a5..28bcba2e0590 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1429,8 +1429,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, clear_bits, page_ops); start += cur_alloc_size; - if (start >= end) - return ret; } /* @@ -1439,9 +1437,11 @@ static noinline int cow_file_range(struct btrfs_inode *inode, * space_info's bytes_may_use counter, reserved in * btrfs_check_data_free_space(). */ - extent_clear_unlock_delalloc(inode, start, end, locked_page, - clear_bits | EXTENT_CLEAR_DATA_RESV, - page_ops); + if (start < end) { + clear_bits |= EXTENT_CLEAR_DATA_RESV; + extent_clear_unlock_delalloc(inode, start, end, locked_page, + clear_bits, page_ops); + } return ret; } From 9d04716e36654275aea00fb93fc9b30b850925e7 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 3 Aug 2023 17:20:42 +0800 Subject: [PATCH 0299/2093] btrfs: exit gracefully if reloc roots don't match commit 05d7ce504545f7874529701664c90814ca645c5d upstream. [BUG] Syzbot reported a crash that an ASSERT() got triggered inside prepare_to_merge(). [CAUSE] The root cause of the triggered ASSERT() is we can have a race between quota tree creation and relocation. This leads us to create a duplicated quota tree in the btrfs_read_fs_root() path, and since it's treated as fs tree, it would have ROOT_SHAREABLE flag, causing us to create a reloc tree for it. The bug itself is fixed by a dedicated patch for it, but this already taught us the ASSERT() is not something straightforward for developers. [ENHANCEMENT] Instead of using an ASSERT(), let's handle it gracefully and output extra info about the mismatch reloc roots to help debug. Also with the above ASSERT() removed, we can trigger ASSERT(0)s inside merge_reloc_roots() later. Also replace those ASSERT(0)s with WARN_ON()s. CC: stable@vger.kernel.org # 5.15+ Reported-by: syzbot+ae97a827ae1c3336bbb4@syzkaller.appspotmail.com Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/relocation.c | 45 +++++++++++++++++++++++++++++++++++-------- 1 file changed, 37 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 666a37a0ee89..d3591c7f166a 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1902,7 +1902,39 @@ int prepare_to_merge(struct reloc_control *rc, int err) err = PTR_ERR(root); break; } - ASSERT(root->reloc_root == reloc_root); + + if (unlikely(root->reloc_root != reloc_root)) { + if (root->reloc_root) { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + root->reloc_root->root_key.objectid, + root->reloc_root->root_key.type, + root->reloc_root->root_key.offset, + btrfs_root_generation( + &root->reloc_root->root_item), + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } else { + btrfs_err(fs_info, +"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu", + root->root_key.objectid, + reloc_root->root_key.objectid, + reloc_root->root_key.type, + reloc_root->root_key.offset, + btrfs_root_generation( + &reloc_root->root_item)); + } + list_add(&reloc_root->root_list, &reloc_roots); + btrfs_put_root(root); + btrfs_abort_transaction(trans, -EUCLEAN); + if (!err) + err = -EUCLEAN; + break; + } /* * set reference count to 1, so btrfs_recover_relocation @@ -1975,7 +2007,7 @@ void merge_reloc_roots(struct reloc_control *rc) root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false); if (btrfs_root_refs(&reloc_root->root_item) > 0) { - if (IS_ERR(root)) { + if (WARN_ON(IS_ERR(root))) { /* * For recovery we read the fs roots on mount, * and if we didn't find the root then we marked @@ -1984,17 +2016,14 @@ void merge_reloc_roots(struct reloc_control *rc) * memory. However there's no reason we can't * handle the error properly here just in case. */ - ASSERT(0); ret = PTR_ERR(root); goto out; } - if (root->reloc_root != reloc_root) { + if (WARN_ON(root->reloc_root != reloc_root)) { /* - * This is actually impossible without something - * going really wrong (like weird race condition - * or cosmic rays). + * This can happen if on-disk metadata has some + * corruption, e.g. bad reloc tree key offset. */ - ASSERT(0); ret = -EINVAL; goto out; } From 3ae93b316ca4b8b3c33798ef1d210355f2fb9318 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 3 Aug 2023 17:20:43 +0800 Subject: [PATCH 0300/2093] btrfs: reject invalid reloc tree root keys with stack dump commit 6ebcd021c92b8e4b904552e4d87283032100796d upstream. [BUG] Syzbot reported a crash that an ASSERT() got triggered inside prepare_to_merge(). That ASSERT() makes sure the reloc tree is properly pointed back by its subvolume tree. [CAUSE] After more debugging output, it turns out we had an invalid reloc tree: BTRFS error (device loop1): reloc tree mismatch, root 8 has no reloc root, expect reloc root key (-8, 132, 8) gen 17 Note the above root key is (TREE_RELOC_OBJECTID, ROOT_ITEM, QUOTA_TREE_OBJECTID), meaning it's a reloc tree for quota tree. But reloc trees can only exist for subvolumes, as for non-subvolume trees, we just COW the involved tree block, no need to create a reloc tree since those tree blocks won't be shared with other trees. Only subvolumes tree can share tree blocks with other trees (thus they have BTRFS_ROOT_SHAREABLE flag). Thus this new debug output proves my previous assumption that corrupted on-disk data can trigger that ASSERT(). [FIX] Besides the dedicated fix and the graceful exit, also let tree-checker to check such root keys, to make sure reloc trees can only exist for subvolumes. CC: stable@vger.kernel.org # 5.15+ Reported-by: syzbot+ae97a827ae1c3336bbb4@syzkaller.appspotmail.com Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 3 ++- fs/btrfs/tree-checker.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f22e00dfec6c..96369c44863a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1455,7 +1455,8 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) goto fail; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID && - !btrfs_is_data_reloc_root(root)) { + !btrfs_is_data_reloc_root(root) && + is_fstree(root->root_key.objectid)) { set_bit(BTRFS_ROOT_SHAREABLE, &root->state); btrfs_check_and_init_root_item(&root->root_item); } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 43f905ab0a18..2b39c7f9226f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -442,6 +442,20 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_key_to_cpu(leaf, &item_key, slot); is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY); + /* + * Bad rootid for reloc trees. + * + * Reloc trees are only for subvolume trees, other trees only need + * to be COWed to be relocated. + */ + if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID && + !is_fstree(key->offset))) { + generic_err(leaf, slot, + "invalid reloc tree for root %lld, root id is not a subvolume tree", + key->offset); + return -EUCLEAN; + } + /* No such tree id */ if (unlikely(key->objectid == 0)) { if (is_root_item) From bf67802453d3ebe1a9bcead9201d48f8c97f0f5a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 2 Aug 2023 09:20:24 -0400 Subject: [PATCH 0301/2093] btrfs: set cache_block_group_error if we find an error commit 92fb94b69c6accf1e49fff699640fa0ce03dc910 upstream. We set cache_block_group_error if btrfs_cache_block_group() returns an error, this is because we could end up not finding space to allocate and mistakenly return -ENOSPC, and which could then abort the transaction with the incorrect errno, and in the case of ENOSPC result in a WARN_ON() that will trip up tests like generic/475. However there's the case where multiple threads can be racing, one thread gets the proper error, and the other thread doesn't actually call btrfs_cache_block_group(), it instead sees ->cached == BTRFS_CACHE_ERROR. Again the result is the same, we fail to allocate our space and return -ENOSPC. Instead we need to set cache_block_group_error to -EIO in this case to make sure that if we do not make our allocation we get the appropriate error returned back to the caller. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent-tree.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 571fcc5ae4dc..f2ee70c03f0d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4411,8 +4411,11 @@ static noinline int find_free_extent(struct btrfs_root *root, ret = 0; } - if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) + if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) { + if (!cache_block_group_error) + cache_block_group_error = -EIO; goto loop; + } bg_ret = NULL; ret = do_allocation(block_group, ffe_ctl, &bg_ret); From cddbaa8dee7e7d4eb678e6f04fec1aa43117c7f4 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 11 Jul 2023 17:40:40 +0800 Subject: [PATCH 0302/2093] nvme-tcp: fix potential unbalanced freeze & unfreeze commit 99dc264014d5aed66ee37ddf136a38b5a2b1b529 upstream. Move start_freeze into nvme_tcp_configure_io_queues(), and there is at least two benefits: 1) fix unbalanced freeze and unfreeze, since re-connection work may fail or be broken by removal 2) IO during error recovery can be failfast quickly because nvme fabrics unquiesces queues after teardown. One side-effect is that !mpath request may timeout during connecting because of queue topo change, but that looks not one big deal: 1) same problem exists with current code base 2) compared with !mpath, mpath use case is dominant Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic") Cc: stable@vger.kernel.org Signed-off-by: Ming Lei Tested-by: Yi Zhang Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/nvme/host/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 8f17cbec5a0e..f2fedd25915f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1890,6 +1890,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) goto out_cleanup_connect_q; if (!new) { + nvme_start_freeze(ctrl); nvme_start_queues(ctrl); if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) { /* @@ -1898,6 +1899,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) * to be safe. */ ret = -ENODEV; + nvme_unfreeze(ctrl); goto out_wait_freeze_timed_out; } blk_mq_update_nr_hw_queues(ctrl->tagset, @@ -2002,7 +2004,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, if (ctrl->queue_count <= 1) return; nvme_stop_admin_queue(ctrl); - nvme_start_freeze(ctrl); nvme_stop_queues(ctrl); nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); From c21fddce7e450b737a77cd918e55969076143bb0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 11 Jul 2023 17:40:41 +0800 Subject: [PATCH 0303/2093] nvme-rdma: fix potential unbalanced freeze & unfreeze commit 29b434d1e49252b3ad56ad3197e47fafff5356a1 upstream. Move start_freeze into nvme_rdma_configure_io_queues(), and there is at least two benefits: 1) fix unbalanced freeze and unfreeze, since re-connection work may fail or be broken by removal 2) IO during error recovery can be failfast quickly because nvme fabrics unquiesces queues after teardown. One side-effect is that !mpath request may timeout during connecting because of queue topo change, but that looks not one big deal: 1) same problem exists with current code base 2) compared with !mpath, mpath use case is dominant Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic") Cc: stable@vger.kernel.org Signed-off-by: Ming Lei Tested-by: Yi Zhang Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/nvme/host/rdma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 80383213b882..c478480f54aa 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -923,6 +923,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) goto out_cleanup_tagset; if (!new) { + nvme_start_freeze(&ctrl->ctrl); nvme_start_queues(&ctrl->ctrl); if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) { /* @@ -931,6 +932,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) * to be safe. */ ret = -ENODEV; + nvme_unfreeze(&ctrl->ctrl); goto out_wait_freeze_timed_out; } blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset, @@ -980,7 +982,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { if (ctrl->ctrl.queue_count > 1) { - nvme_start_freeze(&ctrl->ctrl); nvme_stop_queues(&ctrl->ctrl); nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); From f3f0f95a023370561a9b4d2028308f8452f1e7d1 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 28 Jun 2023 16:24:27 +0200 Subject: [PATCH 0304/2093] netfilter: nf_tables: report use refcount overflow commit 1689f25924ada8fe14a4a82c38925d04994c7142 upstream. Overflow use refcount checks are not complete. Add helper function to deal with object reference counter tracking. Report -EMFILE in case UINT_MAX is reached. nft_use_dec() splats in case that reference counter underflows, which should not ever happen. Add nft_use_inc_restore() and nft_use_dec_restore() which are used to restore reference counter from error and abort paths. Use u32 in nft_flowtable and nft_object since helper functions cannot work on bitfields. Remove the few early incomplete checks now that the helper functions are in place and used to check for refcount overflow. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 31 +++++- net/netfilter/nf_tables_api.c | 163 ++++++++++++++++++------------ net/netfilter/nft_flow_offload.c | 6 +- net/netfilter/nft_immediate.c | 8 +- net/netfilter/nft_objref.c | 8 +- 5 files changed, 141 insertions(+), 75 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f3a37cacb32c..c752b6f50979 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1192,6 +1192,29 @@ int __nft_release_basechain(struct nft_ctx *ctx); unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); +static inline bool nft_use_inc(u32 *use) +{ + if (*use == UINT_MAX) + return false; + + (*use)++; + + return true; +} + +static inline void nft_use_dec(u32 *use) +{ + WARN_ON_ONCE((*use)-- == 0); +} + +/* For error and abort path: restore use counter to previous state. */ +static inline void nft_use_inc_restore(u32 *use) +{ + WARN_ON_ONCE(!nft_use_inc(use)); +} + +#define nft_use_dec_restore nft_use_dec + /** * struct nft_table - nf_tables table * @@ -1275,8 +1298,8 @@ struct nft_object { struct list_head list; struct rhlist_head rhlhead; struct nft_object_hash_key key; - u32 genmask:2, - use:30; + u32 genmask:2; + u32 use; u64 handle; u16 udlen; u8 *udata; @@ -1378,8 +1401,8 @@ struct nft_flowtable { char *name; int hooknum; int ops_len; - u32 genmask:2, - use:30; + u32 genmask:2; + u32 use; u64 handle; /* runtime data below here */ struct list_head hook_list ____cacheline_aligned; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dd57a9ebe113..f6e627383885 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -255,8 +255,10 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) if (chain->bound) return -EBUSY; + if (!nft_use_inc(&chain->use)) + return -EMFILE; + chain->bound = true; - chain->use++; nft_chain_trans_bind(ctx, chain); return 0; @@ -439,7 +441,7 @@ static int nft_delchain(struct nft_ctx *ctx) if (IS_ERR(trans)) return PTR_ERR(trans); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; @@ -478,7 +480,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; @@ -645,7 +647,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -677,7 +679,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; nft_deactivate_next(ctx->net, obj); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -712,7 +714,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; nft_deactivate_next(ctx->net, flowtable); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -2358,9 +2360,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, unsigned int data_size; int err; - if (table->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; @@ -2457,6 +2456,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err_destroy_chain; + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err_use; + } + trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2473,10 +2477,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } - table->use++; - return 0; + err_unregister_hook: + nft_use_dec_restore(&table->use); +err_use: nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -3663,9 +3668,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return -EINVAL; handle = nf_tables_alloc_handle(table); - if (chain->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); @@ -3759,6 +3761,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } + if (!nft_use_inc(&chain->use)) { + err = -EMFILE; + goto err_release_rule; + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { err = nft_delrule(&ctx, old_rule); if (err < 0) @@ -3790,7 +3797,6 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } } kvfree(expr_info); - chain->use++; if (flow) nft_trans_flow_rule(trans) = flow; @@ -3801,6 +3807,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, return 0; err_destroy_flow_rule: + nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: @@ -4818,9 +4825,15 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; + + if (!nft_use_inc(&table->use)) + return -EMFILE; + set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); - if (!set) - return -ENOMEM; + if (!set) { + err = -ENOMEM; + goto err_alloc; + } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { @@ -4878,7 +4891,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); - table->use++; + return 0; err_set_expr_alloc: @@ -4890,6 +4903,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, kfree(set->name); err_set_name: kvfree(set); +err_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -5024,9 +5040,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; - if (set->use == UINT_MAX) - return -EOVERFLOW; - if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -5054,10 +5067,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, return iter.err; } bind: + if (!nft_use_inc(&set->use)) + return -EMFILE; + binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); - set->use++; return 0; } @@ -5131,7 +5146,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) nft_clear(ctx->net, set); } - set->use++; + nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); @@ -5147,7 +5162,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, else list_del_rcu(&binding->list); - set->use--; + nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { @@ -5156,7 +5171,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_deactivate_next(ctx->net, set); } - set->use--; + nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -5164,7 +5179,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); - set->use--; + nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, @@ -5933,7 +5948,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6435,8 +6450,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); + obj = NULL; goto err_parse_key_end; } + + if (!nft_use_inc(&obj->use)) { + err = -EMFILE; + obj = NULL; + goto err_parse_key_end; + } + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; @@ -6505,10 +6528,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; - if (obj) { + if (obj) *nft_set_ext_obj(ext) = obj; - obj->use++; - } + if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; @@ -6573,12 +6595,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); - if (obj) - obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: + if (obj) + nft_use_dec_restore(&obj->use); + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); @@ -6659,7 +6682,7 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use++; + nft_use_inc_restore(&chain->use); break; } } @@ -6674,7 +6697,7 @@ static void nft_setelem_data_activate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use++; + nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } static void nft_setelem_data_deactivate(const struct net *net, @@ -6686,7 +6709,7 @@ static void nft_setelem_data_deactivate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, @@ -7225,9 +7248,14 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + type = nft_obj_type_get(net, objtype); - if (IS_ERR(type)) - return PTR_ERR(type); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; + } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { @@ -7261,7 +7289,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); - table->use++; + return 0; err_obj_ht: /* queued in transaction log */ @@ -7277,6 +7305,9 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, kfree(obj); err_init: module_put(type->owner); +err_type: + nft_use_dec_restore(&table->use); + return err; } @@ -7667,7 +7698,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: - flowtable->use--; + nft_use_dec(&flowtable->use); fallthrough; default: return; @@ -8015,9 +8046,14 @@ static int nf_tables_newflowtable(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); - if (!flowtable) - return -ENOMEM; + if (!flowtable) { + err = -ENOMEM; + goto flowtable_alloc; + } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); @@ -8072,7 +8108,6 @@ static int nf_tables_newflowtable(struct sk_buff *skb, goto err5; list_add_tail_rcu(&flowtable->list, &table->flowtables); - table->use++; return 0; err5: @@ -8089,6 +8124,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb, kfree(flowtable->name); err1: kfree(flowtable); +flowtable_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -9374,7 +9412,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + nft_use_dec(&trans->ctx.table->use); } nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); @@ -9593,7 +9631,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -9601,7 +9639,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } break; case NFT_MSG_DELCHAIN: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); break; @@ -9610,7 +9648,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.chain->use--; + nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), @@ -9619,7 +9657,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: - trans->ctx.chain->use++; + nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) @@ -9632,7 +9670,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -9640,7 +9678,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&trans->ctx, nft_trans_set(trans)); @@ -9683,12 +9721,12 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; @@ -9697,7 +9735,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); @@ -9708,7 +9746,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); @@ -10161,8 +10199,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; + if (!nft_use_inc(&chain->use)) + return -EMFILE; - chain->use++; data->verdict.chain = chain; break; } @@ -10180,7 +10219,7 @@ static void nft_verdict_uninit(const struct nft_data *data) case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; - chain->use--; + nft_use_dec(&chain->use); break; } } @@ -10349,11 +10388,11 @@ int __nft_release_basechain(struct nft_ctx *ctx) nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; @@ -10406,18 +10445,18 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); - chain->use--; + nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); - table->use--; + nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); - table->use--; + nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); @@ -10425,13 +10464,13 @@ static void __nft_release_table(struct net *net, struct nft_table *table) } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); - table->use--; + nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; nft_chain_del(chain); - table->use--; + nft_use_dec(&table->use); nf_tables_chain_destroy(&ctx); } nf_tables_table_destroy(&ctx); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a25c88bc8b75..8a43f6f9c90b 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -404,8 +404,10 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (IS_ERR(flowtable)) return PTR_ERR(flowtable); + if (!nft_use_inc(&flowtable->use)) + return -EMFILE; + priv->flowtable = flowtable; - flowtable->use++; return nf_ct_netns_get(ctx->net, ctx->family); } @@ -424,7 +426,7 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx, { struct nft_flow_offload *priv = nft_expr_priv(expr); - priv->flowtable->use++; + nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 391c18e4b3eb..5f59dbab3e93 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -168,7 +168,7 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, nft_immediate_chain_deactivate(ctx, chain, phase); nft_chain_del(chain); chain->bound = false; - chain->table->use--; + nft_use_dec(&chain->table->use); break; } break; @@ -207,7 +207,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, * let the transaction records release this chain and its rules. */ if (chain->bound) { - chain->use--; + nft_use_dec(&chain->use); break; } @@ -215,9 +215,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, chain_ctx = *ctx; chain_ctx.chain = chain; - chain->use--; + nft_use_dec(&chain->use); list_for_each_entry_safe(rule, n, &chain->rules, list) { - chain->use--; + nft_use_dec(&chain->use); list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 7f8e480b6be5..0017bd341872 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -41,8 +41,10 @@ static int nft_objref_init(const struct nft_ctx *ctx, if (IS_ERR(obj)) return -ENOENT; + if (!nft_use_inc(&obj->use)) + return -EMFILE; + nft_objref_priv(expr) = obj; - obj->use++; return 0; } @@ -71,7 +73,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx, if (phase == NFT_TRANS_COMMIT) return; - obj->use--; + nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, @@ -79,7 +81,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx, { struct nft_object *obj = nft_objref_priv(expr); - obj->use++; + nft_use_inc_restore(&obj->use); } static struct nft_expr_type nft_objref_type; From 0e1605ec5bea016117bc6d9d0bfe95906c014c7a Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Mon, 24 Jul 2023 14:25:40 -0400 Subject: [PATCH 0305/2093] scsi: core: Fix legacy /proc parsing buffer overflow commit 9426d3cef5000824e5f24f80ed5f42fb935f2488 upstream. (lightly modified commit message mostly by Linus Torvalds) The parsing code for /proc/scsi/scsi is disgusting and broken. We should have just used 'sscanf()' or something simple like that, but the logic may actually predate our kernel sscanf library routine for all I know. It certainly predates both git and BK histories. And we can't change it to be something sane like that now, because the string matching at the start is done case-insensitively, and the separator parsing between numbers isn't done at all, so *any* separator will work, including a possible terminating NUL character. This interface is root-only, and entirely for legacy use, so there is absolutely no point in trying to tighten up the parsing. Because any separator has traditionally worked, it's entirely possible that people have used random characters rather than the suggested space. So don't bother to try to pretty it up, and let's just make a minimal patch that can be back-ported and we can forget about this whole sorry thing for another two decades. Just make it at least not read past the end of the supplied data. Link: https://lore.kernel.org/linux-scsi/b570f5fe-cb7c-863a-6ed9-f6774c219b88@cybernetics.com/ Cc: Linus Torvalds Cc: Martin K Petersen Cc: James Bottomley Cc: Willy Tarreau Cc: stable@kernel.org Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tony Battersby Signed-off-by: Martin K Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_proc.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index 95aee1ad1383..7184e169a4a5 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -311,7 +311,7 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, size_t length, loff_t *ppos) { int host, channel, id, lun; - char *buffer, *p; + char *buffer, *end, *p; int err; if (!buf || length > PAGE_SIZE) @@ -326,10 +326,14 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, goto out; err = -EINVAL; - if (length < PAGE_SIZE) - buffer[length] = '\0'; - else if (buffer[PAGE_SIZE-1]) - goto out; + if (length < PAGE_SIZE) { + end = buffer + length; + *end = '\0'; + } else { + end = buffer + PAGE_SIZE - 1; + if (*end) + goto out; + } /* * Usage: echo "scsi add-single-device 0 1 2 3" >/proc/scsi/scsi @@ -338,10 +342,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, if (!strncmp("scsi add-single-device", buffer, 22)) { p = buffer + 23; - host = simple_strtoul(p, &p, 0); - channel = simple_strtoul(p + 1, &p, 0); - id = simple_strtoul(p + 1, &p, 0); - lun = simple_strtoul(p + 1, &p, 0); + host = (p < end) ? simple_strtoul(p, &p, 0) : 0; + channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; err = scsi_add_single_device(host, channel, id, lun); @@ -352,10 +356,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf, } else if (!strncmp("scsi remove-single-device", buffer, 25)) { p = buffer + 26; - host = simple_strtoul(p, &p, 0); - channel = simple_strtoul(p + 1, &p, 0); - id = simple_strtoul(p + 1, &p, 0); - lun = simple_strtoul(p + 1, &p, 0); + host = (p < end) ? simple_strtoul(p, &p, 0) : 0; + channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + id = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; + lun = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0; err = scsi_remove_single_device(host, channel, id, lun); } From ed70fa5629a8b992a5372d7044d1db1f8fa6de29 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 28 Jul 2023 21:59:24 -0700 Subject: [PATCH 0306/2093] scsi: storvsc: Fix handling of virtual Fibre Channel timeouts commit 175544ad48cbf56affeef2a679c6a4d4fb1e2881 upstream. Hyper-V provides the ability to connect Fibre Channel LUNs to the host system and present them in a guest VM as a SCSI device. I/O to the vFC device is handled by the storvsc driver. The storvsc driver includes a partial integration with the FC transport implemented in the generic portion of the Linux SCSI subsystem so that FC attributes can be displayed in /sys. However, the partial integration means that some aspects of vFC don't work properly. Unfortunately, a full and correct integration isn't practical because of limitations in what Hyper-V provides to the guest. In particular, in the context of Hyper-V storvsc, the FC transport timeout function fc_eh_timed_out() causes a kernel panic because it can't find the rport and dereferences a NULL pointer. The original patch that added the call from storvsc_eh_timed_out() to fc_eh_timed_out() is faulty in this regard. In many cases a timeout is due to a transient condition, so the situation can be improved by just continuing to wait like with other I/O requests issued by storvsc, and avoiding the guaranteed panic. For a permanent failure, continuing to wait may result in a hung thread instead of a panic, which again may be better. So fix the panic by removing the storvsc call to fc_eh_timed_out(). This allows storvsc to keep waiting for a response. The change has been tested by users who experienced a panic in fc_eh_timed_out() due to transient timeouts, and it solves their problem. In the future we may want to deprecate the vFC functionality in storvsc since it can't be fully fixed. But it has current users for whom it is working well enough, so it should probably stay for a while longer. Fixes: 3930d7309807 ("scsi: storvsc: use default I/O timeout handler for FC devices") Cc: stable@vger.kernel.org Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1690606764-79669-1-git-send-email-mikelley@microsoft.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/storvsc_drv.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 54a1b8514f04..83d09c200928 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1670,10 +1670,6 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) */ static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) { -#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS) - if (scmnd->device->host->transportt == fc_transport_template) - return fc_eh_timed_out(scmnd); -#endif return BLK_EH_RESET_TIMER; } From 8282d0b35880dd5378f83cabd1e58b9f7b9b3f24 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Thu, 3 Aug 2023 17:18:12 +0900 Subject: [PATCH 0307/2093] scsi: ufs: renesas: Fix private allocation commit b6d128f89a85771433a004e8656090ccbe1fb969 upstream. Should use devm_kzalloc() for struct ufs_renesas_priv because the .initialized should be false as default. Fixes: d69520288efd ("scsi: ufs: ufs-renesas: Add support for Renesas R-Car UFS controller") Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20230803081812.1446282-1-yoshihiro.shimoda.uh@renesas.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/ufs/host/ufs-renesas.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ufs/host/ufs-renesas.c b/drivers/ufs/host/ufs-renesas.c index f8a5e79ed3b4..ab0652d8705a 100644 --- a/drivers/ufs/host/ufs-renesas.c +++ b/drivers/ufs/host/ufs-renesas.c @@ -359,7 +359,7 @@ static int ufs_renesas_init(struct ufs_hba *hba) { struct ufs_renesas_priv *priv; - priv = devm_kmalloc(hba->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(hba->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; ufshcd_set_variant(hba, priv); From 9fdb273ede6f4428f44b09267a95f2a10b738809 Mon Sep 17 00:00:00 2001 From: Alexandra Diupina Date: Fri, 28 Jul 2023 15:35:21 +0300 Subject: [PATCH 0308/2093] scsi: 53c700: Check that command slot is not NULL commit 8366d1f1249a0d0bba41d0bd1298d63e5d34c7f7 upstream. Add a check for the command slot value to avoid dereferencing a NULL pointer. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Co-developed-by: Vladimir Telezhnikov Signed-off-by: Vladimir Telezhnikov Signed-off-by: Alexandra Diupina Link: https://lore.kernel.org/r/20230728123521.18293-1-adiupina@astralinux.ru Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/53c700.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index e1e4f9d10887..857be0f3ae5b 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1598,7 +1598,7 @@ NCR_700_intr(int irq, void *dev_id) printk("scsi%d (%d:%d) PHASE MISMATCH IN SEND MESSAGE %d remain, return %p[%04x], phase %s\n", host->host_no, pun, lun, count, (void *)temp, temp - hostdata->pScript, sbcl_to_string(NCR_700_readb(host, SBCL_REG))); #endif resume_offset = hostdata->pScript + Ent_SendMessagePhaseMismatch; - } else if(dsp >= to32bit(&slot->pSG[0].ins) && + } else if (slot && dsp >= to32bit(&slot->pSG[0].ins) && dsp <= to32bit(&slot->pSG[NCR_700_SG_SEGMENTS].ins)) { int data_transfer = NCR_700_readl(host, DBC_REG) & 0xffffff; int SGcount = (dsp - to32bit(&slot->pSG[0].ins))/sizeof(struct NCR_700_SG_List); From 7723a5d5d187626c4c640842e522cf4e9e39492e Mon Sep 17 00:00:00 2001 From: Zhu Wang Date: Tue, 1 Aug 2023 19:14:21 +0800 Subject: [PATCH 0309/2093] scsi: snic: Fix possible memory leak if device_add() fails commit 41320b18a0e0dfb236dba4edb9be12dba1878156 upstream. If device_add() returns error, the name allocated by dev_set_name() needs be freed. As the comment of device_add() says, put_device() should be used to give up the reference in the error path. So fix this by calling put_device(), then the name can be freed in kobject_cleanp(). Fixes: c8806b6c9e82 ("snic: driver for Cisco SCSI HBA") Signed-off-by: Zhu Wang Acked-by: Narsimhulu Musini Link: https://lore.kernel.org/r/20230801111421.63651-1-wangzhu9@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/snic/snic_disc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index 8fbf3c1b1311..cd27562ec922 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -303,6 +303,7 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid) "Snic Tgt: device_add, with err = %d\n", ret); + put_device(&tgt->dev); put_device(&snic->shost->shost_gendev); spin_lock_irqsave(snic->shost->host_lock, flags); list_del(&tgt->list); From b191ff1f075c4875f11271cbf0093e6e044a12aa Mon Sep 17 00:00:00 2001 From: Zhu Wang Date: Thu, 3 Aug 2023 10:02:30 +0800 Subject: [PATCH 0310/2093] scsi: core: Fix possible memory leak if device_add() fails commit 04b5b5cb0136ce970333a9c6cec7e46adba1ea3a upstream. If device_add() returns error, the name allocated by dev_set_name() needs be freed. As the comment of device_add() says, put_device() should be used to decrease the reference count in the error path. So fix this by calling put_device(), then the name can be freed in kobject_cleanp(). Fixes: ee959b00c335 ("SCSI: convert struct class_device to struct device") Signed-off-by: Zhu Wang Link: https://lore.kernel.org/r/20230803020230.226903-1-wangzhu9@huawei.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/raid_class.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c index 898a0bdf8df6..711252e52d8e 100644 --- a/drivers/scsi/raid_class.c +++ b/drivers/scsi/raid_class.c @@ -248,6 +248,7 @@ int raid_component_add(struct raid_template *r,struct device *raid_dev, return 0; err_out: + put_device(&rc->dev); list_del(&rc->node); rd->component_count--; put_device(component_dev); From fb004497b3ea4bdc4f8e005f4ed07c133f4c43a0 Mon Sep 17 00:00:00 2001 From: Karan Tilak Kumar Date: Thu, 27 Jul 2023 12:39:19 -0700 Subject: [PATCH 0311/2093] scsi: fnic: Replace return codes in fnic_clean_pending_aborts() commit 5a43b07a87835660f91d88a4db11abfea8c523b7 upstream. fnic_clean_pending_aborts() was returning a non-zero value irrespective of failure or success. This caused the caller of this function to assume that the device reset had failed, even though it would succeed in most cases. As a consequence, a successful device reset would escalate to host reset. Reviewed-by: Sesidhar Baddela Tested-by: Karan Tilak Kumar Signed-off-by: Karan Tilak Kumar Link: https://lore.kernel.org/r/20230727193919.2519-1-kartilak@cisco.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/fnic/fnic.h | 2 +- drivers/scsi/fnic/fnic_scsi.c | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index d82de34f6fd7..e51e92f932fa 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -27,7 +27,7 @@ #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.6.0.54" +#define DRV_VERSION "1.6.0.55" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 26dbd347156e..be89ce96df46 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -2139,7 +2139,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, bool new_sc) { - int ret = SUCCESS; + int ret = 0; struct fnic_pending_aborts_iter_data iter_data = { .fnic = fnic, .lun_dev = lr_sc->device, @@ -2159,9 +2159,11 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, /* walk again to check, if IOs are still pending in fw */ if (fnic_is_abts_pending(fnic, lr_sc)) - ret = FAILED; + ret = 1; clean_pending_aborts_end: + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "%s: exit status: %d\n", __func__, ret); return ret; } From a9518f4a4978c0db34d5305c0538e3c1ad9b1658 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Mon, 7 Aug 2023 15:07:25 +0530 Subject: [PATCH 0312/2093] scsi: qedi: Fix firmware halt over suspend and resume commit 1516ee035df32115197cd93ae3619dba7b020986 upstream. While performing certain power-off sequences, PCI drivers are called to suspend and resume their underlying devices through PCI PM (power management) interface. However the hardware does not support PCI PM suspend/resume operations so system wide suspend/resume leads to bad MFW (management firmware) state which causes various follow-up errors in driver when communicating with the device/firmware. To fix this driver implements PCI PM suspend handler to indicate unsupported operation to the PCI subsystem explicitly, thus avoiding system to go into suspended/standby mode. Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.") Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230807093725.46829-2-njavali@marvell.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qedi/qedi_main.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index f530bb036493..9fd68d362698 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi); static void qedi_recovery_handler(struct work_struct *work); static void qedi_schedule_hw_err_handler(void *dev, enum qed_hw_err_type err_type); +static int qedi_suspend(struct pci_dev *pdev, pm_message_t state); static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle) { @@ -2510,6 +2511,22 @@ static void qedi_shutdown(struct pci_dev *pdev) __qedi_remove(pdev, QEDI_MODE_SHUTDOWN); } +static int qedi_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct qedi_ctx *qedi; + + if (!pdev) { + QEDI_ERR(NULL, "pdev is NULL.\n"); + return -ENODEV; + } + + qedi = pci_get_drvdata(pdev); + + QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__); + + return -EPERM; +} + static int __qedi_probe(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi; @@ -2868,6 +2885,7 @@ static struct pci_driver qedi_pci_driver = { .remove = qedi_remove, .shutdown = qedi_shutdown, .err_handler = &qedi_err_handler, + .suspend = qedi_suspend, }; static int __init qedi_init(void) From 38b0020f68b7d80242e46b8eba69ed80ceaec157 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Mon, 7 Aug 2023 15:07:24 +0530 Subject: [PATCH 0313/2093] scsi: qedf: Fix firmware halt over suspend and resume commit ef222f551e7c4e2008fc442ffc9edcd1a7fd8f63 upstream. While performing certain power-off sequences, PCI drivers are called to suspend and resume their underlying devices through PCI PM (power management) interface. However the hardware does not support PCI PM suspend/resume operations so system wide suspend/resume leads to bad MFW (management firmware) state which causes various follow-up errors in driver when communicating with the device/firmware. To fix this driver implements PCI PM suspend handler to indicate unsupported operation to the PCI subsystem explicitly, thus avoiding system to go into suspended/standby mode. Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.") Signed-off-by: Saurav Kashyap Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230807093725.46829-1-njavali@marvell.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qedf/qedf_main.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index ecff2ec83a00..c4f293d39f22 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev); static void qedf_shutdown(struct pci_dev *pdev); static void qedf_schedule_recovery_handler(void *dev); static void qedf_recovery_handler(struct work_struct *work); +static int qedf_suspend(struct pci_dev *pdev, pm_message_t state); /* * Driver module parameters. @@ -3276,6 +3277,7 @@ static struct pci_driver qedf_pci_driver = { .probe = qedf_probe, .remove = qedf_remove, .shutdown = qedf_shutdown, + .suspend = qedf_suspend, }; static int __qedf_probe(struct pci_dev *pdev, int mode) @@ -4005,6 +4007,22 @@ static void qedf_shutdown(struct pci_dev *pdev) __qedf_remove(pdev, QEDF_MODE_NORMAL); } +static int qedf_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct qedf_ctx *qedf; + + if (!pdev) { + QEDF_ERR(NULL, "pdev is NULL.\n"); + return -ENODEV; + } + + qedf = pci_get_drvdata(pdev); + + QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__); + + return -EPERM; +} + /* * Recovery handler code */ From afc4ddd9507f2d829b503a41b8de33535e521c55 Mon Sep 17 00:00:00 2001 From: David Xu Date: Thu, 13 Jul 2023 21:35:28 +0800 Subject: [PATCH 0314/2093] platform/x86: serial-multi-instantiate: Auto detect IRQ resource for CSC3551 commit 676b7c5ecab36274442887ceadd6dee8248a244f upstream. The current code assumes that the CSC3551(multiple cs35l41) always have its interrupt pin connected to GPIO thus the IRQ can be acquired with acpi_dev_gpio_irq_get. However on some newer laptop models this is no longer the case as they have the CSC3551's interrupt pin connected to APIC. This causes smi_i2c_probe to fail on these machines. To support these machines, a new macro IRQ_RESOURCE_AUTO was introduced for cs35l41 smi_node, and smi_get_irq function was modified so it tries to get GPIO irq resource first and if failed, tries to get APIC irq resource for cs35l41. This patch affects only the cs35l41's probing and brings no negative influence on machines that indeed have the cs35l41's interrupt pin connected to GPIO. Signed-off-by: David Xu Link: https://lore.kernel.org/r/SY4P282MB18350CD8288687B87FFD2243E037A@SY4P282MB1835.AUSP282.PROD.OUTLOOK.COM Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- .../platform/x86/serial-multi-instantiate.c | 21 +++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c index 5362f1a7b77c..85c9eabd85c0 100644 --- a/drivers/platform/x86/serial-multi-instantiate.c +++ b/drivers/platform/x86/serial-multi-instantiate.c @@ -21,6 +21,7 @@ #define IRQ_RESOURCE_NONE 0 #define IRQ_RESOURCE_GPIO 1 #define IRQ_RESOURCE_APIC 2 +#define IRQ_RESOURCE_AUTO 3 enum smi_bus_type { SMI_I2C, @@ -52,6 +53,18 @@ static int smi_get_irq(struct platform_device *pdev, struct acpi_device *adev, int ret; switch (inst->flags & IRQ_RESOURCE_TYPE) { + case IRQ_RESOURCE_AUTO: + ret = acpi_dev_gpio_irq_get(adev, inst->irq_idx); + if (ret > 0) { + dev_dbg(&pdev->dev, "Using gpio irq\n"); + break; + } + ret = platform_get_irq(pdev, inst->irq_idx); + if (ret > 0) { + dev_dbg(&pdev->dev, "Using platform irq\n"); + break; + } + break; case IRQ_RESOURCE_GPIO: ret = acpi_dev_gpio_irq_get(adev, inst->irq_idx); break; @@ -308,10 +321,10 @@ static const struct smi_node int3515_data = { static const struct smi_node cs35l41_hda = { .instances = { - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, - { "cs35l41-hda", IRQ_RESOURCE_GPIO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l41-hda", IRQ_RESOURCE_AUTO, 0 }, {} }, .bus_type = SMI_AUTO_DETECT, From cbce265f959f0b58feb06fa90600e683b853c220 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Fri, 28 Jul 2023 12:13:45 +0100 Subject: [PATCH 0315/2093] ACPI: scan: Create platform device for CS35L56 commit 1cd0302be5645420f73090aee26fa787287e1096 upstream. The ACPI device CSC3556 is a Cirrus Logic CS35L56 mono amplifier which is used in multiples, and can be connected either to I2C or SPI. There will be multiple instances under the same Device() node. Add it to ignore_serial_bus_ids and handle it in the serial-multi-instantiate driver. There can be a 5th I2cSerialBusV2, but this is an alias address and doesn't represent a real device. Ignore this by having a dummy 5th entry in the serial-multi-instantiate instance list with the name of a non-existent driver, on the same pattern as done for bsg2150. Signed-off-by: Simon Trimmer Signed-off-by: Richard Fitzgerald Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230728111345.7224-1-rf@opensource.cirrus.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/scan.c | 1 + drivers/platform/x86/serial-multi-instantiate.c | 14 ++++++++++++++ 2 files changed, 15 insertions(+) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dbfa58e799e2..a0e347f6f97e 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1712,6 +1712,7 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device) {"BSG1160", }, {"BSG2150", }, {"CSC3551", }, + {"CSC3556", }, {"INT33FE", }, {"INT3515", }, /* Non-conforming _HID for Cirrus Logic already released */ diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c index 85c9eabd85c0..7a9c758e9547 100644 --- a/drivers/platform/x86/serial-multi-instantiate.c +++ b/drivers/platform/x86/serial-multi-instantiate.c @@ -330,6 +330,19 @@ static const struct smi_node cs35l41_hda = { .bus_type = SMI_AUTO_DETECT, }; +static const struct smi_node cs35l56_hda = { + .instances = { + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + { "cs35l56-hda", IRQ_RESOURCE_AUTO, 0 }, + /* a 5th entry is an alias address, not a real device */ + { "cs35l56-hda_dummy_dev" }, + {} + }, + .bus_type = SMI_AUTO_DETECT, +}; + /* * Note new device-ids must also be added to ignore_serial_bus_ids in * drivers/acpi/scan.c: acpi_device_enumeration_by_parent(). @@ -338,6 +351,7 @@ static const struct acpi_device_id smi_acpi_ids[] = { { "BSG1160", (unsigned long)&bsg1160_data }, { "BSG2150", (unsigned long)&bsg2150_data }, { "CSC3551", (unsigned long)&cs35l41_hda }, + { "CSC3556", (unsigned long)&cs35l56_hda }, { "INT3515", (unsigned long)&int3515_data }, /* Non-conforming _HID for Cirrus Logic already released */ { "CLSA0100", (unsigned long)&cs35l41_hda }, From 3ae919c317dd6607f9c166ce1e0cb2cf5f02dd2b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 29 Jul 2023 16:42:23 +0900 Subject: [PATCH 0316/2093] alpha: remove __init annotation from exported page_is_ram() commit 6ccbd7fd474674654019a20177c943359469103a upstream. EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Commit c5a130325f13 ("ACPI/APEI: Add parameter check before error injection") exported page_is_ram(), hence the __init annotation should be removed. This fixes the modpost warning in ARCH=alpha builds: WARNING: modpost: vmlinux: page_is_ram: EXPORT_SYMBOL used for init symbol. Remove __init or EXPORT_SYMBOL. Fixes: c5a130325f13 ("ACPI/APEI: Add parameter check before error injection") Signed-off-by: Masahiro Yamada Reviewed-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- arch/alpha/kernel/setup.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 33bf3a627002..45a920ba4921 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -385,8 +385,7 @@ setup_memory(void *kernel_end) #endif /* CONFIG_BLK_DEV_INITRD */ } -int __init -page_is_ram(unsigned long pfn) +int page_is_ram(unsigned long pfn) { struct memclust_struct * cluster; struct memdesc_struct * memdesc; From 4346a66ad19876663e46d57c85dac5958f227033 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Jun 2023 18:15:03 +0000 Subject: [PATCH 0317/2093] sch_netem: fix issues in netem_change() vs get_dist_table() commit 11b73313c12403f617b47752db0ab3deef201af7 upstream. In blamed commit, I missed that get_dist_table() was allocating memory using GFP_KERNEL, and acquiring qdisc lock to perform the swap of newly allocated table with current one. In this patch, get_dist_table() is allocating memory and copy user data before we acquire the qdisc lock. Then we perform swap operations while being protected by the lock. Note that after this patch netem_change() no longer can do partial changes. If an error is returned, qdisc conf is left unchanged. Fixes: 2174a08db80d ("sch_netem: acquire qdisc lock in netem_change()") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Acked-by: Jamal Hadi Salim Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230622181503.2327695-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- net/sched/sch_netem.c | 59 ++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 34 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index aa9842158df0..d0e045116d4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -773,12 +773,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -966,6 +960,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -975,26 +981,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; + q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1044,17 +1041,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, unlock: sch_tree_unlock(sch); + +table_free: + dist_free(delay_dist); + dist_free(slot_dist); return ret; - -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - - goto unlock; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, From 5525c289dbcf2b1adecc5e727e7d544ade9c7be1 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 6 Feb 2023 11:47:47 -0500 Subject: [PATCH 0318/2093] drm/amd/pm/smu7: move variables to where they are used commit 63a9ab264a8c030482ab9e7e20b6c4c162299531 upstream. Move variable declarations to where they are used. Fixes a segfault on smu7 V0 structures where some tables don't exist. Cc: Evan Quan Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2388 Fixes: b1a9557a7d00 ("drm/amd/pm: fulfill powerplay peak profiling mode shader/memory clock settings") Reviewed-by: Evan Quan Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 44ec238cfeff..a31a62a1ce0b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1505,12 +1505,6 @@ static void smu7_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) { struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); struct smu7_dpm_table *golden_dpm_table = &data->golden_dpm_table; - struct phm_clock_voltage_dependency_table *vddc_dependency_on_sclk = - hwmgr->dyn_state.vddc_dependency_on_sclk; - struct phm_ppt_v1_information *table_info = - (struct phm_ppt_v1_information *)(hwmgr->pptable); - struct phm_ppt_v1_clock_voltage_dependency_table *vdd_dep_on_sclk = - table_info->vdd_dep_on_sclk; int32_t tmp_sclk, count, percentage; if (golden_dpm_table->mclk_table.count == 1) { @@ -1525,6 +1519,9 @@ static void smu7_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) tmp_sclk = hwmgr->pstate_mclk * percentage / 100; if (hwmgr->pp_table_version == PP_TABLE_V0) { + struct phm_clock_voltage_dependency_table *vddc_dependency_on_sclk = + hwmgr->dyn_state.vddc_dependency_on_sclk; + for (count = vddc_dependency_on_sclk->count - 1; count >= 0; count--) { if (tmp_sclk >= vddc_dependency_on_sclk->entries[count].clk) { hwmgr->pstate_sclk = vddc_dependency_on_sclk->entries[count].clk; @@ -1537,6 +1534,11 @@ static void smu7_populate_umdpstate_clocks(struct pp_hwmgr *hwmgr) hwmgr->pstate_sclk_peak = vddc_dependency_on_sclk->entries[vddc_dependency_on_sclk->count - 1].clk; } else if (hwmgr->pp_table_version == PP_TABLE_V1) { + struct phm_ppt_v1_information *table_info = + (struct phm_ppt_v1_information *)(hwmgr->pptable); + struct phm_ppt_v1_clock_voltage_dependency_table *vdd_dep_on_sclk = + table_info->vdd_dep_on_sclk; + for (count = vdd_dep_on_sclk->count - 1; count >= 0; count--) { if (tmp_sclk >= vdd_dep_on_sclk->entries[count].clk) { hwmgr->pstate_sclk = vdd_dep_on_sclk->entries[count].clk; From 6c44e13dc284f7f4db17706ca48fd016d6b3d49a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 16 Aug 2023 18:27:31 +0200 Subject: [PATCH 0319/2093] Linux 6.1.46 Link: https://lore.kernel.org/r/20230813211718.757428827@linuxfoundation.org Tested-by: Bagas Sanjaya Tested-by: Takeshi Ogasawara Tested-by: Conor Dooley Tested-by: Thierry Reding Tested-by: SeongJae Park Tested-by: Salvatore Bonaccorso Tested-by: Ron Economos Tested-by: Shuah Khan Tested-by: Florian Fainelli Tested-by: Allen Pais Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 82c958299e98..bdb965177db5 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 45 +SUBLEVEL = 46 EXTRAVERSION = NAME = Curry Ramen From 78721c8f93799d63882be15f64d428a79074db96 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Fri, 30 Jun 2023 09:45:33 +0900 Subject: [PATCH 0320/2093] mmc: sdhci-f-sdh30: Replace with sdhci_pltfm [ Upstream commit 5def5c1c15bf22934ee227af85c1716762f3829f ] Even if sdhci_pltfm_pmops is specified for PM, this driver doesn't apply sdhci_pltfm, so the structure is not correctly referenced in PM functions. This applies sdhci_pltfm to this driver to fix this issue. - Call sdhci_pltfm_init() instead of sdhci_alloc_host() and other functions that covered by sdhci_pltfm. - Move ops and quirks to sdhci_pltfm_data - Replace sdhci_priv() with own private function sdhci_f_sdh30_priv(). Fixes: 87a507459f49 ("mmc: sdhci: host: add new f_sdh30") Signed-off-by: Kunihiko Hayashi Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230630004533.26644-1-hayashi.kunihiko@socionext.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/sdhci_f_sdh30.c | 60 ++++++++++++++------------------ 1 file changed, 27 insertions(+), 33 deletions(-) diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c index 6c4f43e11282..8876fd1c7eee 100644 --- a/drivers/mmc/host/sdhci_f_sdh30.c +++ b/drivers/mmc/host/sdhci_f_sdh30.c @@ -26,9 +26,16 @@ struct f_sdhost_priv { bool enable_cmd_dat_delay; }; +static void *sdhci_f_sdhost_priv(struct sdhci_host *host) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + + return sdhci_pltfm_priv(pltfm_host); +} + static void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host) { - struct f_sdhost_priv *priv = sdhci_priv(host); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); u32 ctrl = 0; usleep_range(2500, 3000); @@ -61,7 +68,7 @@ static unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host) static void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask) { - struct f_sdhost_priv *priv = sdhci_priv(host); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); u32 ctl; if (sdhci_readw(host, SDHCI_CLOCK_CONTROL) == 0) @@ -85,30 +92,32 @@ static const struct sdhci_ops sdhci_f_sdh30_ops = { .set_uhs_signaling = sdhci_set_uhs_signaling, }; +static const struct sdhci_pltfm_data sdhci_f_sdh30_pltfm_data = { + .ops = &sdhci_f_sdh30_ops, + .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC + | SDHCI_QUIRK_INVERTED_WRITE_PROTECT, + .quirks2 = SDHCI_QUIRK2_SUPPORT_SINGLE + | SDHCI_QUIRK2_TUNING_WORK_AROUND, +}; + static int sdhci_f_sdh30_probe(struct platform_device *pdev) { struct sdhci_host *host; struct device *dev = &pdev->dev; - int irq, ctrl = 0, ret = 0; + int ctrl = 0, ret = 0; struct f_sdhost_priv *priv; + struct sdhci_pltfm_host *pltfm_host; u32 reg = 0; - irq = platform_get_irq(pdev, 0); - if (irq < 0) - return irq; - - host = sdhci_alloc_host(dev, sizeof(struct f_sdhost_priv)); + host = sdhci_pltfm_init(pdev, &sdhci_f_sdh30_pltfm_data, + sizeof(struct f_sdhost_priv)); if (IS_ERR(host)) return PTR_ERR(host); - priv = sdhci_priv(host); + pltfm_host = sdhci_priv(host); + priv = sdhci_pltfm_priv(pltfm_host); priv->dev = dev; - host->quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC | - SDHCI_QUIRK_INVERTED_WRITE_PROTECT; - host->quirks2 = SDHCI_QUIRK2_SUPPORT_SINGLE | - SDHCI_QUIRK2_TUNING_WORK_AROUND; - priv->enable_cmd_dat_delay = device_property_read_bool(dev, "fujitsu,cmd-dat-delay-select"); @@ -116,18 +125,6 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev) if (ret) goto err; - platform_set_drvdata(pdev, host); - - host->hw_name = "f_sdh30"; - host->ops = &sdhci_f_sdh30_ops; - host->irq = irq; - - host->ioaddr = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(host->ioaddr)) { - ret = PTR_ERR(host->ioaddr); - goto err; - } - if (dev_of_node(dev)) { sdhci_get_of_property(pdev); @@ -182,23 +179,20 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev) err_clk: clk_disable_unprepare(priv->clk_iface); err: - sdhci_free_host(host); + sdhci_pltfm_free(pdev); + return ret; } static int sdhci_f_sdh30_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); - struct f_sdhost_priv *priv = sdhci_priv(host); - - sdhci_remove_host(host, readl(host->ioaddr + SDHCI_INT_STATUS) == - 0xffffffff); + struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); clk_disable_unprepare(priv->clk_iface); clk_disable_unprepare(priv->clk); - sdhci_free_host(host); - platform_set_drvdata(pdev, NULL); + sdhci_pltfm_unregister(pdev); return 0; } From ad1fa1a028ee75b07f6802e40e8bfd526d52186b Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 20 Oct 2022 13:55:13 +0200 Subject: [PATCH 0321/2093] cpuidle: psci: Extend information in log about OSI/PC mode [ Upstream commit 668057b07db069daac3ca4e4978f8373db9cb71c ] It's useful to understand whether we are using OS-initiated (OSI) mode or Platform Coordinated (PC) mode, when initializing the CPU PM domains. Therefore, let's extend the print in the log after a successful probe with this information. Signed-off-by: Ulf Hansson Acked-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki Stable-dep-of: 12acb348fa45 ("cpuidle: psci: Move enabling OSI mode after power domains creation") Signed-off-by: Sasha Levin --- drivers/cpuidle/cpuidle-psci-domain.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index fe0664472520..1fca250d5dec 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -182,7 +182,8 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) if (ret) goto remove_pd; - pr_info("Initialized CPU PM domain topology\n"); + pr_info("Initialized CPU PM domain topology using %s mode\n", + use_osi ? "OSI" : "PC"); return 0; put_node: From 8a214f88e8ff459467f2652f341f755e38b94045 Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Mon, 3 Jul 2023 14:25:54 +0530 Subject: [PATCH 0322/2093] cpuidle: psci: Move enabling OSI mode after power domains creation [ Upstream commit 12acb348fa4528a4203edf1cce7a3be2c9af2279 ] A switch from OSI to PC mode is only possible if all CPUs other than the calling one are OFF, either through a call to CPU_OFF or not yet booted. Currently OSI mode is enabled before power domains are created. In cases where CPUidle states are not using hierarchical CPU topology the bail out path tries to switch back to PC mode which gets denied by firmware since other CPUs are online at this point and creates inconsistent state as firmware is in OSI mode and Linux in PC mode. This change moves enabling OSI mode after power domains are created, this would makes sure that hierarchical CPU topology is used before switching firmware to OSI mode. Cc: stable@vger.kernel.org Fixes: 70c179b49870 ("cpuidle: psci: Allow PM domain to be initialized even if no OSI mode") Signed-off-by: Maulik Shah Reviewed-by: Ulf Hansson Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/cpuidle/cpuidle-psci-domain.c | 39 +++++++++------------------ 1 file changed, 13 insertions(+), 26 deletions(-) diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index 1fca250d5dec..f5d4359555d7 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -117,20 +117,6 @@ static void psci_pd_remove(void) } } -static bool psci_pd_try_set_osi_mode(void) -{ - int ret; - - if (!psci_has_osi_support()) - return false; - - ret = psci_set_osi_mode(true); - if (ret) - return false; - - return true; -} - static void psci_cpuidle_domain_sync_state(struct device *dev) { /* @@ -149,15 +135,12 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *node; - bool use_osi; + bool use_osi = psci_has_osi_support(); int ret = 0, pd_count = 0; if (!np) return -ENODEV; - /* If OSI mode is supported, let's try to enable it. */ - use_osi = psci_pd_try_set_osi_mode(); - /* * Parse child nodes for the "#power-domain-cells" property and * initialize a genpd/genpd-of-provider pair when it's found. @@ -167,33 +150,37 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) continue; ret = psci_pd_init(node, use_osi); - if (ret) - goto put_node; + if (ret) { + of_node_put(node); + goto exit; + } pd_count++; } /* Bail out if not using the hierarchical CPU topology. */ if (!pd_count) - goto no_pd; + return 0; /* Link genpd masters/subdomains to model the CPU topology. */ ret = dt_idle_pd_init_topology(np); if (ret) goto remove_pd; + /* let's try to enable OSI. */ + ret = psci_set_osi_mode(use_osi); + if (ret) + goto remove_pd; + pr_info("Initialized CPU PM domain topology using %s mode\n", use_osi ? "OSI" : "PC"); return 0; -put_node: - of_node_put(node); remove_pd: + dt_idle_pd_remove_topology(np); psci_pd_remove(); +exit: pr_err("failed to create CPU PM domains ret=%d\n", ret); -no_pd: - if (use_osi) - psci_set_osi_mode(false); return ret; } From 802b34e99224cf625ca8a8cc0646ad55385225f5 Mon Sep 17 00:00:00 2001 From: Nhat Pham Date: Mon, 28 Nov 2022 11:16:12 -0800 Subject: [PATCH 0323/2093] zsmalloc: consolidate zs_pool's migrate_lock and size_class's locks [ Upstream commit c0547d0b6a4b637db05406b90ba82e1b2e71de56 ] Currently, zsmalloc has a hierarchy of locks, which includes a pool-level migrate_lock, and a lock for each size class. We have to obtain both locks in the hotpath in most cases anyway, except for zs_malloc. This exception will no longer exist when we introduce a LRU into the zs_pool for the new writeback functionality - we will need to obtain a pool-level lock to synchronize LRU handling even in zs_malloc. In preparation for zsmalloc writeback, consolidate these locks into a single pool-level lock, which drastically reduces the complexity of synchronization in zsmalloc. We have also benchmarked the lock consolidation to see the performance effect of this change on zram. First, we ran a synthetic FS workload on a server machine with 36 cores (same machine for all runs), using fs_mark -d ../zram1mnt -s 100000 -n 2500 -t 32 -k before and after for btrfs and ext4 on zram (FS usage is 80%). Here is the result (unit is file/second): With lock consolidation (btrfs): Average: 13520.2, Median: 13531.0, Stddev: 137.5961482019028 Without lock consolidation (btrfs): Average: 13487.2, Median: 13575.0, Stddev: 309.08283679298665 With lock consolidation (ext4): Average: 16824.4, Median: 16839.0, Stddev: 89.97388510006668 Without lock consolidation (ext4) Average: 16958.0, Median: 16986.0, Stddev: 194.7370021336469 As you can see, we observe a 0.3% regression for btrfs, and a 0.9% regression for ext4. This is a small, barely measurable difference in my opinion. For a more realistic scenario, we also tries building the kernel on zram. Here is the time it takes (in seconds): With lock consolidation (btrfs): real Average: 319.6, Median: 320.0, Stddev: 0.8944271909999159 user Average: 6894.2, Median: 6895.0, Stddev: 25.528415540334656 sys Average: 521.4, Median: 522.0, Stddev: 1.51657508881031 Without lock consolidation (btrfs): real Average: 319.8, Median: 320.0, Stddev: 0.8366600265340756 user Average: 6896.6, Median: 6899.0, Stddev: 16.04057355583023 sys Average: 520.6, Median: 521.0, Stddev: 1.140175425099138 With lock consolidation (ext4): real Average: 320.0, Median: 319.0, Stddev: 1.4142135623730951 user Average: 6896.8, Median: 6878.0, Stddev: 28.621670111997307 sys Average: 521.2, Median: 521.0, Stddev: 1.7888543819998317 Without lock consolidation (ext4) real Average: 319.6, Median: 319.0, Stddev: 0.8944271909999159 user Average: 6886.2, Median: 6887.0, Stddev: 16.93221781102523 sys Average: 520.4, Median: 520.0, Stddev: 1.140175425099138 The difference is entirely within the noise of a typical run on zram. This hardly justifies the complexity of maintaining both the pool lock and the class lock. In fact, for writeback, we would need to introduce yet another lock to prevent data races on the pool's LRU, further complicating the lock handling logic. IMHO, it is just better to collapse all of these into a single pool-level lock. Link: https://lkml.kernel.org/r/20221128191616.1261026-4-nphamcs@gmail.com Signed-off-by: Nhat Pham Suggested-by: Johannes Weiner Acked-by: Minchan Kim Acked-by: Johannes Weiner Reviewed-by: Sergey Senozhatsky Cc: Dan Streetman Cc: Nitin Gupta Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Stable-dep-of: 4b5d1e47b694 ("zsmalloc: fix races between modifications of fullness and isolated") Signed-off-by: Sasha Levin --- mm/zsmalloc.c | 87 ++++++++++++++++++++++----------------------------- 1 file changed, 37 insertions(+), 50 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index d03941cace2c..326faa751f0a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -33,8 +33,7 @@ /* * lock ordering: * page_lock - * pool->migrate_lock - * class->lock + * pool->lock * zspage->lock */ @@ -192,7 +191,6 @@ static const int fullness_threshold_frac = 4; static size_t huge_class_size; struct size_class { - spinlock_t lock; struct list_head fullness_list[NR_ZS_FULLNESS]; /* * Size of objects stored in this class. Must be multiple @@ -247,8 +245,7 @@ struct zs_pool { #ifdef CONFIG_COMPACTION struct work_struct free_work; #endif - /* protect page/zspage migration */ - rwlock_t migrate_lock; + spinlock_t lock; }; struct zspage { @@ -355,7 +352,7 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) kmem_cache_free(pool->zspage_cachep, zspage); } -/* class->lock(which owns the handle) synchronizes races */ +/* pool->lock(which owns the handle) synchronizes races */ static void record_obj(unsigned long handle, unsigned long obj) { *(unsigned long *)handle = obj; @@ -452,7 +449,7 @@ static __maybe_unused int is_first_page(struct page *page) return PagePrivate(page); } -/* Protected by class->lock */ +/* Protected by pool->lock */ static inline int get_zspage_inuse(struct zspage *zspage) { return zspage->inuse; @@ -597,13 +594,13 @@ static int zs_stats_size_show(struct seq_file *s, void *v) if (class->index != i) continue; - spin_lock(&class->lock); + spin_lock(&pool->lock); class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); obj_used = zs_stat_get(class, OBJ_USED); freeable = zs_can_compact(class); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); objs_per_zspage = class->objs_per_zspage; pages_used = obj_allocated / objs_per_zspage * @@ -916,7 +913,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, get_zspage_mapping(zspage, &class_idx, &fg); - assert_spin_locked(&class->lock); + assert_spin_locked(&pool->lock); VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(fg != ZS_EMPTY); @@ -1247,19 +1244,19 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, BUG_ON(in_interrupt()); /* It guarantees it can get zspage from handle safely */ - read_lock(&pool->migrate_lock); + spin_lock(&pool->lock); obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); /* - * migration cannot move any zpages in this zspage. Here, class->lock + * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls * zs_unmap_object API so delegate the locking from class to zspage * which is smaller granularity. */ migrate_read_lock(zspage); - read_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); class = zspage_class(pool, zspage); off = (class->size * obj_idx) & ~PAGE_MASK; @@ -1412,8 +1409,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; - /* class->lock effectively protects the zpage migration */ - spin_lock(&class->lock); + /* pool->lock effectively protects the zpage migration */ + spin_lock(&pool->lock); zspage = find_get_zspage(class); if (likely(zspage)) { obj = obj_malloc(pool, zspage, handle); @@ -1421,12 +1418,12 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, OBJ_USED, 1); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); return handle; } - spin_unlock(&class->lock); + spin_unlock(&pool->lock); zspage = alloc_zspage(pool, class, gfp); if (!zspage) { @@ -1434,7 +1431,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) return (unsigned long)ERR_PTR(-ENOMEM); } - spin_lock(&class->lock); + spin_lock(&pool->lock); obj = obj_malloc(pool, zspage, handle); newfg = get_fullness_group(class, zspage); insert_zspage(class, zspage, newfg); @@ -1447,7 +1444,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); return handle; } @@ -1491,16 +1488,14 @@ void zs_free(struct zs_pool *pool, unsigned long handle) return; /* - * The pool->migrate_lock protects the race with zpage's migration + * The pool->lock protects the race with zpage's migration * so it's safe to get the page from handle. */ - read_lock(&pool->migrate_lock); + spin_lock(&pool->lock); obj = handle_to_obj(handle); obj_to_page(obj, &f_page); zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - spin_lock(&class->lock); - read_unlock(&pool->migrate_lock); obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); @@ -1510,7 +1505,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle) free_zspage(pool, class, zspage); out: - spin_unlock(&class->lock); + spin_unlock(&pool->lock); cache_free_handle(pool, handle); } EXPORT_SYMBOL_GPL(zs_free); @@ -1867,16 +1862,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page, pool = zspage->pool; /* - * The pool migrate_lock protects the race between zpage migration + * The pool's lock protects the race between zpage migration * and zs_free. */ - write_lock(&pool->migrate_lock); + spin_lock(&pool->lock); class = zspage_class(pool, zspage); - /* - * the class lock protects zpage alloc/free in the zspage. - */ - spin_lock(&class->lock); /* the migrate_write_lock protects zpage access via zs_map_object */ migrate_write_lock(zspage); @@ -1906,10 +1897,9 @@ static int zs_page_migrate(struct page *newpage, struct page *page, replace_sub_page(class, zspage, newpage, page); /* * Since we complete the data copy and set up new zspage structure, - * it's okay to release migration_lock. + * it's okay to release the pool's lock. */ - write_unlock(&pool->migrate_lock); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); dec_zspage_isolation(zspage); migrate_write_unlock(zspage); @@ -1964,9 +1954,9 @@ static void async_free_zspage(struct work_struct *work) if (class->index != i) continue; - spin_lock(&class->lock); + spin_lock(&pool->lock); list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); } list_for_each_entry_safe(zspage, tmp, &free_pages, list) { @@ -1976,9 +1966,9 @@ static void async_free_zspage(struct work_struct *work) get_zspage_mapping(zspage, &class_idx, &fullness); VM_BUG_ON(fullness != ZS_EMPTY); class = pool->size_class[class_idx]; - spin_lock(&class->lock); + spin_lock(&pool->lock); __free_zspage(pool, class, zspage); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); } }; @@ -2039,10 +2029,11 @@ static unsigned long __zs_compact(struct zs_pool *pool, struct zspage *dst_zspage = NULL; unsigned long pages_freed = 0; - /* protect the race between zpage migration and zs_free */ - write_lock(&pool->migrate_lock); - /* protect zpage allocation/free */ - spin_lock(&class->lock); + /* + * protect the race between zpage migration and zs_free + * as well as zpage allocation/free + */ + spin_lock(&pool->lock); while ((src_zspage = isolate_zspage(class, true))) { /* protect someone accessing the zspage(i.e., zs_map_object) */ migrate_write_lock(src_zspage); @@ -2067,7 +2058,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, putback_zspage(class, dst_zspage); migrate_write_unlock(dst_zspage); dst_zspage = NULL; - if (rwlock_is_contended(&pool->migrate_lock)) + if (spin_is_contended(&pool->lock)) break; } @@ -2084,11 +2075,9 @@ static unsigned long __zs_compact(struct zs_pool *pool, pages_freed += class->pages_per_zspage; } else migrate_write_unlock(src_zspage); - spin_unlock(&class->lock); - write_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); cond_resched(); - write_lock(&pool->migrate_lock); - spin_lock(&class->lock); + spin_lock(&pool->lock); } if (src_zspage) { @@ -2096,8 +2085,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, migrate_write_unlock(src_zspage); } - spin_unlock(&class->lock); - write_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); return pages_freed; } @@ -2200,7 +2188,7 @@ struct zs_pool *zs_create_pool(const char *name) return NULL; init_deferred_free(pool); - rwlock_init(&pool->migrate_lock); + spin_lock_init(&pool->lock); pool->name = kstrdup(name, GFP_KERNEL); if (!pool->name) @@ -2271,7 +2259,6 @@ struct zs_pool *zs_create_pool(const char *name) class->index = i; class->pages_per_zspage = pages_per_zspage; class->objs_per_zspage = objs_per_zspage; - spin_lock_init(&class->lock); pool->size_class[i] = class; for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS; fullness++) From f872672edd5eb02c61a3630d0c3ba4a3c919b479 Mon Sep 17 00:00:00 2001 From: Andrew Yang Date: Fri, 21 Jul 2023 14:37:01 +0800 Subject: [PATCH 0324/2093] zsmalloc: fix races between modifications of fullness and isolated [ Upstream commit 4b5d1e47b69426c0f7491d97d73ad0152d02d437 ] We encountered many kernel exceptions of VM_BUG_ON(zspage->isolated == 0) in dec_zspage_isolation() and BUG_ON(!pages[1]) in zs_unmap_object() lately. This issue only occurs when migration and reclamation occur at the same time. With our memory stress test, we can reproduce this issue several times a day. We have no idea why no one else encountered this issue. BTW, we switched to the new kernel version with this defect a few months ago. Since fullness and isolated share the same unsigned int, modifications of them should be protected by the same lock. [andrew.yang@mediatek.com: move comment] Link: https://lkml.kernel.org/r/20230727062910.6337-1-andrew.yang@mediatek.com Link: https://lkml.kernel.org/r/20230721063705.11455-1-andrew.yang@mediatek.com Fixes: c4549b871102 ("zsmalloc: remove zspage isolation for migration") Signed-off-by: Andrew Yang Reviewed-by: Sergey Senozhatsky Cc: AngeloGioacchino Del Regno Cc: Matthias Brugger Cc: Minchan Kim Cc: Sebastian Andrzej Siewior Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- mm/zsmalloc.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 326faa751f0a..2f5e6d35b03b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1816,6 +1816,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage, static bool zs_page_isolate(struct page *page, isolate_mode_t mode) { + struct zs_pool *pool; struct zspage *zspage; /* @@ -1826,9 +1827,10 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode) VM_BUG_ON_PAGE(PageIsolated(page), page); zspage = get_zspage(page); - migrate_write_lock(zspage); + pool = zspage->pool; + spin_lock(&pool->lock); inc_zspage_isolation(zspage); - migrate_write_unlock(zspage); + spin_unlock(&pool->lock); return true; } @@ -1895,12 +1897,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page, kunmap_atomic(s_addr); replace_sub_page(class, zspage, newpage, page); + dec_zspage_isolation(zspage); /* * Since we complete the data copy and set up new zspage structure, * it's okay to release the pool's lock. */ spin_unlock(&pool->lock); - dec_zspage_isolation(zspage); migrate_write_unlock(zspage); get_page(newpage); @@ -1917,15 +1919,17 @@ static int zs_page_migrate(struct page *newpage, struct page *page, static void zs_page_putback(struct page *page) { + struct zs_pool *pool; struct zspage *zspage; VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); zspage = get_zspage(page); - migrate_write_lock(zspage); + pool = zspage->pool; + spin_lock(&pool->lock); dec_zspage_isolation(zspage); - migrate_write_unlock(zspage); + spin_unlock(&pool->lock); } static const struct movable_operations zsmalloc_mops = { From 306a5dddfb124af7d920a8b59a9f8df3747d4e1f Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Tue, 14 Feb 2023 10:52:37 +0100 Subject: [PATCH 0325/2093] selftests: forwarding: tc_actions: cleanup temporary files when test is aborted [ Upstream commit f58531716ced8975a4ade108ef4af35f98722af7 ] remove temporary files created by 'mirred_egress_to_ingress_tcp' test in the cleanup() handler. Also, change variable names to avoid clashing with globals from lib.sh. Suggested-by: Paolo Abeni Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/091649045a017fc00095ecbb75884e5681f7025f.1676368027.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski Stable-dep-of: 5e8670610b93 ("selftests: forwarding: tc_actions: Use ncat instead of nc") Signed-off-by: Sasha Levin --- .../selftests/net/forwarding/tc_actions.sh | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 919c0dd9fe4b..a96cff8e7219 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -201,10 +201,10 @@ mirred_egress_to_ingress_test() mirred_egress_to_ingress_tcp_test() { - local tmpfile=$(mktemp) tmpfile1=$(mktemp) + mirred_e2i_tf1=$(mktemp) mirred_e2i_tf2=$(mktemp) RET=0 - dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile + dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$mirred_e2i_tf1 tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ action ct commit nat src addr 192.0.2.2 pipe \ @@ -220,11 +220,11 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1 & + ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile + ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid - cmp -s $tmpfile $tmpfile1 + cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ @@ -241,7 +241,7 @@ mirred_egress_to_ingress_tcp_test() tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower - rm -f $tmpfile $tmpfile1 + rm -f $mirred_e2i_tf1 $mirred_e2i_tf2 log_test "mirred_egress_to_ingress_tcp ($tcflags)" } @@ -270,6 +270,8 @@ setup_prepare() cleanup() { + local tf + pre_cleanup switch_destroy @@ -280,6 +282,8 @@ cleanup() ip link set $swp2 address $swp2origmac ip link set $swp1 address $swp1origmac + + for tf in $mirred_e2i_tf1 $mirred_e2i_tf2; do rm -f $tf; done } mirred_egress_redirect_test() From 0fc3c55a3a4b0ef635e2cc6f32417649de49b0d2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Aug 2023 17:14:57 +0300 Subject: [PATCH 0326/2093] selftests: forwarding: tc_actions: Use ncat instead of nc [ Upstream commit 5e8670610b93158ffacc3241f835454ff26a3469 ] The test relies on 'nc' being the netcat version from the nmap project. While this seems to be the case on Fedora, it is not the case on Ubuntu, resulting in failures such as [1]. Fix by explicitly using the 'ncat' utility from the nmap project and the skip the test in case it is not installed. [1] # timeout set to 0 # selftests: net/forwarding: tc_actions.sh # TEST: gact drop and ok (skip_hw) [ OK ] # TEST: mirred egress flower redirect (skip_hw) [ OK ] # TEST: mirred egress flower mirror (skip_hw) [ OK ] # TEST: mirred egress matchall mirror (skip_hw) [ OK ] # TEST: mirred_egress_to_ingress (skip_hw) [ OK ] # nc: invalid option -- '-' # usage: nc [-46CDdFhklNnrStUuvZz] [-I length] [-i interval] [-M ttl] # [-m minttl] [-O length] [-P proxy_username] [-p source_port] # [-q seconds] [-s sourceaddr] [-T keyword] [-V rtable] [-W recvlimit] # [-w timeout] [-X proxy_protocol] [-x proxy_address[:port]] # [destination] [port] # nc: invalid option -- '-' # usage: nc [-46CDdFhklNnrStUuvZz] [-I length] [-i interval] [-M ttl] # [-m minttl] [-O length] [-P proxy_username] [-p source_port] # [-q seconds] [-s sourceaddr] [-T keyword] [-V rtable] [-W recvlimit] # [-w timeout] [-X proxy_protocol] [-x proxy_address[:port]] # [destination] [port] # TEST: mirred_egress_to_ingress_tcp (skip_hw) [FAIL] # server output check failed # INFO: Could not test offloaded functionality not ok 80 selftests: net/forwarding: tc_actions.sh # exit=1 Fixes: ca22da2fbd69 ("act_mirred: use the backlog for nested calls to mirred ingress") Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/adc5e40d-d040-a65e-eb26-edf47dac5b02@alu.unizg.hr/ Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Hangbin Liu Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230808141503.4060661-12-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- tools/testing/selftests/net/forwarding/tc_actions.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index a96cff8e7219..b0f5e55d2d0b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -9,6 +9,8 @@ NUM_NETIFS=4 source tc_common.sh source lib.sh +require_command ncat + tcflags="skip_hw" h1_create() @@ -220,9 +222,9 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" From 206381cee964c26547173be36280991bebd9ebcc Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 2 Feb 2023 16:26:42 +0800 Subject: [PATCH 0327/2093] net/smc: replace mutex rmbs_lock and sndbufs_lock with rw_semaphore [ Upstream commit aff7bfed9097435ea38de919befbe2d7771a3e87 ] It's clear that rmbs_lock and sndbufs_lock are aims to protect the rmbs list or the sndbufs list. During connection establieshment, smc_buf_get_slot() will always be invoked, and it only performs read semantics in rmbs list and sndbufs list. Based on the above considerations, we replace mutex with rw_semaphore. Only smc_buf_get_slot() use down_read() to allow smc_buf_get_slot() run concurrently, other part use down_write() to keep exclusive semantics. Signed-off-by: D. Wythe Signed-off-by: David S. Miller Stable-dep-of: 833bac7ec392 ("net/smc: Fix setsockopt and sysctl to specify same buffer size again") Signed-off-by: Sasha Levin --- net/smc/smc_core.c | 55 +++++++++++++++++++++++----------------------- net/smc/smc_core.h | 4 ++-- net/smc/smc_llc.c | 16 +++++++------- 3 files changed, 38 insertions(+), 37 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f82f43573a15..f793101e0ecc 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -852,8 +852,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ - mutex_init(&lgr->sndbufs_lock); - mutex_init(&lgr->rmbs_lock); + init_rwsem(&lgr->sndbufs_lock); + init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); @@ -1095,7 +1095,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { - struct mutex *lock; /* lock buffer list */ + struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { @@ -1115,9 +1115,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; - mutex_lock(lock); + down_write(lock); list_del(&buf_desc->list); - mutex_unlock(lock); + up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { @@ -1220,15 +1220,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk) int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); - mutex_unlock(&lgr->rmbs_lock); - mutex_lock(&lgr->sndbufs_lock); + up_write(&lgr->rmbs_lock); + + down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); } } @@ -1986,19 +1987,19 @@ int smc_uncompress_bufsize(u8 compressed) * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, - struct mutex *lock, + struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; - mutex_lock(lock); + down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { - mutex_unlock(lock); + up_read(lock); return buf_slot; } } - mutex_unlock(lock); + up_read(lock); return NULL; } @@ -2107,13 +2108,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) return 0; } -static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, +static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; - mutex_lock(lock); + down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; @@ -2122,7 +2123,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, goto out; } out: - mutex_unlock(lock); + up_write(lock); return rc; } @@ -2155,37 +2156,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) int i, rc = 0; /* reg all RMBs for a new link */ - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } } } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ - mutex_lock(&lgr->sndbufs_lock); + down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } } } - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } @@ -2305,8 +2306,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - struct mutex *lock; /* lock buffer list */ int sk_buf_size; if (is_rmb) @@ -2354,9 +2355,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; - mutex_lock(lock); + down_write(lock); list_add(&buf_desc->list, buf_list); - mutex_unlock(lock); + up_write(lock); break; /* found */ } @@ -2430,9 +2431,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc) { - mutex_lock(&smc->conn.lgr->sndbufs_lock); + down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); - mutex_unlock(&smc->conn.lgr->sndbufs_lock); + up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 285f9bd8e232..6051d9227013 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -252,9 +252,9 @@ struct smc_link_group { unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ - struct mutex sndbufs_lock; /* protects tx buffers */ + struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 760f8bbff822..fcb24a0ccf76 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -611,7 +611,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, prim_lnk_idx = link->link_idx; lnk_idx = link_new->link_idx; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); ext->num_rkeys = lgr->conns_num; if (!ext->num_rkeys) goto out; @@ -631,7 +631,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, } len += i * sizeof(ext->rt[0]); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return len; } @@ -892,7 +892,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -919,7 +919,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, break; } while (num_rkeys_send || num_rkeys_recv); - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -1002,14 +1002,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link, ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, ext->rt[i].rmb_key, ext->rt[i].rmb_vaddr_new, ext->rt[i].rmb_key_new); } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); } static void smc_llc_save_add_link_info(struct smc_link *link, @@ -1316,7 +1316,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -1341,7 +1341,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); } while (num_rkeys_send || num_rkeys_recv); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } From 0d52759710faf29e32acbb72e8a2a05c210dcffd Mon Sep 17 00:00:00 2001 From: Gerd Bayer Date: Fri, 4 Aug 2023 19:06:23 +0200 Subject: [PATCH 0328/2093] net/smc: Fix setsockopt and sysctl to specify same buffer size again MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 833bac7ec392bf75053c8a4fa4c36d4148dac77d ] Commit 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and make them tunable") introduced the net.smc.rmem and net.smc.wmem sysctls to specify the size of buffers to be used for SMC type connections. This created a regression for users that specified the buffer size via setsockopt() as the effective buffer size was now doubled. Re-introduce the division by 2 in the SMC buffer create code and level this out by duplicating the net.smc.[rw]mem values used for initializing sk_rcvbuf/sk_sndbuf at socket creation time. This gives users of both methods (setsockopt or sysctl) the effective buffer size that they expect. Initialize net.smc.[rw]mem from its own constant of 64kB, respectively. Internal performance tests show that this value is a good compromise between throughput/latency and memory consumption. Also, this decouples it from any tuning that was done to net.ipv4.tcp_[rw]mem[1] before the module for SMC protocol was loaded. Check that no more than INT_MAX / 2 is assigned to net.smc.[rw]mem, in order to avoid any overflow condition when that is doubled for use in sk_sndbuf or sk_rcvbuf. While at it, drop the confusing sk_buf_size variable from __smc_buf_create and name "compressed" buffer size variables more consistently. Background: Before the commit mentioned above, SMC's buffer allocator in __smc_buf_create() always used half of the sockets' sk_rcvbuf/sk_sndbuf value as initial value to search for appropriate buffers. If the search resorted to using a bigger buffer when all buffers of the specified size were busy, the duplicate of the used effective buffer size is stored back to sk_rcvbuf/sk_sndbuf. When available, buffers of exactly the size that a user had specified as input to setsockopt() were used, despite setsockopt()'s documentation in "man 7 socket" talking of a mandatory duplication: [...] SO_SNDBUF Sets or gets the maximum socket send buffer in bytes. The kernel doubles this value (to allow space for book‐ keeping overhead) when it is set using setsockopt(2), and this doubled value is returned by getsockopt(2). The default value is set by the /proc/sys/net/core/wmem_default file and the maximum allowed value is set by the /proc/sys/net/core/wmem_max file. The minimum (doubled) value for this option is 2048. [...] Fixes: 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and make them tunable") Co-developed-by: Jan Karcher Signed-off-by: Jan Karcher Reviewed-by: Wenjia Zhang Reviewed-by: Tony Lu Signed-off-by: Gerd Bayer Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/af_smc.c | 4 ++-- net/smc/smc.h | 2 +- net/smc/smc_clc.c | 4 ++-- net/smc/smc_core.c | 25 ++++++++++++------------- net/smc/smc_sysctl.c | 10 ++++++++-- 5 files changed, 25 insertions(+), 20 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5712a5297bd0..84219c5121bc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -379,8 +379,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; - WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem)); - WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem)); + WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); + WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5ed765ea0c73..1d36720fc019 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -161,7 +161,7 @@ struct smc_connection { struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ + int rmbe_size_comp; /* compressed notation */ int rmbe_update_limit; /* lower limit for consumer * cursor update diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index dfb9797f7bc6..9b8999e2afca 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1002,7 +1002,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->hdr.typev1 = SMC_TYPE_D; clc->d0.gid = conn->lgr->smcd->local_gid; clc->d0.token = conn->rmb_desc->token; - clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { @@ -1045,7 +1045,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } - clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f793101e0ecc..c676d92af7b7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2305,31 +2305,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; - int bufsize, bufsize_short; + int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - int sk_buf_size; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_rcvbuf; + bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_sndbuf; + bufsize = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); - bufsize_short >= 0; bufsize_short--) { + for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); + bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; - buf_list = &lgr->rmbs[bufsize_short]; + buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; - buf_list = &lgr->sndbufs[bufsize_short]; + buf_list = &lgr->sndbufs[bufsize_comp]; } - bufsize = smc_uncompress_bufsize(bufsize_short); + bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); @@ -2373,8 +2372,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size_short = bufsize_short; - smc->sk.sk_rcvbuf = bufsize; + conn->rmbe_size_comp = bufsize_comp; + smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); @@ -2382,7 +2381,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; - smc->sk.sk_sndbuf = bufsize; + smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index b6f79fabb9d3..0b2a957ca5f5 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -21,6 +21,10 @@ static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; +static int max_sndbuf = INT_MAX / 2; +static int max_rcvbuf = INT_MAX / 2; +static const int net_smc_wmem_init = (64 * 1024); +static const int net_smc_rmem_init = (64 * 1024); static struct ctl_table smc_table[] = { { @@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, + .extra2 = &max_sndbuf, }, { .procname = "rmem", @@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, + .extra2 = &max_rcvbuf, }, { } }; @@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; - WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1])); - WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1])); + WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); + WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); return 0; From 7dcc894e1518b5be6de890deaafbcbef54c26d72 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 17 Jun 2023 16:24:37 +0200 Subject: [PATCH 0329/2093] net: phy: at803x: Use devm_regulator_get_enable_optional() [ Upstream commit 988e8d90b3dc482637532e61bc2d58bfc4af5167 ] Use devm_regulator_get_enable_optional() instead of hand writing it. It saves some line of code. Signed-off-by: Christophe JAILLET Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Stable-dep-of: e58f30246c35 ("net: phy: at803x: fix the wol setting functions") Signed-off-by: Sasha Levin --- drivers/net/phy/at803x.c | 44 +++++++--------------------------------- 1 file changed, 7 insertions(+), 37 deletions(-) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 61824a463df8..e351fa8b84b7 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -305,7 +305,6 @@ struct at803x_priv { bool is_1000basex; struct regulator_dev *vddio_rdev; struct regulator_dev *vddh_rdev; - struct regulator *vddio; u64 stats[ARRAY_SIZE(at803x_hw_stats)]; }; @@ -825,11 +824,11 @@ static int at803x_parse_dt(struct phy_device *phydev) if (ret < 0) return ret; - priv->vddio = devm_regulator_get_optional(&phydev->mdio.dev, - "vddio"); - if (IS_ERR(priv->vddio)) { + ret = devm_regulator_get_enable_optional(&phydev->mdio.dev, + "vddio"); + if (ret) { phydev_err(phydev, "failed to get VDDIO regulator\n"); - return PTR_ERR(priv->vddio); + return ret; } /* Only AR8031/8033 support 1000Base-X for SFP modules */ @@ -857,12 +856,6 @@ static int at803x_probe(struct phy_device *phydev) if (ret) return ret; - if (priv->vddio) { - ret = regulator_enable(priv->vddio); - if (ret < 0) - return ret; - } - if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; @@ -870,10 +863,8 @@ static int at803x_probe(struct phy_device *phydev) .wolopts = 0, }; - if (ccr < 0) { - ret = ccr; - goto err; - } + if (ccr < 0) + return ccr; mode_cfg = ccr & AT803X_MODE_CFG_MASK; switch (mode_cfg) { @@ -891,25 +882,11 @@ static int at803x_probe(struct phy_device *phydev) ret = at803x_set_wol(phydev, &wol); if (ret < 0) { phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); - goto err; + return ret; } } return 0; - -err: - if (priv->vddio) - regulator_disable(priv->vddio); - - return ret; -} - -static void at803x_remove(struct phy_device *phydev) -{ - struct at803x_priv *priv = phydev->priv; - - if (priv->vddio) - regulator_disable(priv->vddio); } static int at803x_get_features(struct phy_device *phydev) @@ -2022,7 +1999,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm Atheros AR8035", .flags = PHY_POLL_CABLE_TEST, .probe = at803x_probe, - .remove = at803x_remove, .config_aneg = at803x_config_aneg, .config_init = at803x_config_init, .soft_reset = genphy_soft_reset, @@ -2044,7 +2020,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm Atheros AR8030", .phy_id_mask = AT8030_PHY_ID_MASK, .probe = at803x_probe, - .remove = at803x_remove, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, .set_wol = at803x_set_wol, @@ -2060,7 +2035,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm Atheros AR8031/AR8033", .flags = PHY_POLL_CABLE_TEST, .probe = at803x_probe, - .remove = at803x_remove, .config_init = at803x_config_init, .config_aneg = at803x_config_aneg, .soft_reset = genphy_soft_reset, @@ -2083,7 +2057,6 @@ static struct phy_driver at803x_driver[] = { PHY_ID_MATCH_EXACT(ATH8032_PHY_ID), .name = "Qualcomm Atheros AR8032", .probe = at803x_probe, - .remove = at803x_remove, .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, @@ -2099,7 +2072,6 @@ static struct phy_driver at803x_driver[] = { PHY_ID_MATCH_EXACT(ATH9331_PHY_ID), .name = "Qualcomm Atheros AR9331 built-in PHY", .probe = at803x_probe, - .remove = at803x_remove, .suspend = at803x_suspend, .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, @@ -2116,7 +2088,6 @@ static struct phy_driver at803x_driver[] = { PHY_ID_MATCH_EXACT(QCA9561_PHY_ID), .name = "Qualcomm Atheros QCA9561 built-in PHY", .probe = at803x_probe, - .remove = at803x_remove, .suspend = at803x_suspend, .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, @@ -2182,7 +2153,6 @@ static struct phy_driver at803x_driver[] = { .name = "Qualcomm QCA8081", .flags = PHY_POLL_CABLE_TEST, .probe = at803x_probe, - .remove = at803x_remove, .config_intr = at803x_config_intr, .handle_interrupt = at803x_handle_interrupt, .get_tunable = at803x_get_tunable, From caa2d40a0da25b9878de063931aa631dd80b62e4 Mon Sep 17 00:00:00 2001 From: Li Yang Date: Wed, 2 Aug 2023 14:13:46 -0500 Subject: [PATCH 0330/2093] net: phy: at803x: fix the wol setting functions [ Upstream commit e58f30246c35c126c7571065b33bee4b3b1d2ef8 ] In commit 7beecaf7d507 ("net: phy: at803x: improve the WOL feature"), it seems not correct to use a wol_en bit in a 1588 Control Register which is only available on AR8031/AR8033(share the same phy_id) to determine if WoL is enabled. Change it back to use AT803X_INTR_ENABLE_WOL for determining the WoL status which is applicable on all chips supporting wol. Also update the at803x_set_wol() function to only update the 1588 register on chips having it. After this change, disabling wol at probe from commit d7cd5e06c9dd ("net: phy: at803x: disable WOL at probe") is no longer needed. Change it to just disable the WoL bit in 1588 register for AR8031/AR8033 to be aligned with AT803X_INTR_ENABLE_WOL in probe. Fixes: 7beecaf7d507 ("net: phy: at803x: improve the WOL feature") Signed-off-by: Li Yang Reviewed-by: Viorel Suman Reviewed-by: Wei Fang Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/at803x.c | 45 ++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index e351fa8b84b7..edd4b1e58d96 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -460,21 +460,27 @@ static int at803x_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i], mac[(i * 2) + 1] | (mac[(i * 2)] << 8)); - /* Enable WOL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - if (ret) - return ret; + /* Enable WOL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + if (ret) + return ret; + } /* Enable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL); if (ret) return ret; } else { - /* Disable WoL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - if (ret) - return ret; + /* Disable WoL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; + } /* Disable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0); if (ret) @@ -509,11 +515,11 @@ static void at803x_get_wol(struct phy_device *phydev, wol->supported = WAKE_MAGIC; wol->wolopts = 0; - value = phy_read_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL); + value = phy_read(phydev, AT803X_INTR_ENABLE); if (value < 0) return; - if (value & AT803X_WOL_EN) + if (value & AT803X_INTR_ENABLE_WOL) wol->wolopts |= WAKE_MAGIC; } @@ -859,9 +865,6 @@ static int at803x_probe(struct phy_device *phydev) if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; - struct ethtool_wolinfo wol = { - .wolopts = 0, - }; if (ccr < 0) return ccr; @@ -878,12 +881,14 @@ static int at803x_probe(struct phy_device *phydev) break; } - /* Disable WOL by default */ - ret = at803x_set_wol(phydev, &wol); - if (ret < 0) { - phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); + /* Disable WoL in 1588 register which is enabled + * by default + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) return ret; - } } return 0; From ab6f446c220db0c131f2071846afd835799be0fb Mon Sep 17 00:00:00 2001 From: Longlong Yao Date: Thu, 13 Apr 2023 13:21:45 +0800 Subject: [PATCH 0331/2093] drm/amdgpu: fix calltrace warning in amddrm_buddy_fini [ Upstream commit 01382501509871d0799bab6bd412c228486af5bf ] The following call trace is observed when removing the amdgpu driver, which is caused by that BOs allocated for psp are not freed until removing. [61811.450562] RIP: 0010:amddrm_buddy_fini.cold+0x29/0x47 [amddrm_buddy] [61811.450577] Call Trace: [61811.450577] [61811.450579] amdgpu_vram_mgr_fini+0x135/0x1c0 [amdgpu] [61811.450728] amdgpu_ttm_fini+0x207/0x290 [amdgpu] [61811.450870] amdgpu_bo_fini+0x27/0xa0 [amdgpu] [61811.451012] gmc_v9_0_sw_fini+0x4a/0x60 [amdgpu] [61811.451166] amdgpu_device_fini_sw+0x117/0x520 [amdgpu] [61811.451306] amdgpu_driver_release_kms+0x16/0x30 [amdgpu] [61811.451447] devm_drm_dev_init_release+0x4d/0x80 [drm] [61811.451466] devm_action_release+0x15/0x20 [61811.451469] release_nodes+0x40/0xb0 [61811.451471] devres_release_all+0x9b/0xd0 [61811.451473] __device_release_driver+0x1bb/0x2a0 [61811.451476] driver_detach+0xf3/0x140 [61811.451479] bus_remove_driver+0x6c/0xf0 [61811.451481] driver_unregister+0x31/0x60 [61811.451483] pci_unregister_driver+0x40/0x90 [61811.451486] amdgpu_exit+0x15/0x447 [amdgpu] For smu v13_0_2, if the GPU supports xgmi, refer to commit f5c7e7797060 ("drm/amdgpu: Adjust removal control flow for smu v13_0_2"), it will run gpu recover in AMDGPU_RESET_FOR_DEVICE_REMOVE mode when removing, which makes all devices in hive list have hw reset but no resume except the basic ip blocks, then other ip blocks will not call .hw_fini according to ip_block.status.hw. Since psp_free_shared_bufs just includes some software operations, so move it to psp_sw_fini. Reviewed-by: Guchun Chen Reviewed-by: Feifei Xu Signed-off-by: Longlong Yao Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index eecbd8eeb1f5..8764ff7ed97e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -514,6 +514,8 @@ static int psp_sw_fini(void *handle) kfree(cmd); cmd = NULL; + psp_free_shared_bufs(psp); + if (psp->km_ring.ring_mem) amdgpu_bo_free_kernel(&adev->firmware.rbuf, &psp->km_ring.ring_mem_mc_addr, @@ -2673,8 +2675,6 @@ static int psp_hw_fini(void *handle) psp_ring_destroy(psp, PSP_RING_TYPE__KM); - psp_free_shared_bufs(psp); - return 0; } From 9f55d300541cb5b435984d269087810581580b00 Mon Sep 17 00:00:00 2001 From: hackyzh002 Date: Wed, 19 Apr 2023 20:22:33 +0800 Subject: [PATCH 0332/2093] drm/amdgpu: Fix integer overflow in amdgpu_cs_pass1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 87c2213e85bd81e4a9a4d0880c256568794ae388 ] The type of size is unsigned int, if size is 0x40000000, there will be an integer overflow, size will be zero after size *= sizeof(uint32_t), will cause uninitialized memory to be referenced later. Reviewed-by: Christian König Signed-off-by: hackyzh002 Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index fdb53d4394f3..6d3d01c5f0a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -185,7 +185,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, uint64_t *chunk_array_user; uint64_t *chunk_array; uint32_t uf_offset = 0; - unsigned int size; + size_t size; int ret; int i; From ce3288d8d654b252ba832626e7de481c195ef20a Mon Sep 17 00:00:00 2001 From: Jack Xiao Date: Fri, 21 Apr 2023 14:20:38 +0800 Subject: [PATCH 0333/2093] drm/amdgpu: fix memory leak in mes self test [ Upstream commit 31d7c3a4fc3d312a0646990767647925d5bde540 ] The fences associated with mes queue have to be freed up during amdgpu_ring_fini. Signed-off-by: Jack Xiao Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index d3558c34d406..296b2d5976af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -361,6 +361,8 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) amdgpu_bo_free_kernel(&ring->ring_obj, &ring->gpu_addr, (void **)&ring->ring); + } else { + kfree(ring->fence_drv.fences); } dma_fence_put(ring->vmid_wait); From 3f498ae94c54d02d6430374d9e54932798dda5a1 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 12 May 2023 12:33:00 -0500 Subject: [PATCH 0334/2093] ASoC: Intel: sof_sdw: add quirk for MTL RVP [ Upstream commit 289e1df00e49a229a1c924c059242e759a552f01 ] We should use RT711_JD2_100K for on board rt711. Signed-off-by: Bard Liao --- sound/soc/intel/boards/sof_sdw.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index a37c85d30147..7f9940c722a3 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -374,6 +374,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(RT711_JD1), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Meteor Lake Client Platform"), + }, + .driver_data = (void *)(RT711_JD2_100K), + }, {} }; From 5c23d9bd5f5d03527e847f46faa0b05b0d44bb21 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 12 May 2023 12:33:05 -0500 Subject: [PATCH 0335/2093] ASoC: Intel: sof_sdw: add quirk for LNL RVP [ Upstream commit dfe25fea968dc4884e12d471c8263f0f611b380a ] We should use RT711_JD2_100K for on board rt711 Signed-off-by: Peter Ujfalusi --- sound/soc/intel/boards/sof_sdw.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 7f9940c722a3..0cf9efec46ce 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -382,6 +382,15 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(RT711_JD2_100K), }, + /* LunarLake devices */ + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Lunar Lake Client Platform"), + }, + .driver_data = (void *)(RT711_JD2_100K), + }, {} }; From ea88c6c7819e71ba14fdb99955e58cdb528a16eb Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Thu, 11 May 2023 23:02:09 +0530 Subject: [PATCH 0336/2093] PCI: tegra194: Fix possible array out of bounds access [ Upstream commit 205b3d02d57ce6dce96f6d2b9c230f56a9bf9817 ] Add check to fix the possible array out of bounds violation by making speed equal to GEN1_CORE_CLK_FREQ when its value is more than the size of "pcie_gen_freq" array. This array has size of four but possible speed (CLS) values are from "0 to 0xF". So, "speed - 1" values are "-1 to 0xE". Suggested-by: Bjorn Helgaas Signed-off-by: Sumit Gupta Link: https://lore.kernel.org/lkml/72b9168b-d4d6-4312-32ea-69358df2f2d0@nvidia.com/ Acked-by: Lorenzo Pieralisi Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-tegra194.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 1b6b437823d2..528e73ccfa43 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -224,6 +224,7 @@ #define EP_STATE_ENABLED 1 static const unsigned int pcie_gen_freq[] = { + GEN1_CORE_CLK_FREQ, /* PCI_EXP_LNKSTA_CLS == 0; undefined */ GEN1_CORE_CLK_FREQ, GEN2_CORE_CLK_FREQ, GEN3_CORE_CLK_FREQ, @@ -455,7 +456,11 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) & PCI_EXP_LNKSTA_CLS; - clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]); + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); if (pcie->of_data->has_ltr_req_fix) return IRQ_HANDLED; @@ -1016,7 +1021,11 @@ static int tegra_pcie_dw_start_link(struct dw_pcie *pci) speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) & PCI_EXP_LNKSTA_CLS; - clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]); + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); tegra_pcie_enable_interrupts(pp); From f934cad9131854c8a78192ad07b1cf44bc0415cd Mon Sep 17 00:00:00 2001 From: Venkata Prasad Potturu Date: Tue, 23 May 2023 12:50:01 +0530 Subject: [PATCH 0337/2093] ASoC: SOF: amd: Add pci revision id check [ Upstream commit 1d4a84632b90d88316986b05bcdfe715399a33db ] Add pci revision id check for renoir and rembrandt platforms. Signed-off-by: Venkata Prasad Potturu Link: https://lore.kernel.org/r/20230523072009.2379198-1-venkataprasad.potturu@amd.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/amd/acp.h | 3 +++ sound/soc/sof/amd/pci-rmb.c | 3 +++ sound/soc/sof/amd/pci-rn.c | 3 +++ 3 files changed, 9 insertions(+) diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h index dd3c072d0172..14148c311f50 100644 --- a/sound/soc/sof/amd/acp.h +++ b/sound/soc/sof/amd/acp.h @@ -54,6 +54,9 @@ #define ACP_DSP_TO_HOST_IRQ 0x04 +#define ACP_RN_PCI_ID 0x01 +#define ACP_RMB_PCI_ID 0x6F + #define HOST_BRIDGE_CZN 0x1630 #define HOST_BRIDGE_RMB 0x14B5 #define ACP_SHA_STAT 0x8000 diff --git a/sound/soc/sof/amd/pci-rmb.c b/sound/soc/sof/amd/pci-rmb.c index 4e1de462b431..5698d910b26f 100644 --- a/sound/soc/sof/amd/pci-rmb.c +++ b/sound/soc/sof/amd/pci-rmb.c @@ -90,6 +90,9 @@ static int acp_pci_rmb_probe(struct pci_dev *pci, const struct pci_device_id *pc unsigned int flag, i, addr; int ret; + if (pci->revision != ACP_RMB_PCI_ID) + return -ENODEV; + flag = snd_amd_acp_find_config(pci); if (flag != FLAG_AMD_SOF && flag != FLAG_AMD_SOF_ONLY_DMIC) return -ENODEV; diff --git a/sound/soc/sof/amd/pci-rn.c b/sound/soc/sof/amd/pci-rn.c index fca40b261671..9189f6363278 100644 --- a/sound/soc/sof/amd/pci-rn.c +++ b/sound/soc/sof/amd/pci-rn.c @@ -90,6 +90,9 @@ static int acp_pci_rn_probe(struct pci_dev *pci, const struct pci_device_id *pci unsigned int flag, i, addr; int ret; + if (pci->revision != ACP_RN_PCI_ID) + return -ENODEV; + flag = snd_amd_acp_find_config(pci); if (flag != FLAG_AMD_SOF && flag != FLAG_AMD_SOF_ONLY_DMIC) return -ENODEV; From 340dba127bbed51e8425cd8e097aacfadd175462 Mon Sep 17 00:00:00 2001 From: Raphael Gallais-Pou Date: Mon, 15 May 2023 14:38:18 +0200 Subject: [PATCH 0338/2093] drm/stm: ltdc: fix late dereference check [ Upstream commit 898a9e3f56db9860ab091d4bf41b6caa99aafc3d ] In ltdc_crtc_set_crc_source(), struct drm_crtc was dereferenced in a container_of() before the pointer check. This could cause a kernel panic. Fix this smatch warning: drivers/gpu/drm/stm/ltdc.c:1124 ltdc_crtc_set_crc_source() warn: variable dereferenced before check 'crtc' (see line 1119) Reported-by: kernel test robot Closes: https://lore.kernel.org/lkml/202212241802.zeLFZCXB-lkp@intel.com/ Reported-by: Dan Carpenter Closes: https://lore.kernel.org/lkml/202212241802.zeLFZCXB-lkp@intel.com/ Signed-off-by: Raphael Gallais-Pou Acked-by: Philippe Cornu Signed-off-by: Philippe Cornu Link: https://patchwork.freedesktop.org/patch/msgid/20230515123818.93971-1-raphael.gallais-pou@foss.st.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/stm/ltdc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 03c6becda795..b8be4c1db423 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -1145,7 +1145,7 @@ static void ltdc_crtc_disable_vblank(struct drm_crtc *crtc) static int ltdc_crtc_set_crc_source(struct drm_crtc *crtc, const char *source) { - struct ltdc_device *ldev = crtc_to_ltdc(crtc); + struct ltdc_device *ldev; int ret; DRM_DEBUG_DRIVER("\n"); @@ -1153,6 +1153,8 @@ static int ltdc_crtc_set_crc_source(struct drm_crtc *crtc, const char *source) if (!crtc) return -ENODEV; + ldev = crtc_to_ltdc(crtc); + if (source && strcmp(source, "auto") == 0) { ldev->crc_active = true; ret = regmap_set_bits(ldev->regmap, LTDC_GCR, GCR_CRCEN); From 633ac567bd9ee2a3e6262a2f517f646eecef9b97 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 9 May 2023 09:48:17 +0200 Subject: [PATCH 0339/2093] drm: rcar-du: remove R-Car H3 ES1.* workarounds [ Upstream commit 2da4b728f994a1f9189a8066b0be90b615768764 ] R-Car H3 ES1.* was only available to an internal development group and needed a lot of quirks and workarounds. These become a maintenance burden now, so our development group decided to remove upstream support for this SoC and prevent booting it. Public users only have ES2 onwards. Signed-off-by: Wolfram Sang Reviewed-by: Kieran Bingham Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/gpu/drm/rcar-du/rcar_du_crtc.c | 37 ++------------------ drivers/gpu/drm/rcar-du/rcar_du_drv.c | 48 -------------------------- drivers/gpu/drm/rcar-du/rcar_du_drv.h | 2 -- drivers/gpu/drm/rcar-du/rcar_du_regs.h | 3 +- 4 files changed, 4 insertions(+), 86 deletions(-) diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c index b7dd59fe119e..9edb5edb2bad 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -223,20 +223,6 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc) * DU channels that have a display PLL can't use the internal * system clock, and have no internal clock divider. */ - - /* - * The H3 ES1.x exhibits dot clock duty cycle stability issues. - * We can work around them by configuring the DPLL to twice the - * desired frequency, coupled with a /2 post-divider. Restrict - * the workaround to H3 ES1.x as ES2.0 and all other SoCs have - * no post-divider when a display PLL is present (as shown by - * the workaround breaking HDMI output on M3-W during testing). - */ - if (rcdu->info->quirks & RCAR_DU_QUIRK_H3_ES1_PCLK_STABILITY) { - target *= 2; - div = 1; - } - extclk = clk_get_rate(rcrtc->extclock); rcar_du_dpll_divider(rcrtc, &dpll, extclk, target); @@ -245,30 +231,13 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc) | DPLLCR_N(dpll.n) | DPLLCR_M(dpll.m) | DPLLCR_STBY; - if (rcrtc->index == 1) { + if (rcrtc->index == 1) dpllcr |= DPLLCR_PLCS1 | DPLLCR_INCS_DOTCLKIN1; - } else { - dpllcr |= DPLLCR_PLCS0_PLL + else + dpllcr |= DPLLCR_PLCS0 | DPLLCR_INCS_DOTCLKIN0; - /* - * On ES2.x we have a single mux controlled via bit 21, - * which selects between DCLKIN source (bit 21 = 0) and - * a PLL source (bit 21 = 1), where the PLL is always - * PLL1. - * - * On ES1.x we have an additional mux, controlled - * via bit 20, for choosing between PLL0 (bit 20 = 0) - * and PLL1 (bit 20 = 1). We always want to use PLL1, - * so on ES1.x, in addition to setting bit 21, we need - * to set the bit 20. - */ - - if (rcdu->info->quirks & RCAR_DU_QUIRK_H3_ES1_PLL) - dpllcr |= DPLLCR_PLCS0_H3ES1X_PLL1; - } - rcar_du_group_write(rcrtc->group, DPLLCR, dpllcr); escr = ESCR_DCLKSEL_DCLKIN | div; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index 6381578c4db5..bd7003d6e075 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -387,43 +386,6 @@ static const struct rcar_du_device_info rcar_du_r8a7795_info = { .dpll_mask = BIT(2) | BIT(1), }; -static const struct rcar_du_device_info rcar_du_r8a7795_es1_info = { - .gen = 3, - .features = RCAR_DU_FEATURE_CRTC_IRQ - | RCAR_DU_FEATURE_CRTC_CLOCK - | RCAR_DU_FEATURE_VSP1_SOURCE - | RCAR_DU_FEATURE_INTERLACED - | RCAR_DU_FEATURE_TVM_SYNC, - .quirks = RCAR_DU_QUIRK_H3_ES1_PCLK_STABILITY - | RCAR_DU_QUIRK_H3_ES1_PLL, - .channels_mask = BIT(3) | BIT(2) | BIT(1) | BIT(0), - .routes = { - /* - * R8A7795 has one RGB output, two HDMI outputs and one - * LVDS output. - */ - [RCAR_DU_OUTPUT_DPAD0] = { - .possible_crtcs = BIT(3), - .port = 0, - }, - [RCAR_DU_OUTPUT_HDMI0] = { - .possible_crtcs = BIT(1), - .port = 1, - }, - [RCAR_DU_OUTPUT_HDMI1] = { - .possible_crtcs = BIT(2), - .port = 2, - }, - [RCAR_DU_OUTPUT_LVDS0] = { - .possible_crtcs = BIT(0), - .port = 3, - }, - }, - .num_lvds = 1, - .num_rpf = 5, - .dpll_mask = BIT(2) | BIT(1), -}; - static const struct rcar_du_device_info rcar_du_r8a7796_info = { .gen = 3, .features = RCAR_DU_FEATURE_CRTC_IRQ @@ -592,11 +554,6 @@ static const struct of_device_id rcar_du_of_table[] = { MODULE_DEVICE_TABLE(of, rcar_du_of_table); -static const struct soc_device_attribute rcar_du_soc_table[] = { - { .soc_id = "r8a7795", .revision = "ES1.*", .data = &rcar_du_r8a7795_es1_info }, - { /* sentinel */ } -}; - const char *rcar_du_output_name(enum rcar_du_output output) { static const char * const names[] = { @@ -688,7 +645,6 @@ static void rcar_du_shutdown(struct platform_device *pdev) static int rcar_du_probe(struct platform_device *pdev) { - const struct soc_device_attribute *soc_attr; struct rcar_du_device *rcdu; unsigned int mask; int ret; @@ -706,10 +662,6 @@ static int rcar_du_probe(struct platform_device *pdev) rcdu->info = of_device_get_match_data(rcdu->dev); - soc_attr = soc_device_match(rcar_du_soc_table); - if (soc_attr) - rcdu->info = soc_attr->data; - platform_set_drvdata(pdev, rcdu); /* I/O resources */ diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h index acc3673fefe1..5cfa2bb7ad93 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h @@ -34,8 +34,6 @@ struct rcar_du_device; #define RCAR_DU_FEATURE_NO_BLENDING BIT(5) /* PnMR.SPIM does not have ALP nor EOR bits */ #define RCAR_DU_QUIRK_ALIGN_128B BIT(0) /* Align pitches to 128 bytes */ -#define RCAR_DU_QUIRK_H3_ES1_PCLK_STABILITY BIT(1) /* H3 ES1 has pclk stability issue */ -#define RCAR_DU_QUIRK_H3_ES1_PLL BIT(2) /* H3 ES1 PLL setup differs from non-ES1 */ enum rcar_du_output { RCAR_DU_OUTPUT_DPAD0, diff --git a/drivers/gpu/drm/rcar-du/rcar_du_regs.h b/drivers/gpu/drm/rcar-du/rcar_du_regs.h index 789ae9285108..288eff12b2b1 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_regs.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_regs.h @@ -283,8 +283,7 @@ #define DPLLCR 0x20044 #define DPLLCR_CODE (0x95 << 24) #define DPLLCR_PLCS1 (1 << 23) -#define DPLLCR_PLCS0_PLL (1 << 21) -#define DPLLCR_PLCS0_H3ES1X_PLL1 (1 << 20) +#define DPLLCR_PLCS0 (1 << 21) #define DPLLCR_CLKE (1 << 18) #define DPLLCR_FDPLL(n) ((n) << 12) #define DPLLCR_N(n) ((n) << 5) From a7d4d28d2c0bd7e2bc5fe9075f70ab83b777b31d Mon Sep 17 00:00:00 2001 From: Venkata Prasad Potturu Date: Tue, 30 May 2023 16:37:58 +0530 Subject: [PATCH 0340/2093] ASoC: amd: vangogh: Add check for acp config flags in vangogh platform [ Upstream commit e89f45edb747ed88e97a5771dd6d3dd1eb517873 ] We have SOF and generic ACP support enabled for Vangogh platform on some machines. Since we have same PCI id used for probing, add check for machine configuration flag to avoid conflict with newer pci drivers. Such machine flag has been initialized via dmi match on few Vangogh based machines. If no flag is specified probe and register older platform device. Signed-off-by: Venkata Prasad Potturu Link: https://lore.kernel.org/r/20230530110802.674939-1-venkataprasad.potturu@amd.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/amd/vangogh/acp5x.h | 2 ++ sound/soc/amd/vangogh/pci-acp5x.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/soc/amd/vangogh/acp5x.h b/sound/soc/amd/vangogh/acp5x.h index bd9f1c5684d1..ac1936a8c43f 100644 --- a/sound/soc/amd/vangogh/acp5x.h +++ b/sound/soc/amd/vangogh/acp5x.h @@ -147,6 +147,8 @@ static inline void acp_writel(u32 val, void __iomem *base_addr) writel(val, base_addr - ACP5x_PHY_BASE_ADDRESS); } +int snd_amd_acp_find_config(struct pci_dev *pci); + static inline u64 acp_get_byte_count(struct i2s_stream_instance *rtd, int direction) { diff --git a/sound/soc/amd/vangogh/pci-acp5x.c b/sound/soc/amd/vangogh/pci-acp5x.c index e0df17c88e8e..c4634a8a17cd 100644 --- a/sound/soc/amd/vangogh/pci-acp5x.c +++ b/sound/soc/amd/vangogh/pci-acp5x.c @@ -125,10 +125,15 @@ static int snd_acp5x_probe(struct pci_dev *pci, { struct acp5x_dev_data *adata; struct platform_device_info pdevinfo[ACP5x_DEVS]; - unsigned int irqflags; + unsigned int irqflags, flag; int ret, i; u32 addr, val; + /* Return if acp config flag is defined */ + flag = snd_amd_acp_find_config(pci); + if (flag) + return -ENODEV; + irqflags = IRQF_SHARED; if (pci->revision != 0x50) return -ENODEV; From 31149bb94f776de99909bd507a3bc41507f3dca2 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 30 May 2023 14:03:44 +0200 Subject: [PATCH 0341/2093] ARM: dts: imx6dl: prtrvt, prtvt7, prti6q, prtwd2: fix USB related warnings [ Upstream commit 1d14bd943fa2bbdfda1efbcc080b298fed5f1803 ] Fix USB-related warnings in prtrvt, prtvt7, prti6q and prtwd2 device trees by disabling unused usbphynop1 and usbphynop2 USB PHYs and providing proper configuration for the over-current detection. This fixes the following warnings with the current kernel: usb_phy_generic usbphynop1: dummy supplies not allowed for exclusive requests usb_phy_generic usbphynop2: dummy supplies not allowed for exclusive requests imx_usb 2184200.usb: No over current polarity defined By the way, fix over-current detection on usbotg port for prtvt7, prti6q and prtwd2 boards. Only prtrvt do not have OC on USB OTG port. Signed-off-by: Oleksij Rempel Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6dl-prtrvt.dts | 4 ++++ arch/arm/boot/dts/imx6qdl-prti6q.dtsi | 11 ++++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6dl-prtrvt.dts b/arch/arm/boot/dts/imx6dl-prtrvt.dts index 56bb1ca56a2d..36b031236e47 100644 --- a/arch/arm/boot/dts/imx6dl-prtrvt.dts +++ b/arch/arm/boot/dts/imx6dl-prtrvt.dts @@ -124,6 +124,10 @@ &usbh1 { status = "disabled"; }; +&usbotg { + disable-over-current; +}; + &vpu { status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx6qdl-prti6q.dtsi b/arch/arm/boot/dts/imx6qdl-prti6q.dtsi index f0db0d4471f4..36f84f4da6b0 100644 --- a/arch/arm/boot/dts/imx6qdl-prti6q.dtsi +++ b/arch/arm/boot/dts/imx6qdl-prti6q.dtsi @@ -69,6 +69,7 @@ &usbh1 { vbus-supply = <®_usb_h1_vbus>; phy_type = "utmi"; dr_mode = "host"; + disable-over-current; status = "okay"; }; @@ -78,10 +79,18 @@ &usbotg { pinctrl-0 = <&pinctrl_usbotg>; phy_type = "utmi"; dr_mode = "host"; - disable-over-current; + over-current-active-low; status = "okay"; }; +&usbphynop1 { + status = "disabled"; +}; + +&usbphynop2 { + status = "disabled"; +}; + &usdhc1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usdhc1>; From c01ec45a7c4c7e09931e96efcf5745a16353cd39 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 2 Jun 2023 15:22:04 -0500 Subject: [PATCH 0342/2093] ASoC: Intel: sof_sdw_rt_sdca_jack_common: test SOF_JACK_JDSRC in _exit [ Upstream commit 526a1876fc48e2d0c0ea8ad63b58bdb2cc13047f ] if (!SOF_RT711_JDSRC(sof_sdw_quirk)) is tested in rt711_sdca_add_codec_ device_props(), and we don't add software node to the device if jack source is not set. We need to do the same test in sof_sdw_rt711_sdca_exit(), and avoid removing software node if jack source is not set. Signed-off-by: Bard Liao Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230602202225.249209-8-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/boards/sof_sdw_rt711_sdca.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw_rt711_sdca.c b/sound/soc/intel/boards/sof_sdw_rt711_sdca.c index 7f16304d025b..cf8b9793fe0e 100644 --- a/sound/soc/intel/boards/sof_sdw_rt711_sdca.c +++ b/sound/soc/intel/boards/sof_sdw_rt711_sdca.c @@ -143,6 +143,9 @@ int sof_sdw_rt711_sdca_exit(struct snd_soc_card *card, struct snd_soc_dai_link * if (!ctx->headset_codec_dev) return 0; + if (!SOF_RT711_JDSRC(sof_sdw_quirk)) + return 0; + device_remove_software_node(ctx->headset_codec_dev); put_device(ctx->headset_codec_dev); From b3e662ece02e7c915bc2e5027e0cb935a27c6cdc Mon Sep 17 00:00:00 2001 From: Uday M Bhat Date: Fri, 2 Jun 2023 15:22:24 -0500 Subject: [PATCH 0343/2093] ASoC: Intel: sof_sdw: Add support for Rex soundwire [ Upstream commit 164e5dc17525181c05563f0a06796f1a363801d5 ] Add rex entry in the soundwire quirk table Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Signed-off-by: Yong Zhi Signed-off-by: Uday M Bhat Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230602202225.249209-28-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/boards/sof_sdw.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 0cf9efec46ce..064b6feb7616 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -382,6 +382,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(RT711_JD2_100K), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Google"), + DMI_MATCH(DMI_PRODUCT_NAME, "Rex"), + }, + .driver_data = (void *)(SOF_SDW_PCH_DMIC), + }, /* LunarLake devices */ { .callback = sof_sdw_quirk_cb, From ff1b4b1e02c33d7d6ca7e5323823d91a75c163b7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 2 Jun 2023 10:50:36 +0200 Subject: [PATCH 0344/2093] iopoll: Call cpu_relax() in busy loops [ Upstream commit b407460ee99033503993ac7437d593451fcdfe44 ] It is considered good practice to call cpu_relax() in busy loops, see Documentation/process/volatile-considered-harmful.rst. This can not only lower CPU power consumption or yield to a hyperthreaded twin processor, but also allows an architecture to mitigate hardware issues (e.g. ARM Erratum 754327 for Cortex-A9 prior to r2p0) in the architecture-specific cpu_relax() implementation. In addition, cpu_relax() is also a compiler barrier. It is not immediately obvious that the @op argument "function" will result in an actual function call (e.g. in case of inlining). Where a function call is a C sequence point, this is lost on inlining. Therefore, with agressive enough optimization it might be possible for the compiler to hoist the: (val) = op(args); "load" out of the loop because it doesn't see the value changing. The addition of cpu_relax() would inhibit this. As the iopoll helpers lack calls to cpu_relax(), people are sometimes reluctant to use them, and may fall back to open-coded polling loops (including cpu_relax() calls) instead. Fix this by adding calls to cpu_relax() to the iopoll helpers: - For the non-atomic case, it is sufficient to call cpu_relax() in case of a zero sleep-between-reads value, as a call to usleep_range() is a safe barrier otherwise. However, it doesn't hurt to add the call regardless, for simplicity, and for similarity with the atomic case below. - For the atomic case, cpu_relax() must be called regardless of the sleep-between-reads value, as there is no guarantee all architecture-specific implementations of udelay() handle this. Signed-off-by: Geert Uytterhoeven Acked-by: Peter Zijlstra (Intel) Acked-by: Arnd Bergmann Reviewed-by: Tony Lindgren Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/45c87bec3397fdd704376807f0eec5cc71be440f.1685692810.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- include/linux/iopoll.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 2c8860e406bd..0417360a6db9 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -53,6 +53,7 @@ } \ if (__sleep_us) \ usleep_range((__sleep_us >> 2) + 1, __sleep_us); \ + cpu_relax(); \ } \ (cond) ? 0 : -ETIMEDOUT; \ }) @@ -95,6 +96,7 @@ } \ if (__delay_us) \ udelay(__delay_us); \ + cpu_relax(); \ } \ (cond) ? 0 : -ETIMEDOUT; \ }) From 3dd5c90c48bf1553e4962e2d8101a96ae320cd9c Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 6 Jun 2023 17:25:28 -0500 Subject: [PATCH 0345/2093] ASoC: SOF: Intel: fix SoundWire/HDaudio mutual exclusion [ Upstream commit f751b99255cacd9ffe8c4bbf99767ad670cee1f7 ] The functionality described in Commit 61bef9e68dca ("ASoC: SOF: Intel: hda: enforce exclusion between HDaudio and SoundWire") does not seem to be properly implemented with two issues that need to be corrected. a) The test used is incorrect when DisplayAudio codecs are not supported. b) Conversely when only Display Audio codecs can be found, we do want to start the SoundWire links, if any. That will help add the relevant topologies and machine descriptors, and identify cases where the SoundWire information in ACPI needs to be modified with a quirk. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20230606222529.57156-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/intel/hda.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 1188ec51816b..63764afdcf61 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1309,12 +1309,22 @@ static void hda_generic_machine_select(struct snd_sof_dev *sdev, hda_mach->mach_params.dmic_num = dmic_num; pdata->tplg_filename = tplg_filename; - if (codec_num == 2) { + if (codec_num == 2 || + (codec_num == 1 && !HDA_IDISP_CODEC(bus->codec_mask))) { /* * Prevent SoundWire links from starting when an external * HDaudio codec is used */ hda_mach->mach_params.link_mask = 0; + } else { + /* + * Allow SoundWire links to start when no external HDaudio codec + * was detected. This will not create a SoundWire card but + * will help detect if any SoundWire codec reports as ATTACHED. + */ + struct sof_intel_hda_dev *hdev = sdev->pdata->hw_pdata; + + hda_mach->mach_params.link_mask = hdev->info.link_mask; } *mach = hda_mach; From b7a34e30d42fcd756f9ffad41def454e4a0474fd Mon Sep 17 00:00:00 2001 From: gaoxu Date: Tue, 6 Jun 2023 12:47:37 +0000 Subject: [PATCH 0346/2093] dma-remap: use kvmalloc_array/kvfree for larger dma memory remap [ Upstream commit 51ff97d54f02b4444dfc42e380ac4c058e12d5dd ] If dma_direct_alloc() alloc memory in size of 64MB, the inner function dma_common_contiguous_remap() will allocate 128KB memory by invoking the function kmalloc_array(). and the kmalloc_array seems to fail to try to allocate 128KB mem. Call trace: [14977.928623] qcrosvm: page allocation failure: order:5, mode:0x40cc0 [14977.928638] dump_backtrace.cfi_jt+0x0/0x8 [14977.928647] dump_stack_lvl+0x80/0xb8 [14977.928652] warn_alloc+0x164/0x200 [14977.928657] __alloc_pages_slowpath+0x9f0/0xb4c [14977.928660] __alloc_pages+0x21c/0x39c [14977.928662] kmalloc_order+0x48/0x108 [14977.928666] kmalloc_order_trace+0x34/0x154 [14977.928668] __kmalloc+0x548/0x7e4 [14977.928673] dma_direct_alloc+0x11c/0x4f8 [14977.928678] dma_alloc_attrs+0xf4/0x138 [14977.928680] gh_vm_ioctl_set_fw_name+0x3c4/0x610 [gunyah] [14977.928698] gh_vm_ioctl+0x90/0x14c [gunyah] [14977.928705] __arm64_sys_ioctl+0x184/0x210 work around by doing kvmalloc_array instead. Signed-off-by: Gao Xu Reviewed-by: Suren Baghdasaryan Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- kernel/dma/remap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index b4526668072e..27596f3b4aef 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -43,13 +43,13 @@ void *dma_common_contiguous_remap(struct page *page, size_t size, void *vaddr; int i; - pages = kmalloc_array(count, sizeof(struct page *), GFP_KERNEL); + pages = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL); if (!pages) return NULL; for (i = 0; i < count; i++) pages[i] = nth_page(page, i); vaddr = vmap(pages, count, VM_DMA_COHERENT, prot); - kfree(pages); + kvfree(pages); return vaddr; } From d7933b92c4caec6a885d4b90df22921898a0b7c1 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Tue, 18 Apr 2023 14:48:22 +0300 Subject: [PATCH 0347/2093] accel/habanalabs: add pci health check during heartbeat [ Upstream commit d8b9cea584661b30305cf341bf9f675dc0a25471 ] Currently upon a heartbeat failure, we don't know if the failure is due to firmware hang or due to a bad PCI link. Hence, we are reading a PCI config space register with a known value (vendor ID) so we will know which of the two possibilities caused the heartbeat failure. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Sasha Levin --- drivers/misc/habanalabs/common/device.c | 15 ++++++++++++++- drivers/misc/habanalabs/common/habanalabs.h | 2 ++ drivers/misc/habanalabs/common/habanalabs_drv.c | 2 -- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index e0dca445abf1..9ee1b6abd8a0 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -870,6 +870,18 @@ static void device_early_fini(struct hl_device *hdev) hdev->asic_funcs->early_fini(hdev); } +static bool is_pci_link_healthy(struct hl_device *hdev) +{ + u16 vendor_id; + + if (!hdev->pdev) + return false; + + pci_read_config_word(hdev->pdev, PCI_VENDOR_ID, &vendor_id); + + return (vendor_id == PCI_VENDOR_ID_HABANALABS); +} + static void hl_device_heartbeat(struct work_struct *work) { struct hl_device *hdev = container_of(work, struct hl_device, @@ -882,7 +894,8 @@ static void hl_device_heartbeat(struct work_struct *work) goto reschedule; if (hl_device_operational(hdev, NULL)) - dev_err(hdev->dev, "Device heartbeat failed!\n"); + dev_err(hdev->dev, "Device heartbeat failed! PCI link is %s\n", + is_pci_link_healthy(hdev) ? "healthy" : "broken"); hl_device_reset(hdev, HL_DRV_RESET_HARD | HL_DRV_RESET_HEARTBEAT); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 58c95b13be69..257b94cec624 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -34,6 +34,8 @@ struct hl_device; struct hl_fpriv; +#define PCI_VENDOR_ID_HABANALABS 0x1da3 + /* Use upper bits of mmap offset to store habana driver specific information. * bits[63:59] - Encode mmap type * bits[45:0] - mmap offset value diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c index 112632afe7d5..ae3cab3f4aa5 100644 --- a/drivers/misc/habanalabs/common/habanalabs_drv.c +++ b/drivers/misc/habanalabs/common/habanalabs_drv.c @@ -54,8 +54,6 @@ module_param(boot_error_status_mask, ulong, 0444); MODULE_PARM_DESC(boot_error_status_mask, "Mask of the error status during device CPU boot (If bitX is cleared then error X is masked. Default all 1's)"); -#define PCI_VENDOR_ID_HABANALABS 0x1da3 - #define PCI_IDS_GOYA 0x0001 #define PCI_IDS_GAUDI 0x1000 #define PCI_IDS_GAUDI_SEC 0x1010 From 83c22663acb6f015aad8ad99f8734767699c5c69 Mon Sep 17 00:00:00 2001 From: stuarthayhurst Date: Tue, 30 May 2023 15:44:28 +0100 Subject: [PATCH 0348/2093] HID: logitech-hidpp: Add USB and Bluetooth IDs for the Logitech G915 TKL Keyboard [ Upstream commit 48aea8b445c422a372cf15915101035a47105421 ] Adds the USB and Bluetooth IDs for the Logitech G915 TKL keyboard, for device detection For this device, this provides battery reporting on top of hid-generic Reviewed-by: Bastien Nocera Signed-off-by: Stuart Hayhurst Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-logitech-hidpp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0b4204b9a253..97eefb77f601 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4403,6 +4403,8 @@ static const struct hid_device_id hidpp_devices[] = { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC086) }, { /* Logitech G903 Hero Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC091) }, + { /* Logitech G915 TKL Keyboard over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC343) }, { /* Logitech G920 Wheel over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL), .driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS}, @@ -4418,6 +4420,8 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, + { /* Logitech G915 TKL keyboard over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb35f) }, { /* M-RCQ142 V470 Cordless Laser Mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb008) }, { /* MX Master mouse over Bluetooth */ From 96522cf9c71e461fd8df47ee746b2a28f785f085 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 30 May 2023 10:11:35 -0400 Subject: [PATCH 0349/2093] iommu/amd: Introduce Disable IRTE Caching Support [ Upstream commit 66419036f68a838c00cbccacd6cb2e99da6e5710 ] An Interrupt Remapping Table (IRT) stores interrupt remapping configuration for each device. In a normal operation, the AMD IOMMU caches the table to optimize subsequent data accesses. This requires the IOMMU driver to invalidate IRT whenever it updates the table. The invalidation process includes issuing an INVALIDATE_INTERRUPT_TABLE command following by a COMPLETION_WAIT command. However, there are cases in which the IRT is updated at a high rate. For example, for IOMMU AVIC, the IRTE[IsRun] bit is updated on every vcpu scheduling (i.e. amd_iommu_update_ga()). On system with large amount of vcpus and VFIO PCI pass-through devices, the invalidation process could potentially become a performance bottleneck. Introducing a new kernel boot option: amd_iommu=irtcachedis which disables IRTE caching by setting the IRTCachedis bit in each IOMMU Control register, and bypass the IRT invalidation process. Reviewed-by: Jerry Snitselaar Co-developed-by: Alejandro Jimenez Signed-off-by: Alejandro Jimenez Signed-off-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/20230530141137.14376-4-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- .../admin-guide/kernel-parameters.txt | 1 + drivers/iommu/amd/amd_iommu_types.h | 4 +++ drivers/iommu/amd/init.c | 36 +++++++++++++++++++ 3 files changed, 41 insertions(+) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 286be425f3bf..882b6198dd0d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -323,6 +323,7 @@ option with care. pgtbl_v1 - Use v1 page table for DMA-API (Default). pgtbl_v2 - Use v2 page table for DMA-API. + irtcachedis - Disable Interrupt Remapping Table (IRT) caching. amd_iommu_dump= [HW,X86-64] Enable AMD IOMMU driver option to dump the ACPI table diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5ecc17240eff..f5e9377b5521 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -172,6 +172,7 @@ #define CONTROL_GAINT_EN 29 #define CONTROL_XT_EN 50 #define CONTROL_INTCAPXT_EN 51 +#define CONTROL_IRTCACHEDIS 59 #define CONTROL_SNPAVIC_EN 61 #define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) @@ -708,6 +709,9 @@ struct amd_iommu { /* if one, we need to send a completion wait command */ bool need_sync; + /* true if disable irte caching */ + bool irtcachedis_enabled; + /* Handle for IOMMU core code */ struct iommu_device iommu; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index b0af8b5967e0..f6e64c985802 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -160,6 +160,7 @@ static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; static bool amd_iommu_detected; static bool amd_iommu_disabled __initdata; static bool amd_iommu_force_enable __initdata; +static bool amd_iommu_irtcachedis; static int amd_iommu_target_ivhd_type; /* Global EFR and EFR2 registers */ @@ -477,6 +478,9 @@ static void iommu_disable(struct amd_iommu *iommu) /* Disable IOMMU hardware itself */ iommu_feature_disable(iommu, CONTROL_IOMMU_EN); + + /* Clear IRTE cache disabling bit */ + iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS); } /* @@ -2700,6 +2704,33 @@ static void iommu_enable_ga(struct amd_iommu *iommu) #endif } +static void iommu_disable_irtcachedis(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_IRTCACHEDIS); +} + +static void iommu_enable_irtcachedis(struct amd_iommu *iommu) +{ + u64 ctrl; + + if (!amd_iommu_irtcachedis) + return; + + /* + * Note: + * The support for IRTCacheDis feature is dertermined by + * checking if the bit is writable. + */ + iommu_feature_enable(iommu, CONTROL_IRTCACHEDIS); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= (1ULL << CONTROL_IRTCACHEDIS); + if (ctrl) + iommu->irtcachedis_enabled = true; + pr_info("iommu%d (%#06x) : IRT cache is %s\n", + iommu->index, iommu->devid, + iommu->irtcachedis_enabled ? "disabled" : "enabled"); +} + static void early_enable_iommu(struct amd_iommu *iommu) { iommu_disable(iommu); @@ -2710,6 +2741,7 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_set_exclusion_range(iommu); iommu_enable_ga(iommu); iommu_enable_xt(iommu); + iommu_enable_irtcachedis(iommu); iommu_enable(iommu); iommu_flush_all_caches(iommu); } @@ -2760,10 +2792,12 @@ static void early_enable_iommus(void) for_each_iommu(iommu) { iommu_disable_command_buffer(iommu); iommu_disable_event_buffer(iommu); + iommu_disable_irtcachedis(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); iommu_enable_ga(iommu); iommu_enable_xt(iommu); + iommu_enable_irtcachedis(iommu); iommu_set_device_table(iommu); iommu_flush_all_caches(iommu); } @@ -3411,6 +3445,8 @@ static int __init parse_amd_iommu_options(char *str) amd_iommu_pgtable = AMD_IOMMU_V1; } else if (strncmp(str, "pgtbl_v2", 8) == 0) { amd_iommu_pgtable = AMD_IOMMU_V2; + } else if (strncmp(str, "irtcachedis", 11) == 0) { + amd_iommu_irtcachedis = true; } else { pr_notice("Unknown option - '%s'\n", str); } From 78b25110eb8c6990f7f5096bc0136c12a2b4cc99 Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Fri, 5 May 2023 20:14:15 +0800 Subject: [PATCH 0350/2093] drm/amdgpu: install stub fence into potential unused fence pointers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 187916e6ed9d0c3b3abc27429f7a5f8c936bd1f0 ] When using cpu to update page tables, vm update fences are unused. Install stub fence into these fence pointers instead of NULL to avoid NULL dereference when calling dma_fence_wait() on them. Suggested-by: Christian König Signed-off-by: Lang Yu Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ec938a1a5062..4c661e024e13 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1352,6 +1352,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, amdgpu_vm_bo_base_init(&bo_va->base, vm, bo); bo_va->ref_count = 1; + bo_va->last_pt_update = dma_fence_get_stub(); INIT_LIST_HEAD(&bo_va->valids); INIT_LIST_HEAD(&bo_va->invalids); @@ -2073,7 +2074,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->update_funcs = &amdgpu_vm_cpu_funcs; else vm->update_funcs = &amdgpu_vm_sdma_funcs; - vm->last_update = NULL; + + vm->last_update = dma_fence_get_stub(); vm->last_unlocked = dma_fence_get_stub(); vm->last_tlb_flush = dma_fence_get_stub(); @@ -2198,7 +2200,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) goto unreserve_bo; dma_fence_put(vm->last_update); - vm->last_update = NULL; + vm->last_update = dma_fence_get_stub(); vm->is_compute_context = true; /* Free the shadow bo for compute VM */ From fbd9332d32ec2e4963620dbfa23d802dd98973be Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Thu, 11 May 2023 15:25:01 -0400 Subject: [PATCH 0351/2093] drm/amd/display: Apply 60us prefetch for DCFCLK <= 300Mhz [ Upstream commit 7e60ab4eb3e4ba2adac46d737fdbbc5732bebd58 ] [Description] - Previously we wanted to apply extra 60us of prefetch for min DCFCLK (200Mhz), but DCFCLK can be calculated to be 201Mhz which underflows also without the extra prefetch - Instead, apply the the extra 60us prefetch for any DCFCLK freq <= 300Mhz Reviewed-by: Nevenko Stupar Reviewed-by: Jun Lei Acked-by: Tom Chung Signed-off-by: Alvin Lee Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c | 4 ++-- .../gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 2bb768413c92..19f55657272e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -808,7 +808,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightC[k], TWait, (v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ || - v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= MIN_DCFCLK_FREQ_MHZ) ? + v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->DSTXAfterScaler[k], @@ -3289,7 +3289,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->swath_width_chroma_ub_this_state[k], v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= MIN_DCFCLK_FREQ_MHZ) ? + (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h index e92eee2c664d..a475775bc389 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h @@ -52,7 +52,7 @@ #define BPP_BLENDED_PIPE 0xffffffff #define MEM_STROBE_FREQ_MHZ 1600 -#define MIN_DCFCLK_FREQ_MHZ 200 +#define DCFCLK_FREQ_EXTRA_PREFETCH_REQ_MHZ 300 #define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0 struct display_mode_lib; From 5fe7815e784bf21061885f8112a7108aef5c45bd Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Mon, 5 Jun 2023 13:14:07 +0300 Subject: [PATCH 0352/2093] RDMA/mlx5: Return the firmware result upon destroying QP/RQ [ Upstream commit 22664c06e997087fe37f9ba208008c948571214a ] Previously when destroying a QP/RQ, the result of the firmware destruction function was ignored and upper layers weren't informed about the failure. Which in turn could lead to various problems since when upper layer isn't aware of the failure it continues its operation thinking that the related QP/RQ was successfully destroyed while it actually wasn't, which could lead to the below kernel WARN. Currently, we return the correct firmware destruction status to upper layers which in case of the RQ would be mlx5_ib_destroy_wq() which was already capable of handling RQ destruction failure or in case of a QP to destroy_qp_common(), which now would actually warn upon qp destruction failure. WARNING: CPU: 3 PID: 995 at drivers/infiniband/core/rdma_core.c:940 uverbs_destroy_ufile_hw+0xcb/0xe0 [ib_uverbs] Modules linked in: xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core overlay mlx5_core fuse CPU: 3 PID: 995 Comm: python3 Not tainted 5.16.0-rc5+ #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:uverbs_destroy_ufile_hw+0xcb/0xe0 [ib_uverbs] Code: 41 5c 41 5d 41 5e e9 44 34 f0 e0 48 89 df e8 4c 77 ff ff 49 8b 86 10 01 00 00 48 85 c0 74 a1 4c 89 e7 ff d0 eb 9a 0f 0b eb c1 <0f> 0b be 04 00 00 00 48 89 df e8 b6 f6 ff ff e9 75 ff ff ff 90 0f RSP: 0018:ffff8881533e3e78 EFLAGS: 00010287 RAX: ffff88811b2cf3e0 RBX: ffff888106209700 RCX: 0000000000000000 RDX: ffff888106209780 RSI: ffff8881533e3d30 RDI: ffff888109b101a0 RBP: 0000000000000001 R08: ffff888127cb381c R09: 0de9890000000009 R10: ffff888127cb3800 R11: 0000000000000000 R12: ffff888106209780 R13: ffff888106209750 R14: ffff888100f20660 R15: 0000000000000000 FS: 00007f8be353b740(0000) GS:ffff88852c980000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f8bd5b117c0 CR3: 000000012cd8a004 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ib_uverbs_close+0x1a/0x90 [ib_uverbs] __fput+0x82/0x230 task_work_run+0x59/0x90 exit_to_user_mode_prepare+0x138/0x140 syscall_exit_to_user_mode+0x1d/0x50 ? __x64_sys_close+0xe/0x40 do_syscall_64+0x4a/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f8be3ae0abb Code: 03 00 00 00 0f 05 48 3d 00 f0 ff ff 77 41 c3 48 83 ec 18 89 7c 24 0c e8 83 43 f9 ff 8b 7c 24 0c 41 89 c0 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 44 89 c7 89 44 24 0c e8 c1 43 f9 ff 8b 44 RSP: 002b:00007ffdb51909c0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000557bb7f7c020 RCX: 00007f8be3ae0abb RDX: 0000557bb7c74010 RSI: 0000557bb7f14ca0 RDI: 0000000000000005 RBP: 0000557bb7fbd598 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000293 R12: 0000557bb7fbd5b8 R13: 0000557bb7fbd5a8 R14: 0000000000001000 R15: 0000557bb7f7c020 Signed-off-by: Patrisious Haddad Link: https://lore.kernel.org/r/c6df677f931d18090bafbe7f7dbb9524047b7d9b.1685953497.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/qpc.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c index 542e4c63a8de..d4e7864c56f1 100644 --- a/drivers/infiniband/hw/mlx5/qpc.c +++ b/drivers/infiniband/hw/mlx5/qpc.c @@ -297,8 +297,7 @@ int mlx5_core_destroy_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp) MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); MLX5_SET(destroy_qp_in, in, qpn, qp->qpn); MLX5_SET(destroy_qp_in, in, uid, qp->uid); - mlx5_cmd_exec_in(dev->mdev, destroy_qp, in); - return 0; + return mlx5_cmd_exec_in(dev->mdev, destroy_qp, in); } int mlx5_core_set_delay_drop(struct mlx5_ib_dev *dev, @@ -548,14 +547,14 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn) return mlx5_cmd_exec_in(dev->mdev, dealloc_xrcd, in); } -static void destroy_rq_tracked(struct mlx5_ib_dev *dev, u32 rqn, u16 uid) +static int destroy_rq_tracked(struct mlx5_ib_dev *dev, u32 rqn, u16 uid) { u32 in[MLX5_ST_SZ_DW(destroy_rq_in)] = {}; MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ); MLX5_SET(destroy_rq_in, in, rqn, rqn); MLX5_SET(destroy_rq_in, in, uid, uid); - mlx5_cmd_exec_in(dev->mdev, destroy_rq, in); + return mlx5_cmd_exec_in(dev->mdev, destroy_rq, in); } int mlx5_core_create_rq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen, @@ -586,8 +585,7 @@ int mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev, struct mlx5_core_qp *rq) { destroy_resource_common(dev, rq); - destroy_rq_tracked(dev, rq->qpn, rq->uid); - return 0; + return destroy_rq_tracked(dev, rq->qpn, rq->uid); } static void destroy_sq_tracked(struct mlx5_ib_dev *dev, u32 sqn, u16 uid) From 5447155001e6aa30d55b06a5b4ff799fd3a1f51d Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Fri, 28 Apr 2023 11:23:50 -0400 Subject: [PATCH 0353/2093] drm/amd/display: Skip DPP DTO update if root clock is gated [ Upstream commit 30f90f3c1c2c63c2fa44f61233737d27b72637c2 ] [Why] Hardware implements root clock gating by utilizing the DPP DTO registers with a special case of DTO enabled, phase = 0, modulo = 1. This conflicts with our policy to always update the DPPDTO for cases where it's expected to be disabled. The pipes unexpectedly enter a higher power state than expected because of this programming flow. [How] Guard the upper layers of HWSS against this hardware quirk with programming the register with an internal state flag in DCCG. While technically acting as global state for the DCCG, HWSS shouldn't be expected to understand the hardware quirk for having DTO disabled causing more power than DTO enabled with this specific setting. This also prevents sequencing errors from occuring in the future if we have to program DPP DTO in multiple locations. Acked-by: Stylon Wang Signed-off-by: Nicholas Kazlauskas Reviewed-by: Jun Lei Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c | 8 ++++++++ drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c | 5 +++++ drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h | 1 + 3 files changed, 14 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c index 7d2b982506fd..cef32a1f91cd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c @@ -47,6 +47,14 @@ void dccg31_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + if (dccg->dpp_clock_gated[dpp_inst]) { + /* + * Do not update the DPPCLK DTO if the clock is stopped. + * It is treated the same as if the pipe itself were in PG. + */ + return; + } + if (dccg->ref_dppclk && req_dppclk) { int ref_dppclk = dccg->ref_dppclk; int modulo, phase; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 85ea3334355c..97c6a79dfba6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -296,6 +296,9 @@ static void dccg314_dpp_root_clock_control( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + if (dccg->dpp_clock_gated[dpp_inst] == clock_on) + return; + if (clock_on) { /* turn off the DTO and leave phase/modulo at max */ REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 0); @@ -309,6 +312,8 @@ static void dccg314_dpp_root_clock_control( DPPCLK0_DTO_PHASE, 0, DPPCLK0_DTO_MODULO, 1); } + + dccg->dpp_clock_gated[dpp_inst] = !clock_on; } static const struct dccg_funcs dccg314_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h index ad6acd1b34e1..9651cccb084a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h @@ -68,6 +68,7 @@ struct dccg { const struct dccg_funcs *funcs; int pipe_dppclk_khz[MAX_PIPES]; int ref_dppclk; + bool dpp_clock_gated[MAX_PIPES]; //int dtbclk_khz[MAX_PIPES];/* TODO needs to be removed */ //int audio_dtbclk_khz;/* TODO needs to be removed */ //int ref_dtbclk_khz;/* TODO needs to be removed */ From 359ec0952cbb15d44d6eeda10dc2c147d0d37a65 Mon Sep 17 00:00:00 2001 From: Daniel Miess Date: Fri, 19 May 2023 13:02:01 -0400 Subject: [PATCH 0354/2093] drm/amd/display: Enable dcn314 DPP RCO [ Upstream commit 17fbdbda9cc87ff5a013898de506212d25323ed7 ] [Why and How] Add back debug bits enabling RCO for dcn314 as underflow associated with this change has been resolved Acked-by: Stylon Wang Signed-off-by: Daniel Miess Reviewed-by: Jun Lei Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../drm/amd/display/dc/dcn314/dcn314_resource.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index b7782433ce6b..012f6369dae2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -920,6 +920,22 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, + + .root_clock_optimization = { + .bits = { + .dpp = true, + .dsc = false, + .hdmistream = false, + .hdmichar = false, + .dpstream = false, + .symclk32_se = false, + .symclk32_le = false, + .symclk_fe = false, + .physymclk = false, + .dpiasymclk = false, + } + }, + .seamless_boot_odm_combine = true }; From 055971715ff65d06964b448cc2099b326ecb1dbe Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 16 Jun 2023 12:00:34 +0200 Subject: [PATCH 0355/2093] ASoC: SOF: core: Free the firmware trace before calling snd_sof_shutdown() [ Upstream commit d389dcb3a48cec4f03c16434c0bf98a4c635372a ] The shutdown is called on reboot/shutdown of the machine. At this point the firmware tracing cannot be used anymore but in case of IPC3 it is using and keeping a DMA channel active (dtrace). For Tiger Lake platforms we have a quirk in place to fix rare reboot issues when a DMA was active before rebooting the system. If the tracing is enabled this quirk will be always used and a print appears on the kernel log which might be misleading or not even correct. Release the fw tracing before executing the shutdown to make sure that this known DMA user is cleared away. Reviewed-by: Kai Vehmanen Reviewed-by: Daniel Baluta Reviewed-by: Ranjani Sridharan Reviewed-by: Rander Wang Reviewed-by: Bard Liao Signed-off-by: Peter Ujfalusi Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230616100039.378150-4-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 625977a29d8a..75a1e2c6539f 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -479,8 +479,10 @@ int snd_sof_device_shutdown(struct device *dev) if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)) cancel_work_sync(&sdev->probe_work); - if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) + if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) { + sof_fw_trace_free(sdev); return snd_sof_shutdown(sdev); + } return 0; } From de840f77f564128e9d48c6b171ac984af1682d9b Mon Sep 17 00:00:00 2001 From: Even Xu Date: Thu, 15 Jun 2023 08:26:41 +0800 Subject: [PATCH 0356/2093] HID: intel-ish-hid: ipc: Add Arrow Lake PCI device ID [ Upstream commit 4982126e3029cd59fbd1da0d9cc0365a0585fe64 ] Add device ID of Arrow Lake-H into ishtp support list. Signed-off-by: Even Xu Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/intel-ish-hid/ipc/hw-ish.h | 1 + drivers/hid/intel-ish-hid/ipc/pci-ish.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index fc108f19a64c..e99f3a3c65e1 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -33,6 +33,7 @@ #define ADL_N_DEVICE_ID 0x54FC #define RPL_S_DEVICE_ID 0x7A78 #define MTL_P_DEVICE_ID 0x7E45 +#define ARL_H_DEVICE_ID 0x7745 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 7120b30ac51d..55cb25038e63 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -44,6 +44,7 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_N_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, RPL_S_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MTL_P_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ARL_H_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); From a783230585e5d8e9d410475468e203f3e720ff78 Mon Sep 17 00:00:00 2001 From: Matthew Anderson Date: Wed, 21 Jun 2023 11:17:14 -0500 Subject: [PATCH 0357/2093] ALSA: hda/realtek: Add quirks for ROG ALLY CS35l41 audio [ Upstream commit 724418b84e6248cd27599607b7e5fac365b8e3f5 ] This requires a patched ACPI table or a firmware from ASUS to work because the system does not come with the _DSD field for the CSC3551. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217550 Signed-off-by: Matthew Anderson Tested-by: Philip Mueller Link: https://lore.kernel.org/r/20230621161714.9442-1-ruinairas1992@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 46 +++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f93b68a2a839..f3c5940b032f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7136,6 +7136,10 @@ enum { ALC294_FIXUP_ASUS_DUAL_SPK, ALC285_FIXUP_THINKPAD_X1_GEN7, ALC285_FIXUP_THINKPAD_HEADSET_JACK, + ALC294_FIXUP_ASUS_ALLY, + ALC294_FIXUP_ASUS_ALLY_PINS, + ALC294_FIXUP_ASUS_ALLY_VERBS, + ALC294_FIXUP_ASUS_ALLY_SPEAKER, ALC294_FIXUP_ASUS_HPE, ALC294_FIXUP_ASUS_COEF_1B, ALC294_FIXUP_ASUS_GX502_HP, @@ -8450,6 +8454,47 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 }, + [ALC294_FIXUP_ASUS_ALLY] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_ALLY_PINS + }, + [ALC294_FIXUP_ASUS_ALLY_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1a, 0x03a11c30 }, + { 0x21, 0x03211420 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_ALLY_VERBS + }, + [ALC294_FIXUP_ASUS_ALLY_VERBS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x45 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5089 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x46 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0004 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x47 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xa47a }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x49 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0049}, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x4a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x201b }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x6b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x4278}, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_ALLY_SPEAKER + }, + [ALC294_FIXUP_ASUS_ALLY_SPEAKER] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + }, [ALC285_FIXUP_THINKPAD_X1_GEN7] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_thinkpad_x1_gen7, @@ -9562,6 +9607,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), From 945f4a7aff84fde1f825d17a5050880345da3228 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Mon, 19 Jun 2023 16:24:37 -0300 Subject: [PATCH 0358/2093] smb: client: fix warning in cifs_smb3_do_mount() [ Upstream commit 12c30f33cc6769bf411088a2872843c4f9ea32f9 ] This fixes the following warning reported by kernel test robot fs/smb/client/cifsfs.c:982 cifs_smb3_do_mount() warn: possible memory leak of 'cifs_sb' Link: https://lore.kernel.org/all/202306170124.CtQqzf0I-lkp@intel.com/ Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/cifsfs.c | 28 ++++++++++------------------ 1 file changed, 10 insertions(+), 18 deletions(-) diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 078df1e2dd18..18d66497c42d 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -883,11 +883,11 @@ struct dentry * cifs_smb3_do_mount(struct file_system_type *fs_type, int flags, struct smb3_fs_context *old_ctx) { - int rc; - struct super_block *sb = NULL; - struct cifs_sb_info *cifs_sb = NULL; struct cifs_mnt_data mnt_data; + struct cifs_sb_info *cifs_sb; + struct super_block *sb; struct dentry *root; + int rc; /* * Prints in Kernel / CIFS log the attempted mount operation @@ -898,11 +898,9 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, else cifs_info("Attempting to mount %s\n", old_ctx->UNC); - cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL); - if (cifs_sb == NULL) { - root = ERR_PTR(-ENOMEM); - goto out; - } + cifs_sb = kzalloc(sizeof(*cifs_sb), GFP_KERNEL); + if (!cifs_sb) + return ERR_PTR(-ENOMEM); cifs_sb->ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL); if (!cifs_sb->ctx) { @@ -945,10 +943,8 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data); if (IS_ERR(sb)) { - root = ERR_CAST(sb); cifs_umount(cifs_sb); - cifs_sb = NULL; - goto out; + return ERR_CAST(sb); } if (sb->s_root) { @@ -979,13 +975,9 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, deactivate_locked_super(sb); return root; out: - if (cifs_sb) { - if (!sb || IS_ERR(sb)) { /* otherwise kill_sb will handle */ - kfree(cifs_sb->prepath); - smb3_cleanup_fs_context(cifs_sb->ctx); - kfree(cifs_sb); - } - } + kfree(cifs_sb->prepath); + smb3_cleanup_fs_context(cifs_sb->ctx); + kfree(cifs_sb); return root; } From 7e4f5c3f01fb0e51ca438e43262d858daf9a0a76 Mon Sep 17 00:00:00 2001 From: Winston Wen Date: Mon, 26 Jun 2023 11:42:56 +0800 Subject: [PATCH 0359/2093] cifs: fix session state check in reconnect to avoid use-after-free issue [ Upstream commit 99f280700b4cc02d5f141b8d15f8e9fad0418f65 ] Don't collect exiting session in smb2_reconnect_server(), because it will be released soon. Note that the exiting session will stay in server->smb_ses_list until it complete the cifs_free_ipc() and logoff() and then delete itself from the list. Signed-off-by: Winston Wen Reviewed-by: Shyam Prasad N Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/smb2pdu.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 3ca593cdda76..ba46156e3268 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3841,6 +3841,12 @@ void smb2_reconnect_server(struct work_struct *work) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } + spin_unlock(&ses->ses_lock); tcon_selected = false; From bda3f463543f864e5f60768542f61194436ae34c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 12 May 2023 19:38:09 +0200 Subject: [PATCH 0360/2093] serial: stm32: Ignore return value of uart_remove_one_port() in .remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6bd6cd29c92401a101993290051fa55078238a52 ] Returning early from stm32_usart_serial_remove() results in a resource leak as several cleanup functions are not called. The driver core ignores the return value and there is no possibility to clean up later. uart_remove_one_port() only returns non-zero if there is some inconsistency (i.e. stm32_usart_driver.state[port->line].uart_port == NULL). This should never happen, and even if it does it's a bad idea to exit early in the remove callback without cleaning up. This prepares changing the prototype of struct platform_driver::remove to return void. See commit 5c5a7680e67b ("platform: Provide a remove callback that returns no value") for further details about this quest. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230512173810.131447-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/stm32-usart.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 28edbaf7bb32..2a9c4058824a 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -1753,13 +1753,10 @@ static int stm32_usart_serial_remove(struct platform_device *pdev) struct uart_port *port = platform_get_drvdata(pdev); struct stm32_port *stm32_port = to_stm32_port(port); const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; - int err; u32 cr3; pm_runtime_get_sync(&pdev->dev); - err = uart_remove_one_port(&stm32_usart_driver, port); - if (err) - return(err); + uart_remove_one_port(&stm32_usart_driver, port); pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); From 6c9317f73b80be20ac1eb3e9cec3e6c294e7e8bd Mon Sep 17 00:00:00 2001 From: Lu Hongfei Date: Thu, 25 May 2023 19:17:03 +0800 Subject: [PATCH 0361/2093] led: qcom-lpg: Fix resource leaks in for_each_available_child_of_node() loops [ Upstream commit 8f38f8fa7261819eb7d4fb369dc3bfab72259033 ] Ensure child node references are decremented properly in the error path. Signed-off-by: Lu Hongfei Link: https://lore.kernel.org/r/20230525111705.3055-1-luhongfei@vivo.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/rgb/leds-qcom-lpg.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c index f1c2419334e6..f85a5d65d131 100644 --- a/drivers/leds/rgb/leds-qcom-lpg.c +++ b/drivers/leds/rgb/leds-qcom-lpg.c @@ -1112,8 +1112,10 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np) i = 0; for_each_available_child_of_node(np, child) { ret = lpg_parse_channel(lpg, child, &led->channels[i]); - if (ret < 0) + if (ret < 0) { + of_node_put(child); return ret; + } info[i].color_index = led->channels[i]->color; info[i].intensity = 0; @@ -1291,8 +1293,10 @@ static int lpg_probe(struct platform_device *pdev) for_each_available_child_of_node(pdev->dev.of_node, np) { ret = lpg_add_led(lpg, np); - if (ret) + if (ret) { + of_node_put(np); return ret; + } } for (i = 0; i < lpg->num_channels; i++) From c71aa5f1cf961264690f2560503ea396b6e3c680 Mon Sep 17 00:00:00 2001 From: Yunfei Dong Date: Mon, 17 Apr 2023 16:17:40 +0800 Subject: [PATCH 0362/2093] media: v4l2-mem2mem: add lock to protect parameter num_rdy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 56b5c3e67b0f9af3f45cf393be048ee8d8a92694 ] Getting below error when using KCSAN to check the driver. Adding lock to protect parameter num_rdy when getting the value with function: v4l2_m2m_num_src_bufs_ready/v4l2_m2m_num_dst_bufs_ready. kworker/u16:3: [name:report&]BUG: KCSAN: data-race in v4l2_m2m_buf_queue kworker/u16:3: [name:report&] kworker/u16:3: [name:report&]read-write to 0xffffff8105f35b94 of 1 bytes by task 20865 on cpu 7: kworker/u16:3:  v4l2_m2m_buf_queue+0xd8/0x10c Signed-off-by: Pina Chen Signed-off-by: Yunfei Dong Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- include/media/v4l2-mem2mem.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index bb9de6a899e0..d6c8eb2b5201 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -593,7 +593,14 @@ void v4l2_m2m_buf_queue(struct v4l2_m2m_ctx *m2m_ctx, static inline unsigned int v4l2_m2m_num_src_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) { - return m2m_ctx->out_q_ctx.num_rdy; + unsigned int num_buf_rdy; + unsigned long flags; + + spin_lock_irqsave(&m2m_ctx->out_q_ctx.rdy_spinlock, flags); + num_buf_rdy = m2m_ctx->out_q_ctx.num_rdy; + spin_unlock_irqrestore(&m2m_ctx->out_q_ctx.rdy_spinlock, flags); + + return num_buf_rdy; } /** @@ -605,7 +612,14 @@ unsigned int v4l2_m2m_num_src_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) static inline unsigned int v4l2_m2m_num_dst_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) { - return m2m_ctx->cap_q_ctx.num_rdy; + unsigned int num_buf_rdy; + unsigned long flags; + + spin_lock_irqsave(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags); + num_buf_rdy = m2m_ctx->cap_q_ctx.num_rdy; + spin_unlock_irqrestore(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags); + + return num_buf_rdy; } /** From 54a55c345c3b2d92743189089da28b3fd0ebbb84 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 19 May 2023 00:52:35 +0300 Subject: [PATCH 0363/2093] media: camss: set VFE bpl_alignment to 16 for sdm845 and sm8250 [ Upstream commit d5b7eb477c286f6ceccbb38704136eea0e6b09ca ] From the experiments with camera sensors using SGRBG10_1X10/3280x2464 and SRGGB10_1X10/3280x2464 formats, it becomes clear that on sdm845 and sm8250 VFE outputs the lines padded to a length multiple of 16 bytes. As in the current driver the value of the bpl_alignment is set to 8 bytes, the frames captured in formats with the bytes-per-line value being not a multiple of 16 get corrupted. Set the bpl_alignment of the camss video output device to 16 for sdm845 and sm8250 to fix that. Signed-off-by: Andrey Konovalov Tested-by: Bryan O'Donoghue Acked-by: Bryan O'Donoghue Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/camss/camss-vfe.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c index a26e4a5d87b6..d8cd9b09c20d 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe.c +++ b/drivers/media/platform/qcom/camss/camss-vfe.c @@ -1540,7 +1540,11 @@ int msm_vfe_register_entities(struct vfe_device *vfe, } video_out->ops = &vfe->video_ops; - video_out->bpl_alignment = 8; + if (vfe->camss->version == CAMSS_845 || + vfe->camss->version == CAMSS_8250) + video_out->bpl_alignment = 16; + else + video_out->bpl_alignment = 8; video_out->line_based = 0; if (i == VFE_LINE_PIX) { video_out->bpl_alignment = 16; From 49038877f948592eb47cf7582ad95e50d47abea0 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Tue, 9 May 2023 18:57:52 +0530 Subject: [PATCH 0364/2093] usb: gadget: u_serial: Avoid spinlock recursion in __gs_console_push [ Upstream commit e5990469943c711cb00bfde6338d2add6c6d0bfe ] When serial console over USB is enabled, gs_console_connect queues gs_console_work, where it acquires the spinlock and queues the usb request, and this request goes to gadget layer. Now consider a situation where gadget layer prints something to dmesg, this will eventually call gs_console_write() which requires cons->lock. And this causes spinlock recursion. Avoid this by excluding usb_ep_queue from the spinlock. spin_lock_irqsave //needs cons->lock gs_console_write . . _printk __warn_printk dev_warn/pr_err . . [USB Gadget Layer] . . usb_ep_queue gs_console_work __gs_console_push // acquires cons->lock process_one_work Signed-off-by: Prashanth K Link: https://lore.kernel.org/r/1683638872-6885-1-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/u_serial.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index ea2c5b6cde8c..3c51355ccc94 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -915,8 +915,11 @@ static void __gs_console_push(struct gs_console *cons) } req->length = size; + + spin_unlock_irq(&cons->lock); if (usb_ep_queue(ep, req, GFP_ATOMIC)) req->length = 0; + spin_lock_irq(&cons->lock); } static void gs_console_work(struct work_struct *work) From 28d900836d476e0e4faf7d023f6a7f7b804e7b50 Mon Sep 17 00:00:00 2001 From: Avichal Rakesh Date: Mon, 8 May 2023 16:11:03 -0700 Subject: [PATCH 0365/2093] usb: gadget: uvc: queue empty isoc requests if no video buffer is available [ Upstream commit c3ff12a92bd7072170978b8b41c2fa41b038139a ] ISOC transfers expect a certain cadence of requests being queued. Not keeping up with the expected rate of requests results in missed ISOC transfers (EXDEV). The application layer may or may not produce video frames to match this expectation, so uvc gadget driver must handle cases where the application is not queuing up buffers fast enough to fulfill ISOC requirements. Currently, uvc gadget driver waits for new video buffer to become available before queuing up usb requests. With this patch the gadget driver queues up 0 length usb requests whenever there are no video buffers available. The USB controller's complete callback is used as the limiter for how quickly the 0 length packets will be queued. Video buffers are still queued as soon as they become available. Link: https://lore.kernel.org/CAMHf4WKbi6KBPQztj9FA4kPvESc1fVKrC8G73-cs6tTeQby9=w@mail.gmail.com/ Signed-off-by: Avichal Rakesh Link: https://lore.kernel.org/r/20230508231103.1621375-1-arakesh@google.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/uvc_video.c | 32 ++++++++++++++++++------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index dd1c6b2ca7c6..e81865978299 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -386,6 +386,9 @@ static void uvcg_video_pump(struct work_struct *work) struct uvc_buffer *buf; unsigned long flags; int ret; + bool buf_int; + /* video->max_payload_size is only set when using bulk transfer */ + bool is_bulk = video->max_payload_size; while (video->ep->enabled) { /* @@ -408,20 +411,35 @@ static void uvcg_video_pump(struct work_struct *work) */ spin_lock_irqsave(&queue->irqlock, flags); buf = uvcg_queue_head(queue); - if (buf == NULL) { + + if (buf != NULL) { + video->encode(req, video, buf); + /* Always interrupt for the last request of a video buffer */ + buf_int = buf->state == UVC_BUF_STATE_DONE; + } else if (!(queue->flags & UVC_QUEUE_DISCONNECTED) && !is_bulk) { + /* + * No video buffer available; the queue is still connected and + * we're traferring over ISOC. Queue a 0 length request to + * prevent missed ISOC transfers. + */ + req->length = 0; + buf_int = false; + } else { + /* + * Either queue has been disconnected or no video buffer + * available to bulk transfer. Either way, stop processing + * further. + */ spin_unlock_irqrestore(&queue->irqlock, flags); break; } - video->encode(req, video, buf); - /* * With usb3 we have more requests. This will decrease the * interrupt load to a quarter but also catches the corner * cases, which needs to be handled. */ - if (list_empty(&video->req_free) || - buf->state == UVC_BUF_STATE_DONE || + if (list_empty(&video->req_free) || buf_int || !(video->req_int_count % DIV_ROUND_UP(video->uvc_num_requests, 4))) { video->req_int_count = 0; @@ -441,8 +459,7 @@ static void uvcg_video_pump(struct work_struct *work) /* Endpoint now owns the request */ req = NULL; - if (buf->state != UVC_BUF_STATE_DONE) - video->req_int_count++; + video->req_int_count++; } if (!req) @@ -527,4 +544,3 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) V4L2_BUF_TYPE_VIDEO_OUTPUT, &video->mutex); return 0; } - From b7bd48f0be84e24d21aa3a8f59a8a9cb8633a1c4 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 24 May 2023 13:11:47 +0100 Subject: [PATCH 0366/2093] media: platform: mediatek: vpu: fix NULL ptr dereference [ Upstream commit 3df55cd773e8603b623425cc97b05e542854ad27 ] If pdev is NULL, then it is still dereferenced. This fixes this smatch warning: drivers/media/platform/mediatek/vpu/mtk_vpu.c:570 vpu_load_firmware() warn: address of NULL pointer 'pdev' Signed-off-by: Hans Verkuil Cc: Yunfei Dong Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/mediatek/vpu/mtk_vpu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/mediatek/vpu/mtk_vpu.c b/drivers/media/platform/mediatek/vpu/mtk_vpu.c index 47b684b92f81..6beab9e86a22 100644 --- a/drivers/media/platform/mediatek/vpu/mtk_vpu.c +++ b/drivers/media/platform/mediatek/vpu/mtk_vpu.c @@ -562,15 +562,17 @@ static int load_requested_vpu(struct mtk_vpu *vpu, int vpu_load_firmware(struct platform_device *pdev) { struct mtk_vpu *vpu; - struct device *dev = &pdev->dev; + struct device *dev; struct vpu_run *run; int ret; if (!pdev) { - dev_err(dev, "VPU platform device is invalid\n"); + pr_err("VPU platform device is invalid\n"); return -EINVAL; } + dev = &pdev->dev; + vpu = platform_get_drvdata(pdev); run = &vpu->run; From 809625f4419ce849f1dc72dd1ffeb0de640cc392 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 26 May 2023 14:46:44 +0300 Subject: [PATCH 0367/2093] thunderbolt: Read retimer NVM authentication status prior tb_retimer_set_inbound_sbtx() [ Upstream commit 1402ba08abae5cfa583ff1a40b99c098a0532d41 ] According to the USB4 retimer guide the correct order is immediately after sending ENUMERATE_RETIMERS so update the code to follow this. Signed-off-by: Mika Westerberg Signed-off-by: Sasha Levin --- drivers/thunderbolt/retimer.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 9cc28197dbc4..edbd92435b41 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -187,6 +187,21 @@ static ssize_t nvm_authenticate_show(struct device *dev, return ret; } +static void tb_retimer_nvm_authenticate_status(struct tb_port *port, u32 *status) +{ + int i; + + tb_port_dbg(port, "reading NVM authentication status of retimers\n"); + + /* + * Before doing anything else, read the authentication status. + * If the retimer has it set, store it for the new retimer + * device instance. + */ + for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) + usb4_port_retimer_nvm_authenticate_status(port, i, &status[i]); +} + static void tb_retimer_set_inbound_sbtx(struct tb_port *port) { int i; @@ -454,20 +469,18 @@ int tb_retimer_scan(struct tb_port *port, bool add) if (ret) return ret; + /* + * Immediately after sending enumerate retimers read the + * authentication status of each retimer. + */ + tb_retimer_nvm_authenticate_status(port, status); + /* * Enable sideband channel for each retimer. We can do this * regardless whether there is device connected or not. */ tb_retimer_set_inbound_sbtx(port); - /* - * Before doing anything else, read the authentication status. - * If the retimer has it set, store it for the new retimer - * device instance. - */ - for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) - usb4_port_retimer_nvm_authenticate_status(port, i, &status[i]); - for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) { /* * Last retimer is true only for the last on-board From 31f8efefa2a90effec3915465ed281128039f7ca Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Tue, 30 May 2023 18:40:07 +0800 Subject: [PATCH 0368/2093] usb: chipidea: imx: don't request QoS for imx8ulp [ Upstream commit 9a070e8e208995a9d638b538ed7abf28bd6ea6f0 ] Use dedicated imx8ulp usb compatible to remove QoS request since imx8ulp has no such limitation of imx7ulp: DMA will not work if system enters idle. Signed-off-by: Xu Yang Signed-off-by: Li Jun Acked-by: Peter Chen Message-ID: <20230530104007.1294702-2-xu.yang_2@nxp.com> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/chipidea/ci_hdrc_imx.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 9ffcecd3058c..60b4de0a4f76 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -70,6 +70,10 @@ static const struct ci_hdrc_imx_platform_flag imx7ulp_usb_data = { CI_HDRC_PMQOS, }; +static const struct ci_hdrc_imx_platform_flag imx8ulp_usb_data = { + .flags = CI_HDRC_SUPPORTS_RUNTIME_PM, +}; + static const struct of_device_id ci_hdrc_imx_dt_ids[] = { { .compatible = "fsl,imx23-usb", .data = &imx23_usb_data}, { .compatible = "fsl,imx28-usb", .data = &imx28_usb_data}, @@ -80,6 +84,7 @@ static const struct of_device_id ci_hdrc_imx_dt_ids[] = { { .compatible = "fsl,imx6ul-usb", .data = &imx6ul_usb_data}, { .compatible = "fsl,imx7d-usb", .data = &imx7d_usb_data}, { .compatible = "fsl,imx7ulp-usb", .data = &imx7ulp_usb_data}, + { .compatible = "fsl,imx8ulp-usb", .data = &imx8ulp_usb_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, ci_hdrc_imx_dt_ids); From 8277a215c872ba60a10c117888a115193817a773 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Wed, 17 May 2023 16:19:07 +0800 Subject: [PATCH 0369/2093] usb: chipidea: imx: add missing USB PHY DPDM wakeup setting [ Upstream commit 53d061c19dc4cb68409df6dc11c40389c8c42a75 ] USB PHY DPDM wakeup bit is enabled by default, when USB wakeup is not required(/sys/.../wakeup is disabled), this bit should be disabled, otherwise we will have unexpected wakeup if do USB device connect/disconnect while system sleep. This bit can be enabled for both host and device mode. Signed-off-by: Li Jun Signed-off-by: Xu Yang Acked-by: Peter Chen Message-ID: <20230517081907.3410465-3-xu.yang_2@nxp.com> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/chipidea/usbmisc_imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c index bac0f5458cab..2318c7906acd 100644 --- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -135,7 +135,7 @@ #define TXVREFTUNE0_MASK (0xf << 20) #define MX6_USB_OTG_WAKEUP_BITS (MX6_BM_WAKEUP_ENABLE | MX6_BM_VBUS_WAKEUP | \ - MX6_BM_ID_WAKEUP) + MX6_BM_ID_WAKEUP | MX6SX_BM_DPDM_WAKEUP_EN) struct usbmisc_ops { /* It's called once when probe a usb device */ From a4f71523ed2123d63b431cc0cea4e9f363a0f054 Mon Sep 17 00:00:00 2001 From: Tuo Li Date: Tue, 13 Jun 2023 11:06:37 +0800 Subject: [PATCH 0370/2093] gfs2: Fix possible data races in gfs2_show_options() [ Upstream commit 6fa0a72cbbe45db4ed967a51f9e6f4e3afe61d20 ] Some fields such as gt_logd_secs of the struct gfs2_tune are accessed without holding the lock gt_spin in gfs2_show_options(): val = sdp->sd_tune.gt_logd_secs; if (val != 30) seq_printf(s, ",commit=%d", val); And thus can cause data races when gfs2_show_options() and other functions such as gfs2_reconfigure() are concurrently executed: spin_lock(>->gt_spin); gt->gt_logd_secs = newargs->ar_commit; To fix these possible data races, the lock sdp->sd_tune.gt_spin is acquired before accessing the fields of gfs2_tune and released after these accesses. Further changes by Andreas: - Don't hold the spin lock over the seq_printf operations. Reported-by: BassCheck Signed-off-by: Tuo Li Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/super.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 9d27aa8bd2bc..44c564f0bc62 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -981,7 +981,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) { struct gfs2_sbd *sdp = root->d_sb->s_fs_info; struct gfs2_args *args = &sdp->sd_args; - int val; + unsigned int logd_secs, statfs_slow, statfs_quantum, quota_quantum; + + spin_lock(&sdp->sd_tune.gt_spin); + logd_secs = sdp->sd_tune.gt_logd_secs; + quota_quantum = sdp->sd_tune.gt_quota_quantum; + statfs_quantum = sdp->sd_tune.gt_statfs_quantum; + statfs_slow = sdp->sd_tune.gt_statfs_slow; + spin_unlock(&sdp->sd_tune.gt_spin); if (is_ancestor(root, sdp->sd_master_dir)) seq_puts(s, ",meta"); @@ -1036,17 +1043,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) } if (args->ar_discard) seq_puts(s, ",discard"); - val = sdp->sd_tune.gt_logd_secs; - if (val != 30) - seq_printf(s, ",commit=%d", val); - val = sdp->sd_tune.gt_statfs_quantum; - if (val != 30) - seq_printf(s, ",statfs_quantum=%d", val); - else if (sdp->sd_tune.gt_statfs_slow) + if (logd_secs != 30) + seq_printf(s, ",commit=%d", logd_secs); + if (statfs_quantum != 30) + seq_printf(s, ",statfs_quantum=%d", statfs_quantum); + else if (statfs_slow) seq_puts(s, ",statfs_quantum=0"); - val = sdp->sd_tune.gt_quota_quantum; - if (val != 60) - seq_printf(s, ",quota_quantum=%d", val); + if (quota_quantum != 60) + seq_printf(s, ",quota_quantum=%d", quota_quantum); if (args->ar_statfs_percent) seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent); if (args->ar_errors != GFS2_ERRORS_DEFAULT) { From e8a80cf06b4bb0396212289d651b384c949f09d0 Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Fri, 12 May 2023 20:45:29 +0200 Subject: [PATCH 0371/2093] pcmcia: rsrc_nonstatic: Fix memory leak in nonstatic_release_resource_db() [ Upstream commit c85fd9422fe0f5d667305efb27f56d09eab120b0 ] When nonstatic_release_resource_db() frees all resources associated with an PCMCIA socket, it forgets to free socket_data too, causing a memory leak observable with kmemleak: unreferenced object 0xc28d1000 (size 64): comm "systemd-udevd", pid 297, jiffies 4294898478 (age 194.484s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 f0 85 0e c3 00 00 00 00 ................ 00 00 00 00 0c 10 8d c2 00 00 00 00 00 00 00 00 ................ backtrace: [] __kmem_cache_alloc_node+0x2d7/0x4a0 [<7e51f0c8>] kmalloc_trace+0x31/0xa4 [] nonstatic_init+0x24/0x1a4 [pcmcia_rsrc] [] pcmcia_register_socket+0x200/0x35c [pcmcia_core] [] yenta_probe+0x4d8/0xa70 [yenta_socket] [] pci_device_probe+0x99/0x194 [<84b7c690>] really_probe+0x181/0x45c [<8060fe6e>] __driver_probe_device+0x75/0x1f4 [] driver_probe_device+0x28/0xac [<648b766f>] __driver_attach+0xeb/0x1e4 [<6e9659eb>] bus_for_each_dev+0x61/0xb4 [<25a669f3>] driver_attach+0x1e/0x28 [] bus_add_driver+0x102/0x20c [] driver_register+0x5b/0x120 [<942cd8a4>] __pci_register_driver+0x44/0x4c [] __UNIQUE_ID___addressable_cleanup_module188+0x1c/0xfffff000 [iTCO_vendor_support] Fix this by freeing socket_data too. Tested on a Acer Travelmate 4002WLMi by manually binding/unbinding the yenta_cardbus driver (yenta_socket). Signed-off-by: Armin Wolf Message-ID: <20230512184529.5094-1-W_Armin@gmx.de> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/pcmcia/rsrc_nonstatic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c index ad1141fddb4c..8bda75990bce 100644 --- a/drivers/pcmcia/rsrc_nonstatic.c +++ b/drivers/pcmcia/rsrc_nonstatic.c @@ -1053,6 +1053,8 @@ static void nonstatic_release_resource_db(struct pcmcia_socket *s) q = p->next; kfree(p); } + + kfree(data); } From acb9038e1d609dc459a140953a1c79fd88db527c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sat, 17 Dec 2022 08:35:04 +0200 Subject: [PATCH 0372/2093] thunderbolt: Add Intel Barlow Ridge PCI ID [ Upstream commit 6f14a210661ce03988ef4ed3c8402037c8e06539 ] Intel Barlow Ridge is the first USB4 v2 controller from Intel. The controller exposes standard USB4 PCI class ID in typical configurations, however there is a way to configure it so that it uses a special class ID to allow using s different driver than the Windows inbox one. For this reason add the Barlow Ridge PCI ID to the Linux driver too so that the driver can attach regardless of the class ID. Tested-by: Pengfei Xu Signed-off-by: Mika Westerberg Signed-off-by: Sasha Levin --- drivers/thunderbolt/nhi.c | 2 ++ drivers/thunderbolt/nhi.h | 2 ++ 2 files changed, 4 insertions(+) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 4a6a3802d7e5..288aaa05d007 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1479,6 +1479,8 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) }, /* Any USB4 compliant host */ { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index b0718020c6f5..c15a0c46c9cf 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -75,6 +75,8 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_BRIDGE 0x15ef #define PCI_DEVICE_ID_INTEL_ADL_NHI0 0x463e #define PCI_DEVICE_ID_INTEL_ADL_NHI1 0x466d +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI 0x5781 +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI 0x5784 #define PCI_DEVICE_ID_INTEL_MTL_M_NHI0 0x7eb2 #define PCI_DEVICE_ID_INTEL_MTL_P_NHI0 0x7ec2 #define PCI_DEVICE_ID_INTEL_MTL_P_NHI1 0x7ec3 From ef87750caea52a2642f796eb65b376009efbc272 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 17 May 2023 10:45:53 +0300 Subject: [PATCH 0373/2093] thunderbolt: Limit Intel Barlow Ridge USB3 bandwidth [ Upstream commit f2bfa944080dcbb8eb56259dfd2c07204cbee17e ] Intel Barlow Ridge discrete USB4 host router has the same limitation as the previous generations so make sure the USB3 bandwidth limitation quirk is applied to Barlow Ridge too. Signed-off-by: Gil Fine Signed-off-by: Mika Westerberg Signed-off-by: Sasha Levin --- drivers/thunderbolt/nhi.h | 2 ++ drivers/thunderbolt/quirks.c | 8 ++++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index c15a0c46c9cf..0f029ce75882 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -77,6 +77,8 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_ADL_NHI1 0x466d #define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI 0x5781 #define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI 0x5784 +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_80G_BRIDGE 0x5786 +#define PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_40G_BRIDGE 0x57a4 #define PCI_DEVICE_ID_INTEL_MTL_M_NHI0 0x7eb2 #define PCI_DEVICE_ID_INTEL_MTL_P_NHI0 0x7ec2 #define PCI_DEVICE_ID_INTEL_MTL_P_NHI1 0x7ec3 diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index 1157b8869bcc..8c2ee431fcde 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -74,6 +74,14 @@ static const struct tb_quirk tb_quirks[] = { quirk_usb3_maximum_bandwidth }, { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI1, 0x0000, 0x0000, quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_80G_BRIDGE, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_40G_BRIDGE, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ From 9040adc38cf6bfbb77034d558ac2c52f70d840ac Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Fri, 23 Jun 2023 13:39:35 +0800 Subject: [PATCH 0374/2093] firewire: net: fix use after free in fwnet_finish_incoming_packet() [ Upstream commit 3ff256751a2853e1ffaa36958ff933ccc98c6cb5 ] The netif_rx() function frees the skb so we can't dereference it to save the skb->len. Signed-off-by: Zhang Shurong Link: https://lore.kernel.org/r/tencent_3B3D24B66ED66A6BB73CC0E63C6A14E45109@qq.com Signed-off-by: Takashi Sakamoto Signed-off-by: Sasha Levin --- drivers/firewire/net.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index af22be84034b..a53eacebca33 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -479,7 +479,7 @@ static int fwnet_finish_incoming_packet(struct net_device *net, struct sk_buff *skb, u16 source_node_id, bool is_broadcast, u16 ether_type) { - int status; + int status, len; switch (ether_type) { case ETH_P_ARP: @@ -533,13 +533,15 @@ static int fwnet_finish_incoming_packet(struct net_device *net, } skb->protocol = protocol; } + + len = skb->len; status = netif_rx(skb); if (status == NET_RX_DROP) { net->stats.rx_errors++; net->stats.rx_dropped++; } else { net->stats.rx_packets++; - net->stats.rx_bytes += skb->len; + net->stats.rx_bytes += len; } return 0; From de8677ccf8830d54af3f4388508bb2dda2b06525 Mon Sep 17 00:00:00 2001 From: Yuechao Zhao Date: Mon, 12 Jun 2023 11:19:07 +0800 Subject: [PATCH 0375/2093] watchdog: sp5100_tco: support Hygon FCH/SCH (Server Controller Hub) [ Upstream commit 009637de1f65cff452ad49554d1e8ef9fda99e43 ] Add PCI_VENDOR_ID_HYGON(Hygon vendor id [0x1d94]) in this driver Signed-off-by: Yuechao Zhao Reviewed-by: Guenter Roeck Link: https://lkml.kernel.org/r/20230612031907.796461-1-a345351830@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/sp5100_tco.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index 14f8d8d90920..2bd3dc25cb03 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -96,7 +96,7 @@ static enum tco_reg_layout tco_reg_layout(struct pci_dev *dev) sp5100_tco_pci->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && sp5100_tco_pci->revision >= AMD_ZEN_SMBUS_PCI_REV) { return efch_mmio; - } else if (dev->vendor == PCI_VENDOR_ID_AMD && + } else if ((dev->vendor == PCI_VENDOR_ID_AMD || dev->vendor == PCI_VENDOR_ID_HYGON) && ((dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS && dev->revision >= 0x41) || (dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && @@ -579,6 +579,8 @@ static const struct pci_device_id sp5100_tco_pci_tbl[] = { PCI_ANY_ID, }, { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, PCI_ANY_ID, PCI_ANY_ID, }, + { PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, PCI_ANY_ID, + PCI_ANY_ID, }, { 0, }, /* End of list */ }; MODULE_DEVICE_TABLE(pci, sp5100_tco_pci_tbl); From 149daab45922ab1ac7f0cbeacab7251a46bf5e63 Mon Sep 17 00:00:00 2001 From: Zhengping Jiang Date: Wed, 24 May 2023 17:04:15 -0700 Subject: [PATCH 0376/2093] Bluetooth: L2CAP: Fix use-after-free [ Upstream commit f752a0b334bb95fe9b42ecb511e0864e2768046f ] Fix potential use-after-free in l2cap_le_command_rej. Signed-off-by: Zhengping Jiang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 02fc9961464c..a7899857aee5 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6375,9 +6375,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (!chan) goto done; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + goto done; + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); done: mutex_unlock(&conn->chan_lock); From d92613aa43da68956a36503d17aa98a3e653d3a5 Mon Sep 17 00:00:00 2001 From: Matthew Anderson Date: Sat, 24 Jun 2023 12:08:10 -0500 Subject: [PATCH 0377/2093] Bluetooth: btusb: Add MT7922 bluetooth ID for the Asus Ally [ Upstream commit fa01eba11f0e57c767a5eab5291c7a01407a00be ] Adding the device ID from the Asus Ally gets the bluetooth working on the device. Signed-off-by: Matthew Anderson Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/bluetooth/btusb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index faad19b396d5..d6f405763c56 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -600,6 +600,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe0d9), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0f5), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, { USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, From 3a89f3bfbf533b89f74dea34e174081eca3381d4 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 18 May 2023 09:40:14 +0800 Subject: [PATCH 0378/2093] ceph: try to dump the msgs when decoding fails [ Upstream commit 8b0da5c549ae63ba1debd92a350f90773cb4bfe7 ] When the msgs are corrupted we need to dump them and then it will be easier to dig what has happened and where the issue is. Signed-off-by: Xiubo Li Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/mds_client.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index dcabe2783edf..5399a9ea5b4f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -645,6 +645,7 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg, err = -EIO; out_bad: pr_err("mds parse_reply err %d\n", err); + ceph_msg_dump(msg); return err; } @@ -3534,6 +3535,7 @@ static void handle_forward(struct ceph_mds_client *mdsc, bad: pr_err("mdsc_handle_forward decode error err=%d\n", err); + ceph_msg_dump(msg); } static int __decode_session_metadata(void **p, void *end, @@ -5254,6 +5256,7 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) bad: pr_err("error decoding fsmap %d. Shutting down mount.\n", err); ceph_umount_begin(mdsc->fsc->sb); + ceph_msg_dump(msg); err_out: mutex_lock(&mdsc->mutex); mdsc->mdsmap_err = err; @@ -5322,6 +5325,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) bad: pr_err("error decoding mdsmap %d. Shutting down mount.\n", err); ceph_umount_begin(mdsc->fsc->sb); + ceph_msg_dump(msg); return; } From dd0b3b367c3839e439f36af908b39c98929a5e54 Mon Sep 17 00:00:00 2001 From: shanzhulig Date: Tue, 27 Jun 2023 18:10:47 -0700 Subject: [PATCH 0379/2093] drm/amdgpu: Fix potential fence use-after-free v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2e54154b9f27262efd0cb4f903cc7d5ad1fe9628 ] fence Decrements the reference count before exiting. Avoid Race Vulnerabilities for fence use-after-free. v2 (chk): actually fix the use after free and not just move it. Signed-off-by: shanzhulig Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 6d3d01c5f0a2..02a112d00d41 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1607,15 +1607,15 @@ static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev, continue; r = dma_fence_wait_timeout(fence, true, timeout); + if (r > 0 && fence->error) + r = fence->error; + dma_fence_put(fence); if (r < 0) return r; if (r == 0) break; - - if (fence->error) - return fence->error; } memset(wait, 0, sizeof(*wait)); From 4246bbef0442f4a1e974df0ab091f4f33ac69451 Mon Sep 17 00:00:00 2001 From: Edward Lo Date: Thu, 16 Mar 2023 10:56:55 +0800 Subject: [PATCH 0380/2093] fs/ntfs3: Enhance sanity check while generating attr_list [ Upstream commit fdec309c7672cbee4dc0229ee4cbb33c948a1bdd ] ni_create_attr_list uses WARN_ON to catch error cases while generating attribute list, which only prints out stack trace and may not be enough. This repalces them with more proper error handling flow. [ 59.666332] BUG: kernel NULL pointer dereference, address: 000000000000000e [ 59.673268] #PF: supervisor read access in kernel mode [ 59.678354] #PF: error_code(0x0000) - not-present page [ 59.682831] PGD 8000000005ff1067 P4D 8000000005ff1067 PUD 7dee067 PMD 0 [ 59.688556] Oops: 0000 [#1] PREEMPT SMP KASAN PTI [ 59.692642] CPU: 0 PID: 198 Comm: poc Tainted: G B W 6.2.0-rc1+ #4 [ 59.698868] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 [ 59.708795] RIP: 0010:ni_create_attr_list+0x505/0x860 [ 59.713657] Code: 7e 10 e8 5e d0 d0 ff 45 0f b7 76 10 48 8d 7b 16 e8 00 d1 d0 ff 66 44 89 73 16 4d 8d 75 0e 4c 89 f7 e8 3f d0 d0 ff 4c 8d8 [ 59.731559] RSP: 0018:ffff88800a56f1e0 EFLAGS: 00010282 [ 59.735691] RAX: 0000000000000001 RBX: ffff88800b7b5088 RCX: ffffffffb83079fe [ 59.741792] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffffffffbb7f9fc0 [ 59.748423] RBP: ffff88800a56f3a8 R08: ffff88800b7b50a0 R09: fffffbfff76ff3f9 [ 59.754654] R10: ffffffffbb7f9fc7 R11: fffffbfff76ff3f8 R12: ffff88800b756180 [ 59.761552] R13: 0000000000000000 R14: 000000000000000e R15: 0000000000000050 [ 59.768323] FS: 00007feaa8c96440(0000) GS:ffff88806d400000(0000) knlGS:0000000000000000 [ 59.776027] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 59.781395] CR2: 00007f3a2e0b1000 CR3: 000000000a5bc000 CR4: 00000000000006f0 [ 59.787607] Call Trace: [ 59.790271] [ 59.792488] ? __pfx_ni_create_attr_list+0x10/0x10 [ 59.797235] ? kernel_text_address+0xd3/0xe0 [ 59.800856] ? unwind_get_return_address+0x3e/0x60 [ 59.805101] ? __kasan_check_write+0x18/0x20 [ 59.809296] ? preempt_count_sub+0x1c/0xd0 [ 59.813421] ni_ins_attr_ext+0x52c/0x5c0 [ 59.817034] ? __pfx_ni_ins_attr_ext+0x10/0x10 [ 59.821926] ? __vfs_setxattr+0x121/0x170 [ 59.825718] ? __vfs_setxattr_noperm+0x97/0x300 [ 59.829562] ? __vfs_setxattr_locked+0x145/0x170 [ 59.833987] ? vfs_setxattr+0x137/0x2a0 [ 59.836732] ? do_setxattr+0xce/0x150 [ 59.839807] ? setxattr+0x126/0x140 [ 59.842353] ? path_setxattr+0x164/0x180 [ 59.845275] ? __x64_sys_setxattr+0x71/0x90 [ 59.848838] ? do_syscall_64+0x3f/0x90 [ 59.851898] ? entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 59.857046] ? stack_depot_save+0x17/0x20 [ 59.860299] ni_insert_attr+0x1ba/0x420 [ 59.863104] ? __pfx_ni_insert_attr+0x10/0x10 [ 59.867069] ? preempt_count_sub+0x1c/0xd0 [ 59.869897] ? _raw_spin_unlock_irqrestore+0x2b/0x50 [ 59.874088] ? __create_object+0x3ae/0x5d0 [ 59.877865] ni_insert_resident+0xc4/0x1c0 [ 59.881430] ? __pfx_ni_insert_resident+0x10/0x10 [ 59.886355] ? kasan_save_alloc_info+0x1f/0x30 [ 59.891117] ? __kasan_kmalloc+0x8b/0xa0 [ 59.894383] ntfs_set_ea+0x90d/0xbf0 [ 59.897703] ? __pfx_ntfs_set_ea+0x10/0x10 [ 59.901011] ? kernel_text_address+0xd3/0xe0 [ 59.905308] ? __kernel_text_address+0x16/0x50 [ 59.909811] ? unwind_get_return_address+0x3e/0x60 [ 59.914898] ? __pfx_stack_trace_consume_entry+0x10/0x10 [ 59.920250] ? arch_stack_walk+0xa2/0x100 [ 59.924560] ? filter_irq_stacks+0x27/0x80 [ 59.928722] ntfs_setxattr+0x405/0x440 [ 59.932512] ? __pfx_ntfs_setxattr+0x10/0x10 [ 59.936634] ? kvmalloc_node+0x2d/0x120 [ 59.940378] ? kasan_save_stack+0x41/0x60 [ 59.943870] ? kasan_save_stack+0x2a/0x60 [ 59.947719] ? kasan_set_track+0x29/0x40 [ 59.951417] ? kasan_save_alloc_info+0x1f/0x30 [ 59.955733] ? __kasan_kmalloc+0x8b/0xa0 [ 59.959598] ? __kmalloc_node+0x68/0x150 [ 59.963163] ? kvmalloc_node+0x2d/0x120 [ 59.966490] ? vmemdup_user+0x2b/0xa0 [ 59.969060] __vfs_setxattr+0x121/0x170 [ 59.972456] ? __pfx___vfs_setxattr+0x10/0x10 [ 59.976008] __vfs_setxattr_noperm+0x97/0x300 [ 59.981562] __vfs_setxattr_locked+0x145/0x170 [ 59.986100] vfs_setxattr+0x137/0x2a0 [ 59.989964] ? __pfx_vfs_setxattr+0x10/0x10 [ 59.993616] ? __kasan_check_write+0x18/0x20 [ 59.997425] do_setxattr+0xce/0x150 [ 60.000304] setxattr+0x126/0x140 [ 60.002967] ? __pfx_setxattr+0x10/0x10 [ 60.006471] ? __virt_addr_valid+0xcb/0x140 [ 60.010461] ? __call_rcu_common.constprop.0+0x1c7/0x330 [ 60.016037] ? debug_smp_processor_id+0x1b/0x30 [ 60.021008] ? kasan_quarantine_put+0x5b/0x190 [ 60.025545] ? putname+0x84/0xa0 [ 60.027910] ? __kasan_slab_free+0x11e/0x1b0 [ 60.031483] ? putname+0x84/0xa0 [ 60.033986] ? preempt_count_sub+0x1c/0xd0 [ 60.036876] ? __mnt_want_write+0xae/0x100 [ 60.040738] ? mnt_want_write+0x8f/0x150 [ 60.044317] path_setxattr+0x164/0x180 [ 60.048096] ? __pfx_path_setxattr+0x10/0x10 [ 60.052096] ? strncpy_from_user+0x175/0x1c0 [ 60.056482] ? debug_smp_processor_id+0x1b/0x30 [ 60.059848] ? fpregs_assert_state_consistent+0x6b/0x80 [ 60.064557] __x64_sys_setxattr+0x71/0x90 [ 60.068892] do_syscall_64+0x3f/0x90 [ 60.072868] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 60.077523] RIP: 0033:0x7feaa86e4469 [ 60.080915] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 088 [ 60.097353] RSP: 002b:00007ffdbd8311e8 EFLAGS: 00000286 ORIG_RAX: 00000000000000bc [ 60.103386] RAX: ffffffffffffffda RBX: 9461c5e290baac00 RCX: 00007feaa86e4469 [ 60.110322] RDX: 00007ffdbd831fe0 RSI: 00007ffdbd831305 RDI: 00007ffdbd831263 [ 60.116808] RBP: 00007ffdbd836180 R08: 0000000000000001 R09: 00007ffdbd836268 [ 60.123879] R10: 000000000000007d R11: 0000000000000286 R12: 0000000000400500 [ 60.130540] R13: 00007ffdbd836260 R14: 0000000000000000 R15: 0000000000000000 [ 60.136553] [ 60.138818] Modules linked in: [ 60.141839] CR2: 000000000000000e [ 60.144831] ---[ end trace 0000000000000000 ]--- [ 60.149058] RIP: 0010:ni_create_attr_list+0x505/0x860 [ 60.153975] Code: 7e 10 e8 5e d0 d0 ff 45 0f b7 76 10 48 8d 7b 16 e8 00 d1 d0 ff 66 44 89 73 16 4d 8d 75 0e 4c 89 f7 e8 3f d0 d0 ff 4c 8d8 [ 60.172443] RSP: 0018:ffff88800a56f1e0 EFLAGS: 00010282 [ 60.176246] RAX: 0000000000000001 RBX: ffff88800b7b5088 RCX: ffffffffb83079fe [ 60.182752] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffffffffbb7f9fc0 [ 60.189949] RBP: ffff88800a56f3a8 R08: ffff88800b7b50a0 R09: fffffbfff76ff3f9 [ 60.196950] R10: ffffffffbb7f9fc7 R11: fffffbfff76ff3f8 R12: ffff88800b756180 [ 60.203671] R13: 0000000000000000 R14: 000000000000000e R15: 0000000000000050 [ 60.209595] FS: 00007feaa8c96440(0000) GS:ffff88806d400000(0000) knlGS:0000000000000000 [ 60.216299] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 60.222276] CR2: 00007f3a2e0b1000 CR3: 000000000a5bc000 CR4: 00000000000006f0 Signed-off-by: Edward Lo Signed-off-by: Konstantin Komarov Signed-off-by: Sasha Levin --- fs/ntfs3/frecord.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index b1b476fb7229..dda13e1f1b33 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -874,6 +874,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) if (err) goto out1; + err = -EINVAL; /* Call mi_remove_attr() in reverse order to keep pointers 'arr_move' valid. */ while (to_free > 0) { struct ATTRIB *b = arr_move[--nb]; @@ -882,7 +883,8 @@ int ni_create_attr_list(struct ntfs_inode *ni) attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off), b->name_len, asize, name_off); - WARN_ON(!attr); + if (!attr) + goto out1; mi_get_ref(mi, &le_b[nb]->ref); le_b[nb]->id = attr->id; @@ -892,17 +894,20 @@ int ni_create_attr_list(struct ntfs_inode *ni) attr->id = le_b[nb]->id; /* Remove from primary record. */ - WARN_ON(!mi_remove_attr(NULL, &ni->mi, b)); + if (!mi_remove_attr(NULL, &ni->mi, b)) + goto out1; if (to_free <= asize) break; to_free -= asize; - WARN_ON(!nb); + if (!nb) + goto out1; } attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0, lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT); - WARN_ON(!attr); + if (!attr) + goto out1; attr->non_res = 0; attr->flags = 0; @@ -922,9 +927,10 @@ int ni_create_attr_list(struct ntfs_inode *ni) kfree(ni->attr_list.le); ni->attr_list.le = NULL; ni->attr_list.size = 0; + return err; out: - return err; + return 0; } /* From 1e2205568bb86cd3e5a8261717bfdbb43b9a4083 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Tue, 21 Mar 2023 21:22:11 +0800 Subject: [PATCH 0381/2093] fs: ntfs3: Fix possible null-pointer dereferences in mi_read() [ Upstream commit 97498cd610c0d030a7bd49a7efad974790661162 ] In a previous commit 2681631c2973 ("fs/ntfs3: Add null pointer check to attr_load_runs_vcn"), ni can be NULL in attr_load_runs_vcn(), and thus it should be checked before being used. However, in the call stack of this commit, mft_ni in mi_read() is aliased with ni in attr_load_runs_vcn(), and it is also used in mi_read() at two places: mi_read() rw_lock = &mft_ni->file.run_lock -> No check attr_load_runs_vcn(mft_ni, ...) ni (namely mft_ni) is checked in the previous commit attr_load_runs_vcn(..., &mft_ni->file.run) -> No check Thus, to avoid possible null-pointer dereferences, the related checks should be added. These bugs are reported by a static analysis tool implemented by myself, and they are found by extending a known bug fixed in the previous commit. Thus, they could be theoretical bugs. Signed-off-by: Jia-Ju Bai Signed-off-by: Konstantin Komarov Signed-off-by: Sasha Levin --- fs/ntfs3/record.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index af1e4b364ea8..07037ec773ac 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -124,7 +124,7 @@ int mi_read(struct mft_inode *mi, bool is_mft) struct rw_semaphore *rw_lock = NULL; if (is_mounted(sbi)) { - if (!is_mft) { + if (!is_mft && mft_ni) { rw_lock = &mft_ni->file.run_lock; down_read(rw_lock); } @@ -148,7 +148,7 @@ int mi_read(struct mft_inode *mi, bool is_mft) ni_lock(mft_ni); down_write(rw_lock); } - err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, &mft_ni->file.run, + err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, run, vbo >> sbi->cluster_bits); if (rw_lock) { up_write(rw_lock); From 9e79f3e8f129eb6a195d5678b18320bb91c75da5 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 8 May 2023 11:36:28 +0400 Subject: [PATCH 0382/2093] fs/ntfs3: Mark ntfs dirty when on-disk struct is corrupted [ Upstream commit e0f363a98830e8d7d70fbaf91c07ae0b7c57aafe ] Signed-off-by: Konstantin Komarov Signed-off-by: Sasha Levin --- fs/ntfs3/fsntfs.c | 2 +- fs/ntfs3/index.c | 6 ++++++ fs/ntfs3/ntfs_fs.h | 2 ++ fs/ntfs3/record.c | 6 ++++++ 4 files changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index b6e22bcb929b..829b62d3bb88 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -154,7 +154,7 @@ int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, /* Check errors. */ if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || fn * SECTOR_SIZE > bytes) { - return -EINVAL; /* Native chkntfs returns ok! */ + return -E_NTFS_CORRUPT; } /* Get fixup pointer. */ diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 9e9a9ffd9295..495cfb37962f 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1103,6 +1103,12 @@ int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, *node = in; out: + if (err == -E_NTFS_CORRUPT) { + ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + } + if (ib != in->index) kfree(ib); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 24227b2e1b2b..8c9abaf139e6 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -53,6 +53,8 @@ enum utf16_endian; #define E_NTFS_NONRESIDENT 556 /* NTFS specific error code about punch hole. */ #define E_NTFS_NOTALIGNED 557 +/* NTFS specific error code when on-disk struct is corrupted. */ +#define E_NTFS_CORRUPT 558 /* sbi->flags */ diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 07037ec773ac..ba336c7280b8 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -180,6 +180,12 @@ int mi_read(struct mft_inode *mi, bool is_mft) return 0; out: + if (err == -E_NTFS_CORRUPT) { + ntfs_err(sbi->sb, "mft corrupted"); + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + } + return err; } From 63e0b5d76d75f3235f50698cb112a7d9736892db Mon Sep 17 00:00:00 2001 From: dengxiang Date: Mon, 3 Jul 2023 10:17:51 +0800 Subject: [PATCH 0383/2093] ALSA: hda/realtek: Add quirks for Unis H3C Desktop B760 & Q760 [ Upstream commit 73f1c75d5e6bd8ce2a887ef493a66ad1b16ed704 ] These models use NSIWAY amplifiers for internal speaker, but cannot put sound outside from these amplifiers. So eapd verbs are needed to initialize the amplifiers. They can be added during boot to get working sound out of internal speaker. Signed-off-by: dengxiang Link: https://lore.kernel.org/r/20230703021751.2945750-1-dengxiang@nfschina.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f3c5940b032f..923b8e0c9efe 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11314,6 +11314,7 @@ enum { ALC897_FIXUP_HP_HSMIC_VERB, ALC897_FIXUP_LENOVO_HEADSET_MODE, ALC897_FIXUP_HEADSET_MIC_PIN2, + ALC897_FIXUP_UNIS_H3C_X500S, }; static const struct hda_fixup alc662_fixups[] = { @@ -11753,6 +11754,13 @@ static const struct hda_fixup alc662_fixups[] = { .chained = true, .chain_id = ALC897_FIXUP_LENOVO_HEADSET_MODE }, + [ALC897_FIXUP_UNIS_H3C_X500S] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x14, AC_VERB_SET_EAPD_BTLENABLE, 0 }, + {} + }, + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -11914,6 +11922,7 @@ static const struct hda_model_fixup alc662_fixup_models[] = { {.id = ALC662_FIXUP_USI_HEADSET_MODE, .name = "usi-headset"}, {.id = ALC662_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"}, {.id = ALC669_FIXUP_ACER_ASPIRE_ETHOS, .name = "aspire-ethos"}, + {.id = ALC897_FIXUP_UNIS_H3C_X500S, .name = "unis-h3c-x500s"}, {} }; From cdd412b528dee6e0851c4735d6676ec138da13a4 Mon Sep 17 00:00:00 2001 From: Tuo Li Date: Mon, 3 Jul 2023 11:10:16 +0800 Subject: [PATCH 0384/2093] ALSA: hda: fix a possible null-pointer dereference due to data race in snd_hdac_regmap_sync() [ Upstream commit 1f4a08fed450db87fbb5ff5105354158bdbe1a22 ] The variable codec->regmap is often protected by the lock codec->regmap_lock when is accessed. However, it is accessed without holding the lock when is accessed in snd_hdac_regmap_sync(): if (codec->regmap) In my opinion, this may be a harmful race, because if codec->regmap is set to NULL right after the condition is checked, a null-pointer dereference can occur in the called function regcache_sync(): map->lock(map->lock_arg); --> Line 360 in drivers/base/regmap/regcache.c To fix this possible null-pointer dereference caused by data race, the mutex_lock coverage is extended to protect the if statement as well as the function call to regcache_sync(). [ Note: the lack of the regmap_lock itself is harmless for the current codec driver implementations, as snd_hdac_regmap_sync() is only for PM runtime resume that is prohibited during the codec probe. But the change makes the whole code more consistent, so it's merged as is -- tiwai ] Reported-by: BassCheck Signed-off-by: Tuo Li Link: https://lore.kernel.org/r/20230703031016.1184711-1-islituo@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/hdac_regmap.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c index fe3587547cfe..39610a15bcc9 100644 --- a/sound/hda/hdac_regmap.c +++ b/sound/hda/hdac_regmap.c @@ -597,10 +597,9 @@ EXPORT_SYMBOL_GPL(snd_hdac_regmap_update_raw_once); */ void snd_hdac_regmap_sync(struct hdac_device *codec) { - if (codec->regmap) { - mutex_lock(&codec->regmap_lock); + mutex_lock(&codec->regmap_lock); + if (codec->regmap) regcache_sync(codec->regmap); - mutex_unlock(&codec->regmap_lock); - } + mutex_unlock(&codec->regmap_lock); } EXPORT_SYMBOL_GPL(snd_hdac_regmap_sync); From c48616e52d5d5a225de5d7c02daa34c68056c273 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Tue, 4 Jul 2023 16:46:15 +1200 Subject: [PATCH 0385/2093] ALSA: hda/realtek: Add quirk for ASUS ROG GX650P [ Upstream commit 8cc87c055d28320e5fa5457922f43bc07dec58bd ] Adds the required quirk to enable the Cirrus amp and correct pins on the ASUS ROG GV601V series which uses an I2C connected Cirrus amp. While this works if the related _DSD properties are made available, these aren't included in the ACPI of these laptops (yet). Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20230704044619.19343-2-luke@ljones.dev Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 923b8e0c9efe..b29039131487 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7081,6 +7081,8 @@ enum { ALC285_FIXUP_SPEAKER2_TO_DAC1, ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, ALC285_FIXUP_ASUS_HEADSET_MIC, + ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_I2C_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -8073,6 +8075,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 }, + [ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC287_FIXUP_CS35L41_I2C_2 + }, + [ALC285_FIXUP_ASUS_I2C_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9598,6 +9616,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), From 2b248cf8b6dbb48b519b8dc3545ee9d89ed14b8f Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Tue, 4 Jul 2023 16:46:16 +1200 Subject: [PATCH 0386/2093] ALSA: hda/realtek: Add quirk for ASUS ROG GA402X [ Upstream commit 9abc77fb144fe916fd2f592dc4b8c7bade02e58a ] Adds the required quirk to enable the Cirrus amp and correct pins on the ASUS ROG GA402X series which uses an I2C connected Cirrus amp. While this works if the related _DSD properties are made available, these aren't included in the ACPI of these laptops (yet). Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20230704044619.19343-3-luke@ljones.dev Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b29039131487..b0cee0a361bf 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9617,6 +9617,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), From 6d06cf0f0238704531522bfae17fc3c8cacb2048 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Fri, 7 Jul 2023 10:33:23 +1200 Subject: [PATCH 0387/2093] ALSA: hda/realtek: Add quirk for ASUS ROG GZ301V [ Upstream commit 5251605f4d297a0eb5d3b7f39f9dcee9e4d0115a ] Adds the required quirk to enable the Cirrus amp and correct pins on the ASUS ROG GZ301V series which uses an SPI connected Cirrus amp. While this works if the related _DSD properties are made available, these aren't included in the ACPI of these laptops (yet). Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20230706223323.30871-2-luke@ljones.dev Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b0cee0a361bf..526ec8cae943 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9621,6 +9621,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), + SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), From a1ceb871284fb14d687091537e63818842c83c01 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Mon, 10 Jul 2023 14:41:43 +1000 Subject: [PATCH 0388/2093] powerpc/kasan: Disable KCOV in KASAN code [ Upstream commit ccb381e1af1ace292153c88eb1fffa5683d16a20 ] As per the generic KASAN code in mm/kasan, disable KCOV with KCOV_INSTRUMENT := n in the makefile. This fixes a ppc64 boot hang when KCOV and KASAN are enabled. kasan_early_init() gets called before a PACA is initialised, but the KCOV hook expects a valid PACA. Suggested-by: Christophe Leroy Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230710044143.146840-1-bgray@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/mm/kasan/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/mm/kasan/Makefile b/arch/powerpc/mm/kasan/Makefile index 699eeffd9f55..f9522fd70b2f 100644 --- a/arch/powerpc/mm/kasan/Makefile +++ b/arch/powerpc/mm/kasan/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 KASAN_SANITIZE := n +KCOV_INSTRUMENT := n obj-$(CONFIG_PPC32) += init_32.o obj-$(CONFIG_PPC_8xx) += 8xx.o From 356fe907dfcd2faa83ec990a487f259c247d2221 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 17 Jul 2023 12:32:14 +0300 Subject: [PATCH 0389/2093] Bluetooth: MGMT: Use correct address for memcpy() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d1f0a9816f5fbc1316355ec1aa4ddfb9b624cca5 ] In function ‘fortify_memcpy_chk’, inlined from ‘get_conn_info_complete’ at net/bluetooth/mgmt.c:7281:2: include/linux/fortify-string.h:592:25: error: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 592 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors This is due to the wrong member is used for memcpy(). Use correct one. Signed-off-by: Andy Shevchenko Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/mgmt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 89c94f3e96bc..d2e8565d0b33 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7277,7 +7277,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { From 128c06a34cfe55212632533a706b050d54552741 Mon Sep 17 00:00:00 2001 From: Chen Lin Date: Wed, 19 Jul 2023 15:58:47 +0800 Subject: [PATCH 0390/2093] ring-buffer: Do not swap cpu_buffer during resize process [ Upstream commit 8a96c0288d0737ad77882024974c075345c72011 ] When ring_buffer_swap_cpu was called during resize process, the cpu buffer was swapped in the middle, resulting in incorrect state. Continuing to run in the wrong state will result in oops. This issue can be easily reproduced using the following two scripts: /tmp # cat test1.sh //#! /bin/sh for i in `seq 0 100000` do echo 2000 > /sys/kernel/debug/tracing/buffer_size_kb sleep 0.5 echo 5000 > /sys/kernel/debug/tracing/buffer_size_kb sleep 0.5 done /tmp # cat test2.sh //#! /bin/sh for i in `seq 0 100000` do echo irqsoff > /sys/kernel/debug/tracing/current_tracer sleep 1 echo nop > /sys/kernel/debug/tracing/current_tracer sleep 1 done /tmp # ./test1.sh & /tmp # ./test2.sh & A typical oops log is as follows, sometimes with other different oops logs. [ 231.711293] WARNING: CPU: 0 PID: 9 at kernel/trace/ring_buffer.c:2026 rb_update_pages+0x378/0x3f8 [ 231.713375] Modules linked in: [ 231.714735] CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G W 6.5.0-rc1-00276-g20edcec23f92 #15 [ 231.716750] Hardware name: linux,dummy-virt (DT) [ 231.718152] Workqueue: events update_pages_handler [ 231.719714] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 231.721171] pc : rb_update_pages+0x378/0x3f8 [ 231.722212] lr : rb_update_pages+0x25c/0x3f8 [ 231.723248] sp : ffff800082b9bd50 [ 231.724169] x29: ffff800082b9bd50 x28: ffff8000825f7000 x27: 0000000000000000 [ 231.726102] x26: 0000000000000001 x25: fffffffffffff010 x24: 0000000000000ff0 [ 231.728122] x23: ffff0000c3a0b600 x22: ffff0000c3a0b5c0 x21: fffffffffffffe0a [ 231.730203] x20: ffff0000c3a0b600 x19: ffff0000c0102400 x18: 0000000000000000 [ 231.732329] x17: 0000000000000000 x16: 0000000000000000 x15: 0000ffffe7aa8510 [ 231.734212] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000002 [ 231.736291] x11: ffff8000826998a8 x10: ffff800082b9baf0 x9 : ffff800081137558 [ 231.738195] x8 : fffffc00030e82c8 x7 : 0000000000000000 x6 : 0000000000000001 [ 231.740192] x5 : ffff0000ffbafe00 x4 : 0000000000000000 x3 : 0000000000000000 [ 231.742118] x2 : 00000000000006aa x1 : 0000000000000001 x0 : ffff0000c0007208 [ 231.744196] Call trace: [ 231.744892] rb_update_pages+0x378/0x3f8 [ 231.745893] update_pages_handler+0x1c/0x38 [ 231.746893] process_one_work+0x1f0/0x468 [ 231.747852] worker_thread+0x54/0x410 [ 231.748737] kthread+0x124/0x138 [ 231.749549] ret_from_fork+0x10/0x20 [ 231.750434] ---[ end trace 0000000000000000 ]--- [ 233.720486] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 233.721696] Mem abort info: [ 233.721935] ESR = 0x0000000096000004 [ 233.722283] EC = 0x25: DABT (current EL), IL = 32 bits [ 233.722596] SET = 0, FnV = 0 [ 233.722805] EA = 0, S1PTW = 0 [ 233.723026] FSC = 0x04: level 0 translation fault [ 233.723458] Data abort info: [ 233.723734] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 233.724176] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 233.724589] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 233.725075] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000104943000 [ 233.725592] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 233.726231] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 233.726720] Modules linked in: [ 233.727007] CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G W 6.5.0-rc1-00276-g20edcec23f92 #15 [ 233.727777] Hardware name: linux,dummy-virt (DT) [ 233.728225] Workqueue: events update_pages_handler [ 233.728655] pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 233.729054] pc : rb_update_pages+0x1a8/0x3f8 [ 233.729334] lr : rb_update_pages+0x154/0x3f8 [ 233.729592] sp : ffff800082b9bd50 [ 233.729792] x29: ffff800082b9bd50 x28: ffff8000825f7000 x27: 0000000000000000 [ 233.730220] x26: 0000000000000000 x25: ffff800082a8b840 x24: ffff0000c0102418 [ 233.730653] x23: 0000000000000000 x22: fffffc000304c880 x21: 0000000000000003 [ 233.731105] x20: 00000000000001f4 x19: ffff0000c0102400 x18: ffff800082fcbc58 [ 233.731727] x17: 0000000000000000 x16: 0000000000000001 x15: 0000000000000001 [ 233.732282] x14: ffff8000825fe0c8 x13: 0000000000000001 x12: 0000000000000000 [ 233.732709] x11: ffff8000826998a8 x10: 0000000000000ae0 x9 : ffff8000801b760c [ 233.733148] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffff0000c03298c0 [ 233.733553] x5 : 0000000000000002 x4 : 0000000000000000 x3 : 0000000000000000 [ 233.733972] x2 : ffff0000c3a0b600 x1 : 0000000000000000 x0 : 0000000000000000 [ 233.734418] Call trace: [ 233.734593] rb_update_pages+0x1a8/0x3f8 [ 233.734853] update_pages_handler+0x1c/0x38 [ 233.735148] process_one_work+0x1f0/0x468 [ 233.735525] worker_thread+0x54/0x410 [ 233.735852] kthread+0x124/0x138 [ 233.736064] ret_from_fork+0x10/0x20 [ 233.736387] Code: 92400000 910006b5 aa000021 aa0303f7 (f9400060) [ 233.736959] ---[ end trace 0000000000000000 ]--- After analysis, the seq of the error is as follows [1-5]: int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, int cpu_id) { for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; //1. get cpu_buffer, aka cpu_buffer(A) ... ... schedule_work_on(cpu, &cpu_buffer->update_pages_work); //2. 'update_pages_work' is queue on 'cpu', cpu_buffer(A) is passed to // update_pages_handler, do the update process, set 'update_done' in // complete(&cpu_buffer->update_done) and to wakeup resize process. //----> //3. Just at this moment, ring_buffer_swap_cpu is triggered, //cpu_buffer(A) be swaped to cpu_buffer(B), the max_buffer. //ring_buffer_swap_cpu is called as the 'Call trace' below. Call trace: dump_backtrace+0x0/0x2f8 show_stack+0x18/0x28 dump_stack+0x12c/0x188 ring_buffer_swap_cpu+0x2f8/0x328 update_max_tr_single+0x180/0x210 check_critical_timing+0x2b4/0x2c8 tracer_hardirqs_on+0x1c0/0x200 trace_hardirqs_on+0xec/0x378 el0_svc_common+0x64/0x260 do_el0_svc+0x90/0xf8 el0_svc+0x20/0x30 el0_sync_handler+0xb0/0xb8 el0_sync+0x180/0x1c0 //<---- /* wait for all the updates to complete */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; //4. get cpu_buffer, cpu_buffer(B) is used in the following process, //the state of cpu_buffer(A) and cpu_buffer(B) is totally wrong. //for example, cpu_buffer(A)->update_done will leave be set 1, and will //not 'wait_for_completion' at the next resize round. if (!cpu_buffer->nr_pages_to_update) continue; if (cpu_online(cpu)) wait_for_completion(&cpu_buffer->update_done); cpu_buffer->nr_pages_to_update = 0; } ... } //5. the state of cpu_buffer(A) and cpu_buffer(B) is totally wrong, //Continuing to run in the wrong state, then oops occurs. Link: https://lore.kernel.org/linux-trace-kernel/202307191558478409990@zte.com.cn Signed-off-by: Chen Lin Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 14 +++++++++++++- kernel/trace/trace.c | 3 ++- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c49ed619a64d..de55107aef5d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -544,6 +544,7 @@ struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; + atomic_t resizing; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; @@ -2173,7 +2174,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); - + atomic_inc(&buffer->resizing); if (cpu_id == RING_BUFFER_ALL_CPUS) { /* @@ -2312,6 +2313,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, atomic_dec(&buffer->record_disabled); } + atomic_dec(&buffer->resizing); mutex_unlock(&buffer->mutex); return 0; @@ -2332,6 +2334,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, } } out_err_unlock: + atomic_dec(&buffer->resizing); mutex_unlock(&buffer->mutex); return err; } @@ -5539,6 +5542,15 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, if (local_read(&cpu_buffer_b->committing)) goto out_dec; + /* + * When resize is in progress, we cannot swap it because + * it will mess the state of the cpu buffer. + */ + if (atomic_read(&buffer_a->resizing)) + goto out_dec; + if (atomic_read(&buffer_b->resizing)) + goto out_dec; + buffer_a->buffers[cpu] = cpu_buffer_b; buffer_b->buffers[cpu] = cpu_buffer_a; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 709af9631be4..af33c5a4166d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1885,9 +1885,10 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * place on this CPU. We fail to record, but we reset * the max trace buffer (no one writes directly to it) * and flag that it failed. + * Another reason is resize is in progress. */ trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, - "Failed to swap buffers due to commit in progress\n"); + "Failed to swap buffers due to commit or resize in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); From 48f0671be2816676b87506b7eae2a7cc47291436 Mon Sep 17 00:00:00 2001 From: Song Yoong Siang Date: Tue, 2 May 2023 08:48:06 -0700 Subject: [PATCH 0391/2093] igc: read before write to SRRCTL register [ Upstream commit 3ce29c17dc847bf4245e16aad78a7617afa96297 ] igc_configure_rx_ring() function will be called as part of XDP program setup. If Rx hardware timestamp is enabled prio to XDP program setup, this timestamp enablement will be overwritten when buffer size is written into SRRCTL register. Thus, this commit read the register value before write to SRRCTL register. This commit is tested by using xdp_hw_metadata bpf selftest tool. The tool enables Rx hardware timestamp and then attach XDP program to igc driver. It will display hardware timestamp of UDP packet with port number 9092. Below are detail of test steps and results. Command on DUT: sudo ./xdp_hw_metadata Command on Link Partner: echo -n skb | nc -u -q1 9092 Result before this patch: skb hwtstamp is not found! Result after this patch: found skb hwtstamp = 1677800973.642836757 Optionally, read PHC to confirm the values obtained are almost the same: Command: sudo ./testptp -d /dev/ptp0 -g Result: clock time: 1677800973.913598978 or Fri Mar 3 07:49:33 2023 Fixes: fc9df2a0b520 ("igc: Enable RX via AF_XDP zero-copy") Cc: # 5.14+ Signed-off-by: Song Yoong Siang Reviewed-by: Jacob Keller Reviewed-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Naama Meir Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_base.h | 11 ++++++++--- drivers/net/ethernet/intel/igc/igc_main.c | 7 +++++-- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index ce530f5fd7bd..52849f5e8048 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -85,8 +85,13 @@ union igc_adv_rx_desc { #define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ /* SRRCTL bit definitions */ -#define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ -#define IGC_SRRCTL_BSIZEHDRSIZE_SHIFT 2 /* Shift _left_ */ -#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define IGC_SRRCTL_BSIZEPKT_MASK GENMASK(6, 0) +#define IGC_SRRCTL_BSIZEPKT(x) FIELD_PREP(IGC_SRRCTL_BSIZEPKT_MASK, \ + (x) / 1024) /* in 1 KB resolution */ +#define IGC_SRRCTL_BSIZEHDR_MASK GENMASK(13, 8) +#define IGC_SRRCTL_BSIZEHDR(x) FIELD_PREP(IGC_SRRCTL_BSIZEHDR_MASK, \ + (x) / 64) /* in 64 bytes resolution */ +#define IGC_SRRCTL_DESCTYPE_MASK GENMASK(27, 25) +#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF FIELD_PREP(IGC_SRRCTL_DESCTYPE_MASK, 1) #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index d877dc0f87f7..2f3947cf513b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -675,8 +675,11 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, else buf_size = IGC_RXBUFFER_2048; - srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT; + srrctl = rd32(IGC_SRRCTL(reg_idx)); + srrctl &= ~(IGC_SRRCTL_BSIZEPKT_MASK | IGC_SRRCTL_BSIZEHDR_MASK | + IGC_SRRCTL_DESCTYPE_MASK); + srrctl |= IGC_SRRCTL_BSIZEHDR(IGC_RX_HDR_LEN); + srrctl |= IGC_SRRCTL_BSIZEPKT(buf_size); srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF; wr32(IGC_SRRCTL(reg_idx), srrctl); From d90f97cb3821c47bdf773dcf6cade143773ec764 Mon Sep 17 00:00:00 2001 From: hersen wu Date: Tue, 15 Nov 2022 10:39:55 -0500 Subject: [PATCH 0392/2093] drm/amd/display: save restore hdcp state when display is unplugged from mst hub [ Upstream commit 82986fd631fa04bcedaefe11a6b3767601cbe84f ] [Why] connector hdcp properties are lost after display is unplgged from mst hub. connector is destroyed with dm_dp_mst_connector_destroy. when display is plugged back, hdcp is not desired and it wouldnt be enabled. [How] save hdcp properties into hdcp_work within amdgpu_dm_atomic_commit_tail. If the same display is plugged back with same display index, its hdcp properties will be retrieved from hdcp_work within dm_dp_mst_get_modes. Acked-by: Aurabindo Pillai Signed-off-by: hersen wu Reviewed-by: Bhawanpreet Lakha Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Stable-dep-of: cdff36a0217a ("drm/amd/display: fix access hdcp_workqueue assert") Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 ++++++++++++++++- .../amd/display/amdgpu_dm/amdgpu_dm_hdcp.h | 14 ++++++++++ .../display/amdgpu_dm/amdgpu_dm_mst_types.c | 26 +++++++++++++++++++ 3 files changed, 63 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9f718b98da1f..bdc6f90b3adb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8350,11 +8350,33 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) continue; } - if (is_content_protection_different(new_con_state, old_con_state, connector, adev->dm.hdcp_workqueue)) + if (is_content_protection_different(new_con_state, old_con_state, connector, adev->dm.hdcp_workqueue)) { + /* when display is unplugged from mst hub, connctor will + * be destroyed within dm_dp_mst_connector_destroy. connector + * hdcp perperties, like type, undesired, desired, enabled, + * will be lost. So, save hdcp properties into hdcp_work within + * amdgpu_dm_atomic_commit_tail. if the same display is + * plugged back with same display index, its hdcp properties + * will be retrieved from hdcp_work within dm_dp_mst_get_modes + */ + + if (aconnector->dc_link && aconnector->dc_sink && + aconnector->dc_link->type == dc_connection_mst_branch) { + struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; + struct hdcp_workqueue *hdcp_w = + &hdcp_work[aconnector->dc_link->link_index]; + + hdcp_w->hdcp_content_type[connector->index] = + new_con_state->hdcp_content_type; + hdcp_w->content_protection[connector->index] = + new_con_state->content_protection; + } + hdcp_update_display( adev->dm.hdcp_workqueue, aconnector->dc_link->link_index, aconnector, new_con_state->hdcp_content_type, new_con_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED); + } } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h index 09294ff122fe..bbbf7d0eff82 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h @@ -52,6 +52,20 @@ struct hdcp_workqueue { struct mod_hdcp_link link; enum mod_hdcp_encryption_status encryption_status; + + /* when display is unplugged from mst hub, connctor will be + * destroyed within dm_dp_mst_connector_destroy. connector + * hdcp perperties, like type, undesired, desired, enabled, + * will be lost. So, save hdcp properties into hdcp_work within + * amdgpu_dm_atomic_commit_tail. if the same display is + * plugged back with same display index, its hdcp properties + * will be retrieved from hdcp_work within dm_dp_mst_get_modes + */ + /* un-desired, desired, enabled */ + unsigned int content_protection[AMDGPU_DM_MAX_DISPLAY_INDEX]; + /* hdcp1.x, hdcp2.x */ + unsigned int hdcp_content_type[AMDGPU_DM_MAX_DISPLAY_INDEX]; + uint8_t max_link; uint8_t *srm; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index d07e1053b36b..9884dd78c652 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -32,6 +32,10 @@ #include "amdgpu_dm.h" #include "amdgpu_dm_mst_types.h" +#ifdef CONFIG_DRM_AMD_DC_HDCP +#include "amdgpu_dm_hdcp.h" +#endif + #include "dc.h" #include "dm_helpers.h" @@ -363,6 +367,28 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) /* dc_link_add_remote_sink returns a new reference */ aconnector->dc_sink = dc_sink; + /* when display is unplugged from mst hub, connctor will be + * destroyed within dm_dp_mst_connector_destroy. connector + * hdcp perperties, like type, undesired, desired, enabled, + * will be lost. So, save hdcp properties into hdcp_work within + * amdgpu_dm_atomic_commit_tail. if the same display is + * plugged back with same display index, its hdcp properties + * will be retrieved from hdcp_work within dm_dp_mst_get_modes + */ +#ifdef CONFIG_DRM_AMD_DC_HDCP + if (aconnector->dc_sink && connector->state) { + struct drm_device *dev = connector->dev; + struct amdgpu_device *adev = drm_to_adev(dev); + struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; + struct hdcp_workqueue *hdcp_w = &hdcp_work[aconnector->dc_link->link_index]; + + connector->state->hdcp_content_type = + hdcp_w->hdcp_content_type[connector->index]; + connector->state->content_protection = + hdcp_w->content_protection[connector->index]; + } +#endif + if (aconnector->dc_sink) { amdgpu_dm_update_freesync_caps( connector, aconnector->edid); From 81e6cf447a2e3affcf54928c01b2476bca28916b Mon Sep 17 00:00:00 2001 From: hersen wu Date: Tue, 15 Nov 2022 14:20:56 -0500 Subject: [PATCH 0393/2093] drm/amd/display: phase3 mst hdcp for multiple displays [ Upstream commit e8fd3eeb5e8711af39b00642da06474e52f4780c ] [Why] multiple display hdcp are enabled within event_property_validate, event_property_update by looping all displays on mst hub. when one of display on mst hub in unplugged or disabled, hdcp are disabled for all displays on mst hub within hdcp_reset_display by looping all displays of mst link. for displays still active, their encryption status are off. kernel driver will not run hdcp authentication again. therefore, hdcp are not enabled automatically. [How] within is_content_protection_different, check drm_crtc_state changes of all displays on mst hub, if need, triger hdcp_update_display to re-run hdcp authentication. Acked-by: Aurabindo Pillai Signed-off-by: hersen wu Reviewed-by: Bhawanpreet Lakha Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Stable-dep-of: cdff36a0217a ("drm/amd/display: fix access hdcp_workqueue assert") Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 185 ++++++++++++++---- 1 file changed, 142 insertions(+), 43 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index bdc6f90b3adb..aa0ea28a86f0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7397,27 +7397,55 @@ is_scaling_state_different(const struct dm_connector_state *dm_state, } #ifdef CONFIG_DRM_AMD_DC_HDCP -static bool is_content_protection_different(struct drm_connector_state *state, - const struct drm_connector_state *old_state, - const struct drm_connector *connector, struct hdcp_workqueue *hdcp_w) +static bool is_content_protection_different(struct drm_crtc_state *new_crtc_state, + struct drm_crtc_state *old_crtc_state, + struct drm_connector_state *new_conn_state, + struct drm_connector_state *old_conn_state, + const struct drm_connector *connector, + struct hdcp_workqueue *hdcp_w) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); struct dm_connector_state *dm_con_state = to_dm_connector_state(connector->state); - /* Handle: Type0/1 change */ - if (old_state->hdcp_content_type != state->hdcp_content_type && - state->content_protection != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { - state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; + pr_debug("[HDCP_DM] connector->index: %x connect_status: %x dpms: %x\n", + connector->index, connector->status, connector->dpms); + pr_debug("[HDCP_DM] state protection old: %x new: %x\n", + old_conn_state->content_protection, new_conn_state->content_protection); + + if (old_crtc_state) + pr_debug("[HDCP_DM] old crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n", + old_crtc_state->enable, + old_crtc_state->active, + old_crtc_state->mode_changed, + old_crtc_state->active_changed, + old_crtc_state->connectors_changed); + + if (new_crtc_state) + pr_debug("[HDCP_DM] NEW crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n", + new_crtc_state->enable, + new_crtc_state->active, + new_crtc_state->mode_changed, + new_crtc_state->active_changed, + new_crtc_state->connectors_changed); + + /* hdcp content type change */ + if (old_conn_state->hdcp_content_type != new_conn_state->hdcp_content_type && + new_conn_state->content_protection != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) { + new_conn_state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; + pr_debug("[HDCP_DM] Type0/1 change %s :true\n", __func__); return true; } - /* CP is being re enabled, ignore this - * - * Handles: ENABLED -> DESIRED - */ - if (old_state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED && - state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) { - state->content_protection = DRM_MODE_CONTENT_PROTECTION_ENABLED; + /* CP is being re enabled, ignore this */ + if (old_conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED && + new_conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) { + if (new_crtc_state && new_crtc_state->mode_changed) { + new_conn_state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; + pr_debug("[HDCP_DM] ENABLED->DESIRED & mode_changed %s :true\n", __func__); + return true; + }; + new_conn_state->content_protection = DRM_MODE_CONTENT_PROTECTION_ENABLED; + pr_debug("[HDCP_DM] ENABLED -> DESIRED %s :false\n", __func__); return false; } @@ -7425,9 +7453,9 @@ static bool is_content_protection_different(struct drm_connector_state *state, * * Handles: UNDESIRED -> ENABLED */ - if (old_state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED && - state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED) - state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; + if (old_conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED && + new_conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED) + new_conn_state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; /* Stream removed and re-enabled * @@ -7437,10 +7465,12 @@ static bool is_content_protection_different(struct drm_connector_state *state, * * Handles: DESIRED -> DESIRED (Special case) */ - if (!(old_state->crtc && old_state->crtc->enabled) && - state->crtc && state->crtc->enabled && + if (!(old_conn_state->crtc && old_conn_state->crtc->enabled) && + new_conn_state->crtc && new_conn_state->crtc->enabled && connector->state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) { dm_con_state->update_hdcp = false; + pr_debug("[HDCP_DM] DESIRED->DESIRED (Stream removed and re-enabled) %s :true\n", + __func__); return true; } @@ -7452,35 +7482,42 @@ static bool is_content_protection_different(struct drm_connector_state *state, * * Handles: DESIRED -> DESIRED (Special case) */ - if (dm_con_state->update_hdcp && state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED && - connector->dpms == DRM_MODE_DPMS_ON && aconnector->dc_sink != NULL) { + if (dm_con_state->update_hdcp && + new_conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED && + connector->dpms == DRM_MODE_DPMS_ON && aconnector->dc_sink != NULL) { dm_con_state->update_hdcp = false; + pr_debug("[HDCP_DM] DESIRED->DESIRED (Hot-plug, headless s3, dpms) %s :true\n", + __func__); return true; } - /* - * Handles: UNDESIRED -> UNDESIRED - * DESIRED -> DESIRED - * ENABLED -> ENABLED - */ - if (old_state->content_protection == state->content_protection) + if (old_conn_state->content_protection == new_conn_state->content_protection) { + if (new_conn_state->content_protection >= DRM_MODE_CONTENT_PROTECTION_DESIRED) { + if (new_crtc_state && new_crtc_state->mode_changed) { + pr_debug("[HDCP_DM] DESIRED->DESIRED or ENABLE->ENABLE mode_change %s :true\n", + __func__); + return true; + }; + pr_debug("[HDCP_DM] DESIRED->DESIRED & ENABLE->ENABLE %s :false\n", + __func__); + return false; + }; + + pr_debug("[HDCP_DM] UNDESIRED->UNDESIRED %s :false\n", __func__); return false; + } - /* - * Handles: UNDESIRED -> DESIRED - * DESIRED -> UNDESIRED - * ENABLED -> UNDESIRED - */ - if (state->content_protection != DRM_MODE_CONTENT_PROTECTION_ENABLED) + if (new_conn_state->content_protection != DRM_MODE_CONTENT_PROTECTION_ENABLED) { + pr_debug("[HDCP_DM] UNDESIRED->DESIRED or DESIRED->UNDESIRED or ENABLED->UNDESIRED %s :true\n", + __func__); return true; + } - /* - * Handles: DESIRED -> ENABLED - */ + pr_debug("[HDCP_DM] DESIRED->ENABLED %s :false\n", __func__); return false; } - #endif + static void remove_stream(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dc_stream_state *stream) @@ -8335,10 +8372,61 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - new_crtc_state = NULL; + pr_debug("[HDCP_DM] -------------- i : %x ----------\n", i); - if (acrtc) + if (!connector) + continue; + + pr_debug("[HDCP_DM] connector->index: %x connect_status: %x dpms: %x\n", + connector->index, connector->status, connector->dpms); + pr_debug("[HDCP_DM] state protection old: %x new: %x\n", + old_con_state->content_protection, new_con_state->content_protection); + + if (aconnector->dc_sink) { + if (aconnector->dc_sink->sink_signal != SIGNAL_TYPE_VIRTUAL && + aconnector->dc_sink->sink_signal != SIGNAL_TYPE_NONE) { + pr_debug("[HDCP_DM] pipe_ctx dispname=%s\n", + aconnector->dc_sink->edid_caps.display_name); + } + } + + new_crtc_state = NULL; + old_crtc_state = NULL; + + if (acrtc) { new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base); + old_crtc_state = drm_atomic_get_old_crtc_state(state, &acrtc->base); + } + + if (old_crtc_state) + pr_debug("old crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n", + old_crtc_state->enable, + old_crtc_state->active, + old_crtc_state->mode_changed, + old_crtc_state->active_changed, + old_crtc_state->connectors_changed); + + if (new_crtc_state) + pr_debug("NEW crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n", + new_crtc_state->enable, + new_crtc_state->active, + new_crtc_state->mode_changed, + new_crtc_state->active_changed, + new_crtc_state->connectors_changed); + } + + for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) { + struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state); + struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + new_crtc_state = NULL; + old_crtc_state = NULL; + + if (acrtc) { + new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base); + old_crtc_state = drm_atomic_get_old_crtc_state(state, &acrtc->base); + } dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); @@ -8350,7 +8438,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) continue; } - if (is_content_protection_different(new_con_state, old_con_state, connector, adev->dm.hdcp_workqueue)) { + if (is_content_protection_different(new_crtc_state, old_crtc_state, new_con_state, + old_con_state, connector, adev->dm.hdcp_workqueue)) { /* when display is unplugged from mst hub, connctor will * be destroyed within dm_dp_mst_connector_destroy. connector * hdcp perperties, like type, undesired, desired, enabled, @@ -8360,6 +8449,11 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) * will be retrieved from hdcp_work within dm_dp_mst_get_modes */ + bool enable_encryption = false; + + if (new_con_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) + enable_encryption = true; + if (aconnector->dc_link && aconnector->dc_sink && aconnector->dc_link->type == dc_connection_mst_branch) { struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; @@ -8372,11 +8466,16 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) new_con_state->content_protection; } + if (new_crtc_state && new_crtc_state->mode_changed && + new_con_state->content_protection >= DRM_MODE_CONTENT_PROTECTION_DESIRED) + enable_encryption = true; + + DRM_INFO("[HDCP_DM] hdcp_update_display enable_encryption = %x\n", enable_encryption); + hdcp_update_display( adev->dm.hdcp_workqueue, aconnector->dc_link->link_index, aconnector, - new_con_state->hdcp_content_type, - new_con_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED); - } + new_con_state->hdcp_content_type, enable_encryption); + } } #endif From 402f1d86ea26c160841da4eb46b0ad8606ab52b3 Mon Sep 17 00:00:00 2001 From: Hersen Wu Date: Tue, 28 Mar 2023 10:45:24 -0400 Subject: [PATCH 0394/2093] drm/amd/display: fix access hdcp_workqueue assert [ Upstream commit cdff36a0217aadf5cbc167893ad1c0da869619cb ] [Why] hdcp are enabled for asics from raven. for old asics which hdcp are not enabled, hdcp_workqueue are null. some access to hdcp work queue are not guarded with pointer check. [How] add hdcp_workqueue pointer check before access workqueue. Reviewed-by: Bhawanpreet Lakha Acked-by: Qingqing Zhuo Signed-off-by: Hersen Wu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 ++++++ .../amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 16 ++++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index aa0ea28a86f0..249b269e2cc5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8372,6 +8372,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + if (!adev->dm.hdcp_workqueue) + continue; + pr_debug("[HDCP_DM] -------------- i : %x ----------\n", i); if (!connector) @@ -8420,6 +8423,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + if (!adev->dm.hdcp_workqueue) + continue; + new_crtc_state = NULL; old_crtc_state = NULL; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 9884dd78c652..a9ddff774a97 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -379,13 +379,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) if (aconnector->dc_sink && connector->state) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = drm_to_adev(dev); - struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; - struct hdcp_workqueue *hdcp_w = &hdcp_work[aconnector->dc_link->link_index]; - connector->state->hdcp_content_type = - hdcp_w->hdcp_content_type[connector->index]; - connector->state->content_protection = - hdcp_w->content_protection[connector->index]; + if (adev->dm.hdcp_workqueue) { + struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; + struct hdcp_workqueue *hdcp_w = + &hdcp_work[aconnector->dc_link->link_index]; + + connector->state->hdcp_content_type = + hdcp_w->hdcp_content_type[connector->index]; + connector->state->content_protection = + hdcp_w->content_protection[connector->index]; + } } #endif From 3d2d051be16115ca930cd2b76b18e54532bf56cd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 13 Jul 2023 08:06:57 +0100 Subject: [PATCH 0395/2093] KVM: arm64: vgic-v4: Make the doorbell request robust w.r.t preemption [ Upstream commit b321c31c9b7b309dcde5e8854b741c8e6a9a05f0 ] Xiang reports that VMs occasionally fail to boot on GICv4.1 systems when running a preemptible kernel, as it is possible that a vCPU is blocked without requesting a doorbell interrupt. The issue is that any preemption that occurs between vgic_v4_put() and schedule() on the block path will mark the vPE as nonresident and *not* request a doorbell irq. This occurs because when the vcpu thread is resumed on its way to block, vcpu_load() will make the vPE resident again. Once the vcpu actually blocks, we don't request a doorbell anymore, and the vcpu won't be woken up on interrupt delivery. Fix it by tracking that we're entering WFI, and key the doorbell request on that flag. This allows us not to make the vPE resident when going through a preempt/schedule cycle, meaning we don't lose any state. Cc: stable@vger.kernel.org Fixes: 8e01d9a396e6 ("KVM: arm64: vgic-v4: Move the GICv4 residency flow to be driven by vcpu_load/put") Reported-by: Xiang Chen Suggested-by: Zenghui Yu Tested-by: Xiang Chen Co-developed-by: Oliver Upton Signed-off-by: Marc Zyngier Acked-by: Zenghui Yu Link: https://lore.kernel.org/r/20230713070657.3873244-1-maz@kernel.org Signed-off-by: Oliver Upton Signed-off-by: Sasha Levin --- arch/arm64/include/asm/kvm_host.h | 2 ++ arch/arm64/kvm/arm.c | 6 ++++-- arch/arm64/kvm/vgic/vgic-v3.c | 2 +- arch/arm64/kvm/vgic/vgic-v4.c | 7 +++++-- include/kvm/arm_vgic.h | 2 +- 5 files changed, 13 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b5a8e8b3c691..577cf444c113 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -559,6 +559,8 @@ struct kvm_vcpu_arch { #define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(4)) /* Software step state is Active-pending */ #define DBG_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(5)) +/* WFI instruction trapped */ +#define IN_WFI __vcpu_single_flag(sflags, BIT(7)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 35481d51aada..6cc380a15eb7 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -692,13 +692,15 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) */ preempt_disable(); kvm_vgic_vmcr_sync(vcpu); - vgic_v4_put(vcpu, true); + vcpu_set_flag(vcpu, IN_WFI); + vgic_v4_put(vcpu); preempt_enable(); kvm_vcpu_halt(vcpu); vcpu_clear_flag(vcpu, IN_WFIT); preempt_disable(); + vcpu_clear_flag(vcpu, IN_WFI); vgic_v4_load(vcpu); preempt_enable(); } @@ -766,7 +768,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { /* The distributor enable bits were changed */ preempt_disable(); - vgic_v4_put(vcpu, false); + vgic_v4_put(vcpu); vgic_v4_load(vcpu); preempt_enable(); } diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index f86c3007a319..1f8eea53e982 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -742,7 +742,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - WARN_ON(vgic_v4_put(vcpu, false)); + WARN_ON(vgic_v4_put(vcpu)); vgic_v3_vmcr_sync(vcpu); diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index c1c28fe680ba..339a55194b2c 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -336,14 +336,14 @@ void vgic_v4_teardown(struct kvm *kvm) its_vm->vpes = NULL; } -int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) +int vgic_v4_put(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; - return its_make_vpe_non_resident(vpe, need_db); + return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI)); } int vgic_v4_load(struct kvm_vcpu *vcpu) @@ -354,6 +354,9 @@ int vgic_v4_load(struct kvm_vcpu *vcpu) if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; + if (vcpu_get_flag(vcpu, IN_WFI)) + return 0; + /* * Before making the VPE resident, make sure the redistributor * corresponding to our current CPU expects us here. See the diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 4df9e73a8bb5..1d7d4cffaefc 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -429,6 +429,6 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); -int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); +int vgic_v4_put(struct kvm_vcpu *vcpu); #endif /* __KVM_ARM_VGIC_H */ From e41170d128e67cedbbd564e0e03c1a44fdb9d7ce Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Mon, 17 Jul 2023 10:28:33 +0800 Subject: [PATCH 0396/2093] ARM: dts: nxp/imx6sll: fix wrong property name in usbphy node [ Upstream commit ee70b908f77a9d8f689dea986f09e6d7dc481934 ] Property name "phy-3p0-supply" is used instead of "phy-reg_3p0-supply". Fixes: 9f30b6b1a957 ("ARM: dts: imx: Add basic dtsi file for imx6sll") cc: Signed-off-by: Xu Yang Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6sll.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi index 2873369a57c0..3659fd5ecfa6 100644 --- a/arch/arm/boot/dts/imx6sll.dtsi +++ b/arch/arm/boot/dts/imx6sll.dtsi @@ -552,7 +552,7 @@ usbphy2: usb-phy@20ca000 { reg = <0x020ca000 0x1000>; interrupts = ; clocks = <&clks IMX6SLL_CLK_USBPHY2>; - phy-reg_3p0-supply = <®_3p0>; + phy-3p0-supply = <®_3p0>; fsl,anatop = <&anatop>; }; From f83ab817effbc5f02b923960876cdeb2df46c443 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 19 Dec 2022 17:05:06 +0100 Subject: [PATCH 0397/2093] fbdev/hyperv-fb: Do not set struct fb_info.apertures [ Upstream commit 81d2393485f0990cf6566b0c9e0697c199f68ae5 ] Generic fbdev drivers use the apertures field in struct fb_info to control ownership of the framebuffer memory and graphics device. Do not set the values in hyperv-fb. Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Reviewed-by: Michael Kelley Link: https://patchwork.freedesktop.org/patch/msgid/20221219160516.23436-9-tzimmermann@suse.de Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/video/fbdev/hyperv_fb.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 4ff25dfc865d..d3d643cf7506 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -995,13 +995,10 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) struct pci_dev *pdev = NULL; void __iomem *fb_virt; int gen2vm = efi_enabled(EFI_BOOT); + resource_size_t base, size; phys_addr_t paddr; int ret; - info->apertures = alloc_apertures(1); - if (!info->apertures) - return -ENOMEM; - if (!gen2vm) { pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT, PCI_DEVICE_ID_HYPERV_VIDEO, NULL); @@ -1010,8 +1007,8 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) return -ENODEV; } - info->apertures->ranges[0].base = pci_resource_start(pdev, 0); - info->apertures->ranges[0].size = pci_resource_len(pdev, 0); + base = pci_resource_start(pdev, 0); + size = pci_resource_len(pdev, 0); /* * For Gen 1 VM, we can directly use the contiguous memory @@ -1034,8 +1031,8 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) } pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n"); } else { - info->apertures->ranges[0].base = screen_info.lfb_base; - info->apertures->ranges[0].size = screen_info.lfb_size; + base = screen_info.lfb_base; + size = screen_info.lfb_size; } /* @@ -1077,9 +1074,7 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) info->screen_size = dio_fb_size; getmem_done: - aperture_remove_conflicting_devices(info->apertures->ranges[0].base, - info->apertures->ranges[0].size, - false, KBUILD_MODNAME); + aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); if (gen2vm) { /* framebuffer is reallocated, clear screen_info to avoid misuse from kexec */ From 485ec8f8e1d8ae12aa1daa5ad345ba8940ad2db7 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 6 Apr 2023 15:21:07 +0200 Subject: [PATCH 0398/2093] video/aperture: Only remove sysfb on the default vga pci device [ Upstream commit 5ae3716cfdcd286268133867f67d0803847acefc ] Instead of calling aperture_remove_conflicting_devices() to remove the conflicting devices, just call to aperture_detach_devices() to detach the device that matches the same PCI BAR / aperture range. Since the former is just a wrapper of the latter plus a sysfb_disable() call, and now that's done in this function but only for the primary devices. This fixes a regression introduced by commit ee7a69aa38d8 ("fbdev: Disable sysfb device registration when removing conflicting FBs"), where we remove the sysfb when loading a driver for an unrelated pci device, resulting in the user losing their efifb console or similar. Note that in practice this only is a problem with the nvidia blob, because that's the only gpu driver people might install which does not come with an fbdev driver of it's own. For everyone else the real gpu driver will restore a working console. Also note that in the referenced bug there's confusion that this same bug also happens on amdgpu. But that was just another amdgpu specific regression, which just happened to happen at roughly the same time and with the same user-observable symptoms. That bug is fixed now, see https://bugzilla.kernel.org/show_bug.cgi?id=216331#c15 Note that we should not have any such issues on non-pci multi-gpu issues, because I could only find two such cases: - SoC with some external panel over spi or similar. These panel drivers do not use drm_aperture_remove_conflicting_framebuffers(), so no problem. - vga+mga, which is a direct console driver and entirely bypasses all this. For the above reasons the cc: stable is just notionally, this patch will need a backport and that's up to nvidia if they care enough. v2: - Explain a bit better why other multi-gpu that aren't pci shouldn't have any issues with making all this fully pci specific. v3 - polish commit message (Javier) v4: - Fix commit message style (i.e., commit 1234 ("...")) - fix Daniel's S-o-b address v5: - add back an S-o-b tag with Daniel's Intel address Fixes: ee7a69aa38d8 ("fbdev: Disable sysfb device registration when removing conflicting FBs") Tested-by: Aaron Plattner Reviewed-by: Javier Martinez Canillas Link: https://bugzilla.kernel.org/show_bug.cgi?id=216303#c28 Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Thomas Zimmermann Cc: Aaron Plattner Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Cc: Helge Deller Cc: Sam Ravnborg Cc: Alex Deucher Cc: # v5.19+ (if someone else does the backport) Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-8-tzimmermann@suse.de Signed-off-by: Sasha Levin --- drivers/video/aperture.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 41e77de1ea82..5c94abdb1ad6 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -332,15 +332,16 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; #endif + if (primary) + sysfb_disable(); + for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; base = pci_resource_start(pdev, bar); size = pci_resource_len(pdev, bar); - ret = aperture_remove_conflicting_devices(base, size, primary, name); - if (ret) - return ret; + aperture_detach_devices(base, size); } /* From 01eca70ef8cf499d0cb6d1bbd691558e7792cf17 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 6 Jun 2023 14:36:34 +0900 Subject: [PATCH 0399/2093] btrfs: move out now unused BG from the reclaim list [ Upstream commit a9f189716cf15913c453299d72f69c51a9b0f86b ] An unused block group is easy to remove to free up space and should be reclaimed fast. Such block group can often already be a target of the reclaim process. As we check list_empty(&bg->bg_list), we keep it in the reclaim list. That block group is never reclaimed until the file system is filled e.g. up to 75%. Instead, we can move unused block group to the unused list and delete it fast. Fixes: 18bb8bbf13c1 ("btrfs: zoned: automatically reclaim zones") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Filipe Manana Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/block-group.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 3495bc775afa..9f5a971bfed4 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1528,11 +1528,14 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; + trace_btrfs_add_unused_block_group(bg); spin_lock(&fs_info->unused_bgs_lock); if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); - trace_btrfs_add_unused_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->unused_bgs); + } else { + /* Pull out the block group from the reclaim_bgs list. */ + list_move_tail(&bg->bg_list, &fs_info->unused_bgs); } spin_unlock(&fs_info->unused_bgs_lock); } From 94cde94169f0770c40cbe7c3f8685c9a61bc4c83 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 31 Oct 2022 20:33:44 +0100 Subject: [PATCH 0400/2093] btrfs: convert btrfs_block_group::needs_free_space to runtime flag [ Upstream commit 0d7764ff58b4b45c39eb03f2c74a819c1a88fa7b ] We already have flags in block group to track various status bits, convert needs_free_space as well and reduce size of btrfs_block_group. Reviewed-by: Anand Jain Signed-off-by: David Sterba Stable-dep-of: 0657b20c5a76 ("btrfs: fix use-after-free of new block group that became unused") Signed-off-by: Sasha Levin --- fs/btrfs/block-group.c | 2 +- fs/btrfs/block-group.h | 8 ++------ fs/btrfs/free-space-tree.c | 10 +++++----- fs/btrfs/tests/free-space-tree-tests.c | 2 +- 4 files changed, 9 insertions(+), 13 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9f5a971bfed4..a726b532b527 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2543,7 +2543,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran cache->global_root_id = calculate_global_root_id(fs_info, cache->start); if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) - cache->needs_free_space = 1; + set_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &cache->runtime_flags); ret = btrfs_load_block_group_zone_info(cache, true); if (ret) { diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index debd42aeae0f..dcad5e959b92 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -55,6 +55,8 @@ enum btrfs_block_group_flags { BLOCK_GROUP_FLAG_CHUNK_ITEM_INSERTED, BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, + /* Does the block group need to be added to the free space tree? */ + BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, }; enum btrfs_caching_type { @@ -204,12 +206,6 @@ struct btrfs_block_group { /* Lock for free space tree operations. */ struct mutex free_space_lock; - /* - * Does the block group need to be added to the free space tree? - * Protected by free_space_lock. - */ - int needs_free_space; - /* Flag indicating this block group is placed on a sequential zone */ bool seq_zone; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index a207db932226..6a44733a95e1 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -803,7 +803,7 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, u32 flags; int ret; - if (block_group->needs_free_space) { + if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; @@ -996,7 +996,7 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans, u32 flags; int ret; - if (block_group->needs_free_space) { + if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; @@ -1350,7 +1350,7 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans, { int ret; - block_group->needs_free_space = 0; + clear_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags); ret = add_new_free_space_info(trans, block_group, path); if (ret) @@ -1372,7 +1372,7 @@ int add_block_group_free_space(struct btrfs_trans_handle *trans, return 0; mutex_lock(&block_group->free_space_lock); - if (!block_group->needs_free_space) + if (!test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) goto out; path = btrfs_alloc_path(); @@ -1405,7 +1405,7 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans, if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; - if (block_group->needs_free_space) { + if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { /* We never added this block group to the free space tree. */ return 0; } diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 13734ed43bfc..766117a76d74 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -470,7 +470,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, } cache->bitmap_low_thresh = 0; cache->bitmap_high_thresh = (u32)-1; - cache->needs_free_space = 1; + set_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &cache->runtime_flags); cache->fs_info = root->fs_info; btrfs_init_dummy_trans(&trans, root->fs_info); From 29cebf80877ba55ec63c666e6a06f241f62fcfa5 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 31 Oct 2022 20:33:46 +0100 Subject: [PATCH 0401/2093] btrfs: convert btrfs_block_group::seq_zone to runtime flag [ Upstream commit 961f5b8bf48a463ac5fe5b13143426d79eb41817 ] In zoned mode the sequential status of zone can be also tracked in the runtime flags of block group. Reviewed-by: Anand Jain Signed-off-by: David Sterba Stable-dep-of: 0657b20c5a76 ("btrfs: fix use-after-free of new block group that became unused") Signed-off-by: Sasha Levin --- fs/btrfs/block-group.h | 5 ++--- fs/btrfs/zoned.c | 7 ++++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index dcad5e959b92..fb4f4901350b 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -57,6 +57,8 @@ enum btrfs_block_group_flags { BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, /* Does the block group need to be added to the free space tree? */ BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, + /* Indicate that the block group is placed on a sequential zone */ + BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, }; enum btrfs_caching_type { @@ -206,9 +208,6 @@ struct btrfs_block_group { /* Lock for free space tree operations. */ struct mutex free_space_lock; - /* Flag indicating this block group is placed on a sequential zone */ - bool seq_zone; - /* * Number of extents in this block group used for swap files. * All accesses protected by the spinlock 'lock'. diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 836babd23db5..9bc7ac06c517 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1436,7 +1436,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } if (num_sequential > 0) - cache->seq_zone = true; + set_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags); if (num_conventional > 0) { /* Zone capacity is always zone size in emulation */ @@ -1658,7 +1658,7 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start) if (!cache) return false; - ret = cache->seq_zone; + ret = !!test_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags); btrfs_put_block_group(cache); return ret; @@ -2177,7 +2177,8 @@ static void btrfs_zone_finish_endio_workfn(struct work_struct *work) void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg, struct extent_buffer *eb) { - if (!bg->seq_zone || eb->start + eb->len * 2 <= bg->start + bg->zone_capacity) + if (!test_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &bg->runtime_flags) || + eb->start + eb->len * 2 <= bg->start + bg->zone_capacity) return; if (WARN_ON(bg->zone_finish_work.func == btrfs_zone_finish_endio_workfn)) { From 6297644db23f77c02ae7961cc542d162629ae2c4 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 28 Jun 2023 17:13:37 +0100 Subject: [PATCH 0402/2093] btrfs: fix use-after-free of new block group that became unused [ Upstream commit 0657b20c5a76c938612f8409735a8830d257866e ] If a task creates a new block group and that block group becomes unused before we finish its creation, at btrfs_create_pending_block_groups(), then when btrfs_mark_bg_unused() is called against the block group, we assume that the block group is currently in the list of block groups to reclaim, and we move it out of the list of new block groups and into the list of unused block groups. This has two consequences: 1) We move it out of the list of new block groups associated to the current transaction. So the block group creation is not finished and if we attempt to delete the bg because it's unused, we will not find the block group item in the extent tree (or the new block group tree), its device extent items in the device tree etc, resulting in the deletion to fail due to the missing items; 2) We don't increment the reference count on the block group when we move it to the list of unused block groups, because we assumed the block group was on the list of block groups to reclaim, and in that case it already has the correct reference count. However the block group was on the list of new block groups, in which case no extra reference was taken because it's local to the current task. This later results in doing an extra reference count decrement when removing the block group from the unused list, eventually leading the reference count to 0. This second case was caught when running generic/297 from fstests, which produced the following assertion failure and stack trace: [589.559] assertion failed: refcount_read(&block_group->refs) == 1, in fs/btrfs/block-group.c:4299 [589.559] ------------[ cut here ]------------ [589.559] kernel BUG at fs/btrfs/block-group.c:4299! [589.560] invalid opcode: 0000 [#1] PREEMPT SMP PTI [589.560] CPU: 8 PID: 2819134 Comm: umount Tainted: G W 6.4.0-rc6-btrfs-next-134+ #1 [589.560] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [589.560] RIP: 0010:btrfs_free_block_groups+0x449/0x4a0 [btrfs] [589.561] Code: 68 62 da c0 (...) [589.561] RSP: 0018:ffffa55a8c3b3d98 EFLAGS: 00010246 [589.561] RAX: 0000000000000058 RBX: ffff8f030d7f2000 RCX: 0000000000000000 [589.562] RDX: 0000000000000000 RSI: ffffffff953f0878 RDI: 00000000ffffffff [589.562] RBP: ffff8f030d7f2088 R08: 0000000000000000 R09: ffffa55a8c3b3c50 [589.562] R10: 0000000000000001 R11: 0000000000000001 R12: ffff8f05850b4c00 [589.562] R13: ffff8f030d7f2090 R14: ffff8f05850b4cd8 R15: dead000000000100 [589.563] FS: 00007f497fd2e840(0000) GS:ffff8f09dfc00000(0000) knlGS:0000000000000000 [589.563] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [589.563] CR2: 00007f497ff8ec10 CR3: 0000000271472006 CR4: 0000000000370ee0 [589.563] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [589.564] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [589.564] Call Trace: [589.564] [589.565] ? __die_body+0x1b/0x60 [589.565] ? die+0x39/0x60 [589.565] ? do_trap+0xeb/0x110 [589.565] ? btrfs_free_block_groups+0x449/0x4a0 [btrfs] [589.566] ? do_error_trap+0x6a/0x90 [589.566] ? btrfs_free_block_groups+0x449/0x4a0 [btrfs] [589.566] ? exc_invalid_op+0x4e/0x70 [589.566] ? btrfs_free_block_groups+0x449/0x4a0 [btrfs] [589.567] ? asm_exc_invalid_op+0x16/0x20 [589.567] ? btrfs_free_block_groups+0x449/0x4a0 [btrfs] [589.567] ? btrfs_free_block_groups+0x449/0x4a0 [btrfs] [589.567] close_ctree+0x35d/0x560 [btrfs] [589.568] ? fsnotify_sb_delete+0x13e/0x1d0 [589.568] ? dispose_list+0x3a/0x50 [589.568] ? evict_inodes+0x151/0x1a0 [589.568] generic_shutdown_super+0x73/0x1a0 [589.569] kill_anon_super+0x14/0x30 [589.569] btrfs_kill_super+0x12/0x20 [btrfs] [589.569] deactivate_locked_super+0x2e/0x70 [589.569] cleanup_mnt+0x104/0x160 [589.570] task_work_run+0x56/0x90 [589.570] exit_to_user_mode_prepare+0x160/0x170 [589.570] syscall_exit_to_user_mode+0x22/0x50 [589.570] ? __x64_sys_umount+0x12/0x20 [589.571] do_syscall_64+0x48/0x90 [589.571] entry_SYSCALL_64_after_hwframe+0x72/0xdc [589.571] RIP: 0033:0x7f497ff0a567 [589.571] Code: af 98 0e (...) [589.572] RSP: 002b:00007ffc98347358 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [589.572] RAX: 0000000000000000 RBX: 00007f49800b8264 RCX: 00007f497ff0a567 [589.572] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000557f558abfa0 [589.573] RBP: 0000557f558a6ba0 R08: 0000000000000000 R09: 00007ffc98346100 [589.573] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [589.573] R13: 0000557f558abfa0 R14: 0000557f558a6cb0 R15: 0000557f558a6dd0 [589.573] [589.574] Modules linked in: dm_snapshot dm_thin_pool (...) [589.576] ---[ end trace 0000000000000000 ]--- Fix this by adding a runtime flag to the block group to tell that the block group is still in the list of new block groups, and therefore it should not be moved to the list of unused block groups, at btrfs_mark_bg_unused(), until the flag is cleared, when we finish the creation of the block group at btrfs_create_pending_block_groups(). Fixes: a9f189716cf1 ("btrfs: move out now unused BG from the reclaim list") CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/block-group.c | 13 +++++++++++-- fs/btrfs/block-group.h | 5 +++++ 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index a726b532b527..08017b180a10 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1528,13 +1528,14 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; - trace_btrfs_add_unused_block_group(bg); spin_lock(&fs_info->unused_bgs_lock); if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); + trace_btrfs_add_unused_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->unused_bgs); - } else { + } else if (!test_bit(BLOCK_GROUP_FLAG_NEW, &bg->runtime_flags)) { /* Pull out the block group from the reclaim_bgs list. */ + trace_btrfs_add_unused_block_group(bg); list_move_tail(&bg->bg_list, &fs_info->unused_bgs); } spin_unlock(&fs_info->unused_bgs_lock); @@ -2496,6 +2497,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) next: btrfs_delayed_refs_rsv_release(fs_info, 1); list_del_init(&block_group->bg_list); + clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags); } btrfs_trans_release_chunk_metadata(trans); } @@ -2535,6 +2537,13 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran if (!cache) return ERR_PTR(-ENOMEM); + /* + * Mark it as new before adding it to the rbtree of block groups or any + * list, so that no other task finds it and calls btrfs_mark_bg_unused() + * before the new flag is set. + */ + set_bit(BLOCK_GROUP_FLAG_NEW, &cache->runtime_flags); + cache->length = size; set_free_space_tree_thresholds(cache); cache->used = bytes_used; diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index fb4f4901350b..47a2dcbfee25 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -59,6 +59,11 @@ enum btrfs_block_group_flags { BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, /* Indicate that the block group is placed on a sequential zone */ BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, + /* + * Indicate that block group is in the list of new block groups of a + * transaction. + */ + BLOCK_GROUP_FLAG_NEW, }; enum btrfs_caching_type { From af5818c35173e096085c6ae2e3aac605d3d15e41 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 29 Jun 2023 14:05:26 +0200 Subject: [PATCH 0403/2093] virtio-mmio: don't break lifecycle of vm_dev [ Upstream commit 55c91fedd03d7b9cf0c5199b2eb12b9b8e95281a ] vm_dev has a separate lifecycle because it has a 'struct device' embedded. Thus, having a release callback for it is correct. Allocating the vm_dev struct with devres totally breaks this protection, though. Instead of waiting for the vm_dev release callback, the memory is freed when the platform_device is removed. Resulting in a use-after-free when finally the callback is to be called. To easily see the problem, compile the kernel with CONFIG_DEBUG_KOBJECT_RELEASE and unbind with sysfs. The fix is easy, don't use devres in this case. Found during my research about object lifetime problems. Fixes: 7eb781b1bbb7 ("virtio_mmio: add cleanup for virtio_mmio_probe") Signed-off-by: Wolfram Sang Message-Id: <20230629120526.7184-1-wsa+renesas@sang-engineering.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/virtio/virtio_mmio.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 3ff746e3f24a..dec3cba88458 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -590,9 +590,8 @@ static void virtio_mmio_release_dev(struct device *_d) struct virtio_device *vdev = container_of(_d, struct virtio_device, dev); struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); - struct platform_device *pdev = vm_dev->pdev; - devm_kfree(&pdev->dev, vm_dev); + kfree(vm_dev); } /* Platform device */ @@ -603,7 +602,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) unsigned long magic; int rc; - vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL); + vm_dev = kzalloc(sizeof(*vm_dev), GFP_KERNEL); if (!vm_dev) return -ENOMEM; From e706675beeec3b7fd175105a5defc08313989262 Mon Sep 17 00:00:00 2001 From: Maxime Coquelin Date: Wed, 5 Jul 2023 13:45:05 +0200 Subject: [PATCH 0404/2093] vduse: Use proper spinlock for IRQ injection [ Upstream commit 7ca26efb09a1543fddb29308ea3b63b66cb5d3ee ] The IRQ injection work used spin_lock_irq() to protect the scheduling of the softirq, but spin_lock_bh() should be used. With spin_lock_irq(), we noticed delay of more than 6 seconds between the time a NAPI polling work is scheduled and the time it is executed. Fixes: c8a6153b6c59 ("vduse: Introduce VDUSE - vDPA Device in Userspace") Cc: xieyongji@bytedance.com Suggested-by: Jason Wang Signed-off-by: Maxime Coquelin Message-Id: <20230705114505.63274-1-maxime.coquelin@redhat.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Xie Yongji Signed-off-by: Sasha Levin --- drivers/vdpa/vdpa_user/vduse_dev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 72f924ec4658..edcd74cc4c0f 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -899,10 +899,10 @@ static void vduse_dev_irq_inject(struct work_struct *work) { struct vduse_dev *dev = container_of(work, struct vduse_dev, inject); - spin_lock_irq(&dev->irq_lock); + spin_lock_bh(&dev->irq_lock); if (dev->config_cb.callback) dev->config_cb.callback(dev->config_cb.private); - spin_unlock_irq(&dev->irq_lock); + spin_unlock_bh(&dev->irq_lock); } static void vduse_vq_irq_inject(struct work_struct *work) @@ -910,10 +910,10 @@ static void vduse_vq_irq_inject(struct work_struct *work) struct vduse_virtqueue *vq = container_of(work, struct vduse_virtqueue, inject); - spin_lock_irq(&vq->irq_lock); + spin_lock_bh(&vq->irq_lock); if (vq->ready && vq->cb.callback) vq->cb.callback(vq->cb.private); - spin_unlock_irq(&vq->irq_lock); + spin_unlock_bh(&vq->irq_lock); } static int vduse_dev_queue_irq_work(struct vduse_dev *dev, From bb4983ec9e752c4cb73b76e6d6e904feac371205 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Wed, 2 Aug 2023 20:12:18 +0300 Subject: [PATCH 0405/2093] vdpa/mlx5: Fix mr->initialized semantics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9ee811009ad8f87982b69e61d07447d12233ad01 ] The mr->initialized flag is shared between the control vq and data vq part of the mr init/uninit. But if the control vq and data vq get placed in different ASIDs, it can happen that initializing the control vq will prevent the data vq mr from being initialized. This patch consolidates the control and data vq init parts into their own init functions. The mr->initialized will now be used for the data vq only. The control vq currently doesn't need a flag. The uninitializing part is also taken care of: mlx5_vdpa_destroy_mr got split into data and control vq functions which are now also ASID aware. Fixes: 8fcd20c30704 ("vdpa/mlx5: Support different address spaces for control and data") Signed-off-by: Dragos Tatulea Reviewed-by: Eugenio Pérez Reviewed-by: Gal Pressman Message-Id: <20230802171231.11001-3-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Sasha Levin --- drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + drivers/vdpa/mlx5/core/mr.c | 105 ++++++++++++++++++++--------- 2 files changed, 75 insertions(+), 31 deletions(-) diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 25fc4120b618..a0420be5059f 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -31,6 +31,7 @@ struct mlx5_vdpa_mr { struct list_head head; unsigned long num_directs; unsigned long num_klms; + /* state of dvq mr */ bool initialized; /* serialize mkey creation and destruction */ diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index a4d7ee2339fa..b3609867d567 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -491,15 +491,24 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr } } -void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) +static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid) +{ + if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid) + return; + + prune_iotlb(mvdev); +} + +static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid) { struct mlx5_vdpa_mr *mr = &mvdev->mr; - mutex_lock(&mr->mkey_mtx); - if (!mr->initialized) - goto out; + if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid) + return; + + if (!mr->initialized) + return; - prune_iotlb(mvdev); if (mr->user_mr) destroy_user_mr(mvdev, mr); else @@ -507,45 +516,79 @@ void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) memset(mr, 0, sizeof(*mr)); mr->initialized = false; -out: +} + +static void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + + mutex_lock(&mr->mkey_mtx); + + _mlx5_vdpa_destroy_dvq_mr(mvdev, asid); + _mlx5_vdpa_destroy_cvq_mr(mvdev, asid); + mutex_unlock(&mr->mkey_mtx); } +void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) +{ + mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_CVQ_GROUP]); + mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]); +} + +static int _mlx5_vdpa_create_cvq_mr(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, + unsigned int asid) +{ + if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid) + return 0; + + return dup_iotlb(mvdev, iotlb); +} + +static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev, + struct vhost_iotlb *iotlb, + unsigned int asid) +{ + struct mlx5_vdpa_mr *mr = &mvdev->mr; + int err; + + if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid) + return 0; + + if (mr->initialized) + return 0; + + if (iotlb) + err = create_user_mr(mvdev, iotlb); + else + err = create_dma_mr(mvdev, mr); + + if (err) + return err; + + mr->initialized = true; + + return 0; +} + static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, unsigned int asid) { - struct mlx5_vdpa_mr *mr = &mvdev->mr; int err; - if (mr->initialized) - return 0; + err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb, asid); + if (err) + return err; - if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { - if (iotlb) - err = create_user_mr(mvdev, iotlb); - else - err = create_dma_mr(mvdev, mr); + err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb, asid); + if (err) + goto out_err; - if (err) - return err; - } - - if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) { - err = dup_iotlb(mvdev, iotlb); - if (err) - goto out_err; - } - - mr->initialized = true; return 0; out_err: - if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) { - if (iotlb) - destroy_user_mr(mvdev, mr); - else - destroy_dma_mr(mvdev, mr); - } + _mlx5_vdpa_destroy_dvq_mr(mvdev, asid); return err; } From cba26abc3f9485871eadd4c8015be3dd4f739a73 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= Date: Wed, 2 Aug 2023 20:12:20 +0300 Subject: [PATCH 0406/2093] vdpa/mlx5: Delete control vq iotlb in destroy_mr only when necessary MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ad03a0f44cdb97b46e5c84ed353dac9b8ae2c276 ] mlx5_vdpa_destroy_mr can be called from .set_map with data ASID after the control virtqueue ASID iotlb has been populated. The control vq iotlb must not be cleared, since it will not be populated again. So call the ASID aware destroy function which makes sure that the right vq resource is destroyed. Fixes: 8fcd20c30704 ("vdpa/mlx5: Support different address spaces for control and data") Signed-off-by: Eugenio Pérez Reviewed-by: Gal Pressman Message-Id: <20230802171231.11001-5-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Sasha Levin --- drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + drivers/vdpa/mlx5/core/mr.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 4 ++-- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index a0420be5059f..b53420e874ac 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -122,6 +122,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, unsigned int asid); void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev); +void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid); #define mlx5_vdpa_warn(__dev, format, ...) \ dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__, \ diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index b3609867d567..113aac0446de 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -518,7 +518,7 @@ static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int mr->initialized = false; } -static void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid) +void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid) { struct mlx5_vdpa_mr *mr = &mvdev->mr; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index daac3ab31478..bf99654371b3 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2406,7 +2406,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, goto err_mr; teardown_driver(ndev); - mlx5_vdpa_destroy_mr(mvdev); + mlx5_vdpa_destroy_mr_asid(mvdev, asid); err = mlx5_vdpa_create_mr(mvdev, iotlb, asid); if (err) goto err_mr; @@ -2422,7 +2422,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, return 0; err_setup: - mlx5_vdpa_destroy_mr(mvdev); + mlx5_vdpa_destroy_mr_asid(mvdev, asid); err_mr: return err; } From 5ee28bcfbaacf289eb25c662a2862542ea6ce6a7 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 10 Aug 2023 15:34:21 -0500 Subject: [PATCH 0407/2093] cifs: fix potential oops in cifs_oplock_break [ Upstream commit e8f5f849ffce24490eb9449e98312b66c0dba76f ] With deferred close we can have closes that race with lease breaks, and so with the current checks for whether to send the lease response, oplock_response(), this can mean that an unmount (kill_sb) can occur just before we were checking if the tcon->ses is valid. See below: [Fri Aug 4 04:12:50 2023] RIP: 0010:cifs_oplock_break+0x1f7/0x5b0 [cifs] [Fri Aug 4 04:12:50 2023] Code: 7d a8 48 8b 7d c0 c0 e9 02 48 89 45 b8 41 89 cf e8 3e f5 ff ff 4c 89 f7 41 83 e7 01 e8 82 b3 03 f2 49 8b 45 50 48 85 c0 74 5e <48> 83 78 60 00 74 57 45 84 ff 75 52 48 8b 43 98 48 83 eb 68 48 39 [Fri Aug 4 04:12:50 2023] RSP: 0018:ffffb30607ddbdf8 EFLAGS: 00010206 [Fri Aug 4 04:12:50 2023] RAX: 632d223d32612022 RBX: ffff97136944b1e0 RCX: 0000000080100009 [Fri Aug 4 04:12:50 2023] RDX: 0000000000000001 RSI: 0000000080100009 RDI: ffff97136944b188 [Fri Aug 4 04:12:50 2023] RBP: ffffb30607ddbe58 R08: 0000000000000001 R09: ffffffffc08e0900 [Fri Aug 4 04:12:50 2023] R10: 0000000000000001 R11: 000000000000000f R12: ffff97136944b138 [Fri Aug 4 04:12:50 2023] R13: ffff97149147c000 R14: ffff97136944b188 R15: 0000000000000000 [Fri Aug 4 04:12:50 2023] FS: 0000000000000000(0000) GS:ffff9714f7c00000(0000) knlGS:0000000000000000 [Fri Aug 4 04:12:50 2023] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Fri Aug 4 04:12:50 2023] CR2: 00007fd8de9c7590 CR3: 000000011228e000 CR4: 0000000000350ef0 [Fri Aug 4 04:12:50 2023] Call Trace: [Fri Aug 4 04:12:50 2023] [Fri Aug 4 04:12:50 2023] process_one_work+0x225/0x3d0 [Fri Aug 4 04:12:50 2023] worker_thread+0x4d/0x3e0 [Fri Aug 4 04:12:50 2023] ? process_one_work+0x3d0/0x3d0 [Fri Aug 4 04:12:50 2023] kthread+0x12a/0x150 [Fri Aug 4 04:12:50 2023] ? set_kthread_struct+0x50/0x50 [Fri Aug 4 04:12:50 2023] ret_from_fork+0x22/0x30 [Fri Aug 4 04:12:50 2023] To fix this change the ordering of the checks before sending the oplock_response to first check if the openFileList is empty. Fixes: da787d5b7498 ("SMB3: Do not send lease break acknowledgment if all file handles have been closed") Suggested-by: Bharath SM Reviewed-by: Bharath SM Reviewed-by: Shyam Prasad N Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/file.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 27c6d14e369f..0a8adec515ae 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -5082,9 +5082,11 @@ void cifs_oplock_break(struct work_struct *work) struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); struct inode *inode = d_inode(cfile->dentry); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cinode = CIFS_I(inode); - struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct TCP_Server_Info *server = tcon->ses->server; + struct cifs_tcon *tcon; + struct TCP_Server_Info *server; + struct tcon_link *tlink; int rc = 0; bool purge_cache = false, oplock_break_cancelled; __u64 persistent_fid, volatile_fid; @@ -5093,6 +5095,12 @@ void cifs_oplock_break(struct work_struct *work) wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + goto out; + tcon = tlink_tcon(tlink); + server = tcon->ses->server; + server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, cfile->oplock_epoch, &purge_cache); @@ -5142,18 +5150,19 @@ void cifs_oplock_break(struct work_struct *work) /* * MS-SMB2 3.2.5.19.1 and 3.2.5.19.2 (and MS-CIFS 3.2.5.42) do not require * an acknowledgment to be sent when the file has already been closed. - * check for server null, since can race with kill_sb calling tree disconnect. */ spin_lock(&cinode->open_file_lock); - if (tcon->ses && tcon->ses->server && !oplock_break_cancelled && - !list_empty(&cinode->openFileList)) { + /* check list empty since can race with kill_sb calling tree disconnect */ + if (!oplock_break_cancelled && !list_empty(&cinode->openFileList)) { spin_unlock(&cinode->open_file_lock); - rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, - volatile_fid, net_fid, cinode); + rc = server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } else spin_unlock(&cinode->open_file_lock); + cifs_put_tlink(tlink); +out: cifs_done_oplock_break(cinode); } From db0416c15572adffaa82278bdc30d892401d76c9 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Fri, 7 Jul 2023 08:49:41 +0000 Subject: [PATCH 0408/2093] i2c: bcm-iproc: Fix bcm_iproc_i2c_isr deadlock issue commit 4caf4cb1eaed469742ef719f2cc024b1ec3fa9e6 upstream. iproc_i2c_rd_reg() and iproc_i2c_wr_reg() are called from both interrupt context (e.g. bcm_iproc_i2c_isr) and process context (e.g. bcm_iproc_i2c_suspend). Therefore, interrupts should be disabled to avoid potential deadlock. To prevent this scenario, use spin_lock_irqsave(). Fixes: 9a1038728037 ("i2c: iproc: add NIC I2C support") Signed-off-by: Chengfeng Ye Acked-by: Ray Jui Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-bcm-iproc.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 85d8a6b04885..30a2a3200bed 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -233,13 +233,14 @@ static inline u32 iproc_i2c_rd_reg(struct bcm_iproc_i2c_dev *iproc_i2c, u32 offset) { u32 val; + unsigned long flags; if (iproc_i2c->idm_base) { - spin_lock(&iproc_i2c->idm_lock); + spin_lock_irqsave(&iproc_i2c->idm_lock, flags); writel(iproc_i2c->ape_addr_mask, iproc_i2c->idm_base + IDM_CTRL_DIRECT_OFFSET); val = readl(iproc_i2c->base + offset); - spin_unlock(&iproc_i2c->idm_lock); + spin_unlock_irqrestore(&iproc_i2c->idm_lock, flags); } else { val = readl(iproc_i2c->base + offset); } @@ -250,12 +251,14 @@ static inline u32 iproc_i2c_rd_reg(struct bcm_iproc_i2c_dev *iproc_i2c, static inline void iproc_i2c_wr_reg(struct bcm_iproc_i2c_dev *iproc_i2c, u32 offset, u32 val) { + unsigned long flags; + if (iproc_i2c->idm_base) { - spin_lock(&iproc_i2c->idm_lock); + spin_lock_irqsave(&iproc_i2c->idm_lock, flags); writel(iproc_i2c->ape_addr_mask, iproc_i2c->idm_base + IDM_CTRL_DIRECT_OFFSET); writel(val, iproc_i2c->base + offset); - spin_unlock(&iproc_i2c->idm_lock); + spin_unlock_irqrestore(&iproc_i2c->idm_lock, flags); } else { writel(val, iproc_i2c->base + offset); } From ba249011f6651952eef267f00f6086c8bac15049 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Tue, 1 Aug 2023 20:46:25 +0800 Subject: [PATCH 0409/2093] i2c: hisi: Only handle the interrupt of the driver's transfer commit fff67c1b17ee093947bdcbac6f64d072e644159a upstream. The controller may be shared with other port, for example the firmware. Handle the interrupt from other sources will cause crash since some data are not initialized. So only handle the interrupt of the driver's transfer and discard others. Fixes: d62fbdb99a85 ("i2c: add support for HiSilicon I2C controller") Signed-off-by: Yicong Yang Reviewed-by: Andi Shyti Link: https://lore.kernel.org/r/20230801124625.63587-1-yangyicong@huawei.com Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-hisi.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/i2c/busses/i2c-hisi.c b/drivers/i2c/busses/i2c-hisi.c index 8a61bee745a1..14ec9ee8f6f3 100644 --- a/drivers/i2c/busses/i2c-hisi.c +++ b/drivers/i2c/busses/i2c-hisi.c @@ -328,6 +328,14 @@ static irqreturn_t hisi_i2c_irq(int irq, void *context) struct hisi_i2c_controller *ctlr = context; u32 int_stat; + /* + * Don't handle the interrupt if cltr->completion is NULL. We may + * reach here because the interrupt is spurious or the transfer is + * started by another port (e.g. firmware) rather than us. + */ + if (!ctlr->completion) + return IRQ_NONE; + int_stat = readl(ctlr->iobase + HISI_I2C_INT_MSTAT); hisi_i2c_clear_int(ctlr, int_stat); if (!(int_stat & HISI_I2C_INT_ALL)) From 3461e6492ca28253edfcd13d176d2b9b24c0ed53 Mon Sep 17 00:00:00 2001 From: Parker Newman Date: Tue, 8 Aug 2023 16:01:06 +0200 Subject: [PATCH 0410/2093] i2c: tegra: Fix i2c-tegra DMA config option processing commit 27ec43c77b5db780a56fc3a6d6de6bf2f74614f7 upstream. Tegra processors prior to Tegra186 used APB DMA for I2C requiring CONFIG_TEGRA20_APB_DMA=y while Tegra186 and later use GPC DMA requiring CONFIG_TEGRA186_GPC_DMA=y. The check for if the processor uses APB DMA is inverted and so the wrong DMA config options are checked. This means if CONFIG_TEGRA20_APB_DMA=y but CONFIG_TEGRA186_GPC_DMA=n with a Tegra186 or later processor the driver will incorrectly think DMA is enabled and attempt to request DMA channels that will never be availible, leaving the driver in a perpetual EPROBE_DEFER state. Fixes: 48cb6356fae1 ("i2c: tegra: Add GPCDMA support") Signed-off-by: Parker Newman Acked-by: Andi Shyti Acked-by: Akhil R Link: https://lore.kernel.org/r/fcfcf9b3-c8c4-9b34-2ff8-cd60a3d490bd@connecttech.com Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-tegra.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 2bc40f957e50..aa469b33ee2e 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -449,7 +449,7 @@ static int tegra_i2c_init_dma(struct tegra_i2c_dev *i2c_dev) if (i2c_dev->is_vi) return 0; - if (!i2c_dev->hw->has_apb_dma) { + if (i2c_dev->hw->has_apb_dma) { if (!IS_ENABLED(CONFIG_TEGRA20_APB_DMA)) { dev_dbg(i2c_dev->dev, "APB DMA support not enabled\n"); return 0; From 9fedcd07abdc7a2b5bf241191930c5c63f7f4a53 Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Fri, 28 Jul 2023 01:03:18 +0800 Subject: [PATCH 0411/2093] fbdev: mmp: fix value check in mmphw_probe() commit 0872b2c0abc0e84ac82472959c8e14e35277549c upstream. in mmphw_probe(), check the return value of clk_prepare_enable() and return the error code if clk_prepare_enable() returns an unexpected value. Fixes: d63028c38905 ("video: mmp display controller support") Signed-off-by: Yuanjun Gong Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/mmp/hw/mmp_ctrl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c index 51fbf02a0343..76b50b6c98ad 100644 --- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c +++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c @@ -519,7 +519,9 @@ static int mmphw_probe(struct platform_device *pdev) "unable to get clk %s\n", mi->clk_name); goto failed; } - clk_prepare_enable(ctrl->clk); + ret = clk_prepare_enable(ctrl->clk); + if (ret) + goto failed; /* init global regs */ ctrl_set_default(ctrl); From b8fee83aa4ed3846c7f50a0b364bc699f48d96e5 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Thu, 10 Aug 2023 22:37:55 -0500 Subject: [PATCH 0412/2093] powerpc/rtas_flash: allow user copy to flash block cache objects commit 4f3175979e62de3b929bfa54a0db4b87d36257a7 upstream. With hardened usercopy enabled (CONFIG_HARDENED_USERCOPY=y), using the /proc/powerpc/rtas/firmware_update interface to prepare a system firmware update yields a BUG(): kernel BUG at mm/usercopy.c:102! Oops: Exception in kernel mode, sig: 5 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 0 PID: 2232 Comm: dd Not tainted 6.5.0-rc3+ #2 Hardware name: IBM,8408-E8E POWER8E (raw) 0x4b0201 0xf000004 of:IBM,FW860.50 (SV860_146) hv:phyp pSeries NIP: c0000000005991d0 LR: c0000000005991cc CTR: 0000000000000000 REGS: c0000000148c76a0 TRAP: 0700 Not tainted (6.5.0-rc3+) MSR: 8000000000029033 CR: 24002242 XER: 0000000c CFAR: c0000000001fbd34 IRQMASK: 0 [ ... GPRs omitted ... ] NIP usercopy_abort+0xa0/0xb0 LR usercopy_abort+0x9c/0xb0 Call Trace: usercopy_abort+0x9c/0xb0 (unreliable) __check_heap_object+0x1b4/0x1d0 __check_object_size+0x2d0/0x380 rtas_flash_write+0xe4/0x250 proc_reg_write+0xfc/0x160 vfs_write+0xfc/0x4e0 ksys_write+0x90/0x160 system_call_exception+0x178/0x320 system_call_common+0x160/0x2c4 The blocks of the firmware image are copied directly from user memory to objects allocated from flash_block_cache, so flash_block_cache must be created using kmem_cache_create_usercopy() to mark it safe for user access. Fixes: 6d07d1cd300f ("usercopy: Restrict non-usercopy caches to size 0") Signed-off-by: Nathan Lynch Reviewed-by: Kees Cook [mpe: Trim and indent oops] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230810-rtas-flash-vs-hardened-usercopy-v2-1-dcf63793a938@linux.ibm.com Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/rtas_flash.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index bc817a5619d6..43c635ddba70 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -710,9 +710,9 @@ static int __init rtas_flash_init(void) if (!rtas_validate_flash_data.buf) return -ENOMEM; - flash_block_cache = kmem_cache_create("rtas_flash_cache", - RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0, - NULL); + flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache", + RTAS_BLK_SIZE, RTAS_BLK_SIZE, + 0, 0, RTAS_BLK_SIZE, NULL); if (!flash_block_cache) { printk(KERN_ERR "%s: failed to create block cache\n", __func__); From 44b508cc96889e61799cc0fc6c00766a54f3ab5a Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Thu, 27 Jul 2023 20:57:48 +0300 Subject: [PATCH 0413/2093] vdpa: Add features attr to vdpa_nl_policy for nlattr length check commit 79c8651587504ba263d2fd67fd4406240fb21f69 upstream. The vdpa_nl_policy structure is used to validate the nlattr when parsing the incoming nlmsg. It will ensure the attribute being described produces a valid nlattr pointer in info->attrs before entering into each handler in vdpa_nl_ops. That is to say, the missing part in vdpa_nl_policy may lead to illegal nlattr after parsing, which could lead to OOB read just like CVE-2023-3773. This patch adds the missing nla_policy for vdpa features attr to avoid such bugs. Fixes: 90fea5a800c3 ("vdpa: device feature provisioning") Signed-off-by: Lin Ma Cc: stable@vger.kernel.org Message-Id: <20230727175757.73988-3-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/vdpa/vdpa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index febdc99b51a7..52c58e7a8e3c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1174,6 +1174,7 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR, /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */ [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68), + [VDPA_ATTR_DEV_FEATURES] = { .type = NLA_U64 }, }; static const struct genl_ops vdpa_nl_ops[] = { From 8ad9bc25cbdcec72e7ca43dd8281decb69ea9a70 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Thu, 27 Jul 2023 20:57:50 +0300 Subject: [PATCH 0414/2093] vdpa: Add queue index attr to vdpa_nl_policy for nlattr length check commit b3003e1b54e057f5f3124e437b80c3bef26ed3fe upstream. The vdpa_nl_policy structure is used to validate the nlattr when parsing the incoming nlmsg. It will ensure the attribute being described produces a valid nlattr pointer in info->attrs before entering into each handler in vdpa_nl_ops. That is to say, the missing part in vdpa_nl_policy may lead to illegal nlattr after parsing, which could lead to OOB read just like CVE-2023-3773. This patch adds the missing nla_policy for vdpa queue index attr to avoid such bugs. Fixes: 13b00b135665 ("vdpa: Add support for querying vendor statistics") Signed-off-by: Lin Ma Cc: stable@vger.kernelorg Message-Id: <20230727175757.73988-5-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/vdpa/vdpa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 52c58e7a8e3c..da6864a889a4 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1174,6 +1174,7 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR, /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */ [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68), + [VDPA_ATTR_DEV_QUEUE_INDEX] = { .type = NLA_U32 }, [VDPA_ATTR_DEV_FEATURES] = { .type = NLA_U64 }, }; From ff71709445ac033e6e250d971683110e4781c068 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Thu, 27 Jul 2023 20:57:52 +0300 Subject: [PATCH 0415/2093] vdpa: Add max vqp attr to vdpa_nl_policy for nlattr length check commit 5d6ba607d6cb5c58a4ddf33381e18c83dbb4098f upstream. The vdpa_nl_policy structure is used to validate the nlattr when parsing the incoming nlmsg. It will ensure the attribute being described produces a valid nlattr pointer in info->attrs before entering into each handler in vdpa_nl_ops. That is to say, the missing part in vdpa_nl_policy may lead to illegal nlattr after parsing, which could lead to OOB read just like CVE-2023-3773. This patch adds the missing nla_policy for vdpa max vqp attr to avoid such bugs. Fixes: ad69dd0bf26b ("vdpa: Introduce query of device config layout") Signed-off-by: Lin Ma Cc: stable@vger.kernel.org Message-Id: <20230727175757.73988-7-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/vdpa/vdpa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index da6864a889a4..291ea4d4c06e 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1172,6 +1172,7 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR, + [VDPA_ATTR_DEV_NET_CFG_MAX_VQP] = { .type = NLA_U16 }, /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */ [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68), [VDPA_ATTR_DEV_QUEUE_INDEX] = { .type = NLA_U32 }, From d6aa03bda8c0ce5a340e33d37e0cb480b40fde08 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 27 Jul 2023 20:57:54 +0300 Subject: [PATCH 0416/2093] vdpa: Enable strict validation for netlinks ops commit f46c1e1620c6bbc9aad5693082efd1b80822e97c upstream. The previous patches added the missing nla policies that were required for validation to work. Now strict validation on netlink ops can be enabled. This patch does it. Signed-off-by: Dragos Tatulea Cc: stable@vger.kernel.org Message-Id: <20230727175757.73988-9-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/vdpa/vdpa.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 291ea4d4c06e..908b3f98ecbe 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1182,37 +1182,31 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { static const struct genl_ops vdpa_nl_ops[] = { { .cmd = VDPA_CMD_MGMTDEV_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_mgmtdev_get_doit, .dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit, }, { .cmd = VDPA_CMD_DEV_NEW, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_add_set_doit, .flags = GENL_ADMIN_PERM, }, { .cmd = VDPA_CMD_DEV_DEL, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_del_set_doit, .flags = GENL_ADMIN_PERM, }, { .cmd = VDPA_CMD_DEV_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_get_doit, .dumpit = vdpa_nl_cmd_dev_get_dumpit, }, { .cmd = VDPA_CMD_DEV_CONFIG_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_config_get_doit, .dumpit = vdpa_nl_cmd_dev_config_get_dumpit, }, { .cmd = VDPA_CMD_DEV_VSTATS_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = vdpa_nl_cmd_dev_stats_get_doit, .flags = GENL_ADMIN_PERM, }, From 31311a9a4baae0ad47c85e448af21b2120344ff0 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Fri, 11 Aug 2023 11:11:21 +0800 Subject: [PATCH 0417/2093] tty: n_gsm: fix the UAF caused by race condition in gsm_cleanup_mux commit 3c4f8333b582487a2d1e02171f1465531cde53e3 upstream. In commit 9b9c8195f3f0 ("tty: n_gsm: fix UAF in gsm_cleanup_mux"), the UAF problem is not completely fixed. There is a race condition in gsm_cleanup_mux(), which caused this UAF. The UAF problem is triggered by the following race: task[5046] task[5054] ----------------------- ----------------------- gsm_cleanup_mux(); dlci = gsm->dlci[0]; mutex_lock(&gsm->mutex); gsm_cleanup_mux(); dlci = gsm->dlci[0]; //Didn't take the lock gsm_dlci_release(gsm->dlci[i]); gsm->dlci[i] = NULL; mutex_unlock(&gsm->mutex); mutex_lock(&gsm->mutex); dlci->dead = true; //UAF Fix it by assigning values after mutex_lock(). Link: https://syzkaller.appspot.com/text?tag=CrashReport&x=176188b5a80000 Cc: stable Fixes: 9b9c8195f3f0 ("tty: n_gsm: fix UAF in gsm_cleanup_mux") Fixes: aa371e96f05d ("tty: n_gsm: fix restart handling via CLD command") Signed-off-by: Yi Yang Co-developed-by: Qiumiao Zhang Signed-off-by: Qiumiao Zhang Link: https://lore.kernel.org/r/20230811031121.153237-1-yiyang13@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_gsm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 59a559366b61..c1fa20a4e342 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2481,12 +2481,13 @@ static void gsm_error(struct gsm_mux *gsm) static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) { int i; - struct gsm_dlci *dlci = gsm->dlci[0]; + struct gsm_dlci *dlci; struct gsm_msg *txq, *ntxq; gsm->dead = true; mutex_lock(&gsm->mutex); + dlci = gsm->dlci[0]; if (dlci) { if (disc && dlci->state != DLCI_CLOSED) { gsm_dlci_begin_close(dlci); From 0693c8f134f97f8973621be76b17be8efbe17589 Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Tue, 1 Aug 2023 10:23:04 +0800 Subject: [PATCH 0418/2093] tty: serial: fsl_lpuart: Clear the error flags by writing 1 for lpuart32 platforms commit 282069845af388b08d622ad192b831dcd0549c62 upstream. Do not read the data register to clear the error flags for lpuart32 platforms, the additional read may cause the receive FIFO underflow since the DMA has already read the data register. Actually all lpuart32 platforms support write 1 to clear those error bits, let's use this method to better clear the error flags. Fixes: 42b68768e51b ("serial: fsl_lpuart: DMA support for 32-bit variant") Cc: stable Signed-off-by: Sherry Sun Link: https://lore.kernel.org/r/20230801022304.24251-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index f6d0ea2c6be4..c5a9b89c4d31 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1125,8 +1125,8 @@ static void lpuart_copy_rx_to_tty(struct lpuart_port *sport) unsigned long sr = lpuart32_read(&sport->port, UARTSTAT); if (sr & (UARTSTAT_PE | UARTSTAT_FE)) { - /* Read DR to clear the error flags */ - lpuart32_read(&sport->port, UARTDATA); + /* Clear the error flags */ + lpuart32_write(&sport->port, sr, UARTSTAT); if (sr & UARTSTAT_PE) sport->port.icount.parity++; From 9f68e2105dd96cf0fafffffafb2337fbd0fbae1f Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 17 Aug 2023 16:57:30 -0400 Subject: [PATCH 0419/2093] btrfs: fix incorrect splitting in btrfs_drop_extent_map_range commit c962098ca4af146f2625ed64399926a098752c9c upstream. In production we were seeing a variety of WARN_ON()'s in the extent_map code, specifically in btrfs_drop_extent_map_range() when we have to call add_extent_mapping() for our second split. Consider the following extent map layout PINNED [0 16K) [32K, 48K) and then we call btrfs_drop_extent_map_range for [0, 36K), with skip_pinned == true. The initial loop will have start = 0 end = 36K len = 36K we will find the [0, 16k) extent, but since we are pinned we will skip it, which has this code start = em_end; if (end != (u64)-1) len = start + len - em_end; em_end here is 16K, so now the values are start = 16K len = 16K + 36K - 16K = 36K len should instead be 20K. This is a problem when we find the next extent at [32K, 48K), we need to split this extent to leave [36K, 48k), however the code for the split looks like this split->start = start + len; split->len = em_end - (start + len); In this case we have em_end = 48K split->start = 16K + 36K // this should be 16K + 20K split->len = 48K - (16K + 36K) // this overflows as 16K + 36K is 52K and now we have an invalid extent_map in the tree that potentially overlaps other entries in the extent map. Even in the non-overlapping case we will have split->start set improperly, which will cause problems with any block related calculations. We don't actually need len in this loop, we can simply use end as our end point, and only adjust start up when we find a pinned extent we need to skip. Adjust the logic to do this, which keeps us from inserting an invalid extent map. We only skip_pinned in the relocation case, so this is relatively rare, except in the case where you are running relocation a lot, which can happen with auto relocation on. Fixes: 55ef68990029 ("Btrfs: Fix btrfs_drop_extent_cache for skip pinned case") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent_map.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 4abbe4b35253..56d7580fdc3c 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -784,8 +784,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) { start = em_end; - if (end != (u64)-1) - len = start + len - em_end; goto next; } @@ -853,8 +851,8 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, if (!split) goto remove_em; } - split->start = start + len; - split->len = em_end - (start + len); + split->start = end; + split->len = em_end - end; split->block_start = em->block_start; split->flags = flags; split->compress_type = em->compress_type; From ceb9ba8e30833a4823e2dc73f80ebcdf2498d01a Mon Sep 17 00:00:00 2001 From: xiaoshoukui Date: Tue, 15 Aug 2023 02:55:59 -0400 Subject: [PATCH 0420/2093] btrfs: fix BUG_ON condition in btrfs_cancel_balance commit 29eefa6d0d07e185f7bfe9576f91e6dba98189c2 upstream. Pausing and canceling balance can race to interrupt balance lead to BUG_ON panic in btrfs_cancel_balance. The BUG_ON condition in btrfs_cancel_balance does not take this race scenario into account. However, the race condition has no other side effects. We can fix that. Reproducing it with panic trace like this: kernel BUG at fs/btrfs/volumes.c:4618! RIP: 0010:btrfs_cancel_balance+0x5cf/0x6a0 Call Trace: ? do_nanosleep+0x60/0x120 ? hrtimer_nanosleep+0xb7/0x1a0 ? sched_core_clone_cookie+0x70/0x70 btrfs_ioctl_balance_ctl+0x55/0x70 btrfs_ioctl+0xa46/0xd20 __x64_sys_ioctl+0x7d/0xa0 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Race scenario as follows: > mutex_unlock(&fs_info->balance_mutex); > -------------------- > .......issue pause and cancel req in another thread > -------------------- > ret = __btrfs_balance(fs_info); > > mutex_lock(&fs_info->balance_mutex); > if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req)) { > btrfs_info(fs_info, "balance: paused"); > btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE_PAUSED); > } CC: stable@vger.kernel.org # 4.19+ Signed-off-by: xiaoshoukui Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/volumes.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2e0832d70406..567c5c010f93 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4652,8 +4652,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) } } - BUG_ON(fs_info->balance_ctl || - test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); + ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); atomic_dec(&fs_info->balance_cancel_req); mutex_unlock(&fs_info->balance_mutex); return 0; From 52114963307e6e3afa22b07da5f54a682ea1b1a5 Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Wed, 26 Jul 2023 15:00:00 +0700 Subject: [PATCH 0421/2093] i2c: designware: Correct length byte validation logic commit 49d4db3953cb9004ff94efc0c176e026c820af5a upstream. Commit 0daede80f870 ("i2c: designware: Convert driver to using regmap API") changes the logic to validate the whole 32-bit return value of DW_IC_DATA_CMD register instead of 8-bit LSB without reason. Later, commit f53f15ba5a85 ("i2c: designware: Get right data length"), introduced partial fix but not enough because the "tmp > 0" still test tmp as 32-bit value and is wrong in case the IC_DATA_CMD[11] is set. Revert the logic to just before commit 0daede80f870 ("i2c: designware: Convert driver to using regmap API"). Fixes: f53f15ba5a85 ("i2c: designware: Get right data length") Fixes: 0daede80f870 ("i2c: designware: Convert driver to using regmap API") Cc: stable@vger.kernel.org Signed-off-by: Tam Nguyen Signed-off-by: Quan Nguyen Acked-by: Jarkko Nikula Link: https://lore.kernel.org/r/20230726080001.337353-2-tamnguyenchi@os.amperecomputing.com Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-designware-master.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index dc3c5a15a95b..553ce16f0666 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -525,9 +525,10 @@ i2c_dw_read(struct dw_i2c_dev *dev) u32 flags = msgs[dev->msg_read_idx].flags; regmap_read(dev->map, DW_IC_DATA_CMD, &tmp); + tmp &= DW_IC_DATA_CMD_DAT; /* Ensure length byte is a valid value */ if (flags & I2C_M_RECV_LEN && - (tmp & DW_IC_DATA_CMD_DAT) <= I2C_SMBUS_BLOCK_MAX && tmp > 0) { + tmp <= I2C_SMBUS_BLOCK_MAX && tmp > 0) { len = i2c_dw_recv_len(dev, tmp); } *buf++ = tmp; From 5a47c2fa0d393927d1776222bb38fe291899a6c2 Mon Sep 17 00:00:00 2001 From: Tam Nguyen Date: Wed, 26 Jul 2023 15:00:01 +0700 Subject: [PATCH 0422/2093] i2c: designware: Handle invalid SMBus block data response length value commit 69f035c480d76f12bf061148ccfd578e1099e5fc upstream. In the I2C_FUNC_SMBUS_BLOCK_DATA case, the invalid length byte value (outside of 1-32) of the SMBus block data response from the Slave device is not correctly handled by the I2C Designware driver. In case IC_EMPTYFIFO_HOLD_MASTER_EN==1, which cannot be detected from the registers, the Master can be disabled only if the STOP bit is set. Without STOP bit set, the Master remains active, holding the bus until receiving a block data response length. This hangs the bus and is unrecoverable. Avoid this by issuing another dump read to reach the stop condition when an invalid length byte is received. Cc: stable@vger.kernel.org Signed-off-by: Tam Nguyen Acked-by: Jarkko Nikula Link: https://lore.kernel.org/r/20230726080001.337353-3-tamnguyenchi@os.amperecomputing.com Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-designware-master.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 553ce16f0666..004ccb2d9f36 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -527,8 +527,19 @@ i2c_dw_read(struct dw_i2c_dev *dev) regmap_read(dev->map, DW_IC_DATA_CMD, &tmp); tmp &= DW_IC_DATA_CMD_DAT; /* Ensure length byte is a valid value */ - if (flags & I2C_M_RECV_LEN && - tmp <= I2C_SMBUS_BLOCK_MAX && tmp > 0) { + if (flags & I2C_M_RECV_LEN) { + /* + * if IC_EMPTYFIFO_HOLD_MASTER_EN is set, which cannot be + * detected from the registers, the controller can be + * disabled if the STOP bit is set. But it is only set + * after receiving block data response length in + * I2C_FUNC_SMBUS_BLOCK_DATA case. That needs to read + * another byte with STOP bit set when the block data + * response length is invalid to complete the transaction. + */ + if (!tmp || tmp > I2C_SMBUS_BLOCK_MAX) + tmp = 1; + len = i2c_dw_recv_len(dev, tmp); } *buf++ = tmp; From 9a0056276f5f38e188732bd7b6949edca6a80ea1 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 27 Jun 2023 11:31:38 +0800 Subject: [PATCH 0423/2093] net: xfrm: Fix xfrm_address_filter OOB read [ Upstream commit dfa73c17d55b921e1d4e154976de35317e43a93a ] We found below OOB crash: [ 44.211730] ================================================================== [ 44.212045] BUG: KASAN: slab-out-of-bounds in memcmp+0x8b/0xb0 [ 44.212045] Read of size 8 at addr ffff88800870f320 by task poc.xfrm/97 [ 44.212045] [ 44.212045] CPU: 0 PID: 97 Comm: poc.xfrm Not tainted 6.4.0-rc7-00072-gdad9774deaf1-dirty #4 [ 44.212045] Call Trace: [ 44.212045] [ 44.212045] dump_stack_lvl+0x37/0x50 [ 44.212045] print_report+0xcc/0x620 [ 44.212045] ? __virt_addr_valid+0xf3/0x170 [ 44.212045] ? memcmp+0x8b/0xb0 [ 44.212045] kasan_report+0xb2/0xe0 [ 44.212045] ? memcmp+0x8b/0xb0 [ 44.212045] kasan_check_range+0x39/0x1c0 [ 44.212045] memcmp+0x8b/0xb0 [ 44.212045] xfrm_state_walk+0x21c/0x420 [ 44.212045] ? __pfx_dump_one_state+0x10/0x10 [ 44.212045] xfrm_dump_sa+0x1e2/0x290 [ 44.212045] ? __pfx_xfrm_dump_sa+0x10/0x10 [ 44.212045] ? __kernel_text_address+0xd/0x40 [ 44.212045] ? kasan_unpoison+0x27/0x60 [ 44.212045] ? mutex_lock+0x60/0xe0 [ 44.212045] ? __pfx_mutex_lock+0x10/0x10 [ 44.212045] ? kasan_save_stack+0x22/0x50 [ 44.212045] netlink_dump+0x322/0x6c0 [ 44.212045] ? __pfx_netlink_dump+0x10/0x10 [ 44.212045] ? mutex_unlock+0x7f/0xd0 [ 44.212045] ? __pfx_mutex_unlock+0x10/0x10 [ 44.212045] __netlink_dump_start+0x353/0x430 [ 44.212045] xfrm_user_rcv_msg+0x3a4/0x410 [ 44.212045] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 44.212045] ? __pfx_xfrm_user_rcv_msg+0x10/0x10 [ 44.212045] ? __pfx_xfrm_dump_sa+0x10/0x10 [ 44.212045] ? __pfx_xfrm_dump_sa_done+0x10/0x10 [ 44.212045] ? __stack_depot_save+0x382/0x4e0 [ 44.212045] ? filter_irq_stacks+0x1c/0x70 [ 44.212045] ? kasan_save_stack+0x32/0x50 [ 44.212045] ? kasan_save_stack+0x22/0x50 [ 44.212045] ? kasan_set_track+0x25/0x30 [ 44.212045] ? __kasan_slab_alloc+0x59/0x70 [ 44.212045] ? kmem_cache_alloc_node+0xf7/0x260 [ 44.212045] ? kmalloc_reserve+0xab/0x120 [ 44.212045] ? __alloc_skb+0xcf/0x210 [ 44.212045] ? netlink_sendmsg+0x509/0x700 [ 44.212045] ? sock_sendmsg+0xde/0xe0 [ 44.212045] ? __sys_sendto+0x18d/0x230 [ 44.212045] ? __x64_sys_sendto+0x71/0x90 [ 44.212045] ? do_syscall_64+0x3f/0x90 [ 44.212045] ? entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 44.212045] ? netlink_sendmsg+0x509/0x700 [ 44.212045] ? sock_sendmsg+0xde/0xe0 [ 44.212045] ? __sys_sendto+0x18d/0x230 [ 44.212045] ? __x64_sys_sendto+0x71/0x90 [ 44.212045] ? do_syscall_64+0x3f/0x90 [ 44.212045] ? entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 44.212045] ? kasan_save_stack+0x22/0x50 [ 44.212045] ? kasan_set_track+0x25/0x30 [ 44.212045] ? kasan_save_free_info+0x2e/0x50 [ 44.212045] ? __kasan_slab_free+0x10a/0x190 [ 44.212045] ? kmem_cache_free+0x9c/0x340 [ 44.212045] ? netlink_recvmsg+0x23c/0x660 [ 44.212045] ? sock_recvmsg+0xeb/0xf0 [ 44.212045] ? __sys_recvfrom+0x13c/0x1f0 [ 44.212045] ? __x64_sys_recvfrom+0x71/0x90 [ 44.212045] ? do_syscall_64+0x3f/0x90 [ 44.212045] ? entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 44.212045] ? copyout+0x3e/0x50 [ 44.212045] netlink_rcv_skb+0xd6/0x210 [ 44.212045] ? __pfx_xfrm_user_rcv_msg+0x10/0x10 [ 44.212045] ? __pfx_netlink_rcv_skb+0x10/0x10 [ 44.212045] ? __pfx_sock_has_perm+0x10/0x10 [ 44.212045] ? mutex_lock+0x8d/0xe0 [ 44.212045] ? __pfx_mutex_lock+0x10/0x10 [ 44.212045] xfrm_netlink_rcv+0x44/0x50 [ 44.212045] netlink_unicast+0x36f/0x4c0 [ 44.212045] ? __pfx_netlink_unicast+0x10/0x10 [ 44.212045] ? netlink_recvmsg+0x500/0x660 [ 44.212045] netlink_sendmsg+0x3b7/0x700 [ 44.212045] ? __pfx_netlink_sendmsg+0x10/0x10 [ 44.212045] ? __pfx_netlink_sendmsg+0x10/0x10 [ 44.212045] sock_sendmsg+0xde/0xe0 [ 44.212045] __sys_sendto+0x18d/0x230 [ 44.212045] ? __pfx___sys_sendto+0x10/0x10 [ 44.212045] ? rcu_core+0x44a/0xe10 [ 44.212045] ? __rseq_handle_notify_resume+0x45b/0x740 [ 44.212045] ? _raw_spin_lock_irq+0x81/0xe0 [ 44.212045] ? __pfx___rseq_handle_notify_resume+0x10/0x10 [ 44.212045] ? __pfx_restore_fpregs_from_fpstate+0x10/0x10 [ 44.212045] ? __pfx_blkcg_maybe_throttle_current+0x10/0x10 [ 44.212045] ? __pfx_task_work_run+0x10/0x10 [ 44.212045] __x64_sys_sendto+0x71/0x90 [ 44.212045] do_syscall_64+0x3f/0x90 [ 44.212045] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 44.212045] RIP: 0033:0x44b7da [ 44.212045] RSP: 002b:00007ffdc8838548 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 44.212045] RAX: ffffffffffffffda RBX: 00007ffdc8839978 RCX: 000000000044b7da [ 44.212045] RDX: 0000000000000038 RSI: 00007ffdc8838770 RDI: 0000000000000003 [ 44.212045] RBP: 00007ffdc88385b0 R08: 00007ffdc883858c R09: 000000000000000c [ 44.212045] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 [ 44.212045] R13: 00007ffdc8839968 R14: 00000000004c37d0 R15: 0000000000000001 [ 44.212045] [ 44.212045] [ 44.212045] Allocated by task 97: [ 44.212045] kasan_save_stack+0x22/0x50 [ 44.212045] kasan_set_track+0x25/0x30 [ 44.212045] __kasan_kmalloc+0x7f/0x90 [ 44.212045] __kmalloc_node_track_caller+0x5b/0x140 [ 44.212045] kmemdup+0x21/0x50 [ 44.212045] xfrm_dump_sa+0x17d/0x290 [ 44.212045] netlink_dump+0x322/0x6c0 [ 44.212045] __netlink_dump_start+0x353/0x430 [ 44.212045] xfrm_user_rcv_msg+0x3a4/0x410 [ 44.212045] netlink_rcv_skb+0xd6/0x210 [ 44.212045] xfrm_netlink_rcv+0x44/0x50 [ 44.212045] netlink_unicast+0x36f/0x4c0 [ 44.212045] netlink_sendmsg+0x3b7/0x700 [ 44.212045] sock_sendmsg+0xde/0xe0 [ 44.212045] __sys_sendto+0x18d/0x230 [ 44.212045] __x64_sys_sendto+0x71/0x90 [ 44.212045] do_syscall_64+0x3f/0x90 [ 44.212045] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 44.212045] [ 44.212045] The buggy address belongs to the object at ffff88800870f300 [ 44.212045] which belongs to the cache kmalloc-64 of size 64 [ 44.212045] The buggy address is located 32 bytes inside of [ 44.212045] allocated 36-byte region [ffff88800870f300, ffff88800870f324) [ 44.212045] [ 44.212045] The buggy address belongs to the physical page: [ 44.212045] page:00000000e4de16ee refcount:1 mapcount:0 mapping:000000000 ... [ 44.212045] flags: 0x100000000000200(slab|node=0|zone=1) [ 44.212045] page_type: 0xffffffff() [ 44.212045] raw: 0100000000000200 ffff888004c41640 dead000000000122 0000000000000000 [ 44.212045] raw: 0000000000000000 0000000080200020 00000001ffffffff 0000000000000000 [ 44.212045] page dumped because: kasan: bad access detected [ 44.212045] [ 44.212045] Memory state around the buggy address: [ 44.212045] ffff88800870f200: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 44.212045] ffff88800870f280: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc [ 44.212045] >ffff88800870f300: 00 00 00 00 04 fc fc fc fc fc fc fc fc fc fc fc [ 44.212045] ^ [ 44.212045] ffff88800870f380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 44.212045] ffff88800870f400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 44.212045] ================================================================== By investigating the code, we find the root cause of this OOB is the lack of checks in xfrm_dump_sa(). The buggy code allows a malicious user to pass arbitrary value of filter->splen/dplen. Hence, with crafted xfrm states, the attacker can achieve 8 bytes heap OOB read, which causes info leak. if (attrs[XFRMA_ADDRESS_FILTER]) { filter = kmemdup(nla_data(attrs[XFRMA_ADDRESS_FILTER]), sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; // NO MORE CHECKS HERE !!! } This patch fixes the OOB by adding necessary boundary checks, just like the code in pfkey_dump() function. Fixes: d3623099d350 ("ipsec: add support of limited SA dump") Signed-off-by: Lin Ma Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_user.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2d68a173b227..3e32fe99a681 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1250,6 +1250,15 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; + + /* see addr_match(), (prefix length >> 5) << 2 + * will be used to compare xfrm_address_t + */ + if (filter->splen > (sizeof(xfrm_address_t) << 3) || + filter->dplen > (sizeof(xfrm_address_t) << 3)) { + kfree(filter); + return -EINVAL; + } } if (attrs[XFRMA_PROTO]) From 479884b4ce16ea6a4cc5a4392f8d778616db9e26 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 27 Jun 2023 11:39:54 +0800 Subject: [PATCH 0424/2093] net: af_key: fix sadb_x_filter validation [ Upstream commit 75065a8929069bc93181848818e23f147a73f83a ] When running xfrm_state_walk_init(), the xfrm_address_filter being used is okay to have a splen/dplen that equals to sizeof(xfrm_address_t)<<3. This commit replaces >= to > to make sure the boundary checking is correct. Fixes: 37bd22420f85 ("af_key: pfkey_dump needs parameter validation") Signed-off-by: Lin Ma Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/key/af_key.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index 8c21de50eadf..8a8f2429d5d9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1848,9 +1848,9 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; - if ((xfilter->sadb_x_filter_splen >= + if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || - (xfilter->sadb_x_filter_dplen >= + (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; From 71dfe71df100fa807660fa16f4a0a66cffeb7f46 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Fri, 30 Jun 2023 16:19:11 +0800 Subject: [PATCH 0425/2093] net: xfrm: Amend XFRMA_SEC_CTX nla_policy structure [ Upstream commit d1e0e61d617ba17aa516db707aa871387566bbf7 ] According to all consumers code of attrs[XFRMA_SEC_CTX], like * verify_sec_ctx_len(), convert to xfrm_user_sec_ctx* * xfrm_state_construct(), call security_xfrm_state_alloc whose prototype is int security_xfrm_state_alloc(.., struct xfrm_user_sec_ctx *sec_ctx); * copy_from_user_sec_ctx(), convert to xfrm_user_sec_ctx * ... It seems that the expected parsing result for XFRMA_SEC_CTX should be structure xfrm_user_sec_ctx, and the current xfrm_sec_ctx is confusing and misleading (Luckily, they happen to have same size 8 bytes). This commit amend the policy structure to xfrm_user_sec_ctx to avoid ambiguity. Fixes: cf5cb79f6946 ("[XFRM] netlink: Establish an attribute policy") Signed-off-by: Lin Ma Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_compat.c | 2 +- net/xfrm/xfrm_user.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 8cbf45a8bcdc..655fe4ff8621 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -108,7 +108,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3e32fe99a681..c6803318ac63 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2969,7 +2969,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, From 0d27567fde5be5f0edc2db5c110142b7915b8fa8 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 10 Jul 2023 17:40:51 +0800 Subject: [PATCH 0426/2093] xfrm: fix slab-use-after-free in decode_session6 [ Upstream commit 53223f2ed1ef5c90dad814daaaefea4e68a933c8 ] When the xfrm device is set to the qdisc of the sfb type, the cb field of the sent skb may be modified during enqueuing. Then, slab-use-after-free may occur when the xfrm device sends IPv6 packets. The stack information is as follows: BUG: KASAN: slab-use-after-free in decode_session6+0x103f/0x1890 Read of size 1 at addr ffff8881111458ef by task swapper/3/0 CPU: 3 PID: 0 Comm: swapper/3 Not tainted 6.4.0-next-20230707 #409 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 Call Trace: dump_stack_lvl+0xd9/0x150 print_address_description.constprop.0+0x2c/0x3c0 kasan_report+0x11d/0x130 decode_session6+0x103f/0x1890 __xfrm_decode_session+0x54/0xb0 xfrmi_xmit+0x173/0x1ca0 dev_hard_start_xmit+0x187/0x700 sch_direct_xmit+0x1a3/0xc30 __qdisc_run+0x510/0x17a0 __dev_queue_xmit+0x2215/0x3b10 neigh_connected_output+0x3c2/0x550 ip6_finish_output2+0x55a/0x1550 ip6_finish_output+0x6b9/0x1270 ip6_output+0x1f1/0x540 ndisc_send_skb+0xa63/0x1890 ndisc_send_rs+0x132/0x6f0 addrconf_rs_timer+0x3f1/0x870 call_timer_fn+0x1a0/0x580 expire_timers+0x29b/0x4b0 run_timer_softirq+0x326/0x910 __do_softirq+0x1d4/0x905 irq_exit_rcu+0xb7/0x120 sysvec_apic_timer_interrupt+0x97/0xc0 asm_sysvec_apic_timer_interrupt+0x1a/0x20 RIP: 0010:intel_idle_hlt+0x23/0x30 Code: 1f 84 00 00 00 00 00 f3 0f 1e fa 41 54 41 89 d4 0f 1f 44 00 00 66 90 0f 1f 44 00 00 0f 00 2d c4 9f ab 00 0f 1f 44 00 00 fb f4 44 89 e0 41 5c c3 66 0f 1f 44 00 00 f3 0f 1e fa 41 54 41 89 d4 RSP: 0018:ffffc90000197d78 EFLAGS: 00000246 RAX: 00000000000a83c3 RBX: ffffe8ffffd09c50 RCX: ffffffff8a22d8e5 RDX: 0000000000000001 RSI: ffffffff8d3f8080 RDI: ffffe8ffffd09c50 RBP: ffffffff8d3f8080 R08: 0000000000000001 R09: ffffed1026ba6d9d R10: ffff888135d36ceb R11: 0000000000000001 R12: 0000000000000001 R13: ffffffff8d3f8100 R14: 0000000000000001 R15: 0000000000000000 cpuidle_enter_state+0xd3/0x6f0 cpuidle_enter+0x4e/0xa0 do_idle+0x2fe/0x3c0 cpu_startup_entry+0x18/0x20 start_secondary+0x200/0x290 secondary_startup_64_no_verify+0x167/0x16b Allocated by task 939: kasan_save_stack+0x22/0x40 kasan_set_track+0x25/0x30 __kasan_slab_alloc+0x7f/0x90 kmem_cache_alloc_node+0x1cd/0x410 kmalloc_reserve+0x165/0x270 __alloc_skb+0x129/0x330 inet6_ifa_notify+0x118/0x230 __ipv6_ifa_notify+0x177/0xbe0 addrconf_dad_completed+0x133/0xe00 addrconf_dad_work+0x764/0x1390 process_one_work+0xa32/0x16f0 worker_thread+0x67d/0x10c0 kthread+0x344/0x440 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff888111145800 which belongs to the cache skbuff_small_head of size 640 The buggy address is located 239 bytes inside of freed 640-byte region [ffff888111145800, ffff888111145a80) As commit f855691975bb ("xfrm6: Fix the nexthdr offset in _decode_session6.") showed, xfrm_decode_session was originally intended only for the receive path. IP6CB(skb)->nhoff is not set during transmission. Therefore, set the cb field in the skb to 0 before sending packets. Fixes: f855691975bb ("xfrm6: Fix the nexthdr offset in _decode_session6.") Signed-off-by: Zhengchao Shao Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_interface_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 94a3609548b1..d71dbe822096 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -528,8 +528,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; @@ -543,8 +543,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) } break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); if (!dst) { struct rtable *rt; From 55ad2309205cc00c585344374c7472420e1b2c12 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 10 Jul 2023 17:40:52 +0800 Subject: [PATCH 0427/2093] ip6_vti: fix slab-use-after-free in decode_session6 [ Upstream commit 9fd41f1ba638938c9a1195d09bc6fa3be2712f25 ] When ipv6_vti device is set to the qdisc of the sfb type, the cb field of the sent skb may be modified during enqueuing. Then, slab-use-after-free may occur when ipv6_vti device sends IPv6 packets. The stack information is as follows: BUG: KASAN: slab-use-after-free in decode_session6+0x103f/0x1890 Read of size 1 at addr ffff88802e08edc2 by task swapper/0/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.4.0-next-20230707-00001-g84e2cad7f979 #410 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 Call Trace: dump_stack_lvl+0xd9/0x150 print_address_description.constprop.0+0x2c/0x3c0 kasan_report+0x11d/0x130 decode_session6+0x103f/0x1890 __xfrm_decode_session+0x54/0xb0 vti6_tnl_xmit+0x3e6/0x1ee0 dev_hard_start_xmit+0x187/0x700 sch_direct_xmit+0x1a3/0xc30 __qdisc_run+0x510/0x17a0 __dev_queue_xmit+0x2215/0x3b10 neigh_connected_output+0x3c2/0x550 ip6_finish_output2+0x55a/0x1550 ip6_finish_output+0x6b9/0x1270 ip6_output+0x1f1/0x540 ndisc_send_skb+0xa63/0x1890 ndisc_send_rs+0x132/0x6f0 addrconf_rs_timer+0x3f1/0x870 call_timer_fn+0x1a0/0x580 expire_timers+0x29b/0x4b0 run_timer_softirq+0x326/0x910 __do_softirq+0x1d4/0x905 irq_exit_rcu+0xb7/0x120 sysvec_apic_timer_interrupt+0x97/0xc0 Allocated by task 9176: kasan_save_stack+0x22/0x40 kasan_set_track+0x25/0x30 __kasan_slab_alloc+0x7f/0x90 kmem_cache_alloc_node+0x1cd/0x410 kmalloc_reserve+0x165/0x270 __alloc_skb+0x129/0x330 netlink_sendmsg+0x9b1/0xe30 sock_sendmsg+0xde/0x190 ____sys_sendmsg+0x739/0x920 ___sys_sendmsg+0x110/0x1b0 __sys_sendmsg+0xf7/0x1c0 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 9176: kasan_save_stack+0x22/0x40 kasan_set_track+0x25/0x30 kasan_save_free_info+0x2b/0x40 ____kasan_slab_free+0x160/0x1c0 slab_free_freelist_hook+0x11b/0x220 kmem_cache_free+0xf0/0x490 skb_free_head+0x17f/0x1b0 skb_release_data+0x59c/0x850 consume_skb+0xd2/0x170 netlink_unicast+0x54f/0x7f0 netlink_sendmsg+0x926/0xe30 sock_sendmsg+0xde/0x190 ____sys_sendmsg+0x739/0x920 ___sys_sendmsg+0x110/0x1b0 __sys_sendmsg+0xf7/0x1c0 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd The buggy address belongs to the object at ffff88802e08ed00 which belongs to the cache skbuff_small_head of size 640 The buggy address is located 194 bytes inside of freed 640-byte region [ffff88802e08ed00, ffff88802e08ef80) As commit f855691975bb ("xfrm6: Fix the nexthdr offset in _decode_session6.") showed, xfrm_decode_session was originally intended only for the receive path. IP6CB(skb)->nhoff is not set during transmission. Therefore, set the cb field in the skb to 0 before sending packets. Fixes: f855691975bb ("xfrm6: Fix the nexthdr offset in _decode_session6.") Signed-off-by: Zhengchao Shao Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/ipv6/ip6_vti.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 151337d7f67b..cb71463bbbab 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -570,12 +570,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; default: goto tx_err; From 2b05bf5dc437f7891dd409a3eaf5058459391c7a Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 10 Jul 2023 17:40:53 +0800 Subject: [PATCH 0428/2093] ip_vti: fix potential slab-use-after-free in decode_session6 [ Upstream commit 6018a266279b1a75143c7c0804dd08a5fc4c3e0b ] When ip_vti device is set to the qdisc of the sfb type, the cb field of the sent skb may be modified during enqueuing. Then, slab-use-after-free may occur when ip_vti device sends IPv6 packets. As commit f855691975bb ("xfrm6: Fix the nexthdr offset in _decode_session6.") showed, xfrm_decode_session was originally intended only for the receive path. IP6CB(skb)->nhoff is not set during transmission. Therefore, set the cb field in the skb to 0 before sending packets. Fixes: f855691975bb ("xfrm6: Fix the nexthdr offset in _decode_session6.") Signed-off-by: Zhengchao Shao Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/ipv4/ip_vti.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 8c2bd1d9ddce..615c1dcf3a28 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -287,12 +287,12 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; default: goto tx_err; From 87b655f4936b6fc01f3658aa88a22c923b379ebd Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Fri, 21 Jul 2023 22:51:03 +0800 Subject: [PATCH 0429/2093] xfrm: add NULL check in xfrm_update_ae_params [ Upstream commit 00374d9b6d9f932802b55181be9831aa948e5b7c ] Normally, x->replay_esn and x->preplay_esn should be allocated at xfrm_alloc_replay_state_esn(...) in xfrm_state_construct(...), hence the xfrm_update_ae_params(...) is okay to update them. However, the current implementation of xfrm_new_ae(...) allows a malicious user to directly dereference a NULL pointer and crash the kernel like below. BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 8253067 P4D 8253067 PUD 8e0e067 PMD 0 Oops: 0002 [#1] PREEMPT SMP KASAN NOPTI CPU: 0 PID: 98 Comm: poc.npd Not tainted 6.4.0-rc7-00072-gdad9774deaf1 #8 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.o4 RIP: 0010:memcpy_orig+0xad/0x140 Code: e8 4c 89 5f e0 48 8d 7f e0 73 d2 83 c2 20 48 29 d6 48 29 d7 83 fa 10 72 34 4c 8b 06 4c 8b 4e 08 c RSP: 0018:ffff888008f57658 EFLAGS: 00000202 RAX: 0000000000000000 RBX: ffff888008bd0000 RCX: ffffffff8238e571 RDX: 0000000000000018 RSI: ffff888007f64844 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff888008f57818 R13: ffff888007f64aa4 R14: 0000000000000000 R15: 0000000000000000 FS: 00000000014013c0(0000) GS:ffff88806d600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000054d8000 CR4: 00000000000006f0 Call Trace: ? __die+0x1f/0x70 ? page_fault_oops+0x1e8/0x500 ? __pfx_is_prefetch.constprop.0+0x10/0x10 ? __pfx_page_fault_oops+0x10/0x10 ? _raw_spin_unlock_irqrestore+0x11/0x40 ? fixup_exception+0x36/0x460 ? _raw_spin_unlock_irqrestore+0x11/0x40 ? exc_page_fault+0x5e/0xc0 ? asm_exc_page_fault+0x26/0x30 ? xfrm_update_ae_params+0xd1/0x260 ? memcpy_orig+0xad/0x140 ? __pfx__raw_spin_lock_bh+0x10/0x10 xfrm_update_ae_params+0xe7/0x260 xfrm_new_ae+0x298/0x4e0 ? __pfx_xfrm_new_ae+0x10/0x10 ? __pfx_xfrm_new_ae+0x10/0x10 xfrm_user_rcv_msg+0x25a/0x410 ? __pfx_xfrm_user_rcv_msg+0x10/0x10 ? __alloc_skb+0xcf/0x210 ? stack_trace_save+0x90/0xd0 ? filter_irq_stacks+0x1c/0x70 ? __stack_depot_save+0x39/0x4e0 ? __kasan_slab_free+0x10a/0x190 ? kmem_cache_free+0x9c/0x340 ? netlink_recvmsg+0x23c/0x660 ? sock_recvmsg+0xeb/0xf0 ? __sys_recvfrom+0x13c/0x1f0 ? __x64_sys_recvfrom+0x71/0x90 ? do_syscall_64+0x3f/0x90 ? entry_SYSCALL_64_after_hwframe+0x72/0xdc ? copyout+0x3e/0x50 netlink_rcv_skb+0xd6/0x210 ? __pfx_xfrm_user_rcv_msg+0x10/0x10 ? __pfx_netlink_rcv_skb+0x10/0x10 ? __pfx_sock_has_perm+0x10/0x10 ? mutex_lock+0x8d/0xe0 ? __pfx_mutex_lock+0x10/0x10 xfrm_netlink_rcv+0x44/0x50 netlink_unicast+0x36f/0x4c0 ? __pfx_netlink_unicast+0x10/0x10 ? netlink_recvmsg+0x500/0x660 netlink_sendmsg+0x3b7/0x700 This Null-ptr-deref bug is assigned CVE-2023-3772. And this commit adds additional NULL check in xfrm_update_ae_params to fix the NPD. Fixes: d8647b79c3b7 ("xfrm: Add user interface for esn and big anti-replay windows") Signed-off-by: Lin Ma Reviewed-by: Leon Romanovsky Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c6803318ac63..9fc1da47d02e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -615,7 +615,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; struct nlattr *mt = attrs[XFRMA_MTIMER_THRESH]; - if (re) { + if (re && x->replay_esn && x->preplay_esn) { struct xfrm_replay_state_esn *replay_esn; replay_esn = nla_data(re); memcpy(x->replay_esn, replay_esn, From a442cd17019385c53bbddf3bb92d91474081916b Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 23 Jul 2023 15:41:10 +0800 Subject: [PATCH 0430/2093] xfrm: add forgotten nla_policy for XFRMA_MTIMER_THRESH [ Upstream commit 5e2424708da7207087934c5c75211e8584d553a0 ] The previous commit 4e484b3e969b ("xfrm: rate limit SA mapping change message to user space") added one additional attribute named XFRMA_MTIMER_THRESH and described its type at compat_policy (net/xfrm/xfrm_compat.c). However, the author forgot to also describe the nla_policy at xfrma_policy (net/xfrm/xfrm_user.c). Hence, this suppose NLA_U32 (4 bytes) value can be faked as empty (0 bytes) by a malicious user, which leads to 4 bytes overflow read and heap information leak when parsing nlattrs. To exploit this, one malicious user can spray the SLUB objects and then leverage this 4 bytes OOB read to leak the heap data into x->mapping_maxage (see xfrm_update_ae_params(...)), and leak it to userspace via copy_to_user_state_extra(...). The above bug is assigned CVE-2023-3773. To fix it, this commit just completes the nla_policy description for XFRMA_MTIMER_THRESH, which enforces the length check and avoids such OOB read. Fixes: 4e484b3e969b ("xfrm: rate limit SA mapping change message to user space") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Reviewed-by: Leon Romanovsky Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 9fc1da47d02e..d042ca01211f 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2989,6 +2989,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, + [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); From 45085ba966fb10e167dab8c229651b5ecee48b66 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Fri, 27 Jan 2023 21:45:00 +0100 Subject: [PATCH 0431/2093] virtio_net: notify MAC address change on device initialization [ Upstream commit 9f62d221a4b0aa6a8d2a18053a0ca349c025297c ] In virtnet_probe(), if the device doesn't provide a MAC address the driver assigns a random one. As we modify the MAC address we need to notify the device to allow it to update all the related information. The problem can be seen with vDPA and mlx5_vdpa driver as it doesn't assign a MAC address by default. The virtio_net device uses a random MAC address (we can see it with "ip link"), but we can't ping a net namespace from another one using the virtio-vdpa device because the new MAC address has not been provided to the hardware: RX packets are dropped since they don't go through the receive filters, TX packets go through unaffected. Signed-off-by: Laurent Vivier Acked-by: Michael S. Tsirkin Signed-off-by: Jakub Kicinski Stable-dep-of: 51b813176f09 ("virtio-net: set queues after driver_ok") Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 075d5d42f5eb..b7a4df4bab81 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3825,6 +3825,8 @@ static int virtnet_probe(struct virtio_device *vdev) eth_hw_addr_set(dev, addr); } else { eth_hw_addr_random(dev); + dev_info(&vdev->dev, "Assigned random MAC address %pM\n", + dev->dev_addr); } /* Set up our device-specific information */ @@ -3954,6 +3956,24 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_device_ready(vdev); + /* a random MAC address has been assigned, notify the device. + * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there + * because many devices work fine without getting MAC explicitly + */ + if (!virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && + virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { + struct scatterlist sg; + + sg_init_one(&sg, dev->dev_addr, dev->addr_len); + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, + VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { + pr_debug("virtio_net: setting MAC address failed\n"); + rtnl_unlock(); + err = -EINVAL; + goto free_unregister_netdev; + } + } + rtnl_unlock(); err = virtnet_cpu_notif_add(vi); From 120a89c36d3d9fb8cfe6bcfa97a2347bb3ba1178 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 9 Aug 2023 23:12:56 -0400 Subject: [PATCH 0432/2093] virtio-net: set queues after driver_ok [ Upstream commit 51b813176f098ff61bd2833f627f5319ead098a5 ] Commit 25266128fe16 ("virtio-net: fix race between set queues and probe") tries to fix the race between set queues and probe by calling _virtnet_set_queues() before DRIVER_OK is set. This violates virtio spec. Fixing this by setting queues after virtio_device_ready(). Note that rtnl needs to be held for userspace requests to change the number of queues. So we are serialized in this way. Fixes: 25266128fe16 ("virtio-net: fix race between set queues and probe") Reported-by: Dragos Tatulea Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b7a4df4bab81..55c20ccb791e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3942,8 +3942,6 @@ static int virtnet_probe(struct virtio_device *vdev) if (vi->has_rss || vi->has_rss_hash_report) virtnet_init_default_rss(vi); - _virtnet_set_queues(vi, vi->curr_queue_pairs); - /* serialize netdev register + virtio_device_ready() with ndo_open() */ rtnl_lock(); @@ -3956,6 +3954,8 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_device_ready(vdev); + _virtnet_set_queues(vi, vi->curr_queue_pairs); + /* a random MAC address has been assigned, notify the device. * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there * because many devices work fine without getting MAC explicitly From a41e5a79a0597cd390e564fcc6ab7cb5297c1372 Mon Sep 17 00:00:00 2001 From: Xiang Yang Date: Thu, 10 Aug 2023 22:06:39 +0800 Subject: [PATCH 0433/2093] net: pcs: Add missing put_device call in miic_create [ Upstream commit 829c6524d6729d05a82575dbcc16f99be5ee843d ] The reference of pdev->dev is taken by of_find_device_by_node, so it should be released when not need anymore. Fixes: 7dc54d3b8d91 ("net: pcs: add Renesas MII converter driver") Signed-off-by: Xiang Yang Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/pcs/pcs-rzn1-miic.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index c1424119e821..847ab37f1367 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -317,15 +317,21 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np) pdev = of_find_device_by_node(pcs_np); of_node_put(pcs_np); - if (!pdev || !platform_get_drvdata(pdev)) + if (!pdev || !platform_get_drvdata(pdev)) { + if (pdev) + put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); + } miic_port = kzalloc(sizeof(*miic_port), GFP_KERNEL); - if (!miic_port) + if (!miic_port) { + put_device(&pdev->dev); return ERR_PTR(-ENOMEM); + } miic = platform_get_drvdata(pdev); device_link_add(dev, miic->dev, DL_FLAG_AUTOREMOVE_CONSUMER); + put_device(&pdev->dev); miic_port->miic = miic; miic_port->port = port - 1; From cd4460b21741a58e5ac7bddfc6689b36a1b515a7 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 11 Aug 2023 11:26:30 +0100 Subject: [PATCH 0434/2093] net: phy: fix IRQ-based wake-on-lan over hibernate / power off MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit cc941e548bffc01b5816b4edc5cb432a137a58b3 ] Uwe reports: "Most PHYs signal WoL using an interrupt. So disabling interrupts [at shutdown] breaks WoL at least on PHYs covered by the marvell driver." Discussing with Ioana, the problem which was trying to be solved was: "The board in question is a LS1021ATSN which has two AR8031 PHYs that share an interrupt line. In case only one of the PHYs is probed and there are pending interrupts on the PHY#2 an IRQ storm will happen since there is no entity to clear the interrupt from PHY#2's registers. PHY#1's driver will get stuck in .handle_interrupt() indefinitely." Further confirmation that "the two AR8031 PHYs are on the same MDIO bus." With WoL using interrupts to wake the system, in such a case, the system will begin booting with an asserted interrupt. Thus, we need to cope with an interrupt asserted during boot. Solve this instead by disabling interrupts during PHY probe. This will ensure in Ioana's situation that both PHYs of the same type sharing an interrupt line on a common MDIO bus will have their interrupt outputs disabled when the driver probes the device, but before we hook in any interrupt handlers - thus avoiding the interrupt storm. A better fix would be for platform firmware to disable the interrupting devices at source during boot, before control is handed to the kernel. Fixes: e2f016cf7751 ("net: phy: add a shutdown procedure") Link: 20230804071757.383971-1-u.kleine-koenig@pengutronix.de Reported-by: Uwe Kleine-König Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/phy_device.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 82f74f96eba2..944f76e6fc8e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3050,6 +3050,8 @@ static int phy_probe(struct device *dev) goto out; } + phy_disable_interrupts(phydev); + /* Start out supporting everything. Eventually, * a controller will attach, and may modify one * or both of these values @@ -3137,16 +3139,6 @@ static int phy_remove(struct device *dev) return 0; } -static void phy_shutdown(struct device *dev) -{ - struct phy_device *phydev = to_phy_device(dev); - - if (phydev->state == PHY_READY || !phydev->attached_dev) - return; - - phy_disable_interrupts(phydev); -} - /** * phy_driver_register - register a phy_driver with the PHY layer * @new_driver: new phy_driver to register @@ -3180,7 +3172,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) new_driver->mdiodrv.driver.bus = &mdio_bus_type; new_driver->mdiodrv.driver.probe = phy_probe; new_driver->mdiodrv.driver.remove = phy_remove; - new_driver->mdiodrv.driver.shutdown = phy_shutdown; new_driver->mdiodrv.driver.owner = owner; new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS; From 2f07f1302ecba4400b8471a5be26750b5cfd9364 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Fri, 11 Aug 2023 17:59:27 +0200 Subject: [PATCH 0435/2093] selftests: mirror_gre_changes: Tighten up the TTL test match [ Upstream commit 855067defa36b1f9effad8c219d9a85b655cf500 ] This test verifies whether the encapsulated packets have the correct configured TTL. It does so by sending ICMP packets through the test topology and mirroring them to a gretap netdevice. On a busy host however, more than just the test ICMP packets may end up flowing through the topology, get mirrored, and counted. This leads to potential spurious failures as the test observes much more mirrored packets than the sent test packets, and assumes a bug. Fix this by tightening up the mirror action match. Change it from matchall to a flower classifier matching on ICMP packets specifically. Fixes: 45315673e0c5 ("selftests: forwarding: Test changes in mirror-to-gretap") Signed-off-by: Petr Machata Tested-by: Mirsad Todorovac Reviewed-by: Ido Schimmel Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- tools/testing/selftests/net/forwarding/mirror_gre_changes.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index aff88f78e339..5ea9d63915f7 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -72,7 +72,8 @@ test_span_gre_ttl() RET=0 - mirror_install $swp1 ingress $tundev "matchall $tcflags" + mirror_install $swp1 ingress $tundev \ + "prot ip flower $tcflags ip_prot icmp" tc filter add dev $h3 ingress pref 77 prot $prot \ flower skip_hw ip_ttl 50 action pass From 06af678c60803acf01626e8f2846d88195f991eb Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Fri, 4 Aug 2023 17:12:39 +0200 Subject: [PATCH 0436/2093] drm/panel: simple: Fix AUO G121EAN01 panel timings according to the docs [ Upstream commit e8470c0a7bcaa82f78ad34282d662dd7bd9630c2 ] Commit 03e909acd95a ("drm/panel: simple: Add support for AUO G121EAN01.4 panel") added support for this panel model, but the timings it implements are very different from what the datasheet describes. I checked both the G121EAN01.0 datasheet from [0] and the G121EAN01.4 one from [1] and they all have the same timings: for example the LVDS clock typical value is 74.4 MHz, not 66.7 MHz as implemented. Replace the timings with the ones from the documentation. These timings have been tested and the clock frequencies verified with an oscilloscope to ensure they are correct. Also use struct display_timing instead of struct drm_display_mode in order to also specify the minimum and maximum values. [0] https://embedded.avnet.com/product/g121ean01-0/ [1] https://embedded.avnet.com/product/g121ean01-4/ Fixes: 03e909acd95a ("drm/panel: simple: Add support for AUO G121EAN01.4 panel") Signed-off-by: Luca Ceresoli Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230804151239.835216-1-luca.ceresoli@bootlin.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-simple.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index f851aaf2c591..5e067ba7e5fb 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -969,21 +969,21 @@ static const struct panel_desc auo_g104sn02 = { .connector_type = DRM_MODE_CONNECTOR_LVDS, }; -static const struct drm_display_mode auo_g121ean01_mode = { - .clock = 66700, - .hdisplay = 1280, - .hsync_start = 1280 + 58, - .hsync_end = 1280 + 58 + 8, - .htotal = 1280 + 58 + 8 + 70, - .vdisplay = 800, - .vsync_start = 800 + 6, - .vsync_end = 800 + 6 + 4, - .vtotal = 800 + 6 + 4 + 10, +static const struct display_timing auo_g121ean01_timing = { + .pixelclock = { 60000000, 74400000, 90000000 }, + .hactive = { 1280, 1280, 1280 }, + .hfront_porch = { 20, 50, 100 }, + .hback_porch = { 20, 50, 100 }, + .hsync_len = { 30, 100, 200 }, + .vactive = { 800, 800, 800 }, + .vfront_porch = { 2, 10, 25 }, + .vback_porch = { 2, 10, 25 }, + .vsync_len = { 4, 18, 50 }, }; static const struct panel_desc auo_g121ean01 = { - .modes = &auo_g121ean01_mode, - .num_modes = 1, + .timings = &auo_g121ean01_timing, + .num_timings = 1, .bpc = 8, .size = { .width = 261, From 58a54bad3a7605bf43e86911a570f6a8ab234e70 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Mon, 7 Aug 2023 18:44:51 +0530 Subject: [PATCH 0437/2093] net: macb: In ZynqMP resume always configure PS GTR for non-wakeup source [ Upstream commit 6c461e394d11a981c662cc16cebfb05b602e23ba ] On Zynq UltraScale+ MPSoC ubuntu platform when systemctl issues suspend, network manager bring down the interface and goes into suspend. When it wakes up it again enables the interface. This leads to xilinx-psgtr "PLL lock timeout" on interface bringup, as the power management controller power down the entire FPD (including SERDES) if none of the FPD devices are in use and serdes is not initialized on resume. $ sudo rtcwake -m no -s 120 -v $ sudo systemctl suspend $ ifconfig eth1 up xilinx-psgtr fd400000.phy: lane 0 (type 10, protocol 5): PLL lock timeout phy phy-fd400000.phy.0: phy poweron failed --> -110 macb driver is called in this way: 1. macb_close: Stop network interface. In this function, it reset MACB IP and disables PHY and network interface. 2. macb_suspend: It is called in kernel suspend flow. But because network interface has been disabled(netif_running(ndev) is false), it does nothing and returns directly; 3. System goes into suspend state. Some time later, system is waken up by RTC wakeup device; 4. macb_resume: It does nothing because network interface has been disabled; 5. macb_open: It is called to enable network interface again. ethernet interface is initialized in this API but serdes which is power-off by PMUFW during FPD-off suspend is not initialized again and so we hit GT PLL lock issue on open. To resolve this PLL timeout issue always do PS GTR initialization when ethernet device is configured as non-wakeup source. Fixes: f22bd29ba19a ("net: macb: Fix ZynqMP SGMII non-wakeup source resume failure") Fixes: 8b73fa3ae02b ("net: macb: Added ZynqMP-specific initialization") Signed-off-by: Radhey Shyam Pandey Link: https://lore.kernel.org/r/1691414091-2260697-1-git-send-email-radhey.shyam.pandey@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/cadence/macb_main.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index abd6cc0cd641..5fb991835078 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5070,6 +5070,9 @@ static int __maybe_unused macb_suspend(struct device *dev) unsigned int q; int err; + if (!device_may_wakeup(&bp->dev->dev)) + phy_exit(bp->sgmii_phy); + if (!netif_running(netdev)) return 0; @@ -5130,7 +5133,6 @@ static int __maybe_unused macb_suspend(struct device *dev) if (!(bp->wol & MACB_WOL_ENABLED)) { rtnl_lock(); phylink_stop(bp->phylink); - phy_exit(bp->sgmii_phy); rtnl_unlock(); spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); @@ -5160,6 +5162,9 @@ static int __maybe_unused macb_resume(struct device *dev) unsigned int q; int err; + if (!device_may_wakeup(&bp->dev->dev)) + phy_init(bp->sgmii_phy); + if (!netif_running(netdev)) return 0; @@ -5220,8 +5225,6 @@ static int __maybe_unused macb_resume(struct device *dev) macb_set_rx_mode(netdev); macb_restore_features(bp); rtnl_lock(); - if (!device_may_wakeup(&bp->dev->dev)) - phy_init(bp->sgmii_phy); phylink_start(bp->phylink); rtnl_unlock(); From 75c724e2b714215c0c101e1cc301e41001ee234c Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Thu, 10 Aug 2023 17:01:12 +0200 Subject: [PATCH 0438/2093] octeon_ep: cancel tx_timeout_task later in remove sequence [ Upstream commit 28458c80006bb4e993a09fc094094a8578cad292 ] tx_timeout_task is canceled too early when removing the driver. Nothing prevents .ndo_tx_timeout from triggering and queuing the work again. Better cancel it after the netdev is unregistered. It's harmless for octep_tx_timeout_task to run in the window between the unregistration and cancelation, because it checks netif_running. Fixes: 862cd659a6fb ("octeon_ep: Add driver framework and device initialization") Signed-off-by: Michal Schmidt Link: https://lore.kernel.org/r/20230810150114.107765-3-mschmidt@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeon_ep/octep_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 8979dd05e873..d4ec46d1c8cf 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1121,12 +1121,12 @@ static void octep_remove(struct pci_dev *pdev) if (!oct) return; - cancel_work_sync(&oct->tx_timeout_task); cancel_work_sync(&oct->ctrl_mbox_task); netdev = oct->netdev; if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + cancel_work_sync(&oct->tx_timeout_task); octep_device_cleanup(oct); pci_release_mem_regions(pdev); free_netdev(netdev); From a800fcd8f18d6b6a7bf6eb1d9ee55c7106f03486 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Aug 2023 20:40:17 +0200 Subject: [PATCH 0439/2093] netfilter: nf_tables: fix false-positive lockdep splat [ Upstream commit b9f052dc68f69dac89fe1e24693354c033daa091 ] ->abort invocation may cause splat on debug kernels: WARNING: suspicious RCU usage net/netfilter/nft_set_pipapo.c:1697 suspicious rcu_dereference_check() usage! [..] rcu_scheduler_active = 2, debug_locks = 1 1 lock held by nft/133554: [..] (nft_net->commit_mutex){+.+.}-{3:3}, at: nf_tables_valid_genid [..] lockdep_rcu_suspicious+0x1ad/0x260 nft_pipapo_abort+0x145/0x180 __nf_tables_abort+0x5359/0x63d0 nf_tables_abort+0x24/0x40 nfnetlink_rcv+0x1a0a/0x22c0 netlink_unicast+0x73c/0x900 netlink_sendmsg+0x7f0/0xc20 ____sys_sendmsg+0x48d/0x760 Transaction mutex is held, so parallel updates are not possible. Switch to _protected and check mutex is held for lockdep enabled builds. Fixes: 212ed75dc5fb ("netfilter: nf_tables: integrate pipapo into commit protocol") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index a81829c10fea..32cfd0a84b0e 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1665,6 +1665,17 @@ static void nft_pipapo_commit(const struct nft_set *set) priv->clone = new_clone; } +static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set) +{ +#ifdef CONFIG_PROVE_LOCKING + const struct net *net = read_pnet(&set->net); + + return lockdep_is_held(&nft_pernet(net)->commit_mutex); +#else + return true; +#endif +} + static void nft_pipapo_abort(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); @@ -1673,7 +1684,7 @@ static void nft_pipapo_abort(const struct nft_set *set) if (!priv->dirty) return; - m = rcu_dereference(priv->match); + m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set)); new_clone = pipapo_clone(m); if (IS_ERR(new_clone)) From 00ea7eb1c69eec91cdf9259f0e427c56e7999fcd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 12 Aug 2023 13:05:16 +0200 Subject: [PATCH 0440/2093] netfilter: nf_tables: deactivate catchall elements in next generation [ Upstream commit 90e5b3462efa37b8bba82d7c4e63683856e188af ] When flushing, individual set elements are disabled in the next generation via the ->flush callback. Catchall elements are not disabled. This is incorrect and may lead to double-deactivations of catchall elements which then results in memory leaks: WARNING: CPU: 1 PID: 3300 at include/net/netfilter/nf_tables.h:1172 nft_map_deactivate+0x549/0x730 CPU: 1 PID: 3300 Comm: nft Not tainted 6.5.0-rc5+ #60 RIP: 0010:nft_map_deactivate+0x549/0x730 [..] ? nft_map_deactivate+0x549/0x730 nf_tables_delset+0xb66/0xeb0 (the warn is due to nft_use_dec() detecting underflow). Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support") Reported-by: lonial con Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f6e627383885..4c2df7af73f7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6874,6 +6874,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, ret = __nft_set_catchall_flush(ctx, set, &elem); if (ret < 0) break; + nft_set_elem_change_active(ctx->net, set, ext); } return ret; From 7f8a160d40ef9264f850be41021bb46504a9c868 Mon Sep 17 00:00:00 2001 From: Sishuai Gong Date: Thu, 10 Aug 2023 15:12:42 -0400 Subject: [PATCH 0441/2093] ipvs: fix racy memcpy in proc_do_sync_threshold [ Upstream commit 5310760af1d4fbea1452bfc77db5f9a680f7ae47 ] When two threads run proc_do_sync_threshold() in parallel, data races could happen between the two memcpy(): Thread-1 Thread-2 memcpy(val, valp, sizeof(val)); memcpy(valp, val, sizeof(val)); This race might mess up the (struct ctl_table *) table->data, so we add a mutex lock to serialize them. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/netdev/B6988E90-0A1E-4B85-BF26-2DAF6D482433@gmail.com/ Signed-off-by: Sishuai Gong Acked-by: Simon Horman Acked-by: Julian Anastasov Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 03af6a2ffd56..17a1b731a76b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1798,6 +1798,7 @@ static int proc_do_sync_threshold(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { + struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val[2]; int rc; @@ -1807,6 +1808,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, .mode = table->mode, }; + mutex_lock(&ipvs->sync_mutex); memcpy(val, valp, sizeof(val)); rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write) { @@ -1816,6 +1818,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, else memcpy(valp, val, sizeof(val)); } + mutex_unlock(&ipvs->sync_mutex); return rc; } @@ -4080,6 +4083,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; + tbl[idx].extra2 = ipvs; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD; tbl[idx++].data = &ipvs->sysctl_sync_refresh_period; From 7148bca63b212fc8e5c2e8374e14cd62b1c8441c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 15 Aug 2023 15:39:02 +0200 Subject: [PATCH 0442/2093] netfilter: nft_dynset: disallow object maps [ Upstream commit 23185c6aed1ffb8fc44087880ba2767aba493779 ] Do not allow to insert elements from datapath to objects maps. Fixes: 8aeff920dcc9 ("netfilter: nf_tables: add stateful object reference to set elements") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_dynset.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index e65a83328b55..cf9a1ae87d9b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -191,6 +191,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_OBJECT) + return -EOPNOTSUPP; + if (set->ops->update == NULL) return -EOPNOTSUPP; From 85bd0af939947947a37cb631b772fa0792c4fec5 Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Sat, 12 Aug 2023 21:41:47 -0700 Subject: [PATCH 0443/2093] net: phy: broadcom: stub c45 read/write for 54810 [ Upstream commit 096516d092d54604d590827d05b1022c8f326639 ] The 54810 does not support c45. The mmd_phy_indirect accesses return arbirtary values leading to odd behavior like saying it supports EEE when it doesn't. We also see that reading/writing these non-existent MMD registers leads to phy instability in some cases. Fixes: b14995ac2527 ("net: phy: broadcom: Add BCM54810 PHY entry") Signed-off-by: Justin Chen Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/1691901708-28650-1-git-send-email-justin.chen@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/broadcom.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ad71c88c87e7..f9ad8902100f 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -486,6 +486,17 @@ static int bcm54xx_resume(struct phy_device *phydev) return bcm54xx_config_init(phydev); } +static int bcm54810_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) +{ + return -EOPNOTSUPP; +} + +static int bcm54810_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, + u16 val) +{ + return -EOPNOTSUPP; +} + static int bcm54811_config_init(struct phy_device *phydev) { int err, reg; @@ -981,6 +992,8 @@ static struct phy_driver broadcom_drivers[] = { .get_strings = bcm_phy_get_strings, .get_stats = bcm54xx_get_stats, .probe = bcm54xx_phy_probe, + .read_mmd = bcm54810_read_mmd, + .write_mmd = bcm54810_write_mmd, .config_init = bcm54xx_config_init, .config_aneg = bcm5481_config_aneg, .config_intr = bcm_phy_config_intr, From d5e4c0e78f1de13b7193573adb8821ae3e62ac20 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Mon, 14 Aug 2023 11:23:01 +0800 Subject: [PATCH 0444/2093] team: Fix incorrect deletion of ETH_P_8021AD protocol vid from slaves [ Upstream commit dafcbce07136d799edc4c67f04f9fd69ff1eac1f ] Similar to commit 01f4fd270870 ("bonding: Fix incorrect deletion of ETH_P_8021AD protocol vid from slaves"), we can trigger BUG_ON(!vlan_info) in unregister_vlan_dev() with the following testcase: # ip netns add ns1 # ip netns exec ns1 ip link add team1 type team # ip netns exec ns1 ip link add team_slave type veth peer veth2 # ip netns exec ns1 ip link set team_slave master team1 # ip netns exec ns1 ip link add link team_slave name team_slave.10 type vlan id 10 protocol 802.1ad # ip netns exec ns1 ip link add link team1 name team1.10 type vlan id 10 protocol 802.1ad # ip netns exec ns1 ip link set team_slave nomaster # ip netns del ns1 Add S-VLAN tag related features support to team driver. So the team driver will always propagate the VLAN info to its slaves. Fixes: 8ad227ff89a7 ("net: vlan: add 802.1ad support") Suggested-by: Ido Schimmel Signed-off-by: Ziyang Xuan Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230814032301.2804971-1-william.xuanziyang@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/team/team.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 509ba706781e..921ca59822b0 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2200,7 +2200,9 @@ static void team_setup(struct net_device *dev) dev->hw_features = TEAM_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; From c965a58376146dcfdda186819462e8eb3aadef3a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Aug 2023 13:38:40 -0700 Subject: [PATCH 0445/2093] net: openvswitch: reject negative ifindex [ Upstream commit a552bfa16bab4ce901ee721346a28c4e483f4066 ] Recent changes in net-next (commit 759ab1edb56c ("net: store netdevs in an xarray")) refactored the handling of pre-assigned ifindexes and let syzbot surface a latent problem in ovs. ovs does not validate ifindex, making it possible to create netdev ports with negative ifindex values. It's easy to repro with YNL: $ ./cli.py --spec netlink/specs/ovs_datapath.yaml \ --do new \ --json '{"upcall-pid": 1, "name":"my-dp"}' $ ./cli.py --spec netlink/specs/ovs_vport.yaml \ --do new \ --json '{"upcall-pid": "00000001", "name": "some-port0", "dp-ifindex":3,"ifindex":4294901760,"type":2}' $ ip link show -65536: some-port0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether 7a:48:21:ad:0b:fb brd ff:ff:ff:ff:ff:ff ... Validate the inputs. Now the second command correctly returns: $ ./cli.py --spec netlink/specs/ovs_vport.yaml \ --do new \ --json '{"upcall-pid": "00000001", "name": "some-port0", "dp-ifindex":3,"ifindex":4294901760,"type":2}' lib.ynl.NlError: Netlink error: Numerical result out of range nl_len = 108 (92) nl_flags = 0x300 nl_type = 2 error: -34 extack: {'msg': 'integer out of range', 'unknown': [[type:4 len:36] b'\x0c\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x0c\x00\x03\x00\xff\xff\xff\x7f\x00\x00\x00\x00\x08\x00\x01\x00\x08\x00\x00\x00'], 'bad-attr': '.ifindex'} Accept 0 since it used to be silently ignored. Fixes: 54c4ef34c4b6 ("openvswitch: allow specifying ifindex of new interfaces") Reported-by: syzbot+7456b5dcf65111553320@syzkaller.appspotmail.com Reviewed-by: Leon Romanovsky Reviewed-by: Aaron Conole Link: https://lore.kernel.org/r/20230814203840.2908710-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/openvswitch/datapath.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 5920fdca1287..3c7b24535409 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1806,7 +1806,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0; /* So far only local changes have been made, now need the lock. */ ovs_lock(); @@ -2026,7 +2026,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, [OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0, PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), - [OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 }, + [OVS_DP_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), }; static const struct genl_small_ops dp_datapath_genl_ops[] = { @@ -2276,7 +2276,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = port_no; parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX] - ? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; + ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; vport = new_vport(&parms); err = PTR_ERR(vport); @@ -2513,7 +2513,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, - [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 0), [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; From ea749b5e3b38cb5ca9de2f3c4fbc25da6529809a Mon Sep 17 00:00:00 2001 From: Piotr Gardocki Date: Mon, 7 Aug 2023 16:46:04 +0200 Subject: [PATCH 0446/2093] iavf: fix FDIR rule fields masks validation [ Upstream commit 751969e5b1196821ef78f0aa664a8a97c92c9057 ] Return an error if a field's mask is neither full nor empty. When a mask is only partial the field is not being used for rule programming but it gives a wrong impression it is used. Fix by returning an error on any partial mask to make it clear they are not supported. The ip_ver assignment is moved earlier in code to allow using it in iavf_validate_fdir_fltr_masks. Fixes: 527691bf0682 ("iavf: Support IPv4 Flow Director filters") Fixes: e90cbc257a6f ("iavf: Support IPv6 Flow Director filters") Signed-off-by: Piotr Gardocki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- .../net/ethernet/intel/iavf/iavf_ethtool.c | 10 +++ drivers/net/ethernet/intel/iavf/iavf_fdir.c | 77 ++++++++++++++++++- drivers/net/ethernet/intel/iavf/iavf_fdir.h | 2 + 3 files changed, 85 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index f544d2b0abdb..fe912b1c468e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1289,6 +1289,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.src_port = fsp->m_u.tcp_ip4_spec.psrc; fltr->ip_mask.dst_port = fsp->m_u.tcp_ip4_spec.pdst; fltr->ip_mask.tos = fsp->m_u.tcp_ip4_spec.tos; + fltr->ip_ver = 4; break; case AH_V4_FLOW: case ESP_V4_FLOW: @@ -1300,6 +1301,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.v4_addrs.dst_ip = fsp->m_u.ah_ip4_spec.ip4dst; fltr->ip_mask.spi = fsp->m_u.ah_ip4_spec.spi; fltr->ip_mask.tos = fsp->m_u.ah_ip4_spec.tos; + fltr->ip_ver = 4; break; case IPV4_USER_FLOW: fltr->ip_data.v4_addrs.src_ip = fsp->h_u.usr_ip4_spec.ip4src; @@ -1312,6 +1314,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.l4_header = fsp->m_u.usr_ip4_spec.l4_4_bytes; fltr->ip_mask.tos = fsp->m_u.usr_ip4_spec.tos; fltr->ip_mask.proto = fsp->m_u.usr_ip4_spec.proto; + fltr->ip_ver = 4; break; case TCP_V6_FLOW: case UDP_V6_FLOW: @@ -1330,6 +1333,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.src_port = fsp->m_u.tcp_ip6_spec.psrc; fltr->ip_mask.dst_port = fsp->m_u.tcp_ip6_spec.pdst; fltr->ip_mask.tclass = fsp->m_u.tcp_ip6_spec.tclass; + fltr->ip_ver = 6; break; case AH_V6_FLOW: case ESP_V6_FLOW: @@ -1345,6 +1349,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe sizeof(struct in6_addr)); fltr->ip_mask.spi = fsp->m_u.ah_ip6_spec.spi; fltr->ip_mask.tclass = fsp->m_u.ah_ip6_spec.tclass; + fltr->ip_ver = 6; break; case IPV6_USER_FLOW: memcpy(&fltr->ip_data.v6_addrs.src_ip, fsp->h_u.usr_ip6_spec.ip6src, @@ -1361,6 +1366,7 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe fltr->ip_mask.l4_header = fsp->m_u.usr_ip6_spec.l4_4_bytes; fltr->ip_mask.tclass = fsp->m_u.usr_ip6_spec.tclass; fltr->ip_mask.proto = fsp->m_u.usr_ip6_spec.l4_proto; + fltr->ip_ver = 6; break; case ETHER_FLOW: fltr->eth_data.etype = fsp->h_u.ether_spec.h_proto; @@ -1371,6 +1377,10 @@ iavf_add_fdir_fltr_info(struct iavf_adapter *adapter, struct ethtool_rx_flow_spe return -EINVAL; } + err = iavf_validate_fdir_fltr_masks(adapter, fltr); + if (err) + return err; + if (iavf_fdir_is_dup_fltr(adapter, fltr)) return -EEXIST; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 505e82ebafe4..03e774bd2a5b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -18,6 +18,79 @@ static const struct in6_addr ipv6_addr_full_mask = { } }; +static const struct in6_addr ipv6_addr_zero_mask = { + .in6_u = { + .u6_addr8 = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + } + } +}; + +/** + * iavf_validate_fdir_fltr_masks - validate Flow Director filter fields masks + * @adapter: pointer to the VF adapter structure + * @fltr: Flow Director filter data structure + * + * Returns 0 if all masks of packet fields are either full or empty. Returns + * error on at least one partial mask. + */ +int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (fltr->eth_mask.etype && fltr->eth_mask.etype != htons(U16_MAX)) + goto partial_mask; + + if (fltr->ip_ver == 4) { + if (fltr->ip_mask.v4_addrs.src_ip && + fltr->ip_mask.v4_addrs.src_ip != htonl(U32_MAX)) + goto partial_mask; + + if (fltr->ip_mask.v4_addrs.dst_ip && + fltr->ip_mask.v4_addrs.dst_ip != htonl(U32_MAX)) + goto partial_mask; + + if (fltr->ip_mask.tos && fltr->ip_mask.tos != U8_MAX) + goto partial_mask; + } else if (fltr->ip_ver == 6) { + if (memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_zero_mask, + sizeof(struct in6_addr)) && + memcmp(&fltr->ip_mask.v6_addrs.src_ip, &ipv6_addr_full_mask, + sizeof(struct in6_addr))) + goto partial_mask; + + if (memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_zero_mask, + sizeof(struct in6_addr)) && + memcmp(&fltr->ip_mask.v6_addrs.dst_ip, &ipv6_addr_full_mask, + sizeof(struct in6_addr))) + goto partial_mask; + + if (fltr->ip_mask.tclass && fltr->ip_mask.tclass != U8_MAX) + goto partial_mask; + } + + if (fltr->ip_mask.proto && fltr->ip_mask.proto != U8_MAX) + goto partial_mask; + + if (fltr->ip_mask.src_port && fltr->ip_mask.src_port != htons(U16_MAX)) + goto partial_mask; + + if (fltr->ip_mask.dst_port && fltr->ip_mask.dst_port != htons(U16_MAX)) + goto partial_mask; + + if (fltr->ip_mask.spi && fltr->ip_mask.spi != htonl(U32_MAX)) + goto partial_mask; + + if (fltr->ip_mask.l4_header && + fltr->ip_mask.l4_header != htonl(U32_MAX)) + goto partial_mask; + + return 0; + +partial_mask: + dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, partial masks are not supported\n"); + return -EOPNOTSUPP; +} + /** * iavf_pkt_udp_no_pay_len - the length of UDP packet without payload * @fltr: Flow Director filter data structure @@ -263,8 +336,6 @@ iavf_fill_fdir_ip4_hdr(struct iavf_fdir_fltr *fltr, VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV4, DST); } - fltr->ip_ver = 4; - return 0; } @@ -309,8 +380,6 @@ iavf_fill_fdir_ip6_hdr(struct iavf_fdir_fltr *fltr, VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, IPV6, DST); } - fltr->ip_ver = 6; - return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 33c55c366315..9eb9f73f6adf 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -110,6 +110,8 @@ struct iavf_fdir_fltr { struct virtchnl_fdir_add vc_add_msg; }; +int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); From 740924313a1b4eb223a6494e199ad83d58f906c7 Mon Sep 17 00:00:00 2001 From: Andrii Staikov Date: Wed, 2 Aug 2023 09:47:32 +0200 Subject: [PATCH 0447/2093] i40e: fix misleading debug logs [ Upstream commit 2f2beb8874cb0844e84ad26e990f05f4f13ff63f ] Change "write" into the actual "read" word. Change parameters description. Fixes: 7073f46e443e ("i40e: Add AQ commands for NVM Update for X722") Signed-off-by: Aleksandr Loktionov Signed-off-by: Andrii Staikov Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_nvm.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 17e3f26eee4a..779ba907009a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -210,11 +210,11 @@ static int i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset, * @hw: pointer to the HW structure. * @module_pointer: module pointer location in words from the NVM beginning * @offset: offset in words from module start - * @words: number of words to write - * @data: buffer with words to write to the Shadow RAM + * @words: number of words to read + * @data: buffer with words to read to the Shadow RAM * @last_command: tells the AdminQ that this is the last command * - * Writes a 16 bit words buffer to the Shadow RAM using the admin command. + * Reads a 16 bit words buffer to the Shadow RAM using the admin command. **/ static int i40e_read_nvm_aq(struct i40e_hw *hw, u8 module_pointer, u32 offset, @@ -234,18 +234,18 @@ static int i40e_read_nvm_aq(struct i40e_hw *hw, */ if ((offset + words) > hw->nvm.sr_size) i40e_debug(hw, I40E_DEBUG_NVM, - "NVM write error: offset %d beyond Shadow RAM limit %d\n", + "NVM read error: offset %d beyond Shadow RAM limit %d\n", (offset + words), hw->nvm.sr_size); else if (words > I40E_SR_SECTOR_SIZE_IN_WORDS) - /* We can write only up to 4KB (one sector), in one AQ write */ + /* We can read only up to 4KB (one sector), in one AQ write */ i40e_debug(hw, I40E_DEBUG_NVM, - "NVM write fail error: tried to write %d words, limit is %d.\n", + "NVM read fail error: tried to read %d words, limit is %d.\n", words, I40E_SR_SECTOR_SIZE_IN_WORDS); else if (((offset + (words - 1)) / I40E_SR_SECTOR_SIZE_IN_WORDS) != (offset / I40E_SR_SECTOR_SIZE_IN_WORDS)) - /* A single write cannot spread over two sectors */ + /* A single read cannot spread over two sectors */ i40e_debug(hw, I40E_DEBUG_NVM, - "NVM write error: cannot spread over two sectors in a single write offset=%d words=%d\n", + "NVM read error: cannot spread over two sectors in a single read offset=%d words=%d\n", offset, words); else ret_code = i40e_aq_read_nvm(hw, module_pointer, From df83af3b996d79d7eb51eaefdffb7f4352e55052 Mon Sep 17 00:00:00 2001 From: Alfred Lee Date: Mon, 14 Aug 2023 17:13:23 -0700 Subject: [PATCH 0448/2093] net: dsa: mv88e6xxx: Wait for EEPROM done before HW reset [ Upstream commit 23d775f12dcd23d052a4927195f15e970e27ab26 ] If the switch is reset during active EEPROM transactions, as in just after an SoC reset after power up, the I2C bus transaction may be cut short leaving the EEPROM internal I2C state machine in the wrong state. When the switch is reset again, the bad state machine state may result in data being read from the wrong memory location causing the switch to enter unexpected mode rendering it inoperational. Fixes: a3dcb3e7e70c ("net: dsa: mv88e6xxx: Wait for EEPROM done after HW reset") Signed-off-by: Alfred Lee Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230815001323.24739-1-l00g33k@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b69bd44ada1f..a73008b9e0b3 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3006,6 +3006,14 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) /* If there is a GPIO connected to the reset pin, toggle it */ if (gpiod) { + /* If the switch has just been reset and not yet completed + * loading EEPROM, the reset may interrupt the I2C transaction + * mid-byte, causing the first EEPROM read after the reset + * from the wrong location resulting in the switch booting + * to wrong mode and inoperable. + */ + mv88e6xxx_g1_wait_eeprom_done(chip); + gpiod_set_value_cansleep(gpiod, 1); usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); From 3d820924c00ceeabdea2b9414a1fbd7d30727a2f Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 15 Aug 2023 16:57:27 +0100 Subject: [PATCH 0449/2093] sfc: don't unregister flow_indr if it was never registered [ Upstream commit fa165e1949976704500a442faeef8d9596faee76 ] In efx_init_tc(), move the setting of efx->tc->up after the flow_indr_dev_register() call, so that if it fails, efx_fini_tc() won't call flow_indr_dev_unregister(). Fixes: 5b2e12d51bd8 ("sfc: bind indirect blocks for TC offload on EF100") Suggested-by: Pieter Jansen van Vuuren Reviewed-by: Martin Habets Signed-off-by: Edward Cree Link: https://lore.kernel.org/r/a81284d7013aba74005277bd81104e4cfbea3f6f.1692114888.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 3478860d4023..d312147cd2dd 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -603,10 +603,10 @@ int efx_init_tc(struct efx_nic *efx) rc = efx_tc_configure_rep_mport(efx); if (rc) return rc; - efx->tc->up = true; rc = flow_indr_dev_register(efx_tc_indr_setup_cb, efx); if (rc) return rc; + efx->tc->up = true; return 0; } From 06b8f06f93024863e5519b7aca500a952ced44cc Mon Sep 17 00:00:00 2001 From: Abel Wu Date: Wed, 16 Aug 2023 17:12:22 +0800 Subject: [PATCH 0450/2093] sock: Fix misuse of sk_under_memory_pressure() [ Upstream commit 2d0c88e84e483982067a82073f6125490ddf3614 ] The status of global socket memory pressure is updated when: a) __sk_mem_raise_allocated(): enter: sk_memory_allocated(sk) > sysctl_mem[1] leave: sk_memory_allocated(sk) <= sysctl_mem[0] b) __sk_mem_reduce_allocated(): leave: sk_under_memory_pressure(sk) && sk_memory_allocated(sk) < sysctl_mem[0] So the conditions of leaving global pressure are inconstant, which may lead to the situation that one pressured net-memcg prevents the global pressure from being cleared when there is indeed no global pressure, thus the global constrains are still in effect unexpectedly on the other sockets. This patch fixes this by ignoring the net-memcg's pressure when deciding whether should leave global memory pressure. Fixes: e1aab161e013 ("socket: initial cgroup code.") Signed-off-by: Abel Wu Acked-by: Shakeel Butt Link: https://lore.kernel.org/r/20230816091226.1542-1-wuyun.abel@bytedance.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/sock.h | 6 ++++++ net/core/sock.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/net/sock.h b/include/net/sock.h index 1bbdddcf6154..699408944952 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1445,6 +1445,12 @@ static inline bool sk_has_memory_pressure(const struct sock *sk) return sk->sk_prot->memory_pressure != NULL; } +static inline bool sk_under_global_memory_pressure(const struct sock *sk) +{ + return sk->sk_prot->memory_pressure && + !!*sk->sk_prot->memory_pressure; +} + static inline bool sk_under_memory_pressure(const struct sock *sk) { if (!sk->sk_prot->memory_pressure) diff --git a/net/core/sock.c b/net/core/sock.c index 3b5304f084ef..509773919d30 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3099,7 +3099,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); - if (sk_under_memory_pressure(sk) && + if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } From 2e03a92b241102aaf490439aa1b00239f84f530f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2023 14:21:58 +0000 Subject: [PATCH 0451/2093] net: do not allow gso_size to be set to GSO_BY_FRAGS [ Upstream commit b616be6b97688f2f2bd7c4a47ab32f27f94fb2a9 ] One missing check in virtio_net_hdr_to_skb() allowed syzbot to crash kernels again [1] Do not allow gso_size to be set to GSO_BY_FRAGS (0xffff), because this magic value is used by the kernel. [1] general protection fault, probably for non-canonical address 0xdffffc000000000e: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 5039 Comm: syz-executor401 Not tainted 6.5.0-rc5-next-20230809-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 RIP: 0010:skb_segment+0x1a52/0x3ef0 net/core/skbuff.c:4500 Code: 00 00 00 e9 ab eb ff ff e8 6b 96 5d f9 48 8b 84 24 00 01 00 00 48 8d 78 70 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e ea 21 00 00 48 8b 84 24 00 01 RSP: 0018:ffffc90003d3f1c8 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 000000000001fffe RCX: 0000000000000000 RDX: 000000000000000e RSI: ffffffff882a3115 RDI: 0000000000000070 RBP: ffffc90003d3f378 R08: 0000000000000005 R09: 000000000000ffff R10: 000000000000ffff R11: 5ee4a93e456187d6 R12: 000000000001ffc6 R13: dffffc0000000000 R14: 0000000000000008 R15: 000000000000ffff FS: 00005555563f2380(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020020000 CR3: 000000001626d000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: udp6_ufo_fragment+0x9d2/0xd50 net/ipv6/udp_offload.c:109 ipv6_gso_segment+0x5c4/0x17b0 net/ipv6/ip6_offload.c:120 skb_mac_gso_segment+0x292/0x610 net/core/gso.c:53 __skb_gso_segment+0x339/0x710 net/core/gso.c:124 skb_gso_segment include/net/gso.h:83 [inline] validate_xmit_skb+0x3a5/0xf10 net/core/dev.c:3625 __dev_queue_xmit+0x8f0/0x3d60 net/core/dev.c:4329 dev_queue_xmit include/linux/netdevice.h:3082 [inline] packet_xmit+0x257/0x380 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3087 [inline] packet_sendmsg+0x24c7/0x5570 net/packet/af_packet.c:3119 sock_sendmsg_nosec net/socket.c:727 [inline] sock_sendmsg+0xd9/0x180 net/socket.c:750 ____sys_sendmsg+0x6ac/0x940 net/socket.c:2496 ___sys_sendmsg+0x135/0x1d0 net/socket.c:2550 __sys_sendmsg+0x117/0x1e0 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7ff27cdb34d9 Fixes: 3953c46c3ac7 ("sk_buff: allow segmenting based on frag sizes") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Xin Long Cc: "Michael S. Tsirkin" Cc: Jason Wang Reviewed-by: Willem de Bruijn Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Xuan Zhuo Link: https://lore.kernel.org/r/20230816142158.1779798-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/linux/virtio_net.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index a960de68ac69..6047058d6703 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -148,6 +148,10 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (gso_type & SKB_GSO_UDP) nh_off -= thlen; + /* Kernel has a special handling for GSO_BY_FRAGS. */ + if (gso_size == GSO_BY_FRAGS) + return -EINVAL; + /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; From fbc7b1dad825575e5340a4844bf66ba672aa47a3 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Wed, 16 Aug 2023 20:37:11 +0530 Subject: [PATCH 0452/2093] qede: fix firmware halt over suspend and resume [ Upstream commit 2eb9625a3a32251ecea470cd576659a3a03b4e59 ] While performing certain power-off sequences, PCI drivers are called to suspend and resume their underlying devices through PCI PM (power management) interface. However this NIC hardware does not support PCI PM suspend/resume operations so system wide suspend/resume leads to bad MFW (management firmware) state which causes various follow-up errors in driver when communicating with the device/firmware afterwards. To fix this driver implements PCI PM suspend handler to indicate unsupported operation to the PCI subsystem explicitly, thus avoiding system to go into suspended/standby mode. Without this fix device/firmware does not recover unless system is power cycled. Fixes: 2950219d87b0 ("qede: Add basic network device support") Signed-off-by: Manish Chopra Signed-off-by: Alok Prasad Reviewed-by: John Meneghini Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230816150711.59035-1-manishc@marvell.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qede/qede_main.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index e8d427c7d1cf..dc43e74147fb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -177,6 +177,15 @@ static int qede_sriov_configure(struct pci_dev *pdev, int num_vfs_param) } #endif +static int __maybe_unused qede_suspend(struct device *dev) +{ + dev_info(dev, "Device does not support suspend operation\n"); + + return -EOPNOTSUPP; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(qede_pm_ops, qede_suspend, NULL); + static const struct pci_error_handlers qede_err_handler = { .error_detected = qede_io_error_detected, }; @@ -191,6 +200,7 @@ static struct pci_driver qede_pci_driver = { .sriov_configure = qede_sriov_configure, #endif .err_handler = &qede_err_handler, + .driver.pm = &qede_pm_ops, }; static struct qed_eth_cb_ops qede_ll_ops = { From 1c82d1b736ce85e77fd4da05eca6f1f4a52a2bc3 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Wed, 16 Aug 2023 12:34:05 -0700 Subject: [PATCH 0453/2093] ice: Block switchdev mode when ADQ is active and vice versa [ Upstream commit 43d00e102d9ecbe2635d7e3f2e14d2e90183d6af ] ADQ and switchdev are not supported simultaneously. Enabling both at the same time can result in nullptr dereference. To prevent this, check if ADQ is active when changing devlink mode to switchdev mode, and check if switchdev is active when enabling ADQ. Fixes: fbc7b27af0f9 ("ice: enable ndo_setup_tc support for mqprio_qdisc") Signed-off-by: Marcin Szycik Reviewed-by: Przemek Kitszel Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230816193405.1307580-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_eswitch.c | 6 ++++++ drivers/net/ethernet/intel/ice/ice_main.c | 5 +++++ 2 files changed, 11 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index f9f15acae90a..2ffe5708a045 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -562,6 +562,12 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, break; case DEVLINK_ESWITCH_MODE_SWITCHDEV: { + if (ice_is_adq_active(pf)) { + dev_err(ice_pf_to_dev(pf), "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root"); + NL_SET_ERR_MSG_MOD(extack, "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root"); + return -EOPNOTSUPP; + } + dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev", pf->hw.pf_id); NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev"); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a771e597795d..7a00d297be3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8787,6 +8787,11 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, ice_setup_tc_block_cb, np, np, true); case TC_SETUP_QDISC_MQPRIO: + if (ice_is_eswitch_mode_switchdev(pf)) { + netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n"); + return -EOPNOTSUPP; + } + if (pf->adev) { mutex_lock(&pf->adev_mutex); device_lock(&pf->adev->dev); From fae3868be8446ead984a1d3e1ececd9b3310c975 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 14 Jun 2023 10:18:23 +0300 Subject: [PATCH 0454/2093] bus: ti-sysc: Flush posted write on enable before reset [ Upstream commit 34539b442b3bc7d5bf10164750302b60b91f18a7 ] The am335x devices started producing boot errors for resetting musb module in because of subtle timing changes: Unhandled fault: external abort on non-linefetch (0x1008) ... sysc_poll_reset_sysconfig from sysc_reset+0x109/0x12 sysc_reset from sysc_probe+0xa99/0xeb0 ... The fix is to flush posted write after enable before reset during probe. Note that some devices also need to specify the delay after enable with ti,sysc-delay-us, but this is not needed for musb on am335x based on my tests. Reported-by: kernelci.org bot Closes: https://storage.kernelci.org/next/master/next-20230614/arm/multi_v7_defconfig+CONFIG_THUMB2_KERNEL=y/gcc-10/lab-cip/baseline-beaglebone-black.html Fixes: 596e7955692b ("bus: ti-sysc: Add support for software reset") Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index cae078bffc71..9b7268bae66a 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2159,6 +2159,8 @@ static int sysc_reset(struct sysc *ddata) sysc_val = sysc_read_sysconfig(ddata); sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); + /* Flush posted write */ + sysc_val = sysc_read_sysconfig(ddata); } if (ddata->cfg.srst_udelay) From 9657a754c5decfd8a648dd342fd25466525549ae Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 13 Jun 2023 16:12:24 +0300 Subject: [PATCH 0455/2093] arm64: dts: qcom: qrb5165-rb5: fix thermal zone conflict [ Upstream commit 798f1df86e5709b7b6aedf493cc04c7fedbf544a ] The commit 3a786086c6f8 ("arm64: dts: qcom: Add missing "-thermal" suffix for thermal zones") renamed the thermal zone in the pm8150l.dtsi file to comply with the schema. However this resulted in a clash with the RB5 board file, which already contained the pm8150l-thermal zone for the on-board sensor. This resulted in the board file definition overriding the thermal zone defined in the PMIC include file (and thus the on-die PMIC temp alarm was not probing at all). Rename the thermal zone in qcom/qrb5165-rb5.dts to remove this override. Fixes: 3a786086c6f8 ("arm64: dts: qcom: Add missing "-thermal" suffix for thermal zones") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230613131224.666668-1-dmitry.baryshkov@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/qrb5165-rb5.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index bf8077a1cf9a..9731a7c63d53 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -121,7 +121,7 @@ active-config0 { }; }; - pm8150l-thermal { + pm8150l-pcb-thermal { polling-delay-passive = <0>; polling-delay = <0>; thermal-sensors = <&pm8150l_adc_tm 1>; From 52d3607db0de375aca8d48d3445f9120f59814db Mon Sep 17 00:00:00 2001 From: Christopher Obbard Date: Wed, 5 Jul 2023 15:42:54 +0100 Subject: [PATCH 0456/2093] arm64: dts: rockchip: Disable HS400 for eMMC on ROCK Pi 4 [ Upstream commit cee572756aa2cb46e959e9797ad4b730b78a050b ] There is some instablity with some eMMC modules on ROCK Pi 4 SBCs running in HS400 mode. This ends up resulting in some block errors after a while or after a "heavy" operation utilising the eMMC (e.g. resizing a filesystem). An example of these errors is as follows: [ 289.171014] mmc1: running CQE recovery [ 290.048972] mmc1: running CQE recovery [ 290.054834] mmc1: running CQE recovery [ 290.060817] mmc1: running CQE recovery [ 290.061337] blk_update_request: I/O error, dev mmcblk1, sector 1411072 op 0x1:(WRITE) flags 0x800 phys_seg 36 prio class 0 [ 290.061370] EXT4-fs warning (device mmcblk1p1): ext4_end_bio:348: I/O error 10 writing to inode 29547 starting block 176466) [ 290.061484] Buffer I/O error on device mmcblk1p1, logical block 172288 [ 290.061531] Buffer I/O error on device mmcblk1p1, logical block 172289 [ 290.061551] Buffer I/O error on device mmcblk1p1, logical block 172290 [ 290.061574] Buffer I/O error on device mmcblk1p1, logical block 172291 [ 290.061592] Buffer I/O error on device mmcblk1p1, logical block 172292 [ 290.061615] Buffer I/O error on device mmcblk1p1, logical block 172293 [ 290.061632] Buffer I/O error on device mmcblk1p1, logical block 172294 [ 290.061654] Buffer I/O error on device mmcblk1p1, logical block 172295 [ 290.061673] Buffer I/O error on device mmcblk1p1, logical block 172296 [ 290.061695] Buffer I/O error on device mmcblk1p1, logical block 172297 Disabling the Command Queue seems to stop the CQE recovery from running, but doesn't seem to improve the I/O errors. Until this can be investigated further, disable HS400 mode on the ROCK Pi 4 SBCs to at least stop I/O errors from occurring. While we are here, set the eMMC maximum clock frequency to 1.5MHz to follow the ROCK 4C+. Fixes: 1b5715c602fd ("arm64: dts: rockchip: add ROCK Pi 4 DTS support") Signed-off-by: Christopher Obbard Tested-By: Folker Schwesinger Link: https://lore.kernel.org/r/20230705144255.115299-2-chris.obbard@collabora.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 1f76d3501bda..24fbb06007f9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -645,9 +645,9 @@ &saradc { }; &sdhci { + max-frequency = <150000000>; bus-width = <8>; - mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; + mmc-hs200-1_8v; non-removable; status = "okay"; }; From 66d761a2290a863b2bbf5a49488b5384df4d856c Mon Sep 17 00:00:00 2001 From: Christopher Obbard Date: Wed, 5 Jul 2023 15:42:55 +0100 Subject: [PATCH 0457/2093] arm64: dts: rockchip: Disable HS400 for eMMC on ROCK 4C+ [ Upstream commit 2bd1d2dd808c60532283e9cf05110bf1bf2f9079 ] There is some instablity with some eMMC modules on ROCK Pi 4 SBCs running in HS400 mode. This ends up resulting in some block errors after a while or after a "heavy" operation utilising the eMMC (e.g. resizing a filesystem). An example of these errors is as follows: [ 289.171014] mmc1: running CQE recovery [ 290.048972] mmc1: running CQE recovery [ 290.054834] mmc1: running CQE recovery [ 290.060817] mmc1: running CQE recovery [ 290.061337] blk_update_request: I/O error, dev mmcblk1, sector 1411072 op 0x1:(WRITE) flags 0x800 phys_seg 36 prio class 0 [ 290.061370] EXT4-fs warning (device mmcblk1p1): ext4_end_bio:348: I/O error 10 writing to inode 29547 starting block 176466) [ 290.061484] Buffer I/O error on device mmcblk1p1, logical block 172288 [ 290.061531] Buffer I/O error on device mmcblk1p1, logical block 172289 [ 290.061551] Buffer I/O error on device mmcblk1p1, logical block 172290 [ 290.061574] Buffer I/O error on device mmcblk1p1, logical block 172291 [ 290.061592] Buffer I/O error on device mmcblk1p1, logical block 172292 [ 290.061615] Buffer I/O error on device mmcblk1p1, logical block 172293 [ 290.061632] Buffer I/O error on device mmcblk1p1, logical block 172294 [ 290.061654] Buffer I/O error on device mmcblk1p1, logical block 172295 [ 290.061673] Buffer I/O error on device mmcblk1p1, logical block 172296 [ 290.061695] Buffer I/O error on device mmcblk1p1, logical block 172297 Disabling the Command Queue seems to stop the CQE recovery from running, but doesn't seem to improve the I/O errors. Until this can be investigated further, disable HS400 mode on the ROCK Pi 4 SBCs to at least stop I/O errors from occurring. Fixes: 246450344dad ("arm64: dts: rockchip: rk3399: Radxa ROCK 4C+") Signed-off-by: Christopher Obbard Link: https://lore.kernel.org/r/20230705144255.115299-3-chris.obbard@collabora.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts index f9884902f874..c3f53aa1ea4a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts @@ -548,9 +548,8 @@ &saradc { &sdhci { max-frequency = <150000000>; bus-width = <8>; - mmc-hs400-1_8v; + mmc-hs200-1_8v; non-removable; - mmc-hs400-enhanced-strobe; status = "okay"; }; From d2d6d51d753a3aaa679eb695387254273f1c1c85 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 25 Nov 2022 15:42:22 +0100 Subject: [PATCH 0458/2093] ARM: dts: imx: align LED node names with dtschema [ Upstream commit 4b0d1f2738899dbcc7a026d826373530019aa31b ] The node names should be generic and DT schema expects certain pattern: imx50-kobo-aura.dtb: gpio-leds: 'on' does not match any of the regexes: '(^led-[0-9a-f]$|led)', 'pinctrl-[0-9]+' imx6dl-yapp4-draco.dtb: led-controller@30: 'chan@0', 'chan@1', 'chan@2' do not match any of the regexes: '^led@[0-8]$', '^multi-led@[0-8]$', 'pinctrl-[0-9]+' Signed-off-by: Krzysztof Kozlowski Signed-off-by: Shawn Guo Stable-dep-of: 762b700982a1 ("ARM: dts: imx6: phytec: fix RTC interrupt level") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx50-kobo-aura.dts | 2 +- arch/arm/boot/dts/imx53-cx9020.dts | 10 +++++----- arch/arm/boot/dts/imx53-m53evk.dts | 4 ++-- arch/arm/boot/dts/imx53-m53menlo.dts | 6 +++--- arch/arm/boot/dts/imx53-tx53.dtsi | 2 +- arch/arm/boot/dts/imx53-usbarmory.dts | 2 +- arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi | 6 +++--- arch/arm/boot/dts/imx6dl-riotboard.dts | 4 ++-- arch/arm/boot/dts/imx6dl-yapp4-common.dtsi | 6 +++--- arch/arm/boot/dts/imx6q-gw5400-a.dts | 6 +++--- arch/arm/boot/dts/imx6q-h100.dts | 6 +++--- arch/arm/boot/dts/imx6q-kp.dtsi | 4 ++-- arch/arm/boot/dts/imx6q-marsboard.dts | 4 ++-- arch/arm/boot/dts/imx6q-tbs2910.dts | 2 +- arch/arm/boot/dts/imx6qdl-emcon.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-gw51xx.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-gw52xx.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw53xx.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw54xx.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw551x.dtsi | 2 +- arch/arm/boot/dts/imx6qdl-gw552x.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw553x.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-gw560x.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw5903.dtsi | 2 +- arch/arm/boot/dts/imx6qdl-gw5904.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw5907.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-gw5910.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw5912.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-gw5913.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi | 10 +++++----- arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi | 6 +++--- arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-rex.dtsi | 2 +- arch/arm/boot/dts/imx6qdl-sabreauto.dtsi | 2 +- arch/arm/boot/dts/imx6qdl-sabresd.dtsi | 2 +- arch/arm/boot/dts/imx6qdl-ts7970.dtsi | 4 ++-- arch/arm/boot/dts/imx6qdl-tx6.dtsi | 2 +- arch/arm/boot/dts/imx6sl-evk.dts | 2 +- arch/arm/boot/dts/imx6sll-evk.dts | 2 +- arch/arm/boot/dts/imx6sx-sabreauto.dts | 2 +- arch/arm/boot/dts/imx6sx-udoo-neo.dtsi | 4 ++-- arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi | 2 +- arch/arm/boot/dts/imx6ul-tx6ul.dtsi | 2 +- 44 files changed, 93 insertions(+), 93 deletions(-) diff --git a/arch/arm/boot/dts/imx50-kobo-aura.dts b/arch/arm/boot/dts/imx50-kobo-aura.dts index 51bf6117fb12..467db6b4ed7f 100644 --- a/arch/arm/boot/dts/imx50-kobo-aura.dts +++ b/arch/arm/boot/dts/imx50-kobo-aura.dts @@ -26,7 +26,7 @@ gpio-leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_leds>; - on { + led-on { label = "kobo_aura:orange:on"; gpios = <&gpio6 24 GPIO_ACTIVE_LOW>; panic-indicator; diff --git a/arch/arm/boot/dts/imx53-cx9020.dts b/arch/arm/boot/dts/imx53-cx9020.dts index cfb18849a92b..055d23a9aee7 100644 --- a/arch/arm/boot/dts/imx53-cx9020.dts +++ b/arch/arm/boot/dts/imx53-cx9020.dts @@ -86,27 +86,27 @@ tfp410_out: endpoint { leds { compatible = "gpio-leds"; - pwr-r { + led-pwr-r { gpios = <&gpio3 22 GPIO_ACTIVE_HIGH>; default-state = "off"; }; - pwr-g { + led-pwr-g { gpios = <&gpio3 24 GPIO_ACTIVE_HIGH>; default-state = "on"; }; - pwr-b { + led-pwr-b { gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; default-state = "off"; }; - sd1-b { + led-sd1-b { linux,default-trigger = "mmc0"; gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>; }; - sd2-b { + led-sd2-b { linux,default-trigger = "mmc1"; gpios = <&gpio3 17 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/imx53-m53evk.dts b/arch/arm/boot/dts/imx53-m53evk.dts index a1a6228d1aa6..2bd2432d317f 100644 --- a/arch/arm/boot/dts/imx53-m53evk.dts +++ b/arch/arm/boot/dts/imx53-m53evk.dts @@ -52,13 +52,13 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&led_pin_gpio>; - user1 { + led-user1 { label = "user1"; gpios = <&gpio2 8 0>; linux,default-trigger = "heartbeat"; }; - user2 { + led-user2 { label = "user2"; gpios = <&gpio2 9 0>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx53-m53menlo.dts b/arch/arm/boot/dts/imx53-m53menlo.dts index d5c68d1ea707..4d77b6077fc1 100644 --- a/arch/arm/boot/dts/imx53-m53menlo.dts +++ b/arch/arm/boot/dts/imx53-m53menlo.dts @@ -34,19 +34,19 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user1 { + led-user1 { label = "TestLed601"; gpios = <&gpio6 1 GPIO_ACTIVE_HIGH>; linux,default-trigger = "mmc0"; }; - user2 { + led-user2 { label = "TestLed602"; gpios = <&gpio6 2 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; - eth { + led-eth { label = "EthLedYe"; gpios = <&gpio2 11 GPIO_ACTIVE_LOW>; linux,default-trigger = "netdev"; diff --git a/arch/arm/boot/dts/imx53-tx53.dtsi b/arch/arm/boot/dts/imx53-tx53.dtsi index 892dd1a4bac3..a439a47fb65a 100644 --- a/arch/arm/boot/dts/imx53-tx53.dtsi +++ b/arch/arm/boot/dts/imx53-tx53.dtsi @@ -94,7 +94,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_stk5led>; - user { + led-user { label = "Heartbeat"; gpios = <&gpio2 20 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx53-usbarmory.dts b/arch/arm/boot/dts/imx53-usbarmory.dts index f34993a490ee..acc44010d510 100644 --- a/arch/arm/boot/dts/imx53-usbarmory.dts +++ b/arch/arm/boot/dts/imx53-usbarmory.dts @@ -67,7 +67,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "LED"; gpios = <&gpio4 27 GPIO_ACTIVE_LOW>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi b/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi index 337db29b0010..37697fac9dea 100644 --- a/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi +++ b/arch/arm/boot/dts/imx6dl-b1x5pv2.dtsi @@ -211,17 +211,17 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_q7_gpio1 &pinctrl_q7_gpio3 &pinctrl_q7_gpio5>; - alarm1 { + led-alarm1 { label = "alarm:red"; gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; }; - alarm2 { + led-alarm2 { label = "alarm:yellow"; gpios = <&gpio4 27 GPIO_ACTIVE_HIGH>; }; - alarm3 { + led-alarm3 { label = "alarm:blue"; gpios = <&gpio4 15 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/imx6dl-riotboard.dts b/arch/arm/boot/dts/imx6dl-riotboard.dts index e7be05f205d3..24c7f535f63b 100644 --- a/arch/arm/boot/dts/imx6dl-riotboard.dts +++ b/arch/arm/boot/dts/imx6dl-riotboard.dts @@ -25,14 +25,14 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio5 2 GPIO_ACTIVE_LOW>; default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio3 28 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index 52162e8c7274..aacbf317feea 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -274,7 +274,7 @@ leds: led-controller@30 { #address-cells = <1>; #size-cells = <0>; - chan@0 { + led@0 { chan-name = "R"; led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; @@ -282,7 +282,7 @@ chan@0 { color = ; }; - chan@1 { + led@1 { chan-name = "G"; led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; @@ -290,7 +290,7 @@ chan@1 { color = ; }; - chan@2 { + led@2 { chan-name = "B"; led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts index e894faba571f..522a51042965 100644 --- a/arch/arm/boot/dts/imx6q-gw5400-a.dts +++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts @@ -34,20 +34,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* 102 -> MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 10 GPIO_ACTIVE_HIGH>; /* 106 -> MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* 111 -> MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6q-h100.dts b/arch/arm/boot/dts/imx6q-h100.dts index b8feadbff967..6406ade14f57 100644 --- a/arch/arm/boot/dts/imx6q-h100.dts +++ b/arch/arm/boot/dts/imx6q-h100.dts @@ -76,19 +76,19 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_h100_leds>; - led0: power { + led0: led-power { label = "power"; gpios = <&gpio3 0 GPIO_ACTIVE_LOW>; default-state = "on"; }; - led1: stream { + led1: led-stream { label = "stream"; gpios = <&gpio2 29 GPIO_ACTIVE_LOW>; default-state = "off"; }; - led2: rec { + led2: led-rec { label = "rec"; gpios = <&gpio2 28 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6q-kp.dtsi b/arch/arm/boot/dts/imx6q-kp.dtsi index 1ade0bff681d..5e0ed5560040 100644 --- a/arch/arm/boot/dts/imx6q-kp.dtsi +++ b/arch/arm/boot/dts/imx6q-kp.dtsi @@ -66,14 +66,14 @@ lcd_panel_in: endpoint { leds { compatible = "gpio-leds"; - green { + led-green { label = "led1"; gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>; linux,default-trigger = "gpio"; default-state = "off"; }; - red { + led-red { label = "led0"; gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; linux,default-trigger = "gpio"; diff --git a/arch/arm/boot/dts/imx6q-marsboard.dts b/arch/arm/boot/dts/imx6q-marsboard.dts index cc1801002394..2c9961333b0a 100644 --- a/arch/arm/boot/dts/imx6q-marsboard.dts +++ b/arch/arm/boot/dts/imx6q-marsboard.dts @@ -73,14 +73,14 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user1 { + led-user1 { label = "imx6:green:user1"; gpios = <&gpio5 2 GPIO_ACTIVE_LOW>; default-state = "off"; linux,default-trigger = "heartbeat"; }; - user2 { + led-user2 { label = "imx6:green:user2"; gpios = <&gpio3 28 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts index 8daef65d5bb3..2f576e2ce73f 100644 --- a/arch/arm/boot/dts/imx6q-tbs2910.dts +++ b/arch/arm/boot/dts/imx6q-tbs2910.dts @@ -49,7 +49,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - blue { + led-blue { label = "blue_status_led"; gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>; default-state = "keep"; diff --git a/arch/arm/boot/dts/imx6qdl-emcon.dtsi b/arch/arm/boot/dts/imx6qdl-emcon.dtsi index 7228b894a763..ee2dd75cead6 100644 --- a/arch/arm/boot/dts/imx6qdl-emcon.dtsi +++ b/arch/arm/boot/dts/imx6qdl-emcon.dtsi @@ -46,14 +46,14 @@ som_leds: leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_som_leds>; - green { + led-green { label = "som:green"; gpios = <&gpio3 0 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; default-state = "on"; }; - red { + led-red { label = "som:red"; gpios = <&gpio3 1 GPIO_ACTIVE_LOW>; default-state = "keep"; diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi index 069c27fab432..e75e1a5364b8 100644 --- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi @@ -71,14 +71,14 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 728810b9d677..47d9a8d08197 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -80,20 +80,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi index 6c0c109046d8..fb1d29abe099 100644 --- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi @@ -80,20 +80,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi index a9b04f9f1c2b..4e20cb97058e 100644 --- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi @@ -81,20 +81,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi index 435dec6338fe..0fa4b8eeddee 100644 --- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi @@ -115,7 +115,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 7 GPIO_ACTIVE_LOW>; default-state = "on"; diff --git a/arch/arm/boot/dts/imx6qdl-gw552x.dtsi b/arch/arm/boot/dts/imx6qdl-gw552x.dtsi index 2e61102ae694..77ae611b817a 100644 --- a/arch/arm/boot/dts/imx6qdl-gw552x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw552x.dtsi @@ -72,20 +72,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw553x.dtsi b/arch/arm/boot/dts/imx6qdl-gw553x.dtsi index 4662408b225a..7f16c602cc07 100644 --- a/arch/arm/boot/dts/imx6qdl-gw553x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw553x.dtsi @@ -113,14 +113,14 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 10 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi index 4b81a975c979..46cf4080fec3 100644 --- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -139,20 +139,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5903.dtsi b/arch/arm/boot/dts/imx6qdl-gw5903.dtsi index 1fdb7ba630f1..a74cde050158 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5903.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5903.dtsi @@ -123,7 +123,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio6 14 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5904.dtsi b/arch/arm/boot/dts/imx6qdl-gw5904.dtsi index 612b6e068e28..9fc79af2bc9a 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5904.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5904.dtsi @@ -120,20 +120,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5907.dtsi b/arch/arm/boot/dts/imx6qdl-gw5907.dtsi index fcd3bdfd6182..955a51226eda 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5907.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5907.dtsi @@ -71,14 +71,14 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index 6bb4855d13ce..218d6e667ed2 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -74,20 +74,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5912.dtsi b/arch/arm/boot/dts/imx6qdl-gw5912.dtsi index 0415bcb41640..40e235e315cc 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5912.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5912.dtsi @@ -72,20 +72,20 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; }; - led2: user3 { + led2: led-user3 { label = "user3"; gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; /* MX6_LOCLED# */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 696427b487f0..82f47c295b08 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -71,14 +71,14 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - led0: user1 { + led0: led-user1 { label = "user1"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDG */ default-state = "on"; linux,default-trigger = "heartbeat"; }; - led1: user2 { + led1: led-user2 { label = "user2"; gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>; /* MX6_PANLEDR */ default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi index a53a5d0766a5..6d4eab1942b9 100644 --- a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi @@ -85,31 +85,31 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_leds>; - j14-pin1 { + led-j14-pin1 { gpios = <&gpio1 2 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j14-pin3 { + led-j14-pin3 { gpios = <&gpio1 3 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j14-pins8-9 { + led-j14-pins8-9 { gpios = <&gpio3 29 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j46-pin2 { + led-j46-pin2 { gpios = <&gpio1 7 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; }; - j46-pin3 { + led-j46-pin3 { gpios = <&gpio1 8 GPIO_ACTIVE_LOW>; retain-state-suspended; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi index 57c21a01f126..81a9a302aec1 100644 --- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi @@ -181,13 +181,13 @@ i2c3mux@1 { leds { compatible = "gpio-leds"; - speaker-enable { + led-speaker-enable { gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; retain-state-suspended; default-state = "off"; }; - ttymxc4-rs232 { + led-ttymxc4-rs232 { gpios = <&gpio6 10 GPIO_ACTIVE_HIGH>; retain-state-suspended; default-state = "on"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi index 120d6e997a4c..1a599c294ab8 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi @@ -25,17 +25,17 @@ gpio_leds: leds { pinctrl-0 = <&pinctrl_gpioleds>; status = "disabled"; - red { + led-red { label = "phyboard-mira:red"; gpios = <&gpio5 22 GPIO_ACTIVE_HIGH>; }; - green { + led-green { label = "phyboard-mira:green"; gpios = <&gpio5 23 GPIO_ACTIVE_HIGH>; }; - blue { + led-blue { label = "phyboard-mira:blue"; gpios = <&gpio5 24 GPIO_ACTIVE_HIGH>; linux,default-trigger = "mmc0"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 768bc0e3a2b3..80adb2a02cc9 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -47,12 +47,12 @@ gpio_leds: leds { pinctrl-0 = <&pinctrl_leds>; compatible = "gpio-leds"; - led_green: green { + led_green: led-green { label = "phyflex:green"; gpios = <&gpio1 30 0>; }; - led_red: red { + led_red: led-red { label = "phyflex:red"; gpios = <&gpio2 31 0>; }; diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi index de514eb5aa99..f804ff95a6ad 100644 --- a/arch/arm/boot/dts/imx6qdl-rex.dtsi +++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi @@ -55,7 +55,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - led0: usr { + led0: led-usr { label = "usr"; gpios = <&gpio1 2 GPIO_ACTIVE_LOW>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 3dbb460ef102..10886a1461bf 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -21,7 +21,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - user { + led-user { label = "debug"; gpios = <&gpio5 15 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi index 37482a9023fc..bcb83d52e26e 100644 --- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi @@ -130,7 +130,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - red { + led-red { gpios = <&gpio1 2 0>; default-state = "on"; }; diff --git a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi index c096d25a6f5b..1e0a041e9f60 100644 --- a/arch/arm/boot/dts/imx6qdl-ts7970.dtsi +++ b/arch/arm/boot/dts/imx6qdl-ts7970.dtsi @@ -73,13 +73,13 @@ blue-led { default-state = "off"; }; - en-usb-5v { + en-usb-5v-led { label = "en-usb-5v"; gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>; default-state = "on"; }; - sel_dc_usb { + sel-dc-usb-led { label = "sel_dc_usb"; gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>; default-state = "off"; diff --git a/arch/arm/boot/dts/imx6qdl-tx6.dtsi b/arch/arm/boot/dts/imx6qdl-tx6.dtsi index f41f86a76ea9..a197bac95cba 100644 --- a/arch/arm/boot/dts/imx6qdl-tx6.dtsi +++ b/arch/arm/boot/dts/imx6qdl-tx6.dtsi @@ -92,7 +92,7 @@ power { leds { compatible = "gpio-leds"; - user_led: user { + user_led: led-user { label = "Heartbeat"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_user_led>; diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts index f16c830f1e91..dc5d596c18db 100644 --- a/arch/arm/boot/dts/imx6sl-evk.dts +++ b/arch/arm/boot/dts/imx6sl-evk.dts @@ -33,7 +33,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "debug"; gpios = <&gpio3 20 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6sll-evk.dts b/arch/arm/boot/dts/imx6sll-evk.dts index 32b3d82fec53..269092ac881c 100644 --- a/arch/arm/boot/dts/imx6sll-evk.dts +++ b/arch/arm/boot/dts/imx6sll-evk.dts @@ -37,7 +37,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "debug"; gpios = <&gpio2 4 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts index 83ee97252ff1..b0c27b9b0244 100644 --- a/arch/arm/boot/dts/imx6sx-sabreauto.dts +++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts @@ -20,7 +20,7 @@ leds { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; - user { + led-user { label = "debug"; gpios = <&gpio1 24 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi index c84ea1fac5e9..725d0b5cb55f 100644 --- a/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi +++ b/arch/arm/boot/dts/imx6sx-udoo-neo.dtsi @@ -15,14 +15,14 @@ chosen { leds { compatible = "gpio-leds"; - red { + led-red { label = "udoo-neo:red:mmc"; gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; default-state = "off"; linux,default-trigger = "mmc0"; }; - orange { + led-orange { label = "udoo-neo:orange:user"; gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>; default-state = "keep"; diff --git a/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi index 3cddc68917a0..e4d2652a75c0 100644 --- a/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/imx6ul-phytec-phycore-som.dtsi @@ -30,7 +30,7 @@ gpio_leds_som: leds { pinctrl-0 = <&pinctrl_gpioleds_som>; compatible = "gpio-leds"; - phycore-green { + led-phycore-green { gpios = <&gpio5 4 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; diff --git a/arch/arm/boot/dts/imx6ul-tx6ul.dtsi b/arch/arm/boot/dts/imx6ul-tx6ul.dtsi index 15ee0275feaf..70cef5e817bd 100644 --- a/arch/arm/boot/dts/imx6ul-tx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul-tx6ul.dtsi @@ -131,7 +131,7 @@ ds1339: rtc@68 { leds { compatible = "gpio-leds"; - user_led: user { + user_led: led-user { label = "Heartbeat"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_led>; From ca69bb14538366f3c86669cc40f8f2aff0993d6f Mon Sep 17 00:00:00 2001 From: Andrej Picej Date: Wed, 19 Jul 2023 13:43:26 +0200 Subject: [PATCH 0459/2093] ARM: dts: imx6: phytec: fix RTC interrupt level MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 762b700982a1e0f562184363f19860c3b9bdd0bf ] RTC interrupt level should be set to "LOW". This was revealed by the introduction of commit: f181987ef477 ("rtc: m41t80: use IRQ flags obtained from fwnode") which changed the way IRQ type is obtained. Signed-off-by: Andrej Picej Reviewed-by: Stefan Riedmüller Fixes: 800d595151bb ("ARM: dts: imx6: Add initial support for phyBOARD-Mira") Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi index 1a599c294ab8..1ca4d219609f 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-mira.dtsi @@ -182,7 +182,7 @@ i2c_rtc: rtc@68 { pinctrl-0 = <&pinctrl_rtc_int>; reg = <0x68>; interrupt-parent = <&gpio7>; - interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; status = "disabled"; }; }; From 6777c4379bd813613e118fdd07f7a2c2e0d9069f Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 25 Jul 2023 20:26:28 -0300 Subject: [PATCH 0460/2093] arm64: dts: imx8mm: Drop CSI1 PHY reference clock configuration [ Upstream commit f02b53375e8f14b4c27a14f6e4fb6e89914fdc29 ] The CSI1 PHY reference clock is limited to 125 MHz according to: i.MX 8M Mini Applications Processor Reference Manual, Rev. 3, 11/2020 Table 5-1. Clock Root Table (continued) / page 307 Slice Index n = 123 . Currently the IMX8MM_CLK_CSI1_PHY_REF clock is configured to be fed directly from 1 GHz PLL2 , which overclocks them. Instead, drop the configuration altogether, which defaults the clock to 24 MHz REF clock input, which for the PHY reference clock is just fine. Based on a patch from Marek Vasut for the imx8mn. Fixes: e523b7c54c05 ("arm64: dts: imx8mm: Add CSI nodes") Signed-off-by: Fabio Estevam Reviewed-by: Marek Vasut Reviewed-by: Marco Felsch Reviewed-by: Adam Ford Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm.dtsi | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 420ba0d6f134..12c82bb1bb7a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -1145,10 +1145,9 @@ mipi_csi: mipi-csi@32e30000 { compatible = "fsl,imx8mm-mipi-csi2"; reg = <0x32e30000 0x1000>; interrupts = ; - assigned-clocks = <&clk IMX8MM_CLK_CSI1_CORE>, - <&clk IMX8MM_CLK_CSI1_PHY_REF>; - assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_1000M>, - <&clk IMX8MM_SYS_PLL2_1000M>; + assigned-clocks = <&clk IMX8MM_CLK_CSI1_CORE>; + assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_1000M>; + clock-frequency = <333000000>; clocks = <&clk IMX8MM_CLK_DISP_APB_ROOT>, <&clk IMX8MM_CLK_CSI1_ROOT>, From 9ba52bd26774a44f703205f340bfbcb7f833ab36 Mon Sep 17 00:00:00 2001 From: Xiaolei Wang Date: Wed, 26 Jul 2023 15:57:47 +0800 Subject: [PATCH 0461/2093] ARM: dts: imx: Set default tuning step for imx6sx usdhc [ Upstream commit 0a2b96e42a0284c4fc03022236f656a085ca714a ] If the tuning step is not set, the tuning step is set to 1. For some sd cards, the following Tuning timeout will occur. Tuning failed, falling back to fixed sampling clock So set the default tuning step. This refers to the NXP vendor's commit below: https://github.com/nxp-imx/linux-imx/blob/lf-6.1.y/ arch/arm/boot/dts/imx6sx.dtsi#L1108-L1109 Fixes: 1e336aa0c025 ("mmc: sdhci-esdhc-imx: correct the tuning start tap and step setting") Signed-off-by: Xiaolei Wang Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6sx.dtsi | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index abc3572d699e..1f1053a898fb 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -981,6 +981,8 @@ usdhc1: mmc@2190000 { <&clks IMX6SX_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; @@ -993,6 +995,8 @@ usdhc2: mmc@2194000 { <&clks IMX6SX_CLK_USDHC2>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; @@ -1005,6 +1009,8 @@ usdhc3: mmc@2198000 { <&clks IMX6SX_CLK_USDHC3>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; From 2b34636b50bffca778b14445e93c2a54a75dd99b Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 28 Jul 2023 10:34:35 +0200 Subject: [PATCH 0462/2093] arm64: dts: imx93: Fix anatop node size [ Upstream commit 78e869dd8b2ba19765ac9b05cdea3e432d1dc188 ] Although the memory map of i.MX93 reference manual rev. 2 claims that analog top has start address of 0x44480000 and end address of 0x4448ffff, this overlaps with TMU memory area starting at 0x44482000, as stated in section 73.6.1. As PLL configuration registers start at addresses up to 0x44481400, as used by clk-imx93, reduce the anatop size to 0x2000, so exclude the TMU area but keep all PLL registers inside. Fixes: ec8b5b5058ea ("arm64: dts: freescale: Add i.MX93 dtsi support") Signed-off-by: Alexander Stein Reviewed-by: Peng Fan Reviewed-by: Jacky Bai Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx93.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 8ab9f8194702..c2f60d41d6fd 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -254,7 +254,7 @@ mlmix: power-domain@44461800 { anatop: anatop@44480000 { compatible = "fsl,imx93-anatop", "syscon"; - reg = <0x44480000 0x10000>; + reg = <0x44480000 0x2000>; }; }; From f0451002a4d9b870e633292a056be088af61c8c7 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Tue, 1 Aug 2023 23:59:11 +0800 Subject: [PATCH 0463/2093] ASoC: rt5665: add missed regulator_bulk_disable [ Upstream commit c163108e706909570f8aa9aa5bcf6806e2b4c98c ] The driver forgets to call regulator_bulk_disable() Add the missed call to fix it. Fixes: 33ada14a26c8 ("ASoC: add rt5665 codec driver") Signed-off-by: Zhang Shurong Link: https://lore.kernel.org/r/tencent_A560D01E3E0A00A85A12F137E4B5205B3508@qq.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt5665.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/codecs/rt5665.c b/sound/soc/codecs/rt5665.c index 6e66cc218fa8..76ff097518c8 100644 --- a/sound/soc/codecs/rt5665.c +++ b/sound/soc/codecs/rt5665.c @@ -4472,6 +4472,8 @@ static void rt5665_remove(struct snd_soc_component *component) struct rt5665_priv *rt5665 = snd_soc_component_get_drvdata(component); regmap_write(rt5665->regmap, RT5665_RESET, 0); + + regulator_bulk_disable(ARRAY_SIZE(rt5665->supplies), rt5665->supplies); } #ifdef CONFIG_PM From 7b041466ed424a57e093ee31615a0e1231fc9196 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 9 Aug 2023 19:19:31 +0200 Subject: [PATCH 0464/2093] ASoC: meson: axg-tdm-formatter: fix channel slot allocation [ Upstream commit c1f848f12103920ca165758aedb1c10904e193e1 ] When the tdm lane mask is computed, the driver currently fills the 1st lane before moving on to the next. If the stream has less channels than the lanes can accommodate, slots will be disabled on the last lanes. Unfortunately, the HW distribute channels in a different way. It distribute channels in pair on each lanes before moving on the next slots. This difference leads to problems if a device has an interface with more than 1 lane and with more than 2 slots per lane. For example: a playback interface with 2 lanes and 4 slots each (total 8 slots - zero based numbering) - Playing a 8ch stream: - All slots activated by the driver - channel #2 will be played on lane #1 - slot #0 following HW placement - Playing a 4ch stream: - Lane #1 disabled by the driver - channel #2 will be played on lane #0 - slot #2 This behaviour is obviously not desirable. Change the way slots are activated on the TDM lanes to follow what the HW does and make sure each channel always get mapped to the same slot/lane. Fixes: 1a11d88f499c ("ASoC: meson: add tdm formatter base driver") Signed-off-by: Jerome Brunet Link: https://lore.kernel.org/r/20230809171931.1244502-1-jbrunet@baylibre.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/meson/axg-tdm-formatter.c | 42 ++++++++++++++++++----------- 1 file changed, 26 insertions(+), 16 deletions(-) diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c index 9883dc777f63..63333a2b0a9c 100644 --- a/sound/soc/meson/axg-tdm-formatter.c +++ b/sound/soc/meson/axg-tdm-formatter.c @@ -30,27 +30,32 @@ int axg_tdm_formatter_set_channel_masks(struct regmap *map, struct axg_tdm_stream *ts, unsigned int offset) { - unsigned int val, ch = ts->channels; - unsigned long mask; - int i, j; + unsigned int ch = ts->channels; + u32 val[AXG_TDM_NUM_LANES]; + int i, j, k; + + /* + * We need to mimick the slot distribution used by the HW to keep the + * channel placement consistent regardless of the number of channel + * in the stream. This is why the odd algorithm below is used. + */ + memset(val, 0, sizeof(*val) * AXG_TDM_NUM_LANES); /* * Distribute the channels of the stream over the available slots - * of each TDM lane + * of each TDM lane. We need to go over the 32 slots ... */ - for (i = 0; i < AXG_TDM_NUM_LANES; i++) { - val = 0; - mask = ts->mask[i]; - - for (j = find_first_bit(&mask, 32); - (j < 32) && ch; - j = find_next_bit(&mask, 32, j + 1)) { - val |= 1 << j; - ch -= 1; + for (i = 0; (i < 32) && ch; i += 2) { + /* ... of all the lanes ... */ + for (j = 0; j < AXG_TDM_NUM_LANES; j++) { + /* ... then distribute the channels in pairs */ + for (k = 0; k < 2; k++) { + if ((BIT(i + k) & ts->mask[j]) && ch) { + val[j] |= BIT(i + k); + ch -= 1; + } + } } - - regmap_write(map, offset, val); - offset += regmap_get_reg_stride(map); } /* @@ -63,6 +68,11 @@ int axg_tdm_formatter_set_channel_masks(struct regmap *map, return -EINVAL; } + for (i = 0; i < AXG_TDM_NUM_LANES; i++) { + regmap_write(map, offset, val[i]); + offset += regmap_get_reg_stride(map); + } + return 0; } EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks); From 6c889d2123ba293f02b0d200657ef734cd83f750 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Wed, 9 Aug 2023 15:29:56 +0100 Subject: [PATCH 0465/2093] ALSA: hda/realtek: Add quirks for HP G11 Laptops [ Upstream commit fb8cce69e5e56eedb35fc4d77b2f099860965859 ] These HP G11 laptops use Realtek HDA codec combined with 2xCS35L41 Amplifiers using SPI or I2C with External Boost. Laptop 103c8c26 has been removed as this has been replaced by this new series of laptops. Fixes: 3e10f6ca76c4 ("ALSA: hda/realtek: Add quirk for HP EliteBook G10 laptops") Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20230809142957.675933-2-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 526ec8cae943..de6bd8a9871c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9596,7 +9596,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c46, "HP EliteBook 830 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c47, "HP EliteBook 840 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c48, "HP EliteBook 860 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c49, "HP Elite x360 830 2-in-1 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From 15db1e594e2c44fbe1508e92d966df584258f6c4 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Thu, 10 Aug 2023 21:59:41 +0930 Subject: [PATCH 0466/2093] soc: aspeed: uart-routing: Use __sysfs_match_string [ Upstream commit e4ad279ae345413d900d791f2f618d0a1cd0d791 ] The existing use of match_string() caused it to reject 'echo foo' due to the implicitly appended newline, which was somewhat ergonomically awkward and inconsistent with typical sysfs behavior. Using the __sysfs_* variant instead provides more convenient and consistent linefeed-agnostic behavior. Signed-off-by: Zev Weiss Fixes: c6807970c3bc ("soc: aspeed: Add UART routing support") Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20230628083735.19946-2-zev@bewilderbeest.net Signed-off-by: Joel Stanley Link: https://lore.kernel.org/r/20230810122941.231085-1-joel@jms.id.au Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- drivers/soc/aspeed/aspeed-uart-routing.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/aspeed/aspeed-uart-routing.c b/drivers/soc/aspeed/aspeed-uart-routing.c index ef8b24fd1851..59123e1f27ac 100644 --- a/drivers/soc/aspeed/aspeed-uart-routing.c +++ b/drivers/soc/aspeed/aspeed-uart-routing.c @@ -524,7 +524,7 @@ static ssize_t aspeed_uart_routing_store(struct device *dev, struct aspeed_uart_routing_selector *sel = to_routing_selector(attr); int val; - val = match_string(sel->options, -1, buf); + val = __sysfs_match_string(sel->options, -1, buf); if (val < 0) { dev_err(dev, "invalid value \"%s\"\n", buf); return -EINVAL; From b662856b71343d9e731c1cd4bbe54758c7791abb Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 10 Aug 2023 22:01:04 +0930 Subject: [PATCH 0467/2093] soc: aspeed: socinfo: Add kfree for kstrdup [ Upstream commit 6e6d847a8ce18ab2fbec4f579f682486a82d2c6b ] Add kfree() in the later error handling in order to avoid memory leak. Fixes: e0218dca5787 ("soc: aspeed: Add soc info driver") Signed-off-by: Jiasheng Jiang Link: https://lore.kernel.org/r/20230707021625.7727-1-jiasheng@iscas.ac.cn Signed-off-by: Joel Stanley Link: https://lore.kernel.org/r/20230810123104.231167-1-joel@jms.id.au Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- drivers/soc/aspeed/aspeed-socinfo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soc/aspeed/aspeed-socinfo.c b/drivers/soc/aspeed/aspeed-socinfo.c index 1ca140356a08..3f759121dc00 100644 --- a/drivers/soc/aspeed/aspeed-socinfo.c +++ b/drivers/soc/aspeed/aspeed-socinfo.c @@ -137,6 +137,7 @@ static int __init aspeed_socinfo_init(void) soc_dev = soc_device_register(attrs); if (IS_ERR(soc_dev)) { + kfree(attrs->machine); kfree(attrs->soc_id); kfree(attrs->serial_number); kfree(attrs); From ea65d78ef999e1d220c126f58d2dd77d5eec775a Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Tue, 15 Aug 2023 15:54:23 +0800 Subject: [PATCH 0468/2093] ALSA: hda/realtek - Remodified 3k pull low procedure [ Upstream commit 46cdff2369cbdf8d78081a22526e77bd1323f563 ] Set spec->en_3kpull_low default to true. Then fillback ALC236 and ALC257 to false. Additional note: this addresses a regression caused by the previous fix 69ea4c9d02b7 ("ALSA: hda/realtek - remove 3k pull low procedure"). The previous workaround was applied too widely without necessity, which resulted in the pop noise at PM again. This patch corrects the condition and restores the old behavior for the devices that don't suffer from the original problem. Fixes: 69ea4c9d02b7 ("ALSA: hda/realtek - remove 3k pull low procedure") Link: https://bugzilla.kernel.org/show_bug.cgi?id=217732 Link: https://lore.kernel.org/r/01e212a538fc407ca6edd10b81ff7b05@realtek.com Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index de6bd8a9871c..aa475154c582 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10620,6 +10620,7 @@ static int patch_alc269(struct hda_codec *codec) spec = codec->spec; spec->gen.shared_mic_vref_pin = 0x18; codec->power_save_node = 0; + spec->en_3kpull_low = true; #ifdef CONFIG_PM codec->patch_ops.suspend = alc269_suspend; @@ -10702,14 +10703,16 @@ static int patch_alc269(struct hda_codec *codec) spec->shutup = alc256_shutup; spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ - if (codec->bus->pci->vendor == PCI_VENDOR_ID_AMD) - spec->en_3kpull_low = true; + if (codec->core.vendor_id == 0x10ec0236 && + codec->bus->pci->vendor != PCI_VENDOR_ID_AMD) + spec->en_3kpull_low = false; break; case 0x10ec0257: spec->codec_variant = ALC269_TYPE_ALC257; spec->shutup = alc256_shutup; spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; + spec->en_3kpull_low = false; break; case 0x10ec0215: case 0x10ec0245: From af7ca7ad37530c7e26d839e47a636284fdf5002e Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 11 Aug 2023 17:06:04 +0200 Subject: [PATCH 0469/2093] riscv: uaccess: Return the number of bytes effectively not copied MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4b05b993900dd3eba0fc83ef5c5ddc7d65d786c6 ] It was reported that the riscv kernel hangs while executing the test in [1]. Indeed, the test hangs when trying to write a buffer to a file. The problem is that the riscv implementation of raw_copy_from_user() does not return the correct number of bytes not written when an exception happens and is fixed up, instead it always returns the initial size to copy, even if some bytes were actually copied. generic_perform_write() pre-faults the user pages and bails out if nothing can be written, otherwise it will access the userspace buffer: here the riscv implementation keeps returning it was not able to copy any byte though the pre-faulting indicates otherwise. So generic_perform_write() keeps retrying to access the user memory and ends up in an infinite loop. Note that before the commit mentioned in [1] that introduced this regression, it worked because generic_perform_write() would bail out if only one byte could not be written. So fix this by returning the number of bytes effectively not written in __asm_copy_[to|from]_user() and __clear_user(), as it is expected. Link: https://lore.kernel.org/linux-riscv/20230309151841.bomov6hq3ybyp42a@debian/ [1] Fixes: ebcbd75e3962 ("riscv: Fix the bug in memory access fixup code") Reported-by: Bo YU Closes: https://lore.kernel.org/linux-riscv/20230309151841.bomov6hq3ybyp42a@debian/#t Reported-by: Aurelien Jarno Closes: https://lore.kernel.org/linux-riscv/ZNOnCakhwIeue3yr@aurel32.net/ Signed-off-by: Alexandre Ghiti Reviewed-by: Björn Töpel Tested-by: Aurelien Jarno Reviewed-by: Aurelien Jarno Link: https://lore.kernel.org/r/20230811150604.1621784-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/lib/uaccess.S | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index ec486e5369d9..09b47ebacf2e 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -17,8 +17,11 @@ ENTRY(__asm_copy_from_user) li t6, SR_SUM csrs CSR_STATUS, t6 - /* Save for return value */ - mv t5, a2 + /* + * Save the terminal address which will be used to compute the number + * of bytes copied in case of a fixup exception. + */ + add t5, a0, a2 /* * Register allocation for code below: @@ -176,7 +179,7 @@ ENTRY(__asm_copy_from_user) 10: /* Disable access to user memory */ csrc CSR_STATUS, t6 - mv a0, t5 + sub a0, t5, a0 ret ENDPROC(__asm_copy_to_user) ENDPROC(__asm_copy_from_user) @@ -228,7 +231,7 @@ ENTRY(__clear_user) 11: /* Disable access to user memory */ csrc CSR_STATUS, t6 - mv a0, a1 + sub a0, a3, a0 ret ENDPROC(__clear_user) EXPORT_SYMBOL(__clear_user) From 0c05493341d6f2097f75f0a5dbb7b53a9e8c5f6c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 4 Aug 2023 16:15:51 +0300 Subject: [PATCH 0470/2093] serial: 8250: Fix oops for port->pm on uart_change_pm() [ Upstream commit dfe2aeb226fd5e19b0ee795f4f6ed8bc494c1534 ] Unloading a hardware specific 8250 driver can produce error "Unable to handle kernel paging request at virtual address" about ten seconds after unloading the driver. This happens on uart_hangup() calling uart_change_pm(). Turns out commit 04e82793f068 ("serial: 8250: Reinit port->pm on port specific driver unbind") was only a partial fix. If the hardware specific driver has initialized port->pm function, we need to clear port->pm too. Just reinitializing port->ops does not do this. Otherwise serial8250_pm() will call port->pm() instead of serial8250_do_pm(). Fixes: 04e82793f068 ("serial: 8250: Reinit port->pm on port specific driver unbind") Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20230804131553.52927-1-tony@atomide.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_port.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index acf578aa9930..38760bd6e0c2 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -3281,6 +3281,7 @@ void serial8250_init_port(struct uart_8250_port *up) struct uart_port *port = &up->port; spin_lock_init(&port->lock); + port->pm = NULL; port->ops = &serial8250_pops; port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); From bfd25f5e6400a50990ed9871601b65c2ad74f34e Mon Sep 17 00:00:00 2001 From: dengxiang Date: Thu, 3 Aug 2023 10:44:37 +0800 Subject: [PATCH 0471/2093] ALSA: usb-audio: Add support for Mythware XA001AU capture and playback interfaces. commit 788449ae57f4273111b779bbcaad552b67f517d5 upstream. This patch adds a USB quirk for Mythware XA001AU USB interface. Signed-off-by: dengxiang Cc: Link: https://lore.kernel.org/r/20230803024437.370069-1-dengxiang@nfschina.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks-table.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index efb4a3311cc5..5d72dc8441cb 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -4507,6 +4507,35 @@ YAMAHA_DEVICE(0x7010, "UB99"), } } }, +{ + /* Advanced modes of the Mythware XA001AU. + * For the standard mode, Mythware XA001AU has ID ffad:a001 + */ + USB_DEVICE_VENDOR_SPEC(0xffad, 0xa001), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .vendor_name = "Mythware", + .product_name = "XA001AU", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_IGNORE_INTERFACE, + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE, + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE, + }, + { + .ifnum = -1 + } + } + } +}, #undef USB_DEVICE_VENDOR_SPEC #undef USB_AUDIO_DEVICE From 9e725386d4262ef23ae51993f04602bc535b5be2 Mon Sep 17 00:00:00 2001 From: Russell Harmon via samba-technical Date: Thu, 10 Aug 2023 00:19:22 -0700 Subject: [PATCH 0472/2093] cifs: Release folio lock on fscache read hit. commit 69513dd669e243928f7450893190915a88f84a2b upstream. Under the current code, when cifs_readpage_worker is called, the call contract is that the callee should unlock the page. This is documented in the read_folio section of Documentation/filesystems/vfs.rst as: > The filesystem should unlock the folio once the read has completed, > whether it was successful or not. Without this change, when fscache is in use and cache hit occurs during a read, the page lock is leaked, producing the following stack on subsequent reads (via mmap) to the page: $ cat /proc/3890/task/12864/stack [<0>] folio_wait_bit_common+0x124/0x350 [<0>] filemap_read_folio+0xad/0xf0 [<0>] filemap_fault+0x8b1/0xab0 [<0>] __do_fault+0x39/0x150 [<0>] do_fault+0x25c/0x3e0 [<0>] __handle_mm_fault+0x6ca/0xc70 [<0>] handle_mm_fault+0xe9/0x350 [<0>] do_user_addr_fault+0x225/0x6c0 [<0>] exc_page_fault+0x84/0x1b0 [<0>] asm_exc_page_fault+0x27/0x30 This requires a reboot to resolve; it is a deadlock. Note however that the call to cifs_readpage_from_fscache does mark the page clean, but does not free the folio lock. This happens in __cifs_readpage_from_fscache on success. Releasing the lock at that point however is not appropriate as cifs_readahead also calls cifs_readpage_from_fscache and *does* unconditionally release the lock after its return. This change therefore effectively makes cifs_readpage_worker work like cifs_readahead. Signed-off-by: Russell Harmon Acked-by: Paulo Alcantara (SUSE) Reviewed-by: David Howells Cc: stable@vger.kernel.org Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 0a8adec515ae..0f3405e0f2e4 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -4885,9 +4885,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page, io_error: kunmap(page); - unlock_page(page); read_complete: + unlock_page(page); return rc; } From fc66f81579170861c798819c4f495ee9b80ba7ff Mon Sep 17 00:00:00 2001 From: Hawkins Jiawei Date: Thu, 10 Aug 2023 19:04:05 +0800 Subject: [PATCH 0473/2093] virtio-net: Zero max_tx_vq field for VIRTIO_NET_CTRL_MQ_HASH_CONFIG case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2c507ce90e02cd78d00fd4b0fe26c8641873c13f upstream. Kernel uses `struct virtio_net_ctrl_rss` to save command-specific-data for both the VIRTIO_NET_CTRL_MQ_HASH_CONFIG and VIRTIO_NET_CTRL_MQ_RSS_CONFIG commands. According to the VirtIO standard, "Field reserved MUST contain zeroes. It is defined to make the structure to match the layout of virtio_net_rss_config structure, defined in 5.1.6.5.7.". Yet for the VIRTIO_NET_CTRL_MQ_HASH_CONFIG command case, the `max_tx_vq` field in struct virtio_net_ctrl_rss, which corresponds to the `reserved` field in struct virtio_net_hash_config, is not zeroed, thereby violating the VirtIO standard. This patch solves this problem by zeroing this field in virtnet_init_default_rss(). Cc: Andrew Melnychenko Cc: stable@vger.kernel.org Fixes: c7114b1249fa ("drivers/net/virtio_net: Added basic RSS support.") Signed-off-by: Hawkins Jiawei Acked-by: Jason Wang Acked-by: Eugenio Pérez Acked-by: Michael S. Tsirkin Message-Id: <20230810110405.25558-1-yin31149@gmail.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo Acked-by: Jason Wang Signed-off-by: Greg Kroah-Hartman --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 55c20ccb791e..21d3461fb5d1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2504,7 +2504,7 @@ static void virtnet_init_default_rss(struct virtnet_info *vi) vi->ctrl->rss.indirection_table[i] = indir_val; } - vi->ctrl->rss.max_tx_vq = vi->curr_queue_pairs; + vi->ctrl->rss.max_tx_vq = vi->has_rss ? vi->curr_queue_pairs : 0; vi->ctrl->rss.hash_key_length = vi->rss_key_size; netdev_rss_key_fill(vi->ctrl->rss.key, vi->rss_key_size); From 65bcb07b1262f995301d5343834c23ebc1312f96 Mon Sep 17 00:00:00 2001 From: Yogesh Hegde Date: Tue, 18 Jul 2023 22:09:41 +0530 Subject: [PATCH 0474/2093] arm64: dts: rockchip: Fix Wifi/Bluetooth on ROCK Pi 4 boards commit ebceec271e552a2b05e47d8ef0597052b1a39449 upstream. This patch fixes an issue affecting the Wifi/Bluetooth connectivity on ROCK Pi 4 boards. Commit f471b1b2db08 ("arm64: dts: rockchip: Fix Bluetooth on ROCK Pi 4 boards") introduced a problem with the clock configuration. Specifically, the clock-names property of the sdio-pwrseq node was not updated to 'lpo', causing the driver to wait indefinitely for the wrong clock signal 'ext_clock' instead of the expected one 'lpo'. This prevented the proper initialization of Wifi/Bluetooth chip on ROCK Pi 4 boards. To address this, this patch updates the clock-names property of the sdio-pwrseq node to "lpo" to align with the changes made to the bluetooth node. This patch has been tested on ROCK Pi 4B. Fixes: f471b1b2db08 ("arm64: dts: rockchip: Fix Bluetooth on ROCK Pi 4 boards") Cc: stable@vger.kernel.org Signed-off-by: Yogesh Hegde Link: https://lore.kernel.org/r/ZLbATQRjOl09aLAp@zephyrusG14 Signed-off-by: Heiko Stuebner Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 24fbb06007f9..9bdc0b93001f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -45,7 +45,7 @@ led-0 { sdio_pwrseq: sdio-pwrseq { compatible = "mmc-pwrseq-simple"; clocks = <&rk808 1>; - clock-names = "ext_clock"; + clock-names = "lpo"; pinctrl-names = "default"; pinctrl-0 = <&wifi_enable_h>; reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>; From 8ad3bfdd227e0f644e0c528c9d80d108a74c0f0f Mon Sep 17 00:00:00 2001 From: Sweet Tea Dorminy Date: Thu, 17 Aug 2023 10:15:56 -0400 Subject: [PATCH 0475/2093] blk-crypto: dynamically allocate fallback profile commit c984ff1423ae9f70b1f28ce811856db0d9c99021 upstream. blk_crypto_profile_init() calls lockdep_register_key(), which warns and does not register if the provided memory is a static object. blk-crypto-fallback currently has a static blk_crypto_profile and calls blk_crypto_profile_init() thereupon, resulting in the warning and failure to register. Fortunately it is simple enough to use a dynamically allocated profile and make lockdep function correctly. Fixes: 2fb48d88e77f ("blk-crypto: use dynamic lock class for blk_crypto_profile::lock") Cc: stable@vger.kernel.org Signed-off-by: Sweet Tea Dorminy Reviewed-by: Eric Biggers Link: https://lore.kernel.org/r/20230817141615.15387-1-sweettea-kernel@dorminy.me Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-crypto-fallback.c | 36 +++++++++++++++++++++++------------- 1 file changed, 23 insertions(+), 13 deletions(-) diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index ad9844c5b40c..e6468eab2681 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -78,7 +78,7 @@ static struct blk_crypto_fallback_keyslot { struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX]; } *blk_crypto_keyslots; -static struct blk_crypto_profile blk_crypto_fallback_profile; +static struct blk_crypto_profile *blk_crypto_fallback_profile; static struct workqueue_struct *blk_crypto_wq; static mempool_t *blk_crypto_bounce_page_pool; static struct bio_set crypto_bio_split; @@ -292,7 +292,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr) * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for * this bio's algorithm and key. */ - blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile, + blk_st = blk_crypto_get_keyslot(blk_crypto_fallback_profile, bc->bc_key, &slot); if (blk_st != BLK_STS_OK) { src_bio->bi_status = blk_st; @@ -395,7 +395,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work) * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for * this bio's algorithm and key. */ - blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile, + blk_st = blk_crypto_get_keyslot(blk_crypto_fallback_profile, bc->bc_key, &slot); if (blk_st != BLK_STS_OK) { bio->bi_status = blk_st; @@ -499,7 +499,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) return false; } - if (!__blk_crypto_cfg_supported(&blk_crypto_fallback_profile, + if (!__blk_crypto_cfg_supported(blk_crypto_fallback_profile, &bc->bc_key->crypto_cfg)) { bio->bi_status = BLK_STS_NOTSUPP; return false; @@ -526,7 +526,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) { - return __blk_crypto_evict_key(&blk_crypto_fallback_profile, key); + return __blk_crypto_evict_key(blk_crypto_fallback_profile, key); } static bool blk_crypto_fallback_inited; @@ -534,7 +534,6 @@ static int blk_crypto_fallback_init(void) { int i; int err; - struct blk_crypto_profile *profile = &blk_crypto_fallback_profile; if (blk_crypto_fallback_inited) return 0; @@ -545,18 +544,27 @@ static int blk_crypto_fallback_init(void) if (err) goto out; - err = blk_crypto_profile_init(profile, blk_crypto_num_keyslots); - if (err) + /* Dynamic allocation is needed because of lockdep_register_key(). */ + blk_crypto_fallback_profile = + kzalloc(sizeof(*blk_crypto_fallback_profile), GFP_KERNEL); + if (!blk_crypto_fallback_profile) { + err = -ENOMEM; goto fail_free_bioset; + } + + err = blk_crypto_profile_init(blk_crypto_fallback_profile, + blk_crypto_num_keyslots); + if (err) + goto fail_free_profile; err = -ENOMEM; - profile->ll_ops = blk_crypto_fallback_ll_ops; - profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; + blk_crypto_fallback_profile->ll_ops = blk_crypto_fallback_ll_ops; + blk_crypto_fallback_profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; /* All blk-crypto modes have a crypto API fallback. */ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) - profile->modes_supported[i] = 0xFFFFFFFF; - profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; + blk_crypto_fallback_profile->modes_supported[i] = 0xFFFFFFFF; + blk_crypto_fallback_profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; blk_crypto_wq = alloc_workqueue("blk_crypto_wq", WQ_UNBOUND | WQ_HIGHPRI | @@ -597,7 +605,9 @@ static int blk_crypto_fallback_init(void) fail_free_wq: destroy_workqueue(blk_crypto_wq); fail_destroy_profile: - blk_crypto_profile_destroy(profile); + blk_crypto_profile_destroy(blk_crypto_fallback_profile); +fail_free_profile: + kfree(blk_crypto_fallback_profile); fail_free_bioset: bioset_exit(&crypto_bio_split); out: From dccd07b0d9e4efe795441514cdbd691bc1a5fb9e Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 7 Aug 2023 20:44:42 +0800 Subject: [PATCH 0476/2093] mmc: wbsd: fix double mmc_free_host() in wbsd_init() commit d83035433701919ac6db15f7737cbf554c36c1a6 upstream. mmc_free_host() has already be called in wbsd_free_mmc(), remove the mmc_free_host() in error path in wbsd_init(). Fixes: dc5b9b50fc9d ("mmc: wbsd: fix return value check of mmc_add_host()") Signed-off-by: Yang Yingliang Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230807124443.3431366-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/wbsd.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c index 7c7ec8d10232..b5b1a42ca25e 100644 --- a/drivers/mmc/host/wbsd.c +++ b/drivers/mmc/host/wbsd.c @@ -1705,8 +1705,6 @@ static int wbsd_init(struct device *dev, int base, int irq, int dma, wbsd_release_resources(host); wbsd_free_mmc(dev); - - mmc_free_host(mmc); return ret; } From 5818da46a2b5f04ff1c6b2b506c1137ffee1dbd6 Mon Sep 17 00:00:00 2001 From: Yibin Ding Date: Wed, 2 Aug 2023 10:30:23 +0800 Subject: [PATCH 0477/2093] mmc: block: Fix in_flight[issue_type] value error commit 4b430d4ac99750ee2ae2f893f1055c7af1ec3dc5 upstream. For a completed request, after the mmc_blk_mq_complete_rq(mq, req) function is executed, the bitmap_tags corresponding to the request will be cleared, that is, the request will be regarded as idle. If the request is acquired by a different type of process at this time, the issue_type of the request may change. It further caused the value of mq->in_flight[issue_type] to be abnormal, and a large number of requests could not be sent. p1: p2: mmc_blk_mq_complete_rq blk_mq_free_request blk_mq_get_request blk_mq_rq_ctx_init mmc_blk_mq_dec_in_flight mmc_issue_type(mq, req) This strategy can ensure the consistency of issue_type before and after executing mmc_blk_mq_complete_rq. Fixes: 81196976ed94 ("mmc: block: Add blk-mq support") Cc: stable@vger.kernel.org Signed-off-by: Yibin Ding Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20230802023023.1318134-1-yunlong.xing@unisoc.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/core/block.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 498333b769fd..cdd7f126d4ae 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2097,14 +2097,14 @@ static void mmc_blk_mq_poll_completion(struct mmc_queue *mq, mmc_blk_urgent_bkops(mq, mqrq); } -static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, struct request *req) +static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, enum mmc_issue_type issue_type) { unsigned long flags; bool put_card; spin_lock_irqsave(&mq->lock, flags); - mq->in_flight[mmc_issue_type(mq, req)] -= 1; + mq->in_flight[issue_type] -= 1; put_card = (mmc_tot_in_flight(mq) == 0); @@ -2117,6 +2117,7 @@ static void mmc_blk_mq_dec_in_flight(struct mmc_queue *mq, struct request *req) static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req, bool can_sleep) { + enum mmc_issue_type issue_type = mmc_issue_type(mq, req); struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req); struct mmc_request *mrq = &mqrq->brq.mrq; struct mmc_host *host = mq->card->host; @@ -2136,7 +2137,7 @@ static void mmc_blk_mq_post_req(struct mmc_queue *mq, struct request *req, blk_mq_complete_request(req); } - mmc_blk_mq_dec_in_flight(mq, req); + mmc_blk_mq_dec_in_flight(mq, issue_type); } void mmc_blk_mq_recovery(struct mmc_queue *mq) From a1fa8f0fc58e0ec972f718030710efc442d7304b Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Mon, 14 Aug 2023 13:51:19 -0300 Subject: [PATCH 0478/2093] drm/qxl: fix UAF on handle creation commit c611589b4259ed63b9b77be6872b1ce07ec0ac16 upstream. qxl_mode_dumb_create() dereferences the qobj returned by qxl_gem_object_create_with_handle(), but the handle is the only one holding a reference to it. A potential attacker could guess the returned handle value and closes it between the return of qxl_gem_object_create_with_handle() and the qobj usage, triggering a use-after-free scenario. Reproducer: int dri_fd =-1; struct drm_mode_create_dumb arg = {0}; void gem_close(int handle); void* trigger(void* ptr) { int ret; arg.width = arg.height = 0x20; arg.bpp = 32; ret = ioctl(dri_fd, DRM_IOCTL_MODE_CREATE_DUMB, &arg); if(ret) { perror("[*] DRM_IOCTL_MODE_CREATE_DUMB Failed"); exit(-1); } gem_close(arg.handle); while(1) { struct drm_mode_create_dumb args = {0}; args.width = args.height = 0x20; args.bpp = 32; ret = ioctl(dri_fd, DRM_IOCTL_MODE_CREATE_DUMB, &args); if (ret) { perror("[*] DRM_IOCTL_MODE_CREATE_DUMB Failed"); exit(-1); } printf("[*] DRM_IOCTL_MODE_CREATE_DUMB created, %d\n", args.handle); gem_close(args.handle); } return NULL; } void gem_close(int handle) { struct drm_gem_close args; args.handle = handle; int ret = ioctl(dri_fd, DRM_IOCTL_GEM_CLOSE, &args); // gem close handle if (!ret) printf("gem close handle %d\n", args.handle); } int main(void) { dri_fd= open("/dev/dri/card0", O_RDWR); printf("fd:%d\n", dri_fd); if(dri_fd == -1) return -1; pthread_t tid1; if(pthread_create(&tid1,NULL,trigger,NULL)){ perror("[*] thread_create tid1\n"); return -1; } while (1) { gem_close(arg.handle); } return 0; } This is a KASAN report: ================================================================== BUG: KASAN: slab-use-after-free in qxl_mode_dumb_create+0x3c2/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:69 Write of size 1 at addr ffff88801136c240 by task poc/515 CPU: 1 PID: 515 Comm: poc Not tainted 6.3.0 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-debian-1.16.0-4 04/01/2014 Call Trace: __dump_stack linux/lib/dump_stack.c:88 dump_stack_lvl+0x48/0x70 linux/lib/dump_stack.c:106 print_address_description linux/mm/kasan/report.c:319 print_report+0xd2/0x660 linux/mm/kasan/report.c:430 kasan_report+0xd2/0x110 linux/mm/kasan/report.c:536 __asan_report_store1_noabort+0x17/0x30 linux/mm/kasan/report_generic.c:383 qxl_mode_dumb_create+0x3c2/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:69 drm_mode_create_dumb linux/drivers/gpu/drm/drm_dumb_buffers.c:96 drm_mode_create_dumb_ioctl+0x1f5/0x2d0 linux/drivers/gpu/drm/drm_dumb_buffers.c:102 drm_ioctl_kernel+0x21d/0x430 linux/drivers/gpu/drm/drm_ioctl.c:788 drm_ioctl+0x56f/0xcc0 linux/drivers/gpu/drm/drm_ioctl.c:891 vfs_ioctl linux/fs/ioctl.c:51 __do_sys_ioctl linux/fs/ioctl.c:870 __se_sys_ioctl linux/fs/ioctl.c:856 __x64_sys_ioctl+0x13d/0x1c0 linux/fs/ioctl.c:856 do_syscall_x64 linux/arch/x86/entry/common.c:50 do_syscall_64+0x5b/0x90 linux/arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc linux/arch/x86/entry/entry_64.S:120 RIP: 0033:0x7ff5004ff5f7 Code: 00 00 00 48 8b 05 99 c8 0d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 69 c8 0d 00 f7 d8 64 89 01 48 RSP: 002b:00007ff500408ea8 EFLAGS: 00000286 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ff5004ff5f7 RDX: 00007ff500408ec0 RSI: 00000000c02064b2 RDI: 0000000000000003 RBP: 00007ff500408ef0 R08: 0000000000000000 R09: 000000000000002a R10: 0000000000000000 R11: 0000000000000286 R12: 00007fff1c6cdafe R13: 00007fff1c6cdaff R14: 00007ff500408fc0 R15: 0000000000802000 Allocated by task 515: kasan_save_stack+0x38/0x70 linux/mm/kasan/common.c:45 kasan_set_track+0x25/0x40 linux/mm/kasan/common.c:52 kasan_save_alloc_info+0x1e/0x40 linux/mm/kasan/generic.c:510 ____kasan_kmalloc linux/mm/kasan/common.c:374 __kasan_kmalloc+0xc3/0xd0 linux/mm/kasan/common.c:383 kasan_kmalloc linux/./include/linux/kasan.h:196 kmalloc_trace+0x48/0xc0 linux/mm/slab_common.c:1066 kmalloc linux/./include/linux/slab.h:580 kzalloc linux/./include/linux/slab.h:720 qxl_bo_create+0x11a/0x610 linux/drivers/gpu/drm/qxl/qxl_object.c:124 qxl_gem_object_create+0xd9/0x360 linux/drivers/gpu/drm/qxl/qxl_gem.c:58 qxl_gem_object_create_with_handle+0xa1/0x180 linux/drivers/gpu/drm/qxl/qxl_gem.c:89 qxl_mode_dumb_create+0x1cd/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:63 drm_mode_create_dumb linux/drivers/gpu/drm/drm_dumb_buffers.c:96 drm_mode_create_dumb_ioctl+0x1f5/0x2d0 linux/drivers/gpu/drm/drm_dumb_buffers.c:102 drm_ioctl_kernel+0x21d/0x430 linux/drivers/gpu/drm/drm_ioctl.c:788 drm_ioctl+0x56f/0xcc0 linux/drivers/gpu/drm/drm_ioctl.c:891 vfs_ioctl linux/fs/ioctl.c:51 __do_sys_ioctl linux/fs/ioctl.c:870 __se_sys_ioctl linux/fs/ioctl.c:856 __x64_sys_ioctl+0x13d/0x1c0 linux/fs/ioctl.c:856 do_syscall_x64 linux/arch/x86/entry/common.c:50 do_syscall_64+0x5b/0x90 linux/arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc linux/arch/x86/entry/entry_64.S:120 Freed by task 515: kasan_save_stack+0x38/0x70 linux/mm/kasan/common.c:45 kasan_set_track+0x25/0x40 linux/mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x60 linux/mm/kasan/generic.c:521 ____kasan_slab_free linux/mm/kasan/common.c:236 ____kasan_slab_free+0x180/0x1f0 linux/mm/kasan/common.c:200 __kasan_slab_free+0x12/0x30 linux/mm/kasan/common.c:244 kasan_slab_free linux/./include/linux/kasan.h:162 slab_free_hook linux/mm/slub.c:1781 slab_free_freelist_hook+0xd2/0x1a0 linux/mm/slub.c:1807 slab_free linux/mm/slub.c:3787 __kmem_cache_free+0x196/0x2d0 linux/mm/slub.c:3800 kfree+0x78/0x120 linux/mm/slab_common.c:1019 qxl_ttm_bo_destroy+0x140/0x1a0 linux/drivers/gpu/drm/qxl/qxl_object.c:49 ttm_bo_release+0x678/0xa30 linux/drivers/gpu/drm/ttm/ttm_bo.c:381 kref_put linux/./include/linux/kref.h:65 ttm_bo_put+0x50/0x80 linux/drivers/gpu/drm/ttm/ttm_bo.c:393 qxl_gem_object_free+0x3e/0x60 linux/drivers/gpu/drm/qxl/qxl_gem.c:42 drm_gem_object_free+0x5c/0x90 linux/drivers/gpu/drm/drm_gem.c:974 kref_put linux/./include/linux/kref.h:65 __drm_gem_object_put linux/./include/drm/drm_gem.h:431 drm_gem_object_put linux/./include/drm/drm_gem.h:444 qxl_gem_object_create_with_handle+0x151/0x180 linux/drivers/gpu/drm/qxl/qxl_gem.c:100 qxl_mode_dumb_create+0x1cd/0x400 linux/drivers/gpu/drm/qxl/qxl_dumb.c:63 drm_mode_create_dumb linux/drivers/gpu/drm/drm_dumb_buffers.c:96 drm_mode_create_dumb_ioctl+0x1f5/0x2d0 linux/drivers/gpu/drm/drm_dumb_buffers.c:102 drm_ioctl_kernel+0x21d/0x430 linux/drivers/gpu/drm/drm_ioctl.c:788 drm_ioctl+0x56f/0xcc0 linux/drivers/gpu/drm/drm_ioctl.c:891 vfs_ioctl linux/fs/ioctl.c:51 __do_sys_ioctl linux/fs/ioctl.c:870 __se_sys_ioctl linux/fs/ioctl.c:856 __x64_sys_ioctl+0x13d/0x1c0 linux/fs/ioctl.c:856 do_syscall_x64 linux/arch/x86/entry/common.c:50 do_syscall_64+0x5b/0x90 linux/arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc linux/arch/x86/entry/entry_64.S:120 The buggy address belongs to the object at ffff88801136c000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 576 bytes inside of freed 1024-byte region [ffff88801136c000, ffff88801136c400) The buggy address belongs to the physical page: page:0000000089fc329b refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11368 head:0000000089fc329b order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0010200 ffff888007841dc0 dead000000000122 0000000000000000 raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88801136c100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88801136c180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88801136c200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88801136c280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88801136c300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint Instead of returning a weak reference to the qxl_bo object, return the created drm_gem_object and let the caller decrement the reference count when it no longer needs it. As a convenience, if the caller is not interested in the gobj object, it can pass NULL to the parameter and the reference counting is descremented internally. The bug and the reproducer were originally found by the Zero Day Initiative project (ZDI-CAN-20940). Link: https://www.zerodayinitiative.com/ Signed-off-by: Wander Lairson Costa Cc: stable@vger.kernel.org Reviewed-by: Dave Airlie Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20230814165119.90847-1-wander@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/qxl/qxl_drv.h | 2 +- drivers/gpu/drm/qxl/qxl_dumb.c | 5 ++++- drivers/gpu/drm/qxl/qxl_gem.c | 25 +++++++++++++++++-------- drivers/gpu/drm/qxl/qxl_ioctl.c | 6 ++---- 4 files changed, 24 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 432758ad39a3..94753e017ea8 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -312,7 +312,7 @@ int qxl_gem_object_create_with_handle(struct qxl_device *qdev, u32 domain, size_t size, struct qxl_surface *surf, - struct qxl_bo **qobj, + struct drm_gem_object **gobj, uint32_t *handle); void qxl_gem_object_free(struct drm_gem_object *gobj); int qxl_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv); diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c index d636ba685451..17df5c7ccf69 100644 --- a/drivers/gpu/drm/qxl/qxl_dumb.c +++ b/drivers/gpu/drm/qxl/qxl_dumb.c @@ -34,6 +34,7 @@ int qxl_mode_dumb_create(struct drm_file *file_priv, { struct qxl_device *qdev = to_qxl(dev); struct qxl_bo *qobj; + struct drm_gem_object *gobj; uint32_t handle; int r; struct qxl_surface surf; @@ -62,11 +63,13 @@ int qxl_mode_dumb_create(struct drm_file *file_priv, r = qxl_gem_object_create_with_handle(qdev, file_priv, QXL_GEM_DOMAIN_CPU, - args->size, &surf, &qobj, + args->size, &surf, &gobj, &handle); if (r) return r; + qobj = gem_to_qxl_bo(gobj); qobj->is_dumb = true; + drm_gem_object_put(gobj); args->pitch = pitch; args->handle = handle; return 0; diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c index a08da0bd9098..fc5e3763c359 100644 --- a/drivers/gpu/drm/qxl/qxl_gem.c +++ b/drivers/gpu/drm/qxl/qxl_gem.c @@ -72,32 +72,41 @@ int qxl_gem_object_create(struct qxl_device *qdev, int size, return 0; } +/* + * If the caller passed a valid gobj pointer, it is responsible to call + * drm_gem_object_put() when it no longer needs to acess the object. + * + * If gobj is NULL, it is handled internally. + */ int qxl_gem_object_create_with_handle(struct qxl_device *qdev, struct drm_file *file_priv, u32 domain, size_t size, struct qxl_surface *surf, - struct qxl_bo **qobj, + struct drm_gem_object **gobj, uint32_t *handle) { - struct drm_gem_object *gobj; int r; + struct drm_gem_object *local_gobj; - BUG_ON(!qobj); BUG_ON(!handle); r = qxl_gem_object_create(qdev, size, 0, domain, false, false, surf, - &gobj); + &local_gobj); if (r) return -ENOMEM; - r = drm_gem_handle_create(file_priv, gobj, handle); + r = drm_gem_handle_create(file_priv, local_gobj, handle); if (r) return r; - /* drop reference from allocate - handle holds it now */ - *qobj = gem_to_qxl_bo(gobj); - drm_gem_object_put(gobj); + + if (gobj) + *gobj = local_gobj; + else + /* drop reference from allocate - handle holds it now */ + drm_gem_object_put(local_gobj); + return 0; } diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 30f58b21372a..dd0f834d881c 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -38,7 +38,6 @@ int qxl_alloc_ioctl(struct drm_device *dev, void *data, struct drm_file *file_pr struct qxl_device *qdev = to_qxl(dev); struct drm_qxl_alloc *qxl_alloc = data; int ret; - struct qxl_bo *qobj; uint32_t handle; u32 domain = QXL_GEM_DOMAIN_VRAM; @@ -50,7 +49,7 @@ int qxl_alloc_ioctl(struct drm_device *dev, void *data, struct drm_file *file_pr domain, qxl_alloc->size, NULL, - &qobj, &handle); + NULL, &handle); if (ret) { DRM_ERROR("%s: failed to create gem ret=%d\n", __func__, ret); @@ -386,7 +385,6 @@ int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data, struct drm_file *fi { struct qxl_device *qdev = to_qxl(dev); struct drm_qxl_alloc_surf *param = data; - struct qxl_bo *qobj; int handle; int ret; int size, actual_stride; @@ -406,7 +404,7 @@ int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data, struct drm_file *fi QXL_GEM_DOMAIN_SURFACE, size, &surf, - &qobj, &handle); + NULL, &handle); if (ret) { DRM_ERROR("%s: failed to create gem ret=%d\n", __func__, ret); From df1566ce41ee6c477e82816c10fca3d0b4291de4 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 3 Aug 2023 15:27:06 +0300 Subject: [PATCH 0479/2093] drm/i915/sdvo: fix panel_type initialization MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2002eb6d3ea954dde9f8a223018d5335779937d0 upstream. Commit 3f9ffce5765d ("drm/i915: Do panel VBT init early if the VBT declares an explicit panel type") started using -1 as the value for unset panel_type. It gets initialized in intel_panel_init_alloc(), but the SDVO code never calls it. Call intel_panel_init_alloc() to initialize the panel, including the panel_type. Reported-by: Tomi Leppänen Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8896 Fixes: 3f9ffce5765d ("drm/i915: Do panel VBT init early if the VBT declares an explicit panel type") Cc: Ville Syrjälä Cc: # v6.1+ Reviewed-by: Uma Shankar Tested-by: Tomi Leppänen Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20230803122706.838721-1-jani.nikula@intel.com (cherry picked from commit 26e60294e8eacedc8ebb33405b2c375fd80e0900) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_sdvo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index a15e09b55170..2c2e0f041f86 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2727,7 +2727,7 @@ static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void) __drm_atomic_helper_connector_reset(&sdvo_connector->base.base, &conn_state->base.base); - INIT_LIST_HEAD(&sdvo_connector->base.panel.fixed_modes); + intel_panel_init_alloc(&sdvo_connector->base); return sdvo_connector; } From e1cbd5637f37e7facfd38d19cda4a36a85780613 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 18 May 2023 11:52:51 -0500 Subject: [PATCH 0480/2093] drm/amd: flush any delayed gfxoff on suspend entry commit a7b7d9e8aee4f71b4c7151702fd74237b8cef989 upstream. DCN 3.1.4 is reported to hang on s2idle entry if graphics activity is happening during entry. This is because GFXOFF was scheduled as delayed but RLC gets disabled in s2idle entry sequence which will hang GFX IP if not already in GFXOFF. To help this problem, flush any delayed work for GFXOFF early in s2idle entry sequence to ensure that it's off when RLC is changed. commit 4b31b92b143f ("drm/amdgpu: complete gfxoff allow signal during suspend without delay") modified power gating flow so that if called in s0ix that it ensured that GFXOFF wasn't put in work queue but instead processed immediately. This is dead code due to commit 10cb67eb8a1b ("drm/amdgpu: skip CG/PG for gfx during S0ix") because GFXOFF will now not be explicitly called as part of the suspend entry code. Remove that dead code. Signed-off-by: Mario Limonciello Signed-off-by: Tim Huang Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 9 +-------- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 773383e660e8..e6427a00cf6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4232,6 +4232,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true); cancel_delayed_work_sync(&adev->delayed_init_work); + flush_delayed_work(&adev->gfx.gfx_off_delay_work); amdgpu_ras_suspend(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index b803e785d3af..23f0067f92e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -585,15 +585,8 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) { - /* If going to s2idle, no need to wait */ - if (adev->in_s0ix) { - if (!amdgpu_dpm_set_powergating_by_smu(adev, - AMD_IP_BLOCK_TYPE_GFX, true)) - adev->gfx.gfx_off_state = true; - } else { - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, delay); - } } } else { if (adev->gfx.gfx_off_req_count == 0) { From 9c8c2cf9f9bce4fa4c4c4e821bdaa4e15762e403 Mon Sep 17 00:00:00 2001 From: Tim Huang Date: Mon, 14 Aug 2023 15:13:04 +0800 Subject: [PATCH 0481/2093] drm/amdgpu: skip fence GFX interrupts disable/enable for S0ix commit f1740b1ab2703b2a057da7cf33b03297e0381aa0 upstream. GFX v11.0.1 reported fence fallback timer expired issue on SDMA and GFX rings after S0ix resume. This is generated by EOP interrupts are disabled when S0ix suspend but fails to re-enable when resume because of the GFX is in GFXOFF. [ 203.349571] [drm] Fence fallback timer expired on ring sdma0 [ 203.349572] [drm] Fence fallback timer expired on ring gfx_0.0.0 [ 203.861635] [drm] Fence fallback timer expired on ring gfx_0.0.0 For S0ix, GFX is in GFXOFF state, avoid to touch the GFX registers to configure the fence driver interrupts for rings that belong to GFX. The interrupts configuration will be restored by GFXOFF exit. Signed-off-by: Tim Huang Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 41 +++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index ed6878d5b3ce..418e4c77ceb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -501,6 +501,41 @@ int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev) return 0; } +/** + * amdgpu_fence_need_ring_interrupt_restore - helper function to check whether + * fence driver interrupts need to be restored. + * + * @ring: ring that to be checked + * + * Interrupts for rings that belong to GFX IP don't need to be restored + * when the target power state is s0ix. + * + * Return true if need to restore interrupts, false otherwise. + */ +static bool amdgpu_fence_need_ring_interrupt_restore(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + bool is_gfx_power_domain = false; + + switch (ring->funcs->type) { + case AMDGPU_RING_TYPE_SDMA: + /* SDMA 5.x+ is part of GFX power domain so it's covered by GFXOFF */ + if (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(5, 0, 0)) + is_gfx_power_domain = true; + break; + case AMDGPU_RING_TYPE_GFX: + case AMDGPU_RING_TYPE_COMPUTE: + case AMDGPU_RING_TYPE_KIQ: + case AMDGPU_RING_TYPE_MES: + is_gfx_power_domain = true; + break; + default: + break; + } + + return !(adev->in_s0ix && is_gfx_power_domain); +} + /** * amdgpu_fence_driver_hw_fini - tear down the fence driver * for all possible rings. @@ -529,7 +564,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) amdgpu_fence_driver_force_completion(ring); if (!drm_dev_is_unplugged(adev_to_drm(adev)) && - ring->fence_drv.irq_src) + ring->fence_drv.irq_src && + amdgpu_fence_need_ring_interrupt_restore(ring)) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); @@ -604,7 +640,8 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev) continue; /* enable the interrupt */ - if (ring->fence_drv.irq_src) + if (ring->fence_drv.irq_src && + amdgpu_fence_need_ring_interrupt_restore(ring)) amdgpu_irq_get(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); } From 7de99bf5bcd6d04b2202dd908782cc05edca0340 Mon Sep 17 00:00:00 2001 From: Umio Yasuno Date: Tue, 8 Aug 2023 06:40:42 +0000 Subject: [PATCH 0482/2093] drm/amdgpu/pm: fix throttle_status for other than MP1 11.0.7 commit 6a92761a86817ad15c9a562e2a809386237fae3e upstream. Use the right metrics table version based on the firmware. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2720 Reviewed-by: Evan Quan Signed-off-by: Umio Yasuno Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- .../drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 31835d96deef..839a812e0da3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -588,7 +588,9 @@ static int sienna_cichlid_tables_init(struct smu_context *smu) return -ENOMEM; } -static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu) +static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *smu, + bool use_metrics_v3, + bool use_metrics_v2) { struct smu_table_context *smu_table= &smu->smu_table; SmuMetricsExternal_t *metrics_ext = @@ -596,13 +598,11 @@ static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *s uint32_t throttler_status = 0; int i; - if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && - (smu->smc_fw_version >= 0x3A4900)) { + if (use_metrics_v3) { for (i = 0; i < THROTTLER_COUNT; i++) throttler_status |= (metrics_ext->SmuMetrics_V3.ThrottlingPercentage[i] ? 1U << i : 0); - } else if ((smu->adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 7)) && - (smu->smc_fw_version >= 0x3A4300)) { + } else if (use_metrics_v2) { for (i = 0; i < THROTTLER_COUNT; i++) throttler_status |= (metrics_ext->SmuMetrics_V2.ThrottlingPercentage[i] ? 1U << i : 0); @@ -864,7 +864,7 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, metrics->TemperatureVrSoc) * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_THROTTLER_STATUS: - *value = sienna_cichlid_get_throttler_status_locked(smu); + *value = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2); break; case METRICS_CURR_FANSPEED: *value = use_metrics_v3 ? metrics_v3->CurrFanSpeed : @@ -4017,7 +4017,7 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk1 = use_metrics_v3 ? metrics_v3->CurrClock[PPCLK_DCLK_1] : use_metrics_v2 ? metrics_v2->CurrClock[PPCLK_DCLK_1] : metrics->CurrClock[PPCLK_DCLK_1]; - gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu); + gpu_metrics->throttle_status = sienna_cichlid_get_throttler_status_locked(smu, use_metrics_v3, use_metrics_v2); gpu_metrics->indep_throttle_status = smu_cmn_get_indep_throttler_status(gpu_metrics->throttle_status, sienna_cichlid_throttler_map); From b2f599c014f3aabc76c185f42e39de64b86deede Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Jun 2023 14:44:39 +0200 Subject: [PATCH 0483/2093] ASoC: amd: vangogh: select CONFIG_SND_AMD_ACP_CONFIG commit 812a05256d673b2b9c5db906775d1e6625ba4787 upstream. The vangogh driver just gained a link time dependency that now causes randconfig builds to fail: x86_64-linux-ld: sound/soc/amd/vangogh/pci-acp5x.o: in function `snd_acp5x_probe': pci-acp5x.c:(.text+0xbb): undefined reference to `snd_amd_acp_find_config' Fixes: e89f45edb747e ("ASoC: amd: vangogh: Add check for acp config flags in vangogh platform") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230602124447.863476-1-arnd@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/amd/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig index c88ebd84bdd5..3968c478c938 100644 --- a/sound/soc/amd/Kconfig +++ b/sound/soc/amd/Kconfig @@ -81,6 +81,7 @@ config SND_SOC_AMD_VANGOGH_MACH tristate "AMD Vangogh support for NAU8821 CS35L41" select SND_SOC_NAU8821 select SND_SOC_CS35L41_SPI + select SND_AMD_ACP_CONFIG depends on SND_SOC_AMD_ACP5x && I2C && SPI_MASTER help This option enables machine driver for Vangogh platform From d4008eadfce5d7791bf078f5e51ba5b735fd8c09 Mon Sep 17 00:00:00 2001 From: Daniel Miess Date: Wed, 7 Jun 2023 11:11:44 -0400 Subject: [PATCH 0484/2093] drm/amd/display: disable RCO for DCN314 commit 85e41f1ed5d94a26fe4e57003c399936d291ed70 upstream. [Why] RCO is causing error messages on some DCN314 systems [How] Force disable RCO for DCN314 Fixes: 17fbdbda9cc8 ("drm/amd/display: Enable dcn314 DPP RCO") Reviewed-by: Nicholas Kazlauskas Acked-by: Hamza Mahfooz Signed-off-by: Daniel Miess Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 97c6a79dfba6..b74705c1c8dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -296,7 +296,7 @@ static void dccg314_dpp_root_clock_control( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (dccg->dpp_clock_gated[dpp_inst] == clock_on) + if (dccg->dpp_clock_gated[dpp_inst] != clock_on) return; if (clock_on) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 012f6369dae2..503ab45b4ace 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -1933,6 +1933,10 @@ static bool dcn314_resource_construct( dc->debug = debug_defaults_drv; else dc->debug = debug_defaults_diags; + + /* Disable root clock optimization */ + dc->debug.root_clock_optimization.u32All = 0; + // Init the vm_helper if (dc->vm_helper) vm_helper_init(dc->vm_helper, 16); From 5274bf1f743f604a4e994f0ce1879575b9848aa7 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Tue, 18 Apr 2023 16:46:39 +0900 Subject: [PATCH 0485/2093] zsmalloc: allow only one active pool compaction context commit d2658f2052c7db6ec0a79977205f8cf1cb9effc2 upstream. zsmalloc pool can be compacted concurrently by many contexts, e.g. cc1 handle_mm_fault() do_anonymous_page() __alloc_pages_slowpath() try_to_free_pages() do_try_to_free_pages( lru_gen_shrink_node() shrink_slab() do_shrink_slab() zs_shrinker_scan() zs_compact() Pool compaction is currently (basically) single-threaded as it is performed under pool->lock. Having multiple compaction threads results in unnecessary contention, as each thread competes for pool->lock. This, in turn, affects all zsmalloc operations such as zs_malloc(), zs_map_object(), zs_free(), etc. Introduce the pool->compaction_in_progress atomic variable, which ensures that only one compaction context can run at a time. This reduces overall pool->lock contention in (corner) cases when many contexts attempt to shrink zspool simultaneously. Link: https://lkml.kernel.org/r/20230418074639.1903197-1-senozhatsky@chromium.org Fixes: c0547d0b6a4b ("zsmalloc: consolidate zs_pool's migrate_lock and size_class's locks") Signed-off-by: Sergey Senozhatsky Reviewed-by: Yosry Ahmed Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/zsmalloc.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 2f5e6d35b03b..37f755c9a1b7 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -246,6 +246,7 @@ struct zs_pool { struct work_struct free_work; #endif spinlock_t lock; + atomic_t compaction_in_progress; }; struct zspage { @@ -2100,6 +2101,15 @@ unsigned long zs_compact(struct zs_pool *pool) struct size_class *class; unsigned long pages_freed = 0; + /* + * Pool compaction is performed under pool->lock so it is basically + * single-threaded. Having more than one thread in __zs_compact() + * will increase pool->lock contention, which will impact other + * zsmalloc operations that need pool->lock. + */ + if (atomic_xchg(&pool->compaction_in_progress, 1)) + return 0; + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; if (class->index != i) @@ -2107,6 +2117,7 @@ unsigned long zs_compact(struct zs_pool *pool) pages_freed += __zs_compact(pool, class); } atomic_long_add(pages_freed, &pool->stats.pages_compacted); + atomic_set(&pool->compaction_in_progress, 0); return pages_freed; } @@ -2193,6 +2204,7 @@ struct zs_pool *zs_create_pool(const char *name) init_deferred_free(pool); spin_lock_init(&pool->lock); + atomic_set(&pool->compaction_in_progress, 0); pool->name = kstrdup(name, GFP_KERNEL); if (!pool->name) From e8acf9971fbe52b7e22d458edb843649d6206565 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 1 Feb 2023 15:36:27 +0100 Subject: [PATCH 0486/2093] sched/fair: unlink misfit task from cpu overutilized commit e5ed0550c04c5469ecdc1634d8aa18c8609590f0 upstream. By taking into account uclamp_min, the 1:1 relation between task misfit and cpu overutilized is no more true as a task with a small util_avg may not fit a high capacity cpu because of uclamp_min constraint. Add a new state in util_fits_cpu() to reflect the case that task would fit a CPU except for the uclamp_min hint which is a performance requirement. Use -1 to reflect that a CPU doesn't fit only because of uclamp_min so we can use this new value to take additional action to select the best CPU that doesn't match uclamp_min hint. When util_fits_cpu() returns -1, we will continue to look for a possible CPU with better performance, which replaces Capacity Inversion detection with capacity_orig_of() - thermal_load_avg to detect a capacity inversion. Signed-off-by: Vincent Guittot Reviewed-and-tested-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Tested-by: Kajetan Puchalski Link: https://lore.kernel.org/r/20230201143628.270912-2-vincent.guittot@linaro.org Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 109 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 84 insertions(+), 25 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5e5aea2360a8..a45ccee98ab1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4549,8 +4549,8 @@ static inline int util_fits_cpu(unsigned long util, * handle the case uclamp_min > uclamp_max. */ uclamp_min = min(uclamp_min, uclamp_max); - if (util < uclamp_min && capacity_orig != SCHED_CAPACITY_SCALE) - fits = fits && (uclamp_min <= capacity_orig_thermal); + if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal)) + return -1; return fits; } @@ -4560,7 +4560,11 @@ static inline int task_fits_cpu(struct task_struct *p, int cpu) unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN); unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX); unsigned long util = task_util_est(p); - return util_fits_cpu(util, uclamp_min, uclamp_max, cpu); + /* + * Return true only if the cpu fully fits the task requirements, which + * include the utilization but also the performance hints. + */ + return (util_fits_cpu(util, uclamp_min, uclamp_max, cpu) > 0); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -6043,6 +6047,7 @@ static inline bool cpu_overutilized(int cpu) unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + /* Return true only if the utilization doesn't fit CPU's capacity */ return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu); } @@ -6836,6 +6841,7 @@ static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { unsigned long task_util, util_min, util_max, best_cap = 0; + int fits, best_fits = 0; int cpu, best_cpu = -1; struct cpumask *cpus; @@ -6851,12 +6857,28 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (util_fits_cpu(task_util, util_min, util_max, cpu)) - return cpu; - if (cpu_cap > best_cap) { + fits = util_fits_cpu(task_util, util_min, util_max, cpu); + + /* This CPU fits with all requirements */ + if (fits > 0) + return cpu; + /* + * Only the min performance hint (i.e. uclamp_min) doesn't fit. + * Look for the CPU with best capacity. + */ + else if (fits < 0) + cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu)); + + /* + * First, select CPU which fits better (-1 being better than 0). + * Then, select the one with best capacity at same level. + */ + if ((fits < best_fits) || + ((fits == best_fits) && (cpu_cap > best_cap))) { best_cap = cpu_cap; best_cpu = cpu; + best_fits = fits; } } @@ -6869,7 +6891,11 @@ static inline bool asym_fits_cpu(unsigned long util, int cpu) { if (sched_asym_cpucap_active()) - return util_fits_cpu(util, util_min, util_max, cpu); + /* + * Return true only if the cpu fully fits the task requirements + * which include the utilization and the performance hints. + */ + return (util_fits_cpu(util, util_min, util_max, cpu) > 0); return true; } @@ -7236,6 +7262,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024; struct root_domain *rd = this_rq()->rd; int cpu, best_energy_cpu, target = -1; + int prev_fits = -1, best_fits = -1; + unsigned long best_thermal_cap = 0; + unsigned long prev_thermal_cap = 0; struct sched_domain *sd; struct perf_domain *pd; struct energy_env eenv; @@ -7271,6 +7300,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) unsigned long prev_spare_cap = 0; int max_spare_cap_cpu = -1; unsigned long base_energy; + int fits, max_fits = -1; cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); @@ -7320,7 +7350,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util_min = max(rq_util_min, p_util_min); util_max = max(rq_util_max, p_util_max); } - if (!util_fits_cpu(util, util_min, util_max, cpu)) + + fits = util_fits_cpu(util, util_min, util_max, cpu); + if (!fits) continue; lsub_positive(&cpu_cap, util); @@ -7328,7 +7360,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (cpu == prev_cpu) { /* Always use prev_cpu as a candidate. */ prev_spare_cap = cpu_cap; - } else if (cpu_cap > max_spare_cap) { + prev_fits = fits; + } else if ((fits > max_fits) || + ((fits == max_fits) && (cpu_cap > max_spare_cap))) { /* * Find the CPU with the maximum spare capacity * among the remaining CPUs in the performance @@ -7336,6 +7370,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) */ max_spare_cap = cpu_cap; max_spare_cap_cpu = cpu; + max_fits = fits; } } @@ -7354,26 +7389,50 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (prev_delta < base_energy) goto unlock; prev_delta -= base_energy; + prev_thermal_cap = cpu_thermal_cap; best_delta = min(best_delta, prev_delta); } /* Evaluate the energy impact of using max_spare_cap_cpu. */ if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) { + /* Current best energy cpu fits better */ + if (max_fits < best_fits) + continue; + + /* + * Both don't fit performance hint (i.e. uclamp_min) + * but best energy cpu has better capacity. + */ + if ((max_fits < 0) && + (cpu_thermal_cap <= best_thermal_cap)) + continue; + cur_delta = compute_energy(&eenv, pd, cpus, p, max_spare_cap_cpu); /* CPU utilization has changed */ if (cur_delta < base_energy) goto unlock; cur_delta -= base_energy; - if (cur_delta < best_delta) { - best_delta = cur_delta; - best_energy_cpu = max_spare_cap_cpu; - } + + /* + * Both fit for the task but best energy cpu has lower + * energy impact. + */ + if ((max_fits > 0) && (best_fits > 0) && + (cur_delta >= best_delta)) + continue; + + best_delta = cur_delta; + best_energy_cpu = max_spare_cap_cpu; + best_fits = max_fits; + best_thermal_cap = cpu_thermal_cap; } } rcu_read_unlock(); - if (best_delta < prev_delta) + if ((best_fits > prev_fits) || + ((best_fits > 0) && (best_delta < prev_delta)) || + ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap))) target = best_energy_cpu; return target; @@ -10183,6 +10242,16 @@ static struct sched_group *find_busiest_group(struct lb_env *env) */ update_sd_lb_stats(env, &sds); + /* There is no busy sibling group to pull tasks from */ + if (!sds.busiest) + goto out_balanced; + + busiest = &sds.busiest_stat; + + /* Misfit tasks should be dealt with regardless of the avg load */ + if (busiest->group_type == group_misfit_task) + goto force_balance; + if (sched_energy_enabled()) { struct root_domain *rd = env->dst_rq->rd; @@ -10190,17 +10259,6 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto out_balanced; } - local = &sds.local_stat; - busiest = &sds.busiest_stat; - - /* There is no busy sibling group to pull tasks from */ - if (!sds.busiest) - goto out_balanced; - - /* Misfit tasks should be dealt with regardless of the avg load */ - if (busiest->group_type == group_misfit_task) - goto force_balance; - /* ASYM feature bypasses nice load balance check */ if (busiest->group_type == group_asym_packing) goto force_balance; @@ -10213,6 +10271,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (busiest->group_type == group_imbalanced) goto force_balance; + local = &sds.local_stat; /* * If the local group is busier than the selected busiest group * don't try and pull any tasks. From 8517d739923e054d774d6004e1c60e9793588502 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 1 Feb 2023 15:36:28 +0100 Subject: [PATCH 0487/2093] sched/fair: Remove capacity inversion detection commit a2e90611b9f425adbbfcdaa5b5e49958ddf6f61b upstream. Remove the capacity inversion detection which is now handled by util_fits_cpu() returning -1 when we need to continue to look for a potential CPU with better performance. This ends up almost reverting patches below except for some comments: commit da07d2f9c153 ("sched/fair: Fixes for capacity inversion detection") commit aa69c36f31aa ("sched/fair: Consider capacity inversion in util_fits_cpu()") commit 44c7b80bffc3 ("sched/fair: Detect capacity inversion") Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230201143628.270912-3-vincent.guittot@linaro.org Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 84 +++----------------------------------------- kernel/sched/sched.h | 19 ---------- 2 files changed, 5 insertions(+), 98 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a45ccee98ab1..612873ec2197 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4464,17 +4464,9 @@ static inline int util_fits_cpu(unsigned long util, * * For uclamp_max, we can tolerate a drop in performance level as the * goal is to cap the task. So it's okay if it's getting less. - * - * In case of capacity inversion we should honour the inverted capacity - * for both uclamp_min and uclamp_max all the time. */ - capacity_orig = cpu_in_capacity_inversion(cpu); - if (capacity_orig) { - capacity_orig_thermal = capacity_orig; - } else { - capacity_orig = capacity_orig_of(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); - } + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); /* * We want to force a task to fit a cpu as implied by uclamp_max. @@ -8929,82 +8921,16 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity_orig = arch_scale_cpu_capacity(cpu); unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - struct rq *rq = cpu_rq(cpu); - rq->cpu_capacity_orig = capacity_orig; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); if (!capacity) capacity = 1; - rq->cpu_capacity = capacity; - - /* - * Detect if the performance domain is in capacity inversion state. - * - * Capacity inversion happens when another perf domain with equal or - * lower capacity_orig_of() ends up having higher capacity than this - * domain after subtracting thermal pressure. - * - * We only take into account thermal pressure in this detection as it's - * the only metric that actually results in *real* reduction of - * capacity due to performance points (OPPs) being dropped/become - * unreachable due to thermal throttling. - * - * We assume: - * * That all cpus in a perf domain have the same capacity_orig - * (same uArch). - * * Thermal pressure will impact all cpus in this perf domain - * equally. - */ - if (sched_energy_enabled()) { - unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd; - - rcu_read_lock(); - - pd = rcu_dereference(rq->rd->pd); - rq->cpu_capacity_inverted = 0; - - for (; pd; pd = pd->next) { - struct cpumask *pd_span = perf_domain_span(pd); - unsigned long pd_cap_orig, pd_cap; - - /* We can't be inverted against our own pd */ - if (cpumask_test_cpu(cpu_of(rq), pd_span)) - continue; - - cpu = cpumask_any(pd_span); - pd_cap_orig = arch_scale_cpu_capacity(cpu); - - if (capacity_orig < pd_cap_orig) - continue; - - /* - * handle the case of multiple perf domains have the - * same capacity_orig but one of them is under higher - * thermal pressure. We record it as capacity - * inversion. - */ - if (capacity_orig == pd_cap_orig) { - pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu)); - - if (pd_cap > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } else if (pd_cap_orig > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } - - rcu_read_unlock(); - } - - trace_sched_cpu_capacity_tp(rq); + cpu_rq(cpu)->cpu_capacity = capacity; + trace_sched_cpu_capacity_tp(cpu_rq(cpu)); sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5f18460f62f0..d6d488e8eb55 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1041,7 +1041,6 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; - unsigned long cpu_capacity_inverted; struct balance_callback *balance_callback; @@ -2879,24 +2878,6 @@ static inline unsigned long capacity_orig_of(int cpu) return cpu_rq(cpu)->cpu_capacity_orig; } -/* - * Returns inverted capacity if the CPU is in capacity inversion state. - * 0 otherwise. - * - * Capacity inversion detection only considers thermal impact where actual - * performance points (OPPs) gets dropped. - * - * Capacity inversion state happens when another performance domain that has - * equal or lower capacity_orig_of() becomes effectively larger than the perf - * domain this CPU belongs to due to thermal pressure throttling it hard. - * - * See comment in update_cpu_capacity(). - */ -static inline unsigned long cpu_in_capacity_inversion(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity_inverted; -} - /** * enum cpu_util_type - CPU utilization type * @FREQUENCY_UTIL: Utilization used to select frequency From 4bdfe20d85b32274234bbcd705d5547fd70a4ea1 Mon Sep 17 00:00:00 2001 From: Saaem Rizvi Date: Mon, 6 Mar 2023 15:10:13 -0500 Subject: [PATCH 0488/2093] drm/amd/display: Implement workaround for writing to OTG_PIXEL_RATE_DIV register commit 74fa4c81aadf418341f0d073c864ea7dca730a2e upstream. [Why and How] Current implementation requires FPGA builds to take a different code path from DCN32 to write to OTG_PIXEL_RATE_DIV. Now that we have a workaround to write to OTG_PIXEL_RATE_DIV register without blanking display on hotplug on DCN32, we can allow the code paths for FPGA to be exactly the same allowing for more consistent testing. Reviewed-by: Alvin Lee Acked-by: Qingqing Zhuo Signed-off-by: Saaem Rizvi Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: "Limonciello, Mario" Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h | 3 ++- .../gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c | 22 +++++++++++++++++++ .../gpu/drm/amd/display/dc/dcn32/dcn32_dccg.h | 3 ++- .../drm/amd/display/dc/dcn32/dcn32_hwseq.c | 2 +- .../drm/amd/display/dc/dcn32/dcn32_resource.h | 3 ++- 5 files changed, 29 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h index 915a20461c77..893c0809cd4e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h @@ -230,7 +230,8 @@ type DTBCLK_P2_SRC_SEL;\ type DTBCLK_P2_EN;\ type DTBCLK_P3_SRC_SEL;\ - type DTBCLK_P3_EN; + type DTBCLK_P3_EN;\ + type DENTIST_DISPCLK_CHG_DONE; struct dccg_shift { DCCG_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index 3fb4bcc34353..ffbb739d85b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -42,6 +42,20 @@ #define DC_LOGGER \ dccg->ctx->logger +/* This function is a workaround for writing to OTG_PIXEL_RATE_DIV + * without the probability of causing a DIG FIFO error. + */ +static void dccg32_wait_for_dentist_change_done( + struct dccg *dccg) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + + uint32_t dentist_dispclk_value = REG_READ(DENTIST_DISPCLK_CNTL); + + REG_WRITE(DENTIST_DISPCLK_CNTL, dentist_dispclk_value); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 2000); +} + static void dccg32_get_pixel_rate_div( struct dccg *dccg, uint32_t otg_inst, @@ -110,21 +124,29 @@ static void dccg32_set_pixel_rate_div( REG_UPDATE_2(OTG_PIXEL_RATE_DIV, OTG0_PIXEL_RATE_DIVK1, k1, OTG0_PIXEL_RATE_DIVK2, k2); + + dccg32_wait_for_dentist_change_done(dccg); break; case 1: REG_UPDATE_2(OTG_PIXEL_RATE_DIV, OTG1_PIXEL_RATE_DIVK1, k1, OTG1_PIXEL_RATE_DIVK2, k2); + + dccg32_wait_for_dentist_change_done(dccg); break; case 2: REG_UPDATE_2(OTG_PIXEL_RATE_DIV, OTG2_PIXEL_RATE_DIVK1, k1, OTG2_PIXEL_RATE_DIVK2, k2); + + dccg32_wait_for_dentist_change_done(dccg); break; case 3: REG_UPDATE_2(OTG_PIXEL_RATE_DIV, OTG3_PIXEL_RATE_DIVK1, k1, OTG3_PIXEL_RATE_DIVK2, k2); + + dccg32_wait_for_dentist_change_done(dccg); break; default: BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.h index 1c46fad0977b..fc3c9c650d43 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.h @@ -147,7 +147,8 @@ DCCG_SF(DTBCLK_P_CNTL, DTBCLK_P3_SRC_SEL, mask_sh),\ DCCG_SF(DTBCLK_P_CNTL, DTBCLK_P3_EN, mask_sh),\ DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO_SEL, mask_sh),\ - DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL, mask_sh) + DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL, mask_sh),\ + DCCG_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh) struct dccg *dccg32_create( diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index f5fa7abd97fc..d477dcc9149f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -1177,7 +1177,7 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign *k2_div = PIXEL_RATE_DIV_BY_2; else *k2_div = PIXEL_RATE_DIV_BY_4; - } else if (dc_is_dp_signal(stream->signal)) { + } else if (dc_is_dp_signal(stream->signal) || dc_is_virtual_signal(stream->signal)) { if (two_pix_per_container) { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_2; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index 026cf13d203f..03cdfb557788 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -1272,7 +1272,8 @@ unsigned int dcn32_calc_num_avail_chans_for_mall(struct dc *dc, int num_chans); DCCG_SRII(PHASE, DTBCLK_DTO, 0), DCCG_SRII(PHASE, DTBCLK_DTO, 1), \ DCCG_SRII(PHASE, DTBCLK_DTO, 2), DCCG_SRII(PHASE, DTBCLK_DTO, 3), \ SR(DCCG_AUDIO_DTBCLK_DTO_MODULO), SR(DCCG_AUDIO_DTBCLK_DTO_PHASE), \ - SR(OTG_PIXEL_RATE_DIV), SR(DTBCLK_P_CNTL), SR(DCCG_AUDIO_DTO_SOURCE) \ + SR(OTG_PIXEL_RATE_DIV), SR(DTBCLK_P_CNTL), \ + SR(DCCG_AUDIO_DTO_SOURCE), SR(DENTIST_DISPCLK_CNTL) \ ) /* VMID */ From 1b4ce2952b4f33e198d5e993acff0611dff1e399 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 11 Jul 2023 15:09:41 -0700 Subject: [PATCH 0489/2093] hugetlb: do not clear hugetlb dtor until allocating vmemmap commit 32c877191e022b55fe3a374f3d7e9fb5741c514d upstream. Patch series "Fix hugetlb free path race with memory errors". In the discussion of Jiaqi Yan's series "Improve hugetlbfs read on HWPOISON hugepages" the race window was discovered. https://lore.kernel.org/linux-mm/20230616233447.GB7371@monkey/ Freeing a hugetlb page back to low level memory allocators is performed in two steps. 1) Under hugetlb lock, remove page from hugetlb lists and clear destructor 2) Outside lock, allocate vmemmap if necessary and call low level free Between these two steps, the hugetlb page will appear as a normal compound page. However, vmemmap for tail pages could be missing. If a memory error occurs at this time, we could try to update page flags non-existant page structs. A much more detailed description is in the first patch. The first patch addresses the race window. However, it adds a hugetlb_lock lock/unlock cycle to every vmemmap optimized hugetlb page free operation. This could lead to slowdowns if one is freeing a large number of hugetlb pages. The second path optimizes the update_and_free_pages_bulk routine to only take the lock once in bulk operations. The second patch is technically not a bug fix, but includes a Fixes tag and Cc stable to avoid a performance regression. It can be combined with the first, but was done separately make reviewing easier. This patch (of 2): Freeing a hugetlb page and releasing base pages back to the underlying allocator such as buddy or cma is performed in two steps: - remove_hugetlb_folio() is called to remove the folio from hugetlb lists, get a ref on the page and remove hugetlb destructor. This all must be done under the hugetlb lock. After this call, the page can be treated as a normal compound page or a collection of base size pages. - update_and_free_hugetlb_folio() is called to allocate vmemmap if needed and the free routine of the underlying allocator is called on the resulting page. We can not hold the hugetlb lock here. One issue with this scheme is that a memory error could occur between these two steps. In this case, the memory error handling code treats the old hugetlb page as a normal compound page or collection of base pages. It will then try to SetPageHWPoison(page) on the page with an error. If the page with error is a tail page without vmemmap, a write error will occur when trying to set the flag. Address this issue by modifying remove_hugetlb_folio() and update_and_free_hugetlb_folio() such that the hugetlb destructor is not cleared until after allocating vmemmap. Since clearing the destructor requires holding the hugetlb lock, the clearing is done in remove_hugetlb_folio() if the vmemmap is present. This saves a lock/unlock cycle. Otherwise, destructor is cleared in update_and_free_hugetlb_folio() after allocating vmemmap. Note that this will leave hugetlb pages in a state where they are marked free (by hugetlb specific page flag) and have a ref count. This is not a normal state. The only code that would notice is the memory error code, and it is set up to retry in such a case. A subsequent patch will create a routine to do bulk processing of vmemmap allocation. This will eliminate a lock/unlock cycle for each hugetlb page in the case where we are freeing a large number of pages. Link: https://lkml.kernel.org/r/20230711220942.43706-1-mike.kravetz@oracle.com Link: https://lkml.kernel.org/r/20230711220942.43706-2-mike.kravetz@oracle.com Fixes: ad2fa3717b74 ("mm: hugetlb: alloc the vmemmap pages associated with each HugeTLB page") Signed-off-by: Mike Kravetz Reviewed-by: Muchun Song Tested-by: Naoya Horiguchi Cc: Axel Rasmussen Cc: James Houghton Cc: Jiaqi Yan Cc: Miaohe Lin Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Mike Kravetz Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 75 +++++++++++++++++++++++++++++++++++----------------- 1 file changed, 51 insertions(+), 24 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d3ffa0fd49e5..c38ec6efec0f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1581,9 +1581,37 @@ static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } #endif +static inline void __clear_hugetlb_destructor(struct hstate *h, + struct page *page) +{ + lockdep_assert_held(&hugetlb_lock); + + /* + * Very subtle + * + * For non-gigantic pages set the destructor to the normal compound + * page dtor. This is needed in case someone takes an additional + * temporary ref to the page, and freeing is delayed until they drop + * their reference. + * + * For gigantic pages set the destructor to the null dtor. This + * destructor will never be called. Before freeing the gigantic + * page destroy_compound_gigantic_folio will turn the folio into a + * simple group of pages. After this the destructor does not + * apply. + * + */ + if (hstate_is_gigantic(h)) + set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + else + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); +} + /* - * Remove hugetlb page from lists, and update dtor so that page appears - * as just a compound page. + * Remove hugetlb page from lists. + * If vmemmap exists for the page, update dtor so that the page appears + * as just a compound page. Otherwise, wait until after allocating vmemmap + * to update dtor. * * A reference is held on the page, except in the case of demote. * @@ -1614,31 +1642,19 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, } /* - * Very subtle - * - * For non-gigantic pages set the destructor to the normal compound - * page dtor. This is needed in case someone takes an additional - * temporary ref to the page, and freeing is delayed until they drop - * their reference. - * - * For gigantic pages set the destructor to the null dtor. This - * destructor will never be called. Before freeing the gigantic - * page destroy_compound_gigantic_page will turn the compound page - * into a simple group of pages. After this the destructor does not - * apply. - * - * This handles the case where more than one ref is held when and - * after update_and_free_page is called. - * - * In the case of demote we do not ref count the page as it will soon - * be turned into a page of smaller size. + * We can only clear the hugetlb destructor after allocating vmemmap + * pages. Otherwise, someone (memory error handling) may try to write + * to tail struct pages. + */ + if (!HPageVmemmapOptimized(page)) + __clear_hugetlb_destructor(h, page); + + /* + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. */ if (!demote) set_page_refcounted(page); - if (hstate_is_gigantic(h)) - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); - else - set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; @@ -1706,6 +1722,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage; + bool clear_dtor = HPageVmemmapOptimized(page); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; @@ -1736,6 +1753,16 @@ static void __update_and_free_page(struct hstate *h, struct page *page) if (unlikely(PageHWPoison(page))) hugetlb_clear_page_hwpoison(page); + /* + * If vmemmap pages were allocated above, then we need to clear the + * hugetlb destructor under the hugetlb lock. + */ + if (clear_dtor) { + spin_lock_irq(&hugetlb_lock); + __clear_hugetlb_destructor(h, page); + spin_unlock_irq(&hugetlb_lock); + } + for (i = 0; i < pages_per_huge_page(h); i++) { subpage = nth_page(page, i); subpage->flags &= ~(1 << PG_locked | 1 << PG_error | From 1be35f5c16703e1f46ff66c9da55341c918f7c3d Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 15 Aug 2023 14:08:47 -0400 Subject: [PATCH 0490/2093] netfilter: set default timeout to 3 secs for sctp shutdown send and recv state commit 9bfab6d23a2865966a4f89a96536fbf23f83bc8c upstream. In SCTP protocol, it is using the same timer (T2 timer) for SHUTDOWN and SHUTDOWN_ACK retransmission. However in sctp conntrack the default timeout value for SCTP_CONNTRACK_SHUTDOWN_ACK_SENT state is 3 secs while it's 300 msecs for SCTP_CONNTRACK_SHUTDOWN_SEND/RECV state. As Paolo Valerio noticed, this might cause unwanted expiration of the ct entry. In my test, with 1s tc netem delay set on the NAT path, after the SHUTDOWN is sent, the sctp ct entry enters SCTP_CONNTRACK_SHUTDOWN_SEND state. However, due to 300ms (too short) delay, when the SHUTDOWN_ACK is sent back from the peer, the sctp ct entry has expired and been deleted, and then the SHUTDOWN_ACK has to be dropped. Also, it is confusing these two sysctl options always show 0 due to all timeout values using sec as unit: net.netfilter.nf_conntrack_sctp_timeout_shutdown_recd = 0 net.netfilter.nf_conntrack_sctp_timeout_shutdown_sent = 0 This patch fixes it by also using 3 secs for sctp shutdown send and recv state in sctp conntrack, which is also RTO.initial value in SCTP protocol. Note that the very short time value for SCTP_CONNTRACK_SHUTDOWN_SEND/RECV was probably used for a rare scenario where SHUTDOWN is sent on 1st path but SHUTDOWN_ACK is replied on 2nd path, then a new connection started immediately on 1st path. So this patch also moves from SHUTDOWN_SEND/RECV to CLOSE when receiving INIT in the ORIGINAL direction. Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Reported-by: Paolo Valerio Signed-off-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: Florian Westphal Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conntrack_proto_sctp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 895e0ca54299..7247af51bdfc 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -49,8 +49,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, - [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, - [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, + [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS, + [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, }; @@ -105,7 +105,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, From 21614ba60883eb93b99a7ee4b41cb927f93b39ae Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 10 Aug 2023 12:28:19 +0100 Subject: [PATCH 0491/2093] arm64/ptrace: Ensure that SME is set up for target when writing SSVE state commit 5d0a8d2fba50e9c07cde4aad7fba28c008b07a5b upstream. When we use NT_ARM_SSVE to either enable streaming mode or change the vector length for a process we do not currently do anything to ensure that there is storage allocated for the SME specific register state. If the task had not previously used SME or we changed the vector length then the task will not have had TIF_SME set or backing storage for ZA/ZT allocated, resulting in inconsistent register sizes when saving state and spurious traps which flush the newly set register state. We should set TIF_SME to disable traps and ensure that storage is allocated for ZA and ZT if it is not already allocated. This requires modifying sme_alloc() to make the flush of any existing register state optional so we don't disturb existing state for ZA and ZT. Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers") Reported-by: David Spickett Signed-off-by: Mark Brown Cc: # 5.19.x Link: https://lore.kernel.org/r/20230810-arm64-fix-ptrace-race-v1-1-a5361fad2bd6@kernel.org Signed-off-by: Catalin Marinas Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/fpsimd.h | 4 ++-- arch/arm64/kernel/fpsimd.c | 6 +++--- arch/arm64/kernel/ptrace.c | 9 ++++++++- arch/arm64/kernel/signal.c | 2 +- 4 files changed, 14 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 6f86b7ab6c28..d720b6f7e5f9 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -339,7 +339,7 @@ static inline int sme_max_virtualisable_vl(void) return vec_max_virtualisable_vl(ARM64_VEC_SME); } -extern void sme_alloc(struct task_struct *task); +extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); @@ -365,7 +365,7 @@ static inline void sme_smstart_sm(void) { } static inline void sme_smstop_sm(void) { } static inline void sme_smstop(void) { } -static inline void sme_alloc(struct task_struct *task) { } +static inline void sme_alloc(struct task_struct *task, bool flush) { } static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 356036babd09..8cd59d387b90 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1239,9 +1239,9 @@ void fpsimd_release_task(struct task_struct *dead_task) * the interest of testability and predictability, the architecture * guarantees that when ZA is enabled it will be zeroed. */ -void sme_alloc(struct task_struct *task) +void sme_alloc(struct task_struct *task, bool flush) { - if (task->thread.za_state) { + if (task->thread.za_state && flush) { memset(task->thread.za_state, 0, za_state_size(task)); return; } @@ -1460,7 +1460,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) } sve_alloc(current, false); - sme_alloc(current); + sme_alloc(current, true); if (!current->thread.sve_state || !current->thread.za_state) { force_sig(SIGKILL); return; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index f19f020ccff9..f606c942f514 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -886,6 +886,13 @@ static int sve_set_common(struct task_struct *target, break; case ARM64_VEC_SME: target->thread.svcr |= SVCR_SM_MASK; + + /* + * Disable traps and ensure there is SME storage but + * preserve any currently set values in ZA/ZT. + */ + sme_alloc(target, false); + set_tsk_thread_flag(target, TIF_SME); break; default: WARN_ON_ONCE(1); @@ -1107,7 +1114,7 @@ static int za_set(struct task_struct *target, } /* Allocate/reinit ZA storage */ - sme_alloc(target); + sme_alloc(target, true); if (!target->thread.za_state) { ret = -ENOMEM; goto out; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 43adbfa5ead7..82f4572c8ddf 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -430,7 +430,7 @@ static int restore_za_context(struct user_ctxs *user) fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ - sme_alloc(current); + sme_alloc(current, true); if (!current->thread.za_state) { current->thread.svcr &= ~SVCR_ZA_MASK; clear_thread_flag(TIF_SME); From 8abce61273c2815ea2ca096ecfb030c4b9e4e686 Mon Sep 17 00:00:00 2001 From: Tim Huang Date: Thu, 27 Jul 2023 09:59:45 +0800 Subject: [PATCH 0492/2093] drm/amd/pm: skip the RLC stop when S0i3 suspend for SMU v13.0.4/11 commit 730d44e1fa306a20746ad4a85da550662aed9daa upstream. For SMU v13.0.4/11, driver does not need to stop RLC for S0i3, the firmwares will handle that properly. Signed-off-by: Tim Huang Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index d191ff52d4f0..a664a0a28478 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1562,9 +1562,9 @@ static int smu_disable_dpms(struct smu_context *smu) /* * For SMU 13.0.4/11, PMFW will handle the features disablement properly - * for gpu reset case. Driver involvement is unnecessary. + * for gpu reset and S0i3 cases. Driver involvement is unnecessary. */ - if (amdgpu_in_reset(adev)) { + if (amdgpu_in_reset(adev) || adev->in_s0ix) { switch (adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 4): case IP_VERSION(13, 0, 11): From ab63f883bfdcfffde60f18918d6c850700eac0fb Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Thu, 25 May 2023 17:24:31 +0800 Subject: [PATCH 0493/2093] drm/amdgpu: keep irq count in amdgpu_irq_disable_all MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8ffd6f0442674f32c048ec8dffdbc5ec67829beb upstream. This can clean up all irq warnings because of unbalanced amdgpu_irq_get/put when unplugging/unbinding device, and leave irq count decrease in each ip fini function. Signed-off-by: Guchun Chen Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index ca5dc51600fa..9efbc0f7c6bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -160,7 +160,6 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev) continue; for (k = 0; k < src->num_types; ++k) { - atomic_set(&src->enabled_types[k], 0); r = src->funcs->set(adev, src, k, AMDGPU_IRQ_STATE_DISABLE); if (r) From 790c2f9d15b594350ae9bca7b236f2b1859de02c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Aug 2023 10:55:05 -0700 Subject: [PATCH 0494/2093] af_unix: Fix null-ptr-deref in unix_stream_sendpage(). Bing-Jhong Billy Jheng reported null-ptr-deref in unix_stream_sendpage() with detailed analysis and a nice repro. unix_stream_sendpage() tries to add data to the last skb in the peer's recv queue without locking the queue. If the peer's FD is passed to another socket and the socket's FD is passed to the peer, there is a loop between them. If we close both sockets without receiving FD, the sockets will be cleaned up by garbage collection. The garbage collection iterates such sockets and unlinks skb with FD from the socket's receive queue under the queue's lock. So, there is a race where unix_stream_sendpage() could access an skb locklessly that is being released by garbage collection, resulting in use-after-free. To avoid the issue, unix_stream_sendpage() must lock the peer's recv queue. Note the issue does not exist in 6.5+ thanks to the recent sendpage() refactoring. This patch is originally written by Linus Torvalds. BUG: unable to handle page fault for address: ffff988004dd6870 PF: supervisor read access in kernel mode PF: error_code(0x0000) - not-present page PGD 0 P4D 0 PREEMPT SMP PTI CPU: 4 PID: 297 Comm: garbage_uaf Not tainted 6.1.46 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:kmem_cache_alloc_node+0xa2/0x1e0 Code: c0 0f 84 32 01 00 00 41 83 fd ff 74 10 48 8b 00 48 c1 e8 3a 41 39 c5 0f 85 1c 01 00 00 41 8b 44 24 28 49 8b 3c 24 48 8d 4a 40 <49> 8b 1c 06 4c 89 f0 65 48 0f c7 0f 0f 94 c0 84 c0 74 a1 41 8b 44 RSP: 0018:ffffc9000079fac0 EFLAGS: 00000246 RAX: 0000000000000070 RBX: 0000000000000005 RCX: 000000000001a284 RDX: 000000000001a244 RSI: 0000000000400cc0 RDI: 000000000002eee0 RBP: 0000000000400cc0 R08: 0000000000400cc0 R09: 0000000000000003 R10: 0000000000000001 R11: 0000000000000000 R12: ffff888003970f00 R13: 00000000ffffffff R14: ffff988004dd6800 R15: 00000000000000e8 FS: 00007f174d6f3600(0000) GS:ffff88807db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff988004dd6870 CR3: 00000000092be000 CR4: 00000000007506e0 PKRU: 55555554 Call Trace: ? __die_body.cold+0x1a/0x1f ? page_fault_oops+0xa9/0x1e0 ? fixup_exception+0x1d/0x310 ? exc_page_fault+0xa8/0x150 ? asm_exc_page_fault+0x22/0x30 ? kmem_cache_alloc_node+0xa2/0x1e0 ? __alloc_skb+0x16c/0x1e0 __alloc_skb+0x16c/0x1e0 alloc_skb_with_frags+0x48/0x1e0 sock_alloc_send_pskb+0x234/0x270 unix_stream_sendmsg+0x1f5/0x690 sock_sendmsg+0x5d/0x60 ____sys_sendmsg+0x210/0x260 ___sys_sendmsg+0x83/0xd0 ? kmem_cache_alloc+0xc6/0x1c0 ? avc_disable+0x20/0x20 ? percpu_counter_add_batch+0x53/0xc0 ? alloc_empty_file+0x5d/0xb0 ? alloc_file+0x91/0x170 ? alloc_file_pseudo+0x94/0x100 ? __fget_light+0x9f/0x120 __sys_sendmsg+0x54/0xa0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x69/0xd3 RIP: 0033:0x7f174d639a7d Code: 28 89 54 24 1c 48 89 74 24 10 89 7c 24 08 e8 8a c1 f4 ff 8b 54 24 1c 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 33 44 89 c7 48 89 44 24 08 e8 de c1 f4 ff 48 RSP: 002b:00007ffcb563ea50 EFLAGS: 00000293 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f174d639a7d RDX: 0000000000000000 RSI: 00007ffcb563eab0 RDI: 0000000000000007 RBP: 00007ffcb563eb10 R08: 0000000000000000 R09: 00000000ffffffff R10: 00000000004040a0 R11: 0000000000000293 R12: 00007ffcb563ec28 R13: 0000000000401398 R14: 0000000000403e00 R15: 00007f174d72c000 Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support") Reported-by: Bing-Jhong Billy Jheng Reviewed-by: Bing-Jhong Billy Jheng Co-developed-by: Linus Torvalds Signed-off-by: Linus Torvalds Signed-off-by: Kuniyuki Iwashima Signed-off-by: Greg Kroah-Hartman --- net/unix/af_unix.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 78fa620a6398..ca31847a6c70 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2290,6 +2290,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, @@ -2329,6 +2330,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, init_scm = false; } + spin_lock(&other->sk_receive_queue.lock); skb = skb_peek_tail(&other->sk_receive_queue); if (tail && tail == skb) { skb = newskb; @@ -2359,14 +2361,11 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); + unix_scm_to_skb(&scm, skb, false); __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); } + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); From 3f27451c9f29d5ed00232968680c7838a44dcac7 Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Mon, 14 Aug 2023 16:49:32 +0200 Subject: [PATCH 0495/2093] drm/nouveau/disp: fix use-after-free in error handling of nouveau_connector_create commit 1b254b791d7b7dea6e8adc887fbbd51746d8bb27 upstream. We can't simply free the connector after calling drm_connector_init on it. We need to clean up the drm side first. It might not fix all regressions from commit 2b5d1c29f6c4 ("drm/nouveau/disp: PIOR DP uses GPIO for HPD, not PMGR AUX interrupts"), but at least it fixes a memory corruption in error handling related to that commit. Link: https://lore.kernel.org/lkml/20230806213107.GFZNARG6moWpFuSJ9W@fat_crate.local/ Fixes: 95983aea8003 ("drm/nouveau/disp: add connector class") Signed-off-by: Karol Herbst Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230814144933.3956959-1-kherbst@redhat.com Signed-off-by: Karol Herbst Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/nouveau_connector.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 49c5451cdfb1..d6dd79541f6a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -1407,8 +1407,7 @@ nouveau_connector_create(struct drm_device *dev, ret = nvif_conn_ctor(&disp->disp, nv_connector->base.name, nv_connector->index, &nv_connector->conn); if (ret) { - kfree(nv_connector); - return ERR_PTR(ret); + goto drm_conn_err; } } @@ -1470,4 +1469,9 @@ nouveau_connector_create(struct drm_device *dev, drm_connector_register(connector); return connector; + +drm_conn_err: + drm_connector_cleanup(connector); + kfree(nv_connector); + return ERR_PTR(ret); } From b2c55af89b513bfc1fb31d8b2864cba29aace6b0 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Fri, 11 Aug 2023 10:37:47 +0800 Subject: [PATCH 0496/2093] net: fix the RTO timer retransmitting skb every 1ms if linear option is enabled commit e4dd0d3a2f64b8bd8029ec70f52bdbebd0644408 upstream. In the real workload, I encountered an issue which could cause the RTO timer to retransmit the skb per 1ms with linear option enabled. The amount of lost-retransmitted skbs can go up to 1000+ instantly. The root cause is that if the icsk_rto happens to be zero in the 6th round (which is the TCP_THIN_LINEAR_RETRIES value), then it will always be zero due to the changed calculation method in tcp_retransmit_timer() as follows: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); Above line could be converted to icsk->icsk_rto = min(0 << 1, TCP_RTO_MAX) = 0 Therefore, the timer expires so quickly without any doubt. I read through the RFC 6298 and found that the RTO value can be rounded up to a certain value, in Linux, say TCP_RTO_MIN as default, which is regarded as the lower bound in this patch as suggested by Eric. Fixes: 36e31b0af587 ("net: TCP thin linear timeouts") Suggested-by: Eric Dumazet Signed-off-by: Jason Xing Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_timer.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0b5d0a2867a8..cf354c29ec12 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -586,7 +586,9 @@ void tcp_retransmit_timer(struct sock *sk) tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; - icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); + icsk->icsk_rto = clamp(__tcp_set_rto(tp), + tcp_rto_min(sk), + TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); From 0768ecc49ea76a19dde119e79bf770cdfda93e29 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Thu, 27 Jul 2023 15:00:51 +0800 Subject: [PATCH 0497/2093] mmc: f-sdh30: fix order of function calls in sdhci_f_sdh30_remove MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 58abdd80b93b09023ca03007b608685c41e3a289 upstream. The order of function calls in sdhci_f_sdh30_remove is wrong, let's call sdhci_pltfm_unregister first. Cc: Uwe Kleine-König Fixes: 5def5c1c15bf ("mmc: sdhci-f-sdh30: Replace with sdhci_pltfm") Signed-off-by: Yangtao Li Reported-by: Uwe Kleine-König Acked-by: Uwe Kleine-König Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230727070051.17778-62-frank.li@vivo.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci_f_sdh30.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c index 8876fd1c7eee..7ede74bf3723 100644 --- a/drivers/mmc/host/sdhci_f_sdh30.c +++ b/drivers/mmc/host/sdhci_f_sdh30.c @@ -188,12 +188,14 @@ static int sdhci_f_sdh30_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); struct f_sdhost_priv *priv = sdhci_f_sdhost_priv(host); - - clk_disable_unprepare(priv->clk_iface); - clk_disable_unprepare(priv->clk); + struct clk *clk_iface = priv->clk_iface; + struct clk *clk = priv->clk; sdhci_pltfm_unregister(pdev); + clk_disable_unprepare(clk_iface); + clk_disable_unprepare(clk); + return 0; } From 802aacbbffe2512dce9f8f33ad99d01cfec435de Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 23 Aug 2023 17:52:42 +0200 Subject: [PATCH 0498/2093] Linux 6.1.47 Link: https://lore.kernel.org/r/20230821194122.695845670@linuxfoundation.org Tested-by: Joel Fernandes (Google) Tested-by: Takeshi Ogasawara Tested-by: Bagas Sanjaya Tested-by: SeongJae Park Tested-by: Shuah Khan Tested-by: Florian Fainelli Tested-by: Ron Economos Tested-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index bdb965177db5..375efcfb91f8 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 46 +SUBLEVEL = 47 EXTRAVERSION = NAME = Curry Ramen From 6e4dd7d2636d8e8fb634cc9e7fc84eb13928e88a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:27 +0200 Subject: [PATCH 0499/2093] x86/cpu: Fix __x86_return_thunk symbol type commit 77f67119004296a9b2503b377d610e08b08afc2a upstream. Commit fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") reimplemented __x86_return_thunk with a mix of SYM_FUNC_START and SYM_CODE_END, this is not a sane combination. Since nothing should ever actually 'CALL' this, make it consistently CODE. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.571027074@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/retpoline.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 30e76fab678a..591d4a2419b5 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -207,7 +207,9 @@ SYM_CODE_END(srso_safe_ret) SYM_FUNC_END(srso_untrain_ret) __EXPORT_THUNK(srso_untrain_ret) -SYM_FUNC_START(__x86_return_thunk) +SYM_CODE_START(__x86_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS int3 From 8bb1ed390d358f6c167f45a27305b775aa8fc898 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:28 +0200 Subject: [PATCH 0500/2093] x86/cpu: Fix up srso_safe_ret() and __x86_return_thunk() commit af023ef335f13c8b579298fc432daeef609a9e60 upstream. vmlinux.o: warning: objtool: srso_untrain_ret() falls through to next function __x86_return_skl() vmlinux.o: warning: objtool: __x86_return_thunk() falls through to next function __x86_return_skl() This is because these functions (can) end with CALL, which objtool does not consider a terminating instruction. Therefore, replace the INT3 instruction (which is a non-fatal trap) with UD2 (which is a fatal-trap). This indicates execution will not continue past this point. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.637802730@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/retpoline.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 591d4a2419b5..271f6560448d 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -202,7 +202,7 @@ SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) int3 lfence call srso_safe_ret - int3 + ud2 SYM_CODE_END(srso_safe_ret) SYM_FUNC_END(srso_untrain_ret) __EXPORT_THUNK(srso_untrain_ret) @@ -212,7 +212,7 @@ SYM_CODE_START(__x86_return_thunk) ANNOTATE_NOENDBR ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS - int3 + ud2 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) From 53ebbe1c8c02aa7b7f072dd2f96bca4faa1daa59 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:30 +0200 Subject: [PATCH 0501/2093] x86/alternative: Make custom return thunk unconditional commit 095b8303f3835c68ac4a8b6d754ca1c3b6230711 upstream. There is infrastructure to rewrite return thunks to point to any random thunk one desires, unwrap that from CALL_THUNKS, which up to now was the sole user of that. [ bp: Make the thunks visible on 32-bit and add ifdeffery for the 32-bit builds. ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.775293785@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 5 +++++ arch/x86/kernel/cpu/bugs.c | 2 ++ 2 files changed, 7 insertions(+) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 31fa631c8587..9a4ffd321d29 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -210,7 +210,12 @@ typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; +#ifdef CONFIG_RETHUNK extern void __x86_return_thunk(void); +#else +static inline void __x86_return_thunk(void) {} +#endif + extern void zen_untrain_ret(void); extern void srso_untrain_ret(void); extern void srso_untrain_ret_alias(void); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d98f33ea57e4..666f5bed2d97 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -62,6 +62,8 @@ EXPORT_SYMBOL_GPL(x86_pred_cmd); static DEFINE_MUTEX(spec_ctrl_mutex); +void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { From 44dbc912fd8a132f01eca8fc0928d6c9beb1f51c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:31 +0200 Subject: [PATCH 0502/2093] x86/cpu: Clean up SRSO return thunk mess commit d43490d0ab824023e11d0b57d0aeec17a6e0ca13 upstream. Use the existing configurable return thunk. There is absolute no justification for having created this __x86_return_thunk alternative. To clarify, the whole thing looks like: Zen3/4 does: srso_alias_untrain_ret: nop2 lfence jmp srso_alias_return_thunk int3 srso_alias_safe_ret: // aliasses srso_alias_untrain_ret just so add $8, %rsp ret int3 srso_alias_return_thunk: call srso_alias_safe_ret ud2 While Zen1/2 does: srso_untrain_ret: movabs $foo, %rax lfence call srso_safe_ret (jmp srso_return_thunk ?) int3 srso_safe_ret: // embedded in movabs instruction add $8,%rsp ret int3 srso_return_thunk: call srso_safe_ret ud2 While retbleed does: zen_untrain_ret: test $0xcc, %bl lfence jmp zen_return_thunk int3 zen_return_thunk: // embedded in the test instruction ret int3 Where Zen1/2 flush the BTB entry using the instruction decoder trick (test,movabs) Zen3/4 use BTB aliasing. SRSO adds a return sequence (srso_safe_ret()) which forces the function return instruction to speculate into a trap (UD2). This RET will then mispredict and execution will continue at the return site read from the top of the stack. Pick one of three options at boot (evey function can only ever return once). [ bp: Fixup commit message uarch details and add them in a comment in the code too. Add a comment about the srso_select_mitigation() dependency on retbleed_select_mitigation(). Add moar ifdeffery for 32-bit builds. Add a dummy srso_untrain_ret_alias() definition for 32-bit alternatives needing the symbol. ] Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.842775684@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 5 +++ arch/x86/kernel/cpu/bugs.c | 17 ++++++-- arch/x86/kernel/vmlinux.lds.S | 4 +- arch/x86/lib/retpoline.S | 58 ++++++++++++++++++++-------- tools/objtool/arch/x86/decode.c | 2 +- 5 files changed, 64 insertions(+), 22 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 9a4ffd321d29..71899b8a86e7 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -216,9 +216,14 @@ extern void __x86_return_thunk(void); static inline void __x86_return_thunk(void) {} #endif +extern void zen_return_thunk(void); +extern void srso_return_thunk(void); +extern void srso_alias_return_thunk(void); + extern void zen_untrain_ret(void); extern void srso_untrain_ret(void); extern void srso_untrain_ret_alias(void); + extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 666f5bed2d97..757c973531c5 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -166,8 +166,13 @@ void __init cpu_select_mitigations(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); - gds_select_mitigation(); + + /* + * srso_select_mitigation() depends and must run after + * retbleed_select_mitigation(). + */ srso_select_mitigation(); + gds_select_mitigation(); } /* @@ -1015,6 +1020,9 @@ static void __init retbleed_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); + if (IS_ENABLED(CONFIG_RETHUNK)) + x86_return_thunk = zen_return_thunk; + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) pr_err(RETBLEED_UNTRAIN_MSG); @@ -2422,10 +2430,13 @@ static void __init srso_select_mitigation(void) */ setup_force_cpu_cap(X86_FEATURE_RETHUNK); - if (boot_cpu_data.x86 == 0x19) + if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); - else + x86_return_thunk = srso_alias_return_thunk; + } else { setup_force_cpu_cap(X86_FEATURE_SRSO); + x86_return_thunk = srso_return_thunk; + } srso_mitigation = SRSO_MITIGATION_SAFE_RET; } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e6939ebb606a..8af3ac61ee5f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -507,8 +507,8 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif - #ifdef CONFIG_RETHUNK -. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned"); +#ifdef CONFIG_RETHUNK +. = ASSERT((zen_return_thunk & 0x3f) == 0, "zen_return_thunk not cacheline-aligned"); . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 271f6560448d..a08a53b31447 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -94,22 +94,27 @@ SYM_CODE_END(__x86_indirect_thunk_array) .section .text.__x86.rethunk_untrain SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + UNWIND_HINT_FUNC ANNOTATE_NOENDBR ASM_NOP2 lfence - jmp __x86_return_thunk + jmp srso_alias_return_thunk SYM_FUNC_END(srso_untrain_ret_alias) __EXPORT_THUNK(srso_untrain_ret_alias) .section .text.__x86.rethunk_safe +#else +/* dummy definition for alternatives */ +SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_untrain_ret_alias) #endif -/* Needs a definition for the __x86_return_thunk alternative below. */ SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) -#ifdef CONFIG_CPU_SRSO add $8, %_ASM_SP UNWIND_HINT_FUNC -#endif ANNOTATE_UNRET_SAFE ret int3 @@ -117,9 +122,16 @@ SYM_FUNC_END(srso_safe_ret_alias) .section .text.__x86.return_thunk +SYM_CODE_START(srso_alias_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_safe_ret_alias + ud2 +SYM_CODE_END(srso_alias_return_thunk) + /* * Safety details here pertain to the AMD Zen{1,2} microarchitecture: - * 1) The RET at __x86_return_thunk must be on a 64 byte boundary, for + * 1) The RET at zen_return_thunk must be on a 64 byte boundary, for * alignment within the BTB. * 2) The instruction at zen_untrain_ret must contain, and not * end with, the 0xc3 byte of the RET. @@ -127,7 +139,7 @@ SYM_FUNC_END(srso_safe_ret_alias) * from re-poisioning the BTB prediction. */ .align 64 - .skip 64 - (__ret - zen_untrain_ret), 0xcc + .skip 64 - (zen_return_thunk - zen_untrain_ret), 0xcc SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR /* @@ -135,16 +147,16 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * * TEST $0xcc, %bl * LFENCE - * JMP __x86_return_thunk + * JMP zen_return_thunk * * Executing the TEST instruction has a side effect of evicting any BTB * prediction (potentially attacker controlled) attached to the RET, as - * __x86_return_thunk + 1 isn't an instruction boundary at the moment. + * zen_return_thunk + 1 isn't an instruction boundary at the moment. */ .byte 0xf6 /* - * As executed from __x86_return_thunk, this is a plain RET. + * As executed from zen_return_thunk, this is a plain RET. * * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8. * @@ -156,13 +168,13 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * With SMT enabled and STIBP active, a sibling thread cannot poison * RET's prediction to a type of its choice, but can evict the * prediction due to competitive sharing. If the prediction is - * evicted, __x86_return_thunk will suffer Straight Line Speculation + * evicted, zen_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(__ret, SYM_L_GLOBAL) +SYM_INNER_LABEL(zen_return_thunk, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(__ret) +SYM_CODE_END(zen_return_thunk) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -173,7 +185,7 @@ SYM_CODE_END(__ret) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp __ret + jmp zen_return_thunk int3 SYM_FUNC_END(zen_untrain_ret) __EXPORT_THUNK(zen_untrain_ret) @@ -194,12 +206,19 @@ SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR .byte 0x48, 0xb8 +/* + * This forces the function return instruction to speculate into a trap + * (UD2 in srso_return_thunk() below). This RET will then mispredict + * and execution will continue at the return site read from the top of + * the stack. + */ SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) add $8, %_ASM_SP ret int3 int3 int3 + /* end of movabs */ lfence call srso_safe_ret ud2 @@ -207,12 +226,19 @@ SYM_CODE_END(srso_safe_ret) SYM_FUNC_END(srso_untrain_ret) __EXPORT_THUNK(srso_untrain_ret) +SYM_CODE_START(srso_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_safe_ret + ud2 +SYM_CODE_END(srso_return_thunk) + SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR - ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ - "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS - ud2 + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index a60c5efe34b3..8d8bc07184ea 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -799,5 +799,5 @@ bool arch_is_rethunk(struct symbol *sym) return !strcmp(sym->name, "__x86_return_thunk") || !strcmp(sym->name, "srso_untrain_ret") || !strcmp(sym->name, "srso_safe_ret") || - !strcmp(sym->name, "__ret"); + !strcmp(sym->name, "zen_return_thunk"); } From 54dde78a50a8eb0d6a293c8416fcf6365d189af3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:32 +0200 Subject: [PATCH 0503/2093] x86/cpu: Rename original retbleed methods commit d025b7bac07a6e90b6b98b487f88854ad9247c39 upstream. Rename the original retbleed return thunk and untrain_ret to retbleed_return_thunk() and retbleed_untrain_ret(). No functional changes. Suggested-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.909378169@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 8 ++++---- arch/x86/kernel/cpu/bugs.c | 2 +- arch/x86/kernel/vmlinux.lds.S | 2 +- arch/x86/lib/retpoline.S | 30 ++++++++++++++-------------- tools/objtool/arch/x86/decode.c | 2 +- tools/objtool/check.c | 2 +- 6 files changed, 23 insertions(+), 23 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 71899b8a86e7..da8795d73836 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -168,7 +168,7 @@ .endm #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_ZEN_UNTRAIN_RET "call zen_untrain_ret" +#define CALL_ZEN_UNTRAIN_RET "call retbleed_untrain_ret" #else #define CALL_ZEN_UNTRAIN_RET "" #endif @@ -178,7 +178,7 @@ * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * - * While zen_untrain_ret() doesn't clobber anything but requires stack, + * While retbleed_untrain_ret() doesn't clobber anything but requires stack, * entry_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point @@ -216,11 +216,11 @@ extern void __x86_return_thunk(void); static inline void __x86_return_thunk(void) {} #endif -extern void zen_return_thunk(void); +extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); -extern void zen_untrain_ret(void); +extern void retbleed_untrain_ret(void); extern void srso_untrain_ret(void); extern void srso_untrain_ret_alias(void); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 757c973531c5..07eebfa39f5b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1021,7 +1021,7 @@ static void __init retbleed_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_UNRET); if (IS_ENABLED(CONFIG_RETHUNK)) - x86_return_thunk = zen_return_thunk; + x86_return_thunk = retbleed_return_thunk; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8af3ac61ee5f..72efa6d59b2f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -508,7 +508,7 @@ INIT_PER_CPU(irq_stack_backing_store); #endif #ifdef CONFIG_RETHUNK -. = ASSERT((zen_return_thunk & 0x3f) == 0, "zen_return_thunk not cacheline-aligned"); +. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index a08a53b31447..ff2196cbf0d6 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -131,32 +131,32 @@ SYM_CODE_END(srso_alias_return_thunk) /* * Safety details here pertain to the AMD Zen{1,2} microarchitecture: - * 1) The RET at zen_return_thunk must be on a 64 byte boundary, for + * 1) The RET at retbleed_return_thunk must be on a 64 byte boundary, for * alignment within the BTB. - * 2) The instruction at zen_untrain_ret must contain, and not + * 2) The instruction at retbleed_untrain_ret must contain, and not * end with, the 0xc3 byte of the RET. * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread * from re-poisioning the BTB prediction. */ .align 64 - .skip 64 - (zen_return_thunk - zen_untrain_ret), 0xcc -SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + .skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc +SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_NOENDBR /* - * As executed from zen_untrain_ret, this is: + * As executed from retbleed_untrain_ret, this is: * * TEST $0xcc, %bl * LFENCE - * JMP zen_return_thunk + * JMP retbleed_return_thunk * * Executing the TEST instruction has a side effect of evicting any BTB * prediction (potentially attacker controlled) attached to the RET, as - * zen_return_thunk + 1 isn't an instruction boundary at the moment. + * retbleed_return_thunk + 1 isn't an instruction boundary at the moment. */ .byte 0xf6 /* - * As executed from zen_return_thunk, this is a plain RET. + * As executed from retbleed_return_thunk, this is a plain RET. * * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8. * @@ -168,13 +168,13 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * With SMT enabled and STIBP active, a sibling thread cannot poison * RET's prediction to a type of its choice, but can evict the * prediction due to competitive sharing. If the prediction is - * evicted, zen_return_thunk will suffer Straight Line Speculation + * evicted, retbleed_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(zen_return_thunk, SYM_L_GLOBAL) +SYM_INNER_LABEL(retbleed_return_thunk, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(zen_return_thunk) +SYM_CODE_END(retbleed_return_thunk) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -185,13 +185,13 @@ SYM_CODE_END(zen_return_thunk) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp zen_return_thunk + jmp retbleed_return_thunk int3 -SYM_FUNC_END(zen_untrain_ret) -__EXPORT_THUNK(zen_untrain_ret) +SYM_FUNC_END(retbleed_untrain_ret) +__EXPORT_THUNK(retbleed_untrain_ret) /* - * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret() + * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() * above. On kernel entry, srso_untrain_ret() is executed which is a * * movabs $0xccccccc308c48348,%rax diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 8d8bc07184ea..29c35279c7ed 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -799,5 +799,5 @@ bool arch_is_rethunk(struct symbol *sym) return !strcmp(sym->name, "__x86_return_thunk") || !strcmp(sym->name, "srso_untrain_ret") || !strcmp(sym->name, "srso_safe_ret") || - !strcmp(sym->name, "zen_return_thunk"); + !strcmp(sym->name, "retbleed_return_thunk"); } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c2c350933a23..8ec97762b607 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1430,7 +1430,7 @@ static int add_jump_destinations(struct objtool_file *file) struct symbol *sym = find_symbol_by_offset(dest_sec, dest_off); /* - * This is a special case for zen_untrain_ret(). + * This is a special case for retbleed_untrain_ret(). * It jumps to __x86_return_thunk(), but objtool * can't find the thunk's starting RET * instruction, because the RET is also in the From e6b40d2cb5aae35cc3659f9b74c999a01120ad30 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:33 +0200 Subject: [PATCH 0504/2093] x86/cpu: Rename srso_(.*)_alias to srso_alias_\1 commit 42be649dd1f2eee6b1fb185f1a231b9494cf095f upstream. For a more consistent namespace. [ bp: Fixup names in the doc too. ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.976236447@infradead.org Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/srso.rst | 4 ++-- arch/x86/include/asm/nospec-branch.h | 4 ++-- arch/x86/kernel/vmlinux.lds.S | 8 +++---- arch/x86/lib/retpoline.S | 26 +++++++++++----------- 4 files changed, 21 insertions(+), 21 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst index 2f923c805802..f79cb11b080f 100644 --- a/Documentation/admin-guide/hw-vuln/srso.rst +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -124,8 +124,8 @@ sequence. To ensure the safety of this mitigation, the kernel must ensure that the safe return sequence is itself free from attacker interference. In Zen3 and Zen4, this is accomplished by creating a BTB alias between the -untraining function srso_untrain_ret_alias() and the safe return -function srso_safe_ret_alias() which results in evicting a potentially +untraining function srso_alias_untrain_ret() and the safe return +function srso_alias_safe_ret() which results in evicting a potentially poisoned BTB entry and using that safe one for all function returns. In older Zen1 and Zen2, this is accomplished using a reinterpretation diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index da8795d73836..08262e6badc3 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -195,7 +195,7 @@ #ifdef CONFIG_CPU_SRSO ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ - "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif .endm @@ -222,7 +222,7 @@ extern void srso_alias_return_thunk(void); extern void retbleed_untrain_ret(void); extern void srso_untrain_ret(void); -extern void srso_untrain_ret_alias(void); +extern void srso_alias_untrain_ret(void); extern void entry_ibpb(void); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 72efa6d59b2f..6b137c002778 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -141,10 +141,10 @@ SECTIONS #ifdef CONFIG_CPU_SRSO /* - * See the comment above srso_untrain_ret_alias()'s + * See the comment above srso_alias_untrain_ret()'s * definition. */ - . = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + . = srso_alias_untrain_ret | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); *(.text.__x86.rethunk_safe) #endif ALIGN_ENTRY_TEXT_END @@ -523,8 +523,8 @@ INIT_PER_CPU(irq_stack_backing_store); * Instead do: (A | B) - (A & B) in order to compute the XOR * of the two function addresses: */ -. = ASSERT(((ABSOLUTE(srso_untrain_ret_alias) | srso_safe_ret_alias) - - (ABSOLUTE(srso_untrain_ret_alias) & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), +. = ASSERT(((ABSOLUTE(srso_alias_untrain_ret) | srso_alias_safe_ret) - + (ABSOLUTE(srso_alias_untrain_ret) & srso_alias_safe_ret)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), "SRSO function pair won't alias"); #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index ff2196cbf0d6..4ba7739be027 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -76,56 +76,56 @@ SYM_CODE_END(__x86_indirect_thunk_array) #ifdef CONFIG_RETHUNK /* - * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at + * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at * special addresses: * - * - srso_untrain_ret_alias() is 2M aligned - * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14 + * - srso_alias_untrain_ret() is 2M aligned + * - srso_alias_safe_ret() is also in the same 2M page but bits 2, 8, 14 * and 20 in its virtual address are set (while those bits in the - * srso_untrain_ret_alias() function are cleared). + * srso_alias_untrain_ret() function are cleared). * * This guarantees that those two addresses will alias in the branch * target buffer of Zen3/4 generations, leading to any potential * poisoned entries at that BTB slot to get evicted. * - * As a result, srso_safe_ret_alias() becomes a safe return. + * As a result, srso_alias_safe_ret() becomes a safe return. */ #ifdef CONFIG_CPU_SRSO .section .text.__x86.rethunk_untrain -SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) UNWIND_HINT_FUNC ANNOTATE_NOENDBR ASM_NOP2 lfence jmp srso_alias_return_thunk -SYM_FUNC_END(srso_untrain_ret_alias) -__EXPORT_THUNK(srso_untrain_ret_alias) +SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) .section .text.__x86.rethunk_safe #else /* dummy definition for alternatives */ -SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_UNRET_SAFE ret int3 -SYM_FUNC_END(srso_untrain_ret_alias) +SYM_FUNC_END(srso_alias_untrain_ret) #endif -SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) add $8, %_ASM_SP UNWIND_HINT_FUNC ANNOTATE_UNRET_SAFE ret int3 -SYM_FUNC_END(srso_safe_ret_alias) +SYM_FUNC_END(srso_alias_safe_ret) .section .text.__x86.return_thunk SYM_CODE_START(srso_alias_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR - call srso_safe_ret_alias + call srso_alias_safe_ret ud2 SYM_CODE_END(srso_alias_return_thunk) From 529a9f087a7e03e87dd9c2acd687739e3e348045 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:34 +0200 Subject: [PATCH 0505/2093] x86/cpu: Cleanup the untrain mess commit e7c25c441e9e0fa75b4c83e0b26306b702cfe90d upstream. Since there can only be one active return_thunk, there only needs be one (matching) untrain_ret. It fundamentally doesn't make sense to allow multiple untrain_ret at the same time. Fold all the 3 different untrain methods into a single (temporary) helper stub. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121149.042774962@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 12 ++++-------- arch/x86/kernel/cpu/bugs.c | 1 + arch/x86/lib/retpoline.S | 7 +++++++ 3 files changed, 12 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 08262e6badc3..2f123d4fb85b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -168,9 +168,9 @@ .endm #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_ZEN_UNTRAIN_RET "call retbleed_untrain_ret" +#define CALL_UNTRAIN_RET "call entry_untrain_ret" #else -#define CALL_ZEN_UNTRAIN_RET "" +#define CALL_UNTRAIN_RET "" #endif /* @@ -189,14 +189,9 @@ defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ - CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ + CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif - -#ifdef CONFIG_CPU_SRSO - ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ - "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS -#endif .endm #else /* __ASSEMBLY__ */ @@ -224,6 +219,7 @@ extern void retbleed_untrain_ret(void); extern void srso_untrain_ret(void); extern void srso_alias_untrain_ret(void); +extern void entry_untrain_ret(void); extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 07eebfa39f5b..c2f8f98f20d5 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2429,6 +2429,7 @@ static void __init srso_select_mitigation(void) * like ftrace, static_call, etc. */ setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_UNRET); if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 4ba7739be027..08a9faa220fe 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -233,6 +233,13 @@ SYM_CODE_START(srso_return_thunk) ud2 SYM_CODE_END(srso_return_thunk) +SYM_FUNC_START(entry_untrain_ret) + ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ + "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ + "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS +SYM_FUNC_END(entry_untrain_ret) +__EXPORT_THUNK(entry_untrain_ret) + SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR From c16d0b3baff418ca09c4f6a7e04f0bfc472187bf Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Mon, 14 Aug 2023 21:29:50 +0200 Subject: [PATCH 0506/2093] x86/srso: Explain the untraining sequences a bit more commit 9dbd23e42ff0b10c9b02c9e649c76e5228241a8e upstream. The goal is to eventually have a proper documentation about all this. Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814164447.GFZNpZ/64H4lENIe94@fat_crate.local Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/retpoline.S | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 08a9faa220fe..455a44aa22fb 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -129,6 +129,25 @@ SYM_CODE_START(srso_alias_return_thunk) ud2 SYM_CODE_END(srso_alias_return_thunk) +/* + * Some generic notes on the untraining sequences: + * + * They are interchangeable when it comes to flushing potentially wrong + * RET predictions from the BTB. + * + * The SRSO Zen1/2 (MOVABS) untraining sequence is longer than the + * Retbleed sequence because the return sequence done there + * (srso_safe_ret()) is longer and the return sequence must fully nest + * (end before) the untraining sequence. Therefore, the untraining + * sequence must fully overlap the return sequence. + * + * Regarding alignment - the instructions which need to be untrained, + * must all start at a cacheline boundary for Zen1/2 generations. That + * is, instruction sequences starting at srso_safe_ret() and + * the respective instruction sequences at retbleed_return_thunk() + * must start at a cacheline boundary. + */ + /* * Safety details here pertain to the AMD Zen{1,2} microarchitecture: * 1) The RET at retbleed_return_thunk must be on a 64 byte boundary, for From c1f831425fe900fd18789733b66f4c987345296c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Aug 2023 12:44:19 +0200 Subject: [PATCH 0507/2093] x86/static_call: Fix __static_call_fixup() commit 54097309620ef0dc2d7083783dc521c6a5fef957 upstream. Christian reported spurious module load crashes after some of Song's module memory layout patches. Turns out that if the very last instruction on the very last page of the module is a 'JMP __x86_return_thunk' then __static_call_fixup() will trip a fault and die. And while the module rework made this slightly more likely to happen, it's always been possible. Fixes: ee88d363d156 ("x86,static_call: Use alternative RET encoding") Reported-by: Christian Bricart Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/20230816104419.GA982867@hirez.programming.kicks-ass.net Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/static_call.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index a9b54b795ebf..3fbb49168827 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -184,6 +184,19 @@ EXPORT_SYMBOL_GPL(arch_static_call_transform); */ bool __static_call_fixup(void *tramp, u8 op, void *dest) { + unsigned long addr = (unsigned long)tramp; + /* + * Not all .return_sites are a static_call trampoline (most are not). + * Check if the 3 bytes after the return are still kernel text, if not, + * then this definitely is not a trampoline and we need not worry + * further. + * + * This avoids the memcmp() below tripping over pagefaults etc.. + */ + if (((addr >> PAGE_SHIFT) != ((addr + 7) >> PAGE_SHIFT)) && + !kernel_text_address(addr + 7)) + return false; + if (memcmp(tramp+5, tramp_ud, 3)) { /* Not a trampoline site, not our problem. */ return false; From b41eb316c95c98d16dba2045c4890a3020f0a5bc Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 11 Aug 2023 08:52:55 -0700 Subject: [PATCH 0508/2093] x86/retpoline: Don't clobber RFLAGS during srso_safe_ret() commit ba5ca5e5e6a1d55923e88b4a83da452166f5560e upstream. Use LEA instead of ADD when adjusting %rsp in srso_safe_ret{,_alias}() so as to avoid clobbering flags. Drop one of the INT3 instructions to account for the LEA consuming one more byte than the ADD. KVM's emulator makes indirect calls into a jump table of sorts, where the destination of each call is a small blob of code that performs fast emulation by executing the target instruction with fixed operands. E.g. to emulate ADC, fastop() invokes adcb_al_dl(): adcb_al_dl: <+0>: adc %dl,%al <+2>: jmp <__x86_return_thunk> A major motivation for doing fast emulation is to leverage the CPU to handle consumption and manipulation of arithmetic flags, i.e. RFLAGS is both an input and output to the target of the call. fastop() collects the RFLAGS result by pushing RFLAGS onto the stack and popping them back into a variable (held in %rdi in this case): asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" <+71>: mov 0xc0(%r8),%rdx <+78>: mov 0x100(%r8),%rcx <+85>: push %rdi <+86>: popf <+87>: call *%rsi <+89>: nop <+90>: nop <+91>: nop <+92>: pushf <+93>: pop %rdi and then propagating the arithmetic flags into the vCPU's emulator state: ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); <+64>: and $0xfffffffffffff72a,%r9 <+94>: and $0x8d5,%edi <+109>: or %rdi,%r9 <+122>: mov %r9,0x10(%r8) The failures can be most easily reproduced by running the "emulator" test in KVM-Unit-Tests. If you're feeling a bit of deja vu, see commit b63f20a778c8 ("x86/retpoline: Don't clobber RFLAGS during CALL_NOSPEC on i386"). In addition, this breaks booting of clang-compiled guest on a gcc-compiled host where the host contains the %rsp-modifying SRSO mitigations. [ bp: Massage commit message, extend, remove addresses. ] Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Closes: https://lore.kernel.org/all/de474347-122d-54cd-eabf-9dcc95ab9eae@amd.com Reported-by: Srikanth Aithal Reported-by: Nathan Chancellor Signed-off-by: Sean Christopherson Signed-off-by: Borislav Petkov (AMD) Tested-by: Nathan Chancellor Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20230810013334.GA5354@dev-arch.thelio-3990X/ Link: https://lore.kernel.org/r/20230811155255.250835-1-seanjc@google.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/retpoline.S | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 455a44aa22fb..5a55ee2e80f0 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -113,7 +113,7 @@ SYM_FUNC_END(srso_alias_untrain_ret) #endif SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) - add $8, %_ASM_SP + lea 8(%_ASM_SP), %_ASM_SP UNWIND_HINT_FUNC ANNOTATE_UNRET_SAFE ret @@ -213,7 +213,7 @@ __EXPORT_THUNK(retbleed_untrain_ret) * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() * above. On kernel entry, srso_untrain_ret() is executed which is a * - * movabs $0xccccccc308c48348,%rax + * movabs $0xccccc30824648d48,%rax * * and when the return thunk executes the inner label srso_safe_ret() * later, it is a stack manipulation and a RET which is mispredicted and @@ -232,11 +232,10 @@ SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) * the stack. */ SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) - add $8, %_ASM_SP + lea 8(%_ASM_SP), %_ASM_SP ret int3 int3 - int3 /* end of movabs */ lfence call srso_safe_ret From e4679a0342e05a962639a6ec3781f257f417f0ff Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 11 Aug 2023 23:38:24 +0200 Subject: [PATCH 0509/2093] x86/CPU/AMD: Fix the DIV(0) initial fix attempt commit f58d6fbcb7c848b7f2469be339bc571f2e9d245b upstream. Initially, it was thought that doing an innocuous division in the #DE handler would take care to prevent any leaking of old data from the divider but by the time the fault is raised, the speculation has already advanced too far and such data could already have been used by younger operations. Therefore, do the innocuous division on every exit to userspace so that userspace doesn't see any potentially old data from integer divisions in kernel space. Do the same before VMRUN too, to protect host data from leaking into the guest too. Fixes: 77245f1c3c64 ("x86/CPU/AMD: Do not leak quotient data after a division by 0") Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/20230811213824.10025-1-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/entry-common.h | 1 + arch/x86/kernel/cpu/amd.c | 1 + arch/x86/kernel/traps.c | 2 -- arch/x86/kvm/svm/svm.c | 2 ++ 4 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 674ed46d3ced..11203a9fe0a8 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -92,6 +92,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { mds_user_clear_cpu_buffers(); + amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 239b302973d7..f240c978d85e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1295,3 +1295,4 @@ void noinstr amd_clear_divider(void) asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) :: "a" (0), "d" (0), "r" (1)); } +EXPORT_SYMBOL_GPL(amd_clear_divider); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 7e8795d8b0f1..c0a5a4f225d9 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -206,8 +206,6 @@ DEFINE_IDTENTRY(exc_divide_error) { do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, FPE_INTDIV, error_get_trap_addr(regs)); - - amd_clear_divider(); } DEFINE_IDTENTRY(exc_overflow) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index fdb6007f2eb8..a96f9a17e8b5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3947,6 +3947,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in guest_state_enter_irqoff(); + amd_clear_divider(); + if (sev_es_guest(vcpu->kvm)) __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); else From dae93ed961a8a315cefe64491e8573c5d9e3484e Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sun, 13 Aug 2023 12:39:34 +0200 Subject: [PATCH 0510/2093] x86/srso: Disable the mitigation on unaffected configurations commit e9fbc47b818b964ddff5df5b2d5c0f5f32f4a147 upstream. Skip the srso cmd line parsing which is not needed on Zen1/2 with SMT disabled and with the proper microcode applied (latter should be the case anyway) as those are not affected. Fixes: 5a15d8348881 ("x86/srso: Tie SBPB bit setting to microcode patch detection") Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230813104517.3346-1-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c2f8f98f20d5..971f28944037 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2399,8 +2399,10 @@ static void __init srso_select_mitigation(void) * IBPB microcode has been applied. */ if ((boot_cpu_data.x86 < 0x19) && - (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) + (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) { setup_force_cpu_cap(X86_FEATURE_SRSO_NO); + return; + } } if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { @@ -2686,6 +2688,9 @@ static ssize_t gds_show_state(char *buf) static ssize_t srso_show_state(char *buf) { + if (boot_cpu_has(X86_FEATURE_SRSO_NO)) + return sysfs_emit(buf, "Not affected\n"); + return sysfs_emit(buf, "%s%s\n", srso_strings[srso_mitigation], (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); From c8b056a3b4ebb33adbb873cab152ed499d1a1dcb Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Tue, 11 Jul 2023 11:19:51 +0200 Subject: [PATCH 0511/2093] x86/retpoline,kprobes: Fix position of thunk sections with CONFIG_LTO_CLANG commit 79cd2a11224eab86d6673fe8a11d2046ae9d2757 upstream. The linker script arch/x86/kernel/vmlinux.lds.S matches the thunk sections ".text.__x86.*" from arch/x86/lib/retpoline.S as follows: .text { [...] TEXT_TEXT [...] __indirect_thunk_start = .; *(.text.__x86.*) __indirect_thunk_end = .; [...] } Macro TEXT_TEXT references TEXT_MAIN which normally expands to only ".text". However, with CONFIG_LTO_CLANG, TEXT_MAIN becomes ".text .text.[0-9a-zA-Z_]*" which wrongly matches also the thunk sections. The output layout is then different than expected. For instance, the currently defined range [__indirect_thunk_start, __indirect_thunk_end] becomes empty. Prevent the problem by using ".." as the first separator, for example, ".text..__x86.indirect_thunk". This pattern is utilized by other explicit section names which start with one of the standard prefixes, such as ".text" or ".data", and that need to be individually selected in the linker script. [ nathan: Fix conflicts with SRSO and fold in fix issue brought up by Andrew Cooper in post-review: https://lore.kernel.org/20230803230323.1478869-1-andrew.cooper3@citrix.com ] Fixes: dc5723b02e52 ("kbuild: add support for Clang LTO") Signed-off-by: Petr Pavlu Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Nathan Chancellor Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230711091952.27944-2-petr.pavlu@suse.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/vmlinux.lds.S | 8 ++++---- arch/x86/lib/retpoline.S | 8 ++++---- tools/objtool/check.c | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 6b137c002778..78ccb5ec3c0e 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -134,7 +134,7 @@ SECTIONS KPROBES_TEXT ALIGN_ENTRY_TEXT_BEGIN #ifdef CONFIG_CPU_SRSO - *(.text.__x86.rethunk_untrain) + *(.text..__x86.rethunk_untrain) #endif ENTRY_TEXT @@ -145,7 +145,7 @@ SECTIONS * definition. */ . = srso_alias_untrain_ret | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); - *(.text.__x86.rethunk_safe) + *(.text..__x86.rethunk_safe) #endif ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT @@ -154,8 +154,8 @@ SECTIONS #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.indirect_thunk) - *(.text.__x86.return_thunk) + *(.text..__x86.indirect_thunk) + *(.text..__x86.return_thunk) __indirect_thunk_end = .; #endif } :text =0xcccc diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5a55ee2e80f0..65c5c44f006b 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -11,7 +11,7 @@ #include #include - .section .text.__x86.indirect_thunk + .section .text..__x86.indirect_thunk .macro RETPOLINE reg ANNOTATE_INTRA_FUNCTION_CALL @@ -91,7 +91,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) * As a result, srso_alias_safe_ret() becomes a safe return. */ #ifdef CONFIG_CPU_SRSO - .section .text.__x86.rethunk_untrain + .section .text..__x86.rethunk_untrain SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) UNWIND_HINT_FUNC @@ -102,7 +102,7 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) SYM_FUNC_END(srso_alias_untrain_ret) __EXPORT_THUNK(srso_alias_untrain_ret) - .section .text.__x86.rethunk_safe + .section .text..__x86.rethunk_safe #else /* dummy definition for alternatives */ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) @@ -120,7 +120,7 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) int3 SYM_FUNC_END(srso_alias_safe_ret) - .section .text.__x86.return_thunk + .section .text..__x86.return_thunk SYM_CODE_START(srso_alias_return_thunk) UNWIND_HINT_FUNC diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8ec97762b607..7c4e61cbefaa 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -379,7 +379,7 @@ static int decode_instructions(struct objtool_file *file) if (!strcmp(sec->name, ".noinstr.text") || !strcmp(sec->name, ".entry.text") || - !strncmp(sec->name, ".text.__x86.", 12)) + !strncmp(sec->name, ".text..__x86.", 13)) sec->noinstr = true; for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { From 4da4aae04b7f3d5ba4345a75f92de00a54644f11 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Aug 2023 13:59:21 +0200 Subject: [PATCH 0512/2093] objtool/x86: Fixup frame-pointer vs rethunk commit dbf46008775516f7f25c95b7760041c286299783 upstream. For stack-validation of a frame-pointer build, objtool validates that every CALL instruction is preceded by a frame-setup. The new SRSO return thunks violate this with their RSB stuffing trickery. Extend the __fentry__ exception to also cover the embedded_insn case used for this. This cures: vmlinux.o: warning: objtool: srso_untrain_ret+0xd: call without frame pointer save/setup Fixes: 4ae68b26c3ab ("objtool/x86: Fix SRSO mess") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20230816115921.GH980931@hirez.programming.kicks-ass.net Signed-off-by: Greg Kroah-Hartman --- tools/objtool/check.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 7c4e61cbefaa..913bd361c368 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2450,12 +2450,17 @@ static int decode_sections(struct objtool_file *file) return 0; } -static bool is_fentry_call(struct instruction *insn) +static bool is_special_call(struct instruction *insn) { - if (insn->type == INSN_CALL && - insn->call_dest && - insn->call_dest->fentry) - return true; + if (insn->type == INSN_CALL) { + struct symbol *dest = insn->call_dest; + + if (!dest) + return false; + + if (dest->fentry) + return true; + } return false; } @@ -3448,7 +3453,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (ret) return ret; - if (opts.stackval && func && !is_fentry_call(insn) && + if (opts.stackval && func && !is_special_call(insn) && !has_valid_stack_frame(&state)) { WARN_FUNC("call without frame pointer save/setup", sec, insn->offset); From 7487244912b13a918812b8f830e6a0dde269fdeb Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 15 Aug 2023 11:53:13 +0200 Subject: [PATCH 0513/2093] x86/srso: Correct the mitigation status when SMT is disabled commit 6405b72e8d17bd1875a56ae52d23ec3cd51b9d66 upstream. Specify how is SRSO mitigated when SMT is disabled. Also, correct the SMT check for that. Fixes: e9fbc47b818b ("x86/srso: Disable the mitigation on unaffected configurations") Suggested-by: Josh Poimboeuf Signed-off-by: Borislav Petkov (AMD) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20230814200813.p5czl47zssuej7nv@treble Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 971f28944037..3a893ab398a0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2398,8 +2398,7 @@ static void __init srso_select_mitigation(void) * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. */ - if ((boot_cpu_data.x86 < 0x19) && - (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) { + if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) { setup_force_cpu_cap(X86_FEATURE_SRSO_NO); return; } @@ -2689,7 +2688,7 @@ static ssize_t gds_show_state(char *buf) static ssize_t srso_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_SRSO_NO)) - return sysfs_emit(buf, "Not affected\n"); + return sysfs_emit(buf, "Mitigation: SMT disabled\n"); return sysfs_emit(buf, "%s%s\n", srso_strings[srso_mitigation], From cd363bb9548ec3208120bb3f55ff4ded2487d7fb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 26 Aug 2023 13:27:01 +0200 Subject: [PATCH 0514/2093] Linux 6.1.48 Link: https://lore.kernel.org/r/20230824141447.155846739@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: SeongJae Park Tested-by: Joel Fernandes (Google) Tested-by: Sudip Mukherjee Tested-by: Linux Kernel Functional Testing Tested-by: Jon Hunter Tested-by: Conor Dooley Tested-by: Takeshi Ogasawara Tested-by: Shuah Khan Tested-by: Bagas Sanjaya Tested-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 375efcfb91f8..8bb8dd199c55 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 47 +SUBLEVEL = 48 EXTRAVERSION = NAME = Curry Ramen From 77c576602dc7406781e0e9934bfe8dc9506d1bf4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Aug 2023 13:44:29 +0200 Subject: [PATCH 0515/2093] objtool/x86: Fix SRSO mess commit 4ae68b26c3ab5a82aa271e6e9fc9b1a06e1d6b40 upstream. Objtool --rethunk does two things: - it collects all (tail) call's of __x86_return_thunk and places them into .return_sites. These are typically compiler generated, but RET also emits this same. - it fudges the validation of the __x86_return_thunk symbol; because this symbol is inside another instruction, it can't actually find the instruction pointed to by the symbol offset and gets upset. Because these two things pertained to the same symbol, there was no pressing need to separate these two separate things. However, alas, along comes SRSO and more crazy things to deal with appeared. The SRSO patch itself added the following symbol names to identify as rethunk: 'srso_untrain_ret', 'srso_safe_ret' and '__ret' Where '__ret' is the old retbleed return thunk, 'srso_safe_ret' is a new similarly embedded return thunk, and 'srso_untrain_ret' is completely unrelated to anything the above does (and was only included because of that INT3 vs UD2 issue fixed previous). Clear things up by adding a second category for the embedded instruction thing. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230814121148.704502245@infradead.org Signed-off-by: Josh Poimboeuf Signed-off-by: Greg Kroah-Hartman --- tools/objtool/arch/x86/decode.c | 11 +++++++---- tools/objtool/check.c | 22 +++++++++++++++++++++- tools/objtool/include/objtool/arch.h | 1 + tools/objtool/include/objtool/elf.h | 1 + 4 files changed, 30 insertions(+), 5 deletions(-) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 29c35279c7ed..1ed49ab4e871 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -796,8 +796,11 @@ bool arch_is_retpoline(struct symbol *sym) bool arch_is_rethunk(struct symbol *sym) { - return !strcmp(sym->name, "__x86_return_thunk") || - !strcmp(sym->name, "srso_untrain_ret") || - !strcmp(sym->name, "srso_safe_ret") || - !strcmp(sym->name, "retbleed_return_thunk"); + return !strcmp(sym->name, "__x86_return_thunk"); +} + +bool arch_is_embedded_insn(struct symbol *sym) +{ + return !strcmp(sym->name, "retbleed_return_thunk") || + !strcmp(sym->name, "srso_safe_ret"); } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 913bd361c368..f8008ab31eef 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1164,16 +1164,33 @@ static int add_ignore_alternatives(struct objtool_file *file) return 0; } +/* + * Symbols that replace INSN_CALL_DYNAMIC, every (tail) call to such a symbol + * will be added to the .retpoline_sites section. + */ __weak bool arch_is_retpoline(struct symbol *sym) { return false; } +/* + * Symbols that replace INSN_RETURN, every (tail) call to such a symbol + * will be added to the .return_sites section. + */ __weak bool arch_is_rethunk(struct symbol *sym) { return false; } +/* + * Symbols that are embedded inside other instructions, because sometimes crazy + * code exists. These are mostly ignored for validation purposes. + */ +__weak bool arch_is_embedded_insn(struct symbol *sym) +{ + return false; +} + #define NEGATIVE_RELOC ((void *)-1L) static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) @@ -1437,7 +1454,7 @@ static int add_jump_destinations(struct objtool_file *file) * middle of another instruction. Objtool only * knows about the outer instruction. */ - if (sym && sym->return_thunk) { + if (sym && sym->embedded_insn) { add_return_call(file, insn, false); continue; } @@ -2327,6 +2344,9 @@ static int classify_symbols(struct objtool_file *file) if (arch_is_rethunk(func)) func->return_thunk = true; + if (arch_is_embedded_insn(func)) + func->embedded_insn = true; + if (!strcmp(func->name, "__fentry__")) func->fentry = true; diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index beb2f3aa94ff..861c0c60ac81 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -90,6 +90,7 @@ int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); bool arch_is_rethunk(struct symbol *sym); +bool arch_is_embedded_insn(struct symbol *sym); int arch_rewrite_retpolines(struct objtool_file *file); diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 16f4067b82ae..5d4a841fbd31 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -60,6 +60,7 @@ struct symbol { u8 return_thunk : 1; u8 fentry : 1; u8 profiling_func : 1; + u8 embedded_insn : 1; struct list_head pv_target; }; From 76e18e6709c84af8cdc95e5c09437e29ec337d1c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 26 Aug 2023 17:28:48 +0200 Subject: [PATCH 0516/2093] Revert "f2fs: don't reset unchangable mount option in f2fs_remount()" This reverts commit e2fb24ce37caeaecff08af4e9967c8462624312b which is commit 458c15dfbce62c35fefd9ca637b20a051309c9f1 upstream. Something is currently broken in the f2fs code, Guenter has reported boot problems with it for a few releases now, so revert the most recent f2fs changes in the hope to get this back to a working filesystem. Reported-by: Guenter Roeck Link: https://lore.kernel.org/r/b392e1a8-b987-4993-bd45-035db9415a6e@roeck-us.net Cc: Chao Yu Cc: Jaegeuk Kim Cc: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/super.c | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index ff47aad636e5..36bb1c969e8b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2040,22 +2040,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) return 0; } -static void default_options(struct f2fs_sb_info *sbi, bool remount) +static void default_options(struct f2fs_sb_info *sbi) { /* init some FS parameters */ - if (!remount) { - set_opt(sbi, READ_EXTENT_CACHE); - clear_opt(sbi, DISABLE_CHECKPOINT); - - if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) - set_opt(sbi, DISCARD); - - if (f2fs_sb_has_blkzoned(sbi)) - F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; - else - F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; - } - if (f2fs_sb_has_readonly(sbi)) F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE; else @@ -2078,16 +2065,23 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount) set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); + set_opt(sbi, READ_EXTENT_CACHE); set_opt(sbi, NOHEAP); + clear_opt(sbi, DISABLE_CHECKPOINT); set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; if (!f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) set_opt(sbi, FLUSH_MERGE); - if (f2fs_sb_has_blkzoned(sbi)) + if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) + set_opt(sbi, DISCARD); + if (f2fs_sb_has_blkzoned(sbi)) { F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; - else + F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; + } else { F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; + F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; + } #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -2259,7 +2253,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } - default_options(sbi, true); + default_options(sbi); /* parse mount options */ err = parse_options(sb, data, true); @@ -4156,7 +4150,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid, sizeof(raw_super->uuid)); - default_options(sbi, false); + default_options(sbi); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); if (data && !options) { From c5bd20577ff33c8ce2df9079df1c70e943652d56 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 26 Aug 2023 17:28:54 +0200 Subject: [PATCH 0517/2093] Revert "f2fs: fix to set flush_merge opt and show noflush_merge" This reverts commit 6ba0594a81f91d6fd8ca9bd4ad23aa1618635a0f which is commit 967eaad1fed5f6335ea97a47d45214744dc57925 upstream. Something is currently broken in the f2fs code, Guenter has reported boot problems with it for a few releases now, so revert the most recent f2fs changes in the hope to get this back to a working filesystem. Reported-by: Guenter Roeck Link: https://lore.kernel.org/r/b392e1a8-b987-4993-bd45-035db9415a6e@roeck-us.net Cc: Chao Yu Cc: Jaegeuk Kim Cc: Yangtao Li Cc: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/super.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 36bb1c969e8b..b6dad389fa14 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1347,12 +1347,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) return -EINVAL; } - if ((f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb)) && - test_opt(sbi, FLUSH_MERGE)) { - f2fs_err(sbi, "FLUSH_MERGE not compatible with readonly mode"); - return -EINVAL; - } - if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { f2fs_err(sbi, "Allow to mount readonly mode only"); return -EROFS; @@ -1939,10 +1933,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",inline_dentry"); else seq_puts(seq, ",noinline_dentry"); - if (test_opt(sbi, FLUSH_MERGE)) + if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE)) seq_puts(seq, ",flush_merge"); - else - seq_puts(seq, ",noflush_merge"); if (test_opt(sbi, NOBARRIER)) seq_puts(seq, ",nobarrier"); if (test_opt(sbi, FASTBOOT)) @@ -2071,8 +2063,7 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; - if (!f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) - set_opt(sbi, FLUSH_MERGE); + set_opt(sbi, FLUSH_MERGE); if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi)) { From db05f8449bb3529aa65753d30ed2df7720d4f36a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 26 Aug 2023 17:29:00 +0200 Subject: [PATCH 0518/2093] Revert "f2fs: fix to do sanity check on direct node in truncate_dnode()" This reverts commit a78a8bcdc26de5ef3a0ee27c9c6c512e54a6051c which is commit a6ec83786ab9f13f25fb18166dee908845713a95 upstream. Something is currently broken in the f2fs code, Guenter has reported boot problems with it for a few releases now, so revert the most recent f2fs changes in the hope to get this back to a working filesystem. Reported-by: Guenter Roeck Link: https://lore.kernel.org/r/b392e1a8-b987-4993-bd45-035db9415a6e@roeck-us.net Cc: Chao Yu Cc: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/f2fs.h | 1 + fs/f2fs/file.c | 5 +++++ fs/f2fs/node.c | 14 ++------------ include/linux/f2fs_fs.h | 1 - 4 files changed, 8 insertions(+), 13 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 78f39a78de29..4d1e48c676fa 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3431,6 +3431,7 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr) * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); +void f2fs_truncate_data_blocks(struct dnode_of_data *dn); int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3ce6da4fac9c..7b94f047cbf7 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -628,6 +628,11 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) dn->ofs_in_node, nr_free); } +void f2fs_truncate_data_blocks(struct dnode_of_data *dn) +{ + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); +} + static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9fe502485930..a010b4bc36d2 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -923,7 +923,6 @@ static int truncate_node(struct dnode_of_data *dn) static int truncate_dnode(struct dnode_of_data *dn) { - struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *page; int err; @@ -931,25 +930,16 @@ static int truncate_dnode(struct dnode_of_data *dn) return 1; /* get direct node */ - page = f2fs_get_node_page(sbi, dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); - if (IS_INODE(page) || ino_of_node(page) != dn->inode->i_ino) { - f2fs_err(sbi, "incorrect node reference, ino: %lu, nid: %u, ino_of_node: %u", - dn->inode->i_ino, dn->nid, ino_of_node(page)); - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_handle_error(sbi, ERROR_INVALID_NODE_REFERENCE); - f2fs_put_page(page, 1); - return -EFSCORRUPTED; - } - /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; - f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); + f2fs_truncate_data_blocks(dn); err = truncate_node(dn); if (err) { f2fs_put_page(page, 1); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 77055b239165..ee0d75d9a302 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -104,7 +104,6 @@ enum f2fs_error { ERROR_INCONSISTENT_SIT, ERROR_CORRUPTED_VERITY_XATTR, ERROR_CORRUPTED_XATTR, - ERROR_INVALID_NODE_REFERENCE, ERROR_MAX, }; From 024f76bca9d0e29513fa99e1cd0f86bfa841743b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 27 Aug 2023 21:01:32 +0200 Subject: [PATCH 0519/2093] Linux 6.1.49 Link: https://lore.kernel.org/r/20230826154625.450325166@linuxfoundation.org Tested-by: Joel Fernandes (Google) Tested-by: Takeshi Ogasawara Tested-by: Sudip Mukherjee Tested-by: Bagas Sanjaya Tested-by: Guenter Roeck Tested-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 8bb8dd199c55..61ebd54aba89 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 48 +SUBLEVEL = 49 EXTRAVERSION = NAME = Curry Ramen From 4a289d123f62f7fdf33e7ce02c4c4c0d3b708a2b Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Tue, 25 Jul 2023 14:58:58 +0300 Subject: [PATCH 0520/2093] NFSv4.2: fix error handling in nfs42_proc_getxattr [ Upstream commit 4e3733fd2b0f677faae21cf838a43faf317986d3 ] There is a slight issue with error handling code inside nfs42_proc_getxattr(). If page allocating loop fails then we free the failing page array element which is NULL but __free_page() can't deal with NULL args. Found by Linux Verification Center (linuxtesting.org). Fixes: a1f26739ccdc ("NFSv4.2: improve page handling for GETXATTR") Signed-off-by: Fedor Pchelkin Reviewed-by: Benjamin Coddington Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs42proc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ecb428512fe1..7c33bba179d2 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1359,7 +1359,6 @@ ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, for (i = 0; i < np; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) { - np = i + 1; err = -ENOMEM; goto out; } @@ -1383,8 +1382,8 @@ ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name, } while (exception.retry); out: - while (--np >= 0) - __free_page(pages[np]); + while (--i >= 0) + __free_page(pages[i]); kfree(pages); return err; From d9aac9cdd6e2b4cf21dc91ad0803a7df2b177bac Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Tue, 25 Jul 2023 14:59:30 +0300 Subject: [PATCH 0521/2093] NFSv4: fix out path in __nfs4_get_acl_uncached [ Upstream commit f4e89f1a6dab4c063fc1e823cc9dddc408ff40cf ] Another highly rare error case when a page allocating loop (inside __nfs4_get_acl_uncached, this time) is not properly unwound on error. Since pages array is allocated being uninitialized, need to free only lower array indices. NULL checks were useful before commit 62a1573fcf84 ("NFSv4 fix acl retrieval over krb5i/krb5p mounts") when the array had been initialized to zero on stack. Found by Linux Verification Center (linuxtesting.org). Fixes: 62a1573fcf84 ("NFSv4 fix acl retrieval over krb5i/krb5p mounts") Signed-off-by: Fedor Pchelkin Reviewed-by: Benjamin Coddington Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 177cb7b089b9..d67383665e9b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5995,9 +5995,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, out_ok: ret = res.acl_len; out_free: - for (i = 0; i < npages; i++) - if (pages[i]) - __free_page(pages[i]); + while (--i >= 0) + __free_page(pages[i]); if (res.acl_scratch) __free_page(res.acl_scratch); kfree(pages); From 26ea8668b8aae5f57068c2f442a28a8e420a759b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 3 Jul 2023 14:18:29 -0400 Subject: [PATCH 0522/2093] xprtrdma: Remap Receive buffers after a reconnect [ Upstream commit 895cedc1791916e8a98864f12b656702fad0bb67 ] On server-initiated disconnect, rpcrdma_xprt_disconnect() was DMA- unmapping the Receive buffers, but rpcrdma_post_recvs() neglected to remap them after a new connection had been established. The result was immediate failure of the new connection with the Receives flushing with LOCAL_PROT_ERR. Fixes: 671c450b6fe0 ("xprtrdma: Fix oops in Receive handler after device removal") Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- net/sunrpc/xprtrdma/verbs.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b098fde373ab..28c0771c4e8c 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -935,9 +935,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, if (!rep->rr_rdmabuf) goto out_free; - if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) - goto out_free_regbuf; - rep->rr_cid.ci_completion_id = atomic_inc_return(&r_xprt->rx_ep->re_completion_ids); @@ -956,8 +953,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, spin_unlock(&buf->rb_lock); return rep; -out_free_regbuf: - rpcrdma_regbuf_free(rep->rr_rdmabuf); out_free: kfree(rep); out: @@ -1363,6 +1358,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) break; + if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) { + rpcrdma_rep_put(buf, rep); + break; + } rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id; trace_xprtrdma_post_recv(rep); From cd1f889c99eee5a6fae671962a63bc89e68d7837 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 11 Jan 2023 16:41:02 +0100 Subject: [PATCH 0523/2093] drm/ast: Use drm_aperture_remove_conflicting_pci_framebuffers [ Upstream commit c1ebead36099deb85384f6fb262fe619a04cee73 ] It's just open coded and matches. Note that Thomas said that his version apparently failed for some reason, but hey maybe we should try again. Signed-off-by: Daniel Vetter Cc: Dave Airlie Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Tested-by: Thomas Zimmmermann Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230111154112.90575-1-daniel.vetter@ffwll.ch Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/gpu/drm/ast/ast_drv.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index b9392f31e629..800471f2a203 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -89,27 +89,13 @@ static const struct pci_device_id ast_pciidlist[] = { MODULE_DEVICE_TABLE(pci, ast_pciidlist); -static int ast_remove_conflicting_framebuffers(struct pci_dev *pdev) -{ - bool primary = false; - resource_size_t base, size; - - base = pci_resource_start(pdev, 0); - size = pci_resource_len(pdev, 0); -#ifdef CONFIG_X86 - primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; -#endif - - return drm_aperture_remove_conflicting_framebuffers(base, size, primary, &ast_driver); -} - static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct ast_private *ast; struct drm_device *dev; int ret; - ret = ast_remove_conflicting_framebuffers(pdev); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &ast_driver); if (ret) return ret; From 6db53af15444e7022640d7b8d5e7531d94e27a43 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 11 Jan 2023 16:41:08 +0100 Subject: [PATCH 0524/2093] fbdev/radeon: use pci aperture helpers [ Upstream commit 9b539c4d1b921bc9c8c578d4d50f0a7e7874d384 ] It's not exactly the same since the open coded version doesn't set primary correctly. But that's a bugfix, so shouldn't hurt really. Signed-off-by: Daniel Vetter Cc: Benjamin Herrenschmidt Cc: linux-fbdev@vger.kernel.org Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230111154112.90575-7-daniel.vetter@ffwll.ch Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/video/fbdev/aty/radeon_base.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 8b28c9bddd97..50c384ce2883 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -2238,14 +2238,6 @@ static const struct bin_attribute edid2_attr = { .read = radeon_show_edid2, }; -static int radeon_kick_out_firmware_fb(struct pci_dev *pdev) -{ - resource_size_t base = pci_resource_start(pdev, 0); - resource_size_t size = pci_resource_len(pdev, 0); - - return aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); -} - static int radeonfb_pci_register(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2296,7 +2288,7 @@ static int radeonfb_pci_register(struct pci_dev *pdev, rinfo->fb_base_phys = pci_resource_start (pdev, 0); rinfo->mmio_base_phys = pci_resource_start (pdev, 2); - ret = radeon_kick_out_firmware_fb(pdev); + ret = aperture_remove_conflicting_pci_devices(pdev, KBUILD_MODNAME); if (ret) goto err_release_fb; From cccfcbb9e51af026529618e3bdc09b6beacac919 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 6 Apr 2023 15:21:01 +0200 Subject: [PATCH 0525/2093] drm/gma500: Use drm_aperture_remove_conflicting_pci_framebuffers [ Upstream commit 80e993988b97fe794f3ec2be6db05fe30f9353c3 ] This one nukes all framebuffers, which is a bit much. In reality gma500 is igpu and never shipped with anything discrete, so there should not be any difference. v2: Unfortunately the framebuffer sits outside of the pci bars for gma500, and so only using the pci helpers won't be enough. Otoh if we only use non-pci helper, then we don't get the vga handling, and subsequent refactoring to untangle these special cases won't work. It's not pretty, but the simplest fix (since gma500 really is the only quirky pci driver like this we have) is to just have both calls. v4: - fix Daniel's S-o-b address v5: - add back an S-o-b tag with Daniel's Intel address Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Thomas Zimmermann Cc: Patrik Jakobsson Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-2-tzimmermann@suse.de Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/gpu/drm/gma500/psb_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index cd9c73f5a64a..000e6704e3c7 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -424,12 +424,17 @@ static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* * We cannot yet easily find the framebuffer's location in memory. So - * remove all framebuffers here. + * remove all framebuffers here. Note that we still want the pci special + * handling to kick out vgacon. * * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we * might be able to read the framebuffer range from the device. */ - ret = drm_aperture_remove_framebuffers(true, &driver); + ret = drm_aperture_remove_framebuffers(false, &driver); + if (ret) + return ret; + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); if (ret) return ret; From 437e99f2a1e933348c4cedb2c7ce6f0ad81b935e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 6 Apr 2023 15:21:03 +0200 Subject: [PATCH 0526/2093] drm/aperture: Remove primary argument [ Upstream commit 62aeaeaa1b267c5149abee6b45967a5df3feed58 ] Only really pci devices have a business setting this - it's for figuring out whether the legacy vga stuff should be nuked too. And with the preceding two patches those are all using the pci version of this. Which means for all other callers primary == false and we can remove it now. v2: - Reorder to avoid compile fail (Thomas) - Include gma500, which retained it's called to the non-pci version. v4: - fix Daniel's S-o-b address v5: - add back an S-o-b tag with Daniel's Intel address Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Thomas Zimmermann Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Deepak Rawat Cc: Neil Armstrong Cc: Kevin Hilman Cc: Jerome Brunet Cc: Martin Blumenstingl Cc: Thierry Reding Cc: Jonathan Hunter Cc: Emma Anholt Cc: Helge Deller Cc: David Airlie Cc: Daniel Vetter Cc: linux-hyperv@vger.kernel.org Cc: linux-amlogic@lists.infradead.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-tegra@vger.kernel.org Cc: linux-fbdev@vger.kernel.org Acked-by: Martin Blumenstingl Acked-by: Thierry Reding Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-4-tzimmermann@suse.de Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/gpu/drm/arm/hdlcd_drv.c | 2 +- drivers/gpu/drm/armada/armada_drv.c | 2 +- drivers/gpu/drm/drm_aperture.c | 11 +++-------- drivers/gpu/drm/gma500/psb_drv.c | 2 +- drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 1 - drivers/gpu/drm/meson/meson_drv.c | 2 +- drivers/gpu/drm/msm/msm_fbdev.c | 2 +- drivers/gpu/drm/rockchip/rockchip_drm_drv.c | 2 +- drivers/gpu/drm/stm/drv.c | 2 +- drivers/gpu/drm/sun4i/sun4i_drv.c | 2 +- drivers/gpu/drm/tegra/drm.c | 2 +- drivers/gpu/drm/vc4/vc4_drv.c | 2 +- include/drm/drm_aperture.h | 7 +++---- 13 files changed, 16 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index a032003c340c..d6ea47873627 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -290,7 +290,7 @@ static int hdlcd_drm_bind(struct device *dev) */ if (hdlcd_read(hdlcd, HDLCD_REG_COMMAND)) { hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0); - drm_aperture_remove_framebuffers(false, &hdlcd_driver); + drm_aperture_remove_framebuffers(&hdlcd_driver); } drm_mode_config_reset(drm); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 142668cd6d7c..688ba358f531 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -95,7 +95,7 @@ static int armada_drm_bind(struct device *dev) } /* Remove early framebuffers */ - ret = drm_aperture_remove_framebuffers(false, &armada_drm_driver); + ret = drm_aperture_remove_framebuffers(&armada_drm_driver); if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c index 3b8fdeeafd53..697cffbfd603 100644 --- a/drivers/gpu/drm/drm_aperture.c +++ b/drivers/gpu/drm/drm_aperture.c @@ -32,17 +32,13 @@ * * static int remove_conflicting_framebuffers(struct pci_dev *pdev) * { - * bool primary = false; * resource_size_t base, size; * int ret; * * base = pci_resource_start(pdev, 0); * size = pci_resource_len(pdev, 0); - * #ifdef CONFIG_X86 - * primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; - * #endif * - * return drm_aperture_remove_conflicting_framebuffers(base, size, primary, + * return drm_aperture_remove_conflicting_framebuffers(base, size, * &example_driver); * } * @@ -161,7 +157,6 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * drm_aperture_remove_conflicting_framebuffers - remove existing framebuffers in the given range * @base: the aperture's base address in physical memory * @size: aperture size in bytes - * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes graphics device drivers which use the memory range described by @@ -171,9 +166,9 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * 0 on success, or a negative errno code otherwise */ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const struct drm_driver *req_driver) + const struct drm_driver *req_driver) { - return aperture_remove_conflicting_devices(base, size, primary, req_driver->name); + return aperture_remove_conflicting_devices(base, size, false, req_driver->name); } EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers); diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 000e6704e3c7..738eb558a97e 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -430,7 +430,7 @@ static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we * might be able to read the framebuffer range from the device. */ - ret = drm_aperture_remove_framebuffers(false, &driver); + ret = drm_aperture_remove_framebuffers(&driver); if (ret) return ret; diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index ca127ff797f7..29ee0814bccc 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -74,7 +74,6 @@ static int hyperv_setup_vram(struct hyperv_drm_device *hv, drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, screen_info.lfb_size, - false, &hyperv_driver); hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index eea433ade79d..119544d88b58 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -285,7 +285,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) * Remove early framebuffers (ie. simplefb). The framebuffer can be * located anywhere in RAM */ - ret = drm_aperture_remove_framebuffers(false, &meson_driver); + ret = drm_aperture_remove_framebuffers(&meson_driver); if (ret) goto free_drm; diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index 46168eccfac4..d4a9b501e1bc 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -157,7 +157,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev) } /* the fw fb could be anywhere in memory */ - ret = drm_aperture_remove_framebuffers(false, dev->driver); + ret = drm_aperture_remove_framebuffers(dev->driver); if (ret) goto fini; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 813f9f8c8698..8e12053a220b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -140,7 +140,7 @@ static int rockchip_drm_bind(struct device *dev) int ret; /* Remove existing drivers that may own the framebuffer memory. */ - ret = drm_aperture_remove_framebuffers(false, &rockchip_drm_driver); + ret = drm_aperture_remove_framebuffers(&rockchip_drm_driver); if (ret) { DRM_DEV_ERROR(dev, "Failed to remove existing framebuffers - %d.\n", diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index d7914f5122df..0a09a85ac9d6 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -185,7 +185,7 @@ static int stm_drm_platform_probe(struct platform_device *pdev) DRM_DEBUG("%s\n", __func__); - ret = drm_aperture_remove_framebuffers(false, &drv_driver); + ret = drm_aperture_remove_framebuffers(&drv_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 7910c5853f0a..5c483bbccbbb 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -98,7 +98,7 @@ static int sun4i_drv_bind(struct device *dev) goto unbind_all; /* Remove early framebuffers (ie. simplefb) */ - ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver); + ret = drm_aperture_remove_framebuffers(&sun4i_drv_driver); if (ret) goto unbind_all; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index a1f909dac89a..5fc55b9777cb 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1252,7 +1252,7 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(false, &tegra_drm_driver); + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); if (err < 0) goto hub; diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 8c329c071c62..b6384a5dfdbc 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -351,7 +351,7 @@ static int vc4_drm_bind(struct device *dev) return -EPROBE_DEFER; } - ret = drm_aperture_remove_framebuffers(false, driver); + ret = drm_aperture_remove_framebuffers(driver); if (ret) return ret; diff --git a/include/drm/drm_aperture.h b/include/drm/drm_aperture.h index 7096703c3949..cbe33b49fd5d 100644 --- a/include/drm/drm_aperture.h +++ b/include/drm/drm_aperture.h @@ -13,14 +13,13 @@ int devm_aperture_acquire_from_firmware(struct drm_device *dev, resource_size_t resource_size_t size); int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const struct drm_driver *req_driver); + const struct drm_driver *req_driver); int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const struct drm_driver *req_driver); /** * drm_aperture_remove_framebuffers - remove all existing framebuffers - * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes all graphics device drivers. Use this function on systems @@ -30,9 +29,9 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, * 0 on success, or a negative errno code otherwise */ static inline int -drm_aperture_remove_framebuffers(bool primary, const struct drm_driver *req_driver) +drm_aperture_remove_framebuffers(const struct drm_driver *req_driver) { - return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary, + return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, req_driver); } From 4aad3b82b9de7c4ffccb02f87d0c6903569333c9 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 6 Apr 2023 15:21:04 +0200 Subject: [PATCH 0527/2093] video/aperture: Only kick vgacon when the pdev is decoding vga [ Upstream commit 7450cd235b45d43ee6f3c235f89e92623458175d ] Otherwise it's a bit silly, and we might throw out the driver for the screen the user is actually looking at. I haven't found a bug report for this case yet, but we did get bug reports for the analog case where we're throwing out the efifb driver. v2: Flip the check around to make it clear it's a special case for kicking out the vgacon driver only (Thomas) v4: - fixes to commit message - fix Daniel's S-o-b address v5: - add back an S-o-b tag with Daniel's Intel address Link: https://bugzilla.kernel.org/show_bug.cgi?id=216303 Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Thomas Zimmermann Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-5-tzimmermann@suse.de Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/video/aperture.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 5c94abdb1ad6..7ea18086e659 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -344,13 +344,15 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na aperture_detach_devices(base, size); } - /* - * WARNING: Apparently we must kick fbdev drivers before vgacon, - * otherwise the vga fbdev driver falls over. - */ - ret = vga_remove_vgacon(pdev); - if (ret) - return ret; + if (primary) { + /* + * WARNING: Apparently we must kick fbdev drivers before vgacon, + * otherwise the vga fbdev driver falls over. + */ + ret = vga_remove_vgacon(pdev); + if (ret) + return ret; + } return 0; From 28916927b7626ed3c44d902eafbf9d00691266e1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 6 Apr 2023 15:21:05 +0200 Subject: [PATCH 0528/2093] video/aperture: Move vga handling to pci function [ Upstream commit f1d599d315fb7b7343cddaf365e671aaa8453aca ] A few reasons for this: - It's really the only one where this matters. I tried looking around, and I didn't find any non-pci vga-compatible controllers for x86 (since that's the only platform where we had this until a few patches ago), where a driver participating in the aperture claim dance would interfere. - I also don't expect that any future bus anytime soon will not just look like pci towards the OS, that's been the case for like 25+ years by now for practically everything (even non non-x86). - Also it's a bit funny if we have one part of the vga removal in the pci function, and the other in the generic one. v2: Rebase. v4: - fix Daniel's S-o-b address v5: - add back an S-o-b tag with Daniel's Intel address Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Thomas Zimmermann Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-6-tzimmermann@suse.de Stable-dep-of: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Signed-off-by: Sasha Levin --- drivers/video/aperture.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 7ea18086e659..3e4a1f55f51b 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -298,14 +298,6 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si aperture_detach_devices(base, size); - /* - * If this is the primary adapter, there could be a VGA device - * that consumes the VGA framebuffer I/O range. Remove this device - * as well. - */ - if (primary) - aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); - return 0; } EXPORT_SYMBOL(aperture_remove_conflicting_devices); @@ -345,6 +337,13 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na } if (primary) { + /* + * If this is the primary adapter, there could be a VGA device + * that consumes the VGA framebuffer I/O range. Remove this + * device as well. + */ + aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); + /* * WARNING: Apparently we must kick fbdev drivers before vgacon, * otherwise the vga fbdev driver falls over. From 3e4d038da33e75765584fa54d6cc1a327535af65 Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Mon, 24 Apr 2023 21:15:57 +0200 Subject: [PATCH 0529/2093] PCI: acpiphp: Reassign resources on bridge if necessary [ Upstream commit 40613da52b13fb21c5566f10b287e0ca8c12c4e9 ] When using ACPI PCI hotplug, hotplugging a device with large BARs may fail if bridge windows programmed by firmware are not large enough. Reproducer: $ qemu-kvm -monitor stdio -M q35 -m 4G \ -global ICH9-LPC.acpi-pci-hotplug-with-bridge-support=on \ -device id=rp1,pcie-root-port,bus=pcie.0,chassis=4 \ disk_image wait till linux guest boots, then hotplug device: (qemu) device_add qxl,bus=rp1 hotplug on guest side fails with: pci 0000:01:00.0: [1b36:0100] type 00 class 0x038000 pci 0000:01:00.0: reg 0x10: [mem 0x00000000-0x03ffffff] pci 0000:01:00.0: reg 0x14: [mem 0x00000000-0x03ffffff] pci 0000:01:00.0: reg 0x18: [mem 0x00000000-0x00001fff] pci 0000:01:00.0: reg 0x1c: [io 0x0000-0x001f] pci 0000:01:00.0: BAR 0: no space for [mem size 0x04000000] pci 0000:01:00.0: BAR 0: failed to assign [mem size 0x04000000] pci 0000:01:00.0: BAR 1: no space for [mem size 0x04000000] pci 0000:01:00.0: BAR 1: failed to assign [mem size 0x04000000] pci 0000:01:00.0: BAR 2: assigned [mem 0xfe800000-0xfe801fff] pci 0000:01:00.0: BAR 3: assigned [io 0x1000-0x101f] qxl 0000:01:00.0: enabling device (0000 -> 0003) Unable to create vram_mapping qxl: probe of 0000:01:00.0 failed with error -12 However when using native PCIe hotplug '-global ICH9-LPC.acpi-pci-hotplug-with-bridge-support=off' it works fine, since kernel attempts to reassign unused resources. Use the same machinery as native PCIe hotplug to (re)assign resources. Link: https://lore.kernel.org/r/20230424191557.2464760-1-imammedo@redhat.com Signed-off-by: Igor Mammedov Signed-off-by: Bjorn Helgaas Acked-by: Michael S. Tsirkin Acked-by: Rafael J. Wysocki Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin --- drivers/pci/hotplug/acpiphp_glue.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 6efa3d8db9a5..393f341d9d76 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -490,7 +490,6 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) acpiphp_native_scan_bridge(dev); } } else { - LIST_HEAD(add_list); int max, pass; acpiphp_rescan_slot(slot); @@ -504,12 +503,10 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); - __pci_bus_size_bridges(dev->subordinate, - &add_list); } } } - __pci_bus_assign_resources(bus, &add_list, NULL); + pci_assign_unassigned_bridge_resources(bus->self); } acpiphp_sanitize_bus(bus); From 92c568c82ee74cb8343620d14190d9c1169e9f71 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:44 +0100 Subject: [PATCH 0530/2093] MIPS: cpu-features: Enable octeon_cache by cpu_type [ Upstream commit f641519409a73403ee6612b8648b95a688ab85c2 ] cpu_has_octeon_cache was tied to 0 for generic cpu-features, whith this generic kernel built for octeon CPU won't boot. Just enable this flag by cpu_type. It won't hurt orther platforms because compiler will eliminate the code path on other processors. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Stable-dep-of: 5487a7b60695 ("MIPS: cpu-features: Use boot_cpu_type for CPU type based features") Signed-off-by: Sasha Levin --- arch/mips/include/asm/cpu-features.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index c0983130a44c..53c8551ec89b 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -121,7 +121,24 @@ #define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_octeon_cache -#define cpu_has_octeon_cache 0 +#define cpu_has_octeon_cache \ +({ \ + int __res; \ + \ + switch (current_cpu_type()) { \ + case CPU_CAVIUM_OCTEON: \ + case CPU_CAVIUM_OCTEON_PLUS: \ + case CPU_CAVIUM_OCTEON2: \ + case CPU_CAVIUM_OCTEON3: \ + __res = 1; \ + break; \ + \ + default: \ + __res = 0; \ + } \ + \ + __res; \ +}) #endif /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work. */ #ifndef cpu_has_fpu From 1fa68a78109840ccb3d1b69ea0ba3cd9b30ed17f Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Wed, 7 Jun 2023 13:51:22 +0800 Subject: [PATCH 0531/2093] MIPS: cpu-features: Use boot_cpu_type for CPU type based features [ Upstream commit 5487a7b60695a92cf998350e4beac17144c91fcd ] Some CPU feature macros were using current_cpu_type to mark feature availability. However current_cpu_type will use smp_processor_id, which is prohibited under preemptable context. Since those features are all uniform on all CPUs in a SMP system, use boot_cpu_type instead of current_cpu_type to fix preemptable kernel. Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/include/asm/cpu-features.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 53c8551ec89b..e0a4da4cfd8b 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -125,7 +125,7 @@ ({ \ int __res; \ \ - switch (current_cpu_type()) { \ + switch (boot_cpu_type()) { \ case CPU_CAVIUM_OCTEON: \ case CPU_CAVIUM_OCTEON_PLUS: \ case CPU_CAVIUM_OCTEON2: \ @@ -368,7 +368,7 @@ ({ \ int __res; \ \ - switch (current_cpu_type()) { \ + switch (boot_cpu_type()) { \ case CPU_M14KC: \ case CPU_74K: \ case CPU_1074K: \ From 8168c96c24ecfe0265c295aa4d969b4b650f00d3 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Tue, 6 Jun 2023 21:59:24 +0800 Subject: [PATCH 0532/2093] jbd2: remove t_checkpoint_io_list [ Upstream commit be22255360f80d3af789daad00025171a65424a5 ] Since t_checkpoint_io_list was stop using in jbd2_log_do_checkpoint() now, it's time to remove the whole t_checkpoint_io_list logic. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230606135928.434610-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Stable-dep-of: 46f881b5b175 ("jbd2: fix a race when checking checkpoint buffer busy") Signed-off-by: Sasha Levin --- fs/jbd2/checkpoint.c | 42 ++---------------------------------------- fs/jbd2/commit.c | 3 +-- include/linux/jbd2.h | 6 ------ 3 files changed, 3 insertions(+), 48 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index c4e0da6db719..723b4eb11282 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -27,7 +27,7 @@ * * Called with j_list_lock held. */ -static inline void __buffer_unlink_first(struct journal_head *jh) +static inline void __buffer_unlink(struct journal_head *jh) { transaction_t *transaction = jh->b_cp_transaction; @@ -40,23 +40,6 @@ static inline void __buffer_unlink_first(struct journal_head *jh) } } -/* - * Unlink a buffer from a transaction checkpoint(io) list. - * - * Called with j_list_lock held. - */ -static inline void __buffer_unlink(struct journal_head *jh) -{ - transaction_t *transaction = jh->b_cp_transaction; - - __buffer_unlink_first(jh); - if (transaction->t_checkpoint_io_list == jh) { - transaction->t_checkpoint_io_list = jh->b_cpnext; - if (transaction->t_checkpoint_io_list == jh) - transaction->t_checkpoint_io_list = NULL; - } -} - /* * Check a checkpoint buffer could be release or not. * @@ -505,15 +488,6 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, break; if (need_resched() || spin_needbreak(&journal->j_list_lock)) break; - if (released) - continue; - - nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list, - nr_to_scan, &released); - if (*nr_to_scan == 0) - break; - if (need_resched() || spin_needbreak(&journal->j_list_lock)) - break; } while (transaction != last_transaction); if (transaction != last_transaction) { @@ -568,17 +542,6 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) */ if (need_resched()) return; - if (ret) - continue; - /* - * It is essential that we are as careful as in the case of - * t_checkpoint_list with removing the buffer from the list as - * we can possibly see not yet submitted buffers on io_list - */ - ret = journal_clean_one_cp_list(transaction-> - t_checkpoint_io_list, destroy); - if (need_resched()) - return; /* * Stop scanning if we couldn't free the transaction. This * avoids pointless scanning of transactions which still @@ -663,7 +626,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) jbd2_journal_put_journal_head(jh); /* Is this transaction empty? */ - if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list) + if (transaction->t_checkpoint_list) return 0; /* @@ -755,7 +718,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact J_ASSERT(transaction->t_forget == NULL); J_ASSERT(transaction->t_shadow_list == NULL); J_ASSERT(transaction->t_checkpoint_list == NULL); - J_ASSERT(transaction->t_checkpoint_io_list == NULL); J_ASSERT(atomic_read(&transaction->t_updates) == 0); J_ASSERT(journal->j_committing_transaction != transaction); J_ASSERT(journal->j_running_transaction != transaction); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 885a7a6cc53e..f1d9db6686e3 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -1171,8 +1171,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) spin_lock(&journal->j_list_lock); commit_transaction->t_state = T_FINISHED; /* Check if the transaction can be dropped now that we are finished */ - if (commit_transaction->t_checkpoint_list == NULL && - commit_transaction->t_checkpoint_io_list == NULL) { + if (commit_transaction->t_checkpoint_list == NULL) { __jbd2_journal_drop_transaction(journal, commit_transaction); jbd2_journal_free_transaction(commit_transaction); } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0b7242370b56..67912fe08fbb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -622,12 +622,6 @@ struct transaction_s */ struct journal_head *t_checkpoint_list; - /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and From 5fda50e262e65bd553ff777c4b280afd1495a18b Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Tue, 6 Jun 2023 21:59:25 +0800 Subject: [PATCH 0533/2093] jbd2: remove journal_clean_one_cp_list() [ Upstream commit b98dba273a0e47dbfade89c9af73c5b012a4eabb ] journal_clean_one_cp_list() and journal_shrink_one_cp_list() are almost the same, so merge them into journal_shrink_one_cp_list(), remove the nr_to_scan parameter, always scan and try to free the whole checkpoint list. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230606135928.434610-4-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Stable-dep-of: 46f881b5b175 ("jbd2: fix a race when checking checkpoint buffer busy") Signed-off-by: Sasha Levin --- fs/jbd2/checkpoint.c | 85 ++++++++++--------------------------- include/trace/events/jbd2.h | 12 ++---- 2 files changed, 26 insertions(+), 71 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 723b4eb11282..42b34cab64fb 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -350,19 +350,24 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* Checkpoint list management */ /* - * journal_clean_one_cp_list + * journal_shrink_one_cp_list * - * Find all the written-back checkpoint buffers in the given list and - * release them. If 'destroy' is set, clean all buffers unconditionally. + * Find all the written-back checkpoint buffers in the given list + * and try to release them. If the whole transaction is released, set + * the 'released' parameter. Return the number of released checkpointed + * buffers. * * Called with j_list_lock held. - * Returns 1 if we freed the transaction, 0 otherwise. */ -static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) +static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, + bool destroy, bool *released) { struct journal_head *last_jh; struct journal_head *next_jh = jh; + unsigned long nr_freed = 0; + int ret; + *released = false; if (!jh) return 0; @@ -372,52 +377,6 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) next_jh = jh->b_cpnext; if (!destroy && __cp_buffer_busy(jh)) - return 0; - - if (__jbd2_journal_remove_checkpoint(jh)) - return 1; - /* - * This function only frees up some memory - * if possible so we dont have an obligation - * to finish processing. Bail out if preemption - * requested: - */ - if (need_resched()) - return 0; - } while (jh != last_jh); - - return 0; -} - -/* - * journal_shrink_one_cp_list - * - * Find 'nr_to_scan' written-back checkpoint buffers in the given list - * and try to release them. If the whole transaction is released, set - * the 'released' parameter. Return the number of released checkpointed - * buffers. - * - * Called with j_list_lock held. - */ -static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, - unsigned long *nr_to_scan, - bool *released) -{ - struct journal_head *last_jh; - struct journal_head *next_jh = jh; - unsigned long nr_freed = 0; - int ret; - - if (!jh || *nr_to_scan == 0) - return 0; - - last_jh = jh->b_cpprev; - do { - jh = next_jh; - next_jh = jh->b_cpnext; - - (*nr_to_scan)--; - if (__cp_buffer_busy(jh)) continue; nr_freed++; @@ -429,7 +388,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, if (need_resched()) break; - } while (jh != last_jh && *nr_to_scan); + } while (jh != last_jh); return nr_freed; } @@ -447,11 +406,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan) { transaction_t *transaction, *last_transaction, *next_transaction; - bool released; + bool __maybe_unused released; tid_t first_tid = 0, last_tid = 0, next_tid = 0; tid_t tid = 0; unsigned long nr_freed = 0; - unsigned long nr_scanned = *nr_to_scan; + unsigned long freed; again: spin_lock(&journal->j_list_lock); @@ -480,10 +439,11 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, transaction = next_transaction; next_transaction = transaction->t_cpnext; tid = transaction->t_tid; - released = false; - nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list, - nr_to_scan, &released); + freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, + false, &released); + nr_freed += freed; + (*nr_to_scan) -= min(*nr_to_scan, freed); if (*nr_to_scan == 0) break; if (need_resched() || spin_needbreak(&journal->j_list_lock)) @@ -504,9 +464,8 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, if (*nr_to_scan && next_tid) goto again; out: - nr_scanned -= *nr_to_scan; trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid, - nr_freed, nr_scanned, next_tid); + nr_freed, next_tid); return nr_freed; } @@ -522,7 +481,7 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) { transaction_t *transaction, *last_transaction, *next_transaction; - int ret; + bool released; transaction = journal->j_checkpoint_transactions; if (!transaction) @@ -533,8 +492,8 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) do { transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret = journal_clean_one_cp_list(transaction->t_checkpoint_list, - destroy); + journal_shrink_one_cp_list(transaction->t_checkpoint_list, + destroy, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if @@ -547,7 +506,7 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) * avoids pointless scanning of transactions which still * weren't checkpointed. */ - if (!ret) + if (!released) return; } while (transaction != last_transaction); } diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 8f5ee380d309..5646ae15a957 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -462,11 +462,9 @@ TRACE_EVENT(jbd2_shrink_scan_exit, TRACE_EVENT(jbd2_shrink_checkpoint_list, TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid, - unsigned long nr_freed, unsigned long nr_scanned, - tid_t next_tid), + unsigned long nr_freed, tid_t next_tid), - TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, - nr_scanned, next_tid), + TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, next_tid), TP_STRUCT__entry( __field(dev_t, dev) @@ -474,7 +472,6 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list, __field(tid_t, tid) __field(tid_t, last_tid) __field(unsigned long, nr_freed) - __field(unsigned long, nr_scanned) __field(tid_t, next_tid) ), @@ -484,15 +481,14 @@ TRACE_EVENT(jbd2_shrink_checkpoint_list, __entry->tid = tid; __entry->last_tid = last_tid; __entry->nr_freed = nr_freed; - __entry->nr_scanned = nr_scanned; __entry->next_tid = next_tid; ), TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu " - "scanned %lu next transaction %u", + "next transaction %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->first_tid, __entry->tid, __entry->last_tid, - __entry->nr_freed, __entry->nr_scanned, __entry->next_tid) + __entry->nr_freed, __entry->next_tid) ); #endif /* _TRACE_JBD2_H */ From e5c768d809a85e9efd0274b2efe69d4970cc0014 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Tue, 6 Jun 2023 21:59:27 +0800 Subject: [PATCH 0534/2093] jbd2: fix a race when checking checkpoint buffer busy [ Upstream commit 46f881b5b1758dc4a35fba4a643c10717d0cf427 ] Before removing checkpoint buffer from the t_checkpoint_list, we have to check both BH_Dirty and BH_Lock bits together to distinguish buffers have not been or were being written back. But __cp_buffer_busy() checks them separately, it first check lock state and then check dirty, the window between these two checks could be raced by writing back procedure, which locks buffer and clears buffer dirty before I/O completes. So it cannot guarantee checkpointing buffers been written back to disk if some error happens later. Finally, it may clean checkpoint transactions and lead to inconsistent filesystem. jbd2_journal_forget() and __journal_try_to_free_buffer() also have the same problem (journal_unmap_buffer() escape from this issue since it's running under the buffer lock), so fix them through introducing a new helper to try holding the buffer lock and remove really clean buffer. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217490 Cc: stable@vger.kernel.org Suggested-by: Jan Kara Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230606135928.434610-6-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/jbd2/checkpoint.c | 38 +++++++++++++++++++++++++++++++++++--- fs/jbd2/transaction.c | 17 +++++------------ include/linux/jbd2.h | 1 + 3 files changed, 41 insertions(+), 15 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 42b34cab64fb..9ec91017a7f3 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -376,11 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, jh = next_jh; next_jh = jh->b_cpnext; - if (!destroy && __cp_buffer_busy(jh)) - continue; + if (destroy) { + ret = __jbd2_journal_remove_checkpoint(jh); + } else { + ret = jbd2_journal_try_remove_checkpoint(jh); + if (ret < 0) + continue; + } nr_freed++; - ret = __jbd2_journal_remove_checkpoint(jh); if (ret) { *released = true; break; @@ -616,6 +620,34 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) return 1; } +/* + * Check the checkpoint buffer and try to remove it from the checkpoint + * list if it's clean. Returns -EBUSY if it is not clean, returns 1 if + * it frees the transaction, 0 otherwise. + * + * This function is called with j_list_lock held. + */ +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + if (!trylock_buffer(bh)) + return -EBUSY; + if (buffer_dirty(bh)) { + unlock_buffer(bh); + return -EBUSY; + } + unlock_buffer(bh); + + /* + * Buffer is clean and the IO has finished (we held the buffer + * lock) so the checkpoint is done. We can safely remove the + * buffer from this transaction. + */ + JBUFFER_TRACE(jh, "remove from checkpoint list"); + return __jbd2_journal_remove_checkpoint(jh); +} + /* * journal_insert_checkpoint: put a committed buffer onto a checkpoint * list so that we know when it is safe to clean the transaction out of diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 18611241f451..6ef5022949c4 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1784,8 +1784,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) * Otherwise, if the buffer has been written to disk, * it is safe to remove the checkpoint and drop it. */ - if (!buffer_dirty(bh)) { - __jbd2_journal_remove_checkpoint(jh); + if (jbd2_journal_try_remove_checkpoint(jh) >= 0) { spin_unlock(&journal->j_list_lock); goto drop; } @@ -2112,20 +2111,14 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) jh = bh2jh(bh); - if (buffer_locked(bh) || buffer_dirty(bh)) - goto out; - if (jh->b_next_transaction != NULL || jh->b_transaction != NULL) - goto out; + return; spin_lock(&journal->j_list_lock); - if (jh->b_cp_transaction != NULL) { - /* written-back checkpointed metadata buffer */ - JBUFFER_TRACE(jh, "remove from checkpoint list"); - __jbd2_journal_remove_checkpoint(jh); - } + /* Remove written-back checkpointed metadata buffer */ + if (jh->b_cp_transaction != NULL) + jbd2_journal_try_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); -out: return; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 67912fe08fbb..ebb1608d9dcd 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1435,6 +1435,7 @@ extern void jbd2_journal_commit_transaction(journal_t *); void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); From 335987e21237fff0902262ca02b29463e84e3272 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Tue, 11 Jul 2023 09:17:37 +0800 Subject: [PATCH 0535/2093] can: raw: fix receiver memory leak [ Upstream commit ee8b94c8510ce64afe0b87ef548d23e00915fb10 ] Got kmemleak errors with the following ltp can_filter testcase: for ((i=1; i<=100; i++)) do ./can_filter & sleep 0.1 done ============================================================== [<00000000db4a4943>] can_rx_register+0x147/0x360 [can] [<00000000a289549d>] raw_setsockopt+0x5ef/0x853 [can_raw] [<000000006d3d9ebd>] __sys_setsockopt+0x173/0x2c0 [<00000000407dbfec>] __x64_sys_setsockopt+0x61/0x70 [<00000000fd468496>] do_syscall_64+0x33/0x40 [<00000000b7e47d51>] entry_SYSCALL_64_after_hwframe+0x61/0xc6 It's a bug in the concurrent scenario of unregister_netdevice_many() and raw_release() as following: cpu0 cpu1 unregister_netdevice_many(can_dev) unlist_netdevice(can_dev) // dev_get_by_index() return NULL after this net_set_todo(can_dev) raw_release(can_socket) dev = dev_get_by_index(, ro->ifindex); // dev == NULL if (dev) { // receivers in dev_rcv_lists not free because dev is NULL raw_disable_allfilters(, dev, ); dev_put(dev); } ... ro->bound = 0; ... call_netdevice_notifiers(NETDEV_UNREGISTER, ) raw_notify(, NETDEV_UNREGISTER, ) if (ro->bound) // invalid because ro->bound has been set 0 raw_disable_allfilters(, dev, ); // receivers in dev_rcv_lists will never be freed Add a net_device pointer member in struct raw_sock to record bound can_dev, and use rtnl_lock to serialize raw_socket members between raw_bind(), raw_release(), raw_setsockopt() and raw_notify(). Use ro->dev to decide whether to free receivers in dev_rcv_lists. Fixes: 8d0caedb7596 ("can: bcm/raw/isotp: use per module netdevice notifier") Reviewed-by: Oliver Hartkopp Acked-by: Oliver Hartkopp Signed-off-by: Ziyang Xuan Link: https://lore.kernel.org/all/20230711011737.1969582-1-william.xuanziyang@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- net/can/raw.c | 57 ++++++++++++++++++++++----------------------------- 1 file changed, 24 insertions(+), 33 deletions(-) diff --git a/net/can/raw.c b/net/can/raw.c index 4abab2c3011a..1cd2c8748c26 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,7 +278,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { @@ -292,6 +293,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +339,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -385,19 +388,13 @@ static int raw_release(struct socket *sock) lock_sock(sk); + rtnl_lock(); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } if (ro->count > 1) @@ -405,8 +402,10 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); + rtnl_unlock(); sock_orphan(sk); sock->sk = NULL; @@ -422,6 +421,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,14 +431,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -467,26 +466,20 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } ro->ifindex = ifindex; ro->bound = 1; + ro->dev = dev; } out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -552,9 +545,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -595,7 +588,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -613,9 +605,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -639,7 +631,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); From 40dafcab9da92179d610ea5a5f0c32f5ff2fc365 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Jul 2023 11:44:38 +0000 Subject: [PATCH 0536/2093] can: raw: fix lockdep issue in raw_release() [ Upstream commit 11c9027c983e9e4b408ee5613b6504d24ebd85be ] syzbot complained about a lockdep issue [1] Since raw_bind() and raw_setsockopt() first get RTNL before locking the socket, we must adopt the same order in raw_release() [1] WARNING: possible circular locking dependency detected 6.5.0-rc1-syzkaller-00192-g78adb4bcf99e #0 Not tainted ------------------------------------------------------ syz-executor.0/14110 is trying to acquire lock: ffff88804e4b6130 (sk_lock-AF_CAN){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1708 [inline] ffff88804e4b6130 (sk_lock-AF_CAN){+.+.}-{0:0}, at: raw_bind+0xb1/0xab0 net/can/raw.c:435 but task is already holding lock: ffffffff8e3df368 (rtnl_mutex){+.+.}-{3:3}, at: raw_bind+0xa7/0xab0 net/can/raw.c:434 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (rtnl_mutex){+.+.}-{3:3}: __mutex_lock_common kernel/locking/mutex.c:603 [inline] __mutex_lock+0x181/0x1340 kernel/locking/mutex.c:747 raw_release+0x1c6/0x9b0 net/can/raw.c:391 __sock_release+0xcd/0x290 net/socket.c:654 sock_close+0x1c/0x20 net/socket.c:1386 __fput+0x3fd/0xac0 fs/file_table.c:384 task_work_run+0x14d/0x240 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x210/0x240 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:297 do_syscall_64+0x44/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #0 (sk_lock-AF_CAN){+.+.}-{0:0}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x2e3d/0x5de0 kernel/locking/lockdep.c:5144 lock_acquire kernel/locking/lockdep.c:5761 [inline] lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726 lock_sock_nested+0x3a/0xf0 net/core/sock.c:3492 lock_sock include/net/sock.h:1708 [inline] raw_bind+0xb1/0xab0 net/can/raw.c:435 __sys_bind+0x1ec/0x220 net/socket.c:1792 __do_sys_bind net/socket.c:1803 [inline] __se_sys_bind net/socket.c:1801 [inline] __x64_sys_bind+0x72/0xb0 net/socket.c:1801 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(rtnl_mutex); lock(sk_lock-AF_CAN); lock(rtnl_mutex); lock(sk_lock-AF_CAN); *** DEADLOCK *** 1 lock held by syz-executor.0/14110: stack backtrace: CPU: 0 PID: 14110 Comm: syz-executor.0 Not tainted 6.5.0-rc1-syzkaller-00192-g78adb4bcf99e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/03/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106 check_noncircular+0x311/0x3f0 kernel/locking/lockdep.c:2195 check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x2e3d/0x5de0 kernel/locking/lockdep.c:5144 lock_acquire kernel/locking/lockdep.c:5761 [inline] lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726 lock_sock_nested+0x3a/0xf0 net/core/sock.c:3492 lock_sock include/net/sock.h:1708 [inline] raw_bind+0xb1/0xab0 net/can/raw.c:435 __sys_bind+0x1ec/0x220 net/socket.c:1792 __do_sys_bind net/socket.c:1803 [inline] __se_sys_bind net/socket.c:1801 [inline] __x64_sys_bind+0x72/0xb0 net/socket.c:1801 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fd89007cb29 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fd890d2a0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000031 RAX: ffffffffffffffda RBX: 00007fd89019bf80 RCX: 00007fd89007cb29 RDX: 0000000000000010 RSI: 0000000020000040 RDI: 0000000000000003 RBP: 00007fd8900c847a R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fd89019bf80 R15: 00007ffebf8124f8 Fixes: ee8b94c8510c ("can: raw: fix receiver memory leak") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Ziyang Xuan Cc: Oliver Hartkopp Cc: stable@vger.kernel.org Cc: Marc Kleine-Budde Link: https://lore.kernel.org/all/20230720114438.172434-1-edumazet@google.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- net/can/raw.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/can/raw.c b/net/can/raw.c index 1cd2c8748c26..0dd3259357a3 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -386,9 +386,9 @@ static int raw_release(struct socket *sock) list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); + rtnl_lock(); lock_sock(sk); - rtnl_lock(); /* remove current filters & unregister */ if (ro->bound) { if (ro->dev) @@ -405,12 +405,13 @@ static int raw_release(struct socket *sock) ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); - rtnl_unlock(); sock_orphan(sk); sock->sk = NULL; release_sock(sk); + rtnl_unlock(); + sock_put(sk); return 0; From 246d763b79a597fcc84ff10d96b620974f47bb56 Mon Sep 17 00:00:00 2001 From: Yu Zhe Date: Fri, 3 Mar 2023 13:21:55 +0800 Subject: [PATCH 0537/2093] s390/zcrypt: remove unnecessary (void *) conversions [ Upstream commit 72c2112ce9d72e6c40dd893f32187a3d34453113 ] Pointer variables of void * type do not require type cast. Signed-off-by: Yu Zhe Reviewed-by: Muhammad Usama Anjum Link: https://lore.kernel.org/r/20230303052155.21072-1-yuzhe@nfschina.com Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik Stable-dep-of: 4cfca532ddc3 ("s390/zcrypt: fix reply buffer calculations for CCA replies") Signed-off-by: Sasha Levin --- drivers/s390/crypto/zcrypt_msgtype6.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index f99a9ef42116..37c01aaa21a2 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -926,8 +926,7 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86x_reply *t86r; int len; @@ -982,8 +981,7 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86_ep11_reply *t86r; int len; @@ -1157,7 +1155,7 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, struct ap_message *ap_msg) { int rc; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct CPRBX cprbx; @@ -1243,7 +1241,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * { int rc; unsigned int lfmt; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct ep11_cprb cprbx; @@ -1365,7 +1363,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, short int verb_length; short int key_length; } __packed * msg = ap_msg->msg; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; int rc; msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); From d4f5dcf68c0531b8a7191b736e121c6537e1b6cf Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 17 Jul 2023 16:55:29 +0200 Subject: [PATCH 0538/2093] s390/zcrypt: fix reply buffer calculations for CCA replies [ Upstream commit 4cfca532ddc3474b3fc42592d0e4237544344b1a ] The length information for available buffer space for CCA replies is covered with two fields in the T6 header prepended on each CCA reply: fromcardlen1 and fromcardlen2. The sum of these both values must not exceed the AP bus limit for this card (24KB for CEX8, 12KB CEX7 and older) minus the always present headers. The current code adjusted the fromcardlen2 value in case of exceeding the AP bus limit when there was a non-zero value given from userspace. Some tests now showed that this was the wrong assumption. Instead the userspace value given for this field should always be trusted and if the sum of the two fields exceeds the AP bus limit for this card the first field fromcardlen1 should be adjusted instead. So now the calculation is done with this new insight in mind. Also some additional checks for overflow have been introduced and some comments to provide some documentation for future maintainers of this complicated calculation code. Furthermore the 128 bytes of fix overhead which is used in the current code is not correct. Investigations showed that for a reply always the same two header structs are prepended before a possible payload. So this is also fixed with this patch. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Cc: stable@vger.kernel.org Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- drivers/s390/crypto/zcrypt_msgtype6.c | 33 +++++++++++++++++++-------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 37c01aaa21a2..84e3ad290f6b 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1154,23 +1154,36 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, struct ica_xcRB *xcrb, struct ap_message *ap_msg) { - int rc; struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct CPRBX cprbx; /* ... more data blocks ... */ } __packed * msg = ap_msg->msg; + unsigned int max_payload_size; + int rc, delta; - /* - * Set the queue's reply buffer length minus 128 byte padding - * as reply limit for the card firmware. - */ - msg->hdr.fromcardlen1 = min_t(unsigned int, msg->hdr.fromcardlen1, - zq->reply.bufsize - 128); - if (msg->hdr.fromcardlen2) - msg->hdr.fromcardlen2 = - zq->reply.bufsize - msg->hdr.fromcardlen1 - 128; + /* calculate maximum payload for this card and msg type */ + max_payload_size = zq->reply.bufsize - sizeof(struct type86_fmt2_msg); + + /* limit each of the two from fields to the maximum payload size */ + msg->hdr.fromcardlen1 = min(msg->hdr.fromcardlen1, max_payload_size); + msg->hdr.fromcardlen2 = min(msg->hdr.fromcardlen2, max_payload_size); + + /* calculate delta if the sum of both exceeds max payload size */ + delta = msg->hdr.fromcardlen1 + msg->hdr.fromcardlen2 + - max_payload_size; + if (delta > 0) { + /* + * Sum exceeds maximum payload size, prune fromcardlen1 + * (always trust fromcardlen2) + */ + if (delta > msg->hdr.fromcardlen1) { + rc = -EINVAL; + goto out; + } + msg->hdr.fromcardlen1 -= delta; + } init_completion(&rtype->work); rc = ap_queue_message(zq->queue, ap_msg); From c23126f2c76a17b97520d306542cee32bb26fad8 Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Tue, 25 Jul 2023 02:19:45 +0200 Subject: [PATCH 0539/2093] drm/i915: Add the gen12_needs_ccs_aux_inv helper [ Upstream commit b2f59e9026038a5bbcbc0019fa58f963138211ee ] We always assumed that a device might either have AUX or FLAT CCS, but this is an approximation that is not always true, e.g. PVC represents an exception. Set the basis for future finer selection by implementing a boolean gen12_needs_ccs_aux_inv() function that tells whether aux invalidation is needed or not. Currently PVC is the only exception to the above mentioned rule. Requires: 059ae7ae2a1c ("drm/i915/gt: Cleanup aux invalidation registers") Signed-off-by: Andi Shyti Cc: Matt Roper Cc: Jonathan Cavitt Cc: # v5.8+ Reviewed-by: Matt Roper Reviewed-by: Andrzej Hajda Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-3-andi.shyti@linux.intel.com (cherry picked from commit c827655b87ad201ebe36f2e28d16b5491c8f7801) Signed-off-by: Tvrtko Ursulin Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index b2838732ac93..8e286733a436 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,6 +165,18 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } +static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) +{ + if (IS_PONTEVECCHIO(engine->i915)) + return false; + + /* + * so far platforms supported by i915 having + * flat ccs do not require AUX invalidation + */ + return !HAS_FLAT_CCS(engine->i915); +} + u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) { u32 gsi_offset = gt->uncore->gsi_offset; @@ -236,7 +248,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; - if (!HAS_FLAT_CCS(rq->engine->i915)) + if (gen12_needs_ccs_aux_inv(rq->engine)) count = 8 + 4; else count = 8; @@ -254,7 +266,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); - if (!HAS_FLAT_CCS(rq->engine->i915)) { + if (gen12_needs_ccs_aux_inv(rq->engine)) { /* hsdes: 1809175790 */ cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, GEN12_CCS_AUX_INV); @@ -276,7 +288,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (mode & EMIT_INVALIDATE) { cmd += 2; - if (!HAS_FLAT_CCS(rq->engine->i915) && + if (gen12_needs_ccs_aux_inv(rq->engine) && (rq->engine->class == VIDEO_DECODE_CLASS || rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { aux_inv = rq->engine->mask & From 017d4404312ab94a61be218c0221cd0048a37896 Mon Sep 17 00:00:00 2001 From: Jonathan Cavitt Date: Tue, 25 Jul 2023 02:19:46 +0200 Subject: [PATCH 0540/2093] drm/i915/gt: Ensure memory quiesced before invalidation [ Upstream commit 78a6ccd65fa3a7cc697810db079cc4b84dff03d5 ] All memory traffic must be quiesced before requesting an aux invalidation on platforms that use Aux CCS. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Requires: a2a4aa0eef3b ("drm/i915: Add the gen12_needs_ccs_aux_inv helper") Signed-off-by: Jonathan Cavitt Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Nirmoy Das Reviewed-by: Andrzej Hajda Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-4-andi.shyti@linux.intel.com (cherry picked from commit ad8ebf12217e451cd19804b1c3e97ad56491c74a) Signed-off-by: Tvrtko Ursulin Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 8e286733a436..6a8c2fab4ca8 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -193,7 +193,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) { struct intel_engine_cs *engine = rq->engine; - if (mode & EMIT_FLUSH) { + /* + * On Aux CCS platforms the invalidation of the Aux + * table requires quiescing memory traffic beforehand + */ + if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) { u32 flags = 0; u32 *cs; From 8e3f138b96f64fde58d74f886acbfd4baca907fc Mon Sep 17 00:00:00 2001 From: Jonathan Cavitt Date: Tue, 25 Jul 2023 02:19:49 +0200 Subject: [PATCH 0541/2093] drm/i915/gt: Poll aux invalidation register bit on invalidation [ Upstream commit 0fde2f23516a00fd90dfb980b66b4665fcbfa659 ] For platforms that use Aux CCS, wait for aux invalidation to complete by checking the aux invalidation register bit is cleared. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Jonathan Cavitt Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Nirmoy Das Reviewed-by: Andrzej Hajda Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-7-andi.shyti@linux.intel.com (cherry picked from commit d459c86f00aa98028d155a012c65dc42f7c37e76) Signed-off-by: Tvrtko Ursulin Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 17 ++++++++++++----- drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 + 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 6a8c2fab4ca8..975e31d876b1 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -184,7 +184,15 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; *cs++ = AUX_INV; - *cs++ = MI_NOOP; + + *cs++ = MI_SEMAPHORE_WAIT_TOKEN | + MI_SEMAPHORE_REGISTER_POLL | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD; + *cs++ = 0; + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; + *cs++ = 0; + *cs++ = 0; return cs; } @@ -252,10 +260,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; + count = 8; if (gen12_needs_ccs_aux_inv(rq->engine)) - count = 8 + 4; - else - count = 8; + count += 8; cs = intel_ring_begin(rq, count); if (IS_ERR(cs)) @@ -298,7 +305,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) aux_inv = rq->engine->mask & ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); if (aux_inv) - cmd += 4; + cmd += 8; } } diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index d4e9702d3c8e..25ea5f8a464a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -120,6 +120,7 @@ #define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */ #define MI_SEMAPHORE_WAIT_TOKEN MI_INSTR(0x1c, 3) /* GEN12+ */ +#define MI_SEMAPHORE_REGISTER_POLL (1 << 16) #define MI_SEMAPHORE_POLL (1 << 15) #define MI_SEMAPHORE_SAD_GT_SDD (0 << 12) #define MI_SEMAPHORE_SAD_GTE_SDD (1 << 12) From 7e862cce34916458bf6af954d198cce103c1e13f Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Tue, 25 Jul 2023 02:19:50 +0200 Subject: [PATCH 0542/2093] drm/i915/gt: Support aux invalidation on all engines [ Upstream commit 6a35f22d222528e1b157c6978c9424d2f8cbe0a1 ] Perform some refactoring with the purpose of keeping in one single place all the operations around the aux table invalidation. With this refactoring add more engines where the invalidation should be performed. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Andi Shyti Cc: Jonathan Cavitt Cc: Matt Roper Cc: # v5.8+ Reviewed-by: Andrzej Hajda Link: https://patchwork.freedesktop.org/patch/msgid/20230725001950.1014671-8-andi.shyti@linux.intel.com (cherry picked from commit 76ff7789d6e63d1a10b3b58f5c70b2e640c7a880) Signed-off-by: Tvrtko Ursulin Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 66 +++++++++++++----------- drivers/gpu/drm/i915/gt/gen8_engine_cs.h | 3 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 17 +----- 3 files changed, 41 insertions(+), 45 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 975e31d876b1..cc8468536871 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,21 +165,47 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } +static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine) +{ + switch (engine->id) { + case RCS0: + return GEN12_CCS_AUX_INV; + case BCS0: + return GEN12_BCS0_AUX_INV; + case VCS0: + return GEN12_VD0_AUX_INV; + case VCS2: + return GEN12_VD2_AUX_INV; + case VECS0: + return GEN12_VE0_AUX_INV; + case CCS0: + return GEN12_CCS0_AUX_INV; + default: + return INVALID_MMIO_REG; + } +} + static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) { + i915_reg_t reg = gen12_get_aux_inv_reg(engine); + if (IS_PONTEVECCHIO(engine->i915)) return false; /* - * so far platforms supported by i915 having - * flat ccs do not require AUX invalidation + * So far platforms supported by i915 having flat ccs do not require + * AUX invalidation. Check also whether the engine requires it. */ - return !HAS_FLAT_CCS(engine->i915); + return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915); } -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) { - u32 gsi_offset = gt->uncore->gsi_offset; + i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine); + u32 gsi_offset = engine->gt->uncore->gsi_offset; + + if (!gen12_needs_ccs_aux_inv(engine)) + return cs; *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; @@ -277,11 +303,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); - if (gen12_needs_ccs_aux_inv(rq->engine)) { - /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, - GEN12_CCS_AUX_INV); - } + cs = gen12_emit_aux_table_inv(engine, cs); *cs++ = preparser_disable(false); intel_ring_advance(rq, cs); @@ -292,21 +314,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) { - intel_engine_mask_t aux_inv = 0; - u32 cmd, *cs; + u32 cmd = 4; + u32 *cs; - cmd = 4; if (mode & EMIT_INVALIDATE) { cmd += 2; - if (gen12_needs_ccs_aux_inv(rq->engine) && - (rq->engine->class == VIDEO_DECODE_CLASS || - rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { - aux_inv = rq->engine->mask & - ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); - if (aux_inv) - cmd += 8; - } + if (gen12_needs_ccs_aux_inv(rq->engine)) + cmd += 8; } cs = intel_ring_begin(rq, cmd); @@ -337,14 +352,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) *cs++ = 0; /* upper addr */ *cs++ = 0; /* value */ - if (aux_inv) { /* hsdes: 1809175790 */ - if (rq->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_INV); - else - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_INV); - } + cs = gen12_emit_aux_table_inv(rq->engine, cs); if (mode & EMIT_INVALIDATE) *cs++ = preparser_disable(false); diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index e4d24c811dd6..651eb786e930 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -13,6 +13,7 @@ #include "intel_gt_regs.h" #include "intel_gpu_commands.h" +struct intel_engine_cs; struct intel_gt; struct i915_request; @@ -46,7 +47,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs); static inline u32 * __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 137e41e37ea5..7eb01ff17d89 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1296,10 +1296,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_CCS_AUX_INV); + cs = gen12_emit_aux_table_inv(ce->engine, cs); /* Wa_16014892111 */ if (IS_DG2(ce->engine->i915)) @@ -1322,17 +1319,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) { - if (ce->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_INV); - else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_INV); - } - - return cs; + return gen12_emit_aux_table_inv(ce->engine, cs); } static void From 7d0c2b0de2dbf086373049ac9bf45b9ae7f421bb Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Sat, 5 Aug 2023 11:38:15 +0800 Subject: [PATCH 0543/2093] tracing: Fix cpu buffers unavailable due to 'record_disabled' missed [ Upstream commit b71645d6af10196c46cbe3732de2ea7d36b3ff6d ] Trace ring buffer can no longer record anything after executing following commands at the shell prompt: # cd /sys/kernel/tracing # cat tracing_cpumask fff # echo 0 > tracing_cpumask # echo 1 > snapshot # echo fff > tracing_cpumask # echo 1 > tracing_on # echo "hello world" > trace_marker -bash: echo: write error: Bad file descriptor The root cause is that: 1. After `echo 0 > tracing_cpumask`, 'record_disabled' of cpu buffers in 'tr->array_buffer.buffer' became 1 (see tracing_set_cpumask()); 2. After `echo 1 > snapshot`, 'tr->array_buffer.buffer' is swapped with 'tr->max_buffer.buffer', then the 'record_disabled' became 0 (see update_max_tr()); 3. After `echo fff > tracing_cpumask`, the 'record_disabled' become -1; Then array_buffer and max_buffer are both unavailable due to value of 'record_disabled' is not 0. To fix it, enable or disable both array_buffer and max_buffer at the same time in tracing_set_cpumask(). Link: https://lkml.kernel.org/r/20230805033816.3284594-2-zhengyejian1@huawei.com Cc: Cc: Cc: Fixes: 71babb2705e2 ("tracing: change CPU ring buffer state from tracing_cpumask") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index af33c5a4166d..d56dcd78452c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5189,11 +5189,17 @@ int tracing_set_cpumask(struct trace_array *tr, !cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); +#endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); +#ifdef CONFIG_TRACER_MAX_TRACE + ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); +#endif } } arch_spin_unlock(&tr->max_lock); From 2cb0c037c927db4ec928cc927488e52aa359786e Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Thu, 17 Aug 2023 20:55:39 +0800 Subject: [PATCH 0544/2093] tracing: Fix memleak due to race between current_tracer and trace [ Upstream commit eecb91b9f98d6427d4af5fdb8f108f52572a39e7 ] Kmemleak report a leak in graph_trace_open(): unreferenced object 0xffff0040b95f4a00 (size 128): comm "cat", pid 204981, jiffies 4301155872 (age 99771.964s) hex dump (first 32 bytes): e0 05 e7 b4 ab 7d 00 00 0b 00 01 00 00 00 00 00 .....}.......... f4 00 01 10 00 a0 ff ff 00 00 00 00 65 00 10 00 ............e... backtrace: [<000000005db27c8b>] kmem_cache_alloc_trace+0x348/0x5f0 [<000000007df90faa>] graph_trace_open+0xb0/0x344 [<00000000737524cd>] __tracing_open+0x450/0xb10 [<0000000098043327>] tracing_open+0x1a0/0x2a0 [<00000000291c3876>] do_dentry_open+0x3c0/0xdc0 [<000000004015bcd6>] vfs_open+0x98/0xd0 [<000000002b5f60c9>] do_open+0x520/0x8d0 [<00000000376c7820>] path_openat+0x1c0/0x3e0 [<00000000336a54b5>] do_filp_open+0x14c/0x324 [<000000002802df13>] do_sys_openat2+0x2c4/0x530 [<0000000094eea458>] __arm64_sys_openat+0x130/0x1c4 [<00000000a71d7881>] el0_svc_common.constprop.0+0xfc/0x394 [<00000000313647bf>] do_el0_svc+0xac/0xec [<000000002ef1c651>] el0_svc+0x20/0x30 [<000000002fd4692a>] el0_sync_handler+0xb0/0xb4 [<000000000c309c35>] el0_sync+0x160/0x180 The root cause is descripted as follows: __tracing_open() { // 1. File 'trace' is being opened; ... *iter->trace = *tr->current_trace; // 2. Tracer 'function_graph' is // currently set; ... iter->trace->open(iter); // 3. Call graph_trace_open() here, // and memory are allocated in it; ... } s_start() { // 4. The opened file is being read; ... *iter->trace = *tr->current_trace; // 5. If tracer is switched to // 'nop' or others, then memory // in step 3 are leaked!!! ... } To fix it, in s_start(), close tracer before switching then reopen the new tracer after switching. And some tracers like 'wakeup' may not update 'iter->private' in some cases when reopen, then it should be cleared to avoid being mistakenly closed again. Link: https://lore.kernel.org/linux-trace-kernel/20230817125539.1646321-1-zhengyejian1@huawei.com Fixes: d7350c3f4569 ("tracing/core: make the read callbacks reentrants") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace.c | 9 ++++++++- kernel/trace/trace_irqsoff.c | 3 ++- kernel/trace/trace_sched_wakeup.c | 2 ++ 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d56dcd78452c..1a87cb70f1eb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4128,8 +4128,15 @@ static void *s_start(struct seq_file *m, loff_t *pos) * will point to the same string as current_trace->name. */ mutex_lock(&trace_types_lock); - if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) { + /* Close iter->trace before switching to the new current tracer */ + if (iter->trace->close) + iter->trace->close(iter); *iter->trace = *tr->current_trace; + /* Reopen the new current tracer */ + if (iter->trace->open) + iter->trace->open(iter); + } mutex_unlock(&trace_types_lock); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 590b3d51afae..ba37f768e2f2 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -231,7 +231,8 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); - + else + iter->private = NULL; } static void irqsoff_trace_close(struct trace_iterator *iter) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 330aee1c1a49..0469a04a355f 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -168,6 +168,8 @@ static void wakeup_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); + else + iter->private = NULL; } static void wakeup_trace_close(struct trace_iterator *iter) From eaeef5c865ab9dc5c153b552b52ed0d90eea614e Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Thu, 17 Aug 2023 12:00:06 +0530 Subject: [PATCH 0545/2093] octeontx2-af: SDP: fix receive link config [ Upstream commit 05f3d5bc23524bed6f043dfe6b44da687584f9fb ] On SDP interfaces, frame oversize and undersize errors are observed as driver is not considering packet sizes of all subscribers of the link before updating the link config. This patch fixes the same. Fixes: 9b7dd87ac071 ("octeontx2-af: Support to modify min/max allowed packet lengths") Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Goutham Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230817063006.10366-1-hkelam@marvell.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 705325431dec..5541e284cd3f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4005,9 +4005,10 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID; - nix_find_link_frs(rvu, req, pcifunc); linkcfg: + nix_find_link_frs(rvu, req, pcifunc); + cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link)); cfg = (cfg & ~(0xFFFFULL << 16)) | ((u64)req->maxlen << 16); if (req->update_minlen) From 1375d2061204785d592c05f5dec47eb487ec3515 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 Jan 2023 20:05:17 -0800 Subject: [PATCH 0546/2093] devlink: move code to a dedicated directory [ Upstream commit f05bd8ebeb69c803efd6d8a76d96b7fcd7011094 ] The devlink code is hard to navigate with 13kLoC in one file. I really like the way Michal split the ethtool into per-command files and core. It'd probably be too much to split it all up, but we can at least separate the core parts out of the per-cmd implementations and put it in a directory so that new commands can be separate files. Move the code, subsequent commit will do a partial split. Reviewed-by: Jacob Keller Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski Stable-dep-of: 2ebbc9752d06 ("devlink: add missing unregister linecard notification") Signed-off-by: Sasha Levin --- MAINTAINERS | 2 +- net/Makefile | 1 + net/core/Makefile | 1 - net/devlink/Makefile | 3 +++ net/{core/devlink.c => devlink/leftover.c} | 0 5 files changed, 5 insertions(+), 2 deletions(-) create mode 100644 net/devlink/Makefile rename net/{core/devlink.c => devlink/leftover.c} (100%) diff --git a/MAINTAINERS b/MAINTAINERS index 379387e20a96..07a9c274c0e2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6027,7 +6027,7 @@ S: Supported F: Documentation/networking/devlink F: include/net/devlink.h F: include/uapi/linux/devlink.h -F: net/core/devlink.c +F: net/devlink/ DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT M: Christoph Niedermaier diff --git a/net/Makefile b/net/Makefile index 6a62e5b27378..0914bea9c335 100644 --- a/net/Makefile +++ b/net/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ +obj-$(CONFIG_NET_DEVLINK) += devlink/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_ATALK) += appletalk/ obj-$(CONFIG_X25) += x25/ diff --git a/net/core/Makefile b/net/core/Makefile index 5857cec87b83..10edd66a8a37 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o -obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o diff --git a/net/devlink/Makefile b/net/devlink/Makefile new file mode 100644 index 000000000000..3a60959f71ee --- /dev/null +++ b/net/devlink/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := leftover.o diff --git a/net/core/devlink.c b/net/devlink/leftover.c similarity index 100% rename from net/core/devlink.c rename to net/devlink/leftover.c From b701b8d191daae3442942a1c68bb6e0582b566b2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 17 Aug 2023 14:52:40 +0200 Subject: [PATCH 0547/2093] devlink: add missing unregister linecard notification [ Upstream commit 2ebbc9752d06bb1d01201fe632cb6da033b0248d ] Cited fixes commit introduced linecard notifications for register, however it didn't add them for unregister. Fix that by adding them. Fixes: c246f9b5fd61 ("devlink: add support to create line card and expose to user") Signed-off-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230817125240.2144794-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/devlink/leftover.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index 5a4a4b34ac15..63188d6a50fe 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -9727,6 +9727,7 @@ static void devlink_notify_unregister(struct devlink *devlink) struct devlink_param_item *param_item; struct devlink_trap_item *trap_item; struct devlink_port *devlink_port; + struct devlink_linecard *linecard; struct devlink_rate *rate_node; struct devlink_region *region; @@ -9753,6 +9754,8 @@ static void devlink_notify_unregister(struct devlink *devlink) list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + list_for_each_entry_reverse(linecard, &devlink->linecard_list, list) + devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); devlink_notify(devlink, DEVLINK_CMD_DEL); } From cfee17993d1065d7d6553e57d276cb36c2a768d4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 17 Aug 2023 15:01:11 +0300 Subject: [PATCH 0548/2093] net: dsa: felix: fix oversize frame dropping for always closed tc-taprio gates [ Upstream commit d44036cad31170da0cb9c728e80743f84267da6e ] The blamed commit resolved a bug where frames would still get stuck at egress, even though they're smaller than the maxSDU[tc], because the driver did not take into account the extra 33 ns that the queue system needs for scheduling the frame. It now takes that into account, but the arithmetic that we perform in vsc9959_tas_remaining_gate_len_ps() is buggy, because we operate on 64-bit unsigned integers, so gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS may become a very large integer if gate_len_ns < 33 ns. In practice, this means that we've introduced a regression where all traffic class gates which are permanently closed will not get detected by the driver, and we won't enable oversize frame dropping for them. Before: mscc_felix 0000:00:00.5: port 0: max frame size 1526 needs 12400000 ps, 1152000 ps for mPackets at speed 1000 mscc_felix 0000:00:00.5: port 0 tc 0 min gate len 1000000, sending all frames mscc_felix 0000:00:00.5: port 0 tc 1 min gate len 0, sending all frames mscc_felix 0000:00:00.5: port 0 tc 2 min gate len 0, sending all frames mscc_felix 0000:00:00.5: port 0 tc 3 min gate len 0, sending all frames mscc_felix 0000:00:00.5: port 0 tc 4 min gate len 0, sending all frames mscc_felix 0000:00:00.5: port 0 tc 5 min gate len 0, sending all frames mscc_felix 0000:00:00.5: port 0 tc 6 min gate len 0, sending all frames mscc_felix 0000:00:00.5: port 0 tc 7 min gate length 5120 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 615 octets including FCS After: mscc_felix 0000:00:00.5: port 0: max frame size 1526 needs 12400000 ps, 1152000 ps for mPackets at speed 1000 mscc_felix 0000:00:00.5: port 0 tc 0 min gate len 1000000, sending all frames mscc_felix 0000:00:00.5: port 0 tc 1 min gate length 0 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 1 octets including FCS mscc_felix 0000:00:00.5: port 0 tc 2 min gate length 0 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 1 octets including FCS mscc_felix 0000:00:00.5: port 0 tc 3 min gate length 0 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 1 octets including FCS mscc_felix 0000:00:00.5: port 0 tc 4 min gate length 0 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 1 octets including FCS mscc_felix 0000:00:00.5: port 0 tc 5 min gate length 0 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 1 octets including FCS mscc_felix 0000:00:00.5: port 0 tc 6 min gate length 0 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 1 octets including FCS mscc_felix 0000:00:00.5: port 0 tc 7 min gate length 5120 ns not enough for max frame size 1526 at 1000 Mbps, dropping frames over 615 octets including FCS Fixes: 11afdc6526de ("net: dsa: felix: tc-taprio intervals smaller than MTU should send at least one packet") Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230817120111.3522827-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/ocelot/felix_vsc9959.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 5f6af0870dfd..0186482194d2 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1071,6 +1071,9 @@ static u64 vsc9959_tas_remaining_gate_len_ps(u64 gate_len_ns) if (gate_len_ns == U64_MAX) return U64_MAX; + if (gate_len_ns < VSC9959_TAS_MIN_GATE_LEN_NS) + return 0; + return (gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS) * PSEC_PER_NSEC; } From b516a24f4c07426028baaa55595f50730df512c6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 18 Aug 2023 01:51:32 +0000 Subject: [PATCH 0549/2093] sock: annotate data-races around prot->memory_pressure [ Upstream commit 76f33296d2e09f63118db78125c95ef56df438e9 ] *prot->memory_pressure is read/writen locklessly, we need to add proper annotations. A recent commit added a new race, it is time to audit all accesses. Fixes: 2d0c88e84e48 ("sock: Fix misuse of sk_under_memory_pressure()") Fixes: 4d93df0abd50 ("[SCTP]: Rewrite of sctp buffer management code") Signed-off-by: Eric Dumazet Cc: Abel Wu Reviewed-by: Shakeel Butt Link: https://lore.kernel.org/r/20230818015132.2699348-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/sock.h | 7 ++++--- net/sctp/socket.c | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 699408944952..d1f936ed9755 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1320,6 +1320,7 @@ struct proto { /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. + * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ @@ -1448,7 +1449,7 @@ static inline bool sk_has_memory_pressure(const struct sock *sk) static inline bool sk_under_global_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure && - !!*sk->sk_prot->memory_pressure; + !!READ_ONCE(*sk->sk_prot->memory_pressure); } static inline bool sk_under_memory_pressure(const struct sock *sk) @@ -1460,7 +1461,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; - return !!*sk->sk_prot->memory_pressure; + return !!READ_ONCE(*sk->sk_prot->memory_pressure); } static inline long @@ -1537,7 +1538,7 @@ proto_memory_pressure(struct proto *prot) { if (!prot->memory_pressure) return false; - return !!*prot->memory_pressure; + return !!READ_ONCE(*prot->memory_pressure); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c806d272107a..83656fe03a0e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -98,7 +98,7 @@ struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { - sctp_memory_pressure = 1; + WRITE_ONCE(sctp_memory_pressure, 1); } From 265ed382e0f4c7b28742e542d4b14799e131a57e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 18 Aug 2023 01:58:20 +0000 Subject: [PATCH 0550/2093] dccp: annotate data-races in dccp_poll() [ Upstream commit cba3f1786916063261e3e5ccbb803abc325b24ef ] We changed tcp_poll() over time, bug never updated dccp. Note that we also could remove dccp instead of maintaining it. Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230818015820.2701595-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/dccp/proto.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/net/dccp/proto.c b/net/dccp/proto.c index abc02d25edc1..c522c76a9f89 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -312,11 +312,15 @@ EXPORT_SYMBOL_GPL(dccp_disconnect); __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask; struct sock *sk = sock->sk; + __poll_t mask; + u8 shutdown; + int state; sock_poll_wait(file, sock, wait); - if (sk->sk_state == DCCP_LISTEN) + + state = inet_sk_state_load(sk); + if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -325,20 +329,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, */ mask = 0; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; + shutdown = READ_ONCE(sk->sk_shutdown); - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED) + if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ - if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { + if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -356,7 +361,6 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, } return mask; } - EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) From 4496f6ccf599054b9a8d2a9d41e6410221269aa7 Mon Sep 17 00:00:00 2001 From: Lu Wei Date: Thu, 17 Aug 2023 22:54:49 +0800 Subject: [PATCH 0551/2093] ipvlan: Fix a reference count leak warning in ipvlan_ns_exit() [ Upstream commit 043d5f68d0ccdda91029b4b6dce7eeffdcfad281 ] There are two network devices(veth1 and veth3) in ns1, and ipvlan1 with L3S mode and ipvlan2 with L2 mode are created based on them as figure (1). In this case, ipvlan_register_nf_hook() will be called to register nf hook which is needed by ipvlans in L3S mode in ns1 and value of ipvl_nf_hook_refcnt is set to 1. (1) ns1 ns2 ------------ ------------ veth1--ipvlan1 (L3S) veth3--ipvlan2 (L2) (2) ns1 ns2 ------------ ------------ veth1--ipvlan1 (L3S) ipvlan2 (L2) veth3 | | |------->-------->--------->-------- migrate When veth3 migrates from ns1 to ns2 as figure (2), veth3 will register in ns2 and calls call_netdevice_notifiers with NETDEV_REGISTER event: dev_change_net_namespace call_netdevice_notifiers ipvlan_device_event ipvlan_migrate_l3s_hook ipvlan_register_nf_hook(newnet) (I) ipvlan_unregister_nf_hook(oldnet) (II) In function ipvlan_migrate_l3s_hook(), ipvl_nf_hook_refcnt in ns1 is not 0 since veth1 with ipvlan1 still in ns1, (I) and (II) will be called to register nf_hook in ns2 and unregister nf_hook in ns1. As a result, ipvl_nf_hook_refcnt in ns1 is decreased incorrectly and this in ns2 is increased incorrectly. When the second net namespace is removed, a reference count leak warning in ipvlan_ns_exit() will be triggered. This patch add a check before ipvlan_migrate_l3s_hook() is called. The warning can be triggered as follows: $ ip netns add ns1 $ ip netns add ns2 $ ip netns exec ns1 ip link add veth1 type veth peer name veth2 $ ip netns exec ns1 ip link add veth3 type veth peer name veth4 $ ip netns exec ns1 ip link add ipv1 link veth1 type ipvlan mode l3s $ ip netns exec ns1 ip link add ipv2 link veth3 type ipvlan mode l2 $ ip netns exec ns1 ip link set veth3 netns ns2 $ ip net del ns2 Fixes: 3133822f5ac1 ("ipvlan: use pernet operations and restrict l3s hooks to master netns") Signed-off-by: Lu Wei Reviewed-by: Florian Westphal Link: https://lore.kernel.org/r/20230817145449.141827-1-luwei32@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ipvlan/ipvlan_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 796a38f9d7b2..cd16bc8bf154 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -748,7 +748,8 @@ static int ipvlan_device_event(struct notifier_block *unused, write_pnet(&port->pnet, newnet); - ipvlan_migrate_l3s_hook(oldnet, newnet); + if (port->mode == IPVLAN_MODE_L3S) + ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: From 22f9b5468df567ec3b3f493e16c65ff5df5fdff0 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 17 Aug 2023 15:58:22 +0200 Subject: [PATCH 0552/2093] mlxsw: pci: Set time stamp fields also when its type is MIRROR_UTC [ Upstream commit bc2de151ab6ad0762a04563527ec42e54dde572a ] Currently, in Spectrum-2 and above, time stamps are extracted from the CQE into the time stamp fields in 'struct mlxsw_skb_cb', only when the CQE time stamp type is UTC. The time stamps are read directly from the CQE and software can get the time stamp in UTC format using CQEv2. From Spectrum-4, the time stamps that are read from the CQE are allowed to be also from MIRROR_UTC type. Therefore, we get a warning [1] from the driver that the time stamp fields were not set, when LLDP control packet is sent. Allow the time stamp type to be MIRROR_UTC and set the time stamp in this case as well. [1] WARNING: CPU: 11 PID: 0 at drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c:1409 mlxsw_sp2_ptp_hwtstamp_fill+0x1f/0x70 [mlxsw_spectrum] [...] Call Trace: mlxsw_sp2_ptp_receive+0x3c/0x80 [mlxsw_spectrum] mlxsw_core_skb_receive+0x119/0x190 [mlxsw_core] mlxsw_pci_cq_tasklet+0x3c9/0x780 [mlxsw_pci] tasklet_action_common.constprop.0+0x9f/0x110 __do_softirq+0xbb/0x296 irq_exit_rcu+0x79/0xa0 common_interrupt+0x86/0xa0 Fixes: 4735402173e6 ("mlxsw: spectrum: Extend to support Spectrum-4 ASIC") Signed-off-by: Danielle Ratson Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/bcef4d044ef608a4e258d33a7ec0ecd91f480db5.1692268427.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/pci.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c968309657dd..51eea1f0529c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -517,11 +517,15 @@ static void mlxsw_pci_skb_cb_ts_set(struct mlxsw_pci *mlxsw_pci, struct sk_buff *skb, enum mlxsw_pci_cqe_v cqe_v, char *cqe) { + u8 ts_type; + if (cqe_v != MLXSW_PCI_CQE_V2) return; - if (mlxsw_pci_cqe2_time_stamp_type_get(cqe) != - MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC) + ts_type = mlxsw_pci_cqe2_time_stamp_type_get(cqe); + + if (ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_UTC && + ts_type != MLXSW_PCI_CQE_TIME_STAMP_TYPE_MIRROR_UTC) return; mlxsw_skb_cb(skb)->cqe_ts.sec = mlxsw_pci_cqe2_time_stamp_sec_get(cqe); From 7134565a8207fc6fafe188c95bdd5f09744ccfec Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 17 Aug 2023 15:58:23 +0200 Subject: [PATCH 0553/2093] mlxsw: reg: Fix SSPR register layout [ Upstream commit 0dc63b9cfd4c5666ced52c829fdd65dcaeb9f0f1 ] The two most significant bits of the "local_port" field in the SSPR register are always cleared since they are overwritten by the deprecated and overlapping "sub_port" field. On systems with more than 255 local ports (e.g., Spectrum-4), this results in the firmware maintaining invalid mappings between system port and local port. Specifically, two different systems ports (0x1 and 0x101) point to the same local port (0x1), which eventually leads to firmware errors. Fix by removing the deprecated "sub_port" field. Fixes: fd24b29a1b74 ("mlxsw: reg: Align existing registers to use extended local_port field") Signed-off-by: Ido Schimmel Signed-off-by: Petr Machata Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/9b909a3033c8d3d6f67f237306bef4411c5e6ae4.1692268427.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0777bed5bb1a..a34ff19c58bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -97,14 +97,6 @@ MLXSW_ITEM32(reg, sspr, m, 0x00, 31, 1); */ MLXSW_ITEM32_LP(reg, sspr, 0x00, 16, 0x00, 12); -/* reg_sspr_sub_port - * Virtual port within the physical port. - * Should be set to 0 when virtual ports are not enabled on the port. - * - * Access: RW - */ -MLXSW_ITEM32(reg, sspr, sub_port, 0x00, 8, 8); - /* reg_sspr_system_port * Unique identifier within the stacking domain that represents all the ports * that are available in the system (external ports). @@ -120,7 +112,6 @@ static inline void mlxsw_reg_sspr_pack(char *payload, u16 local_port) MLXSW_REG_ZERO(sspr, payload); mlxsw_reg_sspr_m_set(payload, 1); mlxsw_reg_sspr_local_port_set(payload, local_port); - mlxsw_reg_sspr_sub_port_set(payload, 0); mlxsw_reg_sspr_system_port_set(payload, local_port); } From 1288f9907514b8e0cc1e17645252429ee0917182 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 17 Aug 2023 15:58:24 +0200 Subject: [PATCH 0554/2093] mlxsw: Fix the size of 'VIRT_ROUTER_MSB' [ Upstream commit 348c976be0a599918b88729def198a843701c9fe ] The field 'virtual router' was extended to 12 bits in Spectrum-4. Therefore, the element 'MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB' needs 3 bits for Spectrum < 4 and 4 bits for Spectrum >= 4. The elements are stored in an internal storage scratchpad. Currently, the MSB is defined there as 3 bits. It means that for Spectrum-4, only 2K VRFs can be used for multicast routing, as the highest bit is not really used by the driver. Fix the definition of 'VIRT_ROUTER_MSB' to use 4 bits. Adjust the definitions of 'virtual router' field in the blocks accordingly - use '_avoid_size_check' for Spectrum-2 instead of for Spectrum-4. Fix the mask in parse function to use 4 bits. Fixes: 6d5d8ebb881c ("mlxsw: Rename virtual router flex key element") Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/79bed2b70f6b9ed58d4df02e9798a23da648015b.1692268427.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c | 4 ++-- drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index bd1a51a0a540..f208a237d0b5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -32,8 +32,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8), MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2), MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 3), - MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 20, 8), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_MSB, 0x18, 17, 4), + MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_LSB, 0x18, 21, 8), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c index e4f4cded2b6f..b1178b7a7f51 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c @@ -193,7 +193,7 @@ mlxsw_sp2_mr_tcam_rule_parse(struct mlxsw_sp_acl_rule *rule, key->vrid, GENMASK(7, 0)); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB, - key->vrid >> 8, GENMASK(2, 0)); + key->vrid >> 8, GENMASK(3, 0)); switch (key->proto) { case MLXSW_SP_L3_PROTO_IPV4: return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c index 00c32320f891..173808c096ba 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c @@ -169,7 +169,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 24, 8), - MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x00, 0, 3), + MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x00, 0, 3, 0, true), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = { @@ -319,7 +319,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5b[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4b[] = { MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_LSB, 0x04, 13, 8), - MLXSW_AFK_ELEMENT_INST_EXT_U32(VIRT_ROUTER_MSB, 0x04, 21, 4, 0, true), + MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_MSB, 0x04, 21, 4), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2b[] = { From c663607202f58e0fe17d2db1f9967d641c0195f5 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 17 Aug 2023 15:58:25 +0200 Subject: [PATCH 0555/2093] selftests: mlxsw: Fix test failure on Spectrum-4 [ Upstream commit f520489e99a35b0a5257667274fbe9afd2d8c50b ] Remove assumptions about shared buffer cell size and instead query the cell size from devlink. Adjust the test to send small packets that fit inside a single cell. Tested on Spectrum-{1,2,3,4}. Fixes: 4735402173e6 ("mlxsw: spectrum: Extend to support Spectrum-4 ASIC") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/f7dfbf3c4d1cb23838d9eb99bab09afaa320c4ca.1692268427.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../selftests/drivers/net/mlxsw/sharedbuffer.sh | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 7d9e73a43a49..0c47faff9274 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -98,12 +98,12 @@ sb_occ_etc_check() port_pool_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q devlink sb occupancy snapshot $DEVLINK_DEV @@ -126,12 +126,12 @@ port_pool_test() port_tc_ip_test() { - local exp_max_occ=288 + local exp_max_occ=$(devlink_cell_size_get) local max_occ devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ -t ip -q devlink sb occupancy snapshot $DEVLINK_DEV @@ -154,16 +154,12 @@ port_tc_ip_test() port_tc_arp_test() { - local exp_max_occ=96 + local exp_max_occ=$(devlink_cell_size_get) local max_occ - if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then - exp_max_occ=144 - fi - devlink sb occupancy clearmax $DEVLINK_DEV - $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q + $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q devlink sb occupancy snapshot $DEVLINK_DEV From ac259251487a174ece97dd745727e39712f18ebf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sun, 13 Aug 2023 13:59:17 +0300 Subject: [PATCH 0556/2093] net: dsa: mt7530: fix handling of 802.1X PAE frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e94b590abfff2cdbf0bdaa7d9904364c8d480af5 ] 802.1X PAE frames are link-local frames, therefore they must be trapped to the CPU port. Currently, the MT753X switches treat 802.1X PAE frames as regular multicast frames, therefore flooding them to user ports. To fix this, set 802.1X PAE frames to be trapped to the CPU port(s). Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mt7530.c | 4 ++++ drivers/net/dsa/mt7530.h | 2 ++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 51d2ef0dc835..b988c8a40d53 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1005,6 +1005,10 @@ mt753x_trap_frames(struct mt7530_priv *priv) mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, MT753X_BPDU_CPU_ONLY); + /* Trap 802.1X PAE frames to the CPU port(s) */ + mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK, + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 9a45663d8b4e..6202b0f8c3f3 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -64,6 +64,8 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 #define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +#define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_PAE_PORT_FW(x) FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x) /* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c From 029e491b8c11859525a1d6a307622bbc3a4ae559 Mon Sep 17 00:00:00 2001 From: Ruan Jinjie Date: Fri, 18 Aug 2023 13:12:20 +0800 Subject: [PATCH 0557/2093] net: bgmac: Fix return value check for fixed_phy_register() [ Upstream commit 23a14488ea5882dea5851b65c9fce2127ee8fcad ] The fixed_phy_register() function returns error pointers and never returns NULL. Update the checks accordingly. Fixes: c25b23b8a387 ("bgmac: register fixed PHY for ARM BCM470X / BCM5301X chipsets") Signed-off-by: Ruan Jinjie Reviewed-by: Andrew Lunn Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bgmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 10c7c232cc4e..52ee3751187a 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1448,7 +1448,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac) int err; phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); - if (!phy_dev || IS_ERR(phy_dev)) { + if (IS_ERR(phy_dev)) { dev_err(bgmac->dev, "Failed to register fixed PHY device\n"); return -ENODEV; } From afc9d3d217939842ba4e2795356b8dd53f7a2ed6 Mon Sep 17 00:00:00 2001 From: Ruan Jinjie Date: Fri, 18 Aug 2023 13:12:21 +0800 Subject: [PATCH 0558/2093] net: bcmgenet: Fix return value check for fixed_phy_register() [ Upstream commit 32bbe64a1386065ab2aef8ce8cae7c689d0add6e ] The fixed_phy_register() function returns error pointers and never returns NULL. Update the checks accordingly. Fixes: b0ba512e25d7 ("net: bcmgenet: enable driver to work without a device tree") Signed-off-by: Ruan Jinjie Reviewed-by: Leon Romanovsky Acked-by: Doug Berger Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 1fe8038587ac..1779ee524dac 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -608,7 +608,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) }; phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); - if (!phydev || IS_ERR(phydev)) { + if (IS_ERR(phydev)) { dev_err(kdev, "failed to register fixed PHY device\n"); return -ENODEV; } From 4af1fe642f3724f1567e7c2017eeb857b08399d6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 18 Aug 2023 18:26:02 -0700 Subject: [PATCH 0559/2093] net: validate veth and vxcan peer ifindexes [ Upstream commit f534f6581ec084fe94d6759f7672bd009794b07e ] veth and vxcan need to make sure the ifindexes of the peer are not negative, core does not validate this. Using iproute2 with user-space-level checking removed: Before: # ./ip link add index 10 type veth peer index -1 # ip link show 1: lo: mtu 65536 qdisc noqueue state UNKNOWN mode DEFAULT group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 2: enp1s0: mtu 1500 qdisc fq_codel state UP mode DEFAULT group default qlen 1000 link/ether 52:54:00:74:b2:03 brd ff:ff:ff:ff:ff:ff 10: veth1@veth0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether 8a:90:ff:57:6d:5d brd ff:ff:ff:ff:ff:ff -1: veth0@veth1: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether ae:ed:18:e6:fa:7f brd ff:ff:ff:ff:ff:ff Now: $ ./ip link add index 10 type veth peer index -1 Error: ifindex can't be negative. This problem surfaced in net-next because an explicit WARN() was added, the root cause is older. Fixes: e6f8f1a739b6 ("veth: Allow to create peer link with given ifindex") Fixes: a8f820a380a2 ("can: add Virtual CAN Tunnel driver (vxcan)") Reported-by: syzbot+5ba06978f34abb058571@syzkaller.appspotmail.com Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/can/vxcan.c | 7 +------ drivers/net/veth.c | 5 +---- include/net/rtnetlink.h | 4 ++-- net/core/rtnetlink.c | 22 ++++++++++++++++++---- 4 files changed, 22 insertions(+), 16 deletions(-) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 26a472d2ea58..6d549dbdb467 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -192,12 +192,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev, nla_peer = data[VXCAN_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifla(peer_tb, - nla_data(nla_peer) + - sizeof(struct ifinfomsg), - nla_len(nla_peer) - - sizeof(struct ifinfomsg), - NULL); + err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index a71786b3e7ba..727b9278b9fe 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1716,10 +1716,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifla(peer_tb, - nla_data(nla_peer) + sizeof(struct ifinfomsg), - nla_len(nla_peer) - sizeof(struct ifinfomsg), - NULL); + err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); if (err < 0) return err; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index bf8bb3357825..9f881b74f32e 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -189,8 +189,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, int rtnl_delete_link(struct net_device *dev); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); -int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr); +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2758b3f7c021..48e300a144ad 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2220,13 +2220,27 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) return err; } -int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, - struct netlink_ext_ack *exterr) +int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, + struct netlink_ext_ack *exterr) { - return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy, + const struct ifinfomsg *ifmp; + const struct nlattr *attrs; + size_t len; + + ifmp = nla_data(nla_peer); + attrs = nla_data(nla_peer) + sizeof(struct ifinfomsg); + len = nla_len(nla_peer) - sizeof(struct ifinfomsg); + + if (ifmp->ifi_index < 0) { + NL_SET_ERR_MSG_ATTR(exterr, nla_peer, + "ifindex can't be negative"); + return -EINVAL; + } + + return nla_parse_deprecated(tb, IFLA_MAX, attrs, len, ifla_policy, exterr); } -EXPORT_SYMBOL(rtnl_nla_parse_ifla); +EXPORT_SYMBOL(rtnl_nla_parse_ifinfomsg); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { From 417e7ec0d61e2bcb4e264375badbd2e3c879467c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 19 Aug 2023 03:17:07 +0000 Subject: [PATCH 0560/2093] ipv4: fix data-races around inet->inet_id [ Upstream commit f866fbc842de5976e41ba874b76ce31710b634b5 ] UDP sendmsg() is lockless, so ip_select_ident_segs() can very well be run from multiple cpus [1] Convert inet->inet_id to an atomic_t, but implement a dedicated path for TCP, avoiding cost of a locked instruction (atomic_add_return()) Note that this patch will cause a trivial merge conflict because we added inet->flags in net-next tree. v2: added missing change in drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c (David Ahern) [1] BUG: KCSAN: data-race in __ip_make_skb / __ip_make_skb read-write to 0xffff888145af952a of 2 bytes by task 7803 on cpu 1: ip_select_ident_segs include/net/ip.h:542 [inline] ip_select_ident include/net/ip.h:556 [inline] __ip_make_skb+0x844/0xc70 net/ipv4/ip_output.c:1446 ip_make_skb+0x233/0x2c0 net/ipv4/ip_output.c:1560 udp_sendmsg+0x1199/0x1250 net/ipv4/udp.c:1260 inet_sendmsg+0x63/0x80 net/ipv4/af_inet.c:830 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg net/socket.c:748 [inline] ____sys_sendmsg+0x37c/0x4d0 net/socket.c:2494 ___sys_sendmsg net/socket.c:2548 [inline] __sys_sendmmsg+0x269/0x500 net/socket.c:2634 __do_sys_sendmmsg net/socket.c:2663 [inline] __se_sys_sendmmsg net/socket.c:2660 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2660 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888145af952a of 2 bytes by task 7804 on cpu 0: ip_select_ident_segs include/net/ip.h:541 [inline] ip_select_ident include/net/ip.h:556 [inline] __ip_make_skb+0x817/0xc70 net/ipv4/ip_output.c:1446 ip_make_skb+0x233/0x2c0 net/ipv4/ip_output.c:1560 udp_sendmsg+0x1199/0x1250 net/ipv4/udp.c:1260 inet_sendmsg+0x63/0x80 net/ipv4/af_inet.c:830 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg net/socket.c:748 [inline] ____sys_sendmsg+0x37c/0x4d0 net/socket.c:2494 ___sys_sendmsg net/socket.c:2548 [inline] __sys_sendmmsg+0x269/0x500 net/socket.c:2634 __do_sys_sendmmsg net/socket.c:2663 [inline] __se_sys_sendmmsg net/socket.c:2660 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2660 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x184d -> 0x184e Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7804 Comm: syz-executor.1 Not tainted 6.5.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 ================================================================== Fixes: 23f57406b82d ("ipv4: avoid using shared IP generator for connected sockets") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- include/net/inet_sock.h | 2 +- include/net/ip.h | 15 +++++++++++++-- net/dccp/ipv4.c | 4 ++-- net/ipv4/af_inet.c | 2 +- net/ipv4/datagram.c | 2 +- net/ipv4/tcp_ipv4.c | 4 ++-- net/sctp/socket.c | 2 +- 8 files changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index c2e7037c7ba1..7750702900fa 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1466,7 +1466,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) tp->write_seq = snd_isn; tp->snd_nxt = snd_isn; tp->snd_una = snd_isn; - inet_sk(sk)->inet_id = get_random_u16(); + atomic_set(&inet_sk(sk)->inet_id, get_random_u16()); assign_rxopt(sk, opt); if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c8ef3b881f03..c2432c2addc8 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -222,8 +222,8 @@ struct inet_sock { __s16 uc_ttl; __u16 cmsg_flags; struct ip_options_rcu __rcu *inet_opt; + atomic_t inet_id; __be16 inet_sport; - __u16 inet_id; __u8 tos; __u8 min_ttl; diff --git a/include/net/ip.h b/include/net/ip.h index 530e7257e438..1872f570abed 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -532,8 +532,19 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, * generator as much as we can. */ if (sk && inet_sk(sk)->inet_daddr) { - iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += segs; + int val; + + /* avoid atomic operations for TCP, + * as we hold socket lock at this point. + */ + if (sk_is_tcp(sk)) { + sock_owned_by_me(sk); + val = atomic_read(&inet_sk(sk)->inet_id); + atomic_set(&inet_sk(sk)->inet_id, val + segs); + } else { + val = atomic_add_return(segs, &inet_sk(sk)->inet_id); + } + iph->id = htons(val); return; } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b780827f5e0a..bfececa9e244 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -130,7 +130,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); err = dccp_connect(sk); rt = NULL; @@ -430,7 +430,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ebb737ac9e89..04853c83c85c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -340,7 +340,7 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, else inet->pmtudisc = IP_PMTUDISC_WANT; - inet->inet_id = 0; + atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4d1af0cd7d99..cb5dbee9e018 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 08921b96f972..f9b8a4a1d2ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr)); } - inet->inet_id = get_random_u16(); + atomic_set(&inet->inet_id, get_random_u16()); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -1539,7 +1539,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 83656fe03a0e..a11b0d903514 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9472,7 +9472,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = get_random_u16(); + atomic_set(&newinet->inet_id, get_random_u16()); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; From 1188e9dd7af97adb7af7ea2e9e63c771eaaf278c Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 10 Aug 2023 16:51:10 -0700 Subject: [PATCH 0561/2093] ice: fix receive buffer size miscalculation [ Upstream commit 10083aef784031fa9f06c19a1b182e6fad5338d9 ] The driver is misconfiguring the hardware for some values of MTU such that it could use multiple descriptors to receive a packet when it could have simply used one. Change the driver to use a round-up instead of the result of a shift, as the shift can truncate the lower bits of the size, and result in the problem noted above. It also aligns this driver with similar code in i40e. The insidiousness of this problem is that everything works with the wrong size, it's just not working as well as it could, as some MTU sizes end up using two or more descriptors, and there is no way to tell that is happening without looking at ice_trace or a bus analyzer. Fixes: efc2214b6047 ("ice: Add support for XDP") Reviewed-by: Przemek Kitszel Signed-off-by: Jesse Brandeburg Reviewed-by: Leon Romanovsky Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_base.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index e864634d66bc..818eca6aa4a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -396,7 +396,8 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Receive Packet Data Buffer Size. * The Packet Data Buffer Size is defined in 128 byte units. */ - rlan_ctx.dbuf = ring->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; + rlan_ctx.dbuf = DIV_ROUND_UP(ring->rx_buf_len, + BIT_ULL(ICE_RLAN_CTX_DBUF_S)); /* use 32 byte descriptors */ rlan_ctx.dsize = 1; From 7cddaed2a3f639c06ed033c92cfb552346c3ff83 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Fri, 11 Aug 2023 10:07:01 +0200 Subject: [PATCH 0562/2093] Revert "ice: Fix ice VF reset during iavf initialization" [ Upstream commit 0ecff05e6c59dd82dbcb9706db911f7fd9f40fb8 ] This reverts commit 7255355a0636b4eff08d5e8139c77d98f151c4fc. After this commit we are not able to attach VF to VM: virsh attach-interface v0 hostdev --managed 0000:41:01.0 --mac 52:52:52:52:52:52 error: Failed to attach interface error: Cannot set interface MAC to 52:52:52:52:52:52 for ifname enp65s0f0np0 vf 0: Resource temporarily unavailable ice_check_vf_ready_for_cfg() already contain waiting for reset. New condition in ice_check_vf_ready_for_reset() causing only problems. Fixes: 7255355a0636 ("ice: Fix ice VF reset during iavf initialization") Signed-off-by: Petr Oros Reviewed-by: Simon Horman Reviewed-by: Przemek Kitszel Reviewed-by: Jacob Keller Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_sriov.c | 8 ++++---- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 19 ------------------- drivers/net/ethernet/intel/ice/ice_vf_lib.h | 1 - drivers/net/ethernet/intel/ice/ice_virtchnl.c | 1 - 4 files changed, 4 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b8c31bf721ad..b719e9a771e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1240,7 +1240,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1355,7 +1355,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1409,7 +1409,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1722,7 +1722,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 71047fc34139..86abbcb480d9 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -185,25 +185,6 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) return 0; } -/** - * ice_check_vf_ready_for_reset - check if VF is ready to be reset - * @vf: VF to check if it's ready to be reset - * - * The purpose of this function is to ensure that the VF is not in reset, - * disabled, and is both initialized and active, thus enabling us to safely - * initialize another reset. - */ -int ice_check_vf_ready_for_reset(struct ice_vf *vf) -{ - int ret; - - ret = ice_check_vf_ready_for_cfg(vf); - if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) - ret = -EAGAIN; - - return ret; -} - /** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e5bed8572462..9f7fcd8e5714 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -214,7 +214,6 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); -int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ef3c709d6a75..2b4c791b6cba 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3722,7 +3722,6 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: From 850e2322ae59149475500bf1347cf60a0f7f051c Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Fri, 11 Aug 2023 10:07:02 +0200 Subject: [PATCH 0563/2093] ice: Fix NULL pointer deref during VF reset [ Upstream commit 67f6317dfa609846a227a706532439a22828c24b ] During stress test with attaching and detaching VF from KVM and simultaneously changing VFs spoofcheck and trust there was a NULL pointer dereference in ice_reset_vf that VF's VSI is null. More than one instance of ice_reset_vf() can be running at a given time. When we rebuild the VSI in ice_reset_vf, another reset can be triaged from ice_service_task. In this case we can access the currently uninitialized VSI and cause panic. The window for this racing condition has been around for a long time but it's much worse after commit 227bf4500aaa ("ice: move VSI delete outside deconfig") because the reset runs faster. ice_reset_vf() using vf->cfg_lock and when we move this lock before accessing to the VF VSI, we can fix BUG for all cases. Panic occurs sometimes in ice_vsi_is_rx_queue_active() and sometimes in ice_vsi_stop_all_rx_rings() With our reproducer, we can hit BUG: ~8h before commit 227bf4500aaa ("ice: move VSI delete outside deconfig"). ~20m after commit 227bf4500aaa ("ice: move VSI delete outside deconfig"). After this fix we are not able to reproduce it after ~48h There was commit cf90b74341ee ("ice: Fix call trace with null VSI during VF reset") which also tried to fix this issue, but it was only partially resolved and the bug still exists. [ 6420.658415] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 6420.665382] #PF: supervisor read access in kernel mode [ 6420.670521] #PF: error_code(0x0000) - not-present page [ 6420.675659] PGD 0 [ 6420.677679] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 6420.682038] CPU: 53 PID: 326472 Comm: kworker/53:0 Kdump: loaded Not tainted 5.14.0-317.el9.x86_64 #1 [ 6420.691250] Hardware name: Dell Inc. PowerEdge R750/04V528, BIOS 1.6.5 04/15/2022 [ 6420.698729] Workqueue: ice ice_service_task [ice] [ 6420.703462] RIP: 0010:ice_vsi_is_rx_queue_active+0x2d/0x60 [ice] [ 6420.705860] ice 0000:ca:00.0: VF 0 is now untrusted [ 6420.709494] Code: 00 00 66 83 bf 76 04 00 00 00 48 8b 77 10 74 3e 31 c0 eb 0f 0f b7 97 76 04 00 00 48 83 c0 01 39 c2 7e 2b 48 8b 97 68 04 00 00 <0f> b7 0c 42 48 8b 96 20 13 00 00 48 8d 94 8a 00 00 12 00 8b 12 83 [ 6420.714426] ice 0000:ca:00.0 ens7f0: Setting MAC 22:22:22:22:22:00 on VF 0. VF driver will be reinitialized [ 6420.733120] RSP: 0018:ff778d2ff383fdd8 EFLAGS: 00010246 [ 6420.733123] RAX: 0000000000000000 RBX: ff2acf1916294000 RCX: 0000000000000000 [ 6420.733125] RDX: 0000000000000000 RSI: ff2acf1f2c6401a0 RDI: ff2acf1a27301828 [ 6420.762346] RBP: ff2acf1a27301828 R08: 0000000000000010 R09: 0000000000001000 [ 6420.769476] R10: ff2acf1916286000 R11: 00000000019eba3f R12: ff2acf19066460d0 [ 6420.776611] R13: ff2acf1f2c6401a0 R14: ff2acf1f2c6401a0 R15: 00000000ffffffff [ 6420.783742] FS: 0000000000000000(0000) GS:ff2acf28ffa80000(0000) knlGS:0000000000000000 [ 6420.791829] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6420.797575] CR2: 0000000000000000 CR3: 00000016ad410003 CR4: 0000000000773ee0 [ 6420.804708] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 6420.811034] vfio-pci 0000:ca:01.0: enabling device (0000 -> 0002) [ 6420.811840] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 6420.811841] PKRU: 55555554 [ 6420.811842] Call Trace: [ 6420.811843] [ 6420.811844] ice_reset_vf+0x9a/0x450 [ice] [ 6420.811876] ice_process_vflr_event+0x8f/0xc0 [ice] [ 6420.841343] ice_service_task+0x23b/0x600 [ice] [ 6420.845884] ? __schedule+0x212/0x550 [ 6420.849550] process_one_work+0x1e2/0x3b0 [ 6420.853563] ? rescuer_thread+0x390/0x390 [ 6420.857577] worker_thread+0x50/0x3a0 [ 6420.861242] ? rescuer_thread+0x390/0x390 [ 6420.865253] kthread+0xdd/0x100 [ 6420.868400] ? kthread_complete_and_exit+0x20/0x20 [ 6420.873194] ret_from_fork+0x1f/0x30 [ 6420.876774] [ 6420.878967] Modules linked in: vfio_pci vfio_pci_core vfio_iommu_type1 vfio iavf vhost_net vhost vhost_iotlb tap tun xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nft_counter nf_tables bridge stp llc sctp ip6_udp_tunnel udp_tunnel nfp tls nfnetlink bluetooth mlx4_en mlx4_core rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs rfkill sunrpc intel_rapl_msr intel_rapl_common i10nm_edac nfit libnvdimm ipmi_ssif x86_pkg_temp_thermal intel_powerclamp coretemp irdma kvm_intel i40e kvm iTCO_wdt dcdbas ib_uverbs irqbypass iTCO_vendor_support mgag200 mei_me ib_core dell_smbios isst_if_mmio isst_if_mbox_pci rapl i2c_algo_bit drm_shmem_helper intel_cstate drm_kms_helper syscopyarea sysfillrect isst_if_common sysimgblt intel_uncore fb_sys_fops dell_wmi_descriptor wmi_bmof intel_vsec mei i2c_i801 acpi_ipmi ipmi_si i2c_smbus ipmi_devintf intel_pch_thermal acpi_power_meter pcspk r Fixes: efe41860008e ("ice: Fix memory corruption in VF driver") Fixes: f23df5220d2b ("ice: Fix spurious interrupt during removal of trusted VF") Signed-off-by: Petr Oros Reviewed-by: Simon Horman Reviewed-by: Przemek Kitszel Reviewed-by: Jacob Keller Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 86abbcb480d9..9dbe6e9bb1f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -569,11 +569,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + if (flags & ICE_VF_RESET_LOCK) + mutex_lock(&vf->cfg_lock); + else + lockdep_assert_held(&vf->cfg_lock); + if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); if (!vsi) { dev_dbg(dev, "VF is already removed\n"); - return -EINVAL; + err = -EINVAL; + goto out_unlock; } ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); @@ -582,14 +588,9 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", vf->vf_id); - return 0; + goto out_unlock; } - if (flags & ICE_VF_RESET_LOCK) - mutex_lock(&vf->cfg_lock); - else - lockdep_assert_held(&vf->cfg_lock); - /* Set VF disable bit state here, before triggering reset */ set_bit(ICE_VF_STATE_DIS, vf->vf_states); ice_trigger_vf_reset(vf, flags & ICE_VF_RESET_VFLR, false); From f41781b9d8a4af2b1ede0e1045b62359cf6b66b4 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 17 Aug 2023 16:24:59 +0800 Subject: [PATCH 0564/2093] selftests: bonding: do not set port down before adding to bond [ Upstream commit be809424659c2844a2d7ab653aacca4898538023 ] Before adding a port to bond, it need to be set down first. In the lacpdu test the author set the port down specifically. But commit a4abfa627c38 ("net: rtnetlink: Enslave device before bringing it up") changed the operation order, the kernel will set the port down _after_ adding to bond. So all the ports will be down at last and the test failed. In fact, the veth interfaces are already inactive when added. This means there's no need to set them down again before adding to the bond. Let's just remove the link down operation. Fixes: a4abfa627c38 ("net: rtnetlink: Enslave device before bringing it up") Reported-by: Zhengchao Shao Closes: https://lore.kernel.org/netdev/a0ef07c7-91b0-94bd-240d-944a330fcabd@huawei.com/ Signed-off-by: Hangbin Liu Link: https://lore.kernel.org/r/20230817082459.1685972-1-liuhangbin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh index 47ab90596acb..6358df5752f9 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -57,8 +57,8 @@ ip link add name veth2-bond type veth peer name veth2-end # add ports ip link set fbond master fab-br0 -ip link set veth1-bond down master fbond -ip link set veth2-bond down master fbond +ip link set veth1-bond master fbond +ip link set veth2-bond master fbond # bring up ip link set veth1-end up From 39d43b9cdfe8b02d9dc28994ddd578b9e5f34a7e Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 21 Aug 2023 16:45:46 +0200 Subject: [PATCH 0565/2093] can: isotp: fix support for transmission of SF without flow control [ Upstream commit 0bfe71159230bab79ee230225ae12ffecbb69f3e ] The original implementation had a very simple handling for single frame transmissions as it just sent the single frame without a timeout handling. With the new echo frame handling the echo frame was also introduced for single frames but the former exception ('simple without timers') has been maintained by accident. This leads to a 1 second timeout when closing the socket and to an -ECOMM error when CAN_ISOTP_WAIT_TX_DONE is selected. As the echo handling is always active (also for single frames) remove the wrong extra condition for single frames. Fixes: 9f39d36530e5 ("can: isotp: add support for transmission without flow control") Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20230821144547.6658-2-socketcan@hartkopp.net Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/can/isotp.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index b3c2a49b189c..8c97f4061ffd 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -175,12 +175,6 @@ static bool isotp_register_rxid(struct isotp_sock *so) return (isotp_bc_flags(so) == 0); } -static bool isotp_register_txecho(struct isotp_sock *so) -{ - /* all modes but SF_BROADCAST register for tx echo skbs */ - return (isotp_bc_flags(so) != CAN_ISOTP_SF_BROADCAST); -} - static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, @@ -1176,7 +1170,7 @@ static int isotp_release(struct socket *sock) lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (so->ifindex) { struct net_device *dev; @@ -1293,14 +1287,12 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk); - if (isotp_register_txecho(so)) { - /* no consecutive frame echo skb in flight */ - so->cfecho = 0; + /* no consecutive frame echo skb in flight */ + so->cfecho = 0; - /* register for echo skb's */ - can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), - isotp_rcv_echo, sk, "isotpe", sk); - } + /* register for echo skb's */ + can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), + isotp_rcv_echo, sk, "isotpe", sk); dev_put(dev); @@ -1521,7 +1513,7 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && isotp_register_txecho(so)) { + if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), From 9b7fd6beec371a9fceb6bca0068272a4a31ba825 Mon Sep 17 00:00:00 2001 From: Alessio Igor Bogani Date: Mon, 21 Aug 2023 10:19:27 -0700 Subject: [PATCH 0566/2093] igb: Avoid starting unnecessary workqueues [ Upstream commit b888c510f7b3d64ca75fc0f43b4a4bd1a611312f ] If ptp_clock_register() fails or CONFIG_PTP isn't enabled, avoid starting PTP related workqueues. In this way we can fix this: BUG: unable to handle page fault for address: ffffc9000440b6f8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 100000067 P4D 100000067 PUD 1001e0067 PMD 107dc5067 PTE 0 Oops: 0000 [#1] PREEMPT SMP [...] Workqueue: events igb_ptp_overflow_check RIP: 0010:igb_rd32+0x1f/0x60 [...] Call Trace: igb_ptp_read_82580+0x20/0x50 timecounter_read+0x15/0x60 igb_ptp_overflow_check+0x1a/0x50 process_one_work+0x1cb/0x3c0 worker_thread+0x53/0x3f0 ? rescuer_thread+0x370/0x370 kthread+0x142/0x160 ? kthread_associate_blkcg+0xc0/0xc0 ret_from_fork+0x1f/0x30 Fixes: 1f6e8178d685 ("igb: Prevent dropped Tx timestamps via work items and interrupts.") Fixes: d339b1331616 ("igb: add PTP Hardware Clock code") Signed-off-by: Alessio Igor Bogani Tested-by: Arpana Arland (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230821171927.2203644-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_ptp.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 15e57460e19e..07171e574e7d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1404,18 +1404,6 @@ void igb_ptp_init(struct igb_adapter *adapter) return; } - spin_lock_init(&adapter->tmreg_lock); - INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); - - if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) - INIT_DELAYED_WORK(&adapter->ptp_overflow_work, - igb_ptp_overflow_check); - - adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; - adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; - - igb_ptp_reset(adapter); - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { @@ -1425,6 +1413,18 @@ void igb_ptp_init(struct igb_adapter *adapter) dev_info(&adapter->pdev->dev, "added PHC on %s\n", adapter->netdev->name); adapter->ptp_flags |= IGB_PTP_ENABLED; + + spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + + if (adapter->ptp_flags & IGB_PTP_OVERFLOW_CHECK) + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, + igb_ptp_overflow_check); + + adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + igb_ptp_reset(adapter); } } From f94f30e2abfa17f1b8173ce1ed6fdfd0861f3d55 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Mon, 21 Aug 2023 10:17:21 -0700 Subject: [PATCH 0567/2093] igc: Fix the typo in the PTM Control macro [ Upstream commit de43975721b97283d5f17eea4228faddf08f2681 ] The IGC_PTM_CTRL_SHRT_CYC defines the time between two consecutive PTM requests. The bit resolution of this field is six bits. That bit five was missing in the mask. This patch comes to correct the typo in the IGC_PTM_CTRL_SHRT_CYC macro. Fixes: a90ec8483732 ("igc: Add support for PTP getcrosststamp()") Signed-off-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Reviewed-by: Kalesh AP Link: https://lore.kernel.org/r/20230821171721.2203572-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_defines.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index dbfa4b9dee06..90ca01889cd8 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -536,7 +536,7 @@ #define IGC_PTM_CTRL_START_NOW BIT(29) /* Start PTM Now */ #define IGC_PTM_CTRL_EN BIT(30) /* Enable PTM */ #define IGC_PTM_CTRL_TRIG BIT(31) /* PTM Cycle trigger */ -#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x2f) << 2) +#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x3f) << 2) #define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8) #define IGC_PTM_SHORT_CYC_DEFAULT 10 /* Default Short/interrupted cycle interval */ From 581668893e3126176b08349b7e35a3fd6b578d6a Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 22 Aug 2023 06:12:31 -0400 Subject: [PATCH 0568/2093] net/sched: fix a qdisc modification with ambiguous command request [ Upstream commit da71714e359b64bd7aab3bd56ec53f307f058133 ] When replacing an existing root qdisc, with one that is of the same kind, the request boils down to essentially a parameterization change i.e not one that requires allocation and grafting of a new qdisc. syzbot was able to create a scenario which resulted in a taprio qdisc replacing an existing taprio qdisc with a combination of NLM_F_CREATE, NLM_F_REPLACE and NLM_F_EXCL leading to create and graft scenario. The fix ensures that only when the qdisc kinds are different that we should allow a create and graft, otherwise it goes into the "change" codepath. While at it, fix the code and comments to improve readability. While syzbot was able to create the issue, it did not zone on the root cause. Analysis from Vladimir Oltean helped narrow it down. v1->V2 changes: - remove "inline" function definition (Vladmir) - remove extrenous braces in branches (Vladmir) - change inline function names (Pedro) - Run tdc tests (Victor) v2->v3 changes: - dont break else/if (Simon) Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+a3618a167af2021433cd@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/20230816225759.g25x76kmgzya2gei@skbuf/T/ Tested-by: Vladimir Oltean Tested-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: Victor Nogueira Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/sch_api.c | 53 ++++++++++++++++++++++++++++++++++----------- 1 file changed, 40 insertions(+), 13 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 01d07e6a6811..e8f988e1c7e6 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1550,10 +1550,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, return 0; } +static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + /* * Create/change qdisc. */ - static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1647,27 +1665,35 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { @@ -1701,6 +1727,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } +create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), From 136861956ad64429afbe31cfa90234114f7eab2e Mon Sep 17 00:00:00 2001 From: Andrii Staikov Date: Tue, 22 Aug 2023 15:16:53 -0700 Subject: [PATCH 0569/2093] i40e: fix potential NULL pointer dereferencing of pf->vf i40e_sync_vsi_filters() [ Upstream commit 9525a3c38accd2e186f52443e35e633e296cc7f5 ] Add check for pf->vf not being NULL before dereferencing pf->vf[vsi->vf_id] in updating VSI filter sync. Add a similar check before dereferencing !pf->vf[vsi->vf_id].trusted in the condition for clearing promisc mode bit. Fixes: c87c938f62d8 ("i40e: Add VF VLAN pruning") Signed-off-by: Andrii Staikov Signed-off-by: Aleksandr Loktionov Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0e01b1927c1c..08ccf0024ce1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2615,7 +2615,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) retval = i40e_correct_mac_vlan_filters (vsi, &tmp_add_list, &tmp_del_list, vlan_filters); - else + else if (pf->vf) retval = i40e_correct_vf_mac_vlan_filters (vsi, &tmp_add_list, &tmp_del_list, vlan_filters, pf->vf[vsi->vf_id].trusted); @@ -2788,7 +2788,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } /* if the VF is not trusted do not do promisc */ - if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) { + if (vsi->type == I40E_VSI_SRIOV && pf->vf && + !pf->vf[vsi->vf_id].trusted) { clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); goto out; } From 41841b585e53babdfb0fa6fdfa54f6d7c28c1206 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 18 Aug 2023 01:13:31 +0200 Subject: [PATCH 0570/2093] netfilter: nf_tables: flush pending destroy work before netlink notifier [ Upstream commit 2c9f0293280e258606e54ed2b96fa71498432eae ] Destroy work waits for the RCU grace period then it releases the objects with no mutex held. All releases objects follow this path for transactions, therefore, order is guaranteed and references to top-level objects in the hierarchy remain valid. However, netlink notifier might interfer with pending destroy work. rcu_barrier() is not correct because objects are not release via RCU callback. Flush destroy work before releasing objects from netlink notifier path. Fixes: d4bc8271db21 ("netfilter: nf_tables: netlink notifier might race to release objects") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4c2df7af73f7..3c5cac9bd9b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -10509,7 +10509,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, deleted = 0; mutex_lock(&nft_net->commit_mutex); if (!list_empty(&nf_tables_destroy_list)) - rcu_barrier(); + nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && From ed3fe5f9020c90125dfb40c1ae808d915ede68d8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Aug 2023 19:49:52 +0200 Subject: [PATCH 0571/2093] netfilter: nf_tables: fix out of memory error handling [ Upstream commit 5e1be4cdc98c989d5387ce94ff15b5ad06a5b681 ] Several instances of pipapo_resize() don't propagate allocation failures, this causes a crash when fault injection is enabled for gfp_kernel slabs. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal Reviewed-by: Stefano Brivio Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 32cfd0a84b0e..8c16681884b7 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -901,12 +901,14 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, int mask_bits) { - int rule = f->rules++, group, ret, bit_offset = 0; + int rule = f->rules, group, ret, bit_offset = 0; - ret = pipapo_resize(f, f->rules - 1, f->rules); + ret = pipapo_resize(f, f->rules, f->rules + 1); if (ret) return ret; + f->rules++; + for (group = 0; group < f->groups; group++) { int i, v; u8 mask; @@ -1051,7 +1053,9 @@ static int pipapo_expand(struct nft_pipapo_field *f, step++; if (step >= len) { if (!masks) { - pipapo_insert(f, base, 0); + err = pipapo_insert(f, base, 0); + if (err < 0) + return err; masks = 1; } goto out; @@ -1234,6 +1238,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else ret = pipapo_expand(f, start, end, f->groups * f->bb); + if (ret < 0) + return ret; + if (f->bsize > bsize_max) bsize_max = f->bsize; From b15dea3de413b80c6e51acb26c0d09354080af65 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 23 Aug 2023 09:43:48 +0300 Subject: [PATCH 0572/2093] rtnetlink: Reject negative ifindexes in RTM_NEWLINK [ Upstream commit 30188bd7838c16a98a520db1fe9df01ffc6ed368 ] Negative ifindexes are illegal, but the kernel does not validate the ifindex in the ancillary header of RTM_NEWLINK messages, resulting in the kernel generating a warning [1] when such an ifindex is specified. Fix by rejecting negative ifindexes. [1] WARNING: CPU: 0 PID: 5031 at net/core/dev.c:9593 dev_index_reserve+0x1a2/0x1c0 net/core/dev.c:9593 [...] Call Trace: register_netdevice+0x69a/0x1490 net/core/dev.c:10081 br_dev_newlink+0x27/0x110 net/bridge/br_netlink.c:1552 rtnl_newlink_create net/core/rtnetlink.c:3471 [inline] __rtnl_newlink+0x115e/0x18c0 net/core/rtnetlink.c:3688 rtnl_newlink+0x67/0xa0 net/core/rtnetlink.c:3701 rtnetlink_rcv_msg+0x439/0xd30 net/core/rtnetlink.c:6427 netlink_rcv_skb+0x16b/0x440 net/netlink/af_netlink.c:2545 netlink_unicast_kernel net/netlink/af_netlink.c:1342 [inline] netlink_unicast+0x536/0x810 net/netlink/af_netlink.c:1368 netlink_sendmsg+0x93c/0xe40 net/netlink/af_netlink.c:1910 sock_sendmsg_nosec net/socket.c:728 [inline] sock_sendmsg+0xd9/0x180 net/socket.c:751 ____sys_sendmsg+0x6ac/0x940 net/socket.c:2538 ___sys_sendmsg+0x135/0x1d0 net/socket.c:2592 __sys_sendmsg+0x117/0x1e0 net/socket.c:2621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 38f7b870d4a6 ("[RTNETLINK]: Link creation API") Reported-by: syzbot+5ba06978f34abb058571@syzkaller.appspotmail.com Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230823064348.2252280-1-idosch@nvidia.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/core/rtnetlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 48e300a144ad..9d4507aa736b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3465,6 +3465,9 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) { link_specified = true; dev = __dev_get_by_index(net, ifm->ifi_index); + } else if (ifm->ifi_index < 0) { + NL_SET_ERR_MSG(extack, "ifindex can't be negative"); + return -EINVAL; } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) { link_specified = true; dev = rtnl_dev_get(net, tb); From a0559fd0e14eb144b8151e3104785138786274a8 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 23 Aug 2023 15:19:04 +0800 Subject: [PATCH 0573/2093] bonding: fix macvlan over alb bond support [ Upstream commit e74216b8def3803e98ae536de78733e9d7f3b109 ] The commit 14af9963ba1e ("bonding: Support macvlans on top of tlb/rlb mode bonds") aims to enable the use of macvlans on top of rlb bond mode. However, the current rlb bond mode only handles ARP packets to update remote neighbor entries. This causes an issue when a macvlan is on top of the bond, and remote devices send packets to the macvlan using the bond's MAC address as the destination. After delivering the packets to the macvlan, the macvlan will rejects them as the MAC address is incorrect. Consequently, this commit makes macvlan over bond non-functional. To address this problem, one potential solution is to check for the presence of a macvlan port on the bond device using netif_is_macvlan_port(bond->dev) and return NULL in the rlb_arp_xmit() function. However, this approach doesn't fully resolve the situation when a VLAN exists between the bond and macvlan. So let's just do a partial revert for commit 14af9963ba1e in rlb_arp_xmit(). As the comment said, Don't modify or load balance ARPs that do not originate locally. Fixes: 14af9963ba1e ("bonding: Support macvlans on top of tlb/rlb mode bonds") Reported-by: susan.zheng@veritas.com Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2117816 Signed-off-by: Hangbin Liu Acked-by: Jay Vosburgh Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_alb.c | 6 +++--- include/net/bonding.h | 11 +---------- 2 files changed, 4 insertions(+), 13 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index b9dbad3a8af8..fc5da5d7744d 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -660,10 +660,10 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) return NULL; arp = (struct arp_pkt *)skb_network_header(skb); - /* Don't modify or load balance ARPs that do not originate locally - * (e.g.,arrive via a bridge). + /* Don't modify or load balance ARPs that do not originate + * from the bond itself or a VLAN directly above the bond. */ - if (!bond_slave_has_mac_rx(bond, arp->mac_src)) + if (!bond_slave_has_mac_rcu(bond, arp->mac_src)) return NULL; dev = ip_dev_find(dev_net(bond->dev), arp->ip_src); diff --git a/include/net/bonding.h b/include/net/bonding.h index 17329a19f0c6..9a3ac960dfe1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -727,23 +727,14 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, } /* Caller must hold rcu_read_lock() for read */ -static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) +static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; - struct netdev_hw_addr *ha; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; - - if (netdev_uc_empty(bond->dev)) - return false; - - netdev_for_each_uc_addr(ha, bond->dev) - if (ether_addr_equal_64bits(mac, ha->addr)) - return true; - return false; } From 2800385fda534f1bfed8389d634c393a07570bba Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 26 Apr 2023 15:03:23 -0700 Subject: [PATCH 0574/2093] KVM: x86: Preserve TDP MMU roots until they are explicitly invalidated commit edbdb43fc96b11b3bfa531be306a1993d9fe89ec upstream. Preserve TDP MMU roots until they are explicitly invalidated by gifting the TDP MMU itself a reference to a root when it is allocated. Keeping a reference in the TDP MMU fixes a flaw where the TDP MMU exhibits terrible performance, and can potentially even soft-hang a vCPU, if a vCPU frequently unloads its roots, e.g. when KVM is emulating SMI+RSM. When KVM emulates something that invalidates _all_ TLB entries, e.g. SMI and RSM, KVM unloads all of the vCPUs roots (KVM keeps a small per-vCPU cache of previous roots). Unloading roots is a simple way to ensure KVM flushes and synchronizes all roots for the vCPU, as KVM flushes and syncs when allocating a "new" root (from the vCPU's perspective). In the shadow MMU, KVM keeps track of all shadow pages, roots included, in a per-VM hash table. Unloading a shadow MMU root just wipes it from the per-vCPU cache; the root is still tracked in the per-VM hash table. When KVM loads a "new" root for the vCPU, KVM will find the old, unloaded root in the per-VM hash table. Unlike the shadow MMU, the TDP MMU doesn't track "inactive" roots in a per-VM structure, where "active" in this case means a root is either in-use or cached as a previous root by at least one vCPU. When a TDP MMU root becomes inactive, i.e. the last vCPU reference to the root is put, KVM immediately frees the root (asterisk on "immediately" as the actual freeing may be done by a worker, but for all intents and purposes the root is gone). The TDP MMU behavior is especially problematic for 1-vCPU setups, as unloading all roots effectively frees all roots. The issue is mitigated to some degree in multi-vCPU setups as a different vCPU usually holds a reference to an unloaded root and thus keeps the root alive, allowing the vCPU to reuse its old root after unloading (with a flush+sync). The TDP MMU flaw has been known for some time, as until very recently, KVM's handling of CR0.WP also triggered unloading of all roots. The CR0.WP toggling scenario was eventually addressed by not unloading roots when _only_ CR0.WP is toggled, but such an approach doesn't Just Work for emulating SMM as KVM must emulate a full TLB flush on entry and exit to/from SMM. Given that the shadow MMU plays nice with unloading roots at will, teaching the TDP MMU to do the same is far less complex than modifying KVM to track which roots need to be flushed before reuse. Note, preserving all possible TDP MMU roots is not a concern with respect to memory consumption. Now that the role for direct MMUs doesn't include information about the guest, e.g. CR0.PG, CR0.WP, CR4.SMEP, etc., there are _at most_ six possible roots (where "guest_mode" here means L2): 1. 4-level !SMM !guest_mode 2. 4-level SMM !guest_mode 3. 5-level !SMM !guest_mode 4. 5-level SMM !guest_mode 5. 4-level !SMM guest_mode 6. 5-level !SMM guest_mode And because each vCPU can track 4 valid roots, a VM can already have all 6 root combinations live at any given time. Not to mention that, in practice, no sane VMM will advertise different guest.MAXPHYADDR values across vCPUs, i.e. KVM won't ever use both 4-level and 5-level roots for a single VM. Furthermore, the vast majority of modern hypervisors will utilize EPT/NPT when available, thus the guest_mode=%true cases are also unlikely to be utilized. Reported-by: Jeremi Piotrowski Link: https://lore.kernel.org/all/959c5bce-beb5-b463-7158-33fc4a4f910c@linux.microsoft.com Link: https://lkml.kernel.org/r/20220209170020.1775368-1-pbonzini%40redhat.com Link: https://lore.kernel.org/all/20230322013731.102955-1-minipli@grsecurity.net Link: https://lore.kernel.org/all/000000000000a0bc2b05f9dd7fab@google.com Link: https://lore.kernel.org/all/000000000000eca0b905fa0f7756@google.com Cc: Ben Gardon Cc: David Matlack Cc: stable@vger.kernel.org Tested-by: Jeremi Piotrowski Link: https://lore.kernel.org/r/20230426220323.3079789-1-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu/tdp_mmu.c | 121 +++++++++++++++++-------------------- 1 file changed, 56 insertions(+), 65 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 672f0432d777..70945f00ec41 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -51,7 +51,17 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; - /* Also waits for any queued work items. */ + /* + * Invalidate all roots, which besides the obvious, schedules all roots + * for zapping and thus puts the TDP MMU's reference to each root, i.e. + * ultimately frees all roots. + */ + kvm_tdp_mmu_invalidate_all_roots(kvm); + + /* + * Destroying a workqueue also first flushes the workqueue, i.e. no + * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). + */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); @@ -127,16 +137,6 @@ static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); } -static inline bool kvm_tdp_root_mark_invalid(struct kvm_mmu_page *page) -{ - union kvm_mmu_page_role role = page->role; - role.invalid = true; - - /* No need to use cmpxchg, only the invalid bit can change. */ - role.word = xchg(&page->role.word, role.word); - return role.invalid; -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -145,45 +145,12 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; - WARN_ON(!root->tdp_mmu_page); - /* - * The root now has refcount=0. It is valid, but readers already - * cannot acquire a reference to it because kvm_tdp_mmu_get_root() - * rejects it. This remains true for the rest of the execution - * of this function, because readers visit valid roots only - * (except for tdp_mmu_zap_root_work(), which however - * does not acquire any reference itself). - * - * Even though there are flows that need to visit all roots for - * correctness, they all take mmu_lock for write, so they cannot yet - * run concurrently. The same is true after kvm_tdp_root_mark_invalid, - * since the root still has refcount=0. - * - * However, tdp_mmu_zap_root can yield, and writers do not expect to - * see refcount=0 (see for example kvm_tdp_mmu_invalidate_all_roots()). - * So the root temporarily gets an extra reference, going to refcount=1 - * while staying invalid. Readers still cannot acquire any reference; - * but writers are now allowed to run if tdp_mmu_zap_root yields and - * they might take an extra reference if they themselves yield. - * Therefore, when the reference is given back by the worker, - * there is no guarantee that the refcount is still 1. If not, whoever - * puts the last reference will free the page, but they will not have to - * zap the root because a root cannot go from invalid to valid. + * The TDP MMU itself holds a reference to each root until the root is + * explicitly invalidated, i.e. the final reference should be never be + * put for a valid root. */ - if (!kvm_tdp_root_mark_invalid(root)) { - refcount_set(&root->tdp_mmu_root_count, 1); - - /* - * Zapping the root in a worker is not just "nice to have"; - * it is required because kvm_tdp_mmu_invalidate_all_roots() - * skips already-invalid roots. If kvm_tdp_mmu_put_root() did - * not add the root to the workqueue, kvm_tdp_mmu_zap_all_fast() - * might return with some roots not zapped yet. - */ - tdp_mmu_schedule_zap_root(kvm, root); - return; - } + KVM_BUG_ON(!is_tdp_mmu_page(root) || !root->role.invalid, kvm); spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_del_rcu(&root->link); @@ -329,7 +296,14 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) root = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_sp(root, NULL, 0, role); - refcount_set(&root->tdp_mmu_root_count, 1); + /* + * TDP MMU roots are kept until they are explicitly invalidated, either + * by a memslot update or by the destruction of the VM. Initialize the + * refcount to two; one reference for the vCPU, and one reference for + * the TDP MMU itself, which is held until the root is invalidated and + * is ultimately put by tdp_mmu_zap_root_work(). + */ + refcount_set(&root->tdp_mmu_root_count, 2); spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); @@ -1027,32 +1001,49 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously, so a reference is taken on all roots. - * Using a separate workqueue makes it easy to ensure that the destruction is - * performed before the "fast zap" completes, without keeping a separate list - * of invalidated roots; the list is effectively the list of work items in - * the workqueue. + * zapping is performed asynchronously. Using a separate workqueue makes it + * easy to ensure that the destruction is performed before the "fast zap" + * completes, without keeping a separate list of invalidated roots; the list is + * effectively the list of work items in the workqueue. * - * Get a reference even if the root is already invalid, the asynchronous worker - * assumes it was gifted a reference to the root it processes. Because mmu_lock - * is held for write, it should be impossible to observe a root with zero refcount, - * i.e. the list of roots cannot be stale. - * - * This has essentially the same effect for the TDP MMU - * as updating mmu_valid_gen does for the shadow MMU. + * Note, the asynchronous worker is gifted the TDP MMU's reference. + * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); - list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { - if (!root->role.invalid && - !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) { + /* + * mmu_lock must be held for write to ensure that a root doesn't become + * invalid while there are active readers (invalidating a root while + * there are active readers may or may not be problematic in practice, + * but it's uncharted territory and not supported). + * + * Waive the assertion if there are no users of @kvm, i.e. the VM is + * being destroyed after all references have been put, or if no vCPUs + * have been created (which means there are no roots), i.e. the VM is + * being destroyed in an error path of KVM_CREATE_VM. + */ + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && + refcount_read(&kvm->users_count) && kvm->created_vcpus) + lockdep_assert_held_write(&kvm->mmu_lock); + + /* + * As above, mmu_lock isn't held when destroying the VM! There can't + * be other references to @kvm, i.e. nothing else can invalidate roots + * or be consuming roots, but walking the list of roots does need to be + * guarded against roots being deleted by the asynchronous zap worker. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + if (!root->role.invalid) { root->role.invalid = true; tdp_mmu_schedule_zap_root(kvm, root); } } + + rcu_read_unlock(); } /* From 82d811ff566594de3676f35808e8a9e19c5c864c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Aug 2023 18:01:04 -0700 Subject: [PATCH 0575/2093] KVM: x86/mmu: Fix an sign-extension bug with mmu_seq that hangs vCPUs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Upstream commit ba6e3fe25543 ("KVM: x86/mmu: Grab mmu_invalidate_seq in kvm_faultin_pfn()") unknowingly fixed the bug in v6.3 when refactoring how KVM tracks the sequence counter snapshot. Take the vCPU's mmu_seq snapshot as an "unsigned long" instead of an "int" when checking to see if a page fault is stale, as the sequence count is stored as an "unsigned long" everywhere else in KVM. This fixes a bug where KVM will effectively hang vCPUs due to always thinking page faults are stale, which results in KVM refusing to "fix" faults. mmu_invalidate_seq (née mmu_notifier_seq) is a sequence counter used when KVM is handling page faults to detect if userspace mappings relevant to the guest were invalidated between snapshotting the counter and acquiring mmu_lock, i.e. to ensure that the userspace mapping KVM is using to resolve the page fault is fresh. If KVM sees that the counter has changed, KVM simply resumes the guest without fixing the fault. What _should_ happen is that the source of the mmu_notifier invalidations eventually goes away, mmu_invalidate_seq becomes stable, and KVM can once again fix guest page fault(s). But for a long-lived VM and/or a VM that the host just doesn't particularly like, it's possible for a VM to be on the receiving end of 2 billion (with a B) mmu_notifier invalidations. When that happens, bit 31 will be set in mmu_invalidate_seq. This causes the value to be turned into a 32-bit negative value when implicitly cast to an "int" by is_page_fault_stale(), and then sign-extended into a 64-bit unsigned when the signed "int" is implicitly cast back to an "unsigned long" on the call to mmu_invalidate_retry_hva(). As a result of the casting and sign-extension, given a sequence counter of e.g. 0x8002dc25, mmu_invalidate_retry_hva() ends up doing if (0x8002dc25 != 0xffffffff8002dc25) and signals that the page fault is stale and needs to be retried even though the sequence counter is stable, and KVM effectively hangs any vCPU that takes a page fault (EPT violation or #NPF when TDP is enabled). Reported-by: Brian Rak Reported-by: Amaan Cheval Reported-by: Eric Wheeler Closes: https://lore.kernel.org/all/f023d927-52aa-7e08-2ee5-59a2fbc65953@gameservers.com Fixes: a955cad84cda ("KVM: x86/mmu: Retry page fault if root is invalidated by memslot update") Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu/mmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 230108a90cf3..beca03556379 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4212,7 +4212,8 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault, int mmu_seq) + struct kvm_page_fault *fault, + unsigned long mmu_seq) { struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); From 0d617fb6d5132dc1ffd12ec0c90af71fd89c63a0 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 7 Dec 2022 03:53:34 +0000 Subject: [PATCH 0576/2093] io_uring: get rid of double locking Commit 11373026f2960390d5e330df4e92735c4265c440 upstream. We don't need to take both uring_locks at once, msg_ring can be split in two parts, first getting a file from the filetable of the first ring and then installing it into the second one. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a80ecc2bc99c3b3f2cf20015d618b7c51419a797.1670384893.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/msg_ring.c | 87 ++++++++++++++++++++++++++------------------- io_uring/msg_ring.h | 1 + io_uring/opdef.c | 1 + 3 files changed, 52 insertions(+), 37 deletions(-) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 3526389ac218..ee8e7ac8c582 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -15,6 +15,7 @@ struct io_msg { struct file *file; + struct file *src_file; u64 user_data; u32 len; u32 cmd; @@ -23,6 +24,17 @@ struct io_msg { u32 flags; }; +void io_msg_ring_cleanup(struct io_kiocb *req) +{ + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + + if (WARN_ON_ONCE(!msg->src_file)) + return; + + fput(msg->src_file); + msg->src_file = NULL; +} + static int io_msg_ring_data(struct io_kiocb *req) { struct io_ring_ctx *target_ctx = req->file->private_data; @@ -39,17 +51,13 @@ static int io_msg_ring_data(struct io_kiocb *req) return -EOVERFLOW; } -static void io_double_unlock_ctx(struct io_ring_ctx *ctx, - struct io_ring_ctx *octx, +static void io_double_unlock_ctx(struct io_ring_ctx *octx, unsigned int issue_flags) { - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); mutex_unlock(&octx->uring_lock); } -static int io_double_lock_ctx(struct io_ring_ctx *ctx, - struct io_ring_ctx *octx, +static int io_double_lock_ctx(struct io_ring_ctx *octx, unsigned int issue_flags) { /* @@ -62,26 +70,36 @@ static int io_double_lock_ctx(struct io_ring_ctx *ctx, return -EAGAIN; return 0; } - - /* Always grab smallest value ctx first. We know ctx != octx. */ - if (ctx < octx) { - mutex_lock(&ctx->uring_lock); - mutex_lock(&octx->uring_lock); - } else { - mutex_lock(&octx->uring_lock); - mutex_lock(&ctx->uring_lock); - } - + mutex_lock(&octx->uring_lock); return 0; } +static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; + unsigned long file_ptr; + int idx = msg->src_fd; + + io_ring_submit_lock(ctx, issue_flags); + if (likely(idx < ctx->nr_user_files)) { + idx = array_index_nospec(idx, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, idx)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + if (file) + get_file(file); + } + io_ring_submit_unlock(ctx, issue_flags); + return file; +} + static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); struct io_ring_ctx *ctx = req->ctx; - unsigned long file_ptr; - struct file *src_file; + struct file *src_file = msg->src_file; int ret; if (msg->len) @@ -90,28 +108,22 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) return -EINVAL; if (target_ctx->flags & IORING_SETUP_R_DISABLED) return -EBADFD; + if (!src_file) { + src_file = io_msg_grab_file(req, issue_flags); + if (!src_file) + return -EBADF; + msg->src_file = src_file; + req->flags |= REQ_F_NEED_CLEANUP; + } - ret = io_double_lock_ctx(ctx, target_ctx, issue_flags); - if (unlikely(ret)) - return ret; - - ret = -EBADF; - if (unlikely(msg->src_fd >= ctx->nr_user_files)) - goto out_unlock; - - msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr; - if (!file_ptr) - goto out_unlock; - - src_file = (struct file *) (file_ptr & FFS_MASK); - get_file(src_file); + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) + return -EAGAIN; ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); - if (ret < 0) { - fput(src_file); + if (ret < 0) goto out_unlock; - } + msg->src_file = NULL; + req->flags &= ~REQ_F_NEED_CLEANUP; if (msg->flags & IORING_MSG_RING_CQE_SKIP) goto out_unlock; @@ -125,7 +137,7 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) if (!io_post_aux_cqe(target_ctx, msg->user_data, ret, 0, true)) ret = -EOVERFLOW; out_unlock: - io_double_unlock_ctx(ctx, target_ctx, issue_flags); + io_double_unlock_ctx(target_ctx, issue_flags); return ret; } @@ -136,6 +148,7 @@ int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->buf_index || sqe->personality)) return -EINVAL; + msg->src_file = NULL; msg->user_data = READ_ONCE(sqe->off); msg->len = READ_ONCE(sqe->len); msg->cmd = READ_ONCE(sqe->addr); diff --git a/io_uring/msg_ring.h b/io_uring/msg_ring.h index fb9601f202d0..3987ee6c0e5f 100644 --- a/io_uring/msg_ring.h +++ b/io_uring/msg_ring.h @@ -2,3 +2,4 @@ int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags); +void io_msg_ring_cleanup(struct io_kiocb *req); diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 04dd2c983fce..3aa0d65c50e3 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -445,6 +445,7 @@ const struct io_op_def io_op_defs[] = { .name = "MSG_RING", .prep = io_msg_ring_prep, .issue = io_msg_ring, + .cleanup = io_msg_ring_cleanup, }, [IORING_OP_FSETXATTR] = { .needs_file = 1, From 4f59375285188baa5a22100af24f0fb3e2bc0e3d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 7 Dec 2022 03:53:35 +0000 Subject: [PATCH 0577/2093] io_uring: extract a io_msg_install_complete helper Commit 172113101641cf1f9628c528ec790cb809f2b704 upstream. Extract a helper called io_msg_install_complete() from io_msg_send_fd(), will be used later. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/1500ca1054cc4286a3ee1c60aacead57fcdfa02a.1670384893.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/msg_ring.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index ee8e7ac8c582..fd96a0cd85f0 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -94,40 +94,25 @@ static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_fl return file; } -static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); - struct io_ring_ctx *ctx = req->ctx; struct file *src_file = msg->src_file; int ret; - if (msg->len) - return -EINVAL; - if (target_ctx == ctx) - return -EINVAL; - if (target_ctx->flags & IORING_SETUP_R_DISABLED) - return -EBADFD; - if (!src_file) { - src_file = io_msg_grab_file(req, issue_flags); - if (!src_file) - return -EBADF; - msg->src_file = src_file; - req->flags |= REQ_F_NEED_CLEANUP; - } - if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) return -EAGAIN; ret = __io_fixed_fd_install(target_ctx, src_file, msg->dst_fd); if (ret < 0) goto out_unlock; + msg->src_file = NULL; req->flags &= ~REQ_F_NEED_CLEANUP; if (msg->flags & IORING_MSG_RING_CQE_SKIP) goto out_unlock; - /* * If this fails, the target still received the file descriptor but * wasn't notified of the fact. This means that if this request @@ -141,6 +126,25 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) return ret; } +static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *target_ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct io_ring_ctx *ctx = req->ctx; + struct file *src_file = msg->src_file; + + if (target_ctx == ctx) + return -EINVAL; + if (!src_file) { + src_file = io_msg_grab_file(req, issue_flags); + if (!src_file) + return -EBADF; + msg->src_file = src_file; + req->flags |= REQ_F_NEED_CLEANUP; + } + return io_msg_install_complete(req, issue_flags); +} + int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); From 816c7cecf6a0cf04b5b543690e38a1b15bdf8e88 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 19 Jan 2023 09:01:27 -0700 Subject: [PATCH 0578/2093] io_uring/msg_ring: move double lock/unlock helpers higher up Commit 423d5081d0451faa59a707e57373801da5b40141 upstream. In preparation for needing them somewhere else, move them and get rid of the unused 'issue_flags' for the unlock side. No functional changes in this patch. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/msg_ring.c | 47 ++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 24 deletions(-) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index fd96a0cd85f0..825d8c579fd3 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -24,6 +24,28 @@ struct io_msg { u32 flags; }; +static void io_double_unlock_ctx(struct io_ring_ctx *octx) +{ + mutex_unlock(&octx->uring_lock); +} + +static int io_double_lock_ctx(struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + /* + * To ensure proper ordering between the two ctxs, we can only + * attempt a trylock on the target. If that fails and we already have + * the source ctx lock, punt to io-wq. + */ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + if (!mutex_trylock(&octx->uring_lock)) + return -EAGAIN; + return 0; + } + mutex_lock(&octx->uring_lock); + return 0; +} + void io_msg_ring_cleanup(struct io_kiocb *req) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); @@ -51,29 +73,6 @@ static int io_msg_ring_data(struct io_kiocb *req) return -EOVERFLOW; } -static void io_double_unlock_ctx(struct io_ring_ctx *octx, - unsigned int issue_flags) -{ - mutex_unlock(&octx->uring_lock); -} - -static int io_double_lock_ctx(struct io_ring_ctx *octx, - unsigned int issue_flags) -{ - /* - * To ensure proper ordering between the two ctxs, we can only - * attempt a trylock on the target. If that fails and we already have - * the source ctx lock, punt to io-wq. - */ - if (!(issue_flags & IO_URING_F_UNLOCKED)) { - if (!mutex_trylock(&octx->uring_lock)) - return -EAGAIN; - return 0; - } - mutex_lock(&octx->uring_lock); - return 0; -} - static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); @@ -122,7 +121,7 @@ static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flag if (!io_post_aux_cqe(target_ctx, msg->user_data, ret, 0, true)) ret = -EOVERFLOW; out_unlock: - io_double_unlock_ctx(target_ctx, issue_flags); + io_double_unlock_ctx(target_ctx); return ret; } From 22a406b3629a10979916ea7cace47858410117b5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 22 Aug 2023 18:00:02 -0600 Subject: [PATCH 0579/2093] io_uring/msg_ring: fix missing lock on overflow for IOPOLL Commit e12d7a46f65ae4b7d58a5e0c1cbfa825cf8d830d upstream. If the target ring is configured with IOPOLL, then we always need to hold the target ring uring_lock before posting CQEs. We could just grab it unconditionally, but since we don't expect many target rings to be of this type, make grabbing the uring_lock conditional on the ring type. Link: https://lore.kernel.org/io-uring/Y8krlYa52%2F0YGqkg@ip-172-31-85-199.ec2.internal/ Reported-by: Xingyuan Mo Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/msg_ring.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 825d8c579fd3..cd922d2bef5f 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -57,20 +57,30 @@ void io_msg_ring_cleanup(struct io_kiocb *req) msg->src_file = NULL; } -static int io_msg_ring_data(struct io_kiocb *req) +static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + int ret; if (msg->src_fd || msg->dst_fd || msg->flags) return -EINVAL; if (target_ctx->flags & IORING_SETUP_R_DISABLED) return -EBADFD; - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) - return 0; + ret = -EOVERFLOW; + if (target_ctx->flags & IORING_SETUP_IOPOLL) { + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) + return -EAGAIN; + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = 0; + io_double_unlock_ctx(target_ctx); + } else { + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0, true)) + ret = 0; + } - return -EOVERFLOW; + return ret; } static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) @@ -175,7 +185,7 @@ int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) switch (msg->cmd) { case IORING_MSG_DATA: - ret = io_msg_ring_data(req); + ret = io_msg_ring_data(req, issue_flags); break; case IORING_MSG_SEND_FD: ret = io_msg_send_fd(req, issue_flags); From 014fec5540108047a92ce9527e0ec285b0d59691 Mon Sep 17 00:00:00 2001 From: BrenoRCBrito Date: Fri, 18 Aug 2023 18:14:16 -0300 Subject: [PATCH 0580/2093] ASoC: amd: yc: Add VivoBook Pro 15 to quirks list for acp6x commit 3b1f08833c45d0167741e4097b0150e7cf086102 upstream. VivoBook Pro 15 Ryzen Edition uses Ryzen 6800H processor, and adding to quirks list for acp6x will enable internal mic. Signed-off-by: BrenoRCBrito Link: https://lore.kernel.org/r/20230818211417.32167-1-brenorcbrito@gmail.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/amd/yc/acp6x-mach.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index c1ca3ceac5f2..26101299af4d 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -248,6 +248,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 14 2022"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RC"), + } + }, { .driver_data = &acp6x_card, .matches = { From 85607ef399d9763c9a5d122eb6bce91d27d85cb9 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 23 Aug 2023 09:53:08 +0100 Subject: [PATCH 0581/2093] ASoC: cs35l41: Correct amp_gain_tlv values commit 1613781d7e8a93618ff3a6b37f81f06769b53717 upstream. The current analog gain TLV seems to have completely incorrect values in it. The gain starts at 0.5dB, proceeds in 1dB steps, and has no mute value, correct the control to match. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20230823085308.753572-1-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/cs35l41.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index f2b5032daa6a..2f4b0ee93ace 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -167,7 +167,7 @@ static int cs35l41_get_fs_mon_config_index(int freq) static const DECLARE_TLV_DB_RANGE(dig_vol_tlv, 0, 0, TLV_DB_SCALE_ITEM(TLV_DB_GAIN_MUTE, 0, 1), 1, 913, TLV_DB_MINMAX_ITEM(-10200, 1200)); -static DECLARE_TLV_DB_SCALE(amp_gain_tlv, 0, 1, 1); +static DECLARE_TLV_DB_SCALE(amp_gain_tlv, 50, 100, 0); static const struct snd_kcontrol_new dre_ctrl = SOC_DAPM_SINGLE("Switch", CS35L41_PWR_CTRL3, 20, 1, 0); From b8b7243aafecc1046d90b6d636355e2a1fe99835 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 23 Aug 2023 14:51:39 +1000 Subject: [PATCH 0582/2093] ibmveth: Use dcbf rather than dcbfl commit bfedba3b2c7793ce127680bc8f70711e05ec7a17 upstream. When building for power4, newer binutils don't recognise the "dcbfl" extended mnemonic. dcbfl RA, RB is equivalent to dcbf RA, RB, 1. Switch to "dcbf" to avoid the build error. Signed-off-by: Michael Ellerman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmveth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 5b96cd94dcd2..0b4ec6e41eb4 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -203,7 +203,7 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length) unsigned long offset; for (offset = 0; offset < length; offset += SMP_CACHE_BYTES) - asm("dcbfl %0,%1" :: "b" (addr), "r" (offset)); + asm("dcbf %0,%1,1" :: "b" (addr), "r" (offset)); } /* replenish the buffers for a pool. note that we don't need to From e6a60eccd0c8c015a2493ceea832d2c0eaf83dba Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Fri, 18 Aug 2023 09:40:04 +0800 Subject: [PATCH 0583/2093] wifi: mac80211: limit reorder_buf_filtered to avoid UBSAN warning commit b98c16107cc1647242abbd11f234c05a3a5864f6 upstream. The commit 06470f7468c8 ("mac80211: add API to allow filtering frames in BA sessions") added reorder_buf_filtered to mark frames filtered by firmware, and it can only work correctly if hw.max_rx_aggregation_subframes <= 64 since it stores the bitmap in a u64 variable. However, new HE or EHT devices can support BlockAck number up to 256 or 1024, and then using a higher subframe index leads UBSAN warning: UBSAN: shift-out-of-bounds in net/mac80211/rx.c:1129:39 shift exponent 215 is too large for 64-bit type 'long long unsigned int' Call Trace: dump_stack_lvl+0x48/0x70 dump_stack+0x10/0x20 __ubsan_handle_shift_out_of_bounds+0x1ac/0x360 ieee80211_release_reorder_frame.constprop.0.cold+0x64/0x69 [mac80211] ieee80211_sta_reorder_release+0x9c/0x400 [mac80211] ieee80211_prepare_and_rx_handle+0x1234/0x1420 [mac80211] ieee80211_rx_list+0xaef/0xf60 [mac80211] ieee80211_rx_napi+0x53/0xd0 [mac80211] Since only old hardware that supports <=64 BlockAck uses ieee80211_mark_rx_ba_filtered_frames(), limit the use as it is, so add a WARN_ONCE() and comment to note to avoid using this function if hardware capability is not suitable. Signed-off-by: Ping-Ke Shih Link: https://lore.kernel.org/r/20230818014004.16177-1-pkshih@realtek.com [edit commit message] Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- include/net/mac80211.h | 1 + net/mac80211/rx.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 72b739dc6d53..8a338c33118f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6444,6 +6444,7 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, * marks frames marked in the bitmap as having been filtered. Afterwards, it * checks if any frames in the window starting from @ssn can now be released * (in case they were only waiting for frames that were filtered.) + * (Only work correctly if @max_rx_aggregation_subframes <= 64 frames) */ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0f81492da0b4..55dc0610e863 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1102,7 +1102,8 @@ static inline bool ieee80211_rx_reorder_ready(struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *tail = skb_peek_tail(frames); struct ieee80211_rx_status *status; - if (tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) + if (tid_agg_rx->reorder_buf_filtered && + tid_agg_rx->reorder_buf_filtered & BIT_ULL(index)) return true; if (!tail) @@ -1143,7 +1144,8 @@ static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, } no_frame: - tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); + if (tid_agg_rx->reorder_buf_filtered) + tid_agg_rx->reorder_buf_filtered &= ~BIT_ULL(index); tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num); } @@ -4162,6 +4164,7 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, u16 received_mpdus) { + struct ieee80211_local *local; struct sta_info *sta; struct tid_ampdu_rx *tid_agg_rx; struct sk_buff_head frames; @@ -4179,6 +4182,11 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, sta = container_of(pubsta, struct sta_info, sta); + local = sta->sdata->local; + WARN_ONCE(local->hw.max_rx_aggregation_subframes > 64, + "RX BA marker can't support max_rx_aggregation_subframes %u > 64\n", + local->hw.max_rx_aggregation_subframes); + if (!ieee80211_rx_data_set_sta(&rx, sta, -1)) return; From ac467d7405fe69b07b5a3fe233fd62fad7b2faec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Apitzsch?= Date: Sat, 19 Aug 2023 09:12:15 +0200 Subject: [PATCH 0584/2093] platform/x86: ideapad-laptop: Add support for new hotkeys found on ThinkBook 14s Yoga ITL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a260f7d726fde52c0278bd3fa085a758639bcee2 upstream. The Lenovo Thinkbook 14s Yoga ITL has 4 new symbols/shortcuts on their F9-F11 and PrtSc keys: F9: Has a symbol of a head with a headset, the manual says "Service key" F10: Has a symbol of a telephone horn which has been picked up from the receiver, the manual says: "Answer incoming calls" F11: Has a symbol of a telephone horn which is resting on the receiver, the manual says: "Reject incoming calls" PrtSc: Has a symbol of a siccor and a dashed ellipse, the manual says: "Open the Windows 'Snipping' Tool app" This commit adds support for these 4 new hkey events. Signed-off-by: André Apitzsch Link: https://lore.kernel.org/r/20230819-lenovo_keys-v1-1-9d34eac88e0a@apitzsch.eu Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/ideapad-laptop.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index bd38c7dcae34..de03b8889e9d 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1176,6 +1176,11 @@ static const struct key_entry ideapad_keymap[] = { { KE_IGNORE, 0x03 | IDEAPAD_WMI_KEY }, /* Customizable Lenovo Hotkey ("star" with 'S' inside) */ { KE_KEY, 0x01 | IDEAPAD_WMI_KEY, { KEY_FAVORITES } }, + { KE_KEY, 0x04 | IDEAPAD_WMI_KEY, { KEY_SELECTIVE_SCREENSHOT } }, + /* Lenovo Support */ + { KE_KEY, 0x07 | IDEAPAD_WMI_KEY, { KEY_HELP } }, + { KE_KEY, 0x0e | IDEAPAD_WMI_KEY, { KEY_PICKUP_PHONE } }, + { KE_KEY, 0x0f | IDEAPAD_WMI_KEY, { KEY_HANGUP_PHONE } }, /* Dark mode toggle */ { KE_KEY, 0x13 | IDEAPAD_WMI_KEY, { KEY_PROG1 } }, /* Sound profile switch */ From 14904f4d8bf8c7e12794739ee4f5ff3a346d7bb2 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 30 Jun 2023 09:18:13 -0400 Subject: [PATCH 0585/2093] NFSv4: Fix dropped lock for racing OPEN and delegation return commit 1cbc11aaa01f80577b67ae02c73ee781112125fd upstream. Commmit f5ea16137a3f ("NFSv4: Retry LOCK on OLD_STATEID during delegation return") attempted to solve this problem by using nfs4's generic async error handling, but introduced a regression where v4.0 lock recovery would hang. The additional complexity introduced by overloading that error handling is not necessary for this case. This patch expects that commit to be reverted. The problem as originally explained in the above commit is: There's a small window where a LOCK sent during a delegation return can race with another OPEN on client, but the open stateid has not yet been updated. In this case, the client doesn't handle the OLD_STATEID error from the server and will lose this lock, emitting: "NFS: nfs4_handle_delegation_recall_error: unhandled error -10024". Fix this by using the old_stateid refresh helpers if the server replies with OLD_STATEID. Suggested-by: Trond Myklebust Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/nfs4proc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d67383665e9b..1044305e7799 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7170,8 +7170,15 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) goto out_restart; break; - case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: + if (data->arg.new_lock_owner != 0 && + nfs4_refresh_open_old_stateid(&data->arg.open_stateid, + lsp->ls_state)) + goto out_restart; + if (nfs4_refresh_lock_old_stateid(&data->arg.lock_stateid, lsp)) + goto out_restart; + fallthrough; + case -NFS4ERR_BAD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: if (data->arg.new_lock_owner != 0) { From a7d172252bfad47d06a5dcf6fbb6d4ea85f4cedd Mon Sep 17 00:00:00 2001 From: Andrey Skvortsov Date: Sat, 5 Aug 2023 11:48:47 +0300 Subject: [PATCH 0586/2093] clk: Fix slab-out-of-bounds error in devm_clk_release() commit 66fbfb35da47f391bdadf9fa7ceb88af4faa9022 upstream. Problem can be reproduced by unloading snd_soc_simple_card, because in devm_get_clk_from_child() devres data is allocated as `struct clk`, but devm_clk_release() expects devres data to be `struct devm_clk_state`. KASAN report: ================================================================== BUG: KASAN: slab-out-of-bounds in devm_clk_release+0x20/0x54 Read of size 8 at addr ffffff800ee09688 by task (udev-worker)/287 Call trace: dump_backtrace+0xe8/0x11c show_stack+0x1c/0x30 dump_stack_lvl+0x60/0x78 print_report+0x150/0x450 kasan_report+0xa8/0xf0 __asan_load8+0x78/0xa0 devm_clk_release+0x20/0x54 release_nodes+0x84/0x120 devres_release_all+0x144/0x210 device_unbind_cleanup+0x1c/0xac really_probe+0x2f0/0x5b0 __driver_probe_device+0xc0/0x1f0 driver_probe_device+0x68/0x120 __driver_attach+0x140/0x294 bus_for_each_dev+0xec/0x160 driver_attach+0x38/0x44 bus_add_driver+0x24c/0x300 driver_register+0xf0/0x210 __platform_driver_register+0x48/0x54 asoc_simple_card_init+0x24/0x1000 [snd_soc_simple_card] do_one_initcall+0xac/0x340 do_init_module+0xd0/0x300 load_module+0x2ba4/0x3100 __do_sys_init_module+0x2c8/0x300 __arm64_sys_init_module+0x48/0x5c invoke_syscall+0x64/0x190 el0_svc_common.constprop.0+0x124/0x154 do_el0_svc+0x44/0xdc el0_svc+0x14/0x50 el0t_64_sync_handler+0xec/0x11c el0t_64_sync+0x14c/0x150 Allocated by task 287: kasan_save_stack+0x38/0x60 kasan_set_track+0x28/0x40 kasan_save_alloc_info+0x20/0x30 __kasan_kmalloc+0xac/0xb0 __kmalloc_node_track_caller+0x6c/0x1c4 __devres_alloc_node+0x44/0xb4 devm_get_clk_from_child+0x44/0xa0 asoc_simple_parse_clk+0x1b8/0x1dc [snd_soc_simple_card_utils] simple_parse_node.isra.0+0x1ec/0x230 [snd_soc_simple_card] simple_dai_link_of+0x1bc/0x334 [snd_soc_simple_card] __simple_for_each_link+0x2ec/0x320 [snd_soc_simple_card] asoc_simple_probe+0x468/0x4dc [snd_soc_simple_card] platform_probe+0x90/0xf0 really_probe+0x118/0x5b0 __driver_probe_device+0xc0/0x1f0 driver_probe_device+0x68/0x120 __driver_attach+0x140/0x294 bus_for_each_dev+0xec/0x160 driver_attach+0x38/0x44 bus_add_driver+0x24c/0x300 driver_register+0xf0/0x210 __platform_driver_register+0x48/0x54 asoc_simple_card_init+0x24/0x1000 [snd_soc_simple_card] do_one_initcall+0xac/0x340 do_init_module+0xd0/0x300 load_module+0x2ba4/0x3100 __do_sys_init_module+0x2c8/0x300 __arm64_sys_init_module+0x48/0x5c invoke_syscall+0x64/0x190 el0_svc_common.constprop.0+0x124/0x154 do_el0_svc+0x44/0xdc el0_svc+0x14/0x50 el0t_64_sync_handler+0xec/0x11c el0t_64_sync+0x14c/0x150 The buggy address belongs to the object at ffffff800ee09600 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 136 bytes inside of 256-byte region [ffffff800ee09600, ffffff800ee09700) The buggy address belongs to the physical page: page:000000002d97303b refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x4ee08 head:000000002d97303b order:1 compound_mapcount:0 compound_pincount:0 flags: 0x10200(slab|head|zone=0) raw: 0000000000010200 0000000000000000 dead000000000122 ffffff8002c02480 raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffff800ee09580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffff800ee09600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffff800ee09680: 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffffff800ee09700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffff800ee09780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Fixes: abae8e57e49a ("clk: generalize devm_clk_get() a bit") Signed-off-by: Andrey Skvortsov Link: https://lore.kernel.org/r/20230805084847.3110586-1-andrej.skvortzov@gmail.com Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- drivers/clk/clk-devres.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index 4fb4fd4b06bd..737aa70e2cb3 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -205,18 +205,19 @@ EXPORT_SYMBOL(devm_clk_put); struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { - struct clk **ptr, *clk; + struct devm_clk_state *state; + struct clk *clk; - ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) + state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL); + if (!state) return ERR_PTR(-ENOMEM); clk = of_clk_get_by_name(np, con_id); if (!IS_ERR(clk)) { - *ptr = clk; - devres_add(dev, ptr); + state->clk = clk; + devres_add(dev, state); } else { - devres_free(ptr); + devres_free(state); } return clk; From 091591f6e7c35fc2f0a74c9d044b0638a37b0f3f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 17 Aug 2023 13:57:59 -0400 Subject: [PATCH 0587/2093] mm,ima,kexec,of: use memblock_free_late from ima_free_kexec_buffer commit f0362a253606e2031f8d61c74195d4d6556e12a4 upstream. The code calling ima_free_kexec_buffer runs long after the memblock allocator has already been torn down, potentially resulting in a use after free in memblock_isolate_range. With KASAN or KFENCE, this use after free will result in a BUG from the idle task, and a subsequent kernel panic. Switch ima_free_kexec_buffer over to memblock_free_late to avoid that issue. Fixes: fee3ff99bc67 ("powerpc: Move arch independent ima kexec functions to drivers/of/kexec.c") Cc: stable@kernel.org Signed-off-by: Rik van Riel Suggested-by: Mike Rappoport Link: https://lore.kernel.org/r/20230817135759.0888e5ef@imladris.surriel.com Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/kexec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index f26d2ba8a371..68278340cecf 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -184,7 +184,8 @@ int __init ima_free_kexec_buffer(void) if (ret) return ret; - return memblock_phys_free(addr, size); + memblock_free_late(addr, size); + return 0; } #endif From d13f3a63d236d311fceece5f34133636fd334bde Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 22 Aug 2023 22:14:47 -0700 Subject: [PATCH 0588/2093] shmem: fix smaps BUG sleeping while atomic commit e5548f85b4527c4c803b7eae7887c10bf8f90c97 upstream. smaps_pte_hole_lookup() is calling shmem_partial_swap_usage() with page table lock held: but shmem_partial_swap_usage() does cond_resched_rcu() if need_resched(): "BUG: sleeping function called from invalid context". Since shmem_partial_swap_usage() is designed to count across a range, but smaps_pte_hole_lookup() only calls it for a single page slot, just break out of the loop on the last or only page, before checking need_resched(). Link: https://lkml.kernel.org/r/6fe3b3ec-abdf-332f-5c23-6a3b3a3b11a9@google.com Fixes: 230100321518 ("mm/smaps: simplify shmem handling of pte holes") Signed-off-by: Hugh Dickins Acked-by: Peter Xu Cc: [5.16+] Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/shmem.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index aba041a3df73..10365ced5b1f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -800,14 +800,16 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; + unsigned long max = end - 1; rcu_read_lock(); - xas_for_each(&xas, page, end - 1) { + xas_for_each(&xas, page, max) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; - + if (xas.xa_index == max) + break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); From d4e11b85a2690c31b3d45b1dfa7e61d637a8f2fa Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 23 Aug 2023 18:16:25 +0200 Subject: [PATCH 0589/2093] ALSA: ymfpci: Fix the missing snd_card_free() call at probe error commit 1d0eb6143c1e85d3f9a3f5a616ee7e5dc351d33b upstream. Like a few other drivers, YMFPCI driver needs to clean up with snd_card_free() call at an error path of the probe; otherwise the other devres resources are released before the card and it results in the UAF. This patch uses the helper for handling the probe error gracefully. Fixes: f33fc1576757 ("ALSA: ymfpci: Create card with device-managed snd_devm_card_new()") Cc: Reported-and-tested-by: Takashi Yano Closes: https://lore.kernel.org/r/20230823135846.1812-1-takashi.yano@nifty.ne.jp Link: https://lore.kernel.org/r/20230823161625.5807-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/ymfpci/ymfpci.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c index 82d4e0fda91b..d62a0e2ddf60 100644 --- a/sound/pci/ymfpci/ymfpci.c +++ b/sound/pci/ymfpci/ymfpci.c @@ -150,8 +150,8 @@ static inline int snd_ymfpci_create_gameport(struct snd_ymfpci *chip, int dev, i void snd_ymfpci_free_gameport(struct snd_ymfpci *chip) { } #endif /* SUPPORT_JOYSTICK */ -static int snd_card_ymfpci_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_ymfpci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -333,6 +333,12 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, return 0; } +static int snd_card_ymfpci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_ymfpci_probe(pci, pci_id)); +} + static struct pci_driver ymfpci_driver = { .name = KBUILD_MODNAME, .id_table = snd_ymfpci_ids, From a8a60bc8027e099b8dd9e13b49b393db2d940004 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 5 Aug 2023 12:12:56 +0200 Subject: [PATCH 0590/2093] mm/gup: handle cont-PTE hugetlb pages correctly in gup_must_unshare() via GUP-fast commit 5805192c7b7257d290474cb1a3897d0567281bbc upstream. In contrast to most other GUP code, GUP-fast common page table walking code like gup_pte_range() also handles hugetlb pages. But in contrast to other hugetlb page table walking code, it does not look at the hugetlb PTE abstraction whereby we have only a single logical hugetlb PTE per hugetlb page, even when using multiple cont-PTEs underneath -- which is for example what huge_ptep_get() abstracts. So when we have a hugetlb page that is mapped via cont-PTEs, GUP-fast might stumble over a PTE that does not map the head page of a hugetlb page -- not the first "head" PTE of such a cont mapping. Logically, the whole hugetlb page is mapped (entire_mapcount == 1), but we might end up calling gup_must_unshare() with a tail page of a hugetlb page. We only maintain a single PageAnonExclusive flag per hugetlb page (as hugetlb pages cannot get partially COW-shared), stored for the head page. That flag is clear for all tail pages. So when gup_must_unshare() ends up calling PageAnonExclusive() with a tail page of a hugetlb page: 1) With CONFIG_DEBUG_VM_PGFLAGS Stumbles over the: VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); For example, when executing the COW selftests with 64k hugetlb pages on arm64: [ 61.082187] page:00000000829819ff refcount:3 mapcount:1 mapping:0000000000000000 index:0x1 pfn:0x11ee11 [ 61.082842] head:0000000080f79bf7 order:4 entire_mapcount:1 nr_pages_mapped:0 pincount:2 [ 61.083384] anon flags: 0x17ffff80003000e(referenced|uptodate|dirty|head|mappedtodisk|node=0|zone=2|lastcpupid=0xfffff) [ 61.084101] page_type: 0xffffffff() [ 61.084332] raw: 017ffff800000000 fffffc00037b8401 0000000000000402 0000000200000000 [ 61.084840] raw: 0000000000000010 0000000000000000 00000000ffffffff 0000000000000000 [ 61.085359] head: 017ffff80003000e ffffd9e95b09b788 ffffd9e95b09b788 ffff0007ff63cf71 [ 61.085885] head: 0000000000000000 0000000000000002 00000003ffffffff 0000000000000000 [ 61.086415] page dumped because: VM_BUG_ON_PAGE(PageHuge(page) && !PageHead(page)) [ 61.086914] ------------[ cut here ]------------ [ 61.087220] kernel BUG at include/linux/page-flags.h:990! [ 61.087591] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP [ 61.087999] Modules linked in: ... [ 61.089404] CPU: 0 PID: 4612 Comm: cow Kdump: loaded Not tainted 6.5.0-rc4+ #3 [ 61.089917] Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 [ 61.090409] pstate: 604000c5 (nZCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 61.090897] pc : gup_must_unshare.part.0+0x64/0x98 [ 61.091242] lr : gup_must_unshare.part.0+0x64/0x98 [ 61.091592] sp : ffff8000825eb940 [ 61.091826] x29: ffff8000825eb940 x28: 0000000000000000 x27: fffffc00037b8440 [ 61.092329] x26: 0400000000000001 x25: 0000000000080101 x24: 0000000000080000 [ 61.092835] x23: 0000000000080100 x22: ffff0000cffb9588 x21: ffff0000c8ec6b58 [ 61.093341] x20: 0000ffffad6b1000 x19: fffffc00037b8440 x18: ffffffffffffffff [ 61.093850] x17: 2864616548656761 x16: 5021202626202965 x15: 6761702865677548 [ 61.094358] x14: 6567615028454741 x13: 2929656761702864 x12: 6165486567615021 [ 61.094858] x11: 00000000ffff7fff x10: 00000000ffff7fff x9 : ffffd9e958b7a1c0 [ 61.095359] x8 : 00000000000bffe8 x7 : c0000000ffff7fff x6 : 00000000002bffa8 [ 61.095873] x5 : ffff0008bb19e708 x4 : 0000000000000000 x3 : 0000000000000000 [ 61.096380] x2 : 0000000000000000 x1 : ffff0000cf6636c0 x0 : 0000000000000046 [ 61.096894] Call trace: [ 61.097080] gup_must_unshare.part.0+0x64/0x98 [ 61.097392] gup_pte_range+0x3a8/0x3f0 [ 61.097662] gup_pgd_range+0x1ec/0x280 [ 61.097942] lockless_pages_from_mm+0x64/0x1a0 [ 61.098258] internal_get_user_pages_fast+0xe4/0x1d0 [ 61.098612] pin_user_pages_fast+0x58/0x78 [ 61.098917] pin_longterm_test_start+0xf4/0x2b8 [ 61.099243] gup_test_ioctl+0x170/0x3b0 [ 61.099528] __arm64_sys_ioctl+0xa8/0xf0 [ 61.099822] invoke_syscall.constprop.0+0x7c/0xd0 [ 61.100160] el0_svc_common.constprop.0+0xe8/0x100 [ 61.100500] do_el0_svc+0x38/0xa0 [ 61.100736] el0_svc+0x3c/0x198 [ 61.100971] el0t_64_sync_handler+0x134/0x150 [ 61.101280] el0t_64_sync+0x17c/0x180 [ 61.101543] Code: aa1303e0 f00074c1 912b0021 97fffeb2 (d4210000) 2) Without CONFIG_DEBUG_VM_PGFLAGS Always detects "not exclusive" for passed tail pages and refuses to PIN the tail pages R/O, as gup_must_unshare() == true. GUP-fast will fallback to ordinary GUP. As ordinary GUP properly considers the logical hugetlb PTE abstraction in hugetlb_follow_page_mask(), pinning the page will succeed when looking at the PageAnonExclusive on the head page only. So the only real effect of this is that with cont-PTE hugetlb pages, we'll always fallback from GUP-fast to ordinary GUP when not working on the head page, which ends up checking the head page and do the right thing. Consequently, the cow selftests pass with cont-PTE hugetlb pages as well without CONFIG_DEBUG_VM_PGFLAGS. Note that this only applies to anon hugetlb pages that are mapped using cont-PTEs: for example 64k hugetlb pages on a 4k arm64 kernel. ... and only when R/O-pinning (FOLL_PIN) such pages that are mapped into the page table R/O using GUP-fast. On production kernels (and even most debug kernels, that don't set CONFIG_DEBUG_VM_PGFLAGS) this patch should theoretically not be required to be backported. But of course, it does not hurt. Link: https://lkml.kernel.org/r/20230805101256.87306-1-david@redhat.com Fixes: a7f226604170 ("mm/gup: trigger FAULT_FLAG_UNSHARE when R/O-pinning a possibly shared anonymous page") Signed-off-by: David Hildenbrand Reported-by: Ryan Roberts Reviewed-by: Ryan Roberts Tested-by: Ryan Roberts Cc: Vlastimil Babka Cc: John Hubbard Cc: Jason Gunthorpe Cc: Peter Xu Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/mm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index b8ed44f401b5..f83a1c9ec8e4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3091,6 +3091,16 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) smp_rmb(); + /* + * During GUP-fast we might not get called on the head page for a + * hugetlb page that is mapped using cont-PTE, because GUP-fast does + * not work with the abstracted hugetlb PTEs that always point at the + * head page. For hugetlb, PageAnonExclusive only applies on the head + * page (as it cannot be partially COW-shared), so lookup the head page. + */ + if (unlikely(!PageHead(page) && PageHuge(page))) + page = compound_head(page); + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. From 07fad410aa6e90131cd1ba8d12bd1f9488f85af5 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 9 Aug 2023 18:46:33 +0200 Subject: [PATCH 0591/2093] mm: add a call to flush_cache_vmap() in vmap_pfn() commit a50420c79731fc5cf27ad43719c1091e842a2606 upstream. flush_cache_vmap() must be called after new vmalloc mappings are installed in the page table in order to allow architectures to make sure the new mapping is visible. It could lead to a panic since on some architectures (like powerpc), the page table walker could see the wrong pte value and trigger a spurious page fault that can not be resolved (see commit f1cb8f9beba8 ("powerpc/64s/radix: avoid ptesync after set_pte and ptep_set_access_flags")). But actually the patch is aiming at riscv: the riscv specification allows the caching of invalid entries in the TLB, and since we recently removed the vmalloc page fault handling, we now need to emit a tlb shootdown whenever a new vmalloc mapping is emitted (https://lore.kernel.org/linux-riscv/20230725132246.817726-1-alexghiti@rivosinc.com/). That's a temporary solution, there are ways to avoid that :) Link: https://lkml.kernel.org/r/20230809164633.1556126-1-alexghiti@rivosinc.com Fixes: 3e9a9e256b1e ("mm: add a vmap_pfn function") Reported-by: Dylan Jhong Closes: https://lore.kernel.org/linux-riscv/ZMytNY2J8iyjbPPy@atctrx.andestech.com/ Signed-off-by: Alexandre Ghiti Reviewed-by: Christoph Hellwig Reviewed-by: Palmer Dabbelt Acked-by: Palmer Dabbelt Reviewed-by: Dylan Jhong Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmalloc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d5dc361dc104..80bd104a4d42 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2909,6 +2909,10 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) free_vm_area(area); return NULL; } + + flush_cache_vmap((unsigned long)area->addr, + (unsigned long)area->addr + count * PAGE_SIZE); + return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); From bdc544a87d43a4102aa08114fc939dbddf175f98 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 27 Jun 2023 19:28:08 +0800 Subject: [PATCH 0592/2093] mm: memory-failure: fix unexpected return value in soft_offline_page() commit e2c1ab070fdc81010ec44634838d24fce9ff9e53 upstream. When page_handle_poison() fails to handle the hugepage or free page in retry path, soft_offline_page() will return 0 while -EBUSY is expected in this case. Consequently the user will think soft_offline_page succeeds while it in fact failed. So the user will not try again later in this case. Link: https://lkml.kernel.org/r/20230627112808.1275241-1-linmiaohe@huawei.com Fixes: b94e02822deb ("mm,hwpoison: try to narrow window race for free pages") Signed-off-by: Miaohe Lin Acked-by: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/memory-failure.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4457f9423e2c..99de0328d1be 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2591,10 +2591,13 @@ int soft_offline_page(unsigned long pfn, int flags) if (ret > 0) { ret = soft_offline_in_use_page(page); } else if (ret == 0) { - if (!page_handle_poison(page, true, false) && try_again) { - try_again = false; - flags &= ~MF_COUNT_INCREASED; - goto retry; + if (!page_handle_poison(page, true, false)) { + if (try_again) { + try_again = false; + flags &= ~MF_COUNT_INCREASED; + goto retry; + } + ret = -EBUSY; } } From 96fb46ef8281c749abe114ed9385cec39bae00e4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 8 Aug 2023 21:17:11 -0400 Subject: [PATCH 0593/2093] NFS: Fix a use after free in nfs_direct_join_group() commit be2fd1560eb57b7298aa3c258ddcca0d53ecdea3 upstream. Be more careful when tearing down the subrequests of an O_DIRECT write as part of a retransmission. Reported-by: Chris Mason Fixes: ed5d588fe47f ("NFS: Try to join page groups before an O_DIRECT retransmission") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/direct.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1707f46b1335..cf34d0c30945 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -474,20 +474,26 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, return result; } -static void -nfs_direct_join_group(struct list_head *list, struct inode *inode) +static void nfs_direct_join_group(struct list_head *list, struct inode *inode) { - struct nfs_page *req, *next; + struct nfs_page *req, *subreq; list_for_each_entry(req, list, wb_list) { - if (req->wb_head != req || req->wb_this_page == req) + if (req->wb_head != req) continue; - for (next = req->wb_this_page; - next != req->wb_head; - next = next->wb_this_page) { - nfs_list_remove_request(next); - nfs_release_request(next); - } + subreq = req->wb_this_page; + if (subreq == req) + continue; + do { + /* + * Remove subrequests from this list before freeing + * them in the call to nfs_join_page_group(). + */ + if (!list_empty(&subreq->wb_list)) { + nfs_list_remove_request(subreq); + nfs_release_request(subreq); + } + } while ((subreq = subreq->wb_this_page) != req); nfs_join_page_group(req, inode); } } From 36c5aecc789d4f881d18e6a8f4539636e11ab85e Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 4 Aug 2023 10:52:20 -0400 Subject: [PATCH 0594/2093] nfsd: Fix race to FREE_STATEID and cl_revoked commit 3b816601e279756e781e6c4d9b3f3bd21a72ac67 upstream. We have some reports of linux NFS clients that cannot satisfy a linux knfsd server that always sets SEQ4_STATUS_RECALLABLE_STATE_REVOKED even though those clients repeatedly walk all their known state using TEST_STATEID and receive NFS4_OK for all. Its possible for revoke_delegation() to set NFS4_REVOKED_DELEG_STID, then nfsd4_free_stateid() finds the delegation and returns NFS4_OK to FREE_STATEID. Afterward, revoke_delegation() moves the same delegation to cl_revoked. This would produce the observed client/server effect. Fix this by ensuring that the setting of sc_type to NFS4_REVOKED_DELEG_STID and move to cl_revoked happens within the same cl_lock. This will allow nfsd4_free_stateid() to properly remove the delegation from cl_revoked. Link: https://bugzilla.redhat.com/show_bug.cgi?id=2217103 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2176575 Signed-off-by: Benjamin Coddington Cc: stable@vger.kernel.org # v4.17+ Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/nfs4state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c5dc0cd6f703..96714e105d7b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1368,9 +1368,9 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); if (clp->cl_minorversion) { + spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); list_add(&dp->dl_recall_lru, &clp->cl_revoked); spin_unlock(&clp->cl_lock); } From d6b64d710e9bcaa22fa99fdc1cb32e19a0eb5b38 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20G=C3=B6ttsche?= Date: Fri, 18 Aug 2023 17:33:58 +0200 Subject: [PATCH 0595/2093] selinux: set next pointer before attaching to list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 70d91dc9b2ac91327d0eefd86163abc3548effa6 upstream. Set the next pointer in filename_trans_read_helper() before attaching the new node under construction to the list, otherwise garbage would be dereferenced on subsequent failure during cleanup in the out goto label. Cc: Fixes: 430059024389 ("selinux: implement new format of filename transitions") Signed-off-by: Christian Göttsche Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/selinux/ss/policydb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index adcfb63b3550..6f9ff4643dcb 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -2005,6 +2005,7 @@ static int filename_trans_read_helper(struct policydb *p, void *fp) if (!datum) goto out; + datum->next = NULL; *dst = datum; /* ebitmap_read() will at least init the bitmap */ @@ -2017,7 +2018,6 @@ static int filename_trans_read_helper(struct policydb *p, void *fp) goto out; datum->otype = le32_to_cpu(buf[0]); - datum->next = NULL; dst = &datum->next; } From efef746c5a387a5a9553d405735884f7ce7852b6 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 19 Jul 2023 09:29:29 +0200 Subject: [PATCH 0596/2093] batman-adv: Trigger events for auto adjusted MTU commit c6a953cce8d0438391e6da48c8d0793d3fbfcfa6 upstream. If an interface changes the MTU, it is expected that an NETDEV_PRECHANGEMTU and NETDEV_CHANGEMTU notification events is triggered. This worked fine for .ndo_change_mtu based changes because core networking code took care of it. But for auto-adjustments after hard-interfaces changes, these events were simply missing. Due to this problem, non-batman-adv components weren't aware of MTU changes and thus couldn't perform their own tasks correctly. Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Cc: stable@vger.kernel.org Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/hard-interface.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 41c1ad33d009..ae5762af0146 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -630,7 +630,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) */ void batadv_update_min_mtu(struct net_device *soft_iface) { - soft_iface->mtu = batadv_hardif_min_mtu(soft_iface); + dev_set_mtu(soft_iface, batadv_hardif_min_mtu(soft_iface)); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. From ed1eb19806ae645c20890b70b091c751dfd08f53 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 19 Jul 2023 10:01:15 +0200 Subject: [PATCH 0597/2093] batman-adv: Don't increase MTU when set by user commit d8e42a2b0addf238be8b3b37dcd9795a5c1be459 upstream. If the user set an MTU value, it usually means that there are special requirements for the MTU. But if an interface gots activated, the MTU was always recalculated and then the user set value was overwritten. The only reason why this user set value has to be overwritten, is when the MTU has to be decreased because batman-adv is not able to transfer packets with the user specified size. Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Cc: stable@vger.kernel.org Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/hard-interface.c | 14 +++++++++++++- net/batman-adv/soft-interface.c | 3 +++ net/batman-adv/types.h | 6 ++++++ 3 files changed, 22 insertions(+), 1 deletion(-) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index ae5762af0146..24c9c0c3f316 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -630,7 +630,19 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) */ void batadv_update_min_mtu(struct net_device *soft_iface) { - dev_set_mtu(soft_iface, batadv_hardif_min_mtu(soft_iface)); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int limit_mtu; + int mtu; + + mtu = batadv_hardif_min_mtu(soft_iface); + + if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; + else + limit_mtu = ETH_DATA_LEN; + + mtu = min(mtu, limit_mtu); + dev_set_mtu(soft_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0f5c0679b55a..38d411a52f33 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -154,11 +154,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { + struct batadv_priv *bat_priv = netdev_priv(dev); + /* check ranges */ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu; return 0; } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 758cd797a063..76791815b26b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1546,6 +1546,12 @@ struct batadv_priv { /** @soft_iface: net device which holds this struct as private data */ struct net_device *soft_iface; + /** + * @mtu_set_by_user: MTU was set once by user + * protected by rtnl_lock + */ + int mtu_set_by_user; + /** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters) From fc9b87d8b741a955d462fc14da4fcd788d00748a Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Fri, 28 Jul 2023 15:38:50 +0200 Subject: [PATCH 0598/2093] batman-adv: Do not get eth header before batadv_check_management_packet commit eac27a41ab641de074655d2932fc7f8cdb446881 upstream. If received skb in batadv_v_elp_packet_recv or batadv_v_ogm_packet_recv is either cloned or non linearized then its data buffer will be reallocated by batadv_check_management_packet when skb_cow or skb_linearize get called. Thus geting ethernet header address inside skb data buffer before batadv_check_management_packet had any chance to reallocate it could lead to the following kernel panic: Unable to handle kernel paging request at virtual address ffffff8020ab069a Mem abort info: ESR = 0x96000007 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x07: level 3 translation fault Data abort info: ISV = 0, ISS = 0x00000007 CM = 0, WnR = 0 swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000040f45000 [ffffff8020ab069a] pgd=180000007fffa003, p4d=180000007fffa003, pud=180000007fffa003, pmd=180000007fefe003, pte=0068000020ab0706 Internal error: Oops: 96000007 [#1] SMP Modules linked in: ahci_mvebu libahci_platform libahci dvb_usb_af9035 dvb_usb_dib0700 dib0070 dib7000m dibx000_common ath11k_pci ath10k_pci ath10k_core mwl8k_new nf_nat_sip nf_conntrack_sip xhci_plat_hcd xhci_hcd nf_nat_pptp nf_conntrack_pptp at24 sbsa_gwdt CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.15.42-00066-g3242268d425c-dirty #550 Hardware name: A8k (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : batadv_is_my_mac+0x60/0xc0 lr : batadv_v_ogm_packet_recv+0x98/0x5d0 sp : ffffff8000183820 x29: ffffff8000183820 x28: 0000000000000001 x27: ffffff8014f9af00 x26: 0000000000000000 x25: 0000000000000543 x24: 0000000000000003 x23: ffffff8020ab0580 x22: 0000000000000110 x21: ffffff80168ae880 x20: 0000000000000000 x19: ffffff800b561000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 00dc098924ae0032 x14: 0f0405433e0054b0 x13: ffffffff00000080 x12: 0000004000000001 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : 0000000000000000 x7 : ffffffc076dae000 x6 : ffffff8000183700 x5 : ffffffc00955e698 x4 : ffffff80168ae000 x3 : ffffff80059cf000 x2 : ffffff800b561000 x1 : ffffff8020ab0696 x0 : ffffff80168ae880 Call trace: batadv_is_my_mac+0x60/0xc0 batadv_v_ogm_packet_recv+0x98/0x5d0 batadv_batman_skb_recv+0x1b8/0x244 __netif_receive_skb_core.isra.0+0x440/0xc74 __netif_receive_skb_one_core+0x14/0x20 netif_receive_skb+0x68/0x140 br_pass_frame_up+0x70/0x80 br_handle_frame_finish+0x108/0x284 br_handle_frame+0x190/0x250 __netif_receive_skb_core.isra.0+0x240/0xc74 __netif_receive_skb_list_core+0x6c/0x90 netif_receive_skb_list_internal+0x1f4/0x310 napi_complete_done+0x64/0x1d0 gro_cell_poll+0x7c/0xa0 __napi_poll+0x34/0x174 net_rx_action+0xf8/0x2a0 _stext+0x12c/0x2ac run_ksoftirqd+0x4c/0x7c smpboot_thread_fn+0x120/0x210 kthread+0x140/0x150 ret_from_fork+0x10/0x20 Code: f9403844 eb03009f 54fffee1 f94 Thus ethernet header address should only be fetched after batadv_check_management_packet has been called. Fixes: 0da0035942d4 ("batman-adv: OGMv2 - add basic infrastructure") Cc: stable@vger.kernel.org Signed-off-by: Remi Pommarel Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_v_elp.c | 3 ++- net/batman-adv/bat_v_ogm.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index f1741fbfb617..98a624f32b94 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -506,7 +506,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_elp_packet *elp_packet; struct batadv_hard_iface *primary_if; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr; bool res; int ret = NET_RX_DROP; @@ -514,6 +514,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, if (!res) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 033639df96d8..38b4239625fe 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -986,7 +986,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_ogm2_packet *ogm_packet; - struct ethhdr *ethhdr = eth_hdr(skb); + struct ethhdr *ethhdr; int ogm_offset; u8 *packet_pos; int ret = NET_RX_DROP; @@ -1000,6 +1000,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN)) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; From f1bead97f0ad91bb3c1b90449400654fd5814bf6 Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Fri, 4 Aug 2023 11:39:36 +0200 Subject: [PATCH 0599/2093] batman-adv: Fix TT global entry leak when client roamed back commit d25ddb7e788d34cf27ff1738d11a87cb4b67d446 upstream. When a client roamed back to a node before it got time to destroy the pending local entry (i.e. within the same originator interval) the old global one is directly removed from hash table and left as such. But because this entry had an extra reference taken at lookup (i.e using batadv_tt_global_hash_find) there is no way its memory will be reclaimed at any time causing the following memory leak: unreferenced object 0xffff0000073c8000 (size 18560): comm "softirq", pid 0, jiffies 4294907738 (age 228.644s) hex dump (first 32 bytes): 06 31 ac 12 c7 7a 05 00 01 00 00 00 00 00 00 00 .1...z.......... 2c ad be 08 00 80 ff ff 6c b6 be 08 00 80 ff ff ,.......l....... backtrace: [<00000000ee6e0ffa>] kmem_cache_alloc+0x1b4/0x300 [<000000000ff2fdbc>] batadv_tt_global_add+0x700/0xe20 [<00000000443897c7>] _batadv_tt_update_changes+0x21c/0x790 [<000000005dd90463>] batadv_tt_update_changes+0x3c/0x110 [<00000000a2d7fc57>] batadv_tt_tvlv_unicast_handler_v1+0xafc/0xe10 [<0000000011793f2a>] batadv_tvlv_containers_process+0x168/0x2b0 [<00000000b7cbe2ef>] batadv_recv_unicast_tvlv+0xec/0x1f4 [<0000000042aef1d8>] batadv_batman_skb_recv+0x25c/0x3a0 [<00000000bbd8b0a2>] __netif_receive_skb_core.isra.0+0x7a8/0xe90 [<000000004033d428>] __netif_receive_skb_one_core+0x64/0x74 [<000000000f39a009>] __netif_receive_skb+0x48/0xe0 [<00000000f2cd8888>] process_backlog+0x174/0x344 [<00000000507d6564>] __napi_poll+0x58/0x1f4 [<00000000b64ef9eb>] net_rx_action+0x504/0x590 [<00000000056fa5e4>] _stext+0x1b8/0x418 [<00000000878879d6>] run_ksoftirqd+0x74/0xa4 unreferenced object 0xffff00000bae1a80 (size 56): comm "softirq", pid 0, jiffies 4294910888 (age 216.092s) hex dump (first 32 bytes): 00 78 b1 0b 00 00 ff ff 0d 50 00 00 00 00 00 00 .x.......P...... 00 00 00 00 00 00 00 00 50 c8 3c 07 00 00 ff ff ........P.<..... backtrace: [<00000000ee6e0ffa>] kmem_cache_alloc+0x1b4/0x300 [<00000000d9aaa49e>] batadv_tt_global_add+0x53c/0xe20 [<00000000443897c7>] _batadv_tt_update_changes+0x21c/0x790 [<000000005dd90463>] batadv_tt_update_changes+0x3c/0x110 [<00000000a2d7fc57>] batadv_tt_tvlv_unicast_handler_v1+0xafc/0xe10 [<0000000011793f2a>] batadv_tvlv_containers_process+0x168/0x2b0 [<00000000b7cbe2ef>] batadv_recv_unicast_tvlv+0xec/0x1f4 [<0000000042aef1d8>] batadv_batman_skb_recv+0x25c/0x3a0 [<00000000bbd8b0a2>] __netif_receive_skb_core.isra.0+0x7a8/0xe90 [<000000004033d428>] __netif_receive_skb_one_core+0x64/0x74 [<000000000f39a009>] __netif_receive_skb+0x48/0xe0 [<00000000f2cd8888>] process_backlog+0x174/0x344 [<00000000507d6564>] __napi_poll+0x58/0x1f4 [<00000000b64ef9eb>] net_rx_action+0x504/0x590 [<00000000056fa5e4>] _stext+0x1b8/0x418 [<00000000878879d6>] run_ksoftirqd+0x74/0xa4 Releasing the extra reference from batadv_tt_global_hash_find even at roam back when batadv_tt_global_free is called fixes this memory leak. Cc: stable@vger.kernel.org Fixes: 068ee6e204e1 ("batman-adv: roaming handling mechanism redesign") Signed-off-by: Remi Pommarel Signed-off-by; Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/translation-table.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 01d30c1e412c..5d8cee74772f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -774,7 +774,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, if (roamed_back) { batadv_tt_global_free(bat_priv, tt_global, "Roaming canceled"); - tt_global = NULL; } else { /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose From cb1f73e691bb6c46eda7ed7e60c6ce6672094169 Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Wed, 9 Aug 2023 17:29:13 +0200 Subject: [PATCH 0600/2093] batman-adv: Fix batadv_v_ogm_aggr_send memory leak commit 421d467dc2d483175bad4fb76a31b9e5a3d744cf upstream. When batadv_v_ogm_aggr_send is called for an inactive interface, the skb is silently dropped by batadv_v_ogm_send_to_if() but never freed causing the following memory leak: unreferenced object 0xffff00000c164800 (size 512): comm "kworker/u8:1", pid 2648, jiffies 4295122303 (age 97.656s) hex dump (first 32 bytes): 00 80 af 09 00 00 ff ff e1 09 00 00 75 01 60 83 ............u.`. 1f 00 00 00 b8 00 00 00 15 00 05 00 da e3 d3 64 ...............d backtrace: [<0000000007ad20f6>] __kmalloc_track_caller+0x1a8/0x310 [<00000000d1029e55>] kmalloc_reserve.constprop.0+0x70/0x13c [<000000008b9d4183>] __alloc_skb+0xec/0x1fc [<00000000c7af5051>] __netdev_alloc_skb+0x48/0x23c [<00000000642ee5f5>] batadv_v_ogm_aggr_send+0x50/0x36c [<0000000088660bd7>] batadv_v_ogm_aggr_work+0x24/0x40 [<0000000042fc2606>] process_one_work+0x3b0/0x610 [<000000002f2a0b1c>] worker_thread+0xa0/0x690 [<0000000059fae5d4>] kthread+0x1fc/0x210 [<000000000c587d3a>] ret_from_fork+0x10/0x20 Free the skb in that case to fix this leak. Cc: stable@vger.kernel.org Fixes: 0da0035942d4 ("batman-adv: OGMv2 - add basic infrastructure") Signed-off-by: Remi Pommarel Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bat_v_ogm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 38b4239625fe..9f4815f4c8e8 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -124,8 +124,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - if (hard_iface->if_status != BATADV_IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + kfree_skb(skb); return; + } batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, From 82bb5f8aba00cb38759957346119c6fc37f09518 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Mon, 21 Aug 2023 21:48:48 +0200 Subject: [PATCH 0601/2093] batman-adv: Hold rtnl lock during MTU update via netlink commit 987aae75fc1041072941ffb622b45ce2359a99b9 upstream. The automatic recalculation of the maximum allowed MTU is usually triggered by code sections which are already rtnl lock protected by callers outside of batman-adv. But when the fragmentation setting is changed via batman-adv's own batadv genl family, then the rtnl lock is not yet taken. But dev_set_mtu requires that the caller holds the rtnl lock because it uses netdevice notifiers. And this code will then fail the check for this lock: RTNL: assertion failed at net/core/dev.c (1953) Cc: stable@vger.kernel.org Reported-by: syzbot+f8812454d9b3ac00d282@syzkaller.appspotmail.com Fixes: c6a953cce8d0 ("batman-adv: Trigger events for auto adjusted MTU") Signed-off-by: Sven Eckelmann Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230821-batadv-missing-mtu-rtnl-lock-v1-1-1c5a7bfe861e@narfation.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/netlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..86e0664e0511 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -495,7 +495,10 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + + rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); + rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { From 30ffd5890a0349187b820cc09b182f41f267d7b9 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 25 Aug 2023 21:50:33 +0200 Subject: [PATCH 0602/2093] lib/clz_ctz.c: Fix __clzdi2() and __ctzdi2() for 32-bit kernels commit 382d4cd1847517ffcb1800fd462b625db7b2ebea upstream. The gcc compiler translates on some architectures the 64-bit __builtin_clzll() function to a call to the libgcc function __clzdi2(), which should take a 64-bit parameter on 32- and 64-bit platforms. But in the current kernel code, the built-in __clzdi2() function is defined to operate (wrongly) on 32-bit parameters if BITS_PER_LONG == 32, thus the return values on 32-bit kernels are in the range from [0..31] instead of the expected [0..63] range. This patch fixes the in-kernel functions __clzdi2() and __ctzdi2() to take a 64-bit parameter on 32-bit kernels as well, thus it makes the functions identical for 32- and 64-bit kernels. This bug went unnoticed since kernel 3.11 for over 10 years, and here are some possible reasons for that: a) Some architectures have assembly instructions to count the bits and which are used instead of calling __clzdi2(), e.g. on x86 the bsr instruction and on ppc cntlz is used. On such architectures the wrong __clzdi2() implementation isn't used and as such the bug has no effect and won't be noticed. b) Some architectures link to libgcc.a, and the in-kernel weak functions get replaced by the correct 64-bit variants from libgcc.a. c) __builtin_clzll() and __clzdi2() doesn't seem to be used in many places in the kernel, and most likely only in uncritical functions, e.g. when printing hex values via seq_put_hex_ll(). The wrong return value will still print the correct number, but just in a wrong formatting (e.g. with too many leading zeroes). d) 32-bit kernels aren't used that much any longer, so they are less tested. A trivial testcase to verify if the currently running 32-bit kernel is affected by the bug is to look at the output of /proc/self/maps: Here the kernel uses a correct implementation of __clzdi2(): root@debian:~# cat /proc/self/maps 00010000-00019000 r-xp 00000000 08:05 787324 /usr/bin/cat 00019000-0001a000 rwxp 00009000 08:05 787324 /usr/bin/cat 0001a000-0003b000 rwxp 00000000 00:00 0 [heap] f7551000-f770d000 r-xp 00000000 08:05 794765 /usr/lib/hppa-linux-gnu/libc.so.6 ... and this kernel uses the broken implementation of __clzdi2(): root@debian:~# cat /proc/self/maps 0000000010000-0000000019000 r-xp 00000000 000000008:000000005 787324 /usr/bin/cat 0000000019000-000000001a000 rwxp 000000009000 000000008:000000005 787324 /usr/bin/cat 000000001a000-000000003b000 rwxp 00000000 00:00 0 [heap] 00000000f73d1000-00000000f758d000 r-xp 00000000 000000008:000000005 794765 /usr/lib/hppa-linux-gnu/libc.so.6 ... Signed-off-by: Helge Deller Fixes: 4df87bb7b6a22 ("lib: add weak clz/ctz functions") Cc: Chanho Min Cc: Geert Uytterhoeven Cc: stable@vger.kernel.org # v3.11+ Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- lib/clz_ctz.c | 32 ++++++-------------------------- 1 file changed, 6 insertions(+), 26 deletions(-) diff --git a/lib/clz_ctz.c b/lib/clz_ctz.c index 0d3a686b5ba2..fb8c0c5c2bd2 100644 --- a/lib/clz_ctz.c +++ b/lib/clz_ctz.c @@ -28,36 +28,16 @@ int __weak __clzsi2(int val) } EXPORT_SYMBOL(__clzsi2); -int __weak __clzdi2(long val); -int __weak __ctzdi2(long val); -#if BITS_PER_LONG == 32 - -int __weak __clzdi2(long val) +int __weak __clzdi2(u64 val); +int __weak __clzdi2(u64 val) { - return 32 - fls((int)val); + return 64 - fls64(val); } EXPORT_SYMBOL(__clzdi2); -int __weak __ctzdi2(long val) +int __weak __ctzdi2(u64 val); +int __weak __ctzdi2(u64 val) { - return __ffs((u32)val); + return __ffs64(val); } EXPORT_SYMBOL(__ctzdi2); - -#elif BITS_PER_LONG == 64 - -int __weak __clzdi2(long val) -{ - return 64 - fls64((u64)val); -} -EXPORT_SYMBOL(__clzdi2); - -int __weak __ctzdi2(long val) -{ - return __ffs64((u64)val); -} -EXPORT_SYMBOL(__ctzdi2); - -#else -#error BITS_PER_LONG not 32 or 64 -#endif From 33835975740e65c42ad147799bcd6aa430a7eef0 Mon Sep 17 00:00:00 2001 From: Mingzheng Xing Date: Thu, 10 Aug 2023 00:56:48 +0800 Subject: [PATCH 0603/2093] riscv: Handle zicsr/zifencei issue between gcc and binutils commit ca09f772cccaeec4cd05a21528c37a260aa2dd2c upstream. Binutils-2.38 and GCC-12.1.0 bumped[0][1] the default ISA spec to the newer 20191213 version which moves some instructions from the I extension to the Zicsr and Zifencei extensions. So if one of the binutils and GCC exceeds that version, we should explicitly specifying Zicsr and Zifencei via -march to cope with the new changes. but this only occurs when binutils >= 2.36 and GCC >= 11.1.0. It's a different story when binutils < 2.36. binutils-2.36 supports the Zifencei extension[2] and splits Zifencei and Zicsr from I[3]. GCC-11.1.0 is particular[4] because it add support Zicsr and Zifencei extension for -march. binutils-2.35 does not support the Zifencei extension, and does not need to specify Zicsr and Zifencei when working with GCC >= 12.1.0. To make our lives easier, let's relax the check to binutils >= 2.36 in CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. For the other two cases, where clang < 17 or GCC < 11.1.0, we will deal with them in CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC. For more information, please refer to: commit 6df2a016c0c8 ("riscv: fix build with binutils 2.38") commit e89c2e815e76 ("riscv: Handle zicsr/zifencei issues between clang and binutils") Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc [0] Link: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd [1] Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=5a1b31e1e1cee6e9f1c92abff59cdcfff0dddf30 [2] Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=729a53530e86972d1143553a415db34e6e01d5d2 [3] Link: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=b03be74bad08c382da47e048007a78fa3fb4ef49 [4] Link: https://lore.kernel.org/all/20230308220842.1231003-1-conor@kernel.org Link: https://lore.kernel.org/all/20230223220546.52879-1-conor@kernel.org Reviewed-by: Conor Dooley Acked-by: Guo Ren Cc: Signed-off-by: Mingzheng Xing Link: https://lore.kernel.org/r/20230809165648.21071-1-xingmingzheng@iscas.ac.cn Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/Kconfig | 28 ++++++++++++++++---------- arch/riscv/kernel/compat_vdso/Makefile | 8 +++++++- 2 files changed, 24 insertions(+), 12 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 6bf8dc0b8f93..b665ee412aed 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -447,24 +447,30 @@ config TOOLCHAIN_HAS_ZIHINTPAUSE config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI def_bool y # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc - depends on AS_IS_GNU && AS_VERSION >= 23800 + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd + depends on AS_IS_GNU && AS_VERSION >= 23600 help - Newer binutils versions default to ISA spec version 20191213 which - moves some instructions from the I extension to the Zicsr and Zifencei - extensions. + Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer + 20191213 version, which moves some instructions from the I extension to + the Zicsr and Zifencei extensions. This requires explicitly specifying + Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr + and Zifencei are supported in binutils from version 2.36 onwards. + To make life easier, and avoid forcing toolchains that default to a + newer ISA spec to version 2.2, relax the check to binutils >= 2.36. + For clang < 17 or GCC < 11.1.0, for which this is not possible, this is + dealt with in CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC. config TOOLCHAIN_NEEDS_OLD_ISA_SPEC def_bool y depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 - depends on CC_IS_CLANG && CLANG_VERSION < 170000 + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=b03be74bad08c382da47e048007a78fa3fb4ef49 + depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110100) help - Certain versions of clang do not support zicsr and zifencei via -march - but newer versions of binutils require it for the reasons noted in the - help text of CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. This - option causes an older ISA spec compatible with these older versions - of clang to be passed to GAS, which has the same result as passing zicsr - and zifencei to -march. + Certain versions of clang and GCC do not support zicsr and zifencei via + -march. This option causes an older ISA spec compatible with these older + versions of clang and GCC to be passed to GAS, which has the same result + as passing zicsr and zifencei to -march. config FPU bool "FPU support" diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 7f34f3c7c882..737c0857b14c 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -11,7 +11,13 @@ compat_vdso-syms += flush_icache COMPAT_CC := $(CC) COMPAT_LD := $(LD) -COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +# binutils 2.35 does not support the zifencei extension, but in the ISA +# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI. +ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +else + COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32 +endif COMPAT_LD_FLAGS := -melf32lriscv # Disable attributes, as they're useless and break the build. From aa096bc3c8c09fbd836130292ff08cfe0df40d79 Mon Sep 17 00:00:00 2001 From: Mingzheng Xing Date: Fri, 25 Aug 2023 03:08:52 +0800 Subject: [PATCH 0604/2093] riscv: Fix build errors using binutils2.37 toolchains commit ef21fa7c198e04f3d3053b1c5b5f2b4b225c3350 upstream. When building the kernel with binutils 2.37 and GCC-11.1.0/GCC-11.2.0, the following error occurs: Assembler messages: Error: cannot find default versions of the ISA extension `zicsr' Error: cannot find default versions of the ISA extension `zifencei' The above error originated from this commit of binutils[0], which has been resolved and backported by GCC-12.1.0[1] and GCC-11.3.0[2]. So fix this by change the GCC version in CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC to GCC-11.3.0. Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f0bae2552db1dd4f1995608fbf6648fcee4e9e0c [0] Link: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=ca2bbb88f999f4d3cc40e89bc1aba712505dd598 [1] Link: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671 [2] Fixes: ca09f772ccca ("riscv: Handle zicsr/zifencei issue between gcc and binutils") Reported-by: Conor Dooley Cc: Signed-off-by: Mingzheng Xing Link: https://lore.kernel.org/r/20230824190852.45470-1-xingmingzheng@iscas.ac.cn Closes: https://lore.kernel.org/all/20230823-captive-abdomen-befd942a4a73@wendy/ Reviewed-by: Conor Dooley Tested-by: Conor Dooley Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/Kconfig | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b665ee412aed..d702359f8ab5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -457,15 +457,15 @@ config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI and Zifencei are supported in binutils from version 2.36 onwards. To make life easier, and avoid forcing toolchains that default to a newer ISA spec to version 2.2, relax the check to binutils >= 2.36. - For clang < 17 or GCC < 11.1.0, for which this is not possible, this is - dealt with in CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC. + For clang < 17 or GCC < 11.3.0, for which this is not possible or need + special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC. config TOOLCHAIN_NEEDS_OLD_ISA_SPEC def_bool y depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 - # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=b03be74bad08c382da47e048007a78fa3fb4ef49 - depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110100) + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671 + depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300) help Certain versions of clang and GCC do not support zicsr and zifencei via -march. This option causes an older ISA spec compatible with these older From e75de82b378617afd20805551e2e3596fbb447a1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Aug 2023 15:10:13 +0200 Subject: [PATCH 0605/2093] radix tree: remove unused variable commit d59070d1076ec5114edb67c87658aeb1d691d381 upstream. Recent versions of clang warn about an unused variable, though older versions saw the 'slot++' as a use and did not warn: radix-tree.c:1136:50: error: parameter 'slot' set but not used [-Werror,-Wunused-but-set-parameter] It's clearly not needed any more, so just remove it. Link: https://lkml.kernel.org/r/20230811131023.2226509-1-arnd@kernel.org Fixes: 3a08cd52c37c7 ("radix tree: Remove multiorder support") Signed-off-by: Arnd Bergmann Cc: Matthew Wilcox Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peng Zhang Cc: Rong Tao Cc: Tom Rix Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- lib/radix-tree.c | 1 - 1 file changed, 1 deletion(-) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 3c78e1e8b2ad..2ec38f08e4f0 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1134,7 +1134,6 @@ static void set_iter_tags(struct radix_tree_iter *iter, void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { - slot++; iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; From 2d00ca90b81e2ea5f2b604947546be08bbe14094 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 18 Aug 2023 15:40:56 -0500 Subject: [PATCH 0606/2093] of: unittest: Fix EXPECT for parse_phandle_with_args_map() test commit 0aeae3788e28f64ccb95405d4dc8cd80637ffaea upstream. Commit 12e17243d8a1 ("of: base: improve error msg in of_phandle_iterator_next()") added printing of the phandle value on error, but failed to update the unittest. Fixes: 12e17243d8a1 ("of: base: improve error msg in of_phandle_iterator_next()") Cc: stable@vger.kernel.org Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230801-dt-changeset-fixes-v3-1-5f0410e007dd@kernel.org Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/unittest.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index b89ab5d9fea5..9be6ed47a1ce 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -657,12 +657,12 @@ static void __init of_unittest_parse_phandle_with_args_map(void) memset(&args, 0, sizeof(args)); EXPECT_BEGIN(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle"); + "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle 12345678"); rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-phandle", "phandle", 0, &args); EXPECT_END(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle"); + "OF: /testcase-data/phandle-tests/consumer-b: could not find phandle 12345678"); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); From c6b7d8902025a96e61c731dcb75dd8fb91c813e5 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 18 Aug 2023 15:40:57 -0500 Subject: [PATCH 0607/2093] of: dynamic: Refactor action prints to not use "%pOF" inside devtree_lock commit 914d9d831e6126a6e7a92e27fcfaa250671be42c upstream. While originally it was fine to format strings using "%pOF" while holding devtree_lock, this now causes a deadlock. Lockdep reports: of_get_parent from of_fwnode_get_parent+0x18/0x24 ^^^^^^^^^^^^^ of_fwnode_get_parent from fwnode_count_parents+0xc/0x28 fwnode_count_parents from fwnode_full_name_string+0x18/0xac fwnode_full_name_string from device_node_string+0x1a0/0x404 device_node_string from pointer+0x3c0/0x534 pointer from vsnprintf+0x248/0x36c vsnprintf from vprintk_store+0x130/0x3b4 Fix this by moving the printing in __of_changeset_entry_apply() outside the lock. As the only difference in the multiple prints is the action name, use the existing "action_names" to refactor the prints into a single print. Fixes: a92eb7621b9fb2c2 ("lib/vsprintf: Make use of fwnode API to obtain node names and separators") Cc: stable@vger.kernel.org Reported-by: Geert Uytterhoeven Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230801-dt-changeset-fixes-v3-2-5f0410e007dd@kernel.org Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/dynamic.c | 31 +++++++++---------------------- 1 file changed, 9 insertions(+), 22 deletions(-) diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index cd3821a6444f..4e436f2d13ae 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -63,15 +63,14 @@ int of_reconfig_notifier_unregister(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister); -#ifdef DEBUG -const char *action_names[] = { +static const char *action_names[] = { + [0] = "INVALID", [OF_RECONFIG_ATTACH_NODE] = "ATTACH_NODE", [OF_RECONFIG_DETACH_NODE] = "DETACH_NODE", [OF_RECONFIG_ADD_PROPERTY] = "ADD_PROPERTY", [OF_RECONFIG_REMOVE_PROPERTY] = "REMOVE_PROPERTY", [OF_RECONFIG_UPDATE_PROPERTY] = "UPDATE_PROPERTY", }; -#endif int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p) { @@ -594,21 +593,9 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce) } ret = __of_add_property(ce->np, ce->prop); - if (ret) { - pr_err("changeset: add_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; case OF_RECONFIG_REMOVE_PROPERTY: ret = __of_remove_property(ce->np, ce->prop); - if (ret) { - pr_err("changeset: remove_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; case OF_RECONFIG_UPDATE_PROPERTY: @@ -622,20 +609,17 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce) } ret = __of_update_property(ce->np, ce->prop, &old_prop); - if (ret) { - pr_err("changeset: update_property failed @%pOF/%s\n", - ce->np, - ce->prop->name); - break; - } break; default: ret = -EINVAL; } raw_spin_unlock_irqrestore(&devtree_lock, flags); - if (ret) + if (ret) { + pr_err("changeset: apply failed: %-15s %pOF:%s\n", + action_names[ce->action], ce->np, ce->prop->name); return ret; + } switch (ce->action) { case OF_RECONFIG_ATTACH_NODE: @@ -921,6 +905,9 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action, if (!ce) return -ENOMEM; + if (WARN_ON(action >= ARRAY_SIZE(action_names))) + return -EINVAL; + /* get a reference to the node */ ce->action = action; ce->np = of_node_get(np); From 4919043ab93bb662961ffe34c55557b0aafd3bcd Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 18 Aug 2023 09:48:50 -0500 Subject: [PATCH 0608/2093] pinctrl: amd: Mask wake bits on probe again commit 6bc3462a0f5ecaa376a0b3d76dafc55796799e17 upstream. Shubhra reports that their laptop is heating up over s2idle. Even though it's getting into the deepest state, it appears to be having spurious wakeup events. While debugging a tangential issue with the RTC Carsten reports that recent 6.1.y based kernel face a similar problem. Looking at acpidump and GPIO register comparisons these spurious wakeup events are from the GPIO associated with the I2C touchpad on both laptops and occur even when the touchpad is not marked as a wake source by the kernel. This means that the boot firmware has programmed these bits and because Linux didn't touch them lead to spurious wakeup events from that GPIO. To fix this issue, restore most of the code that previously would clear all the bits associated with wakeup sources. This will allow the kernel to only program the wake up sources that are necessary. This is similar to what was done previously; but only the wake bits are cleared by default instead of interrupts and wake bits. If any other problems are reported then it may make sense to clear interrupts again too. Cc: Sachi King Cc: stable@vger.kernel.org Cc: Thorsten Leemhuis Fixes: 65f6c7c91cb2 ("pinctrl: amd: Revert "pinctrl: amd: disable and mask interrupts on probe"") Reported-by: Shubhra Prakash Nandi Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217754 Reported-by: Carsten Hatger Link: https://bugzilla.kernel.org/show_bug.cgi?id=217626#c28 Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230818144850.1439-1-mario.limonciello@amd.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index a8df77e80549..be6838c252f0 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -862,6 +862,33 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +{ + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; + u32 pin_reg, mask; + int i; + + mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | + BIT(WAKE_CNTRL_OFF_S4); + + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); + + if (!pd) + continue; + + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + + pin_reg = readl(gpio_dev->base + pin * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + pin * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } +} + #ifdef CONFIG_PM_SLEEP static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin) { @@ -1099,6 +1126,9 @@ static int amd_gpio_probe(struct platform_device *pdev) return PTR_ERR(gpio_dev->pctrl); } + /* Disable and mask interrupts */ + amd_gpio_irq_init(gpio_dev); + girq = &gpio_dev->gc.irq; gpio_irq_chip_set_chip(girq, &amd_gpio_irqchip); /* This will let us handle the parent IRQ in the driver */ From fe04122b932118e968ea4ba88bdc62aa806b88d1 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Thu, 10 Aug 2023 08:23:33 +0000 Subject: [PATCH 0609/2093] media: vcodec: Fix potential array out-of-bounds in encoder queue_setup commit e7f2e65699e2290fd547ec12a17008764e5d9620 upstream. variable *nplanes is provided by user via system call argument. The possible value of q_data->fmt->num_planes is 1-3, while the value of *nplanes can be 1-8. The array access by index i can cause array out-of-bounds. Fix this bug by checking *nplanes against the array size. Fixes: 4e855a6efa54 ("[media] vcodec: mediatek: Add Mediatek V4L2 Video Encoder Driver") Signed-off-by: Wei Chen Cc: stable@vger.kernel.org Reviewed-by: Chen-Yu Tsai Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c index d810a78dde51..31e3c3766218 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c @@ -821,6 +821,8 @@ static int vb2ops_venc_queue_setup(struct vb2_queue *vq, return -EINVAL; if (*nplanes) { + if (*nplanes != q_data->fmt->num_planes) + return -EINVAL; for (i = 0; i < *nplanes; i++) if (sizes[i] < q_data->sizeimage[i]) return -EINVAL; From 1900e193b5ddd32f55fef7369152531a1886879e Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Wed, 26 Jul 2023 14:35:18 +0200 Subject: [PATCH 0610/2093] PCI: acpiphp: Use pci_assign_unassigned_bridge_resources() only for non-root bus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit cc22522fd55e257c86d340ae9aedc122e705a435 upstream. 40613da52b13 ("PCI: acpiphp: Reassign resources on bridge if necessary") changed acpiphp hotplug to use pci_assign_unassigned_bridge_resources() which depends on bridge being available, however enable_slot() can be called without bridge associated: 1. Legitimate case of hotplug on root bus (widely used in virt world) 2. A (misbehaving) firmware, that sends ACPI Bus Check notifications to non existing root ports (Dell Inspiron 7352/0W6WV0), which end up at enable_slot(..., bridge = 0) where bus has no bridge assigned to it. acpihp doesn't know that it's a bridge, and bus specific 'PCI subsystem' can't augment ACPI context with bridge information since the PCI device to get this data from is/was not available. Issue is easy to reproduce with QEMU's 'pc' machine, which supports PCI hotplug on hostbridge slots. To reproduce, boot kernel at commit 40613da52b13 in VM started with following CLI (assuming guest root fs is installed on sda1 partition): # qemu-system-x86_64 -M pc -m 1G -enable-kvm -cpu host \ -monitor stdio -serial file:serial.log \ -kernel arch/x86/boot/bzImage \ -append "root=/dev/sda1 console=ttyS0" \ guest_disk.img Once guest OS is fully booted at qemu prompt: (qemu) device_add e1000 (check serial.log) it will cause NULL pointer dereference at: void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge) { struct pci_bus *parent = bridge->subordinate; BUG: kernel NULL pointer dereference, address: 0000000000000018 ? pci_assign_unassigned_bridge_resources+0x1f/0x260 enable_slot+0x21f/0x3e0 acpiphp_hotplug_notify+0x13d/0x260 acpi_device_hotplug+0xbc/0x540 acpi_hotplug_work_fn+0x15/0x20 process_one_work+0x1f7/0x370 worker_thread+0x45/0x3b0 The issue was discovered on Dell Inspiron 7352/0W6WV0 laptop with following sequence: 1. Suspend to RAM 2. Wake up with the same backtrace being observed: 3. 2nd suspend to RAM attempt makes laptop freeze Fix it by using __pci_bus_assign_resources() instead of pci_assign_unassigned_bridge_resources() as we used to do, but only in case when bus doesn't have a bridge associated (to cover for the case of ACPI event on hostbridge or non existing root port). That lets us keep hotplug on root bus working like it used to and at the same time keeps resource reassignment usable on root ports (and other 1st level bridges) that was fixed by 40613da52b13. Fixes: 40613da52b13 ("PCI: acpiphp: Reassign resources on bridge if necessary") Link: https://lore.kernel.org/r/20230726123518.2361181-2-imammedo@redhat.com Reported-by: Woody Suwalski Tested-by: Woody Suwalski Tested-by: Michal Koutný Link: https://lore.kernel.org/r/11fc981c-af49-ce64-6b43-3e282728bd1a@gmail.com Signed-off-by: Igor Mammedov Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki Acked-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/pci/hotplug/acpiphp_glue.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 393f341d9d76..ea0195337bab 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -490,6 +490,7 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) acpiphp_native_scan_bridge(dev); } } else { + LIST_HEAD(add_list); int max, pass; acpiphp_rescan_slot(slot); @@ -503,10 +504,15 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); + if (pci_is_root_bus(bus)) + __pci_bus_size_bridges(dev->subordinate, &add_list); } } } - pci_assign_unassigned_bridge_resources(bus->self); + if (pci_is_root_bus(bus)) + __pci_bus_assign_resources(bus, &add_list, NULL); + else + pci_assign_unassigned_bridge_resources(bus->self); } acpiphp_sanitize_bus(bus); From 115f2ccd3a998fe7247f59f8fb5feffc878bcbb7 Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Fri, 16 Jun 2023 15:09:34 -0400 Subject: [PATCH 0611/2093] drm/vmwgfx: Fix shader stage validation commit 14abdfae508228a7307f7491b5c4215ae70c6542 upstream. For multiple commands the driver was not correctly validating the shader stages resulting in possible kernel oopses. The validation code was only. if ever, checking the upper bound on the shader stages but never a lower bound (valid shader stages start at 1 not 0). Fixes kernel oopses ending up in vmw_binding_add, e.g.: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 2443 Comm: testcase Not tainted 6.3.0-rc4-vmwgfx #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020 RIP: 0010:vmw_binding_add+0x4c/0x140 [vmwgfx] Code: 7e 30 49 83 ff 0e 0f 87 ea 00 00 00 4b 8d 04 7f 89 d2 89 cb 48 c1 e0 03 4c 8b b0 40 3d 93 c0 48 8b 80 48 3d 93 c0 49 0f af de <48> 03 1c d0 4c 01 e3 49 8> RSP: 0018:ffffb8014416b968 EFLAGS: 00010206 RAX: ffffffffc0933ec0 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 00000000ffffffff RSI: ffffb8014416b9c0 RDI: ffffb8014316f000 RBP: ffffb8014416b998 R08: 0000000000000003 R09: 746f6c735f726564 R10: ffffffffaaf2bda0 R11: 732e676e69646e69 R12: ffffb8014316f000 R13: ffffb8014416b9c0 R14: 0000000000000040 R15: 0000000000000006 FS: 00007fba8c0af740(0000) GS:ffff8a1277c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000007c0933eb8 CR3: 0000000118244001 CR4: 00000000003706e0 Call Trace: vmw_view_bindings_add+0xf5/0x1b0 [vmwgfx] ? ___drm_dbg+0x8a/0xb0 [drm] vmw_cmd_dx_set_shader_res+0x8f/0xc0 [vmwgfx] vmw_execbuf_process+0x590/0x1360 [vmwgfx] vmw_execbuf_ioctl+0x173/0x370 [vmwgfx] ? __drm_dev_dbg+0xb4/0xe0 [drm] ? __pfx_vmw_execbuf_ioctl+0x10/0x10 [vmwgfx] drm_ioctl_kernel+0xbc/0x160 [drm] drm_ioctl+0x2d2/0x580 [drm] ? __pfx_vmw_execbuf_ioctl+0x10/0x10 [vmwgfx] ? do_fault+0x1a6/0x420 vmw_generic_ioctl+0xbd/0x180 [vmwgfx] vmw_unlocked_ioctl+0x19/0x20 [vmwgfx] __x64_sys_ioctl+0x96/0xd0 do_syscall_64+0x5d/0x90 ? handle_mm_fault+0xe4/0x2f0 ? debug_smp_processor_id+0x1b/0x30 ? fpregs_assert_state_consistent+0x2e/0x50 ? exit_to_user_mode_prepare+0x40/0x180 ? irqentry_exit_to_user_mode+0xd/0x20 ? irqentry_exit+0x3f/0x50 ? exc_page_fault+0x8b/0x180 entry_SYSCALL_64_after_hwframe+0x72/0xdc Signed-off-by: Zack Rusin Cc: security@openanolis.org Reported-by: Ziming Zhang Testcase-found-by: Niels De Graef Fixes: d80efd5cb3de ("drm/vmwgfx: Initial DX support") Cc: # v4.3+ Reviewed-by: Maaz Mombasawala Reviewed-by: Martin Krastev Link: https://patchwork.freedesktop.org/patch/msgid/20230616190934.54828-1-zack@kde.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 12 ++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 29 ++++++++++--------------- 2 files changed, 23 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 1ec9c53a7bf4..8459fab9d979 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1683,4 +1683,16 @@ static inline bool vmw_has_fences(struct vmw_private *vmw) return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0; } +static inline bool vmw_shadertype_is_valid(enum vmw_sm_type shader_model, + u32 shader_type) +{ + SVGA3dShaderType max_allowed = SVGA3D_SHADERTYPE_PREDX_MAX; + + if (shader_model >= VMW_SM_5) + max_allowed = SVGA3D_SHADERTYPE_MAX; + else if (shader_model >= VMW_SM_4) + max_allowed = SVGA3D_SHADERTYPE_DX10_MAX; + return shader_type >= SVGA3D_SHADERTYPE_MIN && shader_type < max_allowed; +} + #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 1c88b74d68cf..58ca9adf0987 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1985,7 +1985,7 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv, cmd = container_of(header, typeof(*cmd), header); - if (cmd->body.type >= SVGA3D_SHADERTYPE_PREDX_MAX) { + if (!vmw_shadertype_is_valid(VMW_SM_LEGACY, cmd->body.type)) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; @@ -2108,8 +2108,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetSingleConstantBuffer); - SVGA3dShaderType max_shader_num = has_sm5_context(dev_priv) ? - SVGA3D_NUM_SHADERTYPE : SVGA3D_NUM_SHADERTYPE_DX10; struct vmw_resource *res = NULL; struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); @@ -2126,6 +2124,14 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, if (unlikely(ret != 0)) return ret; + if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type) || + cmd->body.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) { + VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n", + (unsigned int) cmd->body.type, + (unsigned int) cmd->body.slot); + return -EINVAL; + } + binding.bi.ctx = ctx_node->ctx; binding.bi.res = res; binding.bi.bt = vmw_ctx_binding_cb; @@ -2134,14 +2140,6 @@ vmw_cmd_dx_set_single_constant_buffer(struct vmw_private *dev_priv, binding.size = cmd->body.sizeInBytes; binding.slot = cmd->body.slot; - if (binding.shader_slot >= max_shader_num || - binding.slot >= SVGA3D_DX_MAX_CONSTBUFFERS) { - VMW_DEBUG_USER("Illegal const buffer shader %u slot %u.\n", - (unsigned int) cmd->body.type, - (unsigned int) binding.slot); - return -EINVAL; - } - vmw_binding_add(ctx_node->staged, &binding.bi, binding.shader_slot, binding.slot); @@ -2200,15 +2198,13 @@ static int vmw_cmd_dx_set_shader_res(struct vmw_private *dev_priv, { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShaderResources) = container_of(header, typeof(*cmd), header); - SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ? - SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX; u32 num_sr_view = (cmd->header.size - sizeof(cmd->body)) / sizeof(SVGA3dShaderResourceViewId); if ((u64) cmd->body.startView + (u64) num_sr_view > (u64) SVGA3D_DX_MAX_SRVIEWS || - cmd->body.type >= max_allowed) { + !vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) { VMW_DEBUG_USER("Invalid shader binding.\n"); return -EINVAL; } @@ -2232,8 +2228,6 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, SVGA3dCmdHeader *header) { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXSetShader); - SVGA3dShaderType max_allowed = has_sm5_context(dev_priv) ? - SVGA3D_SHADERTYPE_MAX : SVGA3D_SHADERTYPE_DX10_MAX; struct vmw_resource *res = NULL; struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context); struct vmw_ctx_bindinfo_shader binding; @@ -2244,8 +2238,7 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, cmd = container_of(header, typeof(*cmd), header); - if (cmd->body.type >= max_allowed || - cmd->body.type < SVGA3D_SHADERTYPE_MIN) { + if (!vmw_shadertype_is_valid(dev_priv->sm_type, cmd->body.type)) { VMW_DEBUG_USER("Illegal shader type %u.\n", (unsigned int) cmd->body.type); return -EINVAL; From 3abffee6091c5a2716963c229e192a36a9590a88 Mon Sep 17 00:00:00 2001 From: Anshuman Gupta Date: Wed, 16 Aug 2023 18:22:16 +0530 Subject: [PATCH 0612/2093] drm/i915/dgfx: Enable d3cold at s2idle commit 2872144aec04baa7e43ecd2a60f7f0be3aa843fd upstream. System wide suspend already has support for lmem save/restore during suspend therefore enabling d3cold for s2idle and keepng it disable for runtime PM.(Refer below commit for d3cold runtime PM disable justification) 'commit 66eb93e71a7a ("drm/i915/dgfx: Keep PCI autosuspend control 'on' by default on all dGPU")' It will reduce the DG2 Card power consumption to ~0 Watt for s2idle power KPI. v2: - Added "Cc: stable@vger.kernel.org". Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8755 Cc: stable@vger.kernel.org Cc: Rodrigo Vivi Signed-off-by: Anshuman Gupta Reviewed-by: Rodrigo Vivi Tested-by: Aaron Ma Tested-by: Jianshui Yu Link: https://patchwork.freedesktop.org/patch/msgid/20230816125216.1722002-1-anshuman.gupta@intel.com (cherry picked from commit 2643e6d1f2a5e51877be24042d53cf956589be10) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_driver.c | 33 ++++++++++++++++-------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 35bc2a3fa811..75a93951fe42 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -574,7 +574,6 @@ static int i915_pcode_init(struct drm_i915_private *i915) static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) { struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct pci_dev *root_pdev; int ret; if (i915_inject_probe_failure(dev_priv)) @@ -686,15 +685,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) intel_bw_init_hw(dev_priv); - /* - * FIXME: Temporary hammer to avoid freezing the machine on our DGFX - * This should be totally removed when we handle the pci states properly - * on runtime PM and on s2idle cases. - */ - root_pdev = pcie_find_root_port(pdev); - if (root_pdev) - pci_d3cold_disable(root_pdev); - return 0; err_msi: @@ -718,16 +708,11 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) { struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - struct pci_dev *root_pdev; i915_perf_fini(dev_priv); if (pdev->msi_enabled) pci_disable_msi(pdev); - - root_pdev = pcie_find_root_port(pdev); - if (root_pdev) - pci_d3cold_enable(root_pdev); } /** @@ -1625,6 +1610,8 @@ static int intel_runtime_suspend(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; struct intel_gt *gt; int ret, i; @@ -1674,6 +1661,15 @@ static int intel_runtime_suspend(struct device *kdev) drm_err(&dev_priv->drm, "Unclaimed access detected prior to suspending\n"); + /* + * FIXME: Temporary hammer to avoid freezing the machine on our DGFX + * This should be totally removed when we handle the pci states properly + * on runtime PM. + */ + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_disable(root_pdev); + rpm->suspended = true; /* @@ -1712,6 +1708,8 @@ static int intel_runtime_resume(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *root_pdev; struct intel_gt *gt; int ret, i; @@ -1725,6 +1723,11 @@ static int intel_runtime_resume(struct device *kdev) intel_opregion_notify_adapter(dev_priv, PCI_D0); rpm->suspended = false; + + root_pdev = pcie_find_root_port(pdev); + if (root_pdev) + pci_d3cold_enable(root_pdev); + if (intel_uncore_unclaimed_mmio(&dev_priv->uncore)) drm_dbg(&dev_priv->drm, "Unclaimed access during suspend, bios?\n"); From 3bc9b0364a8c64d1bb1757b620ea3b9104e8054b Mon Sep 17 00:00:00 2001 From: Ankit Nautiyal Date: Fri, 18 Aug 2023 10:14:36 +0530 Subject: [PATCH 0613/2093] drm/display/dp: Fix the DP DSC Receiver cap size commit 5ad1ab30ac0809d2963ddcf39ac34317a24a2f17 upstream. DP DSC Receiver Capabilities are exposed via DPCD 60h-6Fh. Fix the DSC RECEIVER CAP SIZE accordingly. Fixes: ffddc4363c28 ("drm/dp: Add DP DSC DPCD receiver capability size define and missing SHIFT") Cc: Anusha Srivatsa Cc: Manasi Navare Cc: # v5.0+ Signed-off-by: Ankit Nautiyal Reviewed-by: Stanislav Lisovskiy Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20230818044436.177806-1-ankit.k.nautiyal@intel.com Signed-off-by: Greg Kroah-Hartman --- include/drm/display/drm_dp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index 05f2cc03d03d..b235d6833e27 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -1525,7 +1525,7 @@ enum drm_dp_phy { #define DP_BRANCH_OUI_HEADER_SIZE 0xc #define DP_RECEIVER_CAP_SIZE 0xf -#define DP_DSC_RECEIVER_CAP_SIZE 0xf +#define DP_DSC_RECEIVER_CAP_SIZE 0x10 /* DSC Capabilities 0x60 through 0x6F */ #define EDP_PSR_RECEIVER_CAP_SIZE 2 #define EDP_DISPLAY_CTL_CAP_SIZE 3 #define DP_LTTPR_COMMON_CAP_SIZE 8 From 6bcb9c7d043578a71a2409a7c4bdb2febe471cce Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Fri, 18 Aug 2023 10:03:05 -0700 Subject: [PATCH 0614/2093] x86/fpu: Invalidate FPU state correctly on exec() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1f69383b203e28cf8a4ca9570e572da1699f76cd upstream. The thread flag TIF_NEED_FPU_LOAD indicates that the FPU saved state is valid and should be reloaded when returning to userspace. However, the kernel will skip doing this if the FPU registers are already valid as determined by fpregs_state_valid(). The logic embedded there considers the state valid if two cases are both true: 1: fpu_fpregs_owner_ctx points to the current tasks FPU state 2: the last CPU the registers were live in was the current CPU. This is usually correct logic. A CPU’s fpu_fpregs_owner_ctx is set to the current FPU during the fpregs_restore_userregs() operation, so it indicates that the registers have been restored on this CPU. But this alone doesn’t preclude that the task hasn’t been rescheduled to a different CPU, where the registers were modified, and then back to the current CPU. To verify that this was not the case the logic relies on the second condition. So the assumption is that if the registers have been restored, AND they haven’t had the chance to be modified (by being loaded on another CPU), then they MUST be valid on the current CPU. Besides the lazy FPU optimizations, the other cases where the FPU registers might not be valid are when the kernel modifies the FPU register state or the FPU saved buffer. In this case the operation modifying the FPU state needs to let the kernel know the correspondence has been broken. The comment in “arch/x86/kernel/fpu/context.h” has: /* ... * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Either one of these invalidation functions is enough. Invalidate * a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ However, this is not completely true. When the kernel modifies the registers or saved FPU state, it can only rely on __fpu_invalidate_fpregs_state(), which wipes the FPU’s last_cpu tracking. The exec path instead relies on fpregs_deactivate(), which sets the CPU’s FPU context to NULL. This was observed to fail to restore the reset FPU state to the registers when returning to userspace in the following scenario: 1. A task is executing in userspace on CPU0 - CPU0’s FPU context points to tasks - fpu->last_cpu=CPU0 2. The task exec()’s 3. While in the kernel the task is preempted - CPU0 gets a thread executing in the kernel (such that no other FPU context is activated) - Scheduler sets task’s fpu->last_cpu=CPU0 when scheduling out 4. Task is migrated to CPU1 5. Continuing the exec(), the task gets to fpu_flush_thread()->fpu_reset_fpregs() - Sets CPU1’s fpu context to NULL - Copies the init state to the task’s FPU buffer - Sets TIF_NEED_FPU_LOAD on the task 6. The task reschedules back to CPU0 before completing the exec() and returning to userspace - During the reschedule, scheduler finds TIF_NEED_FPU_LOAD is set - Skips saving the registers and updating task’s fpu→last_cpu, because TIF_NEED_FPU_LOAD is the canonical source. 7. Now CPU0’s FPU context is still pointing to the task’s, and fpu->last_cpu is still CPU0. So fpregs_state_valid() returns true even though the reset FPU state has not been restored. So the root cause is that exec() is doing the wrong kind of invalidate. It should reset fpu->last_cpu via __fpu_invalidate_fpregs_state(). Further, fpu__drop() doesn't really seem appropriate as the task (and FPU) are not going away, they are just getting reset as part of an exec. So switch to __fpu_invalidate_fpregs_state(). Also, delete the misleading comment that says that either kind of invalidate will be enough, because it’s not always the case. Fixes: 33344368cb08 ("x86/fpu: Clean up the fpu__clear() variants") Reported-by: Lei Wang Signed-off-by: Rick Edgecombe Signed-off-by: Thomas Gleixner Tested-by: Lijun Pan Reviewed-by: Sohil Mehta Acked-by: Lijun Pan Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230818170305.502891-1-rick.p.edgecombe@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/fpu/context.h | 3 +-- arch/x86/kernel/fpu/core.c | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..71b5059e092a 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -19,8 +19,7 @@ * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * - * Either one of these invalidation functions is enough. Invalidate - * a resource you control: CPU if using the CPU for something else + * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..a083f9ac9e4f 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -679,7 +679,7 @@ static void fpu_reset_fpregs(void) struct fpu *fpu = ¤t->thread.fpu; fpregs_lock(); - fpu__drop(fpu); + __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a From d8f9a9cfdcd31290cb8b720746458cb110301c68 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 23 Aug 2023 14:57:47 +0800 Subject: [PATCH 0615/2093] x86/fpu: Set X86_FEATURE_OSXSAVE feature after enabling OSXSAVE in CR4 commit 2c66ca3949dc701da7f4c9407f2140ae425683a5 upstream. 0-Day found a 34.6% regression in stress-ng's 'af-alg' test case, and bisected it to commit b81fac906a8f ("x86/fpu: Move FPU initialization into arch_cpu_finalize_init()"), which optimizes the FPU init order, and moves the CR4_OSXSAVE enabling into a later place: arch_cpu_finalize_init identify_boot_cpu identify_cpu generic_identify get_cpu_cap --> setup cpu capability ... fpu__init_cpu fpu__init_cpu_xstate cr4_set_bits(X86_CR4_OSXSAVE); As the FPU is not yet initialized the CPU capability setup fails to set X86_FEATURE_OSXSAVE. Many security module like 'camellia_aesni_avx_x86_64' depend on this feature and therefore fail to load, causing the regression. Cure this by setting X86_FEATURE_OSXSAVE feature right after OSXSAVE enabling. [ tglx: Moved it into the actual BSP FPU initialization code and added a comment ] Fixes: b81fac906a8f ("x86/fpu: Move FPU initialization into arch_cpu_finalize_init()") Reported-by: kernel test robot Signed-off-by: Feng Tang Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/202307192135.203ac24e-oliver.sang@intel.com Link: https://lore.kernel.org/lkml/20230823065747.92257-1-feng.tang@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/fpu/xstate.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0bab497c9436..1afbc4866b10 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -882,6 +882,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; } + /* + * CPU capabilities initialization runs before FPU init. So + * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely + * functional, set the feature bit so depending code works. + */ + setup_force_cpu_cap(X86_FEATURE_OSXSAVE); + print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, From f1fa6e6f85cb5cbf3f1e78c42c25f3b974584543 Mon Sep 17 00:00:00 2001 From: Aleksa Savic Date: Mon, 7 Aug 2023 19:20:03 +0200 Subject: [PATCH 0616/2093] hwmon: (aquacomputer_d5next) Add selective 200ms delay after sending ctrl report commit 56b930dcd88c2adc261410501c402c790980bdb5 upstream. Add a 200ms delay after sending a ctrl report to Quadro, Octo, D5 Next and Aquaero to give them enough time to process the request and save the data to memory. Otherwise, under heavier userspace loads where multiple sysfs entries are usually set in quick succession, a new ctrl report could be requested from the device while it's still processing the previous one and fail with -EPIPE. The delay is only applied if two ctrl report operations are near each other in time. Reported by a user on Github [1] and tested by both of us. [1] https://github.com/aleksamagicka/aquacomputer_d5next-hwmon/issues/82 Fixes: 752b927951ea ("hwmon: (aquacomputer_d5next) Add support for Aquacomputer Octo") Signed-off-by: Aleksa Savic Link: https://lore.kernel.org/r/20230807172004.456968-1-savicaleksa83@gmail.com Signed-off-by: Guenter Roeck [ removed Aquaero support as it's not in 6.1 ] Signed-off-by: Aleksa Savic Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/aquacomputer_d5next.c | 36 ++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/aquacomputer_d5next.c b/drivers/hwmon/aquacomputer_d5next.c index c51a2678f0eb..8c7796d3fdd2 100644 --- a/drivers/hwmon/aquacomputer_d5next.c +++ b/drivers/hwmon/aquacomputer_d5next.c @@ -12,9 +12,11 @@ #include #include +#include #include #include #include +#include #include #include #include @@ -49,6 +51,8 @@ static const char *const aqc_device_names[] = { #define CTRL_REPORT_ID 0x03 +#define CTRL_REPORT_DELAY 200 /* ms */ + /* The HID report that the official software always sends * after writing values, currently same for all devices */ @@ -269,6 +273,9 @@ struct aqc_data { enum kinds kind; const char *name; + ktime_t last_ctrl_report_op; + int ctrl_report_delay; /* Delay between two ctrl report operations, in ms */ + int buffer_size; u8 *buffer; int checksum_start; @@ -325,17 +332,35 @@ static int aqc_pwm_to_percent(long val) return DIV_ROUND_CLOSEST(val * 100 * 100, 255); } +static void aqc_delay_ctrl_report(struct aqc_data *priv) +{ + /* + * If previous read or write is too close to this one, delay the current operation + * to give the device enough time to process the previous one. + */ + if (priv->ctrl_report_delay) { + s64 delta = ktime_ms_delta(ktime_get(), priv->last_ctrl_report_op); + + if (delta < priv->ctrl_report_delay) + msleep(priv->ctrl_report_delay - delta); + } +} + /* Expects the mutex to be locked */ static int aqc_get_ctrl_data(struct aqc_data *priv) { int ret; + aqc_delay_ctrl_report(priv); + memset(priv->buffer, 0x00, priv->buffer_size); ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) ret = -ENODATA; + priv->last_ctrl_report_op = ktime_get(); + return ret; } @@ -345,6 +370,8 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) int ret; u16 checksum; + aqc_delay_ctrl_report(priv); + /* Init and xorout value for CRC-16/USB is 0xffff */ checksum = crc16(0xffff, priv->buffer + priv->checksum_start, priv->checksum_length); checksum ^= 0xffff; @@ -356,12 +383,16 @@ static int aqc_send_ctrl_data(struct aqc_data *priv) ret = hid_hw_raw_request(priv->hdev, CTRL_REPORT_ID, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret < 0) - return ret; + goto record_access_and_ret; /* The official software sends this report after every change, so do it here as well */ ret = hid_hw_raw_request(priv->hdev, SECONDARY_CTRL_REPORT_ID, secondary_ctrl_report, SECONDARY_CTRL_REPORT_SIZE, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); + +record_access_and_ret: + priv->last_ctrl_report_op = ktime_get(); + return ret; } @@ -853,6 +884,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = D5NEXT_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = D5NEXT_POWER_CYCLES; priv->buffer_size = D5NEXT_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->temp_label = label_d5next_temp; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -893,6 +925,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = OCTO_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = OCTO_POWER_CYCLES; priv->buffer_size = OCTO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; @@ -913,6 +946,7 @@ static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) priv->virtual_temp_sensor_start_offset = QUADRO_VIRTUAL_SENSORS_START; priv->power_cycle_count_offset = QUADRO_POWER_CYCLES; priv->buffer_size = QUADRO_CTRL_REPORT_SIZE; + priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->flow_sensor_offset = QUADRO_FLOW_SENSOR_OFFSET; priv->temp_label = label_temp_sensors; From a0ec52f36ce98796aa3076885b6b96dc7e093384 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 18 Jan 2023 10:09:27 +0800 Subject: [PATCH 0617/2093] selftests/net: mv bpf/nat6to4.c to net folder MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3c107f36db061603bee7564fbd6388b1f1879fd3 upstream. There are some issues with the bpf/nat6to4.c building. 1. It use TEST_CUSTOM_PROGS, which will add the nat6to4.o to kselftest-list file and run by common run_tests. 2. When building the test via `make -C tools/testing/selftests/ TARGETS="net"`, the nat6to4.o will be build in selftests/net/bpf/ folder. But in test udpgro_frglist.sh it refers to ../bpf/nat6to4.o. The correct path should be ./bpf/nat6to4.o. 3. If building the test via `make -C tools/testing/selftests/ TARGETS="net" install`. The nat6to4.o will be installed to kselftest_install/net/ folder. Then the udpgro_frglist.sh should refer to ./nat6to4.o. To fix the confusing test path, let's just move the nat6to4.c to net folder and build it as TEST_GEN_FILES. Fixes: edae34a3ed92 ("selftests net: add UDP GRO fraglist + bpf self-tests") Tested-by: Björn Töpel Signed-off-by: Hangbin Liu Link: https://lore.kernel.org/r/20230118020927.3971864-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Hardik Garg Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/Makefile | 50 ++++++++++++++++++- tools/testing/selftests/net/bpf/Makefile | 14 ------ .../testing/selftests/net/{bpf => }/nat6to4.c | 0 tools/testing/selftests/net/udpgro_frglist.sh | 8 +-- 4 files changed, 52 insertions(+), 20 deletions(-) delete mode 100644 tools/testing/selftests/net/bpf/Makefile rename tools/testing/selftests/net/{bpf => }/nat6to4.c (100%) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 69c58362c0ed..48d1a68be1d5 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -71,14 +71,60 @@ TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_PROGS += test_ingress_egress_chaining.sh +TEST_GEN_FILES += nat6to4.o TEST_FILES := settings include ../lib.mk -include bpf/Makefile - $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread + +# Rules to generate bpf obj nat6to4.o +CLANG ?= clang +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +BPFDIR := $(abspath ../../../lib/bpf) +APIDIR := $(abspath ../../../include/uapi) + +CCINCLUDE += -I../bpf +CCINCLUDE += -I../../../../usr/include/ +CCINCLUDE += -I$(SCRATCH_DIR)/include + +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + +MAKE_DIRS := $(BUILD_DIR)/libbpf +$(MAKE_DIRS): + mkdir -p $@ + +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - Date: Tue, 14 Mar 2023 12:51:10 +0100 Subject: [PATCH 0618/2093] nfs: use vfs setgid helper commit 4f704d9a8352f5c0a8fcdb6213b934630342bd44 upstream. We've aligned setgid behavior over multiple kernel releases. The details can be found in the following two merge messages: cf619f891971 ("Merge tag 'fs.ovl.setgid.v6.2') 426b4ca2d6a5 ("Merge tag 'fs.setgid.v6.0') Consistent setgid stripping behavior is now encapsulated in the setattr_should_drop_sgid() helper which is used by all filesystems that strip setgid bits outside of vfs proper. Switch nfs to rely on this helper as well. Without this patch the setgid stripping tests in xfstests will fail. Signed-off-by: Christian Brauner (Microsoft) Reviewed-by: Christoph Hellwig Message-Id: <20230313-fs-nfs-setgid-v2-1-9a59f436cfc0@kernel.org> Signed-off-by: Christian Brauner [ Harshit: backport to 6.1.y: fs/internal.h -- minor conflict due to code change differences. include/linux/fs.h -- Used struct user_namespace *mnt_userns instead of struct mnt_idmap *idmap fs/nfs/inode.c -- Used init_user_ns instead of nop_mnt_idmap ] Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman --- fs/attr.c | 1 + fs/internal.h | 2 -- fs/nfs/inode.c | 4 +--- include/linux/fs.h | 2 ++ 4 files changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index b45f30e516fa..9b9a70e0cc54 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,6 +47,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, return ATTR_KILL_SGID; return 0; } +EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to diff --git a/fs/internal.h b/fs/internal.h index 46caa33373a4..42df013f7fe7 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -242,5 +242,3 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po /* * fs/attr.c */ -int setattr_should_drop_sgid(struct user_namespace *mnt_userns, - const struct inode *inode); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6b2cfa59a1a2..e0c1fb98f907 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -717,9 +717,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; - if ((attr->ia_valid & ATTR_KILL_SGID) != 0 && - (inode->i_mode & (S_ISGID | S_IXGRP)) == - (S_ISGID | S_IXGRP)) + if (setattr_should_drop_sgid(&init_user_ns, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; diff --git a/include/linux/fs.h b/include/linux/fs.h index a2b5592c6828..26ea1a0a59a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3120,6 +3120,8 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct user_namespace *, struct inode *); extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct user_namespace *mnt_userns, + const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set From ce59b7c1b027bb2da6a69a81bcca63783561ae9b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 2 May 2023 15:36:02 +0200 Subject: [PATCH 0619/2093] nfsd: use vfs setgid helper commit 2d8ae8c417db284f598dffb178cc01e7db0f1821 upstream. We've aligned setgid behavior over multiple kernel releases. The details can be found in commit cf619f891971 ("Merge tag 'fs.ovl.setgid.v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping") and commit 426b4ca2d6a5 ("Merge tag 'fs.setgid.v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux"). Consistent setgid stripping behavior is now encapsulated in the setattr_should_drop_sgid() helper which is used by all filesystems that strip setgid bits outside of vfs proper. Usually ATTR_KILL_SGID is raised in e.g., chown_common() and is subject to the setattr_should_drop_sgid() check to determine whether the setgid bit can be retained. Since nfsd is raising ATTR_KILL_SGID unconditionally it will cause notify_change() to strip it even if the caller had the necessary privileges to retain it. Ensure that nfsd only raises ATR_KILL_SGID if the caller lacks the necessary privileges to retain the setgid bit. Without this patch the setgid stripping tests in LTP will fail: > As you can see, the problem is S_ISGID (0002000) was dropped on a > non-group-executable file while chown was invoked by super-user, while [...] > fchown02.c:66: TFAIL: testfile2: wrong mode permissions 0100700, expected 0102700 [...] > chown02.c:57: TFAIL: testfile2: wrong mode permissions 0100700, expected 0102700 With this patch all tests pass. Reported-by: Sherry Yang Signed-off-by: Christian Brauner Reviewed-by: Jeff Layton Cc: Signed-off-by: Chuck Lever [Harshit: backport to 6.1.y: Use init_user_ns instead of nop_mnt_idmap as we don't have commit abf08576afe3 ("fs: port vfs_*() helpers to struct mnt_idmap")] Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/vfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 155b34c4683c..4c11046800ab 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -321,7 +321,9 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) iap->ia_mode &= ~S_ISGID; } else { /* set ATTR_KILL_* bits and let VFS handle it */ - iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID); + iap->ia_valid |= ATTR_KILL_SUID; + iap->ia_valid |= + setattr_should_drop_sgid(&init_user_ns, inode); } } } From 7030fbf75f260924b2ab98195e6f9fe7b8c80884 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Sun, 20 Aug 2023 16:24:12 +0100 Subject: [PATCH 0620/2093] cgroup/cpuset: Rename functions dealing with DEADLINE accounting commit ad3a557daf6915296a43ef97a3e9c48e076c9dd8 upstream. rebuild_root_domains() and update_tasks_root_domain() have neutral names, but actually deal with DEADLINE bandwidth accounting. Rename them to use 'dl_' prefix so that intent is more clear. No functional change. Suggested-by: Qais Yousef (Google) Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/cpuset.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e276db722845..888602c54209 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1066,7 +1066,7 @@ static int generate_sched_domains(cpumask_var_t **domains, return ndoms; } -static void update_tasks_root_domain(struct cpuset *cs) +static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; @@ -1079,7 +1079,7 @@ static void update_tasks_root_domain(struct cpuset *cs) css_task_iter_end(&it); } -static void rebuild_root_domains(void) +static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; @@ -1107,7 +1107,7 @@ static void rebuild_root_domains(void) rcu_read_unlock(); - update_tasks_root_domain(cs); + dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); @@ -1121,7 +1121,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); - rebuild_root_domains(); + dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } From 9bcfe1527882deac71d367ea1ff59d38c0fe9486 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Sun, 20 Aug 2023 16:24:13 +0100 Subject: [PATCH 0621/2093] sched/cpuset: Bring back cpuset_mutex commit 111cd11bbc54850f24191c52ff217da88a5e639b upstream. Turns out percpu_cpuset_rwsem - commit 1243dc518c9d ("cgroup/cpuset: Convert cpuset_mutex to percpu_rwsem") - wasn't such a brilliant idea, as it has been reported to cause slowdowns in workloads that need to change cpuset configuration frequently and it is also not implementing priority inheritance (which causes troubles with realtime workloads). Convert percpu_cpuset_rwsem back to regular cpuset_mutex. Also grab it only for SCHED_DEADLINE tasks (other policies don't care about stable cpusets anyway). Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo [ Conflict in kernel/cgroup/cpuset.c due to pulling new code/comments. Reject all new code. Remove BUG_ON() about rwsem that doesn't exist on mainline. ] Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- include/linux/cpuset.h | 8 +- kernel/cgroup/cpuset.c | 161 ++++++++++++++++++++--------------------- kernel/sched/core.c | 22 ++++-- 3 files changed, 99 insertions(+), 92 deletions(-) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..355f796c5f07 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -71,8 +71,8 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); -extern void cpuset_read_lock(void); -extern void cpuset_read_unlock(void); +extern void cpuset_lock(void); +extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -196,8 +196,8 @@ static inline void cpuset_update_active_cpus(void) static inline void cpuset_wait_for_hotplug(void) { } -static inline void cpuset_read_lock(void) { } -static inline void cpuset_read_unlock(void) { } +static inline void cpuset_lock(void) { } +static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 888602c54209..a8a060fea074 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -366,22 +366,23 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* - * There are two global locks guarding cpuset structures - cpuset_rwsem and + * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_rwsem write lock. Other - * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to - * prevent change to cpuset structures. + * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems + * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * structures. Note that cpuset_mutex needs to be a mutex as it is used in + * paths that rely on priority inheritance (e.g. scheduler - on RT) for + * correctness. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it - * is the only task able to also acquire callback_lock and be able to - * modify cpusets. It can perform various checks on the cpuset structure - * first, knowing nothing will change. It can also allocate memory while - * just holding cpuset_rwsem. While it is performing these checks, various - * callback routines can briefly acquire callback_lock to query cpusets. - * Once it is ready to make the changes, it takes callback_lock, blocking - * everyone else. + * cpuset_mutex, it blocks others, ensuring that it is the only task able to + * also acquire callback_lock and be able to modify cpusets. It can perform + * various checks on the cpuset structure first, knowing nothing will change. + * It can also allocate memory while just holding cpuset_mutex. While it is + * performing these checks, various callback routines can briefly acquire + * callback_lock to query cpusets. Once it is ready to make the changes, it + * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock @@ -403,16 +404,16 @@ static struct cpuset top_cpuset = { * guidelines for accessing subsystem state in kernel/cgroup.c */ -DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); +static DEFINE_MUTEX(cpuset_mutex); -void cpuset_read_lock(void) +void cpuset_lock(void) { - percpu_down_read(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); } -void cpuset_read_unlock(void) +void cpuset_unlock(void) { - percpu_up_read(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); @@ -496,7 +497,7 @@ static inline bool partition_is_populated(struct cpuset *cs, * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) @@ -538,7 +539,7 @@ static void guarantee_online_cpus(struct task_struct *tsk, * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -550,7 +551,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_rwsem held. The check can be skipped + * Call with callback_lock or cpuset_mutex held. The check can be skipped * if on default hierarchy. */ static void cpuset_update_task_spread_flags(struct cpuset *cs, @@ -575,7 +576,7 @@ static void cpuset_update_task_spread_flags(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_rwsem. + * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -713,7 +714,7 @@ static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_rwsem held. + * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -829,7 +830,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } -/* Must be called with cpuset_rwsem held. */ +/* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -855,7 +856,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_rwsem held. + * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -1084,7 +1085,7 @@ static void dl_rebuild_rd_accounting(void) struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); @@ -1134,7 +1135,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_rwsem held. Takes cpus_read_lock(). + * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1145,7 +1146,7 @@ static void rebuild_sched_domains_locked(void) int ndoms; lockdep_assert_cpus_held(); - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid @@ -1196,9 +1197,9 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } @@ -1208,7 +1209,7 @@ void rebuild_sched_domains(void) * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) @@ -1317,7 +1318,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, int old_prs, new_prs; int part_error = PERR_NONE; /* Partition error? */ - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. @@ -1540,7 +1541,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, bool force) @@ -1700,7 +1701,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css; - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() @@ -1950,12 +1951,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_rwsem */ + static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; @@ -1968,7 +1969,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_rwsem, we know that no other rebind effort + * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -2014,7 +2015,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -2067,7 +2068,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_rwsem held. May take callback_lock during call. + * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -2159,7 +2160,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_rwsem held, cpuset membership stays + * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -2179,7 +2180,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -2229,7 +2230,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, * @new_prs: new partition root state * Return: 0 if successful, != 0 if error * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { @@ -2467,7 +2468,7 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; } -/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; @@ -2479,7 +2480,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); cs = css_cs(css); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); @@ -2501,7 +2502,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; } @@ -2513,15 +2514,15 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* - * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task() + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2530,7 +2531,7 @@ static nodemask_t cpuset_attach_nodemask_to; static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) { - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); @@ -2558,7 +2559,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2598,7 +2599,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ @@ -2630,7 +2631,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = 0; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; @@ -2666,7 +2667,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2679,7 +2680,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = -ENODEV; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2692,7 +2693,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2725,7 +2726,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_rwsem anyway. This only happens on the legacy + * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); @@ -2733,7 +2734,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, flush_work(&cpuset_hotplug_work); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2757,7 +2758,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); @@ -2905,13 +2906,13 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, css_get(&cs->css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; @@ -3124,7 +3125,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) return 0; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) @@ -3175,7 +3176,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } @@ -3196,7 +3197,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) struct cpuset *cs = css_cs(css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (is_partition_valid(cs)) update_prstate(cs, 0); @@ -3215,7 +3216,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } @@ -3228,7 +3229,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) static void cpuset_bind(struct cgroup_subsys_state *root_css) { - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { @@ -3241,7 +3242,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) } spin_unlock_irq(&callback_lock); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* @@ -3262,7 +3263,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) return 0; lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); @@ -3283,7 +3284,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; } @@ -3299,11 +3300,11 @@ static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) if (same_cs) return; - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* @@ -3331,7 +3332,7 @@ static void cpuset_fork(struct task_struct *task) } /* CLONE_INTO_CGROUP */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cpuset_attach_task(cs, task); @@ -3339,7 +3340,7 @@ static void cpuset_fork(struct task_struct *task) if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } struct cgroup_subsys cpuset_cgrp_subsys = { @@ -3369,8 +3370,6 @@ struct cgroup_subsys cpuset_cgrp_subsys = { int __init cpuset_init(void) { - BUG_ON(percpu_init_rwsem(&cpuset_rwsem)); - BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); @@ -3442,7 +3441,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, @@ -3452,7 +3451,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, if (is_empty) remove_tasks_in_empty_cpuset(cs); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); } static void @@ -3503,14 +3502,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); goto retry; } @@ -3604,7 +3603,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /** @@ -3634,7 +3633,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); @@ -3691,7 +3690,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) update_tasks_nodemask(&top_cpuset); } - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { @@ -4101,7 +4100,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc//cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_rwsem, keeping cpuset_attach() from changing it + * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b23dcbeacdf3..8a8dbb2dac03 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7475,6 +7475,7 @@ static int __sched_setscheduler(struct task_struct *p, int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; + bool cpuset_locked = false; /* The pi code expects interrupts enabled */ BUG_ON(pi && in_interrupt()); @@ -7524,8 +7525,14 @@ static int __sched_setscheduler(struct task_struct *p, return retval; } - if (pi) - cpuset_read_lock(); + /* + * SCHED_DEADLINE bandwidth accounting relies on stable cpusets + * information. + */ + if (dl_policy(policy) || dl_policy(p->policy)) { + cpuset_locked = true; + cpuset_lock(); + } /* * Make sure no PI-waiters arrive (or leave) while we are @@ -7601,8 +7608,8 @@ static int __sched_setscheduler(struct task_struct *p, if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); goto recheck; } @@ -7669,7 +7676,8 @@ static int __sched_setscheduler(struct task_struct *p, task_rq_unlock(rq, p, &rf); if (pi) { - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); rt_mutex_adjust_pi(p); } @@ -7681,8 +7689,8 @@ static int __sched_setscheduler(struct task_struct *p, unlock: task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); return retval; } From d1b4262b78cc7638642833252ae92fc586854ffb Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Sun, 20 Aug 2023 16:24:14 +0100 Subject: [PATCH 0622/2093] sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets commit 6c24849f5515e4966d94fa5279bdff4acf2e9489 upstream. Qais reported that iterating over all tasks when rebuilding root domains for finding out which ones are DEADLINE and need their bandwidth correctly restored on such root domains can be a costly operation (10+ ms delays on suspend-resume). To fix the problem keep track of the number of DEADLINE tasks belonging to each cpuset and then use this information (followup patch) to only perform the above iteration if DEADLINE tasks are actually present in the cpuset for which a corresponding root domain is being rebuilt. Reported-by: Qais Yousef (Google) Link: https://lore.kernel.org/lkml/20230206221428.2125324-1-qyousef@layalina.io/ Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- include/linux/cpuset.h | 4 ++++ kernel/cgroup/cgroup.c | 4 ++++ kernel/cgroup/cpuset.c | 25 +++++++++++++++++++++++++ kernel/sched/deadline.c | 14 ++++++++++++++ 4 files changed, 47 insertions(+) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 355f796c5f07..0348dba5680e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -71,6 +71,8 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); +extern void inc_dl_tasks_cs(struct task_struct *task); +extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); @@ -196,6 +198,8 @@ static inline void cpuset_update_active_cpus(void) static inline void cpuset_wait_for_hotplug(void) { } +static inline void inc_dl_tasks_cs(struct task_struct *task) { } +static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 73f11e4db3a4..97ecca43386d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include @@ -6681,6 +6682,9 @@ void cgroup_exit(struct task_struct *tsk) list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--; + if (dl_task(tsk)) + dec_dl_tasks_cs(tsk); + WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a8a060fea074..5f57829bb986 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -193,6 +193,12 @@ struct cpuset { int use_parent_ecpus; int child_ecpus_count; + /* + * number of SCHED_DEADLINE tasks attached to this cpuset, so that we + * know when to rebuild associated root domain bandwidth information. + */ + int nr_deadline_tasks; + /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; @@ -245,6 +251,20 @@ static inline struct cpuset *parent_cs(struct cpuset *cs) return css_cs(cs->css.parent); } +void inc_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks++; +} + +void dec_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks--; +} + /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, @@ -2494,6 +2514,11 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) ret = security_task_setscheduler(task); if (ret) goto out_unlock; + + if (dl_task(task)) { + cs->nr_deadline_tasks++; + cpuset_attach_old_cs->nr_deadline_tasks--; + } } /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f7d381b6c313..98154a93e05d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,8 @@ * Fabio Checconi */ +#include + /* * Default limits for DL period; on the top end we guard against small util * tasks still getting ridiculously long effective runtimes, on the bottom end we @@ -2597,6 +2599,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); + /* + * In case a task is setscheduled out from SCHED_DEADLINE we need to + * keep track of that on its cpuset (for correct bandwidth tracking). + */ + dec_dl_tasks_cs(p); + if (!task_on_rq_queued(p)) { /* * Inactive timer is armed. However, p is leaving DEADLINE and @@ -2637,6 +2645,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) put_task_struct(p); + /* + * In case a task is setscheduled to SCHED_DEADLINE we need to keep + * track of that on its cpuset (for correct bandwidth tracking). + */ + inc_dl_tasks_cs(p); + /* If p is not queued we will update its parameters at next wakeup. */ if (!task_on_rq_queued(p)) { add_rq_bw(&p->dl, &rq->dl); From 064b960dbe942114a397788a57474c40cea04185 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Sun, 20 Aug 2023 16:24:15 +0100 Subject: [PATCH 0623/2093] cgroup/cpuset: Iterate only if DEADLINE tasks are present commit c0f78fd5edcf29b2822ac165f9248a6c165e8554 upstream. update_tasks_root_domain currently iterates over all tasks even if no DEADLINE task is present on the cpuset/root domain for which bandwidth accounting is being rebuilt. This has been reported to introduce 10+ ms delays on suspend-resume operations. Skip the costly iteration for cpusets that don't contain DEADLINE tasks. Reported-by: Qais Yousef (Google) Link: https://lore.kernel.org/lkml/20230206221428.2125324-1-qyousef@layalina.io/ Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/cpuset.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5f57829bb986..eca07ff71656 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1092,6 +1092,9 @@ static void dl_update_tasks_root_domain(struct cpuset *cs) struct css_task_iter it; struct task_struct *task; + if (cs->nr_deadline_tasks == 0) + return; + css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) From f0135131bb0e5b02313898da809822f4edca7e4f Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Sun, 20 Aug 2023 16:24:16 +0100 Subject: [PATCH 0624/2093] sched/deadline: Create DL BW alloc, free & check overflow interface commit 85989106feb734437e2d598b639991b9185a43a6 upstream. While moving a set of tasks between exclusive cpusets, cpuset_can_attach() -> task_can_attach() calls dl_cpu_busy(..., p) for DL BW overflow checking and per-task DL BW allocation on the destination root_domain for the DL tasks in this set. This approach has the issue of not freeing already allocated DL BW in the following error cases: (1) The set of tasks includes multiple DL tasks and DL BW overflow checking fails for one of the subsequent DL tasks. (2) Another controller next to the cpuset controller which is attached to the same cgroup fails in its can_attach(). To address this problem rework dl_cpu_busy(): (1) Split it into dl_bw_check_overflow() & dl_bw_alloc() and add a dedicated dl_bw_free(). (2) dl_bw_alloc() & dl_bw_free() take a `u64 dl_bw` parameter instead of a `struct task_struct *p` used in dl_cpu_busy(). This allows to allocate DL BW for a set of tasks too rather than only for a single task. Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Signed-off-by: Tejun Heo Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 2 ++ kernel/sched/core.c | 4 ++-- kernel/sched/deadline.c | 53 +++++++++++++++++++++++++++++++---------- kernel/sched/sched.h | 2 +- 4 files changed, 45 insertions(+), 16 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index ffb6eb55cd13..b2e30fbbeef0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1847,6 +1847,8 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int dl_bw_alloc(int cpu, u64 dl_bw); +extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8a8dbb2dac03..6963fc4ef897 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9108,7 +9108,7 @@ int task_can_attach(struct task_struct *p, if (unlikely(cpu >= nr_cpu_ids)) return -EINVAL; - ret = dl_cpu_busy(cpu, p); + ret = dl_bw_alloc(cpu, p->dl.dl_bw); } out: @@ -9393,7 +9393,7 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - int ret = dl_cpu_busy(cpu, NULL); + int ret = dl_bw_check_overflow(cpu); if (ret) return ret; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 98154a93e05d..9ce9810861ba 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3037,26 +3037,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int dl_cpu_busy(int cpu, struct task_struct *p) +enum dl_bw_request { + dl_bw_req_check_overflow = 0, + dl_bw_req_alloc, + dl_bw_req_free +}; + +static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) { - unsigned long flags, cap; + unsigned long flags; struct dl_bw *dl_b; - bool overflow; + bool overflow = 0; rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); - cap = dl_bw_capacity(cpu); - overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0); - if (!overflow && p) { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu)); + if (req == dl_bw_req_free) { + __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu)); + } else { + unsigned long cap = dl_bw_capacity(cpu); + + overflow = __dl_overflow(dl_b, cap, 0, dl_bw); + + if (req == dl_bw_req_alloc && !overflow) { + /* + * We reserve space in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu)); + } } raw_spin_unlock_irqrestore(&dl_b->lock, flags); @@ -3064,6 +3076,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p) return overflow ? -EBUSY : 0; } + +int dl_bw_check_overflow(int cpu) +{ + return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0); +} + +int dl_bw_alloc(int cpu, u64 dl_bw) +{ + return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw); +} + +void dl_bw_free(int cpu, u64 dl_bw) +{ + dl_bw_manage(dl_bw_req_free, cpu, dl_bw); +} #endif #ifdef CONFIG_SCHED_DEBUG diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d6d488e8eb55..b62d53d7c264 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -330,7 +330,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int dl_cpu_busy(int cpu, struct task_struct *p); +extern int dl_bw_check_overflow(int cpu); #ifdef CONFIG_CGROUP_SCHED From d3ff67076bed6b09be43faec7339cc51dfba451d Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Sun, 20 Aug 2023 16:24:17 +0100 Subject: [PATCH 0625/2093] cgroup/cpuset: Free DL BW in case can_attach() fails commit 2ef269ef1ac006acf974793d975539244d77b28f upstream. cpuset_can_attach() can fail. Postpone DL BW allocation until all tasks have been checked. DL BW is not allocated per-task but as a sum over all DL tasks migrating. If multiple controllers are attached to the cgroup next to the cpuset controller a non-cpuset can_attach() can fail. In this case free DL BW in cpuset_cancel_attach(). Finally, update cpuset DL task count (nr_deadline_tasks) only in cpuset_attach(). Suggested-by: Waiman Long Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 2 +- kernel/cgroup/cpuset.c | 53 ++++++++++++++++++++++++++++++++++++++---- kernel/sched/core.c | 17 ++------------ 3 files changed, 51 insertions(+), 21 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index b2e30fbbeef0..0cac69902ec5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1846,7 +1846,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index eca07ff71656..db3e05b6b4dd 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -198,6 +198,8 @@ struct cpuset { * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; + int nr_migrate_dl_tasks; + u64 sum_migrate_dl_bw; /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; @@ -2491,16 +2493,23 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; } +static void reset_migrate_dl_data(struct cpuset *cs) +{ + cs->nr_migrate_dl_tasks = 0; + cs->sum_migrate_dl_bw = 0; +} + /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; - struct cpuset *cs; + struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -2511,7 +2520,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); @@ -2519,11 +2528,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; if (dl_task(task)) { - cs->nr_deadline_tasks++; - cpuset_attach_old_cs->nr_deadline_tasks--; + cs->nr_migrate_dl_tasks++; + cs->sum_migrate_dl_bw += task->dl.dl_bw; } } + if (!cs->nr_migrate_dl_tasks) + goto out_success; + + if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { + int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + + if (unlikely(cpu >= nr_cpu_ids)) { + reset_migrate_dl_data(cs); + ret = -EINVAL; + goto out_unlock; + } + + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) { + reset_migrate_dl_data(cs); + goto out_unlock; + } + } + +out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. @@ -2546,6 +2575,14 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); + + if (cs->nr_migrate_dl_tasks) { + int cpu = cpumask_any(cs->effective_cpus); + + dl_bw_free(cpu, cs->sum_migrate_dl_bw); + reset_migrate_dl_data(cs); + } + mutex_unlock(&cpuset_mutex); } @@ -2623,6 +2660,12 @@ static void cpuset_attach(struct cgroup_taskset *tset) cs->old_mems_allowed = cpuset_attach_nodemask_to; + if (cs->nr_migrate_dl_tasks) { + cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; + oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; + reset_migrate_dl_data(cs); + } + cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); @@ -3298,7 +3341,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) if (ret) goto out_unlock; - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6963fc4ef897..0f6a92737c91 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9083,8 +9083,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int task_can_attach(struct task_struct *p, - const struct cpumask *cs_effective_cpus) +int task_can_attach(struct task_struct *p) { int ret = 0; @@ -9097,21 +9096,9 @@ int task_can_attach(struct task_struct *p, * success of set_cpus_allowed_ptr() on all attached tasks * before cpus_mask may be changed. */ - if (p->flags & PF_NO_SETAFFINITY) { + if (p->flags & PF_NO_SETAFFINITY) ret = -EINVAL; - goto out; - } - if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus); - - if (unlikely(cpu >= nr_cpu_ids)) - return -EINVAL; - ret = dl_bw_alloc(cpu, p->dl.dl_bw); - } - -out: return ret; } From f016326d31d010433b2a1a08a4856c214ae829eb Mon Sep 17 00:00:00 2001 From: Sanjay R Mehta Date: Wed, 2 Aug 2023 06:11:49 -0500 Subject: [PATCH 0626/2093] thunderbolt: Fix Thunderbolt 3 display flickering issue on 2nd hot plug onwards commit 583893a66d731f5da010a3fa38a0460e05f0149b upstream. Previously, on unplug events, the TMU mode was disabled first followed by the Time Synchronization Handshake, irrespective of whether the tb_switch_tmu_rate_write() API was successful or not. However, this caused a problem with Thunderbolt 3 (TBT3) devices, as the TSPacketInterval bits were always enabled by default, leading the host router to assume that the device router's TMU was already enabled and preventing it from initiating the Time Synchronization Handshake. As a result, TBT3 monitors experienced display flickering from the second hot plug onwards. To address this issue, we have modified the code to only disable the Time Synchronization Handshake during TMU disable if the tb_switch_tmu_rate_write() function is successful. This ensures that the TBT3 devices function correctly and eliminates the display flickering issue. Co-developed-by: Sanath S Signed-off-by: Sanath S Signed-off-by: Sanjay R Mehta Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg [ USB4v2 introduced support for uni-directional TMU mode as part of d49b4f043d63 ("thunderbolt: Add support for enhanced uni-directional TMU mode") This is not a stable candidate commit, so adjust the code for backport. ] Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/tmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c index 626aca3124b1..d9544600b386 100644 --- a/drivers/thunderbolt/tmu.c +++ b/drivers/thunderbolt/tmu.c @@ -415,7 +415,8 @@ int tb_switch_tmu_disable(struct tb_switch *sw) * uni-directional mode and we don't want to change it's TMU * mode. */ - tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + ret = tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + return ret; tb_port_tmu_time_sync_disable(up); ret = tb_port_tmu_time_sync_disable(down); From b7803afc77bee77e7df6662e1959df0038fbaac3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 20 Feb 2023 12:14:13 +0800 Subject: [PATCH 0627/2093] ublk: remove check IO_URING_F_SQE128 in ublk_ch_uring_cmd commit 9c7c4bc986932218fd0df9d2a100509772028fb1 upstream. sizeof(struct ublksrv_io_cmd) is 16bytes, which can be held in 64byte SQE, so not necessary to check IO_URING_F_SQE128. With this change, we get chance to save half SQ ring memory. Fixed: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230220041413.1524335-1-ming.lei@redhat.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/ublk_drv.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 4459cfbdbcb1..c2f0f74193f0 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1223,9 +1223,6 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, __func__, cmd->cmd_op, ub_cmd->q_id, tag, ub_cmd->result); - if (!(issue_flags & IO_URING_F_SQE128)) - goto out; - if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues) goto out; From f67e3a725b4975e3be3fda61ea6e4978213dcc2f Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 21 Aug 2023 16:45:47 +0200 Subject: [PATCH 0628/2093] can: raw: add missing refcount for memory leak fix commit c275a176e4b69868576e543409927ae75e3a3288 upstream. Commit ee8b94c8510c ("can: raw: fix receiver memory leak") introduced a new reference to the CAN netdevice that has assigned CAN filters. But this new ro->dev reference did not maintain its own refcount which lead to another KASAN use-after-free splat found by Eric Dumazet. This patch ensures a proper refcount for the CAN nedevice. Fixes: ee8b94c8510c ("can: raw: fix receiver memory leak") Reported-by: Eric Dumazet Cc: Ziyang Xuan Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20230821144547.6658-3-socketcan@hartkopp.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/can/raw.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/net/can/raw.c b/net/can/raw.c index 0dd3259357a3..8c104339d538 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -85,6 +85,7 @@ struct raw_sock { int bound; int ifindex; struct net_device *dev; + netdevice_tracker dev_tracker; struct list_head notifier; int loopback; int recv_own_msgs; @@ -285,8 +286,10 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (ro->bound) + if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); + netdev_put(dev, &ro->dev_tracker); + } if (ro->count > 1) kfree(ro->filter); @@ -391,10 +394,12 @@ static int raw_release(struct socket *sock) /* remove current filters & unregister */ if (ro->bound) { - if (ro->dev) + if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); - else + netdev_put(ro->dev, &ro->dev_tracker); + } else { raw_disable_allfilters(sock_net(sk), NULL, sk); + } } if (ro->count > 1) @@ -445,10 +450,10 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } + if (!(dev->flags & IFF_UP)) notify_enetdown = 1; @@ -456,7 +461,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); - dev_put(dev); + if (err) + goto out_put_dev; + } else { ifindex = 0; @@ -467,18 +474,28 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->dev) + if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); - else + /* drop reference to old ro->dev */ + netdev_put(ro->dev, &ro->dev_tracker); + } else { raw_disable_allfilters(sock_net(sk), NULL, sk); + } } ro->ifindex = ifindex; ro->bound = 1; + /* bind() ok -> hold a reference for new ro->dev */ ro->dev = dev; + if (ro->dev) + netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); } - out: +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + if (dev) + dev_put(dev); +out: release_sock(sk); rtnl_unlock(); From bd20e20c4d64e131498ec91f1b066cd4708088b3 Mon Sep 17 00:00:00 2001 From: Yin Fengwei Date: Tue, 8 Aug 2023 10:09:17 +0800 Subject: [PATCH 0629/2093] madvise:madvise_free_pte_range(): don't use mapcount() against large folio for sharing check commit 0e0e9bd5f7b9d40fd03b70092367247d52da1db0 upstream. Commit 98b211d6415f ("madvise: convert madvise_free_pte_range() to use a folio") replaced the page_mapcount() with folio_mapcount() to check whether the folio is shared by other mapping. It's not correct for large folios. folio_mapcount() returns the total mapcount of large folio which is not suitable to detect whether the folio is shared. Use folio_estimated_sharers() which returns a estimated number of shares. That means it's not 100% correct. It should be OK for madvise case here. User-visible effects is that the THP is skipped when user call madvise. But the correct behavior is THP should be split and processed then. NOTE: this change is a temporary fix to reduce the user-visible effects before the long term fix from David is ready. Link: https://lkml.kernel.org/r/20230808020917.2230692-4-fengwei.yin@intel.com Fixes: 98b211d6415f ("madvise: convert madvise_free_pte_range() to use a folio") Signed-off-by: Yin Fengwei Reviewed-by: Yu Zhao Reviewed-by: Ryan Roberts Cc: David Hildenbrand Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Minchan Kim Cc: Vishal Moola (Oracle) Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/mm.h | 19 +++++++++++++++++++ mm/madvise.c | 4 ++-- 2 files changed, 21 insertions(+), 2 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index f83a1c9ec8e4..104ec00823da 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1727,6 +1727,25 @@ static inline size_t folio_size(struct folio *folio) return PAGE_SIZE << folio_order(folio); } +/** + * folio_estimated_sharers - Estimate the number of sharers of a folio. + * @folio: The folio. + * + * folio_estimated_sharers() aims to serve as a function to efficiently + * estimate the number of processes sharing a folio. This is done by + * looking at the precise mapcount of the first subpage in the folio, and + * assuming the other subpages are the same. This may not be true for large + * folios. If you want exact mapcounts for exact calculations, look at + * page_mapcount() or folio_total_mapcount(). + * + * Return: The estimated number of processes sharing a folio. + */ +static inline int folio_estimated_sharers(struct folio *folio) +{ + return page_mapcount(folio_page(folio, 0)); +} + + #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { diff --git a/mm/madvise.c b/mm/madvise.c index d03e149ffe6e..5973399b2f9b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -654,8 +654,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, * deactivate all pages. */ if (folio_test_large(folio)) { - if (folio_mapcount(folio) != 1) - goto out; + if (folio_estimated_sharers(folio) != 1) + break; folio_get(folio); if (!folio_trylock(folio)) { folio_put(folio); From 774cb3de7ac93b1e3cdbcf29cc0e908b12796473 Mon Sep 17 00:00:00 2001 From: Zhu Wang Date: Sat, 19 Aug 2023 08:39:41 +0000 Subject: [PATCH 0630/2093] scsi: snic: Fix double free in snic_tgt_create() commit 1bd3a76880b2bce017987cf53780b372cf59528e upstream. Commit 41320b18a0e0 ("scsi: snic: Fix possible memory leak if device_add() fails") fixed the memory leak caused by dev_set_name() when device_add() failed. However, it did not consider that 'tgt' has already been released when put_device(&tgt->dev) is called. Remove kfree(tgt) in the error path to avoid double free of 'tgt' and move put_device(&tgt->dev) after the removed kfree(tgt) to avoid a use-after-free. Fixes: 41320b18a0e0 ("scsi: snic: Fix possible memory leak if device_add() fails") Signed-off-by: Zhu Wang Link: https://lore.kernel.org/r/20230819083941.164365-1-wangzhu9@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/snic/snic_disc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index cd27562ec922..6c529b37f3b4 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -303,12 +303,11 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid) "Snic Tgt: device_add, with err = %d\n", ret); - put_device(&tgt->dev); put_device(&snic->shost->shost_gendev); spin_lock_irqsave(snic->shost->host_lock, flags); list_del(&tgt->list); spin_unlock_irqrestore(snic->shost->host_lock, flags); - kfree(tgt); + put_device(&tgt->dev); tgt = NULL; return tgt; From 70461151d0eb765976faf79424385dfdb3e1e468 Mon Sep 17 00:00:00 2001 From: Zhu Wang Date: Tue, 22 Aug 2023 01:52:54 +0000 Subject: [PATCH 0631/2093] scsi: core: raid_class: Remove raid_component_add() commit 60c5fd2e8f3c42a5abc565ba9876ead1da5ad2b7 upstream. The raid_component_add() function was added to the kernel tree via patch "[SCSI] embryonic RAID class" (2005). Remove this function since it never has had any callers in the Linux kernel. And also raid_component_release() is only used in raid_component_add(), so it is also removed. Signed-off-by: Zhu Wang Link: https://lore.kernel.org/r/20230822015254.184270-1-wangzhu9@huawei.com Reviewed-by: Bart Van Assche Fixes: 04b5b5cb0136 ("scsi: core: Fix possible memory leak if device_add() fails") Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/raid_class.c | 48 -------------------------------------- include/linux/raid_class.h | 4 ---- 2 files changed, 52 deletions(-) diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c index 711252e52d8e..95a86e0dfd77 100644 --- a/drivers/scsi/raid_class.c +++ b/drivers/scsi/raid_class.c @@ -209,54 +209,6 @@ raid_attr_ro_state(level); raid_attr_ro_fn(resync); raid_attr_ro_state_fn(state); -static void raid_component_release(struct device *dev) -{ - struct raid_component *rc = - container_of(dev, struct raid_component, dev); - dev_printk(KERN_ERR, rc->dev.parent, "COMPONENT RELEASE\n"); - put_device(rc->dev.parent); - kfree(rc); -} - -int raid_component_add(struct raid_template *r,struct device *raid_dev, - struct device *component_dev) -{ - struct device *cdev = - attribute_container_find_class_device(&r->raid_attrs.ac, - raid_dev); - struct raid_component *rc; - struct raid_data *rd = dev_get_drvdata(cdev); - int err; - - rc = kzalloc(sizeof(*rc), GFP_KERNEL); - if (!rc) - return -ENOMEM; - - INIT_LIST_HEAD(&rc->node); - device_initialize(&rc->dev); - rc->dev.release = raid_component_release; - rc->dev.parent = get_device(component_dev); - rc->num = rd->component_count++; - - dev_set_name(&rc->dev, "component-%d", rc->num); - list_add_tail(&rc->node, &rd->component_list); - rc->dev.class = &raid_class.class; - err = device_add(&rc->dev); - if (err) - goto err_out; - - return 0; - -err_out: - put_device(&rc->dev); - list_del(&rc->node); - rd->component_count--; - put_device(component_dev); - kfree(rc); - return err; -} -EXPORT_SYMBOL(raid_component_add); - struct raid_template * raid_class_attach(struct raid_function_template *ft) { diff --git a/include/linux/raid_class.h b/include/linux/raid_class.h index 5cdfcb873a8f..772d45b2a60a 100644 --- a/include/linux/raid_class.h +++ b/include/linux/raid_class.h @@ -77,7 +77,3 @@ DEFINE_RAID_ATTRIBUTE(enum raid_state, state) struct raid_template *raid_class_attach(struct raid_function_template *); void raid_class_release(struct raid_template *); - -int __must_check raid_component_add(struct raid_template *, struct device *, - struct device *); - From 0ba9a242a6b37be06e8fc5be4ecbbc254df37ff0 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 25 Jul 2023 18:51:40 +0100 Subject: [PATCH 0632/2093] clk: Fix undefined reference to `clk_rate_exclusive_{get,put}' [ Upstream commit 2746f13f6f1df7999001d6595b16f789ecc28ad1 ] The COMMON_CLK config is not enabled in some of the architectures. This causes below build issues: pwm-rz-mtu3.c:(.text+0x114): undefined reference to `clk_rate_exclusive_put' pwm-rz-mtu3.c:(.text+0x32c): undefined reference to `clk_rate_exclusive_get' Fix these issues by moving clk_rate_exclusive_{get,put} inside COMMON_CLK code block, as clk.c is enabled by COMMON_CLK. Fixes: 55e9b8b7b806 ("clk: add clk_rate_exclusive api") Reported-by: kernel test robot Closes: https://lore.kernel.org/all/202307251752.vLfmmhYm-lkp@intel.com/ Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230725175140.361479-1-biju.das.jz@bp.renesas.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- include/linux/clk.h | 80 ++++++++++++++++++++++----------------------- 1 file changed, 40 insertions(+), 40 deletions(-) diff --git a/include/linux/clk.h b/include/linux/clk.h index 1ef013324237..06f1b292f8a0 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -183,6 +183,39 @@ int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale); */ bool clk_is_match(const struct clk *p, const struct clk *q); +/** + * clk_rate_exclusive_get - get exclusivity over the rate control of a + * producer + * @clk: clock source + * + * This function allows drivers to get exclusive control over the rate of a + * provider. It prevents any other consumer to execute, even indirectly, + * opereation which could alter the rate of the provider or cause glitches + * + * If exlusivity is claimed more than once on clock, even by the same driver, + * the rate effectively gets locked as exclusivity can't be preempted. + * + * Must not be called from within atomic context. + * + * Returns success (0) or negative errno. + */ +int clk_rate_exclusive_get(struct clk *clk); + +/** + * clk_rate_exclusive_put - release exclusivity over the rate control of a + * producer + * @clk: clock source + * + * This function allows drivers to release the exclusivity it previously got + * from clk_rate_exclusive_get() + * + * The caller must balance the number of clk_rate_exclusive_get() and + * clk_rate_exclusive_put() calls. + * + * Must not be called from within atomic context. + */ +void clk_rate_exclusive_put(struct clk *clk); + #else static inline int clk_notifier_register(struct clk *clk, @@ -236,6 +269,13 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) return p == q; } +static inline int clk_rate_exclusive_get(struct clk *clk) +{ + return 0; +} + +static inline void clk_rate_exclusive_put(struct clk *clk) {} + #endif #ifdef CONFIG_HAVE_CLK_PREPARE @@ -583,38 +623,6 @@ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); */ struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id); -/** - * clk_rate_exclusive_get - get exclusivity over the rate control of a - * producer - * @clk: clock source - * - * This function allows drivers to get exclusive control over the rate of a - * provider. It prevents any other consumer to execute, even indirectly, - * opereation which could alter the rate of the provider or cause glitches - * - * If exlusivity is claimed more than once on clock, even by the same driver, - * the rate effectively gets locked as exclusivity can't be preempted. - * - * Must not be called from within atomic context. - * - * Returns success (0) or negative errno. - */ -int clk_rate_exclusive_get(struct clk *clk); - -/** - * clk_rate_exclusive_put - release exclusivity over the rate control of a - * producer - * @clk: clock source - * - * This function allows drivers to release the exclusivity it previously got - * from clk_rate_exclusive_get() - * - * The caller must balance the number of clk_rate_exclusive_get() and - * clk_rate_exclusive_put() calls. - * - * Must not be called from within atomic context. - */ -void clk_rate_exclusive_put(struct clk *clk); /** * clk_enable - inform the system when the clock source should be running. @@ -974,14 +982,6 @@ static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {} static inline void devm_clk_put(struct device *dev, struct clk *clk) {} - -static inline int clk_rate_exclusive_get(struct clk *clk) -{ - return 0; -} - -static inline void clk_rate_exclusive_put(struct clk *clk) {} - static inline int clk_enable(struct clk *clk) { return 0; From 4a75bf3f6f4f276a58c4647433ec8676af59ac7c Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 15 Aug 2023 14:15:56 +0100 Subject: [PATCH 0633/2093] pinctrl: renesas: rzg2l: Fix NULL pointer dereference in rzg2l_dt_subnode_to_map() [ Upstream commit 661efa2284bbc2338da0424e219603f034072c74 ] Fix the below random NULL pointer crash during boot by serializing pinctrl group and function creation/remove calls in rzg2l_dt_subnode_to_map() with mutex lock. Crash log: pc : __pi_strcmp+0x20/0x140 lr : pinmux_func_name_to_selector+0x68/0xa4 Call trace: __pi_strcmp+0x20/0x140 pinmux_generic_add_function+0x34/0xcc rzg2l_dt_subnode_to_map+0x314/0x44c rzg2l_dt_node_to_map+0x164/0x194 pinctrl_dt_to_map+0x218/0x37c create_pinctrl+0x70/0x3d8 While at it, add comments for bitmap_lock and lock. Fixes: c4c4637eb57f ("pinctrl: renesas: Add RZ/G2L pin and gpio controller driver") Tested-by: Chris Paterson Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230815131558.33787-2-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/pinctrl/renesas/pinctrl-rzg2l.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index fd11d28e5a1e..2a617832a7e6 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -146,10 +147,11 @@ struct rzg2l_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range; DECLARE_BITMAP(tint_slot, RZG2L_TINT_MAX_INTERRUPT); - spinlock_t bitmap_lock; + spinlock_t bitmap_lock; /* protect tint_slot bitmap */ unsigned int hwirq[RZG2L_TINT_MAX_INTERRUPT]; - spinlock_t lock; + spinlock_t lock; /* lock read/write registers */ + struct mutex mutex; /* serialize adding groups and functions */ }; static const unsigned int iolh_groupa_mA[] = { 2, 4, 8, 12 }; @@ -359,11 +361,13 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; } + mutex_lock(&pctrl->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; - goto done; + goto unlock; } /* @@ -377,6 +381,8 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto remove_group; } + mutex_unlock(&pctrl->mutex); + maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = name; maps[idx].data.mux.function = name; @@ -388,6 +394,8 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&pctrl->mutex); done: *index = idx; kfree(configs); @@ -1501,6 +1509,7 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev) spin_lock_init(&pctrl->lock); spin_lock_init(&pctrl->bitmap_lock); + mutex_init(&pctrl->mutex); platform_set_drvdata(pdev, pctrl); From 3fb1b959af17a723491fb8776562274d229c9bfb Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 15 Aug 2023 14:15:57 +0100 Subject: [PATCH 0634/2093] pinctrl: renesas: rzv2m: Fix NULL pointer dereference in rzv2m_dt_subnode_to_map() [ Upstream commit f982b9d57e7f834138fc908804fe66f646f2b108 ] Fix the below random NULL pointer crash during boot by serializing pinctrl group and function creation/remove calls in rzv2m_dt_subnode_to_map() with mutex lock. Crash logs: pc : __pi_strcmp+0x20/0x140 lr : pinmux_func_name_to_selector+0x68/0xa4 Call trace: __pi_strcmp+0x20/0x140 pinmux_generic_add_function+0x34/0xcc rzv2m_dt_subnode_to_map+0x2e4/0x418 rzv2m_dt_node_to_map+0x15c/0x18c pinctrl_dt_to_map+0x218/0x37c create_pinctrl+0x70/0x3d8 While at it, add a comment for lock. Fixes: 92a9b8252576 ("pinctrl: renesas: Add RZ/V2M pin and gpio controller driver") Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230815131558.33787-3-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/pinctrl/renesas/pinctrl-rzv2m.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c index 35f382b055e8..2858800288bb 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c +++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -121,7 +122,8 @@ struct rzv2m_pinctrl { struct gpio_chip gpio_chip; struct pinctrl_gpio_range gpio_range; - spinlock_t lock; + spinlock_t lock; /* lock read/write registers */ + struct mutex mutex; /* serialize adding groups and functions */ }; static const unsigned int drv_1_8V_group2_uA[] = { 1800, 3800, 7800, 11000 }; @@ -320,11 +322,13 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; } + mutex_lock(&pctrl->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; - goto done; + goto unlock; } /* @@ -338,6 +342,8 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto remove_group; } + mutex_unlock(&pctrl->mutex); + maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = name; maps[idx].data.mux.function = name; @@ -349,6 +355,8 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&pctrl->mutex); done: *index = idx; kfree(configs); @@ -1070,6 +1078,7 @@ static int rzv2m_pinctrl_probe(struct platform_device *pdev) } spin_lock_init(&pctrl->lock); + mutex_init(&pctrl->mutex); platform_set_drvdata(pdev, pctrl); From 6ed06b94f68363f4bc53608623059170d3689f4e Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 15 Aug 2023 14:15:58 +0100 Subject: [PATCH 0635/2093] pinctrl: renesas: rza2: Add lock around pinctrl_generic{{add,remove}_group,{add,remove}_function} [ Upstream commit 8fcc1c40b747069644db6102c1d84c942c9d4d86 ] The pinctrl group and function creation/remove calls expect caller to take care of locking. Add lock around these functions. Fixes: b59d0e782706 ("pinctrl: Add RZ/A2 pin and gpio controller") Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230815131558.33787-4-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/pinctrl/renesas/pinctrl-rza2.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c index c0a04f1ee994..12126e30dc20 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza2.c +++ b/drivers/pinctrl/renesas/pinctrl-rza2.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -46,6 +47,7 @@ struct rza2_pinctrl_priv { struct pinctrl_dev *pctl; struct pinctrl_gpio_range gpio_range; int npins; + struct mutex mutex; /* serialize adding groups and functions */ }; #define RZA2_PDR(port) (0x0000 + (port) * 2) /* Direction 16-bit */ @@ -358,10 +360,14 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, psel_val[i] = MUX_FUNC(value); } + mutex_lock(&priv->mutex); + /* Register a single pin group listing all the pins we read from DT */ gsel = pinctrl_generic_add_group(pctldev, np->name, pins, npins, NULL); - if (gsel < 0) - return gsel; + if (gsel < 0) { + ret = gsel; + goto unlock; + } /* * Register a single group function where the 'data' is an array PSEL @@ -390,6 +396,8 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, (*map)->data.mux.function = np->name; *num_maps = 1; + mutex_unlock(&priv->mutex); + return 0; remove_function: @@ -398,6 +406,9 @@ static int rza2_dt_node_to_map(struct pinctrl_dev *pctldev, remove_group: pinctrl_generic_remove_group(pctldev, gsel); +unlock: + mutex_unlock(&priv->mutex); + dev_err(priv->dev, "Unable to parse DT node %s\n", np->name); return ret; @@ -473,6 +484,8 @@ static int rza2_pinctrl_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); + mutex_init(&priv->mutex); + platform_set_drvdata(pdev, priv); priv->npins = (int)(uintptr_t)of_device_get_match_data(&pdev->dev) * From 3282e79a85c1096b1f59925d7a04a4303d605759 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 18 Aug 2023 07:59:38 -0700 Subject: [PATCH 0636/2093] dma-buf/sw_sync: Avoid recursive lock during fence signal MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e531fdb5cd5ee2564b7fe10c8a9219e2b2fac61e ] If a signal callback releases the sw_sync fence, that will trigger a deadlock as the timeline_fence_release recurses onto the fence->lock (used both for signaling and the the timeline tree). To avoid that, temporarily hold an extra reference to the signalled fences until after we drop the lock. (This is an alternative implementation of https://patchwork.kernel.org/patch/11664717/ which avoids some potential UAF issues with the original patch.) v2: Remove now obsolete comment, use list_move_tail() and list_del_init() Reported-by: Bas Nieuwenhuizen Fixes: d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free") Signed-off-by: Rob Clark Link: https://patchwork.freedesktop.org/patch/msgid/20230818145939.39697-1-robdclark@gmail.com Reviewed-by: Christian König Signed-off-by: Christian König Signed-off-by: Sasha Levin --- drivers/dma-buf/sw_sync.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 348b3a9170fa..7f5ed1aa7a9f 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -191,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = { */ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) { + LIST_HEAD(signalled); struct sync_pt *pt, *next; trace_sync_timeline(obj); @@ -203,21 +204,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) if (!timeline_fence_signaled(&pt->base)) break; - list_del_init(&pt->link); + dma_fence_get(&pt->base); + + list_move_tail(&pt->link, &signalled); rb_erase(&pt->node, &obj->pt_tree); - /* - * A signal callback may release the last reference to this - * fence, causing it to be freed. That operation has to be - * last to avoid a use after free inside this loop, and must - * be after we remove the fence from the timeline in order to - * prevent deadlocking on timeline->lock inside - * timeline_fence_release(). - */ dma_fence_signal_locked(&pt->base); } spin_unlock_irq(&obj->lock); + + list_for_each_entry_safe(pt, next, &signalled, link) { + list_del_init(&pt->link); + dma_fence_put(&pt->base); + } } /** From 3c839f8332dfca0e7480b6c03785cc85da2c5415 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 22 Aug 2023 21:29:42 +0200 Subject: [PATCH 0637/2093] gpio: sim: dispose of irq mappings before destroying the irq_sim domain [ Upstream commit ab4109f91b328ff5cb5e1279f64d443241add2d1 ] If a GPIO simulator device is unbound with interrupts still requested, we will hit a use-after-free issue in __irq_domain_deactivate_irq(). The owner of the irq domain must dispose of all mappings before destroying the domain object. Fixes: cb8c474e79be ("gpio: sim: new testing module") Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Signed-off-by: Sasha Levin --- drivers/gpio/gpio-sim.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index fef12e57b1f1..3fa123bb72ee 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -290,6 +290,15 @@ static void gpio_sim_mutex_destroy(void *data) mutex_destroy(lock); } +static void gpio_sim_dispose_mappings(void *data) +{ + struct gpio_sim_chip *chip = data; + unsigned int i; + + for (i = 0; i < chip->gc.ngpio; i++) + irq_dispose_mapping(irq_find_mapping(chip->irq_sim, i)); +} + static void gpio_sim_sysfs_remove(void *data) { struct gpio_sim_chip *chip = data; @@ -402,6 +411,10 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) if (IS_ERR(chip->irq_sim)) return PTR_ERR(chip->irq_sim); + ret = devm_add_action_or_reset(dev, gpio_sim_dispose_mappings, chip); + if (ret) + return ret; + mutex_init(&chip->lock); ret = devm_add_action_or_reset(dev, gpio_sim_mutex_destroy, &chip->lock); From d10ab996bd5cb63e854924dd3d6ffb036d4d432a Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 22 Aug 2023 21:29:43 +0200 Subject: [PATCH 0638/2093] gpio: sim: pass the GPIO device's software node to irq domain [ Upstream commit 6e39c1ac688161b4db3617aabbca589b395242bc ] Associate the swnode of the GPIO device's (which is the interrupt controller here) with the irq domain. Otherwise the interrupt-controller device attribute is a no-op. Fixes: cb8c474e79be ("gpio: sim: new testing module") Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Signed-off-by: Sasha Levin --- drivers/gpio/gpio-sim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 3fa123bb72ee..b352775e5e0b 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -407,7 +407,7 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) if (!chip->pull_map) return -ENOMEM; - chip->irq_sim = devm_irq_domain_create_sim(dev, NULL, num_lines); + chip->irq_sim = devm_irq_domain_create_sim(dev, swnode, num_lines); if (IS_ERR(chip->irq_sim)) return PTR_ERR(chip->irq_sim); From 936cf79649e0b9cbe6b638e6cc12712a9c6b26de Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 23 Aug 2023 20:11:49 -0500 Subject: [PATCH 0639/2093] ASoC: amd: yc: Fix a non-functional mic on Lenovo 82SJ [ Upstream commit c008323fe361bd62a43d9fb29737dacd5c067fb7 ] Lenovo 82SJ doesn't have DMIC connected like 82V2 does. Narrow the match down to only cover 82V2. Reported-by: prosenfeld@Yuhsbstudents.org Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217063 Fixes: 2232b2dd8cd4 ("ASoC: amd: yc: Add Lenovo Yoga Slim 7 Pro X to quirks table") Signed-off-by: Mario Limonciello --- sound/soc/amd/yc/acp6x-mach.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 26101299af4d..9a9571c3f08c 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -217,7 +217,7 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82"), + DMI_MATCH(DMI_PRODUCT_NAME, "82V2"), } }, { From 9d5a3b4aee11301acce8c1752cb272478d082357 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Fri, 18 Aug 2023 20:43:55 -0400 Subject: [PATCH 0640/2093] maple_tree: disable mas_wr_append() when other readers are possible [ Upstream commit cfeb6ae8bcb96ccf674724f223661bbcef7b0d0b ] The current implementation of append may cause duplicate data and/or incorrect ranges to be returned to a reader during an update. Although this has not been reported or seen, disable the append write operation while the tree is in rcu mode out of an abundance of caution. During the analysis of the mas_next_slot() the following was artificially created by separating the writer and reader code: Writer: reader: mas_wr_append set end pivot updates end metata Detects write to last slot last slot write is to start of slot store current contents in slot overwrite old end pivot mas_next_slot(): read end metadata read old end pivot return with incorrect range store new value Alternatively: Writer: reader: mas_wr_append set end pivot updates end metata Detects write to last slot last lost write to end of slot store value mas_next_slot(): read end metadata read old end pivot read new end pivot return with incorrect range set old end pivot There may be other accesses that are not safe since we are now updating both metadata and pointers, so disabling append if there could be rcu readers is the safest action. Link: https://lkml.kernel.org/r/20230819004356.1454718-2-Liam.Howlett@oracle.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Liam R. Howlett Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- lib/maple_tree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 47d0c95b9a01..250b4c67fac8 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4333,6 +4333,9 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) struct ma_state *mas = wr_mas->mas; unsigned char node_pivots = mt_pivots[wr_mas->type]; + if (mt_in_rcu(mas->tree)) + return false; + if ((mas->index != wr_mas->r_min) && (mas->last == wr_mas->r_max)) { if (new_end < node_pivots) wr_mas->pivots[new_end] = wr_mas->pivots[end]; From 19641b979b24b31c6da4b5ec29f6c57057499657 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 5 Jun 2023 10:58:29 +0200 Subject: [PATCH 0641/2093] ASoC: amd: vangogh: select CONFIG_SND_AMD_ACP_CONFIG commit fd0a7ec379dbf21b7bfd81914381ae5281706ef5 upstream. The vangogh driver just gained a link time dependency that now causes randconfig builds to fail: x86_64-linux-ld: sound/soc/amd/vangogh/pci-acp5x.o: in function `snd_acp5x_probe': pci-acp5x.c:(.text+0xbb): undefined reference to `snd_amd_acp_find_config' Fixes: e89f45edb747e ("ASoC: amd: vangogh: Add check for acp config flags in vangogh platform") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230605085839.2157268-1-arnd@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/amd/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig index 3968c478c938..44d4e6e51a35 100644 --- a/sound/soc/amd/Kconfig +++ b/sound/soc/amd/Kconfig @@ -71,6 +71,7 @@ config SND_SOC_AMD_RENOIR_MACH config SND_SOC_AMD_ACP5x tristate "AMD Audio Coprocessor-v5.x I2S support" depends on X86 && PCI + select SND_AMD_ACP_CONFIG help This option enables ACP v5.x support on AMD platform From a2943d2d9a00ae7c5c1fde2b2e7e9cdb47e7db05 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 30 Aug 2023 16:11:13 +0200 Subject: [PATCH 0642/2093] Linux 6.1.50 Link: https://lore.kernel.org/r/20230828101156.480754469@linuxfoundation.org Tested-by: Conor Dooley Tested-by: Linux Kernel Functional Testing Tested-by: Salvatore Bonaccorso Tested-by: Joel Fernandes (Google) Tested-by: SeongJae Park Tested-by: Bagas Sanjaya Tested-by: Sudip Mukherjee Tested-by: Takeshi Ogasawara Tested-by: Shuah Khan Tested-by: Florian Fainelli Tested-by: Guenter Roeck Tested-by: Jon Hunter Tested-by: Pavel Machek (CIP) Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 61ebd54aba89..e5e1fdeef8bf 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 49 +SUBLEVEL = 50 EXTRAVERSION = NAME = Curry Ramen From b0dc0aac2085db45b4dac7f0ed2917d7da4f266d Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 12 Jul 2023 12:24:59 -0500 Subject: [PATCH 0643/2093] ACPI: thermal: Drop nocrt parameter commit 5f641174a12b8a876a4101201a21ef4675ecc014 upstream. The `nocrt` module parameter has no code associated with it and does nothing. As `crt=-1` has same functionality as what nocrt should be doing drop `nocrt` and associated documentation. This should fix a quirk for Gigabyte GA-7ZX that used `nocrt` and thus didn't function properly. Fixes: 8c99fdce3078 ("ACPI: thermal: set "thermal.nocrt" via DMI on Gigabyte GA-7ZX") Signed-off-by: Mario Limonciello Cc: All applicable Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/kernel-parameters.txt | 4 ---- drivers/acpi/thermal.c | 6 +----- 2 files changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 882b6198dd0d..31af352b4762 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6164,10 +6164,6 @@ -1: disable all critical trip points in all thermal zones : override all critical trip points - thermal.nocrt= [HW,ACPI] - Set to disable actions on ACPI thermal zone - critical and hot trip points. - thermal.off= [HW,ACPI] 1: disable ACPI thermal control diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 40b07057983e..40ecb55b52f8 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -59,10 +59,6 @@ static int tzp; module_param(tzp, int, 0444); MODULE_PARM_DESC(tzp, "Thermal zone polling frequency, in 1/10 seconds."); -static int nocrt; -module_param(nocrt, int, 0); -MODULE_PARM_DESC(nocrt, "Set to take no action upon ACPI thermal zone critical trips points."); - static int off; module_param(off, int, 0); MODULE_PARM_DESC(off, "Set to disable ACPI thermal support."); @@ -1128,7 +1124,7 @@ static int thermal_act(const struct dmi_system_id *d) { static int thermal_nocrt(const struct dmi_system_id *d) { pr_notice("%s detected: disabling all critical thermal trip point actions.\n", d->ident); - nocrt = 1; + crt = -1; return 0; } static int thermal_tzp(const struct dmi_system_id *d) { From 207e228bf1f3b53e5b3eae2c336ea83225155792 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 1 Aug 2023 14:54:07 +0000 Subject: [PATCH 0644/2093] module: Expose module_init_layout_section() commit 2abcc4b5a64a65a2d2287ba0be5c2871c1552416 upstream. module_init_layout_section() choses whether the core module loader considers a section as init or not. This affects the placement of the exit section when module unloading is disabled. This code will never run, so it can be free()d once the module has been initialised. arm and arm64 need to count the number of PLTs they need before applying relocations based on the section name. The init PLTs are stored separately so they can be free()d. arm and arm64 both use within_module_init() to decide which list of PLTs to use when applying the relocation. Because within_module_init()'s behaviour changes when module unloading is disabled, both architecture would need to take this into account when counting the PLTs. Today neither architecture does this, meaning when module unloading is disabled there are insufficient PLTs in the init section to load some modules, resulting in warnings: | WARNING: CPU: 2 PID: 51 at arch/arm64/kernel/module-plts.c:99 module_emit_plt_entry+0x184/0x1cc | Modules linked in: crct10dif_common | CPU: 2 PID: 51 Comm: modprobe Not tainted 6.5.0-rc4-yocto-standard-dirty #15208 | Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 | pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : module_emit_plt_entry+0x184/0x1cc | lr : module_emit_plt_entry+0x94/0x1cc | sp : ffffffc0803bba60 [...] | Call trace: | module_emit_plt_entry+0x184/0x1cc | apply_relocate_add+0x2bc/0x8e4 | load_module+0xe34/0x1bd4 | init_module_from_file+0x84/0xc0 | __arm64_sys_finit_module+0x1b8/0x27c | invoke_syscall.constprop.0+0x5c/0x104 | do_el0_svc+0x58/0x160 | el0_svc+0x38/0x110 | el0t_64_sync_handler+0xc0/0xc4 | el0t_64_sync+0x190/0x194 Instead of duplicating module_init_layout_section()s logic, expose it. Reported-by: Adam Johnston Fixes: 055f23b74b20 ("module: check for exit sections in layout_sections() instead of module_init_section()") Cc: stable@vger.kernel.org Signed-off-by: James Morse Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- include/linux/moduleloader.h | 5 +++++ kernel/module/main.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 9e09d11ffe5b..1322652a9d0d 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -39,6 +39,11 @@ bool module_init_section(const char *name); */ bool module_exit_section(const char *name); +/* Describes whether within_module_init() will consider this an init section + * or not. This behaviour changes with CONFIG_MODULE_UNLOAD. + */ +bool module_init_layout_section(const char *sname); + /* * Apply the given relocation to the (simplified) ELF. Return -error * or 0. diff --git a/kernel/module/main.c b/kernel/module/main.c index 7a627345d4fd..7a6f43d2b775 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1401,7 +1401,7 @@ long module_get_offset(struct module *mod, unsigned int *size, return ret; } -static bool module_init_layout_section(const char *sname) +bool module_init_layout_section(const char *sname) { #ifndef CONFIG_MODULE_UNLOAD if (module_exit_section(sname)) From 42efdb3531abdef03f915acc486ce687f574e05c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 18:06:37 +0200 Subject: [PATCH 0645/2093] arm64: module-plts: inline linux/moduleloader.h commit 60a0aab7463ee69296692d980b96510ccce3934e upstream. module_frob_arch_sections() is declared in moduleloader.h, but that is not included before the definition: arch/arm64/kernel/module-plts.c:286:5: error: no previous prototype for 'module_frob_arch_sections' [-Werror=missing-prototypes] Signed-off-by: Arnd Bergmann Reviewed-by: Kees Cook Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20230516160642.523862-11-arnd@kernel.org Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/module-plts.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 5a0a8f552a61..da77ec62a5bb 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -7,6 +7,7 @@ #include #include #include +#include #include static struct plt_entry __get_adrp_add_pair(u64 dst, u64 pc, From 8d99105d6a1068d2fcad812ceedf373cc829b7d8 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 1 Aug 2023 14:54:08 +0000 Subject: [PATCH 0646/2093] arm64: module: Use module_init_layout_section() to spot init sections commit f928f8b1a2496e7af95b860f9acf553f20f68f16 upstream. Today module_frob_arch_sections() spots init sections from their 'init' prefix, and uses this to keep the init PLTs separate from the rest. module_emit_plt_entry() uses within_module_init() to determine if a location is in the init text or not, but this depends on whether core code thought this was an init section. Naturally the logic is different. module_init_layout_section() groups the init and exit text together if module unloading is disabled, as the exit code will never run. The result is kernels with this configuration can't load all their modules because there are not enough PLTs for the combined init+exit section. This results in the following: | WARNING: CPU: 2 PID: 51 at arch/arm64/kernel/module-plts.c:99 module_emit_plt_entry+0x184/0x1cc | Modules linked in: crct10dif_common | CPU: 2 PID: 51 Comm: modprobe Not tainted 6.5.0-rc4-yocto-standard-dirty #15208 | Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 | pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : module_emit_plt_entry+0x184/0x1cc | lr : module_emit_plt_entry+0x94/0x1cc | sp : ffffffc0803bba60 [...] | Call trace: | module_emit_plt_entry+0x184/0x1cc | apply_relocate_add+0x2bc/0x8e4 | load_module+0xe34/0x1bd4 | init_module_from_file+0x84/0xc0 | __arm64_sys_finit_module+0x1b8/0x27c | invoke_syscall.constprop.0+0x5c/0x104 | do_el0_svc+0x58/0x160 | el0_svc+0x38/0x110 | el0t_64_sync_handler+0xc0/0xc4 | el0t_64_sync+0x190/0x194 A previous patch exposed module_init_layout_section(), use that so the logic is the same. Reported-by: Adam Johnston Tested-by: Adam Johnston Fixes: 055f23b74b20 ("module: check for exit sections in layout_sections() instead of module_init_section()") Cc: # 5.15.x: 60a0aab7463ee69 arm64: module-plts: inline linux/moduleloader.h Cc: # 5.15.x Signed-off-by: James Morse Acked-by: Catalin Marinas Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/module-plts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index da77ec62a5bb..c703b5db8eb1 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -344,7 +344,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (nents) sort(rels, nents, sizeof(Elf64_Rela), cmp_rela, NULL); - if (!str_has_prefix(secstrings + dstsec->sh_name, ".init")) + if (!module_init_layout_section(secstrings + dstsec->sh_name)) core_plts += count_plts(syms, rels, numrels, sechdrs[i].sh_info, dstsec); else From 1cb79e7e0572bf04365428f5b558114517c33ec2 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 1 Aug 2023 14:54:09 +0000 Subject: [PATCH 0647/2093] ARM: module: Use module_init_layout_section() to spot init sections commit a6846234f45801441f0e31a8b37f901ef0abd2df upstream. Today module_frob_arch_sections() spots init sections from their 'init' prefix, and uses this to keep the init PLTs separate from the rest. get_module_plt() uses within_module_init() to determine if a location is in the init text or not, but this depends on whether core code thought this was an init section. Naturally the logic is different. module_init_layout_section() groups the init and exit text together if module unloading is disabled, as the exit code will never run. The result is kernels with this configuration can't load all their modules because there are not enough PLTs for the combined init+exit section. A previous patch exposed module_init_layout_section(), use that so the logic is the same. Fixes: 055f23b74b20 ("module: check for exit sections in layout_sections() instead of module_init_section()") Cc: stable@vger.kernel.org Signed-off-by: James Morse Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- arch/arm/kernel/module-plts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 1fc309b41f94..8d809724cde5 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -256,7 +256,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, /* sort by type and symbol index */ sort(rels, numrels, sizeof(Elf32_Rel), cmp_rel, NULL); - if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0) + if (!module_init_layout_section(secstrings + dstsec->sh_name)) core_plts += count_plts(syms, dstsec->sh_addr, rels, numrels, s->sh_info); else From b3d099df68de4f62ade6f8bf59e80899ac463d3b Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 15 Aug 2023 00:31:09 +0200 Subject: [PATCH 0648/2093] lockdep: fix static memory detection even more commit 0a6b58c5cd0dfd7961e725212f0fc8dfc5d96195 upstream. On the parisc architecture, lockdep reports for all static objects which are in the __initdata section (e.g. "setup_done" in devtmpfs, "kthreadd_done" in init/main.c) this warning: INFO: trying to register non-static key. The warning itself is wrong, because those objects are in the __initdata section, but the section itself is on parisc outside of range from _stext to _end, which is why the static_obj() functions returns a wrong answer. While fixing this issue, I noticed that the whole existing check can be simplified a lot. Instead of checking against the _stext and _end symbols (which include code areas too) just check for the .data and .bss segments (since we check a data object). This can be done with the existing is_kernel_core_data() macro. In addition objects in the __initdata section can be checked with init_section_contains(), and is_kernel_rodata() allows keys to be in the _ro_after_init section. This partly reverts and simplifies commit bac59d18c701 ("x86/setup: Fix static memory detection"). Link: https://lkml.kernel.org/r/ZNqrLRaOi/3wPAdp@p100 Fixes: bac59d18c701 ("x86/setup: Fix static memory detection") Signed-off-by: Helge Deller Cc: Borislav Petkov Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/sections.h | 18 ----------------- kernel/locking/lockdep.c | 36 +++++++++++++-------------------- 2 files changed, 14 insertions(+), 40 deletions(-) diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index a6e8373a5170..3fa87e5e11ab 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_SECTIONS_H #define _ASM_X86_SECTIONS_H -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed - #include #include @@ -18,20 +16,4 @@ extern char __end_of_kernel_reserve[]; extern unsigned long _brk_start, _brk_end; -static inline bool arch_is_kernel_initmem_freed(unsigned long addr) -{ - /* - * If _brk_start has not been cleared, brk allocation is incomplete, - * and we can not make assumptions about its use. - */ - if (_brk_start) - return 0; - - /* - * After brk allocation is complete, space between _brk_end and _end - * is available for allocation. - */ - return addr >= _brk_end && addr < (unsigned long)&_end; -} - #endif /* _ASM_X86_SECTIONS_H */ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 50d4863974e7..0224b0329d01 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -817,34 +817,26 @@ static int very_verbose(struct lock_class *class) * Is this the address of a static object: */ #ifdef __KERNEL__ -/* - * Check if an address is part of freed initmem. After initmem is freed, - * memory can be allocated from it, and such allocations would then have - * addresses within the range [_stext, _end]. - */ -#ifndef arch_is_kernel_initmem_freed -static int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (system_state < SYSTEM_FREEING_INITMEM) - return 0; - - return init_section_contains((void *)addr, 1); -} -#endif - static int static_obj(const void *obj) { - unsigned long start = (unsigned long) &_stext, - end = (unsigned long) &_end, - addr = (unsigned long) obj; + unsigned long addr = (unsigned long) obj; - if (arch_is_kernel_initmem_freed(addr)) - return 0; + if (is_kernel_core_data(addr)) + return 1; /* - * static variable? + * keys are allowed in the __ro_after_init section. */ - if ((addr >= start) && (addr < end)) + if (is_kernel_rodata(addr)) + return 1; + + /* + * in initdata section and used during bootup only? + * NOTE: On some platforms the initdata section is + * outside of the _stext ... _end range. + */ + if (system_state < SYSTEM_FREEING_INITMEM && + init_section_contains((void *)addr, 1)) return 1; /* From e8ac4be717015978636ada1e985e6cc15b8a65c8 Mon Sep 17 00:00:00 2001 From: John David Anglin Date: Sun, 26 Feb 2023 18:03:33 +0000 Subject: [PATCH 0649/2093] parisc: Cleanup mmap implementation regarding color alignment commit 567b35159e76997e95b643b9a8a5d9d2198f2522 upstream. This change simplifies the randomization of file mapping regions. It reworks the code to remove duplication. The flow is now similar to that for mips. Finally, we consistently use the do_color_align variable to determine when color alignment is needed. Tested on rp3440. Signed-off-by: John David Anglin Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/sys_parisc.c | 170 ++++++++++++-------------------- 1 file changed, 65 insertions(+), 105 deletions(-) diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 09a34b07f02e..39acccabf2ed 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -25,31 +25,26 @@ #include #include -/* we construct an artificial offset for the mapping based on the physical - * address of the kernel mapping variable */ -#define GET_LAST_MMAP(filp) \ - (filp ? ((unsigned long) filp->f_mapping) >> 8 : 0UL) -#define SET_LAST_MMAP(filp, val) \ - { /* nothing */ } +/* + * Construct an artificial page offset for the mapping based on the physical + * address of the kernel file mapping variable. + */ +#define GET_FILP_PGOFF(filp) \ + (filp ? (((unsigned long) filp->f_mapping) >> 8) \ + & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) -static int get_offset(unsigned int last_mmap) -{ - return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT; -} - -static unsigned long shared_align_offset(unsigned int last_mmap, +static unsigned long shared_align_offset(unsigned long filp_pgoff, unsigned long pgoff) { - return (get_offset(last_mmap) + pgoff) << PAGE_SHIFT; + return (filp_pgoff + pgoff) << PAGE_SHIFT; } static inline unsigned long COLOR_ALIGN(unsigned long addr, - unsigned int last_mmap, unsigned long pgoff) + unsigned long filp_pgoff, unsigned long pgoff) { unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1); unsigned long off = (SHM_COLOUR-1) & - (shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT); - + shared_align_offset(filp_pgoff, pgoff); return base + off; } @@ -98,92 +93,41 @@ static unsigned long mmap_upper_limit(struct rlimit *rlim_stack) return PAGE_ALIGN(STACK_TOP - stack_base); } +enum mmap_allocation_direction {UP, DOWN}; -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +static unsigned long arch_get_unmapped_area_common(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags, enum mmap_allocation_direction dir) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long task_size = TASK_SIZE; - int do_color_align, last_mmap; + unsigned long filp_pgoff; + int do_color_align; struct vm_unmapped_area_info info; - if (len > task_size) + if (unlikely(len > TASK_SIZE)) return -ENOMEM; do_color_align = 0; if (filp || (flags & MAP_SHARED)) do_color_align = 1; - last_mmap = GET_LAST_MMAP(filp); + filp_pgoff = GET_FILP_PGOFF(filp); if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && last_mmap && - (addr - shared_align_offset(last_mmap, pgoff)) + /* Even MAP_FIXED mappings must reside within TASK_SIZE */ + if (TASK_SIZE - len < addr) + return -EINVAL; + + if ((flags & MAP_SHARED) && filp && + (addr - shared_align_offset(filp_pgoff, pgoff)) & (SHM_COLOUR - 1)) return -EINVAL; - goto found_addr; + return addr; } if (addr) { - if (do_color_align && last_mmap) - addr = COLOR_ALIGN(addr, last_mmap, pgoff); - else - addr = PAGE_ALIGN(addr); - - vma = find_vma_prev(mm, addr, &prev); - if (task_size - len >= addr && - (!vma || addr + len <= vm_start_gap(vma)) && - (!prev || addr >= vm_end_gap(prev))) - goto found_addr; - } - - info.flags = 0; - info.length = len; - info.low_limit = mm->mmap_legacy_base; - info.high_limit = mmap_upper_limit(NULL); - info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; - info.align_offset = shared_align_offset(last_mmap, pgoff); - addr = vm_unmapped_area(&info); - -found_addr: - if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) - SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); - - return addr; -} - -unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) -{ - struct vm_area_struct *vma, *prev; - struct mm_struct *mm = current->mm; - unsigned long addr = addr0; - int do_color_align, last_mmap; - struct vm_unmapped_area_info info; - - /* requested length too big for entire address space */ - if (len > TASK_SIZE) - return -ENOMEM; - - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = 1; - last_mmap = GET_LAST_MMAP(filp); - - if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && last_mmap && - (addr - shared_align_offset(last_mmap, pgoff)) - & (SHM_COLOUR - 1)) - return -EINVAL; - goto found_addr; - } - - /* requesting a specific address */ - if (addr) { - if (do_color_align && last_mmap) - addr = COLOR_ALIGN(addr, last_mmap, pgoff); + if (do_color_align) + addr = COLOR_ALIGN(addr, filp_pgoff, pgoff); else addr = PAGE_ALIGN(addr); @@ -191,33 +135,49 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (TASK_SIZE - len >= addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) - goto found_addr; + return addr; } - info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = mm->mmap_base; - info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; - info.align_offset = shared_align_offset(last_mmap, pgoff); - addr = vm_unmapped_area(&info); - if (!(addr & ~PAGE_MASK)) - goto found_addr; - VM_BUG_ON(addr != -ENOMEM); + info.align_mask = do_color_align ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; + info.align_offset = shared_align_offset(filp_pgoff, pgoff); - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); + if (dir == DOWN) { + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + return addr; + VM_BUG_ON(addr != -ENOMEM); -found_addr: - if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) - SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + } - return addr; + info.flags = 0; + info.low_limit = mm->mmap_legacy_base; + info.high_limit = mmap_upper_limit(NULL); + return vm_unmapped_area(&info); +} + +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return arch_get_unmapped_area_common(filp, + addr, len, pgoff, flags, UP); +} + +unsigned long arch_get_unmapped_area_topdown(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return arch_get_unmapped_area_common(filp, + addr, len, pgoff, flags, DOWN); } static int mmap_is_legacy(void) From fff21bc26bbdd39c09e48828c548a1f1eb0cf530 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 30 Jun 2023 12:36:09 +0200 Subject: [PATCH 0650/2093] parisc: sys_parisc: parisc_personality() is called from asm code commit b5d89408b9fb21258f7c371d6d48a674f60f7181 upstream. Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/sys_parisc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 39acccabf2ed..9915062d5243 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -24,6 +24,7 @@ #include #include #include +#include /* * Construct an artificial page offset for the mapping based on the physical @@ -339,7 +340,7 @@ asmlinkage long parisc_fallocate(int fd, int mode, u32 offhi, u32 offlo, ((u64)lenhi << 32) | lenlo); } -long parisc_personality(unsigned long personality) +asmlinkage long parisc_personality(unsigned long personality) { long err; From 5d54040e9d578513ff5378a422882dbeaaf4886c Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 28 Aug 2023 23:55:55 +0200 Subject: [PATCH 0651/2093] io_uring/parisc: Adjust pgoff in io_uring mmap() for parisc Vidra Jonas reported issues on parisc with libuv which then triggers build errors with cmake. Debugging shows that those issues stem from io_uring(). I was not able to easily pull in upstream commits directly, so here is IMHO the least invasive manual backport of the following upstream commits to fix the cache aliasing issues on parisc on kernel 6.1 with io_uring: 56675f8b9f9b ("io_uring/parisc: Adjust pgoff in io_uring mmap() for parisc") 32832a407a71 ("io_uring: Fix io_uring mmap() by using architecture-provided get_unmapped_area()") d808459b2e31 ("io_uring: Adjust mapping wrt architecture aliasing requirements") With this patch kernel 6.1 has all relevant mmap changes and is identical to kernel 6.5 with regard to mmap() in io_uring. Signed-off-by: Helge Deller Reported-by: Vidra.Jonas@seznam.cz Link: https://lore.kernel.org/linux-parisc/520.NvTX.6mXZpmfh4Ju.1awpAS@seznam.cz/ Cc: Sam James Cc: John David Anglin Cc: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 46 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ed8e9deae284..b0e47fe1eb4b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -72,6 +72,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -3110,6 +3111,49 @@ static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); } +static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + void *ptr; + + /* + * Do not allow to map to user-provided address to avoid breaking the + * aliasing rules. Userspace is not able to guess the offset address of + * kernel kmalloc()ed memory area. + */ + if (addr) + return -EINVAL; + + ptr = io_uring_validate_mmap_request(filp, pgoff, len); + if (IS_ERR(ptr)) + return -ENOMEM; + + /* + * Some architectures have strong cache aliasing requirements. + * For such architectures we need a coherent mapping which aliases + * kernel memory *and* userspace memory. To achieve that: + * - use a NULL file pointer to reference physical memory, and + * - use the kernel virtual address of the shared io_uring context + * (instead of the userspace-provided address, which has to be 0UL + * anyway). + * - use the same pgoff which the get_unmapped_area() uses to + * calculate the page colouring. + * For architectures without such aliasing requirements, the + * architecture will return any suitable mapping because addr is 0. + */ + filp = NULL; + flags |= MAP_SHARED; + pgoff = 0; /* has been translated to ptr above */ +#ifdef SHM_COLOUR + addr = (uintptr_t) ptr; + pgoff = addr >> PAGE_SHIFT; +#else + addr = 0UL; +#endif + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +} + #else /* !CONFIG_MMU */ static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) @@ -3324,6 +3368,8 @@ static const struct file_operations io_uring_fops = { #ifndef CONFIG_MMU .get_unmapped_area = io_uring_nommu_get_unmapped_area, .mmap_capabilities = io_uring_nommu_mmap_capabilities, +#else + .get_unmapped_area = io_uring_mmu_get_unmapped_area, #endif .poll = io_uring_poll, #ifdef CONFIG_PROC_FS From 583a8426abb335030ebaa26081b4636828e66f4b Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 24 Aug 2023 20:46:59 -0700 Subject: [PATCH 0652/2093] kallsyms: Fix kallsyms_selftest failure commit 33f0467fe06934d5e4ea6e24ce2b9c65ce618e26 upstream. Kernel test robot reported a kallsyms_test failure when clang lto is enabled (thin or full) and CONFIG_KALLSYMS_SELFTEST is also enabled. I can reproduce in my local environment with the following error message with thin lto: [ 1.877897] kallsyms_selftest: Test for 1750th symbol failed: (tsc_cs_mark_unstable) addr=ffffffff81038090 [ 1.877901] kallsyms_selftest: abort It appears that commit 8cc32a9bbf29 ("kallsyms: strip LTO-only suffixes from promoted global functions") caused the failure. Commit 8cc32a9bbf29 changed cleanup_symbol_name() based on ".llvm." instead of '.' where ".llvm." is appended to a before-lto-optimization local symbol name. We need to propagate such knowledge in kallsyms_selftest.c as well. Further more, compare_symbol_name() in kallsyms.c needs change as well. In scripts/kallsyms.c, kallsyms_names and kallsyms_seqs_of_names are used to record symbol names themselves and index to symbol names respectively. For example: kallsyms_names: ... __amd_smn_rw._entry <== seq 1000 __amd_smn_rw._entry.5 <== seq 1001 __amd_smn_rw.llvm. <== seq 1002 ... kallsyms_seqs_of_names are sorted based on cleanup_symbol_name() through, so the order in kallsyms_seqs_of_names actually has index 1000: seq 1002 <== __amd_smn_rw.llvm. (actual symbol comparison using '__amd_smn_rw') index 1001: seq 1000 <== __amd_smn_rw._entry index 1002: seq 1001 <== __amd_smn_rw._entry.5 Let us say at a particular point, at index 1000, symbol '__amd_smn_rw.llvm.' is comparing to '__amd_smn_rw._entry' where '__amd_smn_rw._entry' is the one to search e.g., with function kallsyms_on_each_match_symbol(). The current implementation will find out '__amd_smn_rw._entry' is less than '__amd_smn_rw.llvm.' and then continue to search e.g., index 999 and never found a match although the actual index 1001 is a match. To fix this issue, let us do cleanup_symbol_name() first and then do comparison. In the above case, comparing '__amd_smn_rw' vs '__amd_smn_rw._entry' and '__amd_smn_rw._entry' being greater than '__amd_smn_rw', the next comparison will be > index 1000 and eventually index 1001 will be hit an a match is found. For any symbols not having '.llvm.' substr, there is no functionality change for compare_symbol_name(). Fixes: 8cc32a9bbf29 ("kallsyms: strip LTO-only suffixes from promoted global functions") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202308232200.1c932a90-oliver.sang@intel.com Signed-off-by: Yonghong Song Reviewed-by: Song Liu Reviewed-by: Zhen Lei Link: https://lore.kernel.org/r/20230825034659.1037627-1-yonghong.song@linux.dev Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Greg Kroah-Hartman --- kernel/kallsyms.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 676328a7c8c7..ad3cccb0970f 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -188,16 +188,13 @@ static bool cleanup_symbol_name(char *s) static int compare_symbol_name(const char *name, char *namebuf) { - int ret; - - ret = strcmp(name, namebuf); - if (!ret) - return ret; - - if (cleanup_symbol_name(namebuf) && !strcmp(name, namebuf)) - return 0; - - return ret; + /* The kallsyms_seqs_of_names is sorted based on names after + * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled. + * To ensure correct bisection in kallsyms_lookup_names(), do + * cleanup_symbol_name(namebuf) before comparing name and namebuf. + */ + cleanup_symbol_name(namebuf); + return strcmp(name, namebuf); } static int kallsyms_lookup_names(const char *name, From ae0188f9c2a88a2f9e96e5a0ced48adc84982287 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 31 Aug 2023 06:34:21 -0500 Subject: [PATCH 0653/2093] thunderbolt: Fix a backport error for display flickering issue A mistake was made when backporting commit 583893a66d73 ("thunderbolt: Fix Thunderbolt 3 display flickering issue on 2nd hot plug onwards") in missing the `if` block. Add it back in. Reported-by: Joakim.Tjernlund@infinera.com Closes: https://lore.kernel.org/stable/28b5d0accce90bedf2f75d65290c5a1302225f0f.camel@infinera.com/ Fixes: 06614ca4f18e ("thunderbolt: Fix Thunderbolt 3 display flickering issue on 2nd hot plug onwards") Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/tmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c index d9544600b386..49146f97bb16 100644 --- a/drivers/thunderbolt/tmu.c +++ b/drivers/thunderbolt/tmu.c @@ -416,6 +416,7 @@ int tb_switch_tmu_disable(struct tb_switch *sw) * mode. */ ret = tb_switch_tmu_rate_write(sw, TB_SWITCH_TMU_RATE_OFF); + if (ret) return ret; tb_port_tmu_time_sync_disable(up); From c2cbfe5f51227dfe6ef7be013f0d56a32c040faa Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 2 Sep 2023 09:16:20 +0200 Subject: [PATCH 0654/2093] Linux 6.1.51 Link: https://lore.kernel.org/r/20230831110831.079963475@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: SeongJae Park Tested-by: Ron Economos Tested-by: Linux Kernel Functional Testing Tested-by: Bagas Sanjaya Tested-by: Sudip Mukherjee Tested-by: Shuah Khan Tested-by: Takeshi Ogasawara Tested-by: Jon Hunter Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e5e1fdeef8bf..e7c344d5af15 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 50 +SUBLEVEL = 51 EXTRAVERSION = NAME = Curry Ramen From 1ce9ebc96eda5556e5a15bbe6a17b293841af29e Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Thu, 31 Aug 2023 19:29:58 +0800 Subject: [PATCH 0655/2093] erofs: ensure that the post-EOF tails are all zeroed commit e4c1cf523d820730a86cae2c6d55924833b6f7ac upstream. This was accidentally fixed up in commit e4c1cf523d82 but we can't take the full change due to other dependancy issues, so here is just the actual bugfix that is needed. [Background] keltargw reported an issue [1] that with mmaped I/Os, sometimes the tail of the last page (after file ends) is not filled with zeroes. The root cause is that such tail page could be wrongly selected for inplace I/Os so the zeroed part will then be filled with compressed data instead of zeroes. A simple fix is to avoid doing inplace I/Os for such tail parts, actually that was already fixed upstream in commit e4c1cf523d82 ("erofs: tidy up z_erofs_do_read_page()") by accident. [1] https://lore.kernel.org/r/3ad8b469-25db-a297-21f9-75db2d6ad224@linux.alibaba.com Reported-by: keltargw Fixes: 3883a79abd02 ("staging: erofs: introduce VLE decompression support") Signed-off-by: Gao Xiang Signed-off-by: Greg Kroah-Hartman --- fs/erofs/zdata.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 361f3c29897e..1b91ac5be961 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -869,6 +869,8 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, cur = end - min_t(erofs_off_t, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); + ++spiltted; + tight = false; goto next_part; } if (map->m_flags & EROFS_MAP_FRAGMENT) { From 7d8855fd849d9c3186a9e1d3085ea4aedc6e019f Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 25 Aug 2023 23:39:40 +0900 Subject: [PATCH 0656/2093] ksmbd: fix wrong DataOffset validation of create context commit 17d5b135bb720832364e8f55f6a887a3c7ec8fdb upstream. If ->DataOffset of create context is 0, DataBuffer size is not correctly validated. This patch change wrong validation code and consider tag length in request. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21824 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/oplock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 4b210cdd7556..c81aee9ce7ec 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1492,7 +1492,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag, i name_len < 4 || name_off + name_len > cc_len || (value_off & 0x7) != 0 || - (value_off && (value_off < name_off + name_len)) || + (value_len && value_off < name_off + (name_len < 8 ? 8 : name_len)) || ((u64)value_off + value_len > cc_len)) return ERR_PTR(-EINVAL); From 30fd6521b2fbd9b767e438e31945e5ea3e3a2fba Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 25 Aug 2023 23:40:31 +0900 Subject: [PATCH 0657/2093] ksmbd: fix slub overflow in ksmbd_decode_ntlmssp_auth_blob() commit 4b081ce0d830b684fdf967abc3696d1261387254 upstream. If authblob->SessionKey.Length is bigger than session key size(CIFS_KEY_SIZE), slub overflow can happen in key exchange codes. cifs_arc4_crypt copy to session key array from SessionKey from client. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21940 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/auth.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 5e5e120edcc2..15e5684e328c 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -355,6 +355,9 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, if (blob_len < (u64)sess_key_off + sess_key_len) return -EINVAL; + if (sess_key_len > CIFS_KEY_SIZE) + return -EINVAL; + ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL); if (!ctx_arc4) return -ENOMEM; From d070c4dd2a5bed4e9832eec5b6c029c7d14892ea Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 25 Aug 2023 23:41:58 +0900 Subject: [PATCH 0658/2093] ksmbd: replace one-element array with flex-array member in struct smb2_ea_info commit 0ba5439d9afa2722e7728df56f272c89987540a4 upstream. UBSAN complains about out-of-bounds array indexes on 1-element arrays in struct smb2_ea_info. UBSAN: array-index-out-of-bounds in fs/smb/server/smb2pdu.c:4335:15 index 1 is out of range for type 'char [1]' CPU: 1 PID: 354 Comm: kworker/1:4 Not tainted 6.5.0-rc4 #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/22/2020 Workqueue: ksmbd-io handle_ksmbd_work [ksmbd] Call Trace: __dump_stack linux/lib/dump_stack.c:88 dump_stack_lvl+0x48/0x70 linux/lib/dump_stack.c:106 dump_stack+0x10/0x20 linux/lib/dump_stack.c:113 ubsan_epilogue linux/lib/ubsan.c:217 __ubsan_handle_out_of_bounds+0xc6/0x110 linux/lib/ubsan.c:348 smb2_get_ea linux/fs/smb/server/smb2pdu.c:4335 smb2_get_info_file linux/fs/smb/server/smb2pdu.c:4900 smb2_query_info+0x63ae/0x6b20 linux/fs/smb/server/smb2pdu.c:5275 __process_request linux/fs/smb/server/server.c:145 __handle_ksmbd_work linux/fs/smb/server/server.c:213 handle_ksmbd_work+0x348/0x10b0 linux/fs/smb/server/server.c:266 process_one_work+0x85a/0x1500 linux/kernel/workqueue.c:2597 worker_thread+0xf3/0x13a0 linux/kernel/workqueue.c:2748 kthread+0x2b7/0x390 linux/kernel/kthread.c:389 ret_from_fork+0x44/0x90 linux/arch/x86/kernel/process.c:145 ret_from_fork_asm+0x1b/0x30 linux/arch/x86/entry/entry_64.S:304 Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/smb2pdu.c | 2 +- fs/smb/server/smb2pdu.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f8ca44622d90..9b621fd993bb 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -4322,7 +4322,7 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) name_len -= XATTR_USER_PREFIX_LEN; - ptr = (char *)(&eainfo->name + name_len + 1); + ptr = eainfo->name + name_len + 1; buf_free_len -= (offsetof(struct smb2_ea_info, name) + name_len + 1); /* bailout if xattr can't fit in buf_free_len */ diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index dd10f8031606..665a83737854 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -410,7 +410,7 @@ struct smb2_ea_info { __u8 Flags; __u8 EaNameLength; __le16 EaValueLength; - char name[1]; + char name[]; /* optionally followed by value */ } __packed; /* level 15 Query */ From cf859267e639cff1f525bd050f370ea752cc25f7 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 29 Aug 2023 23:40:37 +0900 Subject: [PATCH 0659/2093] ksmbd: reduce descriptor size if remaining bytes is less than request size commit e628bf939aafb61fbc56e9bdac8795cea5127e25 upstream. Create 3 kinds of files to reproduce this problem. dd if=/dev/urandom of=127k.bin bs=1024 count=127 dd if=/dev/urandom of=128k.bin bs=1024 count=128 dd if=/dev/urandom of=129k.bin bs=1024 count=129 When copying files from ksmbd share to windows or cifs.ko, The following error message happen from windows client. "The file '129k.bin' is too large for the destination filesystem." We can see the error logs from ksmbd debug prints [48394.611537] ksmbd: RDMA r/w request 0x0: token 0x669d, length 0x20000 [48394.612054] ksmbd: smb_direct: RDMA write, len 0x20000, needed credits 0x1 [48394.612572] ksmbd: filename 129k.bin, offset 131072, len 131072 [48394.614189] ksmbd: nbytes 1024, offset 132096 mincount 0 [48394.614585] ksmbd: Failed to process 8 [-22] And we can reproduce it with cifs.ko, e.g. dd if=129k.bin of=/dev/null bs=128KB count=2 This problem is that ksmbd rdma return error if remaining bytes is less than Length of Buffer Descriptor V1 Structure. smb_direct_rdma_xmit() ... if (desc_buf_len == 0 || total_length > buf_len || total_length > t->max_rdma_rw_size) return -EINVAL; This patch reduce descriptor size with remaining bytes and remove the check for total_length and buf_len. Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/transport_rdma.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index c06efc020bd9..7578200f63b1 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -1366,24 +1366,35 @@ static int smb_direct_rdma_xmit(struct smb_direct_transport *t, LIST_HEAD(msg_list); char *desc_buf; int credits_needed; - unsigned int desc_buf_len; - size_t total_length = 0; + unsigned int desc_buf_len, desc_num = 0; if (t->status != SMB_DIRECT_CS_CONNECTED) return -ENOTCONN; + if (buf_len > t->max_rdma_rw_size) + return -EINVAL; + /* calculate needed credits */ credits_needed = 0; desc_buf = buf; for (i = 0; i < desc_len / sizeof(*desc); i++) { + if (!buf_len) + break; + desc_buf_len = le32_to_cpu(desc[i].length); + if (!desc_buf_len) + return -EINVAL; + + if (desc_buf_len > buf_len) { + desc_buf_len = buf_len; + desc[i].length = cpu_to_le32(desc_buf_len); + buf_len = 0; + } credits_needed += calc_rw_credits(t, desc_buf, desc_buf_len); desc_buf += desc_buf_len; - total_length += desc_buf_len; - if (desc_buf_len == 0 || total_length > buf_len || - total_length > t->max_rdma_rw_size) - return -EINVAL; + buf_len -= desc_buf_len; + desc_num++; } ksmbd_debug(RDMA, "RDMA %s, len %#x, needed credits %#x\n", @@ -1395,7 +1406,7 @@ static int smb_direct_rdma_xmit(struct smb_direct_transport *t, /* build rdma_rw_ctx for each descriptor */ desc_buf = buf; - for (i = 0; i < desc_len / sizeof(*desc); i++) { + for (i = 0; i < desc_num; i++) { msg = kzalloc(offsetof(struct smb_direct_rdma_rw_msg, sg_list) + sizeof(struct scatterlist) * SG_CHUNK_SIZE, GFP_KERNEL); if (!msg) { From ac6fa0e04be02d7065b176dd8a319a29d4bfb32f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Aug 2023 19:35:40 +0200 Subject: [PATCH 0660/2093] ARM: pxa: remove use of symbol_get() commit 0faa29c4207e6e29cfc81b427df60e326c37083a upstream. The spitz board file uses the obscure symbol_get() function to optionally call a function from sharpsl_pm.c if that is built. However, the two files are always built together these days, and have been for a long time, so this can be changed to a normal function call. Link: https://lore.kernel.org/lkml/20230731162639.GA9441@lst.de/ Signed-off-by: Arnd Bergmann Signed-off-by: Christoph Hellwig Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-pxa/sharpsl_pm.c | 2 -- arch/arm/mach-pxa/spitz.c | 14 +------------- 2 files changed, 1 insertion(+), 15 deletions(-) diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c index a829baf8d922..05c0a0f6fe63 100644 --- a/arch/arm/mach-pxa/sharpsl_pm.c +++ b/arch/arm/mach-pxa/sharpsl_pm.c @@ -220,8 +220,6 @@ void sharpsl_battery_kick(void) { schedule_delayed_work(&sharpsl_bat, msecs_to_jiffies(125)); } -EXPORT_SYMBOL(sharpsl_battery_kick); - static void sharpsl_battery_thread(struct work_struct *private_) { diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 9964729cd428..937f56bbaf6c 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -9,7 +9,6 @@ */ #include -#include /* symbol_get ; symbol_put */ #include #include #include @@ -510,17 +509,6 @@ static struct ads7846_platform_data spitz_ads7846_info = { .wait_for_sync = spitz_ads7846_wait_for_hsync, }; -static void spitz_bl_kick_battery(void) -{ - void (*kick_batt)(void); - - kick_batt = symbol_get(sharpsl_battery_kick); - if (kick_batt) { - kick_batt(); - symbol_put(sharpsl_battery_kick); - } -} - static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { @@ -548,7 +536,7 @@ static struct corgi_lcd_platform_data spitz_lcdcon_info = { .max_intensity = 0x2f, .default_intensity = 0x1f, .limit_mask = 0x0b, - .kick_battery = spitz_bl_kick_battery, + .kick_battery = sharpsl_battery_kick, }; static struct spi_board_info spitz_spi_devices[] = { From 4dab89cccd8c71c16e5ab3fb216290f736417689 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Aug 2023 19:35:41 +0200 Subject: [PATCH 0661/2093] mmc: au1xmmc: force non-modular build and remove symbol_get usage commit d4a5c59a955bba96b273ec1a5885bada24c56979 upstream. au1xmmc is split somewhat awkwardly into the main mmc subsystem driver, and callbacks in platform_data that sit under arch/mips/ and are always built in. The latter than call mmc_detect_change through symbol_get. Remove the use of symbol_get by requiring the driver to be built in. In the future the interrupt handlers for card insert/eject detection should probably be moved into the main driver, and which point it can be built modular again. Signed-off-by: Christoph Hellwig Acked-by: Manuel Lauss Reviewed-by: Arnd Bergmann [mcgrof: squashed in depends on MMC=y suggested by Arnd] Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- arch/mips/alchemy/devboards/db1000.c | 8 +------- arch/mips/alchemy/devboards/db1200.c | 19 ++----------------- arch/mips/alchemy/devboards/db1300.c | 10 +--------- drivers/mmc/host/Kconfig | 5 +++-- 4 files changed, 7 insertions(+), 35 deletions(-) diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index 2c52ee27b4f2..50de86eb8784 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -167,12 +166,7 @@ static struct platform_device db1x00_audio_dev = { static irqreturn_t db1100_mmc_cd(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - /* link against CONFIG_MMC=m */ - mmc_cd = symbol_get(mmc_detect_change); - mmc_cd(ptr, msecs_to_jiffies(500)); - symbol_put(mmc_detect_change); - + mmc_detect_change(ptr, msecs_to_jiffies(500)); return IRQ_HANDLED; } diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c index 1864eb935ca5..76080c71a2a7 100644 --- a/arch/mips/alchemy/devboards/db1200.c +++ b/arch/mips/alchemy/devboards/db1200.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -340,14 +339,7 @@ static irqreturn_t db1200_mmc_cd(int irq, void *ptr) static irqreturn_t db1200_mmc_cdfn(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - - /* link against CONFIG_MMC=m */ - mmc_cd = symbol_get(mmc_detect_change); - if (mmc_cd) { - mmc_cd(ptr, msecs_to_jiffies(200)); - symbol_put(mmc_detect_change); - } + mmc_detect_change(ptr, msecs_to_jiffies(200)); msleep(100); /* debounce */ if (irq == DB1200_SD0_INSERT_INT) @@ -431,14 +423,7 @@ static irqreturn_t pb1200_mmc1_cd(int irq, void *ptr) static irqreturn_t pb1200_mmc1_cdfn(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - - /* link against CONFIG_MMC=m */ - mmc_cd = symbol_get(mmc_detect_change); - if (mmc_cd) { - mmc_cd(ptr, msecs_to_jiffies(200)); - symbol_put(mmc_detect_change); - } + mmc_detect_change(ptr, msecs_to_jiffies(200)); msleep(100); /* debounce */ if (irq == PB1200_SD1_INSERT_INT) diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c index e70e529ddd91..ff61901329c6 100644 --- a/arch/mips/alchemy/devboards/db1300.c +++ b/arch/mips/alchemy/devboards/db1300.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -459,14 +458,7 @@ static irqreturn_t db1300_mmc_cd(int irq, void *ptr) static irqreturn_t db1300_mmc_cdfn(int irq, void *ptr) { - void (*mmc_cd)(struct mmc_host *, unsigned long); - - /* link against CONFIG_MMC=m. We can only be called once MMC core has - * initialized the controller, so symbol_get() should always succeed. - */ - mmc_cd = symbol_get(mmc_detect_change); - mmc_cd(ptr, msecs_to_jiffies(200)); - symbol_put(mmc_detect_change); + mmc_detect_change(ptr, msecs_to_jiffies(200)); msleep(100); /* debounce */ if (irq == DB1300_SD1_INSERT_INT) diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index fb1062a6394c..9b5a2cb110b3 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -528,11 +528,12 @@ config MMC_ALCOR of Alcor Micro PCI-E card reader config MMC_AU1X - tristate "Alchemy AU1XX0 MMC Card Interface support" + bool "Alchemy AU1XX0 MMC Card Interface support" depends on MIPS_ALCHEMY + depends on MMC=y help This selects the AMD Alchemy(R) Multimedia card interface. - If you have a Alchemy platform with a MMC slot, say Y or M here. + If you have a Alchemy platform with a MMC slot, say Y here. If unsure, say N. From 915219699da15281baf8175a5338d29952632fc2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Aug 2023 19:35:42 +0200 Subject: [PATCH 0662/2093] net: enetc: use EXPORT_SYMBOL_GPL for enetc_phc_index commit 569820befb16ffc755ab7af71f4f08cc5f68f0fe upstream. enetc_phc_index is only used via symbol_get, which was only ever intended for very internal symbols like this one. Use EXPORT_SYMBOL_GPL for it so that symbol_get can enforce only being used on EXPORT_SYMBOL_GPL symbols. Signed-off-by: Christoph Hellwig Reviewed-by: Jakub Kicinski Reviewed-by: Greg Kroah-Hartman Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/freescale/enetc/enetc_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c index 17c097cef7d4..5243fc031058 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -8,7 +8,7 @@ #include "enetc.h" int enetc_phc_index = -1; -EXPORT_SYMBOL(enetc_phc_index); +EXPORT_SYMBOL_GPL(enetc_phc_index); static struct ptp_clock_info enetc_ptp_caps = { .owner = THIS_MODULE, From 36231e2c4ebd9ad2597a4c527b286e270f0eabfd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Aug 2023 19:35:43 +0200 Subject: [PATCH 0663/2093] rtc: ds1685: use EXPORT_SYMBOL_GPL for ds1685_rtc_poweroff commit 95e7ebc6823170256a8ce19fad87912805bfa001 upstream. ds1685_rtc_poweroff is only used externally via symbol_get, which was only ever intended for very internal symbols like this one. Use EXPORT_SYMBOL_GPL for it so that symbol_get can enforce only being used on EXPORT_SYMBOL_GPL symbols. Signed-off-by: Christoph Hellwig Acked-by: Joshua Kinard Reviewed-by: Greg Kroah-Hartman Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- drivers/rtc/rtc-ds1685.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 5db9c737c022..db7216f14164 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1434,7 +1434,7 @@ ds1685_rtc_poweroff(struct platform_device *pdev) unreachable(); } } -EXPORT_SYMBOL(ds1685_rtc_poweroff); +EXPORT_SYMBOL_GPL(ds1685_rtc_poweroff); /* ----------------------------------------------------------------------- */ From 5d0fe30be4e28abe373bf951416f29afb0651e01 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Aug 2023 19:35:44 +0200 Subject: [PATCH 0664/2093] modules: only allow symbol_get of EXPORT_SYMBOL_GPL modules commit 9011e49d54dcc7653ebb8a1e05b5badb5ecfa9f9 upstream. It has recently come to my attention that nvidia is circumventing the protection added in 262e6ae7081d ("modules: inherit TAINT_PROPRIETARY_MODULE") by importing exports from their proprietary modules into an allegedly GPL licensed module and then rexporting them. Given that symbol_get was only ever intended for tightly cooperating modules using very internal symbols it is logical to restrict it to being used on EXPORT_SYMBOL_GPL and prevent nvidia from costly DMCA Circumvention of Access Controls law suites. All symbols except for four used through symbol_get were already exported as EXPORT_SYMBOL_GPL, and the remaining four ones were switched over in the preparation patches. Fixes: 262e6ae7081d ("modules: inherit TAINT_PROPRIETARY_MODULE") Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- kernel/module/main.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 7a6f43d2b775..7a376e26de85 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1214,12 +1214,20 @@ void *__symbol_get(const char *symbol) }; preempt_disable(); - if (!find_symbol(&fsa) || strong_try_module_get(fsa.owner)) { - preempt_enable(); - return NULL; + if (!find_symbol(&fsa)) + goto fail; + if (fsa.license != GPL_ONLY) { + pr_warn("failing symbol_get of non-GPLONLY symbol %s.\n", + symbol); + goto fail; } + if (strong_try_module_get(fsa.owner)) + goto fail; preempt_enable(); return (void *)kernel_symbol_value(fsa.sym); +fail: + preempt_enable(); + return NULL; } EXPORT_SYMBOL_GPL(__symbol_get); From 34f396f7abd09bbfa726d2255522099962c7db6a Mon Sep 17 00:00:00 2001 From: Martin Kohn Date: Thu, 27 Jul 2023 22:23:00 +0000 Subject: [PATCH 0665/2093] USB: serial: option: add Quectel EM05G variant (0x030e) commit 873854c02364ebb991fc06f7148c14dfb5419e1b upstream. Add Quectel EM05G with product ID 0x030e. Interface 4 is used for qmi. T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=030e Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Martin Kohn Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 119641761c3b..e1b1929ca350 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -259,6 +259,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b #define QUECTEL_PRODUCT_EM05G_CS 0x030c +#define QUECTEL_PRODUCT_EM05GV2 0x030e #define QUECTEL_PRODUCT_EM05CN_SG 0x0310 #define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM05CN 0x0312 @@ -1190,6 +1191,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05GV2, 0xff), + .driver_info = RSVD(4) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_RS, 0xff), From 69d9330f2effdf93aeac8c930ff1073d664b043e Mon Sep 17 00:00:00 2001 From: Slark Xiao Date: Wed, 23 Aug 2023 15:57:51 +0800 Subject: [PATCH 0666/2093] USB: serial: option: add FOXCONN T99W368/T99W373 product commit 4d9488b294e1f8353bbcadc4c7172a7f7490199b upstream. The difference of T99W368 and T99W373 is the chip solution. T99W368 is designed based on Qualcomm SDX65 and T99W373 is SDX62. Test evidence as below: T: Bus=01 Lev=02 Prnt=05 Port=00 Cnt=01 Dev#= 7 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0489 ProdID=e0f0 Rev=05.04 S: Manufacturer=FII S: Product=OLYMPIC USB WWAN Adapter S: SerialNumber=78ada8c4 C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option T: Bus=01 Lev=02 Prnt=05 Port=00 Cnt=01 Dev#= 8 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0489 ProdID=e0ee Rev=05.04 S: Manufacturer=FII S: Product=OLYMPIC USB WWAN Adapter S: SerialNumber=78ada8d5 C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option Both of them share the same port configuration: 0&1: MBIM, 2: Modem, 3:GNSS, 4:NMEA, 5:Diag GNSS port don't use serial driver. Signed-off-by: Slark Xiao Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e1b1929ca350..f13930b4534c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2235,6 +2235,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff), /* Foxconn T99W265 MBIM */ .driver_info = RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff), /* Foxconn T99W368 MBIM */ + .driver_info = RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0f0, 0xff), /* Foxconn T99W373 MBIM */ + .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ From bfc4ccc0bcae44f2e31e9aa29f94563adb1b0d13 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 21 Aug 2023 13:18:57 +0200 Subject: [PATCH 0667/2093] ALSA: usb-audio: Fix init call orders for UAC1 commit 5fadc941d07530d681f3b7ec91e56d8445bc3825 upstream. There have been reports of USB-audio driver spewing errors at the probe time on a few devices like Jabra and Logitech. The suggested fix there couldn't be applied as is, unfortunately, because it'll likely break other devices. But, the patch suggested an interesting point: looking at the current init code in stream.c, one may notice that it does initialize differently from the device setup in endpoint.c. Namely, for UAC1, we should call snd_usb_init_pitch() and snd_usb_init_sample_rate() after setting the interface, while the init sequence at parsing calls them before setting the interface blindly. This patch changes the init sequence at parsing for UAC1 (and other devices that need a similar behavior) to be aligned with the rest of the code, setting the interface at first. And, this fixes the long-standing problems on a few UAC1 devices like Jabra / Logitech, as reported, too. Reported-and-tested-by: Joakim Tjernlund Closes: https://lore.kernel.org/r/202bbbc0f51522e8545783c4c5577d12a8e2d56d.camel@infinera.com Cc: Link: https://lore.kernel.org/r/20230821111857.28926-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/stream.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/sound/usb/stream.c b/sound/usb/stream.c index f10f4e6d3fb8..3d4add94e367 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -1093,6 +1093,7 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int i, altno, err, stream; struct audioformat *fp = NULL; struct snd_usb_power_domain *pd = NULL; + bool set_iface_first; int num, protocol; dev = chip->dev; @@ -1223,11 +1224,19 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, return err; } + set_iface_first = false; + if (protocol == UAC_VERSION_1 || + (chip->quirk_flags & QUIRK_FLAG_SET_IFACE_FIRST)) + set_iface_first = true; + /* try to set the interface... */ usb_set_interface(chip->dev, iface_no, 0); + if (set_iface_first) + usb_set_interface(chip->dev, iface_no, altno); snd_usb_init_pitch(chip, fp); snd_usb_init_sample_rate(chip, fp, fp->rate_max); - usb_set_interface(chip->dev, iface_no, altno); + if (!set_iface_first) + usb_set_interface(chip->dev, iface_no, altno); } return 0; } From c564d4f91a0c9ec957b82d2293972c13d09d7044 Mon Sep 17 00:00:00 2001 From: Luke Lu Date: Wed, 9 Aug 2023 21:29:11 +0000 Subject: [PATCH 0668/2093] usb: dwc3: meson-g12a: do post init to fix broken usb after resumption commit 1fa206bb764f37d2ab4bf671e483153ef0659b34 upstream. Device connected to usb otg port of GXL-based boards can not be recognised after resumption, doesn't recover even if disconnect and reconnect the device. dmesg shows it disconnects during resumption. [ 41.492911] usb 1-2: USB disconnect, device number 3 [ 41.499346] usb 1-2: unregistering device [ 41.511939] usb 1-2: unregistering interface 1-2:1.0 Calling usb_post_init() will fix this issue, and it's tested and verified on libretech's aml-s905x-cc board. Cc: stable@vger.kernel.org # v5.8+ Fixes: c99993376f72 ("usb: dwc3: Add Amlogic G12A DWC3 glue") Signed-off-by: Luke Lu Acked-by: Neil Armstrong Link: https://lore.kernel.org/r/20230809212911.18903-1-luke.lu@libre.computer Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-meson-g12a.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c index eaea944ebd2c..10298b91731e 100644 --- a/drivers/usb/dwc3/dwc3-meson-g12a.c +++ b/drivers/usb/dwc3/dwc3-meson-g12a.c @@ -938,6 +938,12 @@ static int __maybe_unused dwc3_meson_g12a_resume(struct device *dev) return ret; } + if (priv->drvdata->usb_post_init) { + ret = priv->drvdata->usb_post_init(priv); + if (ret) + return ret; + } + return 0; } From 48729a1d2a7a9444355d412b9a6a4ba6e0741a72 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Tue, 27 Jun 2023 19:21:24 +0800 Subject: [PATCH 0669/2093] usb: chipidea: imx: improve logic if samsung,picophy-* parameter is 0 commit 36668515d56bf73f06765c71e08c8f7465f1e5c4 upstream. In current driver, the value of tuning parameter will not take effect if samsung,picophy-* is assigned as 0. Because 0 is also a valid value acccording to the description of USB_PHY_CFG1 register, this will improve the logic to let it work. Fixes: 58a3cefb3840 ("usb: chipidea: imx: add two samsung picophy parameters tuning implementation") cc: Signed-off-by: Xu Yang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20230627112126.1882666-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci_hdrc_imx.c | 10 ++++++---- drivers/usb/chipidea/usbmisc_imx.c | 6 ++++-- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 60b4de0a4f76..caa91117ba42 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -175,10 +175,12 @@ static struct imx_usbmisc_data *usbmisc_get_init_data(struct device *dev) if (of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) data->ulpi = 1; - of_property_read_u32(np, "samsung,picophy-pre-emp-curr-control", - &data->emp_curr_control); - of_property_read_u32(np, "samsung,picophy-dc-vol-level-adjust", - &data->dc_vol_level_adjust); + if (of_property_read_u32(np, "samsung,picophy-pre-emp-curr-control", + &data->emp_curr_control)) + data->emp_curr_control = -1; + if (of_property_read_u32(np, "samsung,picophy-dc-vol-level-adjust", + &data->dc_vol_level_adjust)) + data->dc_vol_level_adjust = -1; return data; } diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c index 2318c7906acd..a2cb4f48c84c 100644 --- a/drivers/usb/chipidea/usbmisc_imx.c +++ b/drivers/usb/chipidea/usbmisc_imx.c @@ -657,13 +657,15 @@ static int usbmisc_imx7d_init(struct imx_usbmisc_data *data) usbmisc->base + MX7D_USBNC_USB_CTRL2); /* PHY tuning for signal quality */ reg = readl(usbmisc->base + MX7D_USB_OTG_PHY_CFG1); - if (data->emp_curr_control && data->emp_curr_control <= + if (data->emp_curr_control >= 0 && + data->emp_curr_control <= (TXPREEMPAMPTUNE0_MASK >> TXPREEMPAMPTUNE0_BIT)) { reg &= ~TXPREEMPAMPTUNE0_MASK; reg |= (data->emp_curr_control << TXPREEMPAMPTUNE0_BIT); } - if (data->dc_vol_level_adjust && data->dc_vol_level_adjust <= + if (data->dc_vol_level_adjust >= 0 && + data->dc_vol_level_adjust <= (TXVREFTUNE0_MASK >> TXVREFTUNE0_BIT)) { reg &= ~TXVREFTUNE0_MASK; reg |= (data->dc_vol_level_adjust << TXVREFTUNE0_BIT); From bd69537c1a2cd4b24d32f9f621f0ea8378048e5e Mon Sep 17 00:00:00 2001 From: Aaron Armstrong Skomra Date: Tue, 25 Jul 2023 15:20:25 -0700 Subject: [PATCH 0670/2093] HID: wacom: remove the battery when the EKR is off commit 9ac6678b95b0dd9458a7a6869f46e51cd55a1d84 upstream. Currently the EKR battery remains even after we stop getting information from the device. This can lead to a stale battery persisting indefinitely in userspace. The remote sends a heartbeat every 10 seconds. Delete the battery if we miss two heartbeats (after 21 seconds). Restore the battery once we see a heartbeat again. Signed-off-by: Aaron Skomra Signed-off-by: Aaron Armstrong Skomra Reviewed-by: Jason Gerecke Fixes: 9f1015d45f62 ("HID: wacom: EKR: attach the power_supply on first connection") CC: stable@vger.kernel.org Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom.h | 1 + drivers/hid/wacom_sys.c | 25 +++++++++++++++++++++---- drivers/hid/wacom_wac.c | 1 + drivers/hid/wacom_wac.h | 1 + 4 files changed, 24 insertions(+), 4 deletions(-) diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 4da50e19808e..166a76c9bcad 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -150,6 +150,7 @@ struct wacom_remote { struct input_dev *input; bool registered; struct wacom_battery battery; + ktime_t active_time; } remotes[WACOM_MAX_REMOTES]; }; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index aff4a21a46b6..af163e8dfec0 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2527,6 +2527,18 @@ static void wacom_wireless_work(struct work_struct *work) return; } +static void wacom_remote_destroy_battery(struct wacom *wacom, int index) +{ + struct wacom_remote *remote = wacom->remote; + + if (remote->remotes[index].battery.battery) { + devres_release_group(&wacom->hdev->dev, + &remote->remotes[index].battery.bat_desc); + remote->remotes[index].battery.battery = NULL; + remote->remotes[index].active_time = 0; + } +} + static void wacom_remote_destroy_one(struct wacom *wacom, unsigned int index) { struct wacom_remote *remote = wacom->remote; @@ -2541,9 +2553,7 @@ static void wacom_remote_destroy_one(struct wacom *wacom, unsigned int index) remote->remotes[i].registered = false; spin_unlock_irqrestore(&remote->remote_lock, flags); - if (remote->remotes[i].battery.battery) - devres_release_group(&wacom->hdev->dev, - &remote->remotes[i].battery.bat_desc); + wacom_remote_destroy_battery(wacom, i); if (remote->remotes[i].group.name) devres_release_group(&wacom->hdev->dev, @@ -2551,7 +2561,6 @@ static void wacom_remote_destroy_one(struct wacom *wacom, unsigned int index) remote->remotes[i].serial = 0; remote->remotes[i].group.name = NULL; - remote->remotes[i].battery.battery = NULL; wacom->led.groups[i].select = WACOM_STATUS_UNKNOWN; } } @@ -2636,6 +2645,9 @@ static int wacom_remote_attach_battery(struct wacom *wacom, int index) if (remote->remotes[index].battery.battery) return 0; + if (!remote->remotes[index].active_time) + return 0; + if (wacom->led.groups[index].select == WACOM_STATUS_UNKNOWN) return 0; @@ -2651,6 +2663,7 @@ static void wacom_remote_work(struct work_struct *work) { struct wacom *wacom = container_of(work, struct wacom, remote_work); struct wacom_remote *remote = wacom->remote; + ktime_t kt = ktime_get(); struct wacom_remote_data data; unsigned long flags; unsigned int count; @@ -2677,6 +2690,10 @@ static void wacom_remote_work(struct work_struct *work) serial = data.remote[i].serial; if (data.remote[i].connected) { + if (kt - remote->remotes[i].active_time > WACOM_REMOTE_BATTERY_TIMEOUT + && remote->remotes[i].active_time != 0) + wacom_remote_destroy_battery(wacom, i); + if (remote->remotes[i].serial == serial) { wacom_remote_attach_battery(wacom, i); continue; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 15cd0cabee2a..c1270db12178 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1129,6 +1129,7 @@ static int wacom_remote_irq(struct wacom_wac *wacom_wac, size_t len) if (index < 0 || !remote->remotes[index].registered) goto out; + remote->remotes[i].active_time = ktime_get(); input = remote->remotes[index].input; input_report_key(input, BTN_0, (data[9] & 0x01)); diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index ee21bb260f22..2e7cc5e7a0cb 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -13,6 +13,7 @@ #define WACOM_NAME_MAX 64 #define WACOM_MAX_REMOTES 5 #define WACOM_STATUS_UNKNOWN 255 +#define WACOM_REMOTE_BATTERY_TIMEOUT 21000000000ll /* packet length for individual models */ #define WACOM_PKGLEN_BBFUN 9 From 86b818e2495d1cbb2b9014d115952fa105eb8f92 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Mon, 31 Jul 2023 13:06:20 +0200 Subject: [PATCH 0671/2093] staging: rtl8712: fix race condition commit 1422b526fba994cf05fd288a152106563b875fce upstream. In probe function, request_firmware_nowait() is called to load firmware asynchronously. At completion of firmware loading, register_netdev() is called. However, a mutex needed by netdev is initialized after the call to request_firmware_nowait(). Consequently, it can happen that register_netdev() is called before the driver is ready. Move the mutex initialization into r8712_init_drv_sw(), which is called before request_firmware_nowait(). Reported-by: syzbot+b08315e8cf5a78eed03c@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-staging/000000000000d9d4560601b8e0d7@google.com/T/#u Fixes: 8c213fa59199 ("staging: r8712u: Use asynchronous firmware loading") Cc: stable Signed-off-by: Nam Cao Link: https://lore.kernel.org/r/20230731110620.116562-1-namcaov@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8712/os_intfs.c | 1 + drivers/staging/rtl8712/usb_intf.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/rtl8712/os_intfs.c b/drivers/staging/rtl8712/os_intfs.c index 003e97205124..3ea70d042f9a 100644 --- a/drivers/staging/rtl8712/os_intfs.c +++ b/drivers/staging/rtl8712/os_intfs.c @@ -323,6 +323,7 @@ int r8712_init_drv_sw(struct _adapter *padapter) mp871xinit(padapter); init_default_value(padapter); r8712_InitSwLeds(padapter); + mutex_init(&padapter->mutex_start); return ret; } diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index 37364d3101e2..df05213f922f 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -567,7 +567,6 @@ static int r871xu_drv_init(struct usb_interface *pusb_intf, if (rtl871x_load_fw(padapter)) goto deinit_drv_sw; init_completion(&padapter->rx_filter_ready); - mutex_init(&padapter->mutex_start); return 0; deinit_drv_sw: From 179c65828593aff1f444e15debd40a477cb23cf4 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 9 Mar 2023 00:45:01 +0800 Subject: [PATCH 0672/2093] Bluetooth: btsdio: fix use after free bug in btsdio_remove due to race condition commit 73f7b171b7c09139eb3c6a5677c200dc1be5f318 upstream. In btsdio_probe, the data->work is bound with btsdio_work. It will be started in btsdio_send_frame. If the btsdio_remove runs with a unfinished work, there may be a race condition that hdev is freed but used in btsdio_work. Fix it by canceling the work before do cleanup in btsdio_remove. Fixes: CVE-2023-1989 Fixes: ddbaf13e3609 ("[Bluetooth] Add generic driver for Bluetooth SDIO devices") Cc: stable@vger.kernel.org Signed-off-by: Zheng Wang Signed-off-by: Luiz Augusto von Dentz [ Denis: Added CVE-2023-1989 and fixes tags. ] Signed-off-by: Denis Efremov (Oracle) Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btsdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 795be33f2892..f19d31ee37ea 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -357,6 +357,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); From 74ceef6e6925a99a5f79087d791f5eb828dd04d0 Mon Sep 17 00:00:00 2001 From: Deren Wu Date: Wed, 10 May 2023 14:51:13 +0800 Subject: [PATCH 0673/2093] wifi: mt76: mt7921: do not support one stream on secondary antenna only commit d616d3680264beb9a9d2c4fc681064b06f447eeb upstream. mt7921 support following antenna combiantions only. * primary + secondary (2x2) * primary only (1x1) Since we cannot work on secondary antenna only, return error if the antenna bitmap is 0x2 in .set_antenna(). For example: iw phy0 set antenna 3 3 /* valid */ iw phy0 set antenna 1 1 /* valid */ iw phy0 set antenna 2 2 /* invalid */ Cc: stable@vger.kernel.org Fixes: e0f9fdda81bd ("mt76: mt7921: add ieee80211_ops") Suggested-by: Knox Chiou Signed-off-by: Deren Wu Signed-off-by: Felix Fietkau Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 60fbbd1ac2f7..172ba7199485 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1280,7 +1280,7 @@ mt7921_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant) return -EINVAL; if ((BIT(hweight8(tx_ant)) - 1) != tx_ant) - tx_ant = BIT(ffs(tx_ant) - 1) - 1; + return -EINVAL; mt7921_mutex_acquire(dev); From 1cd102aaedb277fbe81dd08cd9f5cae951de2bff Mon Sep 17 00:00:00 2001 From: Deren Wu Date: Wed, 17 May 2023 17:18:24 +0800 Subject: [PATCH 0674/2093] wifi: mt76: mt7921: fix skb leak by txs missing in AMSDU commit b642f4c5f3de0a8f47808d32b1ebd9c427a42a66 upstream. txs may be dropped if the frame is aggregated in AMSDU. When the problem shows up, some SKBs would be hold in driver to cause network stopped temporarily. Even if the problem can be recovered by txs timeout handling, mt7921 still need to disable txs in AMSDU to avoid this issue. Cc: stable@vger.kernel.org Fixes: 163f4d22c118 ("mt76: mt7921: add MAC support") Reviewed-by: Shayne Chen Signed-off-by: Deren Wu Reviewed-by: Simon Horman Signed-off-by: Felix Fietkau Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 68511597599e..f7d392fce8c2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -465,6 +465,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, BSS_CHANGED_BEACON_ENABLED)); bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP | BSS_CHANGED_FILS_DISCOVERY)); + bool amsdu_en = wcid->amsdu; if (vif) { struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; @@ -524,12 +525,14 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, txwi[4] = 0; val = FIELD_PREP(MT_TXD5_PID, pid); - if (pid >= MT_PACKET_ID_FIRST) + if (pid >= MT_PACKET_ID_FIRST) { val |= MT_TXD5_TX_STATUS_HOST; + amsdu_en = amsdu_en && !is_mt7921(dev); + } txwi[5] = cpu_to_le32(val); txwi[6] = 0; - txwi[7] = wcid->amsdu ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0; + txwi[7] = amsdu_en ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0; if (is_8023) mt76_connac2_mac_write_txwi_8023(txwi, skb, wcid); From 4b3de7d2f86910a92377d2b4dda86c3c38c48e3d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 14 Jul 2023 15:02:13 +0200 Subject: [PATCH 0675/2093] serial: qcom-geni: fix opp vote on shutdown commit 8ece7b754bc34ffd7fcc8269ccb9128e72ca76d8 upstream. The operating-performance-point vote needs to be dropped when shutting down the port to avoid wasting power by keeping resources like power domains in an unnecessarily high performance state (e.g. when a UART connected Bluetooth controller is not in use). Fixes: a5819b548af0 ("tty: serial: qcom_geni_serial: Use OPP API to set clk/perf state") Cc: stable@vger.kernel.org # 5.9 Cc: Rajendra Nayak Cc: Matthias Kaehlcke Signed-off-by: Johan Hovold Acked-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230714130214.14552-2-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/qcom_geni_serial.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 6f6c4e9b7743..d6f682ed1581 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -129,6 +129,7 @@ struct qcom_geni_serial_port { u32 tx_fifo_width; u32 rx_fifo_depth; bool setup; + unsigned long clk_rate; int (*handle_rx)(struct uart_port *uport, u32 bytes, bool drop); unsigned int baud; void *rx_fifo; @@ -1061,6 +1062,7 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport, baud * sampling_rate, clk_rate, clk_div); uport->uartclk = clk_rate; + port->clk_rate = clk_rate; dev_pm_opp_set_rate(uport->dev, clk_rate); ser_clk_cfg = SER_CLK_EN; ser_clk_cfg |= clk_div << CLK_DIV_SHFT; @@ -1330,10 +1332,13 @@ static void qcom_geni_serial_pm(struct uart_port *uport, if (new_state == UART_PM_STATE_ON && old_state == UART_PM_STATE_OFF) { geni_icc_enable(&port->se); + if (port->clk_rate) + dev_pm_opp_set_rate(uport->dev, port->clk_rate); geni_se_resources_on(&port->se); } else if (new_state == UART_PM_STATE_OFF && old_state == UART_PM_STATE_ON) { geni_se_resources_off(&port->se); + dev_pm_opp_set_rate(uport->dev, 0); geni_icc_disable(&port->se); } } From 682f9b944374fbdc7ee18b41ec8feb146746c433 Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 7 Aug 2023 17:45:51 -0400 Subject: [PATCH 0676/2093] serial: sc16is7xx: fix broken port 0 uart init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2861ed4d6e6d1a2c9de9bf5b0abd996c2dc673d0 upstream. The sc16is7xx_config_rs485() function is called only for the second port (index 1, channel B), causing initialization problems for the first port. For the sc16is7xx driver, port->membase and port->mapbase are not set, and their default values are 0. And we set port->iobase to the device index. This means that when the first device is registered using the uart_add_one_port() function, the following values will be in the port structure: port->membase = 0 port->mapbase = 0 port->iobase = 0 Therefore, the function uart_configure_port() in serial_core.c will exit early because of the following check: /* * If there isn't a port here, don't do anything further. */ if (!port->iobase && !port->mapbase && !port->membase) return; Typically, I2C and SPI drivers do not set port->membase and port->mapbase. The max310x driver sets port->membase to ~0 (all ones). By implementing the same change in this driver, uart_configure_port() is now correctly executed for all ports. Fixes: dfeae619d781 ("serial: sc16is7xx") Cc: stable@vger.kernel.org Signed-off-by: Hugo Villeneuve Reviewed-by: Ilpo Järvinen Reviewed-by: Lech Perczak Tested-by: Lech Perczak Link: https://lore.kernel.org/r/20230807214556.540627-2-hugo@hugovil.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sc16is7xx.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 93cf5f788817..58b565a12836 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1439,6 +1439,12 @@ static int sc16is7xx_probe(struct device *dev, s->p[i].port.fifosize = SC16IS7XX_FIFO_SIZE; s->p[i].port.flags = UPF_FIXED_TYPE | UPF_LOW_LATENCY; s->p[i].port.iobase = i; + /* + * Use all ones as membase to make sure uart_configure_port() in + * serial_core.c does not abort for SPI/I2C devices where the + * membase address is not applicable. + */ + s->p[i].port.membase = (void __iomem *)~0; s->p[i].port.iotype = UPIO_PORT; s->p[i].port.uartclk = freq; s->p[i].port.rs485_config = sc16is7xx_config_rs485; From b7366429626e4bd83222878f7be0900f8b16c3e2 Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 7 Aug 2023 17:45:55 -0400 Subject: [PATCH 0677/2093] serial: sc16is7xx: fix bug when first setting GPIO direction commit 9baeea723c0fb9c3ba9a336369f758ed9bc6831d upstream. When configuring a pin as an output pin with a value of logic 0, we end up as having a value of logic 1 on the output pin. Setting a logic 0 a second time (or more) after that will correctly output a logic 0 on the output pin. By default, all GPIO pins are configured as inputs. When we enter sc16is7xx_gpio_direction_output() for the first time, we first set the desired value in IOSTATE, and then we configure the pin as an output. The datasheet states that writing to IOSTATE register will trigger a transfer of the value to the I/O pin configured as output, so if the pin is configured as an input, nothing will be transferred. Therefore, set the direction first in IODIR, and then set the desired value in IOSTATE. This is what is done in NXP application note AN10587. Fixes: dfeae619d781 ("serial: sc16is7xx") Cc: stable@vger.kernel.org Signed-off-by: Hugo Villeneuve Reviewed-by: Lech Perczak Tested-by: Lech Perczak Link: https://lore.kernel.org/r/20230807214556.540627-6-hugo@hugovil.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sc16is7xx.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 58b565a12836..8411a0f312db 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1345,9 +1345,18 @@ static int sc16is7xx_gpio_direction_output(struct gpio_chip *chip, state |= BIT(offset); else state &= ~BIT(offset); - sc16is7xx_port_write(port, SC16IS7XX_IOSTATE_REG, state); + + /* + * If we write IOSTATE first, and then IODIR, the output value is not + * transferred to the corresponding I/O pin. + * The datasheet states that each register bit will be transferred to + * the corresponding I/O pin programmed as output when writing to + * IOSTATE. Therefore, configure direction first with IODIR, and then + * set value after with IOSTATE. + */ sc16is7xx_port_update(port, SC16IS7XX_IODIR_REG, BIT(offset), BIT(offset)); + sc16is7xx_port_write(port, SC16IS7XX_IOSTATE_REG, state); return 0; } From b5c7bc370e03dcef02cc0263aae7460b4af0827d Mon Sep 17 00:00:00 2001 From: Wang Ming Date: Thu, 27 Jul 2023 14:37:50 -0500 Subject: [PATCH 0678/2093] firmware: stratix10-svc: Fix an NULL vs IS_ERR() bug in probe commit dd218433f2b635d97e8fda3eed047151fd528ce4 upstream. The devm_memremap() function returns error pointers. It never returns NULL. Fix the check. Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver") Cc: stable@vger.kernel.org Signed-off-by: Wang Ming Signed-off-by: Dinh Nguyen Link: https://lore.kernel.org/r/20230727193750.983795-1-dinguyen@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/stratix10-svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 2d674126160f..cab11af28c23 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -756,7 +756,7 @@ svc_create_memory_pool(struct platform_device *pdev, paddr = begin; size = end - begin; va = devm_memremap(dev, paddr, size, MEMREMAP_WC); - if (!va) { + if (IS_ERR(va)) { dev_err(dev, "fail to remap shared memory\n"); return ERR_PTR(-EINVAL); } From a1fc0096921cc329de77b84eb71636b372a46779 Mon Sep 17 00:00:00 2001 From: Juerg Haefliger Date: Wed, 28 Jun 2023 11:50:39 +0200 Subject: [PATCH 0679/2093] fsi: master-ast-cf: Add MODULE_FIRMWARE macro commit 3a1d7aff6e65ad6e285e28abe55abbfd484997ee upstream. The module loads firmware so add a MODULE_FIRMWARE macro to provide that information via modinfo. Fixes: 6a794a27daca ("fsi: master-ast-cf: Add new FSI master using Aspeed ColdFire") Cc: stable@vger.kernel.org # 4.19+ Signed-off-by: Juerg Haefliger Link: https://lore.kernel.org/r/20230628095039.26218-1-juerg.haefliger@canonical.com Signed-off-by: Joel Stanley Signed-off-by: Greg Kroah-Hartman --- drivers/fsi/fsi-master-ast-cf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/fsi/fsi-master-ast-cf.c b/drivers/fsi/fsi-master-ast-cf.c index 5f608ef8b53c..cde281ec89d7 100644 --- a/drivers/fsi/fsi-master-ast-cf.c +++ b/drivers/fsi/fsi-master-ast-cf.c @@ -1441,3 +1441,4 @@ static struct platform_driver fsi_master_acf = { module_platform_driver(fsi_master_acf); MODULE_LICENSE("GPL"); +MODULE_FIRMWARE(FW_FILE_NAME); From dca7c99651415baad8c1fc39214156c7154aaefb Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Sun, 20 Aug 2023 04:44:48 +0000 Subject: [PATCH 0680/2093] tcpm: Avoid soft reset when partner does not support get_status commit 78e0ea4277546debf7e96797ac3b768539cc44f6 upstream. When partner does not support get_status message, tcpm right now responds with soft reset message. This causes PD renegotiation to happen and resets PPS link. Avoid soft resetting the link when partner does not support get_status message to mitigate PPS resets. [ 208.926752] Setting voltage/current limit 9500 mV 2450 mA [ 208.930407] set_auto_vbus_discharge_threshold mode:3 pps_active:y vbus:9500 ret:0 [ 208.930418] state change SNK_TRANSITION_SINK -> SNK_READY [rev3 POWER_NEGOTIATION] [ 208.930455] AMS POWER_NEGOTIATION finished // ALERT message from the Source [ 213.948442] PD RX, header: 0x19a6 [1] [ 213.948451] state change SNK_READY -> GET_STATUS_SEND [rev3 GETTING_SOURCE_SINK_STATUS] [ 213.948457] PD TX, header: 0x492 [ 213.950402] PD TX complete, status: 0 [ 213.950427] pending state change GET_STATUS_SEND -> GET_STATUS_SEND_TIMEOUT @ 60 ms [rev3 GETTING_SOURCE_SINK_STATUS] // NOT_SUPPORTED from the Source [ 213.959954] PD RX, header: 0xbb0 [1] // sink sends SOFT_RESET [ 213.959958] state change GET_STATUS_SEND -> SNK_SOFT_RESET [rev3 GETTING_SOURCE_SINK_STATUS] [ 213.959962] AMS GETTING_SOURCE_SINK_STATUS finished [ 213.959964] AMS SOFT_RESET_AMS start [ 213.959966] state change SNK_SOFT_RESET -> AMS_START [rev3 SOFT_RESET_AMS] [ 213.959969] state change AMS_START -> SOFT_RESET_SEND [rev3 SOFT_RESET_AMS] Cc: stable@vger.kernel.org Fixes: 8dea75e11380 ("usb: typec: tcpm: Protocol Error handling") Signed-off-by: Badhri Jagan Sridharan Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230820044449.1005889-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index d5950ef9d1f3..5f45b82dd191 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2747,6 +2747,13 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port, port->sink_cap_done = true; tcpm_set_state(port, ready_state(port), 0); break; + /* + * Some port partners do not support GET_STATUS, avoid soft reset the link to + * prevent redundant power re-negotiation + */ + case GET_STATUS_SEND: + tcpm_set_state(port, ready_state(port), 0); + break; case SRC_READY: case SNK_READY: if (port->vdm_state > VDM_STATE_READY) { From 689561db6869ef5a4a898f5087870233bfd5f1e5 Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 7 Aug 2023 17:45:53 -0400 Subject: [PATCH 0681/2093] dt-bindings: sc16is7xx: Add property to change GPIO function commit 4cf478dc5d707e56aefa258c049872eff054a353 upstream. Some variants in this series of UART controllers have GPIO pins that are shared between GPIO and modem control lines. The pin mux mode (GPIO or modem control lines) can be set for each ports (channels) supported by the variant. This adds a property to the device tree to set the GPIO pin mux to modem control lines on selected ports if needed. Cc: stable@vger.kernel.org # 6.1.x Signed-off-by: Hugo Villeneuve Acked-by: Conor Dooley Reviewed-by: Lech Perczak Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230807214556.540627-4-hugo@hugovil.com Signed-off-by: Greg Kroah-Hartman --- .../bindings/serial/nxp,sc16is7xx.txt | 46 +++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt index 0fa8e3e43bf8..1a7e4bff0456 100644 --- a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt +++ b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt @@ -23,6 +23,9 @@ Optional properties: 1 = active low. - irda-mode-ports: An array that lists the indices of the port that should operate in IrDA mode. +- nxp,modem-control-line-ports: An array that lists the indices of the port that + should have shared GPIO lines configured as + modem control lines. Example: sc16is750: sc16is750@51 { @@ -35,6 +38,26 @@ Example: #gpio-cells = <2>; }; + sc16is752: sc16is752@53 { + compatible = "nxp,sc16is752"; + reg = <0x53>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <1>; /* Port 1 as modem control lines */ + gpio-controller; /* Port 0 as GPIOs */ + #gpio-cells = <2>; + }; + + sc16is752: sc16is752@54 { + compatible = "nxp,sc16is752"; + reg = <0x54>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <0 1>; /* Ports 0 and 1 as modem control lines */ + }; + * spi as bus Required properties: @@ -59,6 +82,9 @@ Optional properties: 1 = active low. - irda-mode-ports: An array that lists the indices of the port that should operate in IrDA mode. +- nxp,modem-control-line-ports: An array that lists the indices of the port that + should have shared GPIO lines configured as + modem control lines. Example: sc16is750: sc16is750@0 { @@ -70,3 +96,23 @@ Example: gpio-controller; #gpio-cells = <2>; }; + + sc16is752: sc16is752@1 { + compatible = "nxp,sc16is752"; + reg = <1>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <1>; /* Port 1 as modem control lines */ + gpio-controller; /* Port 0 as GPIOs */ + #gpio-cells = <2>; + }; + + sc16is752: sc16is752@2 { + compatible = "nxp,sc16is752"; + reg = <2>; + clocks = <&clk20m>; + interrupt-parent = <&gpio3>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; + nxp,modem-control-line-ports = <0 1>; /* Ports 0 and 1 as modem control lines */ + }; From fdbfc54d5399999112d25a0221aad5f7ca3f9279 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 5 Aug 2023 22:20:38 +0900 Subject: [PATCH 0682/2093] nilfs2: fix general protection fault in nilfs_lookup_dirty_data_buffers() commit f83913f8c5b882a312e72b7669762f8a5c9385e4 upstream. A syzbot stress test reported that create_empty_buffers() called from nilfs_lookup_dirty_data_buffers() can cause a general protection fault. Analysis using its reproducer revealed that the back reference "mapping" from a page/folio has been changed to NULL after dirty page/folio gang lookup in nilfs_lookup_dirty_data_buffers(). Fix this issue by excluding pages/folios from being collected if, after acquiring a lock on each page/folio, its back reference "mapping" differs from the pointer to the address space struct that held the page/folio. Link: https://lkml.kernel.org/r/20230805132038.6435-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+0ad741797f4565e7e2d2@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/0000000000002930a705fc32b231@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Ryusuke Konishi Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/segment.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 21e8260112c8..a4a147a983e0 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -725,6 +725,11 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, struct page *page = pvec.pages[i]; lock_page(page); + if (unlikely(page->mapping != mapping)) { + /* Exclude pages removed from the address space */ + unlock_page(page); + continue; + } if (!page_has_buffers(page)) create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); From 4da07e958bfda2d69d83db105780e8916e3ac02e Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 18 Aug 2023 22:18:04 +0900 Subject: [PATCH 0683/2093] nilfs2: fix WARNING in mark_buffer_dirty due to discarded buffer reuse commit cdaac8e7e5a059f9b5e816cda257f08d0abffacd upstream. A syzbot stress test using a corrupted disk image reported that mark_buffer_dirty() called from __nilfs_mark_inode_dirty() or nilfs_palloc_commit_alloc_entry() may output a kernel warning, and can panic if the kernel is booted with panic_on_warn. This is because nilfs2 keeps buffer pointers in local structures for some metadata and reuses them, but such buffers may be forcibly discarded by nilfs_clear_dirty_page() in some critical situations. This issue is reported to appear after commit 28a65b49eb53 ("nilfs2: do not write dirty data after degenerating to read-only"), but the issue has potentially existed before. Fix this issue by checking the uptodate flag when attempting to reuse an internally held buffer, and reloading the metadata instead of reusing the buffer if the flag was lost. Link: https://lkml.kernel.org/r/20230818131804.7758-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+cdfcae656bac88ba0e2d@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/0000000000003da75f05fdeffd12@google.com Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Tested-by: Ryusuke Konishi Cc: # 3.10+ Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/alloc.c | 3 ++- fs/nilfs2/inode.c | 7 +++++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 6ce8617b562d..7342de296ec3 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -205,7 +205,8 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, int ret; spin_lock(lock); - if (prev->bh && blkoff == prev->blkoff) { + if (prev->bh && blkoff == prev->blkoff && + likely(buffer_uptodate(prev->bh))) { get_bh(prev->bh); *bhp = prev->bh; spin_unlock(lock); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index d4c0895a8811..f625872321cc 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1025,7 +1025,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) int err; spin_lock(&nilfs->ns_inode_lock); - if (ii->i_bh == NULL) { + if (ii->i_bh == NULL || unlikely(!buffer_uptodate(ii->i_bh))) { spin_unlock(&nilfs->ns_inode_lock); err = nilfs_ifile_get_inode_block(ii->i_root->ifile, inode->i_ino, pbh); @@ -1034,7 +1034,10 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) spin_lock(&nilfs->ns_inode_lock); if (ii->i_bh == NULL) ii->i_bh = *pbh; - else { + else if (unlikely(!buffer_uptodate(ii->i_bh))) { + __brelse(ii->i_bh); + ii->i_bh = *pbh; + } else { brelse(*pbh); *pbh = ii->i_bh; } From 7bec12fa9813c8847ad15816c5f31df24201afac Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Wed, 16 Aug 2023 14:25:02 -0300 Subject: [PATCH 0684/2093] usb: typec: tcpci: clear the fault status bit commit 23e60c8daf5ec2ab1b731310761b668745fcf6ed upstream. According the "USB Type-C Port Controller Interface Specification v2.0" the TCPC sets the fault status register bit-7 (AllRegistersResetToDefault) once the registers have been reset to their default values. This triggers an alert(-irq) on PTN5110 devices albeit we do mask the fault-irq, which may cause a kernel hang. Fix this generically by writing a one to the corresponding bit-7. Cc: stable@vger.kernel.org Fixes: 74e656d6b055 ("staging: typec: Type-C Port Controller Interface driver (tcpci)") Reported-by: "Angus Ainslie (Purism)" Closes: https://lore.kernel.org/all/20190508002749.14816-2-angus@akkea.ca/ Reported-by: Christian Bach Closes: https://lore.kernel.org/regressions/ZR0P278MB07737E5F1D48632897D51AC3EB329@ZR0P278MB0773.CHEP278.PROD.OUTLOOK.COM/t/ Signed-off-by: Marco Felsch Signed-off-by: Fabio Estevam Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230816172502.1155079-1-festevam@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpci.c | 4 ++++ include/linux/usb/tcpci.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 72f8d1e87600..816945913ed0 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -593,6 +593,10 @@ static int tcpci_init(struct tcpc_dev *tcpc) if (time_after(jiffies, timeout)) return -ETIMEDOUT; + ret = tcpci_write16(tcpci, TCPC_FAULT_STATUS, TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT); + if (ret < 0) + return ret; + /* Handle vendor init */ if (tcpci->data->init) { ret = tcpci->data->init(tcpci, tcpci->data); diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 17657451c762..77eb40b918d7 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -103,6 +103,7 @@ #define TCPC_POWER_STATUS_SINKING_VBUS BIT(0) #define TCPC_FAULT_STATUS 0x1f +#define TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT BIT(7) #define TCPC_ALERT_EXTENDED 0x21 From 4a6284a2fc6353ecd15c819bf37fd9376848a185 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 17 Jul 2023 15:16:52 -0500 Subject: [PATCH 0685/2093] pinctrl: amd: Don't show `Invalid config param` errors commit 87b549efcb0f7934b0916d2a00607a878b6f1e0f upstream. On some systems amd_pinconf_set() is called with parameters 0x8 (PIN_CONFIG_DRIVE_PUSH_PULL) or 0x14 (PIN_CONFIG_PERSIST_STATE) which are not supported by pinctrl-amd. Don't show an err message when called with an invalid parameter, downgrade this to debug instead. Cc: stable@vger.kernel.org # 6.1 Fixes: 635a750d958e1 ("pinctrl: amd: Use amd_pinconf_set() for all config options") Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230717201652.17168-1-mario.limonciello@amd.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index be6838c252f0..2b6d996e393e 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -748,7 +748,7 @@ static int amd_pinconf_get(struct pinctrl_dev *pctldev, break; default: - dev_err(&gpio_dev->pdev->dev, "Invalid config param %04x\n", + dev_dbg(&gpio_dev->pdev->dev, "Invalid config param %04x\n", param); return -ENOTSUPP; } @@ -798,7 +798,7 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; default: - dev_err(&gpio_dev->pdev->dev, + dev_dbg(&gpio_dev->pdev->dev, "Invalid config param %04x\n", param); ret = -ENOTSUPP; } From 59b13c2b647e464dd85622c89d7f16c15d681e96 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 6 Sep 2023 21:27:03 +0100 Subject: [PATCH 0686/2093] Linux 6.1.52 Link: https://lore.kernel.org/r/20230904182946.999390199@linuxfoundation.org Tested-by: Salvatore Bonaccorso Tested-by: Joel Fernandes (Google) Tested-by: Bagas Sanjaya Tested-by: Linux Kernel Functional Testing Tested-by: Sudip Mukherjee Tested-by: Takeshi Ogasawara Tested-by: Jon Hunter Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Ron Economos Tested-by: SeongJae Park Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e7c344d5af15..82aaa3ae7395 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 51 +SUBLEVEL = 52 EXTRAVERSION = NAME = Curry Ramen From 9186398472125de06830d3bfbf3c4e123f7b4069 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 18 Jul 2023 10:41:52 -0700 Subject: [PATCH 0687/2093] Revert "bridge: Add extack warning when enabling STP in netns." [ Upstream commit 7ebd00a5a20c48e6020d49a3b2afb3cdfd2da8b7 ] This reverts commit 56a16035bb6effb37177867cea94c13a8382f745. Since the previous commit, STP works on bridge in netns. # unshare -n # ip link add br0 type bridge # ip link add veth0 type veth peer name veth1 # ip link set veth0 master br0 up [ 50.558135] br0: port 1(veth0) entered blocking state [ 50.558366] br0: port 1(veth0) entered disabled state [ 50.558798] veth0: entered allmulticast mode [ 50.564401] veth0: entered promiscuous mode # ip link set veth1 master br0 up [ 54.215487] br0: port 2(veth1) entered blocking state [ 54.215657] br0: port 2(veth1) entered disabled state [ 54.215848] veth1: entered allmulticast mode [ 54.219577] veth1: entered promiscuous mode # ip link set br0 type bridge stp_state 1 # ip link set br0 up [ 61.960726] br0: port 2(veth1) entered blocking state [ 61.961097] br0: port 2(veth1) entered listening state [ 61.961495] br0: port 1(veth0) entered blocking state [ 61.961653] br0: port 1(veth0) entered listening state [ 63.998835] br0: port 2(veth1) entered blocking state [ 77.437113] br0: port 1(veth0) entered learning state [ 86.653501] br0: received packet on veth0 with own address as source address (addr:6e:0f:e7:6f:5f:5f, vlan:0) [ 92.797095] br0: port 1(veth0) entered forwarding state [ 92.797398] br0: topology change detected, propagating Let's remove the warning. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/bridge/br_stp_if.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index b65962682771..75204d36d7f9 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -201,9 +201,6 @@ int br_stp_set_enabled(struct net_bridge *br, unsigned long val, { ASSERT_RTNL(); - if (!net_eq(dev_net(br->dev), &init_net)) - NL_SET_ERR_MSG_MOD(extack, "STP does not work in non-root netns"); - if (br_mrp_enabled(br)) { NL_SET_ERR_MSG_MOD(extack, "STP can't be enabled if MRP is already enabled"); From 9fc3adc6d0fe96e79e21990faebc252814ee18a4 Mon Sep 17 00:00:00 2001 From: Daniel Miess Date: Wed, 31 May 2023 11:47:35 -0400 Subject: [PATCH 0688/2093] Partially revert "drm/amd/display: Fix possible underflow for displays with large vblank" [ Upstream commit a99a4ff6ef205d125002fc7e0857074e4e6597b6 ] This partially reverts commit de231189e7bf ("drm/amd/display: Fix possible underflow for displays with large vblank"). [Why] The increased value of VBlankNomDefaultUS causes underflow at the desktop of an IP KVM setup [How] Change the value from 800 back to 668 Reviewed-by: Nicholas Kazlauskas Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Daniel Miess Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 8a88605827a8..551a63f7064b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -32,7 +32,7 @@ #include "dml/display_mode_vba.h" struct _vcs_dpi_ip_params_st dcn3_14_ip = { - .VBlankNomDefaultUS = 800, + .VBlankNomDefaultUS = 668, .gpuvm_enable = 1, .gpuvm_max_page_table_levels = 1, .hostvm_enable = 1, From 6ab081571f6a4f6b2eab6b5328f8a4273faa40d0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 18 Oct 2022 13:29:55 -0700 Subject: [PATCH 0689/2093] scsi: ufs: Try harder to change the power mode [ Upstream commit 579a4e9dbd53978cad8df88dc612837cdd210ce0 ] Instead of only retrying the START STOP UNIT command if a unit attention is reported, repeat it if any SCSI error is reported by the device or if the command timed out. Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20221018202958.1902564-8-bvanassche@acm.org Signed-off-by: Martin K. Petersen Stable-dep-of: fe8637f7708c ("scsi: ufs: core: Increase the START STOP UNIT timeout from one to ten seconds") Signed-off-by: Sasha Levin --- drivers/ufs/core/ufshcd.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 977bd4b9dd0b..36437d39b93c 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8830,9 +8830,11 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, for (retries = 3; retries > 0; --retries) { ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, HZ, 0, 0, RQF_PM, NULL); - if (!scsi_status_is_check_condition(ret) || - !scsi_sense_valid(&sshdr) || - sshdr.sense_key != UNIT_ATTENTION) + /* + * scsi_execute() only returns a negative value if the request + * queue is dying. + */ + if (ret <= 0) break; } if (ret) { From 7f483ce4699ac4158879833d08a86b57697b05b3 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Wed, 22 Mar 2023 14:29:26 -0400 Subject: [PATCH 0690/2093] Revert "Revert drm/amd/display: Enable Freesync Video Mode by default" [ Upstream commit 11b92df8a2f7f4605ccc764ce6ae4a72760674df ] This reverts commit 4243c84aa082d8fba70c45f48eb2bb5c19799060. Enables freesync video by default, since the hang and corruption issue on eDP panels are now fixed. Acked-by: Stylon Wang Signed-off-by: Aurabindo Pillai Reviewed-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 249b269e2cc5..9beb326a9528 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5921,8 +5921,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, */ DRM_DEBUG_DRIVER("No preferred mode found\n"); } else { - recalculate_timing = amdgpu_freesync_vid_mode && - is_freesync_video_mode(&mode, aconnector); + recalculate_timing = is_freesync_video_mode(&mode, aconnector); if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); @@ -7016,7 +7015,7 @@ static void amdgpu_dm_connector_add_freesync_modes(struct drm_connector *connect struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); - if (!(amdgpu_freesync_vid_mode && edid)) + if (!edid) return; if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) @@ -9022,8 +9021,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, * TODO: Refactor this function to allow this check to work * in all conditions. */ - if (amdgpu_freesync_vid_mode && - dm_new_crtc_state->stream && + if (dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) goto skip_modeset; @@ -9063,7 +9061,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, } /* Now check if we should set freesync video mode */ - if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream && + if (dm_new_crtc_state->stream && dc_is_stream_unchanged(new_stream, dm_old_crtc_state->stream) && dc_is_stream_scaling_unchanged(new_stream, dm_old_crtc_state->stream) && is_timing_unchanged_for_freesync(new_crtc_state, @@ -9076,7 +9074,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, set_freesync_fixed_config(dm_new_crtc_state); goto skip_modeset; - } else if (amdgpu_freesync_vid_mode && aconnector && + } else if (aconnector && is_freesync_video_mode(&new_crtc_state->mode, aconnector)) { struct drm_display_mode *high_mode; From f4bd9a43152e677fa3f1fec3d98e19d169343079 Mon Sep 17 00:00:00 2001 From: Xiaolei Wang Date: Mon, 24 Jul 2023 23:45:10 +0800 Subject: [PATCH 0691/2093] ARM: dts: imx: Set default tuning step for imx7d usdhc [ Upstream commit be18293e47cbca7c6acee9231fc851601d69563a ] If the tuning step is not set, the tuning step is set to 1. For some sd cards, the following Tuning timeout will occur. Tuning failed, falling back to fixed sampling clock mmc0: Tuning failed, falling back to fixed sampling clock So set the default tuning step. This refers to the NXP vendor's commit below: https://github.com/nxp-imx/linux-imx/blob/lf-6.1.y/ arch/arm/boot/dts/imx7s.dtsi#L1216-L1217 Fixes: 1e336aa0c025 ("mmc: sdhci-esdhc-imx: correct the tuning start tap and step setting") Signed-off-by: Xiaolei Wang Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx7s.dtsi | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 11b9321badc5..667568aa4326 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -1184,6 +1184,8 @@ usdhc1: mmc@30b40000 { <&clks IMX7D_USDHC1_ROOT_CLK>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-step = <2>; + fsl,tuning-start-tap = <20>; status = "disabled"; }; @@ -1196,6 +1198,8 @@ usdhc2: mmc@30b50000 { <&clks IMX7D_USDHC2_ROOT_CLK>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-step = <2>; + fsl,tuning-start-tap = <20>; status = "disabled"; }; @@ -1208,6 +1212,8 @@ usdhc3: mmc@30b60000 { <&clks IMX7D_USDHC3_ROOT_CLK>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-step = <2>; + fsl,tuning-start-tap = <20>; status = "disabled"; }; From 4e005f5dd5b0160905367afb3186c0dff9e0af75 Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Tue, 6 Jun 2023 22:57:47 +0800 Subject: [PATCH 0692/2093] ALSA: hda/realtek: Enable 4 amplifiers instead of 2 on a HP platform [ Upstream commit b752a385b584d385683c65cb76a1298f1379a88c ] In the commit 7bb62340951a ("ALSA: hda/realtek: fix speaker, mute/micmute LEDs not work on a HP platform"), speakers and LEDs are fixed but only 2 CS35L41 amplifiers on SPI bus connected to Realtek codec are enabled. Need the ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED to get all amplifiers working. Signed-off-by: Chris Chiu Fixes: 7bb62340951a ("ALSA: hda/realtek: fix speaker, mute/micmute LEDs not work on a HP platform") Cc: Link: https://lore.kernel.org/r/20230606145747.135966-1-chris.chiu@canonical.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index aa475154c582..f70e0ad81607 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9591,7 +9591,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8b, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8d, "HP", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), From 36148a9b144c45a0810fb012151b5720a0c8b82e Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Apr 2023 12:34:53 -0700 Subject: [PATCH 0693/2093] powerpc/boot: Disable power10 features after BOOTAFLAGS assignment [ Upstream commit 2b694fc96fe33a7c042e3a142d27d945c8c668b0 ] When building the boot wrapper assembly files with clang after commit 648a1783fe25 ("powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU"), the following warnings appear for each file built: '-prefixed' is not a recognized feature for this target (ignoring feature) '-pcrel' is not a recognized feature for this target (ignoring feature) While it is questionable whether or not LLVM should be emitting a warning when passed negative versions of code generation flags when building assembly files (since it does not emit a warning for the altivec and vsx flags), it is easy enough to work around this by just moving the disabled flags to BOOTCFLAGS after the assignment of BOOTAFLAGS, so that they are not added when building assembly files. Do so to silence the warnings. Fixes: 648a1783fe25 ("powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU") Link: https://github.com/ClangBuiltLinux/linux/issues/1839 Reviewed-by: Nicholas Piggin Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://msgid.link/20230427-remove-power10-args-from-boot-aflags-clang-v1-1-9107f7c943bc@kernel.org Signed-off-by: Sasha Levin --- arch/powerpc/boot/Makefile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 13fad4f0a6d8..b13324b1a169 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,8 +34,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ - $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ - $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) @@ -71,6 +69,10 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -crD +BOOTCFLAGS += $(call cc-option,-mno-prefixed) \ + $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) + ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) BOOTAFLAGS += $(CLANG_FLAGS) From b608025733579f4e9074a26dc08ea05f0e07ea0f Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Wed, 24 May 2023 16:07:38 +0800 Subject: [PATCH 0694/2093] media: uapi: HEVC: Add num_delta_pocs_of_ref_rps_idx field [ Upstream commit ae440c5da33cdb90a109f2df2a0360c67b3fab7e ] Some drivers firmwares parse by themselves slice header and need num_delta_pocs_of_ref_rps_idx value to parse slice header short_term_ref_pic_set(). Use one of the 4 reserved bytes to store this value without changing the v4l2_ctrl_hevc_decode_params structure size and padding. This value also exist in DXVA API. Signed-off-by: Benjamin Gaignard Signed-off-by: Yunfei Dong Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil [hverkuil: fix typo in num_delta_pocs_of_ref_rps_idx doc] Stable-dep-of: 297160d411e3 ("media: mediatek: vcodec: move core context from device to each instance") Signed-off-by: Sasha Levin --- .../userspace-api/media/v4l/ext-ctrls-codec-stateless.rst | 7 +++++++ include/uapi/linux/v4l2-controls.h | 6 +++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst index cd33857d947d..0ef49647c90b 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst @@ -2923,6 +2923,13 @@ This structure contains all loop filter related parameters. See sections - ``poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - PocLtCurr as described in section 8.3.2 "Decoding process for reference picture set": provides the index of the long term references in DPB array. + * - __u8 + - ``num_delta_pocs_of_ref_rps_idx`` + - When the short_term_ref_pic_set_sps_flag in the slice header is equal to 0, + it is the same as the derived value NumDeltaPocs[RefRpsIdx]. It can be used to parse + the RPS data in slice headers instead of skipping it with @short_term_ref_pic_set_size. + When the value of short_term_ref_pic_set_sps_flag in the slice header is + equal to 1, num_delta_pocs_of_ref_rps_idx shall be set to 0. * - struct :c:type:`v4l2_hevc_dpb_entry` - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - The decoded picture buffer, for meta-data about reference frames. diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index b5e7d082b8ad..d4a4e3cab3c2 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -2411,6 +2411,9 @@ struct v4l2_ctrl_hevc_slice_params { * @poc_st_curr_after: provides the index of the short term after references * in DPB array * @poc_lt_curr: provides the index of the long term references in DPB array + * @num_delta_pocs_of_ref_rps_idx: same as the derived value NumDeltaPocs[RefRpsIdx], + * can be used to parse the RPS data in slice headers + * instead of skipping it with @short_term_ref_pic_set_size. * @reserved: padding field. Should be zeroed by applications. * @dpb: the decoded picture buffer, for meta-data about reference frames * @flags: see V4L2_HEVC_DECODE_PARAM_FLAG_{} @@ -2426,7 +2429,8 @@ struct v4l2_ctrl_hevc_decode_params { __u8 poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u8 poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u8 poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 reserved[4]; + __u8 num_delta_pocs_of_ref_rps_idx; + __u8 reserved[3]; struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u64 flags; }; From 2981ff271d5270255d3ef1af4e443e031dc7b37c Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Thu, 1 Jun 2023 13:56:36 +0100 Subject: [PATCH 0695/2093] Revert "MIPS: unhide PATA_PLATFORM" [ Upstream commit 1e13da548fbffb807633df85a244b70caa90bdf7 ] Revert commit 75b18aac6fa3 ("MIPS: unhide PATA_PLATFORM") now that HAVE_PATA_PLATFORM is set selectively for all the relevant platforms. Verified with `db1xxx_defconfig' and `sb1250_swarm_defconfig' by making sure PATA_PLATFORM is still there in `.config' with this change applied, and with `malta_defconfig' by making sure it's now gone. Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cf1fbf4eaa8a..0e62f5edaee2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -83,7 +83,6 @@ config MIPS select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP From 026e918b3670120fa4a4f44e537a7f18d3bc4685 Mon Sep 17 00:00:00 2001 From: Adrien Thierry Date: Thu, 29 Jun 2023 10:45:40 -0400 Subject: [PATCH 0696/2093] phy: qcom-snps-femto-v2: use qcom_snps_hsphy_suspend/resume error code [ Upstream commit 8932089b566c24ea19b57e37704c492678de1420 ] The return value from qcom_snps_hsphy_suspend/resume is not used. Make sure qcom_snps_hsphy_runtime_suspend/resume return this value as well. Signed-off-by: Adrien Thierry Link: https://lore.kernel.org/r/20230629144542.14906-4-athierry@redhat.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c index 6170f8fd118e..d0319bee01c0 100644 --- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c +++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c @@ -214,8 +214,7 @@ static int __maybe_unused qcom_snps_hsphy_runtime_suspend(struct device *dev) if (!hsphy->phy_initialized) return 0; - qcom_snps_hsphy_suspend(hsphy); - return 0; + return qcom_snps_hsphy_suspend(hsphy); } static int __maybe_unused qcom_snps_hsphy_runtime_resume(struct device *dev) @@ -225,8 +224,7 @@ static int __maybe_unused qcom_snps_hsphy_runtime_resume(struct device *dev) if (!hsphy->phy_initialized) return 0; - qcom_snps_hsphy_resume(hsphy); - return 0; + return qcom_snps_hsphy_resume(hsphy); } static int qcom_snps_hsphy_set_mode(struct phy *phy, enum phy_mode mode, From 0b6e7170ccdf422d844e59abfaf6d5a4691b9c4d Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Tue, 31 Jan 2023 11:32:44 +0100 Subject: [PATCH 0697/2093] media: amphion: use dev_err_probe [ Upstream commit 517f088385e1b8015606143e6212cb30f8714070 ] This simplifies the code and silences -517 error messages. Also the reason is listed in /sys/kernel/debug/devices_deferred. Signed-off-by: Alexander Stein Reviewed-by: ming_qian Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vpu_mbox.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/media/platform/amphion/vpu_mbox.c b/drivers/media/platform/amphion/vpu_mbox.c index bf759eb2fd46..b6d5b4844f67 100644 --- a/drivers/media/platform/amphion/vpu_mbox.c +++ b/drivers/media/platform/amphion/vpu_mbox.c @@ -46,11 +46,10 @@ static int vpu_mbox_request_channel(struct device *dev, struct vpu_mbox *mbox) cl->rx_callback = vpu_mbox_rx_callback; ch = mbox_request_channel_byname(cl, mbox->name); - if (IS_ERR(ch)) { - dev_err(dev, "Failed to request mbox chan %s, ret : %ld\n", - mbox->name, PTR_ERR(ch)); - return PTR_ERR(ch); - } + if (IS_ERR(ch)) + return dev_err_probe(dev, PTR_ERR(ch), + "Failed to request mbox chan %s\n", + mbox->name); mbox->ch = ch; return 0; From eb3c2b3519bffac7550f31c7f11b3a19bdc93a8f Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Tue, 6 Jun 2023 06:38:15 +0200 Subject: [PATCH 0698/2093] media: pulse8-cec: handle possible ping error [ Upstream commit 92cbf865ea2e0f2997ff97815c6db182eb23df1b ] Handle (and warn about) possible error waiting for MSGCODE_PING result. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Dmitry Antipov Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/cec/usb/pulse8/pulse8-cec.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/media/cec/usb/pulse8/pulse8-cec.c b/drivers/media/cec/usb/pulse8/pulse8-cec.c index 04b13cdc38d2..ba67587bd43e 100644 --- a/drivers/media/cec/usb/pulse8/pulse8-cec.c +++ b/drivers/media/cec/usb/pulse8/pulse8-cec.c @@ -809,8 +809,11 @@ static void pulse8_ping_eeprom_work_handler(struct work_struct *work) mutex_lock(&pulse8->lock); cmd = MSGCODE_PING; - pulse8_send_and_wait(pulse8, &cmd, 1, - MSGCODE_COMMAND_ACCEPTED, 0); + if (pulse8_send_and_wait(pulse8, &cmd, 1, + MSGCODE_COMMAND_ACCEPTED, 0)) { + dev_warn(pulse8->dev, "failed to ping EEPROM\n"); + goto unlock; + } if (pulse8->vers < 2) goto unlock; From 72c90ebb2dc54dab2481f39977bba37788a58f35 Mon Sep 17 00:00:00 2001 From: Nikolay Burykin Date: Tue, 10 Jan 2023 10:09:00 +0100 Subject: [PATCH 0699/2093] media: pci: cx23885: fix error handling for cx23885 ATSC boards [ Upstream commit 4aaa96b59df5fac41ba891969df6b092061ea9d7 ] After having been assigned to NULL value at cx23885-dvb.c:1202, pointer '0' is dereferenced at cx23885-dvb.c:2469. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Nikolay Burykin Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/pci/cx23885/cx23885-dvb.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c index 8fd5b6ef2428..7551ca4a322a 100644 --- a/drivers/media/pci/cx23885/cx23885-dvb.c +++ b/drivers/media/pci/cx23885/cx23885-dvb.c @@ -2459,16 +2459,10 @@ static int dvb_register(struct cx23885_tsport *port) request_module("%s", info.type); client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info); if (!i2c_client_has_driver(client_tuner)) { - module_put(client_demod->dev.driver->owner); - i2c_unregister_device(client_demod); - port->i2c_client_demod = NULL; goto frontend_detach; } if (!try_module_get(client_tuner->dev.driver->owner)) { i2c_unregister_device(client_tuner); - module_put(client_demod->dev.driver->owner); - i2c_unregister_device(client_demod); - port->i2c_client_demod = NULL; goto frontend_detach; } port->i2c_client_tuner = client_tuner; @@ -2505,16 +2499,10 @@ static int dvb_register(struct cx23885_tsport *port) request_module("%s", info.type); client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info); if (!i2c_client_has_driver(client_tuner)) { - module_put(client_demod->dev.driver->owner); - i2c_unregister_device(client_demod); - port->i2c_client_demod = NULL; goto frontend_detach; } if (!try_module_get(client_tuner->dev.driver->owner)) { i2c_unregister_device(client_tuner); - module_put(client_demod->dev.driver->owner); - i2c_unregister_device(client_demod); - port->i2c_client_demod = NULL; goto frontend_detach; } port->i2c_client_tuner = client_tuner; From 05d88512e83377cc38c51fc757c3d8fee53b3287 Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Wed, 3 May 2023 16:49:26 +0900 Subject: [PATCH 0700/2093] 9p: virtio: fix unlikely null pointer deref in handle_rerror [ Upstream commit 13ade4ac5c28e8a014fa85278f5a4270b215f906 ] handle_rerror can dereference the pages pointer, but it is not necessarily set for small payloads. In practice these should be filtered out by the size check, but might as well double-check explicitly. This fixes the following scan-build warnings: net/9p/trans_virtio.c:401:24: warning: Dereference of null pointer [core.NullDereference] memcpy_from_page(to, *pages++, offs, n); ^~~~~~~~ net/9p/trans_virtio.c:406:23: warning: Dereference of null pointer (loaded from variable 'pages') [core.NullDereference] memcpy_from_page(to, *pages, offs, size); ^~~~~~ Reviewed-by: Simon Horman Signed-off-by: Dominique Martinet Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin --- net/9p/trans_virtio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 3f3eb03cda7d..6a4a29a2703d 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -385,7 +385,7 @@ static void handle_rerror(struct p9_req_t *req, int in_hdr_len, void *to = req->rc.sdata + in_hdr_len; // Fits entirely into the static data? Nothing to do. - if (req->rc.size < in_hdr_len) + if (req->rc.size < in_hdr_len || !pages) return; // Really long error message? Tough, truncate the reply. Might get From 513eac8b85304dde069dc217e0423c7f7680b6ba Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Wed, 3 May 2023 16:49:27 +0900 Subject: [PATCH 0701/2093] 9p: virtio: make sure 'offs' is initialized in zc_request [ Upstream commit 4a73edab69d3a6623f03817fe950a2d9585f80e4 ] Similarly to the previous patch: offs can be used in handle_rerrors without initializing on small payloads; in this case handle_rerrors will not use it because of the size check, but it doesn't hurt to make sure it is zero to please scan-build. This fixes the following warning: net/9p/trans_virtio.c:539:3: warning: 3rd function call argument is an uninitialized value [core.CallAndMessage] handle_rerror(req, in_hdr_len, offs, in_pages); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Reviewed-by: Simon Horman Signed-off-by: Dominique Martinet Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin --- net/9p/trans_virtio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 6a4a29a2703d..3cf660d8a0a7 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -429,7 +429,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, struct page **in_pages = NULL, **out_pages = NULL; struct virtio_chan *chan = client->trans; struct scatterlist *sgs[4]; - size_t offs; + size_t offs = 0; int need_drop = 0; int kicked = 0; From 9776024ee06b352a995830fc8f3cdaae49de1a51 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 22 Jul 2023 00:09:28 +0900 Subject: [PATCH 0702/2093] ksmbd: fix out of bounds in smb3_decrypt_req() [ Upstream commit dc318846f3dd54574a36ae97fc8d8b75dd7cdb1e ] smb3_decrypt_req() validate if pdu_length is smaller than smb2_transform_hdr size. Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21589 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/smb2pdu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9b621fd993bb..ee954c5ab9c2 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8713,7 +8713,8 @@ int smb3_decrypt_req(struct ksmbd_work *work) struct smb2_transform_hdr *tr_hdr = smb2_get_msg(buf); int rc = 0; - if (buf_data_size < sizeof(struct smb2_hdr)) { + if (pdu_length < sizeof(struct smb2_transform_hdr) || + buf_data_size < sizeof(struct smb2_hdr)) { pr_err("Transform message is too small (%u)\n", pdu_length); return -ECONNABORTED; From becb5191d1d5fdfca0198a2e37457bbbf4fe266f Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 23 Jul 2023 15:21:11 +0900 Subject: [PATCH 0703/2093] ksmbd: validate session id and tree id in compound request [ Upstream commit 3df0411e132ee74a87aa13142dfd2b190275332e ] `smb2_get_msg()` in smb2_get_ksmbd_tcon() and smb2_check_user_session() will always return the first request smb2 header in a compound request. if `SMB2_TREE_CONNECT_HE` is the first command in compound request, will return 0, i.e. The tree id check is skipped. This patch use ksmbd_req_buf_next() to get current command in compound. Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21506 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/smb2pdu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index ee954c5ab9c2..74c245809772 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -86,9 +86,9 @@ struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn */ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) { - struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *req_hdr = ksmbd_req_buf_next(work); unsigned int cmd = le16_to_cpu(req_hdr->Command); - int tree_id; + unsigned int tree_id; if (cmd == SMB2_TREE_CONNECT_HE || cmd == SMB2_CANCEL_HE || @@ -113,7 +113,7 @@ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) pr_err("The first operation in the compound does not have tcon\n"); return -EINVAL; } - if (work->tcon->id != tree_id) { + if (tree_id != UINT_MAX && work->tcon->id != tree_id) { pr_err("tree id(%u) is different with id(%u) in first operation\n", tree_id, work->tcon->id); return -EINVAL; @@ -565,9 +565,9 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) */ int smb2_check_user_session(struct ksmbd_work *work) { - struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *req_hdr = ksmbd_req_buf_next(work); struct ksmbd_conn *conn = work->conn; - unsigned int cmd = conn->ops->get_cmd_val(work); + unsigned int cmd = le16_to_cpu(req_hdr->Command); unsigned long long sess_id; /* @@ -593,7 +593,7 @@ int smb2_check_user_session(struct ksmbd_work *work) pr_err("The first operation in the compound does not have sess\n"); return -EINVAL; } - if (work->sess->id != sess_id) { + if (sess_id != ULLONG_MAX && work->sess->id != sess_id) { pr_err("session id(%llu) is different with the first operation(%lld)\n", sess_id, work->sess->id); return -EINVAL; From 99a2426b135e590ab7e2c930f7ce489ea1e4edbd Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 23 Jul 2023 15:22:33 +0900 Subject: [PATCH 0704/2093] ksmbd: no response from compound read [ Upstream commit e202a1e8634b186da38cbbff85382ea2b9e297cf ] ksmbd doesn't support compound read. If client send read-read in compound to ksmbd, there can be memory leak from read buffer. Windows and linux clients doesn't send it to server yet. For now, No response from compound read. compound read will be supported soon. Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21587, ZDI-CAN-21588 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/smb2pdu.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 74c245809772..f6fd5cf976a5 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -6314,6 +6314,11 @@ int smb2_read(struct ksmbd_work *work) unsigned int max_read_size = conn->vals->max_read_size; WORK_BUFFERS(work, req, rsp); + if (work->next_smb2_rcv_hdr_off) { + work->send_no_response = 1; + err = -EOPNOTSUPP; + goto out; + } if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { From 330d900620dfc9893011d725b3620cd2ee0bc2bc Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 23 Jul 2023 15:27:37 +0900 Subject: [PATCH 0705/2093] ksmbd: fix out of bounds in init_smb2_rsp_hdr() [ Upstream commit 536bb492d39bb6c080c92f31e8a55fe9934f452b ] If client send smb2 negotiate request and then send smb1 negotiate request, init_smb2_rsp_hdr is called for smb1 negotiate request since need_neg is set to false. This patch ignore smb1 packets after ->need_neg is set to false. Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21541 Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/server/server.c | 7 ++++++- fs/smb/server/smb_common.c | 19 +++++++++++-------- fs/smb/server/smb_common.h | 2 +- 3 files changed, 18 insertions(+), 10 deletions(-) diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 847ee62afb8a..9804cabe72a8 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -286,6 +286,7 @@ static void handle_ksmbd_work(struct work_struct *wk) static int queue_ksmbd_work(struct ksmbd_conn *conn) { struct ksmbd_work *work; + int err; work = ksmbd_alloc_work_struct(); if (!work) { @@ -297,7 +298,11 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) work->request_buf = conn->request_buf; conn->request_buf = NULL; - ksmbd_init_smb_server(work); + err = ksmbd_init_smb_server(work); + if (err) { + ksmbd_free_work_struct(work); + return 0; + } ksmbd_conn_enqueue_request(work); atomic_inc(&conn->r_count); diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index d937e2f45c82..a4421d9458d9 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -388,26 +388,29 @@ static struct smb_version_cmds smb1_server_cmds[1] = { [SMB_COM_NEGOTIATE_EX] = { .proc = smb1_negotiate, }, }; -static void init_smb1_server(struct ksmbd_conn *conn) +static int init_smb1_server(struct ksmbd_conn *conn) { conn->ops = &smb1_server_ops; conn->cmds = smb1_server_cmds; conn->max_cmds = ARRAY_SIZE(smb1_server_cmds); + return 0; } -void ksmbd_init_smb_server(struct ksmbd_work *work) +int ksmbd_init_smb_server(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; __le32 proto; - if (conn->need_neg == false) - return; - proto = *(__le32 *)((struct smb_hdr *)work->request_buf)->Protocol; + if (conn->need_neg == false) { + if (proto == SMB1_PROTO_NUMBER) + return -EINVAL; + return 0; + } + if (proto == SMB1_PROTO_NUMBER) - init_smb1_server(conn); - else - init_smb3_11_server(conn); + return init_smb1_server(conn); + return init_smb3_11_server(conn); } int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index e63d2a4f466b..1cbb492cdefe 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -427,7 +427,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn); int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count); -void ksmbd_init_smb_server(struct ksmbd_work *work); +int ksmbd_init_smb_server(struct ksmbd_work *work); struct ksmbd_kstat; int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, From 3c59ad8d6e8e89ced34da6e53abb0400a737f2ef Mon Sep 17 00:00:00 2001 From: Dmytro Maluka Date: Mon, 17 Jul 2023 21:37:36 +0200 Subject: [PATCH 0706/2093] ASoC: da7219: Flush pending AAD IRQ when suspending [ Upstream commit 91e292917dad64ab8d1d5ca2ab3069ad9dac6f72 ] da7219_aad_suspend() disables jack detection, which should prevent generating new interrupts by DA7219 while suspended. However, there is a theoretical possibility that there is a pending interrupt generated just before suspending DA7219 and not handled yet, so the IRQ handler may still run after DA7219 is suspended. To prevent that, wait until the pending IRQ handling is done. This patch arose as an attempt to fix the following I2C failure occurring sometimes during system suspend or resume: [ 355.876211] i2c_designware i2c_designware.3: Transfer while suspended [ 355.876245] WARNING: CPU: 2 PID: 3576 at drivers/i2c/busses/i2c-designware-master.c:570 i2c_dw_xfer+0x411/0x440 ... [ 355.876462] Call Trace: [ 355.876468] [ 355.876475] ? update_load_avg+0x1b3/0x615 [ 355.876484] __i2c_transfer+0x101/0x1d8 [ 355.876494] i2c_transfer+0x74/0x10d [ 355.876504] regmap_i2c_read+0x6a/0x9c [ 355.876513] _regmap_raw_read+0x179/0x223 [ 355.876521] regmap_raw_read+0x1e1/0x28e [ 355.876527] regmap_bulk_read+0x17d/0x1ba [ 355.876532] ? __wake_up+0xed/0x1bb [ 355.876542] da7219_aad_irq_thread+0x54/0x2c9 [snd_soc_da7219 5fb8ebb2179cf2fea29af090f3145d68ed8e2184] [ 355.876556] irq_thread+0x13c/0x231 [ 355.876563] ? irq_forced_thread_fn+0x5f/0x5f [ 355.876570] ? irq_thread_fn+0x4d/0x4d [ 355.876576] kthread+0x13a/0x152 [ 355.876581] ? synchronize_irq+0xc3/0xc3 [ 355.876587] ? kthread_blkcg+0x31/0x31 [ 355.876592] ret_from_fork+0x1f/0x30 [ 355.876601] which indicates that the AAD IRQ handler is unexpectedly running when DA7219 is suspended, and as a result, is trying to read data from DA7219 over I2C and is hitting the I2C driver "Transfer while suspended" failure. However, with this patch the above failure is still reproducible. So this patch does not fix any real observed issue so far, but at least is useful for confirming that the above issue is not caused by a pending IRQ but rather looks like a DA7219 hardware issue with an IRQ unexpectedly generated after jack detection is already disabled. Signed-off-by: Dmytro Maluka Link: https://lore.kernel.org/r/20230717193737.161784-2-dmy@semihalf.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/da7219-aad.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c index bba73c44c219..49b1622e7bad 100644 --- a/sound/soc/codecs/da7219-aad.c +++ b/sound/soc/codecs/da7219-aad.c @@ -863,6 +863,8 @@ void da7219_aad_suspend(struct snd_soc_component *component) } } } + + synchronize_irq(da7219_aad->irq); } void da7219_aad_resume(struct snd_soc_component *component) From eb746c4750a893c2bf75d7548a8f6f40beeca74a Mon Sep 17 00:00:00 2001 From: Dmytro Maluka Date: Mon, 17 Jul 2023 21:37:37 +0200 Subject: [PATCH 0707/2093] ASoC: da7219: Check for failure reading AAD IRQ events [ Upstream commit f0691dc16206f21b13c464434366e2cd632b8ed7 ] When handling an AAD interrupt, if IRQ events read failed (for example, due to i2c "Transfer while suspended" failure, i.e. when attempting to read it while DA7219 is suspended, which may happen due to a spurious AAD interrupt), the events array contains garbage uninitialized values. So instead of trying to interprete those values and doing any actions based on them (potentially resulting in misbehavior, e.g. reporting bogus events), refuse to handle the interrupt. Signed-off-by: Dmytro Maluka Link: https://lore.kernel.org/r/20230717193737.161784-3-dmy@semihalf.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/da7219-aad.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c index 49b1622e7bad..9251490548e8 100644 --- a/sound/soc/codecs/da7219-aad.c +++ b/sound/soc/codecs/da7219-aad.c @@ -353,11 +353,15 @@ static irqreturn_t da7219_aad_irq_thread(int irq, void *data) struct da7219_priv *da7219 = snd_soc_component_get_drvdata(component); u8 events[DA7219_AAD_IRQ_REG_MAX]; u8 statusa; - int i, report = 0, mask = 0; + int i, ret, report = 0, mask = 0; /* Read current IRQ events */ - regmap_bulk_read(da7219->regmap, DA7219_ACCDET_IRQ_EVENT_A, - events, DA7219_AAD_IRQ_REG_MAX); + ret = regmap_bulk_read(da7219->regmap, DA7219_ACCDET_IRQ_EVENT_A, + events, DA7219_AAD_IRQ_REG_MAX); + if (ret) { + dev_warn_ratelimited(component->dev, "Failed to read IRQ events: %d\n", ret); + return IRQ_NONE; + } if (!events[DA7219_AAD_IRQ_REG_A] && !events[DA7219_AAD_IRQ_REG_B]) return IRQ_NONE; From 0f7b43a5776b0c8aa716a18d892fab2ad8f9f3ce Mon Sep 17 00:00:00 2001 From: Edson Juliano Drosdeck Date: Wed, 19 Jul 2023 17:02:41 -0300 Subject: [PATCH 0708/2093] ASoC: nau8821: Add DMI quirk mechanism for active-high jack-detect [ Upstream commit 1bc40efdaf4a0ccfdb10a1c8e4b458f4764e8e5f ] Add a quirk mechanism to allow specifying that active-high jack-detection should be used on platforms where this info is not available in devicetree. And add an entry for the Positivo CW14Q01P-V2 to the DMI table, so that jack-detection will work properly on this laptop. Signed-off-by: Edson Juliano Drosdeck Link: https://lore.kernel.org/r/20230719200241.4865-1-edson.drosdeck@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/nau8821.c | 41 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/sound/soc/codecs/nau8821.c b/sound/soc/codecs/nau8821.c index 4a72b94e8410..efd92656a060 100644 --- a/sound/soc/codecs/nau8821.c +++ b/sound/soc/codecs/nau8821.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -25,6 +26,13 @@ #include #include "nau8821.h" +#define NAU8821_JD_ACTIVE_HIGH BIT(0) + +static int nau8821_quirk; +static int quirk_override = -1; +module_param_named(quirk, quirk_override, uint, 0444); +MODULE_PARM_DESC(quirk, "Board-specific quirk override"); + #define NAU_FREF_MAX 13500000 #define NAU_FVCO_MAX 100000000 #define NAU_FVCO_MIN 90000000 @@ -1696,6 +1704,33 @@ static int nau8821_setup_irq(struct nau8821 *nau8821) return 0; } +/* Please keep this list alphabetically sorted */ +static const struct dmi_system_id nau8821_quirk_table[] = { + { + /* Positivo CW14Q01P-V2 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Positivo Tecnologia SA"), + DMI_MATCH(DMI_BOARD_NAME, "CW14Q01P-V2"), + }, + .driver_data = (void *)(NAU8821_JD_ACTIVE_HIGH), + }, + {} +}; + +static void nau8821_check_quirks(void) +{ + const struct dmi_system_id *dmi_id; + + if (quirk_override != -1) { + nau8821_quirk = quirk_override; + return; + } + + dmi_id = dmi_first_match(nau8821_quirk_table); + if (dmi_id) + nau8821_quirk = (unsigned long)dmi_id->driver_data; +} + static int nau8821_i2c_probe(struct i2c_client *i2c) { struct device *dev = &i2c->dev; @@ -1716,6 +1751,12 @@ static int nau8821_i2c_probe(struct i2c_client *i2c) nau8821->dev = dev; nau8821->irq = i2c->irq; + + nau8821_check_quirks(); + + if (nau8821_quirk & NAU8821_JD_ACTIVE_HIGH) + nau8821->jkdet_polarity = 0; + nau8821_print_device_properties(nau8821); nau8821_reset_chip(nau8821->regmap); From 328fcde050ffb85ffc34566531b4371f73c40e4e Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Thu, 20 Jul 2023 22:42:08 +0800 Subject: [PATCH 0709/2093] ethernet: atheros: fix return value check in atl1c_tso_csum() [ Upstream commit 8d01da0a1db237c44c92859ce3612df7af8d3a53 ] in atl1c_tso_csum, it should check the return value of pskb_trim(), and return an error code if an unexpected value is returned by pskb_trim(). Signed-off-by: Yuanjun Gong Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 40c781695d58..7762e532c6a4 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2104,8 +2104,11 @@ static int atl1c_tso_csum(struct atl1c_adapter *adapter, real_len = (((unsigned char *)ip_hdr(skb) - skb->data) + ntohs(ip_hdr(skb)->tot_len)); - if (real_len < skb->len) - pskb_trim(skb, real_len); + if (real_len < skb->len) { + err = pskb_trim(skb, real_len); + if (err) + return err; + } hdr_len = skb_tcp_all_headers(skb); if (unlikely(skb->len == hdr_len)) { From a41f2f6aff5e7d99111d28486a9b9af2c824dd9b Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 16 Jun 2023 17:36:10 +0200 Subject: [PATCH 0710/2093] m68k: Fix invalid .section syntax [ Upstream commit 922a9bd138101e3e5718f0f4d40dba68ef89bb43 ] gas supports several different forms for .section for ELF targets, including: .section NAME [, "FLAGS"[, @TYPE[,FLAG_SPECIFIC_ARGUMENTS]]] and: .section "NAME"[, #FLAGS...] In several places we use a mix of these two forms: .section NAME, #FLAGS... A current development snapshot of binutils (2.40.50.20230611) treats this mixed syntax as an error. Change to consistently use: .section NAME, "FLAGS" as is used elsewhere in the kernel. Link: https://buildd.debian.org/status/fetch.php?pkg=linux&arch=m68k&ver=6.4%7Erc6-1%7Eexp1&stamp=1686907300&raw=1 Signed-off-by: Ben Hutchings Tested-by: Jan-Benedict Glaw Link: https://lore.kernel.org/r/ZIyBaueWT9jnTwRC@decadent.org.uk Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/m68k/fpsp040/skeleton.S | 4 ++-- arch/m68k/ifpsp060/os.S | 4 ++-- arch/m68k/kernel/relocate_kernel.S | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/m68k/fpsp040/skeleton.S b/arch/m68k/fpsp040/skeleton.S index 439395aa6fb4..081922c72daa 100644 --- a/arch/m68k/fpsp040/skeleton.S +++ b/arch/m68k/fpsp040/skeleton.S @@ -499,13 +499,13 @@ in_ea: dbf %d0,morein rts - .section .fixup,#alloc,#execinstr + .section .fixup,"ax" .even 1: jbsr fpsp040_die jbra .Lnotkern - .section __ex_table,#alloc + .section __ex_table,"a" .align 4 .long in_ea,1b diff --git a/arch/m68k/ifpsp060/os.S b/arch/m68k/ifpsp060/os.S index 7a0d6e428066..89e2ec224ab6 100644 --- a/arch/m68k/ifpsp060/os.S +++ b/arch/m68k/ifpsp060/os.S @@ -379,11 +379,11 @@ _060_real_access: | Execption handling for movs access to illegal memory - .section .fixup,#alloc,#execinstr + .section .fixup,"ax" .even 1: moveq #-1,%d1 rts -.section __ex_table,#alloc +.section __ex_table,"a" .align 4 .long dmrbuae,1b .long dmrwuae,1b diff --git a/arch/m68k/kernel/relocate_kernel.S b/arch/m68k/kernel/relocate_kernel.S index ab0f1e7d4653..f7667079e08e 100644 --- a/arch/m68k/kernel/relocate_kernel.S +++ b/arch/m68k/kernel/relocate_kernel.S @@ -26,7 +26,7 @@ ENTRY(relocate_new_kernel) lea %pc@(.Lcopy),%a4 2: addl #0x00000000,%a4 /* virt_to_phys() */ - .section ".m68k_fixup","aw" + .section .m68k_fixup,"aw" .long M68K_FIXUP_MEMOFFSET, 2b+2 .previous @@ -49,7 +49,7 @@ ENTRY(relocate_new_kernel) lea %pc@(.Lcont040),%a4 5: addl #0x00000000,%a4 /* virt_to_phys() */ - .section ".m68k_fixup","aw" + .section .m68k_fixup,"aw" .long M68K_FIXUP_MEMOFFSET, 5b+2 .previous From d563f679a268b357a44a8d53ee5c15152e357dc5 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 21 Jul 2023 21:36:45 +0200 Subject: [PATCH 0711/2093] s390/dasd: use correct number of retries for ERP requests [ Upstream commit acea28a6b74f458defda7417d2217b051ba7d444 ] If a DASD request fails an error recovery procedure (ERP) request might be built as a copy of the original request to do error recovery. The ERP request gets a number of retries assigned. This number is always 256 no matter what other value might have been set for the original request. This is not what is expected when a user specifies a certain amount of retries for the device via sysfs. Correctly use the number of retries of the original request for ERP requests. Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20230721193647.3889634-3-sth@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/s390/block/dasd_3990_erp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index d030fe2e2964..91cb9d52a425 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -2441,7 +2441,7 @@ static struct dasd_ccw_req *dasd_3990_erp_add_erp(struct dasd_ccw_req *cqr) erp->block = cqr->block; erp->magic = cqr->magic; erp->expires = cqr->expires; - erp->retries = 256; + erp->retries = device->default_retries; erp->buildclk = get_tod_clock(); erp->status = DASD_CQR_FILLED; From d28f76be7952fb525b96d25b388dfd9c2d37faae Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 21 Jul 2023 21:36:46 +0200 Subject: [PATCH 0712/2093] s390/dasd: fix hanging device after request requeue [ Upstream commit 8a2278ce9c25048d999fe1a3561def75d963f471 ] The DASD device driver has a function to requeue requests to the blocklayer. This function is used in various cases when basic settings for the device have to be changed like High Performance Ficon related parameters or copy pair settings. The functions iterates over the device->ccw_queue and also removes the requests from the block->ccw_queue. In case the device is started on an alias device instead of the base device it might be removed from the block->ccw_queue without having it canceled properly before. This might lead to a hanging device since the request is no longer on a queue and can not be handled properly. Fix by iterating over the block->ccw_queue instead of the device->ccw_queue. This will take care of all blocklayer related requests and handle them on all associated DASD devices. Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20230721193647.3889634-4-sth@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/s390/block/dasd.c | 127 +++++++++++++++----------------------- 1 file changed, 49 insertions(+), 78 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index bce3422d8564..04d9b1d4b1ba 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2926,41 +2926,32 @@ static void _dasd_wake_block_flush_cb(struct dasd_ccw_req *cqr, void *data) * Requeue a request back to the block request queue * only works for block requests */ -static int _dasd_requeue_request(struct dasd_ccw_req *cqr) +static void _dasd_requeue_request(struct dasd_ccw_req *cqr) { - struct dasd_block *block = cqr->block; struct request *req; - if (!block) - return -EINVAL; /* * If the request is an ERP request there is nothing to requeue. * This will be done with the remaining original request. */ if (cqr->refers) - return 0; + return; spin_lock_irq(&cqr->dq->lock); req = (struct request *) cqr->callback_data; blk_mq_requeue_request(req, true); spin_unlock_irq(&cqr->dq->lock); - return 0; + return; } -/* - * Go through all request on the dasd_block request queue, cancel them - * on the respective dasd_device, and return them to the generic - * block layer. - */ -static int dasd_flush_block_queue(struct dasd_block *block) +static int _dasd_requests_to_flushqueue(struct dasd_block *block, + struct list_head *flush_queue) { struct dasd_ccw_req *cqr, *n; - int rc, i; - struct list_head flush_queue; unsigned long flags; + int rc, i; - INIT_LIST_HEAD(&flush_queue); - spin_lock_bh(&block->queue_lock); + spin_lock_irqsave(&block->queue_lock, flags); rc = 0; restart: list_for_each_entry_safe(cqr, n, &block->ccw_queue, blocklist) { @@ -2975,13 +2966,32 @@ static int dasd_flush_block_queue(struct dasd_block *block) * is returned from the dasd_device layer. */ cqr->callback = _dasd_wake_block_flush_cb; - for (i = 0; cqr != NULL; cqr = cqr->refers, i++) - list_move_tail(&cqr->blocklist, &flush_queue); + for (i = 0; cqr; cqr = cqr->refers, i++) + list_move_tail(&cqr->blocklist, flush_queue); if (i > 1) /* moved more than one request - need to restart */ goto restart; } - spin_unlock_bh(&block->queue_lock); + spin_unlock_irqrestore(&block->queue_lock, flags); + + return rc; +} + +/* + * Go through all request on the dasd_block request queue, cancel them + * on the respective dasd_device, and return them to the generic + * block layer. + */ +static int dasd_flush_block_queue(struct dasd_block *block) +{ + struct dasd_ccw_req *cqr, *n; + struct list_head flush_queue; + unsigned long flags; + int rc; + + INIT_LIST_HEAD(&flush_queue); + rc = _dasd_requests_to_flushqueue(block, &flush_queue); + /* Now call the callback function of flushed requests */ restart_cb: list_for_each_entry_safe(cqr, n, &flush_queue, blocklist) { @@ -3864,75 +3874,36 @@ EXPORT_SYMBOL_GPL(dasd_generic_space_avail); */ int dasd_generic_requeue_all_requests(struct dasd_device *device) { + struct dasd_block *block = device->block; struct list_head requeue_queue; struct dasd_ccw_req *cqr, *n; - struct dasd_ccw_req *refers; int rc; + if (!block) + return 0; + INIT_LIST_HEAD(&requeue_queue); - spin_lock_irq(get_ccwdev_lock(device->cdev)); - rc = 0; - list_for_each_entry_safe(cqr, n, &device->ccw_queue, devlist) { - /* Check status and move request to flush_queue */ - if (cqr->status == DASD_CQR_IN_IO) { - rc = device->discipline->term_IO(cqr); - if (rc) { - /* unable to terminate requeust */ - dev_err(&device->cdev->dev, - "Unable to terminate request %p " - "on suspend\n", cqr); - spin_unlock_irq(get_ccwdev_lock(device->cdev)); - dasd_put_device(device); - return rc; - } + rc = _dasd_requests_to_flushqueue(block, &requeue_queue); + + /* Now call the callback function of flushed requests */ +restart_cb: + list_for_each_entry_safe(cqr, n, &requeue_queue, blocklist) { + wait_event(dasd_flush_wq, (cqr->status < DASD_CQR_QUEUED)); + /* Process finished ERP request. */ + if (cqr->refers) { + spin_lock_bh(&block->queue_lock); + __dasd_process_erp(block->base, cqr); + spin_unlock_bh(&block->queue_lock); + /* restart list_for_xx loop since dasd_process_erp + * might remove multiple elements + */ + goto restart_cb; } - list_move_tail(&cqr->devlist, &requeue_queue); - } - spin_unlock_irq(get_ccwdev_lock(device->cdev)); - - list_for_each_entry_safe(cqr, n, &requeue_queue, devlist) { - wait_event(dasd_flush_wq, - (cqr->status != DASD_CQR_CLEAR_PENDING)); - - /* - * requeue requests to blocklayer will only work - * for block device requests - */ - if (_dasd_requeue_request(cqr)) - continue; - - /* remove requests from device and block queue */ - list_del_init(&cqr->devlist); - while (cqr->refers != NULL) { - refers = cqr->refers; - /* remove the request from the block queue */ - list_del(&cqr->blocklist); - /* free the finished erp request */ - dasd_free_erp_request(cqr, cqr->memdev); - cqr = refers; - } - - /* - * _dasd_requeue_request already checked for a valid - * blockdevice, no need to check again - * all erp requests (cqr->refers) have a cqr->block - * pointer copy from the original cqr - */ + _dasd_requeue_request(cqr); list_del_init(&cqr->blocklist); cqr->block->base->discipline->free_cp( cqr, (struct request *) cqr->callback_data); } - - /* - * if requests remain then they are internal request - * and go back to the device queue - */ - if (!list_empty(&requeue_queue)) { - /* move freeze_queue to start of the ccw_queue */ - spin_lock_irq(get_ccwdev_lock(device->cdev)); - list_splice_tail(&requeue_queue, &device->ccw_queue); - spin_unlock_irq(get_ccwdev_lock(device->cdev)); - } dasd_schedule_device_bh(device); return rc; } From 952af5cfd5b45ae4a8c9a211c82b66b1ef6c46ca Mon Sep 17 00:00:00 2001 From: Winston Wen Date: Mon, 24 Jul 2023 10:10:56 +0800 Subject: [PATCH 0713/2093] fs/nls: make load_nls() take a const parameter [ Upstream commit c1ed39ec116272935528ca9b348b8ee79b0791da ] load_nls() take a char * parameter, use it to find nls module in list or construct the module name to load it. This change make load_nls() take a const parameter, so we don't need do some cast like this: ses->local_nls = load_nls((char *)ctx->local_nls->charset); Suggested-by: Stephen Rothwell Signed-off-by: Winston Wen Reviewed-by: Paulo Alcantara Reviewed-by: Christian Brauner Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/nls/nls_base.c | 4 ++-- include/linux/nls.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index 52ccd34b1e79..a026dbd3593f 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -272,7 +272,7 @@ int unregister_nls(struct nls_table * nls) return -EINVAL; } -static struct nls_table *find_nls(char *charset) +static struct nls_table *find_nls(const char *charset) { struct nls_table *nls; spin_lock(&nls_lock); @@ -288,7 +288,7 @@ static struct nls_table *find_nls(char *charset) return nls; } -struct nls_table *load_nls(char *charset) +struct nls_table *load_nls(const char *charset) { return try_then_request_module(find_nls(charset), "nls_%s", charset); } diff --git a/include/linux/nls.h b/include/linux/nls.h index 499e486b3722..e0bf8367b274 100644 --- a/include/linux/nls.h +++ b/include/linux/nls.h @@ -47,7 +47,7 @@ enum utf16_endian { /* nls_base.c */ extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); -extern struct nls_table *load_nls(char *); +extern struct nls_table *load_nls(const char *charset); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); #define register_nls(nls) __register_nls((nls), THIS_MODULE) From 10999df817cbb6705ba13ffa243236fd9f27b043 Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Fri, 21 Jul 2023 17:06:43 +0800 Subject: [PATCH 0714/2093] ASoC: rt5682-sdw: fix for JD event handling in ClockStop Mode0 [ Upstream commit 02fb23d72720df2b6be3f29fc5787ca018eb92c3 ] When the system suspends, peripheral Imp-defined interrupt is disabled. When system level resume is invoked, the peripheral Imp-defined interrupts should be enabled to handle JD events. Signed-off-by: Shuming Fan Reported-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20230721090643.128213-1-shumingf@realtek.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt5682-sdw.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index c1a94229dc7e..868a61c8b060 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -786,8 +786,15 @@ static int __maybe_unused rt5682_dev_resume(struct device *dev) if (!rt5682->first_hw_init) return 0; - if (!slave->unattach_request) + if (!slave->unattach_request) { + if (rt5682->disable_irq == true) { + mutex_lock(&rt5682->disable_irq_lock); + sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); + rt5682->disable_irq = false; + mutex_unlock(&rt5682->disable_irq_lock); + } goto regmap_sync; + } time = wait_for_completion_timeout(&slave->initialization_complete, msecs_to_jiffies(RT5682_PROBE_TIMEOUT)); From 82e17577b66f4c0256bbdfe30f5c7df3fbcf2099 Mon Sep 17 00:00:00 2001 From: Edgar Date: Wed, 19 Jul 2023 13:47:22 +0800 Subject: [PATCH 0715/2093] ASoc: codecs: ES8316: Fix DMIC config [ Upstream commit d20d35d1ad62c6cca36368c1e8f29335a068659e ] According to the datasheet, the DMIC config should be changed to { 0, 2 ,3 } Signed-off-by: Edgar Link: https://lore.kernel.org/r/20230719054722.401954-1-ljijcj@163.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/es8316.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index 87775378362e..c4e4ab93fdb6 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -153,7 +153,7 @@ static const char * const es8316_dmic_txt[] = { "dmic data at high level", "dmic data at low level", }; -static const unsigned int es8316_dmic_values[] = { 0, 1, 2 }; +static const unsigned int es8316_dmic_values[] = { 0, 2, 3 }; static const struct soc_enum es8316_dmic_src_enum = SOC_VALUE_ENUM_SINGLE(ES8316_ADC_DMIC, 0, 3, ARRAY_SIZE(es8316_dmic_txt), From a1fbf45a24d37875e9b25635755c2e88a99b607e Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Fri, 21 Jul 2023 17:06:54 +0800 Subject: [PATCH 0716/2093] ASoC: rt711: fix for JD event handling in ClockStop Mode0 [ Upstream commit b69de265bd0e877015a00fbba453ef72af162e0f ] When the system suspends, peripheral Imp-defined interrupt is disabled. When system level resume is invoked, the peripheral Imp-defined interrupts should be enabled to handle JD events. Signed-off-by: Shuming Fan Reported-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20230721090654.128230-1-shumingf@realtek.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt711-sdw.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c index 4fe68bcf2a7c..9545b8a7eb19 100644 --- a/sound/soc/codecs/rt711-sdw.c +++ b/sound/soc/codecs/rt711-sdw.c @@ -541,8 +541,15 @@ static int __maybe_unused rt711_dev_resume(struct device *dev) if (!rt711->first_hw_init) return 0; - if (!slave->unattach_request) + if (!slave->unattach_request) { + if (rt711->disable_irq == true) { + mutex_lock(&rt711->disable_irq_lock); + sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); + rt711->disable_irq = false; + mutex_unlock(&rt711->disable_irq_lock); + } goto regmap_sync; + } time = wait_for_completion_timeout(&slave->initialization_complete, msecs_to_jiffies(RT711_PROBE_TIMEOUT)); From 2e780a9f4ac1591f8797d0ed6834c08a72749fc4 Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Fri, 21 Jul 2023 17:07:11 +0800 Subject: [PATCH 0717/2093] ASoC: rt711-sdca: fix for JD event handling in ClockStop Mode0 [ Upstream commit 23adeb7056acd4fd866969f4afb91441776cc4f5 ] When the system suspends, peripheral SDCA interrupts are disabled. When system level resume is invoked, the peripheral SDCA interrupts should be enabled to handle JD events. Enable SDCA interrupts in resume sequence when ClockStop Mode0 is applied. Signed-off-by: Shuming Fan Reported-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20230721090711.128247-1-shumingf@realtek.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt711-sdca-sdw.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index e23cec4c457d..487d3010ddc1 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -442,8 +442,16 @@ static int __maybe_unused rt711_sdca_dev_resume(struct device *dev) if (!rt711->first_hw_init) return 0; - if (!slave->unattach_request) + if (!slave->unattach_request) { + if (rt711->disable_irq == true) { + mutex_lock(&rt711->disable_irq_lock); + sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0); + sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8); + rt711->disable_irq = false; + mutex_unlock(&rt711->disable_irq_lock); + } goto regmap_sync; + } time = wait_for_completion_timeout(&slave->initialization_complete, msecs_to_jiffies(RT711_PROBE_TIMEOUT)); From 9c1263320163dd6ffad9242fff2a61294b6f3346 Mon Sep 17 00:00:00 2001 From: Guiting Shen Date: Sat, 15 Jul 2023 11:06:20 +0800 Subject: [PATCH 0718/2093] ASoC: atmel: Fix the 8K sample parameter in I2SC master [ Upstream commit f85739c0b2b0d98a32f5ca4fcc5501d2b76df4f6 ] The 8K sample parameter of 12.288Mhz main system bus clock doesn't work because the I2SC_MR.IMCKDIV must not be 0 according to the sama5d2 series datasheet(I2SC Mode Register of Register Summary). So use the 6.144Mhz instead of 12.288Mhz to support 8K sample. Signed-off-by: Guiting Shen Link: https://lore.kernel.org/r/20230715030620.62328-1-aarongt.shen@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/atmel/atmel-i2s.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/soc/atmel/atmel-i2s.c b/sound/soc/atmel/atmel-i2s.c index 425d66edbf86..5e43ff0b537a 100644 --- a/sound/soc/atmel/atmel-i2s.c +++ b/sound/soc/atmel/atmel-i2s.c @@ -163,11 +163,14 @@ struct atmel_i2s_gck_param { #define I2S_MCK_12M288 12288000UL #define I2S_MCK_11M2896 11289600UL +#define I2S_MCK_6M144 6144000UL /* mck = (32 * (imckfs+1) / (imckdiv+1)) * fs */ static const struct atmel_i2s_gck_param gck_params[] = { + /* mck = 6.144Mhz */ + { 8000, I2S_MCK_6M144, 1, 47}, /* mck = 768 fs */ + /* mck = 12.288MHz */ - { 8000, I2S_MCK_12M288, 0, 47}, /* mck = 1536 fs */ { 16000, I2S_MCK_12M288, 1, 47}, /* mck = 768 fs */ { 24000, I2S_MCK_12M288, 3, 63}, /* mck = 512 fs */ { 32000, I2S_MCK_12M288, 3, 47}, /* mck = 384 fs */ From eb54ad1ed620a0c88d2b8775cbb9054030099cfb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 25 Jul 2023 11:20:57 +0200 Subject: [PATCH 0719/2093] ALSA: usb-audio: Add quirk for Microsoft Modern Wireless Headset [ Upstream commit 3da435063777f8d861ba5a165344e3f75f839357 ] Microsoft Modern Wireless Headset (appearing on the host as "Microsoft USB Link") has a playback and a capture mixer volume/switch, but they are fairly broken. The descriptor reports wrong dB ranges for playback, and the capture volume/switch don't influence on the actual recording at all. Moreover, there seem instabilities in the connection, and at best, we should disable the runtime PM. So this ended up with a quirk entry for: - Correct the playback dB range; I picked up some reasonable values but it's a guess work - Disable the capture mixer; it's completely useless and confuses PA/PW - Suppress get-sample-rate, apply the delay for message handling, and suppress the auto-suspend The behavior of the wheel control on the headset is somehow flaky, too, but it's an issue of HID. Link: https://bugzilla.suse.com/show_bug.cgi?id=1207129 Link: https://lore.kernel.org/r/20230725092057.15115-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/mixer_maps.c | 14 ++++++++++++++ sound/usb/quirks.c | 3 +++ 2 files changed, 17 insertions(+) diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index f4bd1e8ae4b6..23260aa1919d 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -374,6 +374,15 @@ static const struct usbmix_name_map corsair_virtuoso_map[] = { { 0 } }; +/* Microsoft USB Link headset */ +/* a guess work: raw playback volume values are from 2 to 129 */ +static const struct usbmix_dB_map ms_usb_link_dB = { -3225, 0, true }; +static const struct usbmix_name_map ms_usb_link_map[] = { + { 9, NULL, .dB = &ms_usb_link_dB }, + { 10, NULL }, /* Headset Capture volume; seems non-working, disabled */ + { 0 } /* terminator */ +}; + /* ASUS ROG Zenith II with Realtek ALC1220-VB */ static const struct usbmix_name_map asus_zenith_ii_map[] = { { 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */ @@ -668,6 +677,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x1395, 0x0025), .map = sennheiser_pc8_map, }, + { + /* Microsoft USB Link headset */ + .id = USB_ID(0x045e, 0x083c), + .map = ms_usb_link_map, + }, { 0 } /* terminator */ }; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 6cf55b7f7a04..d4a7ffef8219 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2011,6 +2011,9 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x041e, 0x4080, /* Creative Live Cam VF0610 */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x045e, 0x083c, /* MS USB Link headset */ + QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_CTL_MSG_DELAY | + QUIRK_FLAG_DISABLE_AUTOSUSPEND), DEVICE_FLG(0x046d, 0x084c, /* Logitech ConferenceCam Connect */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x046d, 0x0991, /* Logitech QuickCam Pro */ From 7d0f7924ef610224c1588c8391d2b24aab64ccb3 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Jul 2023 20:15:16 +0200 Subject: [PATCH 0720/2093] platform/x86: intel: hid: Always call BTNL ACPI method [ Upstream commit e3ab18de2b09361d6f0e4aafb9cfd6d002ce43a1 ] On a HP Elite Dragonfly G2 the 0xcc and 0xcd events for SW_TABLET_MODE are only send after the BTNL ACPI method has been called. Likely more devices need this, so make the BTNL ACPI method unconditional instead of only doing it on devices with a 5 button array. Note this also makes the intel_button_array_enable() call in probe() unconditional, that function does its own priv->array check. This makes the intel_button_array_enable() call in probe() consistent with the calls done on suspend/resume which also rely on the priv->array check inside the function. Reported-by: Maxim Mikityanskiy Closes: https://lore.kernel.org/platform-driver-x86/20230712175023.31651-1-maxtram95@gmail.com/ Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230715181516.5173-1-hdegoede@redhat.com Signed-off-by: Sasha Levin --- drivers/platform/x86/intel/hid.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index b6313ecd190c..df533b277b99 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -601,7 +601,7 @@ static bool button_array_present(struct platform_device *device) static int intel_hid_probe(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); - unsigned long long mode; + unsigned long long mode, dummy; struct intel_hid_priv *priv; acpi_status status; int err; @@ -666,18 +666,15 @@ static int intel_hid_probe(struct platform_device *device) if (err) goto err_remove_notify; - if (priv->array) { - unsigned long long dummy; + intel_button_array_enable(&device->dev, true); - intel_button_array_enable(&device->dev, true); - - /* Call button load method to enable HID power button */ - if (!intel_hid_evaluate_method(handle, INTEL_HID_DSM_BTNL_FN, - &dummy)) { - dev_warn(&device->dev, - "failed to enable HID power button\n"); - } - } + /* + * Call button load method to enable HID power button + * Always do this since it activates events on some devices without + * a button array too. + */ + if (!intel_hid_evaluate_method(handle, INTEL_HID_DSM_BTNL_FN, &dummy)) + dev_warn(&device->dev, "failed to enable HID power button\n"); device_init_wakeup(&device->dev, true); /* From dea41980d793e04b92109f6af4c0a1069dae0a90 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Sun, 16 Jul 2023 21:32:13 +0300 Subject: [PATCH 0721/2093] platform/x86/intel/hid: Add HP Dragonfly G2 to VGBS DMI quirks [ Upstream commit 7783e97f8558ad7a4d1748922461bc88483fbcdf ] HP Elite Dragonfly G2 (a convertible laptop/tablet) has a reliable VGBS method. If VGBS is not called on boot, the firmware sends an initial 0xcd event shortly after calling the BTNL method, but only if the device is booted in the laptop mode. However, if the device is booted in the tablet mode and VGBS is not called, there is no initial 0xcc event, and the input device for SW_TABLET_MODE is not registered up until the user turns the device into the laptop mode. Call VGBS on boot on this device to get the initial state of SW_TABLET_MODE in a reliable way. Tested with BIOS 1.13.1. Signed-off-by: Maxim Mikityanskiy Link: https://lore.kernel.org/r/20230716183213.64173-1-maxtram95@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel/hid.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index df533b277b99..b96ef0eb82af 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -131,6 +131,12 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite Dragonfly G2 Notebook PC"), + }, + }, { } }; From aeee50c1529175a494bc7db72a29d7253376ae45 Mon Sep 17 00:00:00 2001 From: Wang Ming Date: Mon, 17 Jul 2023 18:11:02 +0800 Subject: [PATCH 0722/2093] platform/x86: think-lmi: Use kfree_sensitive instead of kfree [ Upstream commit 1da0893aed2e48e2bdf37c29b029f2e060d25927 ] key might contain private part of the key, so better use kfree_sensitive to free it. Signed-off-by: Wang Ming Link: https://lore.kernel.org/r/20230717101114.18966-1-machel@vivo.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/think-lmi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 3cbb92b6c521..f6290221d139 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -719,12 +719,12 @@ static ssize_t cert_to_password_store(struct kobject *kobj, /* Format: 'Password,Signature' */ auth_str = kasprintf(GFP_KERNEL, "%s,%s", passwd, setting->signature); if (!auth_str) { - kfree(passwd); + kfree_sensitive(passwd); return -ENOMEM; } ret = tlmi_simple_call(LENOVO_CERT_TO_PASSWORD_GUID, auth_str); kfree(auth_str); - kfree(passwd); + kfree_sensitive(passwd); return ret ?: count; } From 5c5628287bacb30300b1c3a51b8bf796539e8ba9 Mon Sep 17 00:00:00 2001 From: Kristian Angelov Date: Thu, 20 Jul 2023 18:29:50 +0300 Subject: [PATCH 0723/2093] platform/x86: asus-wmi: Fix setting RGB mode on some TUF laptops [ Upstream commit 6a758a3e831ce1a84c9c209ac6dc755f4c8ce77a ] This patch fixes setting the cmd values to 0xb3 and 0xb4. This is necessary on some TUF laptops in order to set the RGB mode. Closes: https://lore.kernel.org/platform-driver-x86/443078148.491022.1677576298133@nm83.abv.bg Signed-off-by: Kristian Angelov Reviewed-by: Luke D. Jones Link: https://lore.kernel.org/r/ZLlS7o6UdTUBkyqa@wyvern.localdomain Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/asus-wmi.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 02bf28692418..36effe04c6f3 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -738,13 +738,23 @@ static ssize_t kbd_rgb_mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - u32 cmd, mode, r, g, b, speed; + u32 cmd, mode, r, g, b, speed; int err; if (sscanf(buf, "%d %d %d %d %d %d", &cmd, &mode, &r, &g, &b, &speed) != 6) return -EINVAL; - cmd = !!cmd; + /* B3 is set and B4 is save to BIOS */ + switch (cmd) { + case 0: + cmd = 0xb3; + break; + case 1: + cmd = 0xb4; + break; + default: + return -EINVAL; + } /* These are the known usable modes across all TUF/ROG */ if (mode >= 12 || mode == 9) From 7c2d13fb9bab50a8aaf5fe46215586deb538e69b Mon Sep 17 00:00:00 2001 From: Konstantin Shelekhin Date: Sat, 22 Jul 2023 18:59:20 +0300 Subject: [PATCH 0724/2093] platform/x86: huawei-wmi: Silence ambient light sensor [ Upstream commit c21733754cd6ecbca346f2adf9b17d4cfa50504f ] Currently huawei-wmi causes a lot of spam in dmesg on my Huawei MateBook X Pro 2022: ... [36409.328463] input input9: Unknown key pressed, code: 0x02c1 [36411.335104] input input9: Unknown key pressed, code: 0x02c1 [36412.338674] input input9: Unknown key pressed, code: 0x02c1 [36414.848564] input input9: Unknown key pressed, code: 0x02c1 [36416.858706] input input9: Unknown key pressed, code: 0x02c1 ... Fix that by ignoring events generated by ambient light sensor. This issue was reported on GitHub and resolved with the following merge request: https://github.com/aymanbagabas/Huawei-WMI/pull/70 I've contacted the mainter of this repo and he gave me the "go ahead" to send this patch to the maling list. Signed-off-by: Konstantin Shelekhin Link: https://lore.kernel.org/r/20230722155922.173856-1-k.shelekhin@ftml.net Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/huawei-wmi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/x86/huawei-wmi.c b/drivers/platform/x86/huawei-wmi.c index b85050e4a0d6..ae5daecff177 100644 --- a/drivers/platform/x86/huawei-wmi.c +++ b/drivers/platform/x86/huawei-wmi.c @@ -86,6 +86,8 @@ static const struct key_entry huawei_wmi_keymap[] = { { KE_IGNORE, 0x293, { KEY_KBDILLUMTOGGLE } }, { KE_IGNORE, 0x294, { KEY_KBDILLUMUP } }, { KE_IGNORE, 0x295, { KEY_KBDILLUMUP } }, + // Ignore Ambient Light Sensoring + { KE_KEY, 0x2c1, { KEY_RESERVED } }, { KE_END, 0 } }; From d7b1aa3e209841834965541988154c296196a808 Mon Sep 17 00:00:00 2001 From: Jane Jian Date: Thu, 20 Jul 2023 18:08:07 +0800 Subject: [PATCH 0725/2093] drm/amd/smu: use AverageGfxclkFrequency* to replace previous GFX Curr Clock [ Upstream commit 4a37c55b859a69f429bfa7fab4fc43ee470b60ed ] Report current GFX clock also from average clock value as the original CurrClock data is not valid/accurate any more as per FW team Signed-off-by: Jane Jian Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index f7ac488a3da2..503e844baede 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -1305,7 +1305,7 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_vclk1_frequency = metrics->AverageVclk1Frequency; gpu_metrics->average_dclk1_frequency = metrics->AverageDclk1Frequency; - gpu_metrics->current_gfxclk = metrics->CurrClock[PPCLK_GFXCLK]; + gpu_metrics->current_gfxclk = gpu_metrics->average_gfxclk_frequency; gpu_metrics->current_socclk = metrics->CurrClock[PPCLK_SOCCLK]; gpu_metrics->current_uclk = metrics->CurrClock[PPCLK_UCLK]; gpu_metrics->current_vclk0 = metrics->CurrClock[PPCLK_VCLK_0]; From faa77cf5f28f4bbfbbb00f7e0caa2c8561f7dfe0 Mon Sep 17 00:00:00 2001 From: George Shen Date: Tue, 11 Jul 2023 13:22:36 -0400 Subject: [PATCH 0726/2093] drm/amd/display: Guard DCN31 PHYD32CLK logic against chip family [ Upstream commit 25b054c3c89cb6a7106a7982f0f70e83d0797dab ] [Why] Current yellow carp B0 PHYD32CLK logic is incorrectly applied to other ASICs. [How] Add guard to check chip family is yellow carp before applying logic. Reviewed-by: Hansen Dsouza Acked-by: Alex Hung Signed-off-by: George Shen Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c index cef32a1f91cd..b735e548e26d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c @@ -84,7 +84,8 @@ static enum phyd32clk_clock_source get_phy_mux_symclk( struct dcn_dccg *dccg_dcn, enum phyd32clk_clock_source src) { - if (dccg_dcn->base.ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) { + if (dccg_dcn->base.ctx->asic_id.chip_family == FAMILY_YELLOW_CARP && + dccg_dcn->base.ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) { if (src == PHYD32CLKC) src = PHYD32CLKF; if (src == PHYD32CLKD) From ae1cb9656ef4c7aa366d1201d366866bc0989df7 Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Wed, 12 Jul 2023 16:50:15 -0400 Subject: [PATCH 0727/2093] drm/amd/display: Exit idle optimizations before attempt to access PHY [ Upstream commit de612738e9771bd66aeb20044486c457c512f684 ] [Why & How] DMUB may hang when powering down pixel clocks due to no dprefclk. It is fixed by exiting idle optimization before the attempt to access PHY. Reviewed-by: Nicholas Kazlauskas Acked-by: Alex Hung Signed-off-by: Leo Chen Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index d260eaa1509e..9378c98d02cf 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1813,10 +1813,13 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) hws->funcs.edp_backlight_control(edp_link_with_sink, false); } /*resume from S3, no vbios posting, no need to power down again*/ + clk_mgr_exit_optimized_pwr_state(dc, dc->clk_mgr); + power_down_all_hw_blocks(dc); disable_vga_and_power_gate_all_controllers(dc); if (edp_link_with_sink && !keep_edp_vdd_on) dc->hwss.edp_power_control(edp_link_with_sink, false); + clk_mgr_optimize_pwr_state(dc, dc->clk_mgr); } bios_set_scratch_acc_mode_change(dc->ctx->dc_bios, 1); } From fbf4048d8fba044b4601792bf747dc14fbebe66d Mon Sep 17 00:00:00 2001 From: Eric Snowberg Date: Tue, 25 Jul 2023 17:56:46 -0400 Subject: [PATCH 0728/2093] ovl: Always reevaluate the file signature for IMA [ Upstream commit 18b44bc5a67275641fb26f2c54ba7eef80ac5950 ] Commit db1d1e8b9867 ("IMA: use vfs_getattr_nosec to get the i_version") partially closed an IMA integrity issue when directly modifying a file on the lower filesystem. If the overlay file is first opened by a user and later the lower backing file is modified by root, but the extended attribute is NOT updated, the signature validation succeeds with the old original signature. Update the super_block s_iflags to SB_I_IMA_UNVERIFIABLE_SIGNATURE to force signature reevaluation on every file access until a fine grained solution can be found. Signed-off-by: Eric Snowberg Signed-off-by: Mimi Zohar Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/overlayfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 51eec4a8e82b..08d3a1f34ac6 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -2155,7 +2155,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) ovl_trusted_xattr_handlers; sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; - sb->s_iflags |= SB_I_SKIP_SYNC; + sb->s_iflags |= SB_I_SKIP_SYNC | SB_I_IMA_UNVERIFIABLE_SIGNATURE; err = -ENOMEM; root_dentry = ovl_get_root(sb, upperpath.dentry, oe); From d676d02be8e2abcc6adfebcf99655975cbfaa7eb Mon Sep 17 00:00:00 2001 From: Minjie Du Date: Tue, 25 Jul 2023 11:06:25 +0800 Subject: [PATCH 0729/2093] ata: pata_arasan_cf: Use dev_err_probe() instead dev_err() in data_xfer() [ Upstream commit 4139f992c49356391fb086c0c8ce51f66c26d623 ] It is possible for dma_request_chan() to return EPROBE_DEFER, which means acdev->host->dev is not ready yet. At this point dev_err() will have no output. Use dev_err_probe() instead. Signed-off-by: Minjie Du Acked-by: Viresh Kumar Reviewed-by: Sergey Shtylyov Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- drivers/ata/pata_arasan_cf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c index e89617ed9175..46588fc82943 100644 --- a/drivers/ata/pata_arasan_cf.c +++ b/drivers/ata/pata_arasan_cf.c @@ -529,7 +529,8 @@ static void data_xfer(struct work_struct *work) /* dma_request_channel may sleep, so calling from process context */ acdev->dma_chan = dma_request_chan(acdev->host->dev, "data"); if (IS_ERR(acdev->dma_chan)) { - dev_err(acdev->host->dev, "Unable to get dma_chan\n"); + dev_err_probe(acdev->host->dev, PTR_ERR(acdev->dma_chan), + "Unable to get dma_chan\n"); acdev->dma_chan = NULL; goto chan_request_fail; } From 55954eea708f3a73b72ad17b94c1b7eb5c802f90 Mon Sep 17 00:00:00 2001 From: Jussi Laako Date: Wed, 26 Jul 2023 19:56:45 +0300 Subject: [PATCH 0730/2093] ALSA: usb-audio: Update for native DSD support quirks [ Upstream commit f7fea075edfa085c25eb34c44ceacf3602537f98 ] Maintenance patch for native DSD support. Remove incorrect T+A device quirks. Move set of device quirks to vendor quirks. Add set of missing device and vendor quirks. Signed-off-by: Jussi Laako Link: https://lore.kernel.org/r/20230726165645.404311-1-jussi@sonarnerd.net Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/quirks.c | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index d4a7ffef8219..4667d543f748 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1874,8 +1874,10 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, /* XMOS based USB DACs */ switch (chip->usb_id) { - case USB_ID(0x1511, 0x0037): /* AURALiC VEGA */ - case USB_ID(0x21ed, 0xd75a): /* Accuphase DAC-60 option card */ + case USB_ID(0x139f, 0x5504): /* Nagra DAC */ + case USB_ID(0x20b1, 0x3089): /* Mola-Mola DAC */ + case USB_ID(0x2522, 0x0007): /* LH Labs Geek Out 1V5 */ + case USB_ID(0x2522, 0x0009): /* LH Labs Geek Pulse X Inifinity 2V0 */ case USB_ID(0x2522, 0x0012): /* LH Labs VI DAC Infinity */ case USB_ID(0x2772, 0x0230): /* Pro-Ject Pre Box S2 Digital */ if (fp->altsetting == 2) @@ -1885,14 +1887,18 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */ case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */ case USB_ID(0x16d0, 0x06b2): /* NuPrime DAC-10 */ - case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */ + case USB_ID(0x16d0, 0x06b4): /* NuPrime Audio HD-AVP/AVA */ case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */ + case USB_ID(0x16d0, 0x09d8): /* NuPrime IDA-8 */ case USB_ID(0x16d0, 0x09db): /* NuPrime Audio DAC-9 */ + case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */ case USB_ID(0x1db5, 0x0003): /* Bryston BDA3 */ + case USB_ID(0x20a0, 0x4143): /* WaveIO USB Audio 2.0 */ case USB_ID(0x22e1, 0xca01): /* HDTA Serenade DSD */ case USB_ID(0x249c, 0x9326): /* M2Tech Young MkIII */ case USB_ID(0x2616, 0x0106): /* PS Audio NuWave DAC */ case USB_ID(0x2622, 0x0041): /* Audiolab M-DAC+ */ + case USB_ID(0x278b, 0x5100): /* Rotel RC-1590 */ case USB_ID(0x27f7, 0x3002): /* W4S DAC-2v2SE */ case USB_ID(0x29a2, 0x0086): /* Mutec MC3+ USB */ case USB_ID(0x6b42, 0x0042): /* MSB Technology */ @@ -1902,9 +1908,6 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, /* Amanero Combo384 USB based DACs with native DSD support */ case USB_ID(0x16d0, 0x071a): /* Amanero - Combo384 */ - case USB_ID(0x2ab6, 0x0004): /* T+A DAC8DSD-V2.0, MP1000E-V2.0, MP2000R-V2.0, MP2500R-V2.0, MP3100HV-V2.0 */ - case USB_ID(0x2ab6, 0x0005): /* T+A USB HD Audio 1 */ - case USB_ID(0x2ab6, 0x0006): /* T+A USB HD Audio 2 */ if (fp->altsetting == 2) { switch (le16_to_cpu(chip->dev->descriptor.bcdDevice)) { case 0x199: @@ -2049,6 +2052,9 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x0644, 0x805f, /* TEAC Model 12 */ QUIRK_FLAG_FORCE_IFACE_RESET), + DEVICE_FLG(0x0644, 0x806b, /* TEAC UD-701 */ + QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY | + QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x06f8, 0xb000, /* Hercules DJ Console (Windows Edition) */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */ @@ -2087,6 +2093,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x154e, 0x3006, /* Marantz SA-14S1 */ QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), + DEVICE_FLG(0x154e, 0x300b, /* Marantz SA-KI RUBY / SA-12 */ + QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x154e, 0x500e, /* Denon DN-X1600 */ QUIRK_FLAG_IGNORE_CLOCK_SOURCE), DEVICE_FLG(0x1686, 0x00dd, /* Zoom R16/24 */ @@ -2131,6 +2139,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x21b4, 0x0081, /* AudioQuest DragonFly */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x21b4, 0x0230, /* Ayre QB-9 Twenty */ + QUIRK_FLAG_DSD_RAW), + DEVICE_FLG(0x21b4, 0x0232, /* Ayre QX-5 Twenty */ + QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2522, 0x0007, /* LH Labs Geek Out HD Audio 1V5 */ QUIRK_FLAG_SET_IFACE_FIRST), DEVICE_FLG(0x2708, 0x0002, /* Audient iD14 */ @@ -2173,12 +2185,18 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_VALIDATE_RATES), VENDOR_FLG(0x1235, /* Focusrite Novation */ QUIRK_FLAG_VALIDATE_RATES), + VENDOR_FLG(0x1511, /* AURALiC */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x152a, /* Thesycon devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x18d1, /* iBasso devices */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x1de7, /* Phoenix Audio */ QUIRK_FLAG_GET_SAMPLE_RATE), VENDOR_FLG(0x20b1, /* XMOS based devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x21ed, /* Accuphase Laboratory */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x22d9, /* Oppo */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x23ba, /* Playback Design */ @@ -2194,10 +2212,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x2ab6, /* T+A devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x2d87, /* Cayin device */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x3336, /* HEM devices */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x3353, /* Khadas devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x35f4, /* MSB Technology */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x3842, /* EVGA */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0xc502, /* HiBy devices */ From 0ffed24af577cc942e4c546b167b5cf7ab3fff9e Mon Sep 17 00:00:00 2001 From: Raphael Gallais-Pou Date: Tue, 18 Jul 2023 19:20:24 +0200 Subject: [PATCH 0731/2093] staging: fbtft: ili9341: use macro FBTFT_REGISTER_SPI_DRIVER [ Upstream commit 4912649e1cf0317bf563f91655e04a303cacaf8d ] Using FBTFT_REGISTER_DRIVER resolves to a NULL struct spi_device_id. This ultimately causes a warning when the module probes. Fixes it. Signed-off-by: Raphael Gallais-Pou Link: https://lore.kernel.org/r/20230718172024.67488-1-rgallaispou@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/fbtft/fb_ili9341.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/fbtft/fb_ili9341.c b/drivers/staging/fbtft/fb_ili9341.c index 9ccd0823c3ab..47e72b87d76d 100644 --- a/drivers/staging/fbtft/fb_ili9341.c +++ b/drivers/staging/fbtft/fb_ili9341.c @@ -145,7 +145,7 @@ static struct fbtft_display display = { }, }; -FBTFT_REGISTER_DRIVER(DRVNAME, "ilitek,ili9341", &display); +FBTFT_REGISTER_SPI_DRIVER(DRVNAME, "ilitek", "ili9341", &display); MODULE_ALIAS("spi:" DRVNAME); MODULE_ALIAS("platform:" DRVNAME); From 896e9e57784cc48b9869d0574bd2c2be6cc1eaa8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20G=C3=B6ttsche?= Date: Thu, 11 May 2023 14:32:52 +0200 Subject: [PATCH 0732/2093] security: keys: perform capable check only on privileged operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2d7f105edbb3b2be5ffa4d833abbf9b6965e9ce7 ] If the current task fails the check for the queried capability via `capable(CAP_SYS_ADMIN)` LSMs like SELinux generate a denial message. Issuing such denial messages unnecessarily can lead to a policy author granting more privileges to a subject than needed to silence them. Reorder CAP_SYS_ADMIN checks after the check whether the operation is actually privileged. Signed-off-by: Christian Göttsche Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- security/keys/keyctl.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index d54f73c558f7..19be69fa4d05 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -980,14 +980,19 @@ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group) ret = -EACCES; down_write(&key->sem); - if (!capable(CAP_SYS_ADMIN)) { + { + bool is_privileged_op = false; + /* only the sysadmin can chown a key to some other UID */ if (user != (uid_t) -1 && !uid_eq(key->uid, uid)) - goto error_put; + is_privileged_op = true; /* only the sysadmin can set the key's GID to a group other * than one of those that the current process subscribes to */ if (group != (gid_t) -1 && !gid_eq(gid, key->gid) && !in_group_p(gid)) + is_privileged_op = true; + + if (is_privileged_op && !capable(CAP_SYS_ADMIN)) goto error_put; } @@ -1088,7 +1093,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm) down_write(&key->sem); /* if we're not the sysadmin, we can only change a key that we own */ - if (capable(CAP_SYS_ADMIN) || uid_eq(key->uid, current_fsuid())) { + if (uid_eq(key->uid, current_fsuid()) || capable(CAP_SYS_ADMIN)) { key->perm = perm; notify_key(key, NOTIFY_KEY_SETATTR, 0); ret = 0; From 473a55cfc1318045d0c19530566d4a739106bc6e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 11 Jul 2023 10:50:47 +0900 Subject: [PATCH 0733/2093] kprobes: Prohibit probing on CFI preamble symbol [ Upstream commit de02f2ac5d8cfb311f44f2bf144cc20002f1fbbd ] Do not allow to probe on "__cfi_" or "__pfx_" started symbol, because those are used for CFI and not executed. Probing it will break the CFI. Link: https://lore.kernel.org/all/168904024679.116016.18089228029322008512.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/kprobes.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 00e177de91cc..3da9726232ff 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1545,6 +1545,17 @@ static int check_ftrace_location(struct kprobe *p) return 0; } +static bool is_cfi_preamble_symbol(unsigned long addr) +{ + char symbuf[KSYM_NAME_LEN]; + + if (lookup_symbol_name(addr, symbuf)) + return false; + + return str_has_prefix("__cfi_", symbuf) || + str_has_prefix("__pfx_", symbuf); +} + static int check_kprobe_address_safe(struct kprobe *p, struct module **probed_mod) { @@ -1563,7 +1574,8 @@ static int check_kprobe_address_safe(struct kprobe *p, within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || - find_bug((unsigned long)p->addr)) { + find_bug((unsigned long)p->addr) || + is_cfi_preamble_symbol((unsigned long)p->addr)) { ret = -EINVAL; goto out; } From 98f933716a52282a2c46edf0e4bef1966820065e Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Fri, 7 Jul 2023 21:58:51 +0800 Subject: [PATCH 0734/2093] clk: fixed-mmio: make COMMON_CLK_FIXED_MMIO depend on HAS_IOMEM [ Upstream commit e7dd44f4f3166db45248414f5df8f615392de47a ] On s390 systems (aka mainframes), it has classic channel devices for networking and permanent storage that are currently even more common than PCI devices. Hence it could have a fully functional s390 kernel with CONFIG_PCI=n, then the relevant iomem mapping functions [including ioremap(), devm_ioremap(), etc.] are not available. Here let COMMON_CLK_FIXED_MMIO depend on HAS_IOMEM so that it won't be built to cause below compiling error if PCI is unset: ------ ld: drivers/clk/clk-fixed-mmio.o: in function `fixed_mmio_clk_setup': clk-fixed-mmio.c:(.text+0x5e): undefined reference to `of_iomap' ld: clk-fixed-mmio.c:(.text+0xba): undefined reference to `iounmap' ------ Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306211329.ticOJCSv-lkp@intel.com/ Signed-off-by: Baoquan He Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/r/20230707135852.24292-8-bhe@redhat.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 5da82f2bdd21..a5dcc7293a83 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -427,6 +427,7 @@ config COMMON_CLK_BD718XX config COMMON_CLK_FIXED_MMIO bool "Clock driver for Memory Mapped Fixed values" depends on COMMON_CLK && OF + depends on HAS_IOMEM help Support for Memory Mapped IO Fixed clocks From 51edd7383b1e039dbfcde4124e3eb53ea05e0c2d Mon Sep 17 00:00:00 2001 From: Ani Sinha Date: Wed, 5 Jul 2023 19:14:07 +0530 Subject: [PATCH 0735/2093] vmbus_testing: fix wrong python syntax for integer value comparison [ Upstream commit ed0cf84e9cc42e6310961c87709621f1825c2bb8 ] It is incorrect in python to compare integer values using the "is" keyword. The "is" keyword in python is used to compare references to two objects, not their values. Newer version of python3 (version 3.8) throws a warning when such incorrect comparison is made. For value comparison, "==" should be used. Fix this in the code and suppress the following warning: /usr/sbin/vmbus_testing:167: SyntaxWarning: "is" with a literal. Did you mean "=="? Signed-off-by: Ani Sinha Link: https://lore.kernel.org/r/20230705134408.6302-1-anisinha@redhat.com Signed-off-by: Wei Liu Signed-off-by: Sasha Levin --- tools/hv/vmbus_testing | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/hv/vmbus_testing b/tools/hv/vmbus_testing index e7212903dd1d..4467979d8f69 100755 --- a/tools/hv/vmbus_testing +++ b/tools/hv/vmbus_testing @@ -164,7 +164,7 @@ def recursive_file_lookup(path, file_map): def get_all_devices_test_status(file_map): for device in file_map: - if (get_test_state(locate_state(device, file_map)) is 1): + if (get_test_state(locate_state(device, file_map)) == 1): print("Testing = ON for: {}" .format(device.split("/")[5])) else: @@ -203,7 +203,7 @@ def write_test_files(path, value): def set_test_state(state_path, state_value, quiet): write_test_files(state_path, state_value) - if (get_test_state(state_path) is 1): + if (get_test_state(state_path) == 1): if (not quiet): print("Testing = ON for device: {}" .format(state_path.split("/")[5])) From 848477e08391d4604abcf428fdd6fa0aaaa20089 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Mon, 24 Jul 2023 13:08:23 +0300 Subject: [PATCH 0736/2093] Revert "wifi: ath6k: silence false positive -Wno-dangling-pointer warning on GCC 12" [ Upstream commit a1ce186db7f0e449f35d12fb55ae0da2a1b400e2 ] This reverts commit bd1d129daa3ede265a880e2c6a7f91eab0f4dc62. The dangling-pointer warnings were disabled kernel-wide by commit 49beadbd47c2 ("gcc-12: disable '-Wdangling-pointer' warning for now") for v5.19. So this hack in ath6kl is not needed anymore. Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230724100823.2948804-1-kvalo@kernel.org Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath6kl/Makefile | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/wireless/ath/ath6kl/Makefile b/drivers/net/wireless/ath/ath6kl/Makefile index a75bfa9fd1cf..dc2b3b46781e 100644 --- a/drivers/net/wireless/ath/ath6kl/Makefile +++ b/drivers/net/wireless/ath/ath6kl/Makefile @@ -36,11 +36,6 @@ ath6kl_core-y += wmi.o ath6kl_core-y += core.o ath6kl_core-y += recovery.o -# FIXME: temporarily silence -Wdangling-pointer on non W=1+ builds -ifndef KBUILD_EXTRA_WARN -CFLAGS_htc_mbox.o += $(call cc-disable-warning, dangling-pointer) -endif - ath6kl_core-$(CONFIG_NL80211_TESTMODE) += testmode.o ath6kl_core-$(CONFIG_ATH6KL_TRACING) += trace.o From 94515e9aa84c0458c8825ca661b61381146ba599 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Thu, 27 Jul 2023 10:13:42 +0200 Subject: [PATCH 0737/2093] net: dsa: microchip: KSZ9477 register regmap alignment to 32 bit boundaries [ Upstream commit 8d7ae22ae9f8c8a4407f8e993df64440bdbd0cee ] The commit (SHA1: 5c844d57aa7894154e49cf2fc648bfe2f1aefc1c) provided code to apply "Module 6: Certain PHY registers must be written as pairs instead of singly" errata for KSZ9477 as this chip for certain PHY registers (0xN120 to 0xN13F, N=1,2,3,4,5) must be accesses as 32 bit words instead of 16 or 8 bit access. Otherwise, adjacent registers (no matter if reserved or not) are overwritten with 0x0. Without this patch some registers (e.g. 0x113c or 0x1134) required for 32 bit access are out of valid regmap ranges. As a result, following error is observed and KSZ9477 is not properly configured: ksz-switch spi1.0: can't rmw 32bit reg 0x113c: -EIO ksz-switch spi1.0: can't rmw 32bit reg 0x1134: -EIO ksz-switch spi1.0 lan1 (uninitialized): failed to connect to PHY: -EIO ksz-switch spi1.0 lan1 (uninitialized): error -5 setting up PHY for tree 0, switch 0, port 0 The solution is to modify regmap_reg_range to allow accesses with 4 bytes boundaries. Signed-off-by: Lukasz Majewski Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/microchip/ksz_common.c | 35 +++++++++++--------------- 1 file changed, 15 insertions(+), 20 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8c492d56d2c3..dc9eea3c8ab1 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -590,10 +590,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x1030, 0x1030), regmap_reg_range(0x1100, 0x1115), regmap_reg_range(0x111a, 0x111f), - regmap_reg_range(0x1122, 0x1127), - regmap_reg_range(0x112a, 0x112b), - regmap_reg_range(0x1136, 0x1139), - regmap_reg_range(0x113e, 0x113f), + regmap_reg_range(0x1120, 0x112b), + regmap_reg_range(0x1134, 0x113b), + regmap_reg_range(0x113c, 0x113f), regmap_reg_range(0x1400, 0x1401), regmap_reg_range(0x1403, 0x1403), regmap_reg_range(0x1410, 0x1417), @@ -624,10 +623,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x2030, 0x2030), regmap_reg_range(0x2100, 0x2115), regmap_reg_range(0x211a, 0x211f), - regmap_reg_range(0x2122, 0x2127), - regmap_reg_range(0x212a, 0x212b), - regmap_reg_range(0x2136, 0x2139), - regmap_reg_range(0x213e, 0x213f), + regmap_reg_range(0x2120, 0x212b), + regmap_reg_range(0x2134, 0x213b), + regmap_reg_range(0x213c, 0x213f), regmap_reg_range(0x2400, 0x2401), regmap_reg_range(0x2403, 0x2403), regmap_reg_range(0x2410, 0x2417), @@ -658,10 +656,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x3030, 0x3030), regmap_reg_range(0x3100, 0x3115), regmap_reg_range(0x311a, 0x311f), - regmap_reg_range(0x3122, 0x3127), - regmap_reg_range(0x312a, 0x312b), - regmap_reg_range(0x3136, 0x3139), - regmap_reg_range(0x313e, 0x313f), + regmap_reg_range(0x3120, 0x312b), + regmap_reg_range(0x3134, 0x313b), + regmap_reg_range(0x313c, 0x313f), regmap_reg_range(0x3400, 0x3401), regmap_reg_range(0x3403, 0x3403), regmap_reg_range(0x3410, 0x3417), @@ -692,10 +689,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x4030, 0x4030), regmap_reg_range(0x4100, 0x4115), regmap_reg_range(0x411a, 0x411f), - regmap_reg_range(0x4122, 0x4127), - regmap_reg_range(0x412a, 0x412b), - regmap_reg_range(0x4136, 0x4139), - regmap_reg_range(0x413e, 0x413f), + regmap_reg_range(0x4120, 0x412b), + regmap_reg_range(0x4134, 0x413b), + regmap_reg_range(0x413c, 0x413f), regmap_reg_range(0x4400, 0x4401), regmap_reg_range(0x4403, 0x4403), regmap_reg_range(0x4410, 0x4417), @@ -726,10 +722,9 @@ static const struct regmap_range ksz9477_valid_regs[] = { regmap_reg_range(0x5030, 0x5030), regmap_reg_range(0x5100, 0x5115), regmap_reg_range(0x511a, 0x511f), - regmap_reg_range(0x5122, 0x5127), - regmap_reg_range(0x512a, 0x512b), - regmap_reg_range(0x5136, 0x5139), - regmap_reg_range(0x513e, 0x513f), + regmap_reg_range(0x5120, 0x512b), + regmap_reg_range(0x5134, 0x513b), + regmap_reg_range(0x513c, 0x513f), regmap_reg_range(0x5400, 0x5401), regmap_reg_range(0x5403, 0x5403), regmap_reg_range(0x5410, 0x5417), From a2b5a9654a1d528c3df6a1b6d1e1e2cfabf9b0ad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Jul 2023 15:03:12 +0000 Subject: [PATCH 0738/2093] net: annotate data-races around sk->sk_{rcv|snd}timeo [ Upstream commit 285975dd674258ccb33e77a1803e8f2015e67105 ] sk_getsockopt() runs without locks, we must add annotations to sk->sk_rcvtimeo and sk->sk_sndtimeo. In the future we might allow fetching these fields before we lock the socket in TCP fast path. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 24 ++++++++++++++---------- net/sched/em_meta.c | 4 ++-- 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 509773919d30..8b91d9f91133 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -425,6 +425,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + long val; if (err) return err; @@ -435,7 +436,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (tv.tv_sec < 0) { static int warned __read_mostly; - *timeo_p = 0; + WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", @@ -443,11 +444,12 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, } return 0; } - *timeo_p = MAX_SCHEDULE_TIMEOUT; - if (tv.tv_sec == 0 && tv.tv_usec == 0) - return 0; - if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) - *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); + val = MAX_SCHEDULE_TIMEOUT; + if ((tv.tv_sec || tv.tv_usec) && + (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) + val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, + USEC_PER_SEC / HZ); + WRITE_ONCE(*timeo_p, val); return 0; } @@ -809,9 +811,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) - sk->sk_sndtimeo = secs * HZ; + WRITE_ONCE(sk->sk_sndtimeo, secs * HZ); else - sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT); release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); @@ -1708,12 +1710,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: - lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); + lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v, + SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: - lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); + lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v, + SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 49bae3d5006b..b1f1b49d35ed 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -568,7 +568,7 @@ META_COLLECTOR(int_sk_rcvtimeo) *err = -1; return; } - dst->value = sk->sk_rcvtimeo / HZ; + dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ; } META_COLLECTOR(int_sk_sndtimeo) @@ -579,7 +579,7 @@ META_COLLECTOR(int_sk_sndtimeo) *err = -1; return; } - dst->value = sk->sk_sndtimeo / HZ; + dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ; } META_COLLECTOR(int_sk_sendmsg_off) From 71f5a7f1745c5ba05de5faded02f70c44f1e1dda Mon Sep 17 00:00:00 2001 From: Martin Kohn Date: Thu, 27 Jul 2023 20:00:43 +0000 Subject: [PATCH 0739/2093] net: usb: qmi_wwan: add Quectel EM05GV2 [ Upstream commit d4480c9bb9258db9ddf2e632f6ef81e96b41089c ] Add support for Quectel EM05GV2 (G=global) with vendor ID 0x2c7c and product ID 0x030e Enabling DTR on this modem was necessary to ensure stable operation. Patch for usb: serial: option: is also in progress. T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=030e Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Martin Kohn Link: https://lore.kernel.org/r/AM0PR04MB57648219DE893EE04FA6CC759701A@AM0PR04MB5764.eurprd04.prod.outlook.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 68829a5a93d3..4fb981b8732e 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1422,6 +1422,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ From 54d3fba7d8c523b52e1733773769755b6a887512 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 29 Jul 2023 16:05:00 +0200 Subject: [PATCH 0740/2093] wifi: brcmfmac: Fix field-spanning write in brcmf_scan_params_v2_to_v1() [ Upstream commit 16e455a465fca91907af0108f3d013150386df30 ] Using brcmfmac with 6.5-rc3 on a brcmfmac43241b4-sdio triggers a backtrace caused by the following field-spanning warning: memcpy: detected field-spanning write (size 120) of single field "¶ms_le->channel_list[0]" at drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c:1072 (size 2) The driver still works after this warning. The warning was introduced by the new field-spanning write checks which were enabled recently. Fix this by replacing the channel_list[1] declaration at the end of the struct with a flexible array declaration. Most users of struct brcmf_scan_params_le calculate the size to alloc using the size of the non flex-array part of the struct + needed extra space, so they do not care about sizeof(struct brcmf_scan_params_le). brcmf_notify_escan_complete() however uses the struct on the stack, expecting there to be room for at least 1 entry in the channel-list to store the special -1 abort channel-id. To make this work use an anonymous union with a padding member added + the actual channel_list flexible array. Cc: Kees Cook Signed-off-by: Hans de Goede Reviewed-by: Kees Cook Reviewed-by: Franky Lin Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230729140500.27892-1-hdegoede@redhat.com Signed-off-by: Sasha Levin --- .../net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index f518e025d6e4..a8d88aedc422 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -383,7 +383,12 @@ struct brcmf_scan_params_le { * fixed parameter portion is assumed, otherwise * ssid in the fixed portion is ignored */ - __le16 channel_list[1]; /* list of chanspecs */ + union { + __le16 padding; /* Reserve space for at least 1 entry for abort + * which uses an on stack brcmf_scan_params_le + */ + DECLARE_FLEX_ARRAY(__le16, channel_list); /* chanspecs */ + }; }; struct brcmf_scan_results { From 59c4b9a2caf4b8ec22d83424b8493b4697a78b4f Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Jul 2023 11:08:16 +1000 Subject: [PATCH 0741/2093] powerpc/powermac: Use early_* IO variants in via_calibrate_decr() [ Upstream commit 86582e6189dd8f9f52c25d46c70fe5d111da6345 ] On a powermac platform, via the call path: start_kernel() time_init() ppc_md.calibrate_decr() (pmac_calibrate_decr) via_calibrate_decr() ioremap() and iounmap() are called. The unmap can enable interrupts unexpectedly (cond_resched() in vunmap_pmd_range()), which causes a warning later in the boot sequence in start_kernel(). Use the early_* variants of these IO functions to prevent this. The issue is pre-existing, but is surfaced by commit 721255b9826b ("genirq: Use a maple tree for interrupt descriptor management"). Signed-off-by: Benjamin Gray Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230706010816.72682-1-bgray@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/powermac/time.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index 4c5790aff1b5..8633891b7aa5 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -26,8 +26,8 @@ #include #include +#include #include -#include #include #include #include @@ -182,7 +182,7 @@ static int __init via_calibrate_decr(void) return 0; } of_node_put(vias); - via = ioremap(rsrc.start, resource_size(&rsrc)); + via = early_ioremap(rsrc.start, resource_size(&rsrc)); if (via == NULL) { printk(KERN_ERR "Failed to map VIA for timer calibration !\n"); return 0; @@ -207,7 +207,7 @@ static int __init via_calibrate_decr(void) ppc_tb_freq = (dstart - dend) * 100 / 6; - iounmap(via); + early_iounmap((void *)via, resource_size(&rsrc)); return 1; } From acf4ec3b4244589b8a09e65c6203293e627d3625 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Fri, 7 Jul 2023 21:58:45 +0800 Subject: [PATCH 0742/2093] idmaengine: make FSL_EDMA and INTEL_IDMA64 depends on HAS_IOMEM [ Upstream commit b1e213a9e31c20206f111ec664afcf31cbfe0dbb ] On s390 systems (aka mainframes), it has classic channel devices for networking and permanent storage that are currently even more common than PCI devices. Hence it could have a fully functional s390 kernel with CONFIG_PCI=n, then the relevant iomem mapping functions [including ioremap(), devm_ioremap(), etc.] are not available. Here let FSL_EDMA and INTEL_IDMA64 depend on HAS_IOMEM so that it won't be built to cause below compiling error if PCI is unset. -------- ERROR: modpost: "devm_platform_ioremap_resource" [drivers/dma/fsl-edma.ko] undefined! ERROR: modpost: "devm_platform_ioremap_resource" [drivers/dma/idma64.ko] undefined! -------- Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306211329.ticOJCSv-lkp@intel.com/ Signed-off-by: Baoquan He Cc: Vinod Koul Cc: dmaengine@vger.kernel.org Link: https://lore.kernel.org/r/20230707135852.24292-2-bhe@redhat.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/Kconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index b64ae02c26f8..81de833ccd04 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -210,6 +210,7 @@ config FSL_DMA config FSL_EDMA tristate "Freescale eDMA engine support" depends on OF + depends on HAS_IOMEM select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help @@ -279,6 +280,7 @@ config IMX_SDMA config INTEL_IDMA64 tristate "Intel integrated DMA 64-bit support" + depends on HAS_IOMEM select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help From c70b9758eebe2de7fd7ffdc6083b3149fc1f195c Mon Sep 17 00:00:00 2001 From: Yang Li Date: Thu, 27 Jul 2023 09:43:15 +0800 Subject: [PATCH 0743/2093] platform/x86/amd/pmf: Fix unsigned comparison with less than zero [ Upstream commit 785c00993dc4c4bb2f7b0f3a3f29c03a6f7aab2e ] The return value from the call to amd_pmf_get_pprof_modes() is int. However, the return value is being assigned to an unsigned char variable 'mode', so making 'mode' an int. silence the warning: ./drivers/platform/x86/amd/pmf/sps.c:183:5-9: WARNING: Unsigned expression compared with zero: mode < 0 Reported-by: Abaci Robot Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=5995 Signed-off-by: Yang Li Link: https://lore.kernel.org/r/20230727014315.51375-1-yang.lee@linux.alibaba.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/amd/pmf/sps.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c index fd448844de20..b2cf62937227 100644 --- a/drivers/platform/x86/amd/pmf/sps.c +++ b/drivers/platform/x86/amd/pmf/sps.c @@ -121,7 +121,8 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf) int amd_pmf_power_slider_update_event(struct amd_pmf_dev *dev) { - u8 mode, flag = 0; + u8 flag = 0; + int mode; int src; mode = amd_pmf_get_pprof_modes(dev); From 24d9cc933597597f60af419d5d55605ac6c446ae Mon Sep 17 00:00:00 2001 From: Justin Tee Date: Thu, 3 Aug 2023 14:19:32 -0700 Subject: [PATCH 0744/2093] scsi: lpfc: Remove reftag check in DIF paths [ Upstream commit 8eebf0e84f0614cebc7347f7bbccba4056d77d42 ] When preparing protection DIF I/O for DMA, the driver obtains reference tags from scsi_prot_ref_tag(). Previously, there was a wrong assumption that an all 0xffffffff value meant error and thus the driver failed the I/O. This patch removes the evaluation code and accepts whatever the upper layer returns. Signed-off-by: Justin Tee Link: https://lore.kernel.org/r/20230803211932.155745-1-justintee8345@gmail.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_scsi.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 7a1563564df7..7aac9fc71967 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -109,8 +109,6 @@ lpfc_sli4_set_rsp_sgl_last(struct lpfc_hba *phba, } } -#define LPFC_INVALID_REFTAG ((u32)-1) - /** * lpfc_rampdown_queue_depth - Post RAMP_DOWN_QUEUE event to worker thread * @phba: The Hba for which this call is being executed. @@ -978,8 +976,6 @@ lpfc_bg_err_inject(struct lpfc_hba *phba, struct scsi_cmnd *sc, sgpe = scsi_prot_sglist(sc); lba = scsi_prot_ref_tag(sc); - if (lba == LPFC_INVALID_REFTAG) - return 0; /* First check if we need to match the LBA */ if (phba->lpfc_injerr_lba != LPFC_INJERR_LBA_OFF) { @@ -1560,8 +1556,6 @@ lpfc_bg_setup_bpl(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command for pde*/ reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -1723,8 +1717,6 @@ lpfc_bg_setup_bpl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command */ blksize = scsi_prot_interval(sc); reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -1954,8 +1946,6 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command for pde*/ reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -2155,8 +2145,6 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, /* extract some info from the scsi command */ blksize = scsi_prot_interval(sc); reftag = scsi_prot_ref_tag(sc); - if (reftag == LPFC_INVALID_REFTAG) - goto out; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS rc = lpfc_bg_err_inject(phba, sc, &reftag, NULL, 1); @@ -2748,8 +2736,6 @@ lpfc_calc_bg_err(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd) src = (struct scsi_dif_tuple *)sg_virt(sgpe); start_ref_tag = scsi_prot_ref_tag(cmd); - if (start_ref_tag == LPFC_INVALID_REFTAG) - goto out; start_app_tag = src->app_tag; len = sgpe->length; while (src && protsegcnt) { @@ -3495,11 +3481,11 @@ lpfc_bg_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, scsi_cmnd->sc_data_direction); lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "9084 Cannot setup S/G List for HBA" - "IO segs %d/%d SGL %d SCSI %d: %d %d\n", + "9084 Cannot setup S/G List for HBA " + "IO segs %d/%d SGL %d SCSI %d: %d %d %d\n", lpfc_cmd->seg_cnt, lpfc_cmd->prot_seg_cnt, phba->cfg_total_seg_cnt, phba->cfg_sg_seg_cnt, - prot_group_type, num_sge); + prot_group_type, num_sge, ret); lpfc_cmd->seg_cnt = 0; lpfc_cmd->prot_seg_cnt = 0; From c61d1046127938143dcec974fb9fbdcfb98e72c8 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Wed, 26 Jul 2023 12:56:55 +0000 Subject: [PATCH 0745/2093] scsi: qedi: Fix potential deadlock on &qedi_percpu->p_work_lock [ Upstream commit dd64f80587190265ca8a0f4be6c64c2fda6d3ac2 ] As &qedi_percpu->p_work_lock is acquired by hard IRQ qedi_msix_handler(), other acquisitions of the same lock under process context should disable IRQ, otherwise deadlock could happen if the IRQ preempts the execution while the lock is held in process context on the same CPU. qedi_cpu_offline() is one such function which acquires the lock in process context. [Deadlock Scenario] qedi_cpu_offline() ->spin_lock(&p->p_work_lock) ->qedi_msix_handler() ->edi_process_completions() ->spin_lock_irqsave(&p->p_work_lock, flags); (deadlock here) This flaw was found by an experimental static analysis tool I am developing for IRQ-related deadlocks. The tentative patch fix the potential deadlock by spin_lock_irqsave() under process context. Signed-off-by: Chengfeng Ye Link: https://lore.kernel.org/r/20230726125655.4197-1-dg573847474@gmail.com Acked-by: Manish Rangankar Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedi/qedi_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 9fd68d362698..2ee109fb6561 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1977,8 +1977,9 @@ static int qedi_cpu_offline(unsigned int cpu) struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu); struct qedi_work *work, *tmp; struct task_struct *thread; + unsigned long flags; - spin_lock_bh(&p->p_work_lock); + spin_lock_irqsave(&p->p_work_lock, flags); thread = p->iothread; p->iothread = NULL; @@ -1989,7 +1990,7 @@ static int qedi_cpu_offline(unsigned int cpu) kfree(work); } - spin_unlock_bh(&p->p_work_lock); + spin_unlock_irqrestore(&p->p_work_lock, flags); if (thread) kthread_stop(thread); return 0; From f20bee49dc2a87d7c2048f0099b62d7762cd6491 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Mon, 7 Aug 2023 19:34:49 +0800 Subject: [PATCH 0746/2093] net: hns3: restore user pause configure when disable autoneg [ Upstream commit 15159ec0c831b565820c2de05114ea1b4cf07681 ] Restore the mac pause state to user configuration when autoneg is disabled Signed-off-by: Jian Shen Signed-off-by: Peiyang Wang Signed-off-by: Jijie Shao Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230807113452.474224-2-shaojijie@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 ++++- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6af2273f227c..84ecd8b9be48 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10936,9 +10936,12 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev) u32 rx_pause, tx_pause; u8 flowctl; - if (!phydev->link || !phydev->autoneg) + if (!phydev->link) return 0; + if (!phydev->autoneg) + return hclge_mac_pause_setup_hw(hdev); + local_advertising = linkmode_adv_to_lcl_adv_t(phydev->advertising); if (phydev->pause) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 150f146fa24f..8b40c6b4ee53 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1549,7 +1549,7 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) return 0; } -static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) { bool tx_en, rx_en; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index dd6f1fd486cf..251e80845620 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -242,6 +242,7 @@ int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate); From 5251c835324bee81894fdad1a844d15a79e54883 Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Tue, 25 Jul 2023 19:11:54 +0530 Subject: [PATCH 0747/2093] drm/amdgpu: Match against exact bootloader status [ Upstream commit d3de41ee5febe5c2d9989fe9810bce2bb54a3a8e ] On PSP v13.x ASICs, boot loader will set only the MSB to 1 and clear the least significant bits for any command submission. Hence match against the exact register value, otherwise a register value of all 0xFFs also could falsely indicate that boot loader is ready. Also, from PSP v13.0.6 and newer, bits[7:0] will be used to indicate command error status. Signed-off-by: Lijo Lazar Acked-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/psp_v13_0.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 8c5fa4b7b68a..c7cb30efe43d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -147,14 +147,15 @@ static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) int ret; int retry_loop; + /* Wait for bootloader to signify that it is ready having bit 31 of + * C2PMSG_35 set to 1. All other bits are expected to be cleared. + * If there is an error in processing command, bits[7:0] will be set. + * This is applicable for PSP v13.0.6 and newer. + */ for (retry_loop = 0; retry_loop < 10; retry_loop++) { - /* Wait for bootloader to signify that is - ready having bit 31 of C2PMSG_35 set to 1 */ - ret = psp_wait_for(psp, - SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), - 0x80000000, - 0x80000000, - false); + ret = psp_wait_for( + psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), + 0x80000000, 0xffffffff, false); if (ret == 0) return 0; From 41b446e4904a613e169c75bfea97acb08a065849 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 8 Jun 2023 16:36:04 +0300 Subject: [PATCH 0748/2093] wifi: cfg80211: remove links only on AP [ Upstream commit 34d4e3eb67fed9c19719bedb748e5a8b6ccc97a5 ] Since links are only controlled by userspace via cfg80211 in AP mode, also only remove them from the driver in that case. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230608163202.ed65b94916fa.I2458c46888284cc5ce30715fe642bc5fc4340c8f@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/util.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index 39680e7bad45..f433f3fdd9e9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation */ #include #include @@ -2479,6 +2479,13 @@ void cfg80211_remove_links(struct wireless_dev *wdev) { unsigned int link_id; + /* + * links are controlled by upper layers (userspace/cfg) + * only for AP mode, so only remove them here for AP + */ + if (wdev->iftype != NL80211_IFTYPE_AP) + return; + wdev_lock(wdev); if (wdev->valid_links) { for_each_valid_link(wdev, link_id) From 78ef22febd68aafdef98ae3eb458958c1910ad27 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Thu, 8 Jun 2023 16:36:07 +0300 Subject: [PATCH 0749/2093] wifi: mac80211: Use active_links instead of valid_links in Tx [ Upstream commit 7b3b9ac899b54f53f7c9fc07e1c562f56b2187fa ] Fix few places on the Tx path where the valid_links were used instead of active links. Signed-off-by: Ilan Peer Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230608163202.e24832691fc8.I9ac10dc246d7798a8d26b1a94933df5668df63fc@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/tx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 763cefd0cc26..2f9e1abdf375 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4391,7 +4391,7 @@ static void ieee80211_mlo_multicast_tx(struct net_device *dev, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - unsigned long links = sdata->vif.valid_links; + unsigned long links = sdata->vif.active_links; unsigned int link; u32 ctrl_flags = IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX; @@ -5827,7 +5827,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (WARN_ON_ONCE(link == ARRAY_SIZE(sdata->vif.link_conf))) - link = ffs(sdata->vif.valid_links) - 1; + link = ffs(sdata->vif.active_links) - 1; } IEEE80211_SKB_CB(skb)->control.flags |= @@ -5863,7 +5863,7 @@ void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, band = chanctx_conf->def.chan->band; } else { WARN_ON(link_id >= 0 && - !(sdata->vif.valid_links & BIT(link_id))); + !(sdata->vif.active_links & BIT(link_id))); /* MLD transmissions must not rely on the band */ band = 0; } From 179b9b062fe8ef4d674e5772598b36396b871060 Mon Sep 17 00:00:00 2001 From: Dmitry Mastykin Date: Thu, 8 Jun 2023 16:57:54 +0300 Subject: [PATCH 0750/2093] netlabel: fix shift wrapping bug in netlbl_catmap_setlong() [ Upstream commit b403643d154d15176b060b82f7fc605210033edd ] There is a shift wrapping bug in this code on 32-bit architectures. NETLBL_CATMAP_MAPTYPE is u64, bitmap is unsigned long. Every second 32-bit word of catmap becomes corrupted. Signed-off-by: Dmitry Mastykin Acked-by: Paul Moore Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/netlabel/netlabel_kapi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 54c083003947..27511c90a26f 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -857,7 +857,8 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, offset -= iter->startbit; idx = offset / NETLBL_CATMAP_MAPSIZE; - iter->bitmap[idx] |= bitmap << (offset % NETLBL_CATMAP_MAPSIZE); + iter->bitmap[idx] |= (NETLBL_CATMAP_MAPTYPE)bitmap + << (offset % NETLBL_CATMAP_MAPSIZE); return 0; } From ea13eff14ef2912d4256ef1a67bdd09b3033f473 Mon Sep 17 00:00:00 2001 From: David Christensen Date: Thu, 8 Jun 2023 16:01:43 -0400 Subject: [PATCH 0751/2093] bnx2x: fix page fault following EEH recovery [ Upstream commit 7ebe4eda4265642859507d1b3ca330d8c196cfe5 ] In the last step of the EEH recovery process, the EEH driver calls into bnx2x_io_resume() to re-initialize the NIC hardware via the function bnx2x_nic_load(). If an error occurs during bnx2x_nic_load(), OS and hardware resources are released and an error code is returned to the caller. When called from bnx2x_io_resume(), the return code is ignored and the network interface is brought up unconditionally. Later attempts to send a packet via this interface result in a page fault due to a null pointer reference. This patch checks the return code of bnx2x_nic_load(), prints an error message if necessary, and does not enable the interface. Signed-off-by: David Christensen Reviewed-by: Sridhar Samudrala Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 51b1690fd045..a1783faf4fe9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -14312,11 +14312,16 @@ static void bnx2x_io_resume(struct pci_dev *pdev) bp->fw_seq = SHMEM_RD(bp, func_mb[BP_FW_MB_IDX(bp)].drv_mb_header) & DRV_MSG_SEQ_NUMBER_MASK; - if (netif_running(dev)) - bnx2x_nic_load(bp, LOAD_NORMAL); + if (netif_running(dev)) { + if (bnx2x_nic_load(bp, LOAD_NORMAL)) { + netdev_err(bp->dev, "Error during driver initialization, try unloading/reloading the driver\n"); + goto done; + } + } netif_device_attach(dev); +done: rtnl_unlock(); } From 8a424afa08c54670192f4b0c5351207ff6f8cdc4 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Fri, 9 Jun 2023 17:46:59 +0000 Subject: [PATCH 0752/2093] cifs: fix sockaddr comparison in iface_cmp [ Upstream commit 2991b77409891e14a10b96899755c004b0c07edb ] iface_cmp used to simply do a memcmp of the two provided struct sockaddrs. The comparison needs to do more based on the address family. Similar logic was already present in cifs_match_ipaddr. Doing something similar now. Signed-off-by: Shyam Prasad N Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/cifsglob.h | 37 ----------------------------- fs/smb/client/cifsproto.h | 1 + fs/smb/client/connect.c | 50 +++++++++++++++++++++++++++++++++++++++ fs/smb/client/smb2ops.c | 37 +++++++++++++++++++++++++++++ 4 files changed, 88 insertions(+), 37 deletions(-) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index a37afbb7e399..4a092cc5a393 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -970,43 +970,6 @@ release_iface(struct kref *ref) kfree(iface); } -/* - * compare two interfaces a and b - * return 0 if everything matches. - * return 1 if a has higher link speed, or rdma capable, or rss capable - * return -1 otherwise. - */ -static inline int -iface_cmp(struct cifs_server_iface *a, struct cifs_server_iface *b) -{ - int cmp_ret = 0; - - WARN_ON(!a || !b); - if (a->speed == b->speed) { - if (a->rdma_capable == b->rdma_capable) { - if (a->rss_capable == b->rss_capable) { - cmp_ret = memcmp(&a->sockaddr, &b->sockaddr, - sizeof(a->sockaddr)); - if (!cmp_ret) - return 0; - else if (cmp_ret > 0) - return 1; - else - return -1; - } else if (a->rss_capable > b->rss_capable) - return 1; - else - return -1; - } else if (a->rdma_capable > b->rdma_capable) - return 1; - else - return -1; - } else if (a->speed > b->speed) - return 1; - else - return -1; -} - struct cifs_chan { unsigned int in_reconnect : 1; /* if session setup in progress for this channel */ struct TCP_Server_Info *server; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 98513f5af3f9..a914b88ca51a 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -85,6 +85,7 @@ extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx); extern int smb3_parse_opt(const char *options, const char *key, char **val); +extern int cifs_ipaddr_cmp(struct sockaddr *srcaddr, struct sockaddr *rhs); extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); extern int cifs_discard_remaining_data(struct TCP_Server_Info *server); extern int cifs_call_async(struct TCP_Server_Info *server, diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index cbe08948baf4..9cd282960c0b 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1343,6 +1343,56 @@ cifs_demultiplex_thread(void *p) module_put_and_kthread_exit(0); } +int +cifs_ipaddr_cmp(struct sockaddr *srcaddr, struct sockaddr *rhs) +{ + struct sockaddr_in *saddr4 = (struct sockaddr_in *)srcaddr; + struct sockaddr_in *vaddr4 = (struct sockaddr_in *)rhs; + struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr; + struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)rhs; + + switch (srcaddr->sa_family) { + case AF_UNSPEC: + switch (rhs->sa_family) { + case AF_UNSPEC: + return 0; + case AF_INET: + case AF_INET6: + return 1; + default: + return -1; + } + case AF_INET: { + switch (rhs->sa_family) { + case AF_UNSPEC: + return -1; + case AF_INET: + return memcmp(saddr4, vaddr4, + sizeof(struct sockaddr_in)); + case AF_INET6: + return 1; + default: + return -1; + } + } + case AF_INET6: { + switch (rhs->sa_family) { + case AF_UNSPEC: + case AF_INET: + return -1; + case AF_INET6: + return memcmp(saddr6, + vaddr6, + sizeof(struct sockaddr_in6)); + default: + return -1; + } + } + default: + return -1; /* don't expect to be here */ + } +} + /* * Returns true if srcaddr isn't specified and rhs isn't specified, or * if srcaddr is specified and matches the IP address of the rhs argument diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index e6a191a7499e..bcd4c3a50760 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -511,6 +511,43 @@ smb3_negotiate_rsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) return rsize; } +/* + * compare two interfaces a and b + * return 0 if everything matches. + * return 1 if a is rdma capable, or rss capable, or has higher link speed + * return -1 otherwise. + */ +static int +iface_cmp(struct cifs_server_iface *a, struct cifs_server_iface *b) +{ + int cmp_ret = 0; + + WARN_ON(!a || !b); + if (a->rdma_capable == b->rdma_capable) { + if (a->rss_capable == b->rss_capable) { + if (a->speed == b->speed) { + cmp_ret = cifs_ipaddr_cmp((struct sockaddr *) &a->sockaddr, + (struct sockaddr *) &b->sockaddr); + if (!cmp_ret) + return 0; + else if (cmp_ret > 0) + return 1; + else + return -1; + } else if (a->speed > b->speed) + return 1; + else + return -1; + } else if (a->rss_capable > b->rss_capable) + return 1; + else + return -1; + } else if (a->rdma_capable > b->rdma_capable) + return 1; + else + return -1; +} + static int parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, size_t buf_len, struct cifs_ses *ses, bool in_mount) From fbd3ae6997fb97d8bb23e6674240f4c3856a4744 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Fri, 9 Jun 2023 17:46:58 +0000 Subject: [PATCH 0753/2093] cifs: fix max_credits implementation [ Upstream commit 5e90aa21eb1372736e08cee0c0bf47735c5c4b95 ] The current implementation of max_credits on the client does not work because the CreditRequest logic for several commands does not take max_credits into account. Still, we can end up asking the server for more credits, depending on the number of credits in flight. For this, we need to limit the credits while parsing the responses too. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/smb2ops.c | 2 ++ fs/smb/client/smb2pdu.c | 32 ++++++++++++++++++++++++++++---- 2 files changed, 30 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index bcd4c3a50760..6b020d80bb94 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -34,6 +34,8 @@ static int change_conf(struct TCP_Server_Info *server) { server->credits += server->echo_credits + server->oplock_credits; + if (server->credits > server->max_credits) + server->credits = server->max_credits; server->oplock_credits = server->echo_credits = 0; switch (server->credits) { case 0: diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index ba46156e3268..ae17d78f6ba1 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1312,7 +1312,12 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) } /* enough to enable echos and oplocks and one max size write */ - req->hdr.CreditRequest = cpu_to_le16(130); + if (server->credits >= server->max_credits) + req->hdr.CreditRequest = cpu_to_le16(0); + else + req->hdr.CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, 130)); /* only one of SMB2 signing flags may be set in SMB2 request */ if (server->sign) @@ -1907,7 +1912,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, rqst.rq_nvec = 2; /* Need 64 for max size write so ask for more in case not there yet */ - req->hdr.CreditRequest = cpu_to_le16(64); + if (server->credits >= server->max_credits) + req->hdr.CreditRequest = cpu_to_le16(0); + else + req->hdr.CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, 64)); rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); @@ -4291,6 +4301,7 @@ smb2_async_readv(struct cifs_readdata *rdata) struct TCP_Server_Info *server; struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); unsigned int total_len; + int credit_request; cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n", __func__, rdata->offset, rdata->bytes); @@ -4322,7 +4333,13 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rdata->credits.value > 0) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8); + credit_request = le16_to_cpu(shdr->CreditCharge) + 8; + if (server->credits >= server->max_credits) + shdr->CreditRequest = cpu_to_le16(0); + else + shdr->CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, credit_request)); rc = adjust_credits(server, &rdata->credits, rdata->bytes); if (rc) @@ -4532,6 +4549,7 @@ smb2_async_writev(struct cifs_writedata *wdata, unsigned int total_len; struct cifs_io_parms _io_parms; struct cifs_io_parms *io_parms = NULL; + int credit_request; if (!wdata->server) server = wdata->server = cifs_pick_channel(tcon->ses); @@ -4649,7 +4667,13 @@ smb2_async_writev(struct cifs_writedata *wdata, if (wdata->credits.value > 0) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8); + credit_request = le16_to_cpu(shdr->CreditCharge) + 8; + if (server->credits >= server->max_credits) + shdr->CreditRequest = cpu_to_le16(0); + else + shdr->CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, credit_request)); rc = adjust_credits(server, &wdata->credits, io_parms->length); if (rc) From dcfd75bca8cf003bb57a4a607d3acab69a7e8578 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Jun 2023 14:04:43 +0300 Subject: [PATCH 0754/2093] sctp: handle invalid error codes without calling BUG() [ Upstream commit a0067dfcd9418fd3b0632bc59210d120d038a9c6 ] The sctp_sf_eat_auth() function is supposed to return enum sctp_disposition values but if the call to sctp_ulpevent_make_authkey() fails, it returns -ENOMEM. This results in calling BUG() inside the sctp_side_effects() function. Calling BUG() is an over reaction and not helpful. Call WARN_ON_ONCE() instead. This code predates git. Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sctp/sm_sideeffect.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 463c4a58d2c3..970c6a486a9b 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1251,7 +1251,10 @@ static int sctp_side_effects(enum sctp_event_type event_type, default: pr_err("impossible disposition %d in state %d, event_type %d, event_id %d\n", status, state, event_type, subtype.chunk); - BUG(); + error = status; + if (error >= 0) + error = -EINVAL; + WARN_ON_ONCE(1); break; } From 7d1ac3c2eb70558d2b4c1ec9d966000d4cc6b353 Mon Sep 17 00:00:00 2001 From: Sagar Biradar Date: Fri, 19 May 2023 16:08:34 -0700 Subject: [PATCH 0755/2093] scsi: aacraid: Reply queue mapping to CPUs based on IRQ affinity [ Upstream commit 9dc704dcc09eae7d21b5da0615eb2ed79278f63e ] Fix the I/O hang that arises because of the MSIx vector not having a mapped online CPU upon receiving completion. SCSI cmds take the blk_mq route, which is setup during init. Reserved cmds fetch the vector_no from mq_map after init is complete. Before init, they have to use 0 - as per the norm. Reviewed-by: Gilbert Wu Signed-off-by: Sagar Biradar Reviewed-by: John Garry Link: https://lore.kernel.org/r/20230519230834.27436-1-sagar.biradar@microchip.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/aacraid/aacraid.h | 1 + drivers/scsi/aacraid/commsup.c | 6 +++++- drivers/scsi/aacraid/linit.c | 14 ++++++++++++++ drivers/scsi/aacraid/src.c | 25 +++++++++++++++++++++++-- 4 files changed, 43 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 5e115e8b2ba4..7c6efde75da6 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1678,6 +1678,7 @@ struct aac_dev u32 handle_pci_error; bool init_reset; u8 soft_reset_support; + u8 use_map_queue; }; #define aac_adapter_interrupt(dev) \ diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index deb32c9f4b3e..3f062e4013ab 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -223,8 +223,12 @@ int aac_fib_setup(struct aac_dev * dev) struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd) { struct fib *fibptr; + u32 blk_tag; + int i; - fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag]; + blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); + i = blk_mq_unique_tag_to_tag(blk_tag); + fibptr = &dev->fibs[i]; /* * Null out fields that depend on being zero at the start of * each I/O diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 5ba5c18b77b4..bff49b8ab057 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -505,6 +506,15 @@ static int aac_slave_configure(struct scsi_device *sdev) return 0; } +static void aac_map_queues(struct Scsi_Host *shost) +{ + struct aac_dev *aac = (struct aac_dev *)shost->hostdata; + + blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + aac->pdev, 0); + aac->use_map_queue = true; +} + /** * aac_change_queue_depth - alter queue depths * @sdev: SCSI device we are considering @@ -1489,6 +1499,7 @@ static struct scsi_host_template aac_driver_template = { .bios_param = aac_biosparm, .shost_groups = aac_host_groups, .slave_configure = aac_slave_configure, + .map_queues = aac_map_queues, .change_queue_depth = aac_change_queue_depth, .sdev_groups = aac_dev_groups, .eh_abort_handler = aac_eh_abort, @@ -1776,6 +1787,8 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_lun = AAC_MAX_LUN; pci_set_drvdata(pdev, shost); + shost->nr_hw_queues = aac->max_msix; + shost->host_tagset = 1; error = scsi_add_host(shost, &pdev->dev); if (error) @@ -1908,6 +1921,7 @@ static void aac_remove_one(struct pci_dev *pdev) struct aac_dev *aac = (struct aac_dev *)shost->hostdata; aac_cancel_rescan_worker(aac); + aac->use_map_queue = false; scsi_remove_host(shost); __aac_shutdown(aac); diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 11ef58204e96..61949f374188 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -493,6 +493,10 @@ static int aac_src_deliver_message(struct fib *fib) #endif u16 vector_no; + struct scsi_cmnd *scmd; + u32 blk_tag; + struct Scsi_Host *shost = dev->scsi_host_ptr; + struct blk_mq_queue_map *qmap; atomic_inc(&q->numpending); @@ -505,8 +509,25 @@ static int aac_src_deliver_message(struct fib *fib) if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) && dev->sa_firmware) vector_no = aac_get_vector(dev); - else - vector_no = fib->vector_no; + else { + if (!fib->vector_no || !fib->callback_data) { + if (shost && dev->use_map_queue) { + qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; + vector_no = qmap->mq_map[raw_smp_processor_id()]; + } + /* + * We hardcode the vector_no for + * reserved commands as a valid shost is + * absent during the init + */ + else + vector_no = 0; + } else { + scmd = (struct scsi_cmnd *)fib->callback_data; + blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); + vector_no = blk_mq_unique_tag_to_hwq(blk_tag); + } + } if (native_hba) { if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) { From 1a7f80f33a5911bd33352f639533ba9ca3444bc3 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 9 Jun 2023 13:38:21 -0700 Subject: [PATCH 0756/2093] scsi: storvsc: Always set no_report_opcodes [ Upstream commit 31d16e712bdcaee769de4780f72ff8d6cd3f0589 ] Hyper-V synthetic SCSI devices do not support the MAINTENANCE_IN SCSI command, so scsi_report_opcode() always fails, resulting in messages like this: hv_storvsc : tag#205 cmd 0xa3 status: scsi 0x2 srb 0x86 hv 0xc0000001 The recently added support for command duration limits calls scsi_report_opcode() four times as each device comes online, which significantly increases the number of messages logged in a system with many disks. Fix the problem by always marking Hyper-V synthetic SCSI devices as not supporting scsi_report_opcode(). With this setting, the MAINTENANCE_IN SCSI command is not issued and no messages are logged. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1686343101-18930-1-git-send-email-mikelley@microsoft.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/storvsc_drv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 83d09c200928..7a1dc5c7c49e 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1568,6 +1568,8 @@ static int storvsc_device_configure(struct scsi_device *sdevice) { blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ)); + /* storvsc devices don't support MAINTENANCE_IN SCSI cmd */ + sdevice->no_report_opcodes = 1; sdevice->no_write_same = 1; /* From 790587097c013c95a96151c30312c5e589f0b30d Mon Sep 17 00:00:00 2001 From: Justin Tee Date: Wed, 14 Jun 2023 10:59:44 -0700 Subject: [PATCH 0757/2093] scsi: lpfc: Fix incorrect big endian type assignment in bsg loopback path [ Upstream commit 9cefd6e7e0a77b0fbca5c793f6fb6821b0962775 ] The kernel test robot reported sparse warnings regarding incorrect type assignment for __be16 variables in bsg loopback path. Change the flagged lines to use the be16_to_cpu() and cpu_to_be16() macros appropriately. Signed-off-by: Justin Tee Link: https://lore.kernel.org/r/20230614175944.3577-1-justintee8345@gmail.com Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306110819.sDIKiGgg-lkp@intel.com/ Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_bsg.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 852b025e2fec..b54fafb486e0 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -889,7 +889,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, struct lpfc_iocbq *piocbq) { uint32_t evt_req_id = 0; - uint32_t cmd; + u16 cmd; struct lpfc_dmabuf *dmabuf = NULL; struct lpfc_bsg_event *evt; struct event_data *evt_dat = NULL; @@ -915,7 +915,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, ct_req = (struct lpfc_sli_ct_request *)bdeBuf1->virt; evt_req_id = ct_req->FsType; - cmd = ct_req->CommandResponse.bits.CmdRsp; + cmd = be16_to_cpu(ct_req->CommandResponse.bits.CmdRsp); spin_lock_irqsave(&phba->ct_ev_lock, flags); list_for_each_entry(evt, &phba->ct_ev_waiters, node) { @@ -3186,8 +3186,8 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job) ctreq->RevisionId.bits.InId = 0; ctreq->FsType = SLI_CT_ELX_LOOPBACK; ctreq->FsSubType = 0; - ctreq->CommandResponse.bits.CmdRsp = ELX_LOOPBACK_DATA; - ctreq->CommandResponse.bits.Size = size; + ctreq->CommandResponse.bits.CmdRsp = cpu_to_be16(ELX_LOOPBACK_DATA); + ctreq->CommandResponse.bits.Size = cpu_to_be16(size); segment_offset = ELX_LOOPBACK_HEADER_SZ; } else segment_offset = 0; From 9920a52362a0d37720163e4b7d2de94de92ae470 Mon Sep 17 00:00:00 2001 From: Hongchen Zhang Date: Thu, 15 Jun 2023 14:35:52 +0800 Subject: [PATCH 0758/2093] LoongArch: Let pmd_present() return true when splitting pmd [ Upstream commit ddc1729b07cc84bb29f577698b8d2e74a4004a6e ] When we split a pmd into ptes, pmd_present() and pmd_trans_huge() should return true, otherwise it would be treated as a swap pmd. This is the same as arm64 does in commit b65399f6111b ("arm64/mm: Change THP helpers to comply with generic MM semantics"), we also add a new bit named _PAGE_PRESENT_INVALID for LoongArch. Signed-off-by: Hongchen Zhang Signed-off-by: Huacai Chen Signed-off-by: Sasha Levin --- arch/loongarch/include/asm/pgtable-bits.h | 2 ++ arch/loongarch/include/asm/pgtable.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 3d1e0a69975a..5f2ebcea509c 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -21,12 +21,14 @@ #define _PAGE_HGLOBAL_SHIFT 12 /* HGlobal is a PMD bit */ #define _PAGE_PFN_SHIFT 12 #define _PAGE_PFN_END_SHIFT 48 +#define _PAGE_PRESENT_INVALID_SHIFT 60 #define _PAGE_NO_READ_SHIFT 61 #define _PAGE_NO_EXEC_SHIFT 62 #define _PAGE_RPLV_SHIFT 63 /* Used by software */ #define _PAGE_PRESENT (_ULCAST_(1) << _PAGE_PRESENT_SHIFT) +#define _PAGE_PRESENT_INVALID (_ULCAST_(1) << _PAGE_PRESENT_INVALID_SHIFT) #define _PAGE_WRITE (_ULCAST_(1) << _PAGE_WRITE_SHIFT) #define _PAGE_ACCESSED (_ULCAST_(1) << _PAGE_ACCESSED_SHIFT) #define _PAGE_MODIFIED (_ULCAST_(1) << _PAGE_MODIFIED_SHIFT) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 79d5bfd913e0..e748fad82f13 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -208,7 +208,7 @@ static inline int pmd_bad(pmd_t pmd) static inline int pmd_present(pmd_t pmd) { if (unlikely(pmd_val(pmd) & _PAGE_HUGE)) - return !!(pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE)); + return !!(pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PRESENT_INVALID)); return pmd_val(pmd) != (unsigned long)invalid_pte_table; } @@ -525,6 +525,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) static inline pmd_t pmd_mkinvalid(pmd_t pmd) { + pmd_val(pmd) |= _PAGE_PRESENT_INVALID; pmd_val(pmd) &= ~(_PAGE_PRESENT | _PAGE_VALID | _PAGE_DIRTY | _PAGE_PROTNONE); return pmd; From ab5c5c10d0668578b40e76faa316a995b316064b Mon Sep 17 00:00:00 2001 From: Qi Hu Date: Thu, 15 Jun 2023 14:35:52 +0800 Subject: [PATCH 0759/2093] LoongArch: Fix the write_fcsr() macro [ Upstream commit 346dc929623cef70ff7832a4fa0ffd1b696e312a ] The "write_fcsr()" macro uses wrong the positions for val and dest in asm. Fix it! Reported-by: Miao HAO Signed-off-by: Qi Hu Signed-off-by: Huacai Chen Signed-off-by: Sasha Levin --- arch/loongarch/include/asm/loongarch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 62835d84a647..3d15fa5bef37 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -1488,7 +1488,7 @@ __BUILD_CSR_OP(tlbidx) #define write_fcsr(dest, val) \ do { \ __asm__ __volatile__( \ - " movgr2fcsr %0, "__stringify(dest)" \n" \ + " movgr2fcsr "__stringify(dest)", %0 \n" \ : : "r" (val)); \ } while (0) From f24681b8162bd7c707d07c4d0dce0a04f447c326 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 12 Jun 2023 14:55:33 +0200 Subject: [PATCH 0760/2093] ALSA: seq: oss: Fix racy open/close of MIDI devices [ Upstream commit 297224fc0922e7385573a30c29ffdabb67f27b7d ] Although snd_seq_oss_midi_open() and snd_seq_oss_midi_close() can be called concurrently from different code paths, we have no proper data protection against races. Introduce open_mutex to each seq_oss_midi object for avoiding the races. Reported-by: "Gong, Sishuai" Closes: https://lore.kernel.org/r/7DC9AF71-F481-4ABA-955F-76C535661E33@purdue.edu Link: https://lore.kernel.org/r/20230612125533.27461-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/core/seq/oss/seq_oss_midi.c | 35 +++++++++++++++++++------------ 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c index 07efb38f58ac..f2940b29595f 100644 --- a/sound/core/seq/oss/seq_oss_midi.c +++ b/sound/core/seq/oss/seq_oss_midi.c @@ -37,6 +37,7 @@ struct seq_oss_midi { struct snd_midi_event *coder; /* MIDI event coder */ struct seq_oss_devinfo *devinfo; /* assigned OSSseq device */ snd_use_lock_t use_lock; + struct mutex open_mutex; }; @@ -172,6 +173,7 @@ snd_seq_oss_midi_check_new_port(struct snd_seq_port_info *pinfo) mdev->flags = pinfo->capability; mdev->opened = 0; snd_use_lock_init(&mdev->use_lock); + mutex_init(&mdev->open_mutex); /* copy and truncate the name of synth device */ strscpy(mdev->name, pinfo->name, sizeof(mdev->name)); @@ -322,15 +324,17 @@ snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) int perm; struct seq_oss_midi *mdev; struct snd_seq_port_subscribe subs; + int err; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; + mutex_lock(&mdev->open_mutex); /* already used? */ if (mdev->opened && mdev->devinfo != dp) { - snd_use_lock_free(&mdev->use_lock); - return -EBUSY; + err = -EBUSY; + goto unlock; } perm = 0; @@ -340,14 +344,14 @@ snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) perm |= PERM_READ; perm &= mdev->flags; if (perm == 0) { - snd_use_lock_free(&mdev->use_lock); - return -ENXIO; + err = -ENXIO; + goto unlock; } /* already opened? */ if ((mdev->opened & perm) == perm) { - snd_use_lock_free(&mdev->use_lock); - return 0; + err = 0; + goto unlock; } perm &= ~mdev->opened; @@ -372,13 +376,17 @@ snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) } if (! mdev->opened) { - snd_use_lock_free(&mdev->use_lock); - return -ENXIO; + err = -ENXIO; + goto unlock; } mdev->devinfo = dp; + err = 0; + + unlock: + mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); - return 0; + return err; } /* @@ -393,10 +401,9 @@ snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; - if (! mdev->opened || mdev->devinfo != dp) { - snd_use_lock_free(&mdev->use_lock); - return 0; - } + mutex_lock(&mdev->open_mutex); + if (!mdev->opened || mdev->devinfo != dp) + goto unlock; memset(&subs, 0, sizeof(subs)); if (mdev->opened & PERM_WRITE) { @@ -415,6 +422,8 @@ snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) mdev->opened = 0; mdev->devinfo = NULL; + unlock: + mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); return 0; } From 41103f7f688ad7b57f3d88a51277f51a058b3b52 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Fri, 18 Aug 2023 13:05:56 +0200 Subject: [PATCH 0761/2093] net: sfp: handle 100G/25G active optical cables in sfp_parse_support [ Upstream commit db1a6ad77c180efc7242d7204b9a0c72c8a5a1bb ] Handle extended compliance code 0x1 (SFF8024_ECC_100G_25GAUI_C2M_AOC) for active optical cables supporting 25G and 100G speeds. Since the specification makes no statement about transmitter range, and as the specific sfp module that had been tested features only 2m fiber - short-range (SR) modes are selected. The 100G speed is irrelevant because it would require multiple fibers / multiple SFP28 modules combined under one netdev. sfp-bus.c only handles a single module per netdev, so only 25Gbps modes are selected. sfp_parse_support already handles SFF8024_ECC_100GBASE_SR4_25GBASE_SR with compatible properties, however that entry is a contradiction in itself since with SFP(28) 100GBASE_SR4 is impossible - that would likely be a mode for qsfp modules only. Add a case for SFF8024_ECC_100G_25GAUI_C2M_AOC selecting 25gbase-r interface mode and 25000baseSR link mode. Also enforce SFP28 bitrate limits on the values read from sfp eeprom as requested by Russell King. Tested with fs.com S28-AO02 AOC SFP28 module. Signed-off-by: Josua Mayer Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/sfp-bus.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index daac293e8ede..1865e3dbdfad 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -254,6 +254,16 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, switch (id->base.extended_cc) { case SFF8024_ECC_UNSPEC: break; + case SFF8024_ECC_100G_25GAUI_C2M_AOC: + if (br_min <= 28000 && br_max >= 25000) { + /* 25GBASE-R, possibly with FEC */ + __set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces); + /* There is currently no link mode for 25000base + * with unspecified range, reuse SR. + */ + phylink_set(modes, 25000baseSR_Full); + } + break; case SFF8024_ECC_100GBASE_SR4_25GBASE_SR: phylink_set(modes, 100000baseSR4_Full); phylink_set(modes, 25000baseSR_Full); From 10f358cd4b0e4b43c07c44791d417a87e8a8d61b Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Fri, 18 Aug 2023 10:26:45 +0800 Subject: [PATCH 0762/2093] tracing: Introduce pipe_cpumask to avoid race on trace_pipes [ Upstream commit c2489bb7e6be2e8cdced12c16c42fa128403ac03 ] There is race issue when concurrently splice_read main trace_pipe and per_cpu trace_pipes which will result in data read out being different from what actually writen. As suggested by Steven: > I believe we should add a ref count to trace_pipe and the per_cpu > trace_pipes, where if they are opened, nothing else can read it. > > Opening trace_pipe locks all per_cpu ref counts, if any of them are > open, then the trace_pipe open will fail (and releases any ref counts > it had taken). > > Opening a per_cpu trace_pipe will up the ref count for just that > CPU buffer. This will allow multiple tasks to read different per_cpu > trace_pipe files, but will prevent the main trace_pipe file from > being opened. But because we only need to know whether per_cpu trace_pipe is open or not, using a cpumask instead of using ref count may be easier. After this patch, users will find that: - Main trace_pipe can be opened by only one user, and if it is opened, all per_cpu trace_pipes cannot be opened; - Per_cpu trace_pipes can be opened by multiple users, but each per_cpu trace_pipe can only be opened by one user. And if one of them is opened, main trace_pipe cannot be opened. Link: https://lore.kernel.org/linux-trace-kernel/20230818022645.1948314-1-zhengyejian1@huawei.com Suggested-by: Steven Rostedt (Google) Signed-off-by: Zheng Yejian Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace.c | 55 ++++++++++++++++++++++++++++++++++++++------ kernel/trace/trace.h | 2 ++ 2 files changed, 50 insertions(+), 7 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1a87cb70f1eb..e581253ecc53 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6616,10 +6616,36 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, #endif +static int open_pipe_on_cpu(struct trace_array *tr, int cpu) +{ + if (cpu == RING_BUFFER_ALL_CPUS) { + if (cpumask_empty(tr->pipe_cpumask)) { + cpumask_setall(tr->pipe_cpumask); + return 0; + } + } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) { + cpumask_set_cpu(cpu, tr->pipe_cpumask); + return 0; + } + return -EBUSY; +} + +static void close_pipe_on_cpu(struct trace_array *tr, int cpu) +{ + if (cpu == RING_BUFFER_ALL_CPUS) { + WARN_ON(!cpumask_full(tr->pipe_cpumask)); + cpumask_clear(tr->pipe_cpumask); + } else { + WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask)); + cpumask_clear_cpu(cpu, tr->pipe_cpumask); + } +} + static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; + int cpu; int ret; ret = tracing_check_open_get_tr(tr); @@ -6627,13 +6653,16 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) return ret; mutex_lock(&trace_types_lock); + cpu = tracing_get_cpu(inode); + ret = open_pipe_on_cpu(tr, cpu); + if (ret) + goto fail_pipe_on_cpu; /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; - __trace_array_put(tr); - goto out; + goto fail_alloc_iter; } trace_seq_init(&iter->seq); @@ -6656,7 +6685,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->tr = tr; iter->array_buffer = &tr->array_buffer; - iter->cpu_file = tracing_get_cpu(inode); + iter->cpu_file = cpu; mutex_init(&iter->mutex); filp->private_data = iter; @@ -6666,12 +6695,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) nonseekable_open(inode, filp); tr->trace_ref++; -out: + mutex_unlock(&trace_types_lock); return ret; fail: kfree(iter); +fail_alloc_iter: + close_pipe_on_cpu(tr, cpu); +fail_pipe_on_cpu: __trace_array_put(tr); mutex_unlock(&trace_types_lock); return ret; @@ -6688,7 +6720,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) if (iter->trace->pipe_close) iter->trace->pipe_close(iter); - + close_pipe_on_cpu(tr, iter->cpu_file); mutex_unlock(&trace_types_lock); free_cpumask_var(iter->started); @@ -9356,6 +9388,9 @@ static struct trace_array *trace_array_create(const char *name) if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; + if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) + goto out_free_tr; + tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); @@ -9397,6 +9432,7 @@ static struct trace_array *trace_array_create(const char *name) out_free_tr: ftrace_free_ftrace_ops(tr); free_trace_buffers(tr); + free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); @@ -9499,6 +9535,7 @@ static int __remove_instance(struct trace_array *tr) } kfree(tr->topts); + free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); @@ -10223,12 +10260,14 @@ __init static int tracer_alloc_buffers(void) if (trace_create_savedcmd() < 0) goto out_free_temp_buffer; + if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) + goto out_free_savedcmd; + /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n"); - goto out_free_savedcmd; + goto out_free_pipe_cpumask; } - if (global_trace.buffer_disabled) tracing_off(); @@ -10281,6 +10320,8 @@ __init static int tracer_alloc_buffers(void) return 0; +out_free_pipe_cpumask: + free_cpumask_var(global_trace.pipe_cpumask); out_free_savedcmd: free_saved_cmdlines_buffer(savedcmd); out_free_temp_buffer: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3d3505286aa7..dbb86b0dd3b7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -366,6 +366,8 @@ struct trace_array { struct list_head events; struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ + /* one per_cpu trace_pipe can be opened by only one user */ + cpumask_var_t pipe_cpumask; int ref; int trace_ref; #ifdef CONFIG_FUNCTION_TRACER From 8f647ac91a223d7d1677fe86dace75ff21b61361 Mon Sep 17 00:00:00 2001 From: Shih-Yi Chen Date: Mon, 21 Aug 2023 11:06:27 -0400 Subject: [PATCH 0763/2093] platform/mellanox: Fix mlxbf-tmfifo not handling all virtio CONSOLE notifications [ Upstream commit 0848cab765c634597636810bf76d0934003cce28 ] rshim console does not show all entries of dmesg. Fixed by setting MLXBF_TM_TX_LWM_IRQ for every CONSOLE notification. Signed-off-by: Shih-Yi Chen Reviewed-by: Liming Sung Reviewed-by: David Thompson Link: https://lore.kernel.org/r/20230821150627.26075-1-shihyic@nvidia.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/mlxbf-tmfifo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index b2e19f30a928..d31fe7eed38d 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -868,6 +868,7 @@ static bool mlxbf_tmfifo_virtio_notify(struct virtqueue *vq) tm_vdev = fifo->vdev[VIRTIO_ID_CONSOLE]; mlxbf_tmfifo_console_output(tm_vdev, vring); spin_unlock_irqrestore(&fifo->spin_lock[0], flags); + set_bit(MLXBF_TM_TX_LWM_IRQ, &fifo->pend_events); } else if (test_and_set_bit(MLXBF_TM_TX_LWM_IRQ, &fifo->pend_events)) { return true; From c50fdd53344810b2ca977f4d4979fb1dec811627 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 6 Feb 2023 17:42:01 -0800 Subject: [PATCH 0764/2093] of: property: Simplify of_link_to_phandle() commit 4a032827daa89350365166b19d14d82fe8219128 upstream. The driver core now: - Has the parent device of a supplier pick up the consumers if the supplier never has a device created for it. - Ignores a supplier if the supplier has no parent device and will never be probed by a driver And already prevents creating a device link with the consumer as a supplier of a parent. So, we no longer need to find the "compatible" node of the supplier or do any other checks in of_link_to_phandle(). We simply need to make sure that the supplier is available in DT. Signed-off-by: Saravana Kannan Tested-by: Colin Foster Tested-by: Sudeep Holla Tested-by: Douglas Anderson Tested-by: Geert Uytterhoeven Tested-by: Luca Weiss # qcom/sm7225-fairphone-fp4 Link: https://lore.kernel.org/r/20230207014207.1678715-10-saravanak@google.com Fixes: eaf9b5612a47 ("driver core: fw_devlink: Don't purge child fwnode's consumer links") Signed-off-by: Adam Ford Signed-off-by: Greg Kroah-Hartman --- drivers/of/property.c | 84 +++++++------------------------------------ 1 file changed, 13 insertions(+), 71 deletions(-) diff --git a/drivers/of/property.c b/drivers/of/property.c index 134cfc980b70..c651aad6f34b 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1062,20 +1062,6 @@ of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, return of_device_get_match_data(dev); } -static bool of_is_ancestor_of(struct device_node *test_ancestor, - struct device_node *child) -{ - of_node_get(child); - while (child) { - if (child == test_ancestor) { - of_node_put(child); - return true; - } - child = of_get_next_parent(child); - } - return false; -} - static struct device_node *of_get_compat_node(struct device_node *np) { of_node_get(np); @@ -1106,71 +1092,27 @@ static struct device_node *of_get_compat_node_parent(struct device_node *np) return node; } -/** - * of_link_to_phandle - Add fwnode link to supplier from supplier phandle - * @con_np: consumer device tree node - * @sup_np: supplier device tree node - * - * Given a phandle to a supplier device tree node (@sup_np), this function - * finds the device that owns the supplier device tree node and creates a - * device link from @dev consumer device to the supplier device. This function - * doesn't create device links for invalid scenarios such as trying to create a - * link with a parent device as the consumer of its child device. In such - * cases, it returns an error. - * - * Returns: - * - 0 if fwnode link successfully created to supplier - * - -EINVAL if the supplier link is invalid and should not be created - * - -ENODEV if struct device will never be create for supplier - */ -static int of_link_to_phandle(struct device_node *con_np, +static void of_link_to_phandle(struct device_node *con_np, struct device_node *sup_np) { - struct device *sup_dev; - struct device_node *tmp_np = sup_np; + struct device_node *tmp_np = of_node_get(sup_np); - /* - * Find the device node that contains the supplier phandle. It may be - * @sup_np or it may be an ancestor of @sup_np. - */ - sup_np = of_get_compat_node(sup_np); - if (!sup_np) { - pr_debug("Not linking %pOFP to %pOFP - No device\n", - con_np, tmp_np); - return -ENODEV; - } + /* Check that sup_np and its ancestors are available. */ + while (tmp_np) { + if (of_fwnode_handle(tmp_np)->dev) { + of_node_put(tmp_np); + break; + } - /* - * Don't allow linking a device node as a consumer of one of its - * descendant nodes. By definition, a child node can't be a functional - * dependency for the parent node. - */ - if (of_is_ancestor_of(con_np, sup_np)) { - pr_debug("Not linking %pOFP to %pOFP - is descendant\n", - con_np, sup_np); - of_node_put(sup_np); - return -EINVAL; - } + if (!of_device_is_available(tmp_np)) { + of_node_put(tmp_np); + return; + } - /* - * Don't create links to "early devices" that won't have struct devices - * created for them. - */ - sup_dev = get_dev_from_fwnode(&sup_np->fwnode); - if (!sup_dev && - (of_node_check_flag(sup_np, OF_POPULATED) || - sup_np->fwnode.flags & FWNODE_FLAG_NOT_DEVICE)) { - pr_debug("Not linking %pOFP to %pOFP - No struct device\n", - con_np, sup_np); - of_node_put(sup_np); - return -ENODEV; + tmp_np = of_get_next_parent(tmp_np); } - put_device(sup_dev); fwnode_link_add(of_fwnode_handle(con_np), of_fwnode_handle(sup_np)); - of_node_put(sup_np); - - return 0; } /** From 63f1117db59001a4e1734fba8fc6db6f3540ecdd Mon Sep 17 00:00:00 2001 From: Doug Smythies Date: Sun, 20 Aug 2023 13:46:49 -0700 Subject: [PATCH 0765/2093] cpufreq: intel_pstate: set stale CPU frequency to minimum commit d51847acb018d83186e4af67bc93f9a00a8644f7 upstream. The intel_pstate CPU frequency scaling driver does not use policy->cur and it is 0. When the CPU frequency is outdated arch_freq_get_on_cpu() will default to the nominal clock frequency when its call to cpufreq_quick_getpolicy_cur returns the never updated 0. Thus, the listed frequency might be outside of currently set limits. Some users are complaining about the high reported frequency, albeit stale, when their system is idle and/or it is above the reduced maximum they have set. This patch will maintain policy_cur for the intel_pstate driver at the current minimum CPU frequency. Reported-by: Yang Jie Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217597 Signed-off-by: Doug Smythies [ rjw: White space damage fixes and comment adjustment ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Keyon Jie Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/intel_pstate.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index d51f90f55c05..fbe3a4098743 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2574,6 +2574,11 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_clear_update_util_hook(policy->cpu); intel_pstate_hwp_set(policy->cpu); } + /* + * policy->cur is never updated with the intel_pstate driver, but it + * is used as a stale frequency value. So, keep it within limits. + */ + policy->cur = policy->min; mutex_unlock(&intel_pstate_limits_lock); From 9c8dab18f83001b38c9d3413b108d2dd5671d07f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 22 Nov 2022 13:53:38 +0800 Subject: [PATCH 0766/2093] crypto: rsa-pkcs1pad - Use helper to set reqsize commit 5b11d1a360ea23c80c6d4ec3f5986a788d0a0995 upstream. The value of reqsize must only be changed through the helper. Signed-off-by: Herbert Xu Cc: Giovanni Cabiddu Signed-off-by: Greg Kroah-Hartman --- crypto/rsa-pkcs1pad.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c index 3237b50baf3c..1cf267bc6f9e 100644 --- a/crypto/rsa-pkcs1pad.c +++ b/crypto/rsa-pkcs1pad.c @@ -575,6 +575,10 @@ static int pkcs1pad_init_tfm(struct crypto_akcipher *tfm) return PTR_ERR(child_tfm); ctx->child = child_tfm; + + akcipher_set_reqsize(tfm, sizeof(struct pkcs1pad_request) + + crypto_akcipher_reqsize(child_tfm)); + return 0; } @@ -670,7 +674,6 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.set_pub_key = pkcs1pad_set_pub_key; inst->alg.set_priv_key = pkcs1pad_set_priv_key; inst->alg.max_size = pkcs1pad_get_max_size; - inst->alg.reqsize = sizeof(struct pkcs1pad_request) + rsa_alg->reqsize; inst->free = pkcs1pad_free; From 181831df9de837fc3fc170814e83dfaf3c8f7646 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Mon, 4 Sep 2023 21:12:10 +0300 Subject: [PATCH 0767/2093] tpm: Enable hwrng only for Pluton on AMD CPUs commit 8f7f35e5aa6f2182eabcfa3abef4d898a48e9aa8 upstream. The vendor check introduced by commit 554b841d4703 ("tpm: Disable RNG for all AMD fTPMs") doesn't work properly on a number of Intel fTPMs. On the reported systems the TPM doesn't reply at bootup and returns back the command code. This makes the TPM fail probe on Lenovo Legion Y540 laptop. Since only Microsoft Pluton is the only known combination of AMD CPU and fTPM from other vendor, disable hwrng otherwise. In order to make sysadmin aware of this, print also info message to the klog. Cc: stable@vger.kernel.org Fixes: 554b841d4703 ("tpm: Disable RNG for all AMD fTPMs") Reported-by: Todd Brandt Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217804 Reported-by: Patrick Steinhardt Reported-by: Raymond Jay Golo Reported-by: Ronan Pigott Reviewed-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen Cc: Thorsten Leemhuis Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_crb.c | 33 ++++++++------------------------- 1 file changed, 8 insertions(+), 25 deletions(-) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 7f7f3bded453..db0b774207d3 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -463,28 +463,6 @@ static bool crb_req_canceled(struct tpm_chip *chip, u8 status) return (cancel & CRB_CANCEL_INVOKE) == CRB_CANCEL_INVOKE; } -static int crb_check_flags(struct tpm_chip *chip) -{ - u32 val; - int ret; - - ret = crb_request_locality(chip, 0); - if (ret) - return ret; - - ret = tpm2_get_tpm_pt(chip, TPM2_PT_MANUFACTURER, &val, NULL); - if (ret) - goto release; - - if (val == 0x414D4400U /* AMD */) - chip->flags |= TPM_CHIP_FLAG_HWRNG_DISABLED; - -release: - crb_relinquish_locality(chip, 0); - - return ret; -} - static const struct tpm_class_ops tpm_crb = { .flags = TPM_OPS_AUTO_STARTUP, .status = crb_status, @@ -826,9 +804,14 @@ static int crb_acpi_add(struct acpi_device *device) if (rc) goto out; - rc = crb_check_flags(chip); - if (rc) - goto out; +#ifdef CONFIG_X86 + /* A quirk for https://www.amd.com/en/support/kb/faq/pa-410 */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + priv->sm != ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON) { + dev_info(dev, "Disabling hwrng\n"); + chip->flags |= TPM_CHIP_FLAG_HWRNG_DISABLED; + } +#endif /* CONFIG_X86 */ rc = tpm_chip_register(chip); From 45e3dfbf0e0c33e62614cb02c5df6b39a97d28cc Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 14 Jan 2023 10:39:11 +0100 Subject: [PATCH 0768/2093] KVM: x86/mmu: Use kstrtobool() instead of strtobool() commit 11b36fe7d4500c8ef73677c087f302fd713101c2 upstream. strtobool() is the same as kstrtobool(). However, the latter is more used within the kernel. In order to remove strtobool() and slightly simplify kstrtox.h, switch to the other function name. While at it, include the corresponding header file () Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/670882aa04dbdd171b46d3b20ffab87158454616.1673689135.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sean Christopherson Signed-off-by: Luiz Capitulino Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu/mmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index beca03556379..c089242008b3 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -6667,7 +6668,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) new_val = 1; else if (sysfs_streq(val, "auto")) new_val = get_nx_auto_mode(); - else if (strtobool(val, &new_val) < 0) + else if (kstrtobool(val, &new_val) < 0) return -EINVAL; __set_nx_huge_pages(new_val); From 8c737d950c2b6d69b86d05ef8fde85a9ab2d27a1 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 1 Jun 2023 17:58:59 -0700 Subject: [PATCH 0769/2093] KVM: x86/mmu: Add "never" option to allow sticky disabling of nx_huge_pages commit 0b210faf337314e4bc88e796218bc70c72a51209 upstream. Add a "never" option to the nx_huge_pages module param to allow userspace to do a one-way hard disabling of the mitigation, and don't create the per-VM recovery threads when the mitigation is hard disabled. Letting userspace pinky swear that userspace doesn't want to enable NX mitigation (without reloading KVM) allows certain use cases to avoid the latency problems associated with spawning a kthread for each VM. E.g. in FaaS use cases, the guest kernel is trusted and the host may create 100+ VMs per logical CPU, which can result in 100ms+ latencies when a burst of VMs is created. Reported-by: Li RongQing Closes: https://lore.kernel.org/all/1679555884-32544-1-git-send-email-lirongqing@baidu.com Cc: Yong He Cc: Robert Hoo Cc: Kai Huang Reviewed-by: Robert Hoo Acked-by: Kai Huang Tested-by: Luiz Capitulino Reviewed-by: Li RongQing Link: https://lore.kernel.org/r/20230602005859.784190-1-seanjc@google.com Signed-off-by: Sean Christopherson [ Resolved a small conflict in arch/x86/kvm/mmu/mmu.c::kvm_mmu_post_init_vm() which is due kvm_nx_lpage_recovery_worker() being renamed in upstream commit 55c510e26ab6181c132327a8b90c864e6193ce27 ] Signed-off-by: Luiz Capitulino Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu/mmu.c | 41 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c089242008b3..7a6df4b62c1b 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -56,6 +56,8 @@ extern bool itlb_multihit_kvm_mitigation; +static bool nx_hugepage_mitigation_hard_disabled; + int __read_mostly nx_huge_pages = -1; static uint __read_mostly nx_huge_pages_recovery_period_ms; #ifdef CONFIG_PREEMPT_RT @@ -65,12 +67,13 @@ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; static uint __read_mostly nx_huge_pages_recovery_ratio = 60; #endif +static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp); static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp); static const struct kernel_param_ops nx_huge_pages_ops = { .set = set_nx_huge_pages, - .get = param_get_bool, + .get = get_nx_huge_pages, }; static const struct kernel_param_ops nx_huge_pages_recovery_param_ops = { @@ -6645,6 +6648,14 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) +{ + if (nx_hugepage_mitigation_hard_disabled) + return sprintf(buffer, "never\n"); + + return param_get_bool(buffer, kp); +} + static bool get_nx_auto_mode(void) { /* Return true when CPU has the bug, and mitigations are ON */ @@ -6661,15 +6672,29 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) bool old_val = nx_huge_pages; bool new_val; + if (nx_hugepage_mitigation_hard_disabled) + return -EPERM; + /* In "auto" mode deploy workaround only if CPU has the bug. */ - if (sysfs_streq(val, "off")) + if (sysfs_streq(val, "off")) { new_val = 0; - else if (sysfs_streq(val, "force")) + } else if (sysfs_streq(val, "force")) { new_val = 1; - else if (sysfs_streq(val, "auto")) + } else if (sysfs_streq(val, "auto")) { new_val = get_nx_auto_mode(); - else if (kstrtobool(val, &new_val) < 0) + } else if (sysfs_streq(val, "never")) { + new_val = 0; + + mutex_lock(&kvm_lock); + if (!list_empty(&vm_list)) { + mutex_unlock(&kvm_lock); + return -EBUSY; + } + nx_hugepage_mitigation_hard_disabled = true; + mutex_unlock(&kvm_lock); + } else if (kstrtobool(val, &new_val) < 0) { return -EINVAL; + } __set_nx_huge_pages(new_val); @@ -6800,6 +6825,9 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel uint old_period, new_period; int err; + if (nx_hugepage_mitigation_hard_disabled) + return -EPERM; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); @@ -6923,6 +6951,9 @@ int kvm_mmu_post_init_vm(struct kvm *kvm) { int err; + if (nx_hugepage_mitigation_hard_disabled) + return 0; + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, "kvm-nx-lpage-recovery", &kvm->arch.nx_lpage_recovery_thread); From 8f965b5b525d50c9cf7601de55c9918346ec7cf6 Mon Sep 17 00:00:00 2001 From: Jordan Rife Date: Mon, 21 Aug 2023 16:45:23 -0500 Subject: [PATCH 0770/2093] net: Avoid address overwrite in kernel_connect commit 0bdf399342c5acbd817c9098b6c7ed21f1974312 upstream. BPF programs that run on connect can rewrite the connect address. For the connect system call this isn't a problem, because a copy of the address is made when it is moved into kernel space. However, kernel_connect simply passes through the address it is given, so the caller may observe its address value unexpectedly change. A practical example where this is problematic is where NFS is combined with a system such as Cilium which implements BPF-based load balancing. A common pattern in software-defined storage systems is to have an NFS mount that connects to a persistent virtual IP which in turn maps to an ephemeral server IP. This is usually done to achieve high availability: if your server goes down you can quickly spin up a replacement and remap the virtual IP to that endpoint. With BPF-based load balancing, mounts will forget the virtual IP address when the address rewrite occurs because a pointer to the only copy of that address is passed down the stack. Server failover then breaks, because clients have forgotten the virtual IP address. Reconnects fail and mounts remain broken. This patch was tested by setting up a scenario like this and ensuring that NFS reconnects worked after applying the patch. Signed-off-by: Jordan Rife Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/socket.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/socket.c b/net/socket.c index c2e0a22f16d9..d281a7ef4b1d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3507,7 +3507,11 @@ EXPORT_SYMBOL(kernel_accept); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { - return sock->ops->connect(sock, addr, addrlen, flags); + struct sockaddr_storage address; + + memcpy(&address, addr, addrlen); + + return sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); From 7ac1467f9472af5e7bee1ce923569677fc84fe5b Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Fri, 4 Aug 2023 11:13:04 -0400 Subject: [PATCH 0771/2093] drm/amd/display: ensure async flips are only accepted for fast updates commit a7c0cad0dc060bb77e9c9d235d68441b0fc69507 upstream. We should be checking to see if async flips are supported in amdgpu_dm_atomic_check() (i.e. not dm_crtc_helper_atomic_check()). Also, async flipping isn't supported if a plane's framebuffer changes memory domains during an atomic commit. So, move the check from dm_crtc_helper_atomic_check() to amdgpu_dm_atomic_check() and check if the memory domain has changed in amdgpu_dm_atomic_check(). Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2733 Fixes: c1e18c44dc7f ("drm/amd/display: only accept async flips for fast updates") Reviewed-by: Harry Wentland Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Cc: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 ++++++++++++++++--- .../amd/display/amdgpu_dm/amdgpu_dm_crtc.c | 12 ---------- 2 files changed, 21 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9beb326a9528..c8e562dcd99d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7858,10 +7858,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * fast updates. */ if (crtc->state->async_flip && - acrtc_state->update_type != UPDATE_TYPE_FAST) + (acrtc_state->update_type != UPDATE_TYPE_FAST || + get_mem_type(old_plane_state->fb) != get_mem_type(fb))) drm_warn_once(state->dev, "[PLANE:%d:%s] async flip with non-fast update\n", plane->base.id, plane->name); + bundle->flip_addrs[planes_count].flip_immediate = crtc->state->async_flip && acrtc_state->update_type == UPDATE_TYPE_FAST && @@ -9813,6 +9815,11 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, /* Remove exiting planes if they are modified */ for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { + if (old_plane_state->fb && new_plane_state->fb && + get_mem_type(old_plane_state->fb) != + get_mem_type(new_plane_state->fb)) + lock_and_validation_needed = true; + ret = dm_update_plane_state(dc, state, plane, old_plane_state, new_plane_state, @@ -10064,9 +10071,20 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, struct dm_crtc_state *dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); + /* + * Only allow async flips for fast updates that don't change + * the FB pitch, the DCC state, rotation, etc. + */ + if (new_crtc_state->async_flip && lock_and_validation_needed) { + drm_dbg_atomic(crtc->dev, + "[CRTC:%d:%s] async flips are only supported for fast updates\n", + crtc->base.id, crtc->name); + ret = -EINVAL; + goto fail; + } + dm_new_crtc_state->update_type = lock_and_validation_needed ? - UPDATE_TYPE_FULL : - UPDATE_TYPE_FAST; + UPDATE_TYPE_FULL : UPDATE_TYPE_FAST; } /* Must be success */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index b9b70f4562c7..1ec643a0d00d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -406,18 +406,6 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return -EINVAL; } - /* - * Only allow async flips for fast updates that don't change the FB - * pitch, the DCC state, rotation, etc. - */ - if (crtc_state->async_flip && - dm_crtc_state->update_type != UPDATE_TYPE_FAST) { - drm_dbg_atomic(crtc->dev, - "[CRTC:%d:%s] async flips are only supported for fast updates\n", - crtc->base.id, crtc->name); - return -EINVAL; - } - /* In some use cases, like reset, no stream is attached */ if (!dm_crtc_state->stream) return 0; From 6ac8f2c8362afd2baa8e7b9c946597589e587d22 Mon Sep 17 00:00:00 2001 From: Vladislav Efanov Date: Thu, 2 Feb 2023 17:04:56 +0300 Subject: [PATCH 0772/2093] udf: Check consistency of Space Bitmap Descriptor commit 1e0d4adf17e7ef03281d7b16555e7c1508c8ed2d upstream. Bits, which are related to Bitmap Descriptor logical blocks, are not reset when buffer headers are allocated for them. As the result, these logical blocks can be treated as free and be used for other blocks.This can cause usage of one buffer header for several types of data. UDF issues WARNING in this situation: WARNING: CPU: 0 PID: 2703 at fs/udf/inode.c:2014 __udf_add_aext+0x685/0x7d0 fs/udf/inode.c:2014 RIP: 0010:__udf_add_aext+0x685/0x7d0 fs/udf/inode.c:2014 Call Trace: udf_setup_indirect_aext+0x573/0x880 fs/udf/inode.c:1980 udf_add_aext+0x208/0x2e0 fs/udf/inode.c:2067 udf_insert_aext fs/udf/inode.c:2233 [inline] udf_update_extents fs/udf/inode.c:1181 [inline] inode_getblk+0x1981/0x3b70 fs/udf/inode.c:885 Found by Linux Verification Center (linuxtesting.org) with syzkaller. [JK: Somewhat cleaned up the boundary checks] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Vladislav Efanov Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/balloc.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index 8e597db4d971..f416b7fe092f 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -36,18 +36,41 @@ static int read_block_bitmap(struct super_block *sb, unsigned long bitmap_nr) { struct buffer_head *bh = NULL; - int retval = 0; + int i; + int max_bits, off, count; struct kernel_lb_addr loc; loc.logicalBlockNum = bitmap->s_extPosition; loc.partitionReferenceNum = UDF_SB(sb)->s_partition; bh = udf_tread(sb, udf_get_lb_pblock(sb, &loc, block)); - if (!bh) - retval = -EIO; - bitmap->s_block_bitmap[bitmap_nr] = bh; - return retval; + if (!bh) + return -EIO; + + /* Check consistency of Space Bitmap buffer. */ + max_bits = sb->s_blocksize * 8; + if (!bitmap_nr) { + off = sizeof(struct spaceBitmapDesc) << 3; + count = min(max_bits - off, bitmap->s_nr_groups); + } else { + /* + * Rough check if bitmap number is too big to have any bitmap + * blocks reserved. + */ + if (bitmap_nr > + (bitmap->s_nr_groups >> (sb->s_blocksize_bits + 3)) + 2) + return 0; + off = 0; + count = bitmap->s_nr_groups - bitmap_nr * max_bits + + (sizeof(struct spaceBitmapDesc) << 3); + count = min(count, max_bits); + } + + for (i = 0; i < count; i++) + if (udf_test_bit(i + off, bh->b_data)) + return -EFSCORRUPTED; + return 0; } static int __load_block_bitmap(struct super_block *sb, From b990ac56447cac611cc661e33622c36b7a45cea8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Dec 2022 20:10:35 +0100 Subject: [PATCH 0773/2093] udf: Handle error when adding extent to a file commit 19fd80de0a8b5170ef34704c8984cca920dffa59 upstream. When adding extent to a file fails, so far we've silently squelshed the error. Make sure to propagate it up properly. Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 41 +++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index a4e875b61f89..1cdad5e9950b 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -57,15 +57,15 @@ static int udf_update_inode(struct inode *, int); static int udf_sync_inode(struct inode *inode); static int udf_alloc_i_data(struct inode *inode, size_t size); static sector_t inode_getblk(struct inode *, sector_t, int *, int *); -static int8_t udf_insert_aext(struct inode *, struct extent_position, - struct kernel_lb_addr, uint32_t); +static int udf_insert_aext(struct inode *, struct extent_position, + struct kernel_lb_addr, uint32_t); static void udf_split_extents(struct inode *, int *, int, udf_pblk_t, struct kernel_long_ad *, int *); static void udf_prealloc_extents(struct inode *, int, int, struct kernel_long_ad *, int *); static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *); -static void udf_update_extents(struct inode *, struct kernel_long_ad *, int, - int, struct extent_position *); +static int udf_update_extents(struct inode *, struct kernel_long_ad *, int, + int, struct extent_position *); static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); static void __udf_clear_extent_cache(struct inode *inode) @@ -888,7 +888,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* write back the new extents, inserting new extents if the new number * of extents is greater than the old number, and deleting extents if * the new number of extents is less than the old number */ - udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + *err = udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + if (*err < 0) + goto out_free; newblock = udf_get_pblock(inode->i_sb, newblocknum, iinfo->i_location.partitionReferenceNum, 0); @@ -1156,21 +1158,30 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, } } -static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, - int startnum, int endnum, - struct extent_position *epos) +static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, + int startnum, int endnum, + struct extent_position *epos) { int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; + int err; if (startnum > endnum) { for (i = 0; i < (startnum - endnum); i++) udf_delete_aext(inode, *epos); } else if (startnum < endnum) { for (i = 0; i < (endnum - startnum); i++) { - udf_insert_aext(inode, *epos, laarr[i].extLocation, - laarr[i].extLength); + err = udf_insert_aext(inode, *epos, + laarr[i].extLocation, + laarr[i].extLength); + /* + * If we fail here, we are likely corrupting the extent + * list and leaking blocks. At least stop early to + * limit the damage. + */ + if (err < 0) + return err; udf_next_aext(inode, epos, &laarr[i].extLocation, &laarr[i].extLength, 1); start++; @@ -1182,6 +1193,7 @@ static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } + return 0; } struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, @@ -2210,12 +2222,13 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, return etype; } -static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, - struct kernel_lb_addr neloc, uint32_t nelen) +static int udf_insert_aext(struct inode *inode, struct extent_position epos, + struct kernel_lb_addr neloc, uint32_t nelen) { struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; + int err; if (epos.bh) get_bh(epos.bh); @@ -2225,10 +2238,10 @@ static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, neloc = oeloc; nelen = (etype << 30) | oelen; } - udf_add_aext(inode, &epos, &neloc, nelen, 1); + err = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); - return (nelen >> 30); + return err; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) From f725ae7f0e2b2f1bafda9116366d3b0c88784cd9 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Wed, 12 Jul 2023 11:56:51 -0700 Subject: [PATCH 0774/2093] Input: i8042 - add quirk for TUXEDO Gemini 17 Gen1/Clevo PD70PN commit eb09074bdb05ffd6bfe77f8b4a41b76ef78c997b upstream. The touchpad of this device is both connected via PS/2 and i2c. This causes strange behavior when both driver fight for control. The easy fix is to prevent the PS/2 driver from accessing the mouse port as the full feature set of the touchpad is only supported in the i2c interface anyway. The strange behavior in this case is, that when an external screen is connected and the notebook is closed, the pointer on the external screen is moving to the lower right corner. When the notebook is opened again, this movement stops, but the touchpad clicks are unresponsive afterwards until reboot. Signed-off-by: Werner Sembach Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230607173331.851192-1-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/serio/i8042-acpipnpio.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 028e45bd050b..1724d6cb8649 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1281,6 +1281,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + /* See comment on TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU above */ + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PD5x_7xPNP_PNR_PNN_PNT"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "X170SM"), From 786e09ae59f011cc9592a00dab945a298dc5621f Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Mon, 19 Jun 2023 15:56:04 +0530 Subject: [PATCH 0775/2093] Revert "PCI: tegra194: Enable support for 256 Byte payload" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ebfde1584d9f037b6309fc682c96e22dac7bcb7a upstream. After commit 4fb8e46c1bc4 ("PCI: tegra194: Enable support for 256 Byte payload"), we initialize MPS=256 for tegra194 Root Ports before enumerating the hierarchy. Consider an Endpoint that supports only MPS=128. In the default situation (CONFIG_PCIE_BUS_DEFAULT set and no "pci=pcie_bus_*" parameter), Linux tries to configure the MPS of every device to match the upstream bridge. If the Endpoint is directly below the Root Port, Linux can reduce the Root Port MPS to 128 to match the Endpoint. But if there's a switch in the middle, Linux doesn't reduce the Root Port MPS because other devices below the switch may already be configured with MPS larger than 128. This scenario results in uncorrectable Malformed TLP errors if the Root Port sends TLPs with payloads larger than 128 bytes. These errors can be avoided by using the "pci=pcie_bus_safe" parameter, but it doesn't seem to be a good idea to always have this parameter even for basic functionality to work. Revert commit 4fb8e46c1bc4 ("PCI: tegra194: Enable support for 256 Byte payload") so the Root Ports default to MPS=128, which all devices support. If peer-to-peer DMA is not required, one can use "pci=pcie_bus_perf" to get the benefit of larger MPS settings. [bhelgaas: commit log; kwilczynski: retain "u16 val_16" declaration at the top, add missing acked by tag] Fixes: 4fb8e46c1bc4 ("PCI: tegra194: Enable support for 256 Byte payload") Link: https://lore.kernel.org/linux-pci/20230619102604.3735001-1-vidyas@nvidia.com Signed-off-by: Vidya Sagar Signed-off-by: Krzysztof Wilczyński Acked-by: Jon Hunter Cc: stable@vger.kernel.org # v6.0-rc1+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/dwc/pcie-tegra194.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 528e73ccfa43..2241029537a0 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -879,11 +879,6 @@ static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci, PCI_CAP_ID_EXP); - val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL); - val_16 &= ~PCI_EXP_DEVCTL_PAYLOAD; - val_16 |= PCI_EXP_DEVCTL_PAYLOAD_256B; - dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL, val_16); - val = dw_pcie_readl_dbi(pci, PCI_IO_BASE); val &= ~(IO_BASE_IO_DECODE | IO_BASE_IO_DECODE_BIT8); dw_pcie_writel_dbi(pci, PCI_IO_BASE, val); @@ -1872,11 +1867,6 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci, PCI_CAP_ID_EXP); - val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL); - val_16 &= ~PCI_EXP_DEVCTL_PAYLOAD; - val_16 |= PCI_EXP_DEVCTL_PAYLOAD_256B; - dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL, val_16); - /* Clear Slot Clock Configuration bit if SRNS configuration */ if (pcie->enable_srns) { val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + From b9c54fd37668bd431a2a40028c689da342fed08f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Mon, 4 Sep 2023 10:56:04 +0200 Subject: [PATCH 0776/2093] Revert "net: macsec: preserve ingress frame ordering" commit d3287e4038ca4f81e02067ab72d087af7224c68b upstream. This reverts commit ab046a5d4be4c90a3952a0eae75617b49c0cb01b. It was trying to work around an issue at the crypto layer by excluding ASYNC implementations of gcm(aes), because a bug in the AESNI version caused reordering when some requests bypassed the cryptd queue while older requests were still pending on the queue. This was fixed by commit 38b2f68b4264 ("crypto: aesni - Fix cryptd reordering problem on gcm"), which pre-dates ab046a5d4be4. Herbert Xu confirmed that all ASYNC implementations are expected to maintain the ordering of completions wrt requests, so we can use them in MACsec. On my test machine, this restores the performance of a single netperf instance, from 1.4Gbps to 4.4Gbps. Link: https://lore.kernel.org/netdev/9328d206c5d9f9239cae27e62e74de40b258471d.1692279161.git.sd@queasysnail.net/T/ Link: https://lore.kernel.org/netdev/1b0cec71-d084-8153-2ba4-72ce71abeb65@byu.edu/ Link: https://lore.kernel.org/netdev/d335ddaa-18dc-f9f0-17ee-9783d3b2ca29@mailbox.tu-dresden.de/ Fixes: ab046a5d4be4 ("net: macsec: preserve ingress frame ordering") Signed-off-by: Sabrina Dubroca Link: https://lore.kernel.org/r/11c952469d114db6fb29242e1d9545e61f52f512.1693757159.git.sd@queasysnail.net Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/macsec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 6a7965ed6300..578f470e9fad 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1331,8 +1331,7 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) struct crypto_aead *tfm; int ret; - /* Pick a sync gcm(aes) cipher to ensure order is preserved. */ - tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_aead("gcm(aes)", 0, 0); if (IS_ERR(tfm)) return tfm; From a07388d1a773abb0300b4cb8809043d247af7e22 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 9 Nov 2022 10:49:02 -0800 Subject: [PATCH 0777/2093] tools lib subcmd: Add install target commit 630ae80ea1dd253609cb50cff87f3248f901aca3 upstream. This allows libsubcmd to be installed as a dependency. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Jiri Olsa Cc: Mark Rutland Cc: Masahiro Yamada Cc: Nick Desaulniers Cc: Nicolas Schier Cc: Peter Zijlstra Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: http://lore.kernel.org/lkml/20221109184914.1357295-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/lib/subcmd/Makefile | 49 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 8f1a09cdfd17..e96566f8991c 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -17,6 +17,15 @@ RM = rm -f MAKEFLAGS += --no-print-directory +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + LIBFILE = $(OUTPUT)libsubcmd.a CFLAGS := -ggdb3 -Wall -Wextra -std=gnu99 -fPIC @@ -48,6 +57,18 @@ CFLAGS += $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) SUBCMD_IN := $(OUTPUT)libsubcmd-in.o +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) + all: export srctree OUTPUT CC LD CFLAGS V @@ -61,6 +82,34 @@ $(SUBCMD_IN): FORCE $(LIBFILE): $(SUBCMD_IN) $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(SUBCMD_IN) +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: $(LIBFILE) + $(call QUIET_INSTALL, $(LIBFILE)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,exec-cmd.h,$(prefix)/include/subcmd,644); \ + $(call do_install,help.h,$(prefix)/include/subcmd,644); \ + $(call do_install,pager.h,$(prefix)/include/subcmd,644); \ + $(call do_install,parse-options.h,$(prefix)/include/subcmd,644); \ + $(call do_install,run-command.h,$(prefix)/include/subcmd,644); + +install: install_lib install_headers + clean: $(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \ find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) From 424fd56932461e50ddb30d4a23d22261f660f9df Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 16 Nov 2022 16:43:55 -0800 Subject: [PATCH 0778/2093] tools lib subcmd: Make install_headers clearer commit 77dce6890a2a715b186bdc149c843571a5bb47df upstream. Add libsubcmd to the name so that this install_headers build appears different to similar targets in different libraries. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Daniel Borkmann Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Masahiro Yamada Cc: Namhyung Kim Cc: Nicolas Schier Cc: Peter Zijlstra Cc: Song Liu Cc: Stanislav Fomichev Cc: Stephane Eranian Cc: Yonghong Song Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20221117004356.279422-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/lib/subcmd/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index e96566f8991c..9a316d8b89df 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -101,7 +101,7 @@ install_lib: $(LIBFILE) cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ) install_headers: - $(call QUIET_INSTALL, headers) \ + $(call QUIET_INSTALL, libsubcmd_headers) \ $(call do_install,exec-cmd.h,$(prefix)/include/subcmd,644); \ $(call do_install,help.h,$(prefix)/include/subcmd,644); \ $(call do_install,pager.h,$(prefix)/include/subcmd,644); \ From 05026e944bd20bc131c13f4b485ba205fee94d9f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 1 Dec 2022 20:57:41 -0800 Subject: [PATCH 0779/2093] tools lib subcmd: Add dependency test to install_headers commit 5d890591db6bed8ca69bd4bfe0cdaca372973033 upstream. Compute the headers to be installed from their source headers and make each have its own build target to install it. Using dependencies avoids headers being reinstalled and getting a new timestamp which then causes files that depend on the header to be rebuilt. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Mark Rutland Cc: Masahiro Yamada Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Nicolas Schier Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tom Rix Cc: bpf@vger.kernel.org Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20221202045743.2639466-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/lib/subcmd/Makefile | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 9a316d8b89df..b87213263a5e 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -89,10 +89,10 @@ define do_install_mkdir endef define do_install - if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + if [ ! -d '$2' ]; then \ + $(INSTALL) -d -m 755 '$2'; \ fi; \ - $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' + $(INSTALL) $1 $(if $3,-m $3,) '$2' endef install_lib: $(LIBFILE) @@ -100,13 +100,16 @@ install_lib: $(LIBFILE) $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ) -install_headers: - $(call QUIET_INSTALL, libsubcmd_headers) \ - $(call do_install,exec-cmd.h,$(prefix)/include/subcmd,644); \ - $(call do_install,help.h,$(prefix)/include/subcmd,644); \ - $(call do_install,pager.h,$(prefix)/include/subcmd,644); \ - $(call do_install,parse-options.h,$(prefix)/include/subcmd,644); \ - $(call do_install,run-command.h,$(prefix)/include/subcmd,644); +HDRS := exec-cmd.h help.h pager.h parse-options.h run-command.h +INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/subcmd +INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS)) + +$(INSTALL_HDRS): $(INSTALL_HDRS_PFX)/%.h: %.h + $(call QUIET_INSTALL, $@) \ + $(call do_install,$<,$(INSTALL_HDRS_PFX)/,644) + +install_headers: $(INSTALL_HDRS) + $(call QUIET_INSTALL, libsubcmd_headers) install: install_lib install_headers From d35187340a8ae872f30aa620c406d12a9b9812ad Mon Sep 17 00:00:00 2001 From: Shen Jiamin Date: Thu, 15 Dec 2022 12:47:03 +0800 Subject: [PATCH 0780/2093] tools/resolve_btfids: Use pkg-config to locate libelf commit 0e43662e61f2569500ab83b8188c065603530785 upstream. When libelf was not installed in the standard location, it cannot be located by the current building config. Use pkg-config to help locate libelf in such cases. Signed-off-by: Shen Jiamin Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20221215044703.400139-1-shen_jiamin@comp.nus.edu.sg Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Makefile | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 19a3112e271a..f7375a119f54 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -56,13 +56,17 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \ $(abspath $@) install_headers +LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) +LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) + CFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ - -I$(SUBCMD_SRC) + -I$(SUBCMD_SRC) \ + $(LIBELF_FLAGS) -LIBS = -lelf -lz +LIBS = $(LIBELF_LIBS) -lz export srctree OUTPUT CFLAGS Q include $(srctree)/tools/build/Makefile.include From 2457021a4f07a57134239e10e9c72fe702d15156 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 23 Jan 2023 22:43:23 -0800 Subject: [PATCH 0781/2093] tools/resolve_btfids: Install subcmd headers commit af03299d8536d62b49c7f3cb929349eb2d66bcd5 upstream. Previously tools/lib/subcmd was added to the include path, switch to installing the headers and then including from that directory. This avoids dependencies on headers internal to tools/lib/subcmd. Add the missing subcmd directory to the affected #include. Signed-off-by: Ian Rogers Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230124064324.672022-1-irogers@google.com Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Makefile | 19 ++++++++++++++----- tools/bpf/resolve_btfids/main.c | 2 +- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index f7375a119f54..1fe0082b2ecc 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -35,21 +35,29 @@ SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ BPFOBJ := $(OUTPUT)/libbpf/libbpf.a LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/ SUBCMDOBJ := $(OUTPUT)/libsubcmd/libsubcmd.a +SUBCMD_OUT := $(abspath $(dir $(SUBCMDOBJ)))/ LIBBPF_DESTDIR := $(LIBBPF_OUT) LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include +SUBCMD_DESTDIR := $(SUBCMD_OUT) +SUBCMD_INCLUDE := $(SUBCMD_DESTDIR)include + BINARY := $(OUTPUT)/resolve_btfids BINARY_IN := $(BINARY)-in.o all: $(BINARY) +prepare: $(BPFOBJ) $(SUBCMDOBJ) + $(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT): $(call msg,MKDIR,,$@) $(Q)mkdir -p $(@) $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd - $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(SUBCMD_OUT) \ + DESTDIR=$(SUBCMD_DESTDIR) prefix= \ + $(abspath $@) install_headers $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ @@ -63,7 +71,7 @@ CFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ - -I$(SUBCMD_SRC) \ + -I$(SUBCMD_INCLUDE) \ $(LIBELF_FLAGS) LIBS = $(LIBELF_LIBS) -lz @@ -71,7 +79,7 @@ LIBS = $(LIBELF_LIBS) -lz export srctree OUTPUT CFLAGS Q include $(srctree)/tools/build/Makefile.include -$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT) +$(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) @@ -83,7 +91,8 @@ clean_objects := $(wildcard $(OUTPUT)/*.o \ $(OUTPUT)/.*.o.d \ $(LIBBPF_OUT) \ $(LIBBPF_DESTDIR) \ - $(OUTPUT)/libsubcmd \ + $(SUBCMD_OUT) \ + $(SUBCMD_DESTDIR) \ $(OUTPUT)/resolve_btfids) ifneq ($(clean_objects),) @@ -100,4 +109,4 @@ tags: FORCE: -.PHONY: all FORCE clean tags +.PHONY: all FORCE clean tags prepare diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 80cd7843c677..77058174082d 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -75,7 +75,7 @@ #include #include #include -#include +#include #define BTF_IDS_SECTION ".BTF_ids" #define BTF_ID "__BTF_ID__" From 833a654b510b1dcae258f0c461ab72c57e6feb65 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 23 Jan 2023 22:43:24 -0800 Subject: [PATCH 0782/2093] tools/resolve_btfids: Alter how HOSTCC is forced commit 13e07691a16ff31b209fbfce25c01ff296b05e45 upstream. HOSTCC is always wanted when building. Setting CC to HOSTCC happens after tools/scripts/Makefile.include is included, meaning flags are set assuming say CC is gcc, but then it can be later set to HOSTCC which may be clang. tools/scripts/Makefile.include is needed for host set up and common macros in objtool's Makefile. Rather than override CC to HOSTCC, just pass CC as HOSTCC to Makefile.build, the libsubcmd builds and the linkage step. This means the Makefiles don't see things like CC changing and tool flag determination, and similar, work properly. Also, clear the passed subdir as otherwise an outer build may break by inadvertently passing an inappropriate value. Signed-off-by: Ian Rogers Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230124064324.672022-2-irogers@google.com Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Makefile | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 1fe0082b2ecc..daed388aa5d7 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -18,14 +18,11 @@ else endif # always use the host compiler -AR = $(HOSTAR) -CC = $(HOSTCC) -LD = $(HOSTLD) -ARCH = $(HOSTARCH) +HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ + EXTRA_CFLAGS="$(HOSTCFLAGS) $(KBUILD_HOSTCFLAGS)" + RM ?= rm CROSS_COMPILE = -CFLAGS := $(KBUILD_HOSTCFLAGS) -LDFLAGS := $(KBUILD_HOSTLDFLAGS) OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -56,12 +53,12 @@ $(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT): $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(SUBCMD_OUT) \ - DESTDIR=$(SUBCMD_DESTDIR) prefix= \ + DESTDIR=$(SUBCMD_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \ $(abspath $@) install_headers $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \ + DESTDIR=$(LIBBPF_DESTDIR) $(HOST_OVERRIDES) prefix= subdir= \ $(abspath $@) install_headers LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) @@ -80,11 +77,11 @@ export srctree OUTPUT CFLAGS Q include $(srctree)/tools/build/Makefile.include $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) - $(Q)$(MAKE) $(build)=resolve_btfids + $(Q)$(MAKE) $(build)=resolve_btfids $(HOST_OVERRIDES) $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) $(call msg,LINK,$@) - $(Q)$(CC) $(BINARY_IN) $(LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) + $(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) clean_objects := $(wildcard $(OUTPUT)/*.o \ $(OUTPUT)/.*.o.cmd \ From b3f1d78c672e1f79d9f28ebece2e953cd9b0a502 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 2 Feb 2023 12:28:39 +0100 Subject: [PATCH 0783/2093] tools/resolve_btfids: Compile resolve_btfids as host program commit 56a2df7615fa050cc67b89245b2a482849077939 upstream. Making resolve_btfids to be compiled as host program so we can avoid cross compile issues as reported by Nathan. Also we no longer need HOST_OVERRIDES for BINARY target, just for 'prepare' targets. Fixes: 13e07691a16f ("tools/resolve_btfids: Alter how HOSTCC is forced") Reported-by: Nathan Chancellor Signed-off-by: Jiri Olsa Signed-off-by: Daniel Borkmann Tested-by: Nathan Chancellor Acked-by: Ian Rogers Link: https://lore.kernel.org/bpf/20230202112839.1131892-1-jolsa@kernel.org Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Build | 4 +++- tools/bpf/resolve_btfids/Makefile | 9 ++++++--- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/tools/bpf/resolve_btfids/Build b/tools/bpf/resolve_btfids/Build index ae82da03f9bf..077de3829c72 100644 --- a/tools/bpf/resolve_btfids/Build +++ b/tools/bpf/resolve_btfids/Build @@ -1,3 +1,5 @@ +hostprogs := resolve_btfids + resolve_btfids-y += main.o resolve_btfids-y += rbtree.o resolve_btfids-y += zalloc.o @@ -7,4 +9,4 @@ resolve_btfids-y += str_error_r.o $(OUTPUT)%.o: ../../lib/%.c FORCE $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) + $(call if_changed_dep,host_cc_o_c) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index daed388aa5d7..abdd68ac08f4 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -22,6 +22,9 @@ HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH) EXTRA_CFLAGS="$(HOSTCFLAGS) $(KBUILD_HOSTCFLAGS)" RM ?= rm +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar CROSS_COMPILE = OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -64,7 +67,7 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) -CFLAGS += -g \ +HOSTCFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ @@ -73,11 +76,11 @@ CFLAGS += -g \ LIBS = $(LIBELF_LIBS) -lz -export srctree OUTPUT CFLAGS Q +export srctree OUTPUT HOSTCFLAGS Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) - $(Q)$(MAKE) $(build)=resolve_btfids $(HOST_OVERRIDES) + $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) $(call msg,LINK,$@) From a2a9f5bcccab6d3a649b09a01c607650afc94c0c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 2 Feb 2023 14:42:53 -0800 Subject: [PATCH 0784/2093] tools/resolve_btfids: Tidy HOST_OVERRIDES commit e0975ab92f2406fd3e12834f62dc57cb10404f85 upstream. Don't set EXTRA_CFLAGS to HOSTCFLAGS, ensure CROSS_COMPILE isn't passed through. Signed-off-by: Ian Rogers Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230202224253.40283-1-irogers@google.com Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index abdd68ac08f4..2abdd85b4a08 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -17,9 +17,9 @@ else MAKEFLAGS=--no-print-directory endif -# always use the host compiler +# Overrides for the prepare step libraries. HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ - EXTRA_CFLAGS="$(HOSTCFLAGS) $(KBUILD_HOSTCFLAGS)" + CROSS_COMPILE="" RM ?= rm HOSTCC ?= gcc From 1ad863e91af88d0bdb559a34f0bb678887ec2b3e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 9 Feb 2023 15:37:35 +0100 Subject: [PATCH 0785/2093] tools/resolve_btfids: Pass HOSTCFLAGS as EXTRA_CFLAGS to prepare targets commit 2531ba0e4ae67d6d0219400af27805fe52cd28e8 upstream. Thorsten reported build issue with command line that defined extra HOSTCFLAGS that were not passed into 'prepare' targets, but were used to build resolve_btfids objects. This results in build fail when these objects are linked together: /usr/bin/ld: /build.../tools/bpf/resolve_btfids//libbpf/libbpf.a(libbpf-in.o): relocation R_X86_64_32 against `.rodata.str1.1' can not be used when making a PIE \ object; recompile with -fPIE Fixing this by passing HOSTCFLAGS in EXTRA_CFLAGS as part of HOST_OVERRIDES variable for prepare targets. [1] https://lore.kernel.org/bpf/f7922132-6645-6316-5675-0ece4197bfff@leemhuis.info/ Fixes: 56a2df7615fa ("tools/resolve_btfids: Compile resolve_btfids as host program") Reported-by: Thorsten Leemhuis Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Tested-by: Thorsten Leemhuis Acked-by: Ian Rogers Link: https://lore.kernel.org/bpf/20230209143735.4112845-1-jolsa@kernel.org Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 2abdd85b4a08..ac548a7baa73 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -19,7 +19,7 @@ endif # Overrides for the prepare step libraries. HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ - CROSS_COMPILE="" + CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)" RM ?= rm HOSTCC ?= gcc From 0c7e6ff75e6ce8ef9b8a04edeee733612f755078 Mon Sep 17 00:00:00 2001 From: Viktor Malik Date: Tue, 30 May 2023 14:33:52 +0200 Subject: [PATCH 0786/2093] tools/resolve_btfids: Fix setting HOSTCFLAGS commit edd75c802855271c8610f58a2fc9e54aefc49ce5 upstream. Building BPF selftests with custom HOSTCFLAGS yields an error: # make HOSTCFLAGS="-O2" [...] HOSTCC ./tools/testing/selftests/bpf/tools/build/resolve_btfids/main.o main.c:73:10: fatal error: linux/rbtree.h: No such file or directory 73 | #include | ^~~~~~~~~~~~~~~~ The reason is that tools/bpf/resolve_btfids/Makefile passes header include paths by extending HOSTCFLAGS which is overridden by setting HOSTCFLAGS in the make command (because of Makefile rules [1]). This patch fixes the above problem by passing the include paths via `HOSTCFLAGS_resolve_btfids` which is used by tools/build/Build.include and can be combined with overridding HOSTCFLAGS. [1] https://www.gnu.org/software/make/manual/html_node/Overriding.html Fixes: 56a2df7615fa ("tools/resolve_btfids: Compile resolve_btfids as host program") Signed-off-by: Viktor Malik Signed-off-by: Andrii Nakryiko Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230530123352.1308488-1-vmalik@redhat.com Cc: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- tools/bpf/resolve_btfids/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index ac548a7baa73..4b8079f294f6 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -67,7 +67,7 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) -HOSTCFLAGS += -g \ +HOSTCFLAGS_resolve_btfids += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ @@ -76,7 +76,7 @@ HOSTCFLAGS += -g \ LIBS = $(LIBELF_LIBS) -lz -export srctree OUTPUT HOSTCFLAGS Q HOSTCC HOSTLD HOSTAR +export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) From 9720f894286efd59a715289ced87d00e5bf05563 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sun, 4 Jun 2023 12:16:06 +0100 Subject: [PATCH 0787/2093] reiserfs: Check the return value from __getblk() [ Upstream commit ba38980add7ffc9e674ada5b4ded4e7d14e76581 ] __getblk() can return a NULL pointer if we run out of memory or if we try to access beyond the end of the device; check it and handle it appropriately. Signed-off-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/lkml/CAFcO6XOacq3hscbXevPQP7sXRoYFz34ZdKPYjmd6k5sZuhGFDw@mail.gmail.com/ Tested-by: butt3rflyh4ck Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") # probably introduced in 2002 Acked-by: Edward Shishkin Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/reiserfs/journal.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 9f62da7471c9..eb81b4170cb5 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2326,7 +2326,7 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, int i, j; bh = __getblk(dev, block, bufsize); - if (buffer_uptodate(bh)) + if (!bh || buffer_uptodate(bh)) return (bh); if (block + BUFNR > max_block) { @@ -2336,6 +2336,8 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, j = 1; for (i = 1; i < blocks; i++) { bh = __getblk(dev, block + i, bufsize); + if (!bh) + break; if (buffer_uptodate(bh)) { brelse(bh); break; From e12214c7ad13516a422ec1d6e0eb79148885a032 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Sun, 9 Jul 2023 14:54:51 +0800 Subject: [PATCH 0788/2093] eventfd: prevent underflow for eventfd semaphores [ Upstream commit 758b492047816a3158d027e9fca660bc5bcf20bf ] For eventfd with flag EFD_SEMAPHORE, when its ctx->count is 0, calling eventfd_ctx_do_read will cause ctx->count to overflow to ULLONG_MAX. An underflow can happen with EFD_SEMAPHORE eventfds in at least the following three subsystems: (1) virt/kvm/eventfd.c (2) drivers/vfio/virqfd.c (3) drivers/virt/acrn/irqfd.c where (2) and (3) are just modeled after (1). An eventfd must be specified for use with the KVM_IRQFD ioctl(). This can also be an EFD_SEMAPHORE eventfd. When the eventfd count is zero or has been decremented to zero an underflow can be triggered when the irqfd is shut down by raising the KVM_IRQFD_FLAG_DEASSIGN flag in the KVM_IRQFD ioctl(): // ctx->count == 0 kvm_vm_ioctl() -> kvm_irqfd() -> kvm_irqfd_deassign() -> irqfd_deactivate() -> irqfd_shutdown() -> eventfd_ctx_remove_wait_queue(&cnt) -> eventfd_ctx_do_read(&cnt) Userspace polling on the eventfd wouldn't notice the underflow because 1 is always returned as the value from eventfd_read() while ctx->count would've underflowed. It's not a huge deal because this should only be happening when the irqfd is shutdown but we should still fix it and avoid the spurious wakeup. Fixes: cb289d6244a3 ("eventfd - allow atomic read and waitqueue remove") Signed-off-by: Wen Yang Cc: Alexander Viro Cc: Jens Axboe Cc: Christian Brauner Cc: Christoph Hellwig Cc: Dylan Yudaken Cc: David Woodhouse Cc: Matthew Wilcox Cc: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Message-Id: [brauner: rewrite commit message and add explanation how this underflow can happen] Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/eventfd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/eventfd.c b/fs/eventfd.c index 249ca6c0b784..4a60ea932e3d 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -189,7 +189,7 @@ void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { lockdep_assert_held(&ctx->wqh.lock); - *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; + *cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count; ctx->count -= *cnt; } EXPORT_SYMBOL_GPL(eventfd_ctx_do_read); From b553ac4894e700c90b03f1875b5fa30d3c3cb326 Mon Sep 17 00:00:00 2001 From: Wang Ming Date: Thu, 13 Jul 2023 20:05:42 +0800 Subject: [PATCH 0789/2093] fs: Fix error checking for d_hash_and_lookup() [ Upstream commit 0d5a4f8f775ff990142cdc810a84eae078589d27 ] The d_hash_and_lookup() function returns error pointers or NULL. Most incorrect error checks were fixed, but the one in int path_pts() was forgotten. Fixes: eedf265aa003 ("devpts: Make each mount of devpts an independent filesystem.") Signed-off-by: Wang Ming Message-Id: <20230713120555.7025-1-machel@vivo.com> Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/namei.c b/fs/namei.c index 5b3865ad9d05..4248647f1ab2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2859,7 +2859,7 @@ int path_pts(struct path *path) dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); - if (!child) + if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; From 254c396da3a29e190ab60e260f99f561543e57d4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 2 Jun 2023 18:09:11 -0400 Subject: [PATCH 0790/2093] iomap: Remove large folio handling in iomap_invalidate_folio() [ Upstream commit a221ab717c43147f728d93513923ba3528f861bf ] We do not need to release the iomap_page in iomap_invalidate_folio() to allow the folio to be split. The splitting code will call ->release_folio() if there is still per-fs private data attached to the folio. At that point, we will check if the folio is still dirty and decline to release the iomap_page. It is possible to trigger the warning in perfectly legitimate circumstances (eg if a disk read fails, we do a partial write to the folio, then we truncate the folio), which will cause those writes to be lost. Fixes: 60d8231089f0 ("iomap: Support large folios in invalidatepage") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Sasha Levin --- fs/iomap/buffered-io.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 91ee0b308e13..a0a4d8de82ca 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -488,11 +488,6 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) WARN_ON_ONCE(folio_test_writeback(folio)); folio_cancel_dirty(folio); iomap_page_release(folio); - } else if (folio_test_large(folio)) { - /* Must release the iop so the page can be split */ - WARN_ON_ONCE(!folio_test_uptodate(folio) && - folio_test_dirty(folio)); - iomap_page_release(folio); } } EXPORT_SYMBOL_GPL(iomap_invalidate_folio); From c13e6edbad1af8680896e980e55934dfc9b8248b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 1 Aug 2023 18:17:04 +0200 Subject: [PATCH 0791/2093] tmpfs: verify {g,u}id mount options correctly [ Upstream commit 0200679fc7953177941e41c2a4241d0b6c2c5de8 ] A while ago we received the following report: "The other outstanding issue I noticed comes from the fact that fsconfig syscalls may occur in a different userns than that which called fsopen. That means that resolving the uid/gid via current_user_ns() can save a kuid that isn't mapped in the associated namespace when the filesystem is finally mounted. This means that it is possible for an unprivileged user to create files owned by any group in a tmpfs mount (since we can set the SUID bit on the tmpfs directory), or a tmpfs that is owned by any user, including the root group/user." The contract for {g,u}id mount options and {g,u}id values in general set from userspace has always been that they are translated according to the caller's idmapping. In so far, tmpfs has been doing the correct thing. But since tmpfs is mountable in unprivileged contexts it is also necessary to verify that the resulting {k,g}uid is representable in the namespace of the superblock to avoid such bugs as above. The new mount api's cross-namespace delegation abilities are already widely used. After having talked to a bunch of userspace this is the most faithful solution with minimal regression risks. I know of one users - systemd - that makes use of the new mount api in this way and they don't set unresolable {g,u}ids. So the regression risk is minimal. Link: https://lore.kernel.org/lkml/CALxfFW4BXhEwxR0Q5LSkg-8Vb4r2MONKCcUCVioehXQKr35eHg@mail.gmail.com Fixes: f32356261d44 ("vfs: Convert ramfs, shmem, tmpfs, devtmpfs, rootfs to use the new mount API") Reviewed-by: "Seth Forshee (DigitalOcean)" Reported-by: Seth Jenkins Message-Id: <20230801-vfs-fs_context-uidgid-v1-1-daf46a050bbf@kernel.org> Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- mm/shmem.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 10365ced5b1f..806741bbe4a6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3485,6 +3485,8 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) unsigned long long size; char *rest; int opt; + kuid_t kuid; + kgid_t kgid; opt = fs_parse(fc, shmem_fs_parameters, param, &result); if (opt < 0) @@ -3520,14 +3522,32 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) ctx->mode = result.uint_32 & 07777; break; case Opt_uid: - ctx->uid = make_kuid(current_user_ns(), result.uint_32); - if (!uid_valid(ctx->uid)) + kuid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(kuid)) goto bad_value; + + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fc->user_ns, kuid)) + goto bad_value; + + ctx->uid = kuid; break; case Opt_gid: - ctx->gid = make_kgid(current_user_ns(), result.uint_32); - if (!gid_valid(ctx->gid)) + kgid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(kgid)) goto bad_value; + + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fc->user_ns, kgid)) + goto bad_value; + + ctx->gid = kgid; break; case Opt_huge: ctx->huge = result.uint_32; From 1cdf51b4e5ef531311e2ae9eb207f895148042ad Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 7 Aug 2023 10:43:58 -0700 Subject: [PATCH 0792/2093] selftests/harness: Actually report SKIP for signal tests [ Upstream commit b3d46e11fec0c5a8972e5061bb1462119ae5736d ] Tests that were expecting a signal were not correctly checking for a SKIP condition. Move the check before the signal checking when processing test result. Cc: Shuah Khan Cc: Andy Lutomirski Cc: Will Drewry Cc: linux-kselftest@vger.kernel.org Fixes: 9847d24af95c ("selftests/harness: Refactor XFAIL into SKIP") Signed-off-by: Kees Cook Signed-off-by: Sasha Levin --- tools/testing/selftests/kselftest_harness.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 25f4d54067c0..584687c3286d 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -937,7 +937,11 @@ void __wait_for_test(struct __test_metadata *t) fprintf(TH_LOG_STREAM, "# %s: Test terminated by timeout\n", t->name); } else if (WIFEXITED(status)) { - if (t->termsig != -1) { + if (WEXITSTATUS(status) == 255) { + /* SKIP */ + t->passed = 1; + t->skip = 1; + } else if (t->termsig != -1) { t->passed = 0; fprintf(TH_LOG_STREAM, "# %s: Test exited normally instead of by signal (code: %d)\n", @@ -949,11 +953,6 @@ void __wait_for_test(struct __test_metadata *t) case 0: t->passed = 1; break; - /* SKIP */ - case 255: - t->passed = 1; - t->skip = 1; - break; /* Other failure, assume step report. */ default: t->passed = 0; From ed134f284b4ed85a70d5f760ed0686e3cd555f9b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 8 Aug 2023 07:34:20 -0400 Subject: [PATCH 0793/2093] vfs, security: Fix automount superblock LSM init problem, preventing NFS sb sharing [ Upstream commit d80a8f1b58c2bc8d7c6bfb65401ea4f7ec8cddc2 ] When NFS superblocks are created by automounting, their LSM parameters aren't set in the fs_context struct prior to sget_fc() being called, leading to failure to match existing superblocks. This bug leads to messages like the following appearing in dmesg when fscache is enabled: NFS: Cache volume key already in use (nfs,4.2,2,108,106a8c0,1,,,,100000,100000,2ee,3a98,1d4c,3a98,1) Fix this by adding a new LSM hook to load fc->security for submount creation. Signed-off-by: David Howells Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/165962680944.3334508.6610023900349142034.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/165962729225.3357250.14350728846471527137.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/165970659095.2812394.6868894171102318796.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/166133579016.3678898.6283195019480567275.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/217595.1662033775@warthog.procyon.org.uk/ # v5 Fixes: 9bc61ab18b1d ("vfs: Introduce fs_context, switch vfs_kern_mount() to it.") Fixes: 779df6a5480f ("NFS: Ensure security label is set for root inode") Tested-by: Jeff Layton Acked-by: Casey Schaufler Acked-by: "Christian Brauner (Microsoft)" Acked-by: Paul Moore Reviewed-by: Jeff Layton Message-Id: <20230808-master-v9-1-e0ecde888221@kernel.org> Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/fs_context.c | 23 +++++++++++++++- include/linux/lsm_hook_defs.h | 1 + include/linux/security.h | 6 +++++ security/security.c | 14 ++++++++++ security/selinux/hooks.c | 22 +++++++++++++++ security/smack/smack_lsm.c | 51 +++++++++++++++++++++++++++++++++++ 6 files changed, 116 insertions(+), 1 deletion(-) diff --git a/fs/fs_context.c b/fs/fs_context.c index 851214d1d013..375023e40161 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -315,10 +315,31 @@ struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, } EXPORT_SYMBOL(fs_context_for_reconfigure); +/** + * fs_context_for_submount: allocate a new fs_context for a submount + * @type: file_system_type of the new context + * @reference: reference dentry from which to copy relevant info + * + * Allocate a new fs_context suitable for a submount. This also ensures that + * the fc->security object is inherited from @reference (if needed). + */ struct fs_context *fs_context_for_submount(struct file_system_type *type, struct dentry *reference) { - return alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT); + struct fs_context *fc; + int ret; + + fc = alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT); + if (IS_ERR(fc)) + return fc; + + ret = security_fs_context_submount(fc, reference->d_sb); + if (ret) { + put_fs_context(fc); + return ERR_PTR(ret); + } + + return fc; } EXPORT_SYMBOL(fs_context_for_submount); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ec119da1d89b..4a97a6db9bce 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -54,6 +54,7 @@ LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *f LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) +LSM_HOOK(int, 0, fs_context_submount, struct fs_context *fc, struct super_block *reference) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, diff --git a/include/linux/security.h b/include/linux/security.h index ca1b7109c0db..a6c97cc57caa 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -293,6 +293,7 @@ int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); +int security_fs_context_submount(struct fs_context *fc, struct super_block *reference); int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc); int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param); int security_sb_alloc(struct super_block *sb); @@ -625,6 +626,11 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm) { } +static inline int security_fs_context_submount(struct fs_context *fc, + struct super_block *reference) +{ + return 0; +} static inline int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { diff --git a/security/security.c b/security/security.c index 75dc0947ee0c..5fa286ae9908 100644 --- a/security/security.c +++ b/security/security.c @@ -882,6 +882,20 @@ void security_bprm_committed_creds(struct linux_binprm *bprm) call_void_hook(bprm_committed_creds, bprm); } +/** + * security_fs_context_submount() - Initialise fc->security + * @fc: new filesystem context + * @reference: dentry reference for submount/remount + * + * Fill out the ->security field for a new fs_context. + * + * Return: Returns 0 on success or negative error code on failure. + */ +int security_fs_context_submount(struct fs_context *fc, struct super_block *reference) +{ + return call_int_hook(fs_context_submount, 0, fc, reference); +} + int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, 0, fc, src_fc); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f553c370397e..26c9e4da4efc 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2766,6 +2766,27 @@ static int selinux_umount(struct vfsmount *mnt, int flags) FILESYSTEM__UNMOUNT, NULL); } +static int selinux_fs_context_submount(struct fs_context *fc, + struct super_block *reference) +{ + const struct superblock_security_struct *sbsec; + struct selinux_mnt_opts *opts; + + opts = kzalloc(sizeof(*opts), GFP_KERNEL); + if (!opts) + return -ENOMEM; + + sbsec = selinux_superblock(reference); + if (sbsec->flags & FSCONTEXT_MNT) + opts->fscontext_sid = sbsec->sid; + if (sbsec->flags & CONTEXT_MNT) + opts->context_sid = sbsec->mntpoint_sid; + if (sbsec->flags & DEFCONTEXT_MNT) + opts->defcontext_sid = sbsec->def_sid; + fc->security = opts; + return 0; +} + static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { @@ -7263,6 +7284,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ + LSM_HOOK_INIT(fs_context_submount, selinux_fs_context_submount), LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index b6306d71c908..67dcd31cd3f3 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -611,6 +611,56 @@ static int smack_add_opt(int token, const char *s, void **mnt_opts) return -EINVAL; } +/** + * smack_fs_context_submount - Initialise security data for a filesystem context + * @fc: The filesystem context. + * @reference: reference superblock + * + * Returns 0 on success or -ENOMEM on error. + */ +static int smack_fs_context_submount(struct fs_context *fc, + struct super_block *reference) +{ + struct superblock_smack *sbsp; + struct smack_mnt_opts *ctx; + struct inode_smack *isp; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + fc->security = ctx; + + sbsp = smack_superblock(reference); + isp = smack_inode(reference->s_root->d_inode); + + if (sbsp->smk_default) { + ctx->fsdefault = kstrdup(sbsp->smk_default->smk_known, GFP_KERNEL); + if (!ctx->fsdefault) + return -ENOMEM; + } + + if (sbsp->smk_floor) { + ctx->fsfloor = kstrdup(sbsp->smk_floor->smk_known, GFP_KERNEL); + if (!ctx->fsfloor) + return -ENOMEM; + } + + if (sbsp->smk_hat) { + ctx->fshat = kstrdup(sbsp->smk_hat->smk_known, GFP_KERNEL); + if (!ctx->fshat) + return -ENOMEM; + } + + if (isp->smk_flags & SMK_INODE_TRANSMUTE) { + if (sbsp->smk_root) { + ctx->fstransmute = kstrdup(sbsp->smk_root->smk_known, GFP_KERNEL); + if (!ctx->fstransmute) + return -ENOMEM; + } + } + return 0; +} + /** * smack_fs_context_dup - Duplicate the security data on fs_context duplication * @fc: The new filesystem context. @@ -4792,6 +4842,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ptrace_traceme, smack_ptrace_traceme), LSM_HOOK_INIT(syslog, smack_syslog), + LSM_HOOK_INIT(fs_context_submount, smack_fs_context_submount), LSM_HOOK_INIT(fs_context_dup, smack_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, smack_fs_context_parse_param), From 916ca81922018119823e63488890a8eaf54212a1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 10 Aug 2023 12:54:18 -0700 Subject: [PATCH 0794/2093] ARM: ptrace: Restore syscall restart tracing [ Upstream commit cf007647475b5090819c5fe8da771073145c7334 ] Since commit 4e57a4ddf6b0 ("ARM: 9107/1: syscall: always store thread_info->abi_syscall"), the seccomp selftests "syscall_restart" has been broken. This was caused by the restart syscall not being stored to "abi_syscall" during restart setup before branching to the "local_restart" label. Tracers would see the wrong syscall, and scno would get overwritten while returning from the TIF_WORK path. Add the missing store. Cc: Russell King Cc: Arnd Bergmann Cc: Lecopzer Chen Cc: Oleg Nesterov Cc: linux-arm-kernel@lists.infradead.org Fixes: 4e57a4ddf6b0 ("ARM: 9107/1: syscall: always store thread_info->abi_syscall") Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230810195422.2304827-1-keescook@chromium.org Signed-off-by: Kees Cook Signed-off-by: Sasha Levin --- arch/arm/kernel/entry-common.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 405a607b754f..b413b541c3c7 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -103,6 +103,7 @@ slow_work_pending: cmp r0, #0 beq no_work_pending movlt scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE) + str scno, [tsk, #TI_ABI_SYSCALL] @ make sure tracers see update ldmia sp, {r0 - r6} @ have to reload r0 - r6 b local_restart @ ... and off we go ENDPROC(ret_fast_syscall) From 085fe43238416d77f2a44972abd289d676804d32 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 10 Aug 2023 12:54:19 -0700 Subject: [PATCH 0795/2093] ARM: ptrace: Restore syscall skipping for tracers [ Upstream commit 4697b5848bd933f68ebd04836362c8de0cacaf71 ] Since commit 4e57a4ddf6b0 ("ARM: 9107/1: syscall: always store thread_info->abi_syscall"), the seccomp selftests "syscall_errno" and "syscall_faked" have been broken. Both seccomp and PTRACE depend on using the special value of "-1" for skipping syscalls. This value wasn't working because it was getting masked by __NR_SYSCALL_MASK in both PTRACE_SET_SYSCALL and get_syscall_nr(). Explicitly test for -1 in PTRACE_SET_SYSCALL and get_syscall_nr(), leaving it exposed when present, allowing tracers to skip syscalls again. Cc: Russell King Cc: Arnd Bergmann Cc: Lecopzer Chen Cc: Oleg Nesterov Cc: linux-arm-kernel@lists.infradead.org Fixes: 4e57a4ddf6b0 ("ARM: 9107/1: syscall: always store thread_info->abi_syscall") Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230810195422.2304827-2-keescook@chromium.org Signed-off-by: Kees Cook Signed-off-by: Sasha Levin --- arch/arm/include/asm/syscall.h | 3 +++ arch/arm/kernel/ptrace.c | 5 +++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index dfeed440254a..fe4326d938c1 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -25,6 +25,9 @@ static inline int syscall_get_nr(struct task_struct *task, if (IS_ENABLED(CONFIG_AEABI) && !IS_ENABLED(CONFIG_OABI_COMPAT)) return task_thread_info(task)->abi_syscall; + if (task_thread_info(task)->abi_syscall == -1) + return -1; + return task_thread_info(task)->abi_syscall & __NR_SYSCALL_MASK; } diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index bfe88c6e60d5..cef106913ab7 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -785,8 +785,9 @@ long arch_ptrace(struct task_struct *child, long request, break; case PTRACE_SET_SYSCALL: - task_thread_info(child)->abi_syscall = data & - __NR_SYSCALL_MASK; + if (data != -1) + data &= __NR_SYSCALL_MASK; + task_thread_info(child)->abi_syscall = data; ret = 0; break; From e0322a255a2242dbe4686b6176b3c83dea490529 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 7 Jul 2023 13:53:55 -0400 Subject: [PATCH 0796/2093] refscale: Fix uninitalized use of wait_queue_head_t [ Upstream commit f5063e8948dad7f31adb007284a5d5038ae31bb8 ] Running the refscale test occasionally crashes the kernel with the following error: [ 8569.952896] BUG: unable to handle page fault for address: ffffffffffffffe8 [ 8569.952900] #PF: supervisor read access in kernel mode [ 8569.952902] #PF: error_code(0x0000) - not-present page [ 8569.952904] PGD c4b048067 P4D c4b049067 PUD c4b04b067 PMD 0 [ 8569.952910] Oops: 0000 [#1] PREEMPT_RT SMP NOPTI [ 8569.952916] Hardware name: Dell Inc. PowerEdge R750/0WMWCR, BIOS 1.2.4 05/28/2021 [ 8569.952917] RIP: 0010:prepare_to_wait_event+0x101/0x190 : [ 8569.952940] Call Trace: [ 8569.952941] [ 8569.952944] ref_scale_reader+0x380/0x4a0 [refscale] [ 8569.952959] kthread+0x10e/0x130 [ 8569.952966] ret_from_fork+0x1f/0x30 [ 8569.952973] The likely cause is that init_waitqueue_head() is called after the call to the torture_create_kthread() function that creates the ref_scale_reader kthread. Although this init_waitqueue_head() call will very likely complete before this kthread is created and starts running, it is possible that the calling kthread will be delayed between the calls to torture_create_kthread() and init_waitqueue_head(). In this case, the new kthread will use the waitqueue head before it is properly initialized, which is not good for the kernel's health and well-being. The above crash happened here: static inline void __add_wait_queue(...) { : if (!(wq->flags & WQ_FLAG_PRIORITY)) <=== Crash here The offset of flags from list_head entry in wait_queue_entry is -0x18. If reader_tasks[i].wq.head.next is NULL as allocated reader_task structure is zero initialized, the instruction will try to access address 0xffffffffffffffe8, which is exactly the fault address listed above. This commit therefore invokes init_waitqueue_head() before creating the kthread. Fixes: 653ed64b01dc ("refperf: Add a test to measure performance of read-side synchronization") Signed-off-by: Waiman Long Reviewed-by: Qiuxu Zhuo Reviewed-by: Davidlohr Bueso Acked-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/rcu/refscale.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index d49a9d66e000..3a93c53f615f 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -867,12 +867,11 @@ ref_scale_init(void) VERBOSE_SCALEOUT("Starting %d reader threads", nreaders); for (i = 0; i < nreaders; i++) { + init_waitqueue_head(&reader_tasks[i].wq); firsterr = torture_create_kthread(ref_scale_reader, (void *)i, reader_tasks[i].task); if (torture_init_error(firsterr)) goto unwind; - - init_waitqueue_head(&(reader_tasks[i].wq)); } // Main Task From 5d343b49078de9fbdce2dd0ec894f5b8daeb1031 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 21 Jul 2023 18:16:34 +0530 Subject: [PATCH 0797/2093] OPP: Fix passing 0 to PTR_ERR in _opp_attach_genpd() [ Upstream commit d920920f85a82c1c806a4143871a0e8f534732f2 ] If dev_pm_domain_attach_by_name() returns NULL, then 0 will be passed to PTR_ERR() as reported by the smatch warning below: drivers/opp/core.c:2456 _opp_attach_genpd() warn: passing zero to 'PTR_ERR' Fix it by checking for the non-NULL virt_dev pointer before passing it to PTR_ERR. Otherwise return -ENODEV. Fixes: 4ea9496cbc95 ("opp: Fix error check in dev_pm_opp_attach_genpd()") Signed-off-by: Manivannan Sadhasivam Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/opp/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/opp/core.c b/drivers/opp/core.c index d707214069ca..f0d70ecc0271 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2372,7 +2372,7 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev, virt_dev = dev_pm_domain_attach_by_name(dev, *name); if (IS_ERR_OR_NULL(virt_dev)) { - ret = PTR_ERR(virt_dev) ? : -ENODEV; + ret = virt_dev ? PTR_ERR(virt_dev) : -ENODEV; dev_err(dev, "Couldn't attach to pm_domain: %d\n", ret); goto err; } From 1051a1c5dd2691faa105c962045dcf9a9deab509 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 16:14:49 +0300 Subject: [PATCH 0798/2093] selftests/resctrl: Add resctrl.h into build deps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8e289f4542890168705219e54f0231dccfabddbe ] Makefile only lists *.c as build dependencies for the resctrl_tests executable which excludes resctrl.h. Add *.h to wildcard() to include resctrl.h. Fixes: 591a6e8588fc ("selftests/resctrl: Add basic resctrl file system operations and data") Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Tested-by: Babu Moger Tested-by: Shaopeng Tan (Fujitsu) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/resctrl/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index 73d53257df42..5073dbc96125 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -7,4 +7,4 @@ TEST_GEN_PROGS := resctrl_tests include ../lib.mk -$(OUTPUT)/resctrl_tests: $(wildcard *.c) +$(OUTPUT)/resctrl_tests: $(wildcard *.[ch]) From d4b1f43944c571e09ef75a7f7af0c3a27ba7f5ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 16:14:50 +0300 Subject: [PATCH 0799/2093] selftests/resctrl: Don't leak buffer in fill_cache() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2d320b1029ee7329ee0638181be967789775b962 ] The error path in fill_cache() does return before the allocated buffer is freed leaking the buffer. The leak was introduced when fill_cache_read() started to return errors in commit c7b607fa9325 ("selftests/resctrl: Fix null pointer dereference on open failed"), before that both fill functions always returned 0. Move free() earlier to prevent the mem leak. Fixes: c7b607fa9325 ("selftests/resctrl: Fix null pointer dereference on open failed") Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Tested-by: Babu Moger Tested-by: Shaopeng Tan (Fujitsu) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/resctrl/fill_buf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index c20d0a7ecbe6..ab1d91328d67 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -184,12 +184,13 @@ fill_cache(unsigned long long buf_size, int malloc_and_init, int memflush, else ret = fill_cache_write(start_ptr, end_ptr, resctrl_val); + free(startptr); + if (ret) { printf("\n Error in fill cache read/write...\n"); return -1; } - free(startptr); return 0; } From f046a88cbadd051ed6a019de16f70a2547d9433d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 16:14:51 +0300 Subject: [PATCH 0800/2093] selftests/resctrl: Unmount resctrl FS if child fails to run benchmark MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f99e413eb54652e2436cc56d081176bc9a34cd8d ] A child calls PARENT_EXIT() when it fails to run a benchmark to kill the parent process. PARENT_EXIT() lacks unmount for the resctrl FS and the parent won't be there to unmount it either after it gets killed. Add the resctrl FS unmount also to PARENT_EXIT(). Fixes: 591a6e8588fc ("selftests/resctrl: Add basic resctrl file system operations and data") Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Tested-by: Babu Moger Tested-by: Shaopeng Tan (Fujitsu) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/resctrl/resctrl.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index f44fa2de4d98..dbe5cfb54558 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -43,6 +43,7 @@ do { \ perror(err_msg); \ kill(ppid, SIGKILL); \ + umount_resctrlfs(); \ exit(EXIT_FAILURE); \ } while (0) From 9d8f66d6de833a9b6f98f4833dd48a8e3052a257 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 16:14:52 +0300 Subject: [PATCH 0801/2093] selftests/resctrl: Close perf value read fd on errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 51a0c3b7f028169e40db930575dd01fe81c3e765 ] Perf event fd (fd_lm) is not closed when run_fill_buf() returns error. Close fd_lm only in cat_val() to make it easier to track it is always closed. Fixes: 790bf585b0ee ("selftests/resctrl: Add Cache Allocation Technology (CAT) selftest") Signed-off-by: Ilpo Järvinen Tested-by: Babu Moger Tested-by: Shaopeng Tan (Fujitsu) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/resctrl/cache.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 0485863a169f..338f71445393 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -89,21 +89,19 @@ static int reset_enable_llc_perf(pid_t pid, int cpu_no) static int get_llc_perf(unsigned long *llc_perf_miss) { __u64 total_misses; + int ret; /* Stop counters after one span to get miss rate */ ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); - if (read(fd_lm, &rf_cqm, sizeof(struct read_format)) == -1) { + ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); + if (ret == -1) { perror("Could not get llc misses through perf"); - return -1; } total_misses = rf_cqm.values[0].value; - - close(fd_lm); - *llc_perf_miss = total_misses; return 0; @@ -258,19 +256,25 @@ int cat_val(struct resctrl_val_param *param) memflush, operation, resctrl_val)) { fprintf(stderr, "Error-running fill buffer\n"); ret = -1; - break; + goto pe_close; } sleep(1); ret = measure_cache_vals(param, bm_pid); if (ret) - break; + goto pe_close; + + close(fd_lm); } else { break; } } return ret; + +pe_close: + close(fd_lm); + return ret; } /* From 287aeeb731e93209c892c7a1fa9370c0ce864766 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 17 Jul 2023 19:55:05 +0200 Subject: [PATCH 0802/2093] arm64/ptrace: Clean up error handling path in sve_set_common() [ Upstream commit 5f69ca4229c7d8e23f238174827ee7aa49b0bcb2 ] All error handling paths go to 'out', except this one. Be consistent and also branch to 'out' here. Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers") Signed-off-by: Christophe JAILLET Reviewed-by: Mark Brown Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/aa61301ed2dfd079b74b37f7fede5f179ac3087a.1689616473.git.christophe.jaillet@wanadoo.fr Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/kernel/ptrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index f606c942f514..e1f6366b7ccd 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -896,7 +896,8 @@ static int sve_set_common(struct task_struct *target, break; default: WARN_ON_ONCE(1); - return -EINVAL; + ret = -EINVAL; + goto out; } /* From be361e5ec4b2903493958c225915bba8f297493a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 30 Jul 2023 20:07:40 -0700 Subject: [PATCH 0803/2093] sched/psi: Select KERNFS as needed [ Upstream commit 98dfdd9ee93995a408192dbbf3dd219ba23e3738 ] Users of KERNFS should select it to enforce its being built, so do this to prevent a build error. In file included from ../kernel/sched/build_utility.c:97: ../kernel/sched/psi.c: In function 'psi_trigger_poll': ../kernel/sched/psi.c:1479:17: error: implicit declaration of function 'kernfs_generic_poll' [-Werror=implicit-function-declaration] 1479 | kernfs_generic_poll(t->of, wait); Fixes: aff037078eca ("sched/psi: use kernfs polling functions for PSI trigger polling") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Acked-by: Suren Baghdasaryan Link: lore.kernel.org/r/202307310732.r65EQFY0-lkp@intel.com Signed-off-by: Sasha Levin --- init/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/init/Kconfig b/init/Kconfig index 2028ed4d50f5..de255842f5d0 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -627,6 +627,7 @@ config TASK_IO_ACCOUNTING config PSI bool "Pressure stall information tracking" + select KERNFS help Collect metrics that indicate how overcommitted the CPU, memory, and IO capacity are in the system. From 1d9a735d4e45e9f7c13c2172ede27500a607a4ca Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 7 Aug 2023 18:26:58 +0200 Subject: [PATCH 0804/2093] x86/decompressor: Don't rely on upper 32 bits of GPRs being preserved MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 264b82fdb4989cf6a44a2bcd0c6ea05e8026b2ac ] The 4-to-5 level mode switch trampoline disables long mode and paging in order to be able to flick the LA57 bit. According to section 3.4.1.1 of the x86 architecture manual [0], 64-bit GPRs might not retain the upper 32 bits of their contents across such a mode switch. Given that RBP, RBX and RSI are live at this point, preserve them on the stack, along with the return address that might be above 4G as well. [0] Intel® 64 and IA-32 Architectures Software Developer’s Manual, Volume 1: Basic Architecture "Because the upper 32 bits of 64-bit general-purpose registers are undefined in 32-bit modes, the upper 32 bits of any general-purpose register are not preserved when switching from 64-bit mode to a 32-bit mode (to protected mode or compatibility mode). Software must not depend on these bits to maintain a value after a 64-bit to 32-bit mode switch." Fixes: 194a9749c73d650c ("x86/boot/compressed/64: Handle 5-level paging boot if kernel is above 4G") Signed-off-by: Ard Biesheuvel Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230807162720.545787-2-ardb@kernel.org Signed-off-by: Sasha Levin --- arch/x86/boot/compressed/head_64.S | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d33f060900d2..b4bd6df29116 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -485,11 +485,25 @@ SYM_CODE_START(startup_64) /* Save the trampoline address in RCX */ movq %rax, %rcx + /* Set up 32-bit addressable stack */ + leaq TRAMPOLINE_32BIT_STACK_END(%rcx), %rsp + /* - * Load the address of trampoline_return() into RDI. - * It will be used by the trampoline to return to the main code. + * Preserve live 64-bit registers on the stack: this is necessary + * because the architecture does not guarantee that GPRs will retain + * their full 64-bit values across a 32-bit mode switch. + */ + pushq %rbp + pushq %rbx + pushq %rsi + + /* + * Push the 64-bit address of trampoline_return() onto the new stack. + * It will be used by the trampoline to return to the main code. Due to + * the 32-bit mode switch, it cannot be kept it in a register either. */ leaq trampoline_return(%rip), %rdi + pushq %rdi /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ pushq $__KERNEL32_CS @@ -497,6 +511,11 @@ SYM_CODE_START(startup_64) pushq %rax lretq trampoline_return: + /* Restore live 64-bit registers */ + popq %rsi + popq %rbx + popq %rbp + /* Restore the stack, the 32-bit trampoline uses its own stack */ leaq rva(boot_stack_end)(%rbx), %rsp @@ -606,7 +625,7 @@ SYM_FUNC_END(.Lrelocated) /* * This is the 32-bit trampoline that will be copied over to low memory. * - * RDI contains the return address (might be above 4G). + * Return address is at the top of the stack (might be above 4G). * ECX contains the base address of the trampoline memory. * Non zero RDX means trampoline needs to enable 5-level paging. */ @@ -616,9 +635,6 @@ SYM_CODE_START(trampoline_32bit_src) movl %eax, %ds movl %eax, %ss - /* Set up new stack */ - leal TRAMPOLINE_32BIT_STACK_END(%ecx), %esp - /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax @@ -695,7 +711,7 @@ SYM_CODE_END(trampoline_32bit_src) .code64 SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) /* Return from the trampoline */ - jmp *%rdi + retq SYM_FUNC_END(.Lpaging_enabled) /* From 8efd0420290e81a348358c93d589a97dffdd935d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 27 Dec 2022 13:04:35 +0000 Subject: [PATCH 0805/2093] arm64/sme: Don't use streaming mode to probe the maximum SME VL [ Upstream commit fcd3d2c082b2a19da2326b2b38ba5a05536dcd32 ] During development the architecture added the RDSVL instruction which means we do not need to enter streaming mode to enumerate the SME VLs, use it when we probe the maximum supported VL. Other users were already updated. No functional change. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20221223-arm64-sme-probe-max-v1-1-cbde68f67ad0@kernel.org Signed-off-by: Catalin Marinas Stable-dep-of: 01948b09edc3 ("arm64/fpsimd: Only provide the length to cpufeature for xCR registers") Signed-off-by: Sasha Levin --- arch/arm64/kernel/fpsimd.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8cd59d387b90..4aa579ff3125 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1296,7 +1296,6 @@ u64 read_smcr_features(void) unsigned int vq_max; sme_kernel_enable(NULL); - sme_smstart_sm(); /* * Set the maximum possible VL. @@ -1306,11 +1305,9 @@ u64 read_smcr_features(void) smcr = read_sysreg_s(SYS_SMCR_EL1); smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ - vq_max = sve_vq_from_vl(sve_get_vl()); + vq_max = sve_vq_from_vl(sme_get_vl()); smcr |= vq_max - 1; /* set LEN field to maximum effective value */ - sme_smstop_sm(); - return smcr; } From dfadde1697746092374349dd74da06e923c1c00b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 31 Jul 2023 14:58:48 +0100 Subject: [PATCH 0806/2093] arm64/fpsimd: Only provide the length to cpufeature for xCR registers [ Upstream commit 01948b09edc3fecf8486c57c2d2fb8b80886f3d0 ] For both SVE and SME we abuse the generic register field comparison support in the cpufeature code as part of our detection of unsupported variations in the vector lengths available to PEs, reporting the maximum vector lengths via ZCR_EL1.LEN and SMCR_EL1.LEN. Since these are configuration registers rather than identification registers the assumptions the cpufeature code makes about how unknown bitfields behave are invalid, leading to warnings when SME features like FA64 are enabled and we hotplug a CPU: CPU features: SANITY CHECK: Unexpected variation in SYS_SMCR_EL1. Boot CPU: 0x0000000000000f, CPU3: 0x0000008000000f CPU features: Unsupported CPU feature variation detected. SVE has no controls other than the vector length so is not yet impacted but the same issue will apply there if any are defined. Since the only field we are interested in having the cpufeature code handle is the length field and we use a custom read function to obtain the value we can avoid these warnings by filtering out all other bits when we return the register value, if we're doing that we don't need to bother reading the register at all and can simply use the RDVL/RDSVL value we were filling in instead. Fixes: 2e0f2478ea37 ("arm64/sve: Probe SVE capabilities and usable vector lengths") FixeS: b42990d3bf77 ("arm64/sme: Identify supported SME vector lengths at boot") Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20230731-arm64-sme-fa64-hotplug-v2-1-7714c00dd902@kernel.org Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/kernel/fpsimd.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4aa579ff3125..8c226d79abdf 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1133,9 +1133,6 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) */ u64 read_zcr_features(void) { - u64 zcr; - unsigned int vq_max; - /* * Set the maximum possible VL, and write zeroes to all other * bits to see if they stick. @@ -1143,12 +1140,8 @@ u64 read_zcr_features(void) sve_kernel_enable(NULL); write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1); - zcr = read_sysreg_s(SYS_ZCR_EL1); - zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */ - vq_max = sve_vq_from_vl(sve_get_vl()); - zcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return zcr; + /* Return LEN value that would be written to get the maximum VL */ + return sve_vq_from_vl(sve_get_vl()) - 1; } void __init sve_setup(void) @@ -1292,9 +1285,6 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) */ u64 read_smcr_features(void) { - u64 smcr; - unsigned int vq_max; - sme_kernel_enable(NULL); /* @@ -1303,12 +1293,8 @@ u64 read_smcr_features(void) write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, SYS_SMCR_EL1); - smcr = read_sysreg_s(SYS_SMCR_EL1); - smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ - vq_max = sve_vq_from_vl(sme_get_vl()); - smcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return smcr; + /* Return LEN value that would be written to get the maximum VL */ + return sve_vq_from_vl(sme_get_vl()) - 1; } void __init sme_setup(void) From 5fce29ab20cb05797239e4628fb683d2ee9aa140 Mon Sep 17 00:00:00 2001 From: Cyril Hrubis Date: Wed, 2 Aug 2023 17:19:05 +0200 Subject: [PATCH 0807/2093] sched/rt: Fix sysctl_sched_rr_timeslice intial value [ Upstream commit c7fcb99877f9f542c918509b2801065adcaf46fa ] There is a 10% rounding error in the intial value of the sysctl_sched_rr_timeslice with CONFIG_HZ_300=y. This was found with LTP test sched_rr_get_interval01: sched_rr_get_interval01.c:57: TPASS: sched_rr_get_interval() passed sched_rr_get_interval01.c:64: TPASS: Time quantum 0s 99999990ns sched_rr_get_interval01.c:72: TFAIL: /proc/sys/kernel/sched_rr_timeslice_ms != 100 got 90 sched_rr_get_interval01.c:57: TPASS: sched_rr_get_interval() passed sched_rr_get_interval01.c:64: TPASS: Time quantum 0s 99999990ns sched_rr_get_interval01.c:72: TFAIL: /proc/sys/kernel/sched_rr_timeslice_ms != 100 got 90 What this test does is to compare the return value from the sched_rr_get_interval() and the sched_rr_timeslice_ms sysctl file and fails if they do not match. The problem it found is the intial sysctl file value which was computed as: static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; which works fine as long as MSEC_PER_SEC is multiple of HZ, however it introduces 10% rounding error for CONFIG_HZ_300: (MSEC_PER_SEC / HZ) * (100 * HZ / 1000) (1000 / 300) * (100 * 300 / 1000) 3 * 30 = 90 This can be easily fixed by reversing the order of the multiplication and division. After this fix we get: (MSEC_PER_SEC * (100 * HZ / 1000)) / HZ (1000 * (100 * 300 / 1000)) / 300 (1000 * 30) / 300 = 100 Fixes: 975e155ed873 ("sched/rt: Show the 'sched_rr_timeslice' SCHED_RR timeslice tuning knob in milliseconds") Signed-off-by: Cyril Hrubis Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Petr Vorel Acked-by: Mel Gorman Tested-by: Petr Vorel Link: https://lore.kernel.org/r/20230802151906.25258-2-chrubis@suse.cz Signed-off-by: Sasha Levin --- kernel/sched/rt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 4f5796dd26a5..576eb2f51f04 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -25,7 +25,7 @@ unsigned int sysctl_sched_rt_period = 1000000; int sysctl_sched_rt_runtime = 950000; #ifdef CONFIG_SYSCTL -static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; +static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ; static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, From 048d1a8b9da8d4d36ae4b092342740f08bb7346a Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Fri, 11 Aug 2023 09:54:38 +0800 Subject: [PATCH 0808/2093] perf/imx_ddr: don't enable counter0 if none of 4 counters are used [ Upstream commit f4e2bd91ddf5e8543cbe7ad80b3fba3d2dc63fa3 ] In current driver, counter0 will be enabled after ddr_perf_pmu_enable() is called even though none of the 4 counters are used. This will cause counter0 continue to count until ddr_perf_pmu_disabled() is called. If pmu is not disabled all the time, the pmu interrupt will be asserted from time to time due to counter0 will overflow and irq handler will clear it. It's not an expected behavior. This patch will not enable counter0 if none of 4 counters are used. Fixes: 9a66d36cc7ac ("drivers/perf: imx_ddr: Add DDR performance counter support to perf") Signed-off-by: Xu Yang Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20230811015438.1999307-2-xu.yang_2@nxp.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/perf/fsl_imx8_ddr_perf.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 8e058e08fe81..cd4ce2b4906d 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -102,6 +102,7 @@ struct ddr_pmu { const struct fsl_ddr_devtype_data *devtype_data; int irq; int id; + int active_counter; }; static ssize_t ddr_perf_identifier_show(struct device *dev, @@ -496,6 +497,10 @@ static void ddr_perf_event_start(struct perf_event *event, int flags) ddr_perf_counter_enable(pmu, event->attr.config, counter, true); + if (!pmu->active_counter++) + ddr_perf_counter_enable(pmu, EVENT_CYCLES_ID, + EVENT_CYCLES_COUNTER, true); + hwc->state = 0; } @@ -550,6 +555,10 @@ static void ddr_perf_event_stop(struct perf_event *event, int flags) ddr_perf_counter_enable(pmu, event->attr.config, counter, false); ddr_perf_event_update(event); + if (!--pmu->active_counter) + ddr_perf_counter_enable(pmu, EVENT_CYCLES_ID, + EVENT_CYCLES_COUNTER, false); + hwc->state |= PERF_HES_STOPPED; } @@ -568,25 +577,10 @@ static void ddr_perf_event_del(struct perf_event *event, int flags) static void ddr_perf_pmu_enable(struct pmu *pmu) { - struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu); - - /* enable cycle counter if cycle is not active event list */ - if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL) - ddr_perf_counter_enable(ddr_pmu, - EVENT_CYCLES_ID, - EVENT_CYCLES_COUNTER, - true); } static void ddr_perf_pmu_disable(struct pmu *pmu) { - struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu); - - if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL) - ddr_perf_counter_enable(ddr_pmu, - EVENT_CYCLES_ID, - EVENT_CYCLES_COUNTER, - false); } static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base, From 7d31730c5d81d229e3c4b6a1d7ca2f441a24880c Mon Sep 17 00:00:00 2001 From: "Nysal Jan K.A" Date: Mon, 14 Aug 2023 13:39:27 +0530 Subject: [PATCH 0809/2093] selftests/futex: Order calls to futex_lock_pi [ Upstream commit fbf4dec702774286db409815ffb077711a96b824 ] Observed occassional failures in the futex_wait_timeout test: ok 1 futex_wait relative succeeds ok 2 futex_wait_bitset realtime succeeds ok 3 futex_wait_bitset monotonic succeeds ok 4 futex_wait_requeue_pi realtime succeeds ok 5 futex_wait_requeue_pi monotonic succeeds not ok 6 futex_lock_pi realtime returned 0 ...... The test expects the child thread to complete some steps before the parent thread gets to run. There is an implicit expectation of the order of invocation of futex_lock_pi between the child thread and the parent thread. Make this order explicit. If the order is not met, the futex_lock_pi call in the parent thread succeeds and will not timeout. Fixes: f4addd54b161 ("selftests: futex: Expand timeout test") Signed-off-by: Nysal Jan K.A Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../selftests/futex/functional/futex_wait_timeout.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 3651ce17beeb..d183f878360b 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -24,6 +24,7 @@ static long timeout_ns = 100000; /* 100us default timeout */ static futex_t futex_pi; +static pthread_barrier_t barrier; void usage(char *prog) { @@ -48,6 +49,8 @@ void *get_pi_lock(void *arg) if (ret != 0) error("futex_lock_pi failed\n", ret); + pthread_barrier_wait(&barrier); + /* Blocks forever */ ret = futex_wait(&lock, 0, NULL, 0); error("futex_wait failed\n", ret); @@ -130,6 +133,7 @@ int main(int argc, char *argv[]) basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); + pthread_barrier_init(&barrier, NULL, 2); pthread_create(&thread, NULL, get_pi_lock, NULL); /* initialize relative timeout */ @@ -163,6 +167,9 @@ int main(int argc, char *argv[]) res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, 0); test_timeout(res, &ret, "futex_wait_requeue_pi monotonic", ETIMEDOUT); + /* Wait until the other thread calls futex_lock_pi() */ + pthread_barrier_wait(&barrier); + pthread_barrier_destroy(&barrier); /* * FUTEX_LOCK_PI with CLOCK_REALTIME * Due to historical reasons, FUTEX_LOCK_PI supports only realtime From 87d452a076d121846fb743ad831c843e454fea80 Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Wed, 26 Jul 2023 11:33:45 +0200 Subject: [PATCH 0810/2093] s390/pkey: fix/harmonize internal keyblob headers [ Upstream commit 37a08f010b7c423b5e4c9ed3b187d21166553007 ] Commit 'fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys")' introduced PKEY_TYPE_EP11_AES as a supplement to PKEY_TYPE_EP11. All pkeys have an internal header/payload structure, which is opaque to the userspace. The header structures for PKEY_TYPE_EP11 and PKEY_TYPE_EP11_AES are nearly identical and there is no reason, why different structures are used. In preparation to fix the keyversion handling in the broken PKEY IOCTLs, the same header structure is used for PKEY_TYPE_EP11 and PKEY_TYPE_EP11_AES. This reduces the number of different code paths and increases the readability. Fixes: fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys") Signed-off-by: Holger Dengler Reviewed-by: Ingo Franzki Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- drivers/s390/crypto/pkey_api.c | 2 +- drivers/s390/crypto/zcrypt_ep11misc.c | 4 ++-- drivers/s390/crypto/zcrypt_ep11misc.h | 9 +-------- 3 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index a8def50c149b..e650df3fe7cc 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -747,7 +747,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, if (ktype) *ktype = PKEY_TYPE_EP11; if (ksize) - *ksize = kb->head.keybitlen; + *ksize = kb->head.bitlen; rc = ep11_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain, ZCRYPT_CEX7, EP11_API_V, kb->wkvp); diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index b1c29017be5b..497de7faa2fc 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -787,7 +787,7 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, kb->head.type = TOKTYPE_NON_CCA; kb->head.len = rep_pl->data_len; kb->head.version = TOKVER_EP11_AES; - kb->head.keybitlen = keybitsize; + kb->head.bitlen = keybitsize; out: kfree(req); @@ -1055,7 +1055,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, kb->head.type = TOKTYPE_NON_CCA; kb->head.len = rep_pl->data_len; kb->head.version = TOKVER_EP11_AES; - kb->head.keybitlen = keybitsize; + kb->head.bitlen = keybitsize; out: kfree(req); diff --git a/drivers/s390/crypto/zcrypt_ep11misc.h b/drivers/s390/crypto/zcrypt_ep11misc.h index 07445041869f..912b3918c10a 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.h +++ b/drivers/s390/crypto/zcrypt_ep11misc.h @@ -29,14 +29,7 @@ struct ep11keyblob { union { u8 session[32]; /* only used for PKEY_TYPE_EP11: */ - struct { - u8 type; /* 0x00 (TOKTYPE_NON_CCA) */ - u8 res0; /* unused */ - u16 len; /* total length in bytes of this blob */ - u8 version; /* 0x03 (TOKVER_EP11_AES) */ - u8 res1; /* unused */ - u16 keybitlen; /* clear key bit len, 0 for unknown */ - } head; + struct ep11kblob_header head; }; u8 wkvp[16]; /* wrapping key verification pattern */ u64 attr; /* boolean key attributes */ From f98ea9abc1f7fc85ff0573f4db8f9696590b5c6b Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Tue, 25 Jul 2023 09:49:55 +0200 Subject: [PATCH 0811/2093] s390/pkey: fix PKEY_TYPE_EP11_AES handling in PKEY_GENSECK2 IOCTL [ Upstream commit fb249ce7f7bfd8621a38e4ad401ba74b680786d4 ] Commit 'fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys")' introduced PKEY_TYPE_EP11_AES for the PKEY_GENSECK2 IOCTL, to enable userspace to generate securekey blobs of this type. Unfortunately, all PKEY_GENSECK2 IOCTL requests for PKEY_TYPE_EP11_AES return with an error (-EINVAL). Fix the handling for PKEY_TYPE_EP11_AES in PKEY_GENSECK2 IOCTL, so that userspace can generate securekey blobs of this type. The start of the header and the keyblob, as well as the length need special handling, depending on the internal keyversion. Add a helper function that splits an uninitialized buffer into start and size of the header as well as start and size of the payload, depending on the requested keyversion. Do the header-related calculations and the raw genkey request handling in separate functions. Use the raw genkey request function for internal purposes. Fixes: fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys") Signed-off-by: Holger Dengler Reviewed-by: Ingo Franzki Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- drivers/s390/crypto/pkey_api.c | 18 +++-- drivers/s390/crypto/zcrypt_ep11misc.c | 103 ++++++++++++++++++++++---- drivers/s390/crypto/zcrypt_ep11misc.h | 2 +- 3 files changed, 102 insertions(+), 21 deletions(-) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index e650df3fe7cc..79568da580c6 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -565,6 +565,11 @@ static int pkey_genseckey2(const struct pkey_apqn *apqns, size_t nr_apqns, if (*keybufsize < MINEP11AESKEYBLOBSIZE) return -EINVAL; break; + case PKEY_TYPE_EP11_AES: + if (*keybufsize < (sizeof(struct ep11kblob_header) + + MINEP11AESKEYBLOBSIZE)) + return -EINVAL; + break; default: return -EINVAL; } @@ -581,9 +586,10 @@ static int pkey_genseckey2(const struct pkey_apqn *apqns, size_t nr_apqns, for (i = 0, rc = -ENODEV; i < nr_apqns; i++) { card = apqns[i].card; dom = apqns[i].domain; - if (ktype == PKEY_TYPE_EP11) { + if (ktype == PKEY_TYPE_EP11 || + ktype == PKEY_TYPE_EP11_AES) { rc = ep11_genaeskey(card, dom, ksize, kflags, - keybuf, keybufsize); + keybuf, keybufsize, ktype); } else if (ktype == PKEY_TYPE_CCA_DATA) { rc = cca_genseckey(card, dom, ksize, keybuf); *keybufsize = (rc ? 0 : SECKEYBLOBSIZE); @@ -1313,7 +1319,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, apqns = _copy_apqns_from_user(kgs.apqns, kgs.apqn_entries); if (IS_ERR(apqns)) return PTR_ERR(apqns); - kkey = kmalloc(klen, GFP_KERNEL); + kkey = kzalloc(klen, GFP_KERNEL); if (!kkey) { kfree(apqns); return -ENOMEM; @@ -1969,7 +1975,8 @@ static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits, for (i = 0, rc = -ENODEV; i < nr_apqns; i++) { card = apqns[i] >> 16; dom = apqns[i] & 0xFFFF; - rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize); + rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize, + PKEY_TYPE_EP11); if (rc == 0) break; } @@ -1979,7 +1986,8 @@ static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits, if (is_xts) { keysize = MAXEP11AESKEYBLOBSIZE; buf += MAXEP11AESKEYBLOBSIZE; - rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize); + rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize, + PKEY_TYPE_EP11); if (rc == 0) return 2 * MAXEP11AESKEYBLOBSIZE; } diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 497de7faa2fc..20bbeec1a1a2 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -113,6 +113,50 @@ static void __exit card_cache_free(void) spin_unlock_bh(&card_list_lock); } +static int ep11_kb_split(const u8 *kb, size_t kblen, u32 kbver, + struct ep11kblob_header **kbhdr, size_t *kbhdrsize, + u8 **kbpl, size_t *kbplsize) +{ + struct ep11kblob_header *hdr = NULL; + size_t hdrsize, plsize = 0; + int rc = -EINVAL; + u8 *pl = NULL; + + if (kblen < sizeof(struct ep11kblob_header)) + goto out; + hdr = (struct ep11kblob_header *)kb; + + switch (kbver) { + case TOKVER_EP11_AES: + /* header overlays the payload */ + hdrsize = 0; + break; + case TOKVER_EP11_ECC_WITH_HEADER: + case TOKVER_EP11_AES_WITH_HEADER: + /* payload starts after the header */ + hdrsize = sizeof(struct ep11kblob_header); + break; + default: + goto out; + } + + plsize = kblen - hdrsize; + pl = (u8 *)kb + hdrsize; + + if (kbhdr) + *kbhdr = hdr; + if (kbhdrsize) + *kbhdrsize = hdrsize; + if (kbpl) + *kbpl = pl; + if (kbplsize) + *kbplsize = plsize; + + rc = 0; +out: + return rc; +} + /* * Simple check if the key blob is a valid EP11 AES key blob with header. */ @@ -664,8 +708,9 @@ EXPORT_SYMBOL(ep11_get_domain_info); */ #define KEY_ATTR_DEFAULTS 0x00200c00 -int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, - u8 *keybuf, size_t *keybufsize) +static int _ep11_genaeskey(u16 card, u16 domain, + u32 keybitsize, u32 keygenflags, + u8 *keybuf, size_t *keybufsize) { struct keygen_req_pl { struct pl_head head; @@ -701,7 +746,6 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, struct ep11_cprb *req = NULL, *rep = NULL; struct ep11_target_dev target; struct ep11_urb *urb = NULL; - struct ep11keyblob *kb; int api, rc = -ENOMEM; switch (keybitsize) { @@ -780,14 +824,9 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, goto out; } - /* copy key blob and set header values */ + /* copy key blob */ memcpy(keybuf, rep_pl->data, rep_pl->data_len); *keybufsize = rep_pl->data_len; - kb = (struct ep11keyblob *)keybuf; - kb->head.type = TOKTYPE_NON_CCA; - kb->head.len = rep_pl->data_len; - kb->head.version = TOKVER_EP11_AES; - kb->head.bitlen = keybitsize; out: kfree(req); @@ -795,6 +834,43 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, kfree(urb); return rc; } + +int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, + u8 *keybuf, size_t *keybufsize, u32 keybufver) +{ + struct ep11kblob_header *hdr; + size_t hdr_size, pl_size; + u8 *pl; + int rc; + + switch (keybufver) { + case TOKVER_EP11_AES: + case TOKVER_EP11_AES_WITH_HEADER: + break; + default: + return -EINVAL; + } + + rc = ep11_kb_split(keybuf, *keybufsize, keybufver, + &hdr, &hdr_size, &pl, &pl_size); + if (rc) + return rc; + + rc = _ep11_genaeskey(card, domain, keybitsize, keygenflags, + pl, &pl_size); + if (rc) + return rc; + + *keybufsize = hdr_size + pl_size; + + /* update header information */ + hdr->type = TOKTYPE_NON_CCA; + hdr->len = *keybufsize; + hdr->version = keybufver; + hdr->bitlen = keybitsize; + + return 0; +} EXPORT_SYMBOL(ep11_genaeskey); static int ep11_cryptsingle(u16 card, u16 domain, @@ -1201,7 +1277,6 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, const u8 *clrkey, u8 *keybuf, size_t *keybufsize) { int rc; - struct ep11keyblob *kb; u8 encbuf[64], *kek = NULL; size_t clrkeylen, keklen, encbuflen = sizeof(encbuf); @@ -1223,17 +1298,15 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, } /* Step 1: generate AES 256 bit random kek key */ - rc = ep11_genaeskey(card, domain, 256, - 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ - kek, &keklen); + rc = _ep11_genaeskey(card, domain, 256, + 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ + kek, &keklen); if (rc) { DEBUG_ERR( "%s generate kek key failed, rc=%d\n", __func__, rc); goto out; } - kb = (struct ep11keyblob *)kek; - memset(&kb->head, 0, sizeof(kb->head)); /* Step 2: encrypt clear key value with the kek key */ rc = ep11_cryptsingle(card, domain, 0, 0, def_iv, kek, keklen, diff --git a/drivers/s390/crypto/zcrypt_ep11misc.h b/drivers/s390/crypto/zcrypt_ep11misc.h index 912b3918c10a..ed328c354bad 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.h +++ b/drivers/s390/crypto/zcrypt_ep11misc.h @@ -107,7 +107,7 @@ int ep11_get_domain_info(u16 card, u16 domain, struct ep11_domain_info *info); * Generate (random) EP11 AES secure key. */ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, - u8 *keybuf, size_t *keybufsize); + u8 *keybuf, size_t *keybufsize, u32 keybufver); /* * Generate EP11 AES secure key with given clear key value. From f326e37a210eae051de00c392def0fbca3200356 Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Fri, 4 Aug 2023 16:02:58 +0200 Subject: [PATCH 0812/2093] s390/pkey: fix PKEY_TYPE_EP11_AES handling for sysfs attributes [ Upstream commit b9352e4b9b9eff949bcc6907b8569b3a1d992f1e ] Commit 'fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys")' introduced a new PKEY_TYPE_EP11_AES securekey type as a supplement to the existing PKEY_TYPE_EP11 (which won't work in environments with session-bound keys). The pkey EP11 securekey attributes use PKEY_TYPE_EP11_AES (instead of PKEY_TYPE_EP11) keyblobs, to make the generated keyblobs usable also in environments, where session-bound keys are required. There should be no negative impacts to userspace because the internal structure of the keyblobs is opaque. The increased size of the generated keyblobs is reflected by the changed size of the attributes. Fixes: fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys") Signed-off-by: Holger Dengler Reviewed-by: Ingo Franzki Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/include/uapi/asm/pkey.h | 2 +- drivers/s390/crypto/pkey_api.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h index 924b876f992c..29c6fd369761 100644 --- a/arch/s390/include/uapi/asm/pkey.h +++ b/arch/s390/include/uapi/asm/pkey.h @@ -26,7 +26,7 @@ #define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */ #define MAXAESCIPHERKEYSIZE 136 /* our aes cipher keys have always 136 bytes */ #define MINEP11AESKEYBLOBSIZE 256 /* min EP11 AES key blob size */ -#define MAXEP11AESKEYBLOBSIZE 320 /* max EP11 AES key blob size */ +#define MAXEP11AESKEYBLOBSIZE 336 /* max EP11 AES key blob size */ /* Minimum size of a key blob */ #define MINKEYBLOBSIZE SECKEYBLOBSIZE diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 79568da580c6..2b92ec20ed68 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1947,7 +1947,7 @@ static struct attribute_group ccacipher_attr_group = { * (i.e. off != 0 or count < key blob size) -EINVAL is returned. * This function and the sysfs attributes using it provide EP11 key blobs * padded to the upper limit of MAXEP11AESKEYBLOBSIZE which is currently - * 320 bytes. + * 336 bytes. */ static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits, bool is_xts, char *buf, loff_t off, @@ -1976,7 +1976,7 @@ static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits, card = apqns[i] >> 16; dom = apqns[i] & 0xFFFF; rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize, - PKEY_TYPE_EP11); + PKEY_TYPE_EP11_AES); if (rc == 0) break; } @@ -1987,7 +1987,7 @@ static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits, keysize = MAXEP11AESKEYBLOBSIZE; buf += MAXEP11AESKEYBLOBSIZE; rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize, - PKEY_TYPE_EP11); + PKEY_TYPE_EP11_AES); if (rc == 0) return 2 * MAXEP11AESKEYBLOBSIZE; } From 14e37e08b4e12d00d500ceb14475baa43cd52021 Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Wed, 9 Aug 2023 14:23:45 +0200 Subject: [PATCH 0813/2093] s390/paes: fix PKEY_TYPE_EP11_AES handling for secure keyblobs [ Upstream commit cba33db3fc4dbf2e54294b0e499d2335a3a00d78 ] Commit 'fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys")' introduced PKEY_TYPE_EP11_AES securekey blobs as a supplement to the PKEY_TYPE_EP11 (which won't work in environments with session-bound keys). This new keyblobs has a different maximum size, so fix paes crypto module to accept also these larger keyblobs. Fixes: fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys") Signed-off-by: Holger Dengler Reviewed-by: Ingo Franzki Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/crypto/paes_s390.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index a279b7d23a5e..621322eb0e68 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -35,7 +35,7 @@ * and padding is also possible, the limits need to be generous. */ #define PAES_MIN_KEYSIZE 16 -#define PAES_MAX_KEYSIZE 320 +#define PAES_MAX_KEYSIZE MAXEP11AESKEYBLOBSIZE static u8 *ctrblk; static DEFINE_MUTEX(ctrblk_lock); From 8ee6d04ef24bf566e72d3ab575a81d41910171a5 Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Fri, 11 Aug 2023 17:58:04 +0800 Subject: [PATCH 0814/2093] irqchip/loongson-eiointc: Fix return value checking of eiointc_index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2e99b73afde18853754c5fae8e8d1a66fe5e3f64 ] Return value of function eiointc_index is int, however it is converted into uint32_t and then compared smaller than zero, this will cause logic problem. Fixes: dd281e1a1a93 ("irqchip: Add Loongson Extended I/O interrupt controller support") Signed-off-by: Bibo Mao Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230811095805.2974722-2-maobibo@loongson.cn Signed-off-by: Sasha Levin --- drivers/irqchip/irq-loongson-eiointc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index ac04aeaa2d30..3d99b8bdd8ef 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -145,7 +145,7 @@ static int eiointc_router_init(unsigned int cpu) int i, bit; uint32_t data; uint32_t node = cpu_to_eio_node(cpu); - uint32_t index = eiointc_index(node); + int index = eiointc_index(node); if (index < 0) { pr_err("Error: invalid nodemap!\n"); From a99f32b81ca18221aa1143a5fc0b26adeec5d592 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 18 Aug 2023 14:40:02 -0500 Subject: [PATCH 0815/2093] ACPI: x86: s2idle: Post-increment variables when getting constraints [ Upstream commit 3c6b1212d20bbbffcad5709ab0f2d5ed9b5859a8 ] When code uses a pre-increment it makes the reader question "why". In the constraint fetching code there is no reason for the variables to be pre-incremented so adjust to post-increment. No intended functional changes. Reviewed-by: Kuppuswamy Sathyanarayanan Suggested-by: Bjorn Helgaas Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki Stable-dep-of: 9cc8cd086f05 ("ACPI: x86: s2idle: Fix a logic error parsing AMD constraints table") Signed-off-by: Sasha Levin --- drivers/acpi/x86/s2idle.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index e499c60c4579..3a9195df1aab 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -122,13 +122,13 @@ static void lpi_device_get_constraints_amd(void) acpi_handle_debug(lps0_device_handle, "LPI: constraints list begin:\n"); - for (j = 0; j < package->package.count; ++j) { + for (j = 0; j < package->package.count; j++) { union acpi_object *info_obj = &package->package.elements[j]; struct lpi_device_constraint_amd dev_info = {}; struct lpi_constraints *list; acpi_status status; - for (k = 0; k < info_obj->package.count; ++k) { + for (k = 0; k < info_obj->package.count; k++) { union acpi_object *obj = &info_obj->package.elements[k]; list = &lpi_constraints_table[lpi_constraints_table_size]; @@ -213,7 +213,7 @@ static void lpi_device_get_constraints(void) if (!package) continue; - for (j = 0; j < package->package.count; ++j) { + for (j = 0; j < package->package.count; j++) { union acpi_object *element = &(package->package.elements[j]); @@ -245,7 +245,7 @@ static void lpi_device_get_constraints(void) constraint->min_dstate = -1; - for (j = 0; j < package_count; ++j) { + for (j = 0; j < package_count; j++) { union acpi_object *info_obj = &info.package[j]; union acpi_object *cnstr_pkg; union acpi_object *obj; From 7c70932568068b1396f20c27b43275c4915cb21b Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 18 Aug 2023 14:40:04 -0500 Subject: [PATCH 0816/2093] ACPI: x86: s2idle: Fix a logic error parsing AMD constraints table [ Upstream commit 9cc8cd086f05d9a01026c65c98da88561e9c619e ] The constraints table should be resetting the `list` object after running through all of `info_obj` iterations. This adjusts whitespace as well as less code will now be included with each loop. This fixes a functional problem is fixed where a badly formed package in the inner loop may have incorrect data. Fixes: 146f1ed852a8 ("ACPI: PM: s2idle: Add AMD support to handle _DSM") Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/x86/s2idle.c | 39 ++++++++++++++++----------------------- 1 file changed, 16 insertions(+), 23 deletions(-) diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 3a9195df1aab..ec84da6cc1bf 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -128,12 +128,11 @@ static void lpi_device_get_constraints_amd(void) struct lpi_constraints *list; acpi_status status; + list = &lpi_constraints_table[lpi_constraints_table_size]; + for (k = 0; k < info_obj->package.count; k++) { union acpi_object *obj = &info_obj->package.elements[k]; - list = &lpi_constraints_table[lpi_constraints_table_size]; - list->min_dstate = -1; - switch (k) { case 0: dev_info.enabled = obj->integer.value; @@ -148,27 +147,21 @@ static void lpi_device_get_constraints_amd(void) dev_info.min_dstate = obj->integer.value; break; } - - if (!dev_info.enabled || !dev_info.name || - !dev_info.min_dstate) - continue; - - status = acpi_get_handle(NULL, dev_info.name, - &list->handle); - if (ACPI_FAILURE(status)) - continue; - - acpi_handle_debug(lps0_device_handle, - "Name:%s\n", dev_info.name); - - list->min_dstate = dev_info.min_dstate; - - if (list->min_dstate < 0) { - acpi_handle_debug(lps0_device_handle, - "Incomplete constraint defined\n"); - continue; - } } + + if (!dev_info.enabled || !dev_info.name || + !dev_info.min_dstate) + continue; + + status = acpi_get_handle(NULL, dev_info.name, &list->handle); + if (ACPI_FAILURE(status)) + continue; + + acpi_handle_debug(lps0_device_handle, + "Name:%s\n", dev_info.name); + + list->min_dstate = dev_info.min_dstate; + lpi_constraints_table_size++; } } From 7da6250d29675335a4cd5f0fbacb23cb54420ea0 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 19 Jul 2023 09:16:36 +0800 Subject: [PATCH 0817/2093] thermal/of: Fix potential uninitialized value access [ Upstream commit f96801f0cfcefc0a16b146596577c53c75ee9773 ] If of_parse_phandle_with_args() called from __thermal_of_bind() or __thermal_of_unbind() fails, cooling_spec.np will not be initialized, so move the of_node_put() calls below the respective return value checks to avoid dereferencing an uninitialized pointer. Fixes: 3fd6d6e2b4e8 ("thermal/of: Rework the thermal device tree initialization") Signed-off-by: Peng Fan [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/thermal_of.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index aacba30bc10c..762d1990180b 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -409,13 +409,13 @@ static int __thermal_of_unbind(struct device_node *map_np, int index, int trip_i ret = of_parse_phandle_with_args(map_np, "cooling-device", "#cooling-cells", index, &cooling_spec); - of_node_put(cooling_spec.np); - if (ret < 0) { pr_err("Invalid cooling-device entry\n"); return ret; } + of_node_put(cooling_spec.np); + if (cooling_spec.args_count < 2) { pr_err("wrong reference to cooling device, missing limits\n"); return -EINVAL; @@ -442,13 +442,13 @@ static int __thermal_of_bind(struct device_node *map_np, int index, int trip_id, ret = of_parse_phandle_with_args(map_np, "cooling-device", "#cooling-cells", index, &cooling_spec); - of_node_put(cooling_spec.np); - if (ret < 0) { pr_err("Invalid cooling-device entry\n"); return ret; } + of_node_put(cooling_spec.np); + if (cooling_spec.args_count < 2) { pr_err("wrong reference to cooling device, missing limits\n"); return -EINVAL; From 14920fb907f03fe775fa3d1cf955d544fd07a0e2 Mon Sep 17 00:00:00 2001 From: Swapnil Sapkal Date: Fri, 18 Aug 2023 11:44:51 +0000 Subject: [PATCH 0818/2093] cpufreq: amd-pstate-ut: Remove module parameter access [ Upstream commit 8d6e5e8268e89979d86501dbb8385ce2e6154de1 ] In amd-pstate-ut, shared memory-based systems call get_shared_mem() as part of amd_pstate_ut_check_enabled() function. This function was written when CONFIG_X86_AMD_PSTATE was tristate config and amd_pstate can be built as a module. Currently CONFIG_X86_AMD_PSTATE is a boolean config and module parameter shared_mem is removed. But amd-pstate-ut code still accesses this module parameter. Remove those accesses. Fixes: 456ca88d8a52 ("cpufreq: amd-pstate: change amd-pstate driver to be built-in type") Reviewed-by: Mario Limonciello Reviewed-by: Meng Li Reviewed-by: Wyes Karny Suggested-by: Wyes Karny Signed-off-by: Swapnil Sapkal [ rjw: Subject edits ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/cpufreq/amd-pstate-ut.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index e4a5b4d90f83..e7f452d22138 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -64,27 +64,9 @@ static struct amd_pstate_ut_struct amd_pstate_ut_cases[] = { static bool get_shared_mem(void) { bool result = false; - char path[] = "/sys/module/amd_pstate/parameters/shared_mem"; - char buf[5] = {0}; - struct file *filp = NULL; - loff_t pos = 0; - ssize_t ret; - if (!boot_cpu_has(X86_FEATURE_CPPC)) { - filp = filp_open(path, O_RDONLY, 0); - if (IS_ERR(filp)) - pr_err("%s unable to open %s file!\n", __func__, path); - else { - ret = kernel_read(filp, &buf, sizeof(buf), &pos); - if (ret < 0) - pr_err("%s read %s file fail ret=%ld!\n", - __func__, path, (long)ret); - filp_close(filp, NULL); - } - - if ('Y' == *buf) - result = true; - } + if (!boot_cpu_has(X86_FEATURE_CPPC)) + result = true; return result; } From fcf78a17bbb94bebaa912f0460a1848f7d374c94 Mon Sep 17 00:00:00 2001 From: Swapnil Sapkal Date: Fri, 18 Aug 2023 11:44:52 +0000 Subject: [PATCH 0819/2093] cpufreq: amd-pstate-ut: Fix kernel panic when loading the driver [ Upstream commit 60dd283804479c4a52f995b713f448e2cd65b8c8 ] After loading the amd-pstate-ut driver, amd_pstate_ut_check_perf() and amd_pstate_ut_check_freq() use cpufreq_cpu_get() to get the policy of the CPU and mark it as busy. In these functions, cpufreq_cpu_put() should be used to release the policy, but it is not, so any other entity trying to access the policy is blocked indefinitely. One such scenario is when amd_pstate mode is changed, leading to the following splat: [ 1332.103727] INFO: task bash:2929 blocked for more than 120 seconds. [ 1332.110001] Not tainted 6.5.0-rc2-amd-pstate-ut #5 [ 1332.115315] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1332.123140] task:bash state:D stack:0 pid:2929 ppid:2873 flags:0x00004006 [ 1332.123143] Call Trace: [ 1332.123145] [ 1332.123148] __schedule+0x3c1/0x16a0 [ 1332.123154] ? _raw_read_lock_irqsave+0x2d/0x70 [ 1332.123157] schedule+0x6f/0x110 [ 1332.123160] schedule_timeout+0x14f/0x160 [ 1332.123162] ? preempt_count_add+0x86/0xd0 [ 1332.123165] __wait_for_common+0x92/0x190 [ 1332.123168] ? __pfx_schedule_timeout+0x10/0x10 [ 1332.123170] wait_for_completion+0x28/0x30 [ 1332.123173] cpufreq_policy_put_kobj+0x4d/0x90 [ 1332.123177] cpufreq_policy_free+0x157/0x1d0 [ 1332.123178] ? preempt_count_add+0x58/0xd0 [ 1332.123180] cpufreq_remove_dev+0xb6/0x100 [ 1332.123182] subsys_interface_unregister+0x114/0x120 [ 1332.123185] ? preempt_count_add+0x58/0xd0 [ 1332.123187] ? __pfx_amd_pstate_change_driver_mode+0x10/0x10 [ 1332.123190] cpufreq_unregister_driver+0x3b/0xd0 [ 1332.123192] amd_pstate_change_driver_mode+0x1e/0x50 [ 1332.123194] store_status+0xe9/0x180 [ 1332.123197] dev_attr_store+0x1b/0x30 [ 1332.123199] sysfs_kf_write+0x42/0x50 [ 1332.123202] kernfs_fop_write_iter+0x143/0x1d0 [ 1332.123204] vfs_write+0x2df/0x400 [ 1332.123208] ksys_write+0x6b/0xf0 [ 1332.123210] __x64_sys_write+0x1d/0x30 [ 1332.123213] do_syscall_64+0x60/0x90 [ 1332.123216] ? fpregs_assert_state_consistent+0x2e/0x50 [ 1332.123219] ? exit_to_user_mode_prepare+0x49/0x1a0 [ 1332.123223] ? irqentry_exit_to_user_mode+0xd/0x20 [ 1332.123225] ? irqentry_exit+0x3f/0x50 [ 1332.123226] ? exc_page_fault+0x8e/0x190 [ 1332.123228] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 1332.123232] RIP: 0033:0x7fa74c514a37 [ 1332.123234] RSP: 002b:00007ffe31dd0788 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 1332.123238] RAX: ffffffffffffffda RBX: 0000000000000008 RCX: 00007fa74c514a37 [ 1332.123239] RDX: 0000000000000008 RSI: 000055e27c447aa0 RDI: 0000000000000001 [ 1332.123241] RBP: 000055e27c447aa0 R08: 00007fa74c5d1460 R09: 000000007fffffff [ 1332.123242] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000008 [ 1332.123244] R13: 00007fa74c61a780 R14: 00007fa74c616600 R15: 00007fa74c615a00 [ 1332.123247] Fix this by calling cpufreq_cpu_put() wherever necessary. Fixes: 14eb1c96e3a3 ("cpufreq: amd-pstate: Add test module for amd-pstate driver") Reviewed-by: Mario Limonciello Reviewed-by: Meng Li Reviewed-by: Wyes Karny Suggested-by: Wyes Karny Signed-off-by: Swapnil Sapkal [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/cpufreq/amd-pstate-ut.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index e7f452d22138..b448c8d6a16d 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -140,7 +140,7 @@ static void amd_pstate_ut_check_perf(u32 index) if (ret) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cppc_get_perf_caps ret=%d error!\n", __func__, ret); - return; + goto skip_test; } nominal_perf = cppc_perf.nominal_perf; @@ -151,7 +151,7 @@ static void amd_pstate_ut_check_perf(u32 index) if (ret) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s read CPPC_CAP1 ret=%d error!\n", __func__, ret); - return; + goto skip_test; } nominal_perf = AMD_CPPC_NOMINAL_PERF(cap1); @@ -169,7 +169,7 @@ static void amd_pstate_ut_check_perf(u32 index) nominal_perf, cpudata->nominal_perf, lowest_nonlinear_perf, cpudata->lowest_nonlinear_perf, lowest_perf, cpudata->lowest_perf); - return; + goto skip_test; } if (!((highest_perf >= nominal_perf) && @@ -180,11 +180,15 @@ static void amd_pstate_ut_check_perf(u32 index) pr_err("%s cpu%d highest=%d >= nominal=%d > lowest_nonlinear=%d > lowest=%d > 0, the formula is incorrect!\n", __func__, cpu, highest_perf, nominal_perf, lowest_nonlinear_perf, lowest_perf); - return; + goto skip_test; } + cpufreq_cpu_put(policy); } amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS; + return; +skip_test: + cpufreq_cpu_put(policy); } /* @@ -212,14 +216,14 @@ static void amd_pstate_ut_check_freq(u32 index) pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n", __func__, cpu, cpudata->max_freq, cpudata->nominal_freq, cpudata->lowest_nonlinear_freq, cpudata->min_freq); - return; + goto skip_test; } if (cpudata->min_freq != policy->min) { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cpu%d cpudata_min_freq=%d policy_min=%d, they should be equal!\n", __func__, cpu, cpudata->min_freq, policy->min); - return; + goto skip_test; } if (cpudata->boost_supported) { @@ -231,16 +235,20 @@ static void amd_pstate_ut_check_freq(u32 index) pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n", __func__, cpu, policy->max, cpudata->max_freq, cpudata->nominal_freq); - return; + goto skip_test; } } else { amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL; pr_err("%s cpu%d must support boost!\n", __func__, cpu); - return; + goto skip_test; } + cpufreq_cpu_put(policy); } amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS; + return; +skip_test: + cpufreq_cpu_put(policy); } static int __init amd_pstate_ut_init(void) From 91f76271ec436e3909e1a039574f16480159b0fa Mon Sep 17 00:00:00 2001 From: Mikel Rychliski Date: Wed, 23 Aug 2023 17:51:58 -0400 Subject: [PATCH 0820/2093] x86/efistub: Fix PCI ROM preservation in mixed mode [ Upstream commit 8b94da92559f7e403dc7ab81937cc50f949ee2fd ] preserve_pci_rom_image() was accessing the romsize field in efi_pci_io_protocol_t directly instead of using the efi_table_attr() helper. This prevents the ROM image from being saved correctly during a mixed mode boot. Fixes: 2c3625cb9fa2 ("efi/x86: Fold __setup_efi_pci32() and __setup_efi_pci64() into one function") Signed-off-by: Mikel Rychliski Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- drivers/firmware/efi/libstub/x86-stub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 33a7811e12c6..4f0152b11a89 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -61,7 +61,7 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) rom->data.type = SETUP_PCI; rom->data.len = size - sizeof(struct setup_data); rom->data.next = 0; - rom->pcilen = pci->romsize; + rom->pcilen = romsize; *__rom = rom; status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, From 6f2b84248bab78429d5ff673e13b88b496383301 Mon Sep 17 00:00:00 2001 From: Liao Chang Date: Sat, 26 Aug 2023 09:51:13 +0000 Subject: [PATCH 0821/2093] cpufreq: powernow-k8: Use related_cpus instead of cpus in driver.exit() [ Upstream commit 03997da042dac73c69e60d91942c727c76828b65 ] Since the 'cpus' field of policy structure will become empty in the cpufreq core API, it is better to use 'related_cpus' in the exit() callback of driver. Fixes: c3274763bfc3 ("cpufreq: powernow-k8: Initialize per-cpu data-structures properly") Signed-off-by: Liao Chang Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/cpufreq/powernow-k8.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index d289036beff2..b10f7a1b77f1 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -1101,7 +1101,8 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol) kfree(data->powernow_table); kfree(data); - for_each_cpu(cpu, pol->cpus) + /* pol->cpus will be empty here, use related_cpus instead. */ + for_each_cpu(cpu, pol->related_cpus) per_cpu(powernow_data, cpu) = NULL; return 0; From 010c6a02e6e1448356e2d9ae1248c9077c15ce2f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Jun 2023 15:19:42 +0200 Subject: [PATCH 0822/2093] selftests/bpf: Fix bpf_nf failure upon test rerun [ Upstream commit 17e8e5d6e09adb4b4f4fb5c89b3ec3fcae2c64a6 ] Alexei reported: After fast forwarding bpf-next today bpf_nf test started to fail when run twice: $ ./test_progs -t bpf_nf #17 bpf_nf:OK Summary: 1/10 PASSED, 0 SKIPPED, 0 FAILED $ ./test_progs -t bpf_nf All error logs: test_bpf_nf_ct:PASS:test_bpf_nf__open_and_load 0 nsec test_bpf_nf_ct:PASS:iptables-legacy -t raw -A PREROUTING -j CONNMARK --set-mark 42/0 0 nsec (network_helpers.c:102: errno: Address already in use) Failed to bind socket test_bpf_nf_ct:FAIL:start_server unexpected start_server: actual -1 < expected 0 #17/1 bpf_nf/xdp-ct:FAIL test_bpf_nf_ct:PASS:test_bpf_nf__open_and_load 0 nsec test_bpf_nf_ct:PASS:iptables-legacy -t raw -A PREROUTING -j CONNMARK --set-mark 42/0 0 nsec (network_helpers.c:102: errno: Address already in use) Failed to bind socket test_bpf_nf_ct:FAIL:start_server unexpected start_server: actual -1 < expected 0 #17/2 bpf_nf/tc-bpf-ct:FAIL #17 bpf_nf:FAIL Summary: 0/8 PASSED, 0 SKIPPED, 1 FAILED I was able to locally reproduce as well. Rearrange the connection teardown so that the client closes its connection first so that we don't need to linger in TCP time-wait. Fixes: e81fbd4c1ba7 ("selftests/bpf: Add existing connection bpf_*_ct_lookup() test") Reported-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/CAADnVQ+0dnDq_v_vH1EfkacbfGnHANaon7zsw10pMb-D9FS0Pw@mail.gmail.com Link: https://lore.kernel.org/bpf/20230626131942.5100-1-daniel@iogearbox.net Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/prog_tests/bpf_nf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index 8a838ea8bdf3..b2998896f9f7 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -123,12 +123,13 @@ static void test_bpf_nf_ct(int mode) ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting"); ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting"); end: - if (srv_client_fd != -1) - close(srv_client_fd); if (client_fd != -1) close(client_fd); + if (srv_client_fd != -1) + close(srv_client_fd); if (srv_fd != -1) close(srv_fd); + snprintf(cmd, sizeof(cmd), iptables, "-D"); system(cmd); test_bpf_nf__destroy(skel); From 4d5f00b2fa2c8577da48c9526c3e28abeb06c5fc Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 7 Jul 2023 10:54:22 +0100 Subject: [PATCH 0823/2093] bpftool: use a local copy of perf_event to fix accessing :: Bpf_cookie [ Upstream commit 4cbeeb0dc02f8ac7b975b2ab0080ace53d43d62a ] When CONFIG_PERF_EVENTS is not set, struct perf_event remains empty. However, the structure is being used by bpftool indirectly via BTF. This leads to: skeleton/pid_iter.bpf.c:49:30: error: no member named 'bpf_cookie' in 'struct perf_event' return BPF_CORE_READ(event, bpf_cookie); ~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~ ... skeleton/pid_iter.bpf.c:49:9: error: returning 'void' from a function with incompatible result type '__u64' (aka 'unsigned long long') return BPF_CORE_READ(event, bpf_cookie); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tools and samples can't use any CONFIG_ definitions, so the fields used there should always be present. Define struct perf_event___local with the `preserve_access_index` attribute inside the pid_iter BPF prog to allow compiling on any configs. CO-RE will substitute it with the real struct perf_event accesses later on. Fixes: cbdaf71f7e65 ("bpftool: Add bpf_cookie to link output") Suggested-by: Andrii Nakryiko Signed-off-by: Alexander Lobakin Signed-off-by: Quentin Monnet Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230707095425.168126-2-quentin@isovalent.com Signed-off-by: Sasha Levin --- tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index eb05ea53afb1..e2af8e5fb29e 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -15,6 +15,10 @@ enum bpf_obj_type { BPF_OBJ_BTF, }; +struct perf_event___local { + u64 bpf_cookie; +} __attribute__((preserve_access_index)); + extern const void bpf_link_fops __ksym; extern const void bpf_map_fops __ksym; extern const void bpf_prog_fops __ksym; @@ -41,8 +45,8 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) /* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ static __u64 get_bpf_cookie(struct bpf_link *link) { + struct perf_event___local *event; struct bpf_perf_link *perf_link; - struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = BPF_CORE_READ(perf_link, perf_file, private_data); From 840c64d96e3920144e9616eec6cc66eb3a2325b9 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 7 Jul 2023 10:54:23 +0100 Subject: [PATCH 0824/2093] bpftool: Define a local bpf_perf_link to fix accessing its fields [ Upstream commit 67a43462ee2405c94e985a747bdcb8e3a0d66203 ] When building bpftool with !CONFIG_PERF_EVENTS: skeleton/pid_iter.bpf.c:47:14: error: incomplete definition of type 'struct bpf_perf_link' perf_link = container_of(link, struct bpf_perf_link, link); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helpers.h:74:22: note: expanded from macro 'container_of' ((type *)(__mptr - offsetof(type, member))); \ ^~~~~~~~~~~~~~~~~~~~~~ tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helpers.h:68:60: note: expanded from macro 'offsetof' #define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) ~~~~~~~~~~~^ skeleton/pid_iter.bpf.c:44:9: note: forward declaration of 'struct bpf_perf_link' struct bpf_perf_link *perf_link; ^ &bpf_perf_link is being defined and used only under the ifdef. Define struct bpf_perf_link___local with the `preserve_access_index` attribute inside the pid_iter BPF prog to allow compiling on any configs. CO-RE will substitute it with the real struct bpf_perf_link accesses later on. container_of() uses offsetof(), which does the necessary CO-RE relocation if the field is specified with `preserve_access_index` - as is the case for struct bpf_perf_link___local. Fixes: cbdaf71f7e65 ("bpftool: Add bpf_cookie to link output") Suggested-by: Andrii Nakryiko Signed-off-by: Alexander Lobakin Signed-off-by: Quentin Monnet Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230707095425.168126-3-quentin@isovalent.com Signed-off-by: Sasha Levin --- tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index e2af8e5fb29e..3a4c4f7d83d8 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -15,6 +15,11 @@ enum bpf_obj_type { BPF_OBJ_BTF, }; +struct bpf_perf_link___local { + struct bpf_link link; + struct file *perf_file; +} __attribute__((preserve_access_index)); + struct perf_event___local { u64 bpf_cookie; } __attribute__((preserve_access_index)); @@ -45,10 +50,10 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) /* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ static __u64 get_bpf_cookie(struct bpf_link *link) { + struct bpf_perf_link___local *perf_link; struct perf_event___local *event; - struct bpf_perf_link *perf_link; - perf_link = container_of(link, struct bpf_perf_link, link); + perf_link = container_of(link, struct bpf_perf_link___local, link); event = BPF_CORE_READ(perf_link, perf_file, private_data); return BPF_CORE_READ(event, bpf_cookie); } From 0b20dc1edd88f1eec75567ac971da077b8379818 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 7 Jul 2023 10:54:24 +0100 Subject: [PATCH 0825/2093] bpftool: Use a local copy of BPF_LINK_TYPE_PERF_EVENT in pid_iter.bpf.c [ Upstream commit 44ba7b30e84fb40da2295e85a6d209e199fdc977 ] In order to allow the BPF program in bpftool's pid_iter.bpf.c to compile correctly on hosts where vmlinux.h does not define BPF_LINK_TYPE_PERF_EVENT (running kernel versions lower than 5.15, for example), define and use a local copy of the enum value. This requires LLVM 12 or newer to build the BPF program. Fixes: cbdaf71f7e65 ("bpftool: Add bpf_cookie to link output") Signed-off-by: Quentin Monnet Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230707095425.168126-4-quentin@isovalent.com Signed-off-by: Sasha Levin --- tools/bpf/bpftool/skeleton/pid_iter.bpf.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index 3a4c4f7d83d8..26004f0c5a6a 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -24,6 +24,10 @@ struct perf_event___local { u64 bpf_cookie; } __attribute__((preserve_access_index)); +enum bpf_link_type___local { + BPF_LINK_TYPE_PERF_EVENT___local = 7, +}; + extern const void bpf_link_fops __ksym; extern const void bpf_map_fops __ksym; extern const void bpf_prog_fops __ksym; @@ -93,10 +97,13 @@ int iter(struct bpf_iter__task_file *ctx) e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); - if (obj_type == BPF_OBJ_LINK) { + if (obj_type == BPF_OBJ_LINK && + bpf_core_enum_value_exists(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { struct bpf_link *link = (struct bpf_link *) file->private_data; - if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) { + if (link->type == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { e.has_bpf_cookie = true; e.bpf_cookie = get_bpf_cookie(link); } From fc7ed36a31b15d21f02bd409aa7eda6752e88c5e Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 7 Jul 2023 10:54:25 +0100 Subject: [PATCH 0826/2093] bpftool: Use a local bpf_perf_event_value to fix accessing its fields [ Upstream commit 658ac06801315b739774a15796ff06913ef5cad5 ] Fix the following error when building bpftool: CLANG profiler.bpf.o CLANG pid_iter.bpf.o skeleton/profiler.bpf.c:18:21: error: invalid application of 'sizeof' to an incomplete type 'struct bpf_perf_event_value' __uint(value_size, sizeof(struct bpf_perf_event_value)); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helpers.h:13:39: note: expanded from macro '__uint' tools/bpf/bpftool/bootstrap/libbpf/include/bpf/bpf_helper_defs.h:7:8: note: forward declaration of 'struct bpf_perf_event_value' struct bpf_perf_event_value; ^ struct bpf_perf_event_value is being used in the kernel only when CONFIG_BPF_EVENTS is enabled, so it misses a BTF entry then. Define struct bpf_perf_event_value___local with the `preserve_access_index` attribute inside the pid_iter BPF prog to allow compiling on any configs. It is a full mirror of a UAPI structure, so is compatible both with and w/o CO-RE. bpf_perf_event_read_value() requires a pointer of the original type, so a cast is needed. Fixes: 47c09d6a9f67 ("bpftool: Introduce "prog profile" command") Suggested-by: Andrii Nakryiko Signed-off-by: Alexander Lobakin Signed-off-by: Quentin Monnet Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230707095425.168126-5-quentin@isovalent.com Signed-off-by: Sasha Levin --- tools/bpf/bpftool/skeleton/profiler.bpf.c | 27 ++++++++++++++--------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index ce5b65e07ab1..2f80edc682f1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -4,6 +4,12 @@ #include #include +struct bpf_perf_event_value___local { + __u64 counter; + __u64 enabled; + __u64 running; +} __attribute__((preserve_access_index)); + /* map of perf event fds, num_cpu * num_metric entries */ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -15,14 +21,14 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } fentry_readings SEC(".maps"); /* accumulated readings */ struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(value_size, sizeof(struct bpf_perf_event_value___local)); } accum_readings SEC(".maps"); /* sample counts, one per cpu */ @@ -39,7 +45,7 @@ const volatile __u32 num_metric = 1; SEC("fentry/XXX") int BPF_PROG(fentry_XXX) { - struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS]; u32 key = bpf_get_smp_processor_id(); u32 i; @@ -53,10 +59,10 @@ int BPF_PROG(fentry_XXX) } for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { - struct bpf_perf_event_value reading; + struct bpf_perf_event_value___local reading; int err; - err = bpf_perf_event_read_value(&events, key, &reading, + err = bpf_perf_event_read_value(&events, key, (void *)&reading, sizeof(reading)); if (err) return 0; @@ -68,14 +74,14 @@ int BPF_PROG(fentry_XXX) } static inline void -fexit_update_maps(u32 id, struct bpf_perf_event_value *after) +fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after) { - struct bpf_perf_event_value *before, diff; + struct bpf_perf_event_value___local *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ if (before && before->counter) { - struct bpf_perf_event_value *accum; + struct bpf_perf_event_value___local *accum; diff.counter = after->counter - before->counter; diff.enabled = after->enabled - before->enabled; @@ -93,7 +99,7 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value *after) SEC("fexit/XXX") int BPF_PROG(fexit_XXX) { - struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; + struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); u32 i, zero = 0; int err; @@ -102,7 +108,8 @@ int BPF_PROG(fexit_XXX) /* read all events before updating the maps, to reduce error */ for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, - readings + i, sizeof(*readings)); + (void *)(readings + i), + sizeof(*readings)); if (err) return 0; } From 0cfbadb153515720b0b81fc8d643709f1f64bbf9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 10 Jul 2023 19:41:50 -0700 Subject: [PATCH 0827/2093] libbpf: Fix realloc API handling in zero-sized edge cases [ Upstream commit 8a0260dbf6553c969248b6530cafadac46562f47 ] realloc() and reallocarray() can either return NULL or a special non-NULL pointer, if their size argument is zero. This requires a bit more care to handle NULL-as-valid-result situation differently from NULL-as-error case. This has caused real issues before ([0]), and just recently bit again in production when performing bpf_program__attach_usdt(). This patch fixes 4 places that do or potentially could suffer from this mishandling of NULL, including the reported USDT-related one. There are many other places where realloc()/reallocarray() is used and NULL is always treated as an error value, but all those have guarantees that their size is always non-zero, so those spot don't need any extra handling. [0] d08ab82f59d5 ("libbpf: Fix double-free when linker processes empty sections") Fixes: 999783c8bbda ("libbpf: Wire up spec management and other arch-independent USDT logic") Fixes: b63b3c490eee ("libbpf: Add bpf_program__set_insns function") Fixes: 697f104db8a6 ("libbpf: Support custom SEC() handlers") Fixes: b12688267280 ("libbpf: Change the order of data and text relocations.") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230711024150.1566433-1-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/libbpf.c | 15 ++++++++++++--- tools/lib/bpf/usdt.c | 5 ++++- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index b9a29d105376..eeb2693128d8 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6063,7 +6063,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra if (main_prog == subprog) return 0; relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); - if (!relos) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (!relos && new_cnt) return -ENOMEM; if (subprog->nr_reloc) memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, @@ -8345,7 +8349,8 @@ int bpf_program__set_insns(struct bpf_program *prog, return -EBUSY; insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); - if (!insns) { + /* NULL is a valid return from reallocarray if the new count is zero */ + if (!insns && new_insn_cnt) { pr_warn("prog '%s': failed to realloc prog code\n", prog->name); return -ENOMEM; } @@ -8640,7 +8645,11 @@ int libbpf_unregister_prog_handler(int handler_id) /* try to shrink the array, but it's ok if we couldn't */ sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); - if (sec_defs) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (sec_defs || custom_sec_def_cnt == 0) custom_sec_defs = sec_defs; return 0; diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 49f3c3b7f609..af1cb30556b4 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -852,8 +852,11 @@ static int bpf_link_usdt_detach(struct bpf_link *link) * system is so exhausted on memory, it's the least of user's * concerns, probably. * So just do our best here to return those IDs to usdt_manager. + * Another edge case when we can legitimately get NULL is when + * new_cnt is zero, which can happen in some edge cases, so we + * need to be careful about that. */ - if (new_free_ids) { + if (new_free_ids || new_cnt == 0) { memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids, usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids)); man->free_spec_ids = new_free_ids; From 780f072f4fad608f3d0f15289d1472137b29adc8 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 9 Jul 2023 02:56:25 +0000 Subject: [PATCH 0828/2093] bpf: Clear the probe_addr for uprobe [ Upstream commit 5125e757e62f6c1d5478db4c2b61a744060ddf3f ] To avoid returning uninitialized or random values when querying the file descriptor (fd) and accessing probe_addr, it is necessary to clear the variable prior to its use. Fixes: 41bdc4b40ed6 ("bpf: introduce bpf subcommand BPF_TASK_FD_QUERY") Signed-off-by: Yafang Shao Acked-by: Yonghong Song Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20230709025630.3735-6-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- include/linux/trace_events.h | 3 ++- kernel/trace/bpf_trace.c | 2 +- kernel/trace/trace_uprobe.c | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 04c59f8d801f..422f4ca656cf 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -863,7 +863,8 @@ extern int perf_uprobe_init(struct perf_event *event, extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, - u64 *probe_offset, bool perf_type_tracepoint); + u64 *probe_offset, u64 *probe_addr, + bool perf_type_tracepoint); #endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ad04390883ad..9fc5db194027 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2390,7 +2390,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_UPROBE_EVENTS if (flags & TRACE_EVENT_FL_UPROBE) err = bpf_get_uprobe_info(event, fd_type, buf, - probe_offset, + probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 2ac06a642863..127c78aec17d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1418,7 +1418,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, - bool perf_type_tracepoint) + u64 *probe_addr, bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1435,6 +1435,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; + *probe_addr = 0; return 0; } #endif /* CONFIG_PERF_EVENTS */ From 912310dd841b2e0a2e8319fd68bece8e61e3726c Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 13 Jul 2023 02:56:41 +0000 Subject: [PATCH 0829/2093] bpf: Fix an error in verifying a field in a union [ Upstream commit 33937607efa050d9e237e0c4ac4ada02d961c466 ] We are utilizing BPF LSM to monitor BPF operations within our container environment. When we add support for raw_tracepoint, it hits below error. ; (const void *)attr->raw_tracepoint.name); 27: (79) r3 = *(u64 *)(r2 +0) access beyond the end of member map_type (mend:4) in struct (anon) with off 0 size 8 It can be reproduced with below BPF prog. SEC("lsm/bpf") int BPF_PROG(bpf_audit, int cmd, union bpf_attr *attr, unsigned int size) { switch (cmd) { case BPF_RAW_TRACEPOINT_OPEN: bpf_printk("raw_tracepoint is %s", attr->raw_tracepoint.name); break; default: break; } return 0; } The reason is that when accessing a field in a union, such as bpf_attr, if the field is located within a nested struct that is not the first member of the union, it can result in incorrect field verification. union bpf_attr { struct { __u32 map_type; <<<< Actually it will find that field. __u32 key_size; __u32 value_size; ... }; ... struct { __u64 name; <<<< We want to verify this field. __u32 prog_fd; } raw_tracepoint; }; Considering the potential deep nesting levels, finding a perfect solution to address this issue has proven challenging. Therefore, I propose a solution where we simply skip the verification process if the field in question is located within a union. Fixes: 7e3617a72df3 ("bpf: Add array support to btf_struct_access") Signed-off-by: Yafang Shao Link: https://lore.kernel.org/r/20230713025642.27477-4-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index fb78bb26786f..7582ec4fd413 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5788,7 +5788,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, * that also allows using an array of int as a scratch * space. e.g. skb->cb[]. */ - if (off + size > mtrue_end) { + if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) { bpf_log(log, "access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n", mname, mtrue_end, tname, off, size); From 01964c6308249cb67077fa472e8f08de9eb0ec3f Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Thu, 22 Jun 2023 10:26:35 +0100 Subject: [PATCH 0830/2093] crypto: qat - change value of default idle filter [ Upstream commit 0f942bdfe9d463be3073301519492f8d53c6b2d5 ] The power management configuration of 4xxx devices is too aggressive and in some conditions the device might be prematurely put to a low power state. Increase the idle filter value to prevent that. In future, this will be set by firmware. Fixes: e5745f34113b ("crypto: qat - enable power management for QAT GEN4") Signed-off-by: Giovanni Cabiddu Reviewed-by: Damian Muszynski Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/qat/qat_common/adf_gen4_pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pm.h b/drivers/crypto/qat/qat_common/adf_gen4_pm.h index f8f8a9ee29e5..db4326933d1c 100644 --- a/drivers/crypto/qat/qat_common/adf_gen4_pm.h +++ b/drivers/crypto/qat/qat_common/adf_gen4_pm.h @@ -35,7 +35,7 @@ #define ADF_GEN4_PM_MSG_PENDING BIT(0) #define ADF_GEN4_PM_MSG_PAYLOAD_BIT_MASK GENMASK(28, 1) -#define ADF_GEN4_PM_DEFAULT_IDLE_FILTER (0x0) +#define ADF_GEN4_PM_DEFAULT_IDLE_FILTER (0x6) #define ADF_GEN4_PM_MAX_IDLE_FILTER (0x7) int adf_gen4_enable_pm(struct adf_accel_dev *accel_dev); From 73d97508ab11a4986752e22e62b3c49213272c0f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 18 Jul 2023 16:20:49 +0000 Subject: [PATCH 0831/2093] tcp: tcp_enter_quickack_mode() should be static [ Upstream commit 03b123debcbc8db987bda17ed8412cc011064c22 ] After commit d2ccd7bc8acd ("tcp: avoid resetting ACK timer in DCTCP"), tcp_enter_quickack_mode() is only used from net/ipv4/tcp_input.c. Fixes: d2ccd7bc8acd ("tcp: avoid resetting ACK timer in DCTCP") Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Neal Cardwell Link: https://lore.kernel.org/r/20230718162049.1444938-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 1 - net/ipv4/tcp_input.c | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index e9c8f88f4769..5fd69f2342a4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -355,7 +355,6 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, bool force_schedule); -void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2d3ea2e3456..c697836f2b5b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -287,7 +287,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -295,7 +295,6 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } -EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. From 79a8ea5bf421bc3b71265ba1caddb88cb32d6422 Mon Sep 17 00:00:00 2001 From: Martin Kaiser Date: Sun, 2 Jul 2023 19:35:02 +0200 Subject: [PATCH 0832/2093] hwrng: nomadik - keep clock enabled while hwrng is registered [ Upstream commit 039980de89dc9dd757418d6f296e4126cc3f86c3 ] The nomadik driver uses devres to register itself with the hwrng core, the driver will be unregistered from hwrng when its device goes out of scope. This happens after the driver's remove function is called. However, nomadik's clock is disabled in the remove function. There's a short timeframe where nomadik is still registered with the hwrng core although its clock is disabled. I suppose the clock must be active to access the hardware and serve requests from the hwrng core. Switch to devm_clk_get_enabled and let devres disable the clock and unregister the hwrng. This avoids the race condition. Fixes: 3e75241be808 ("hwrng: drivers - Use device-managed registration API") Signed-off-by: Martin Kaiser Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/nomadik-rng.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/char/hw_random/nomadik-rng.c b/drivers/char/hw_random/nomadik-rng.c index e8f9621e7954..3774adf903a8 100644 --- a/drivers/char/hw_random/nomadik-rng.c +++ b/drivers/char/hw_random/nomadik-rng.c @@ -13,8 +13,6 @@ #include #include -static struct clk *rng_clk; - static int nmk_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) { void __iomem *base = (void __iomem *)rng->priv; @@ -36,21 +34,20 @@ static struct hwrng nmk_rng = { static int nmk_rng_probe(struct amba_device *dev, const struct amba_id *id) { + struct clk *rng_clk; void __iomem *base; int ret; - rng_clk = devm_clk_get(&dev->dev, NULL); + rng_clk = devm_clk_get_enabled(&dev->dev, NULL); if (IS_ERR(rng_clk)) { dev_err(&dev->dev, "could not get rng clock\n"); ret = PTR_ERR(rng_clk); return ret; } - clk_prepare_enable(rng_clk); - ret = amba_request_regions(dev, dev->dev.init_name); if (ret) - goto out_clk; + return ret; ret = -ENOMEM; base = devm_ioremap(&dev->dev, dev->res.start, resource_size(&dev->res)); @@ -64,15 +61,12 @@ static int nmk_rng_probe(struct amba_device *dev, const struct amba_id *id) out_release: amba_release_regions(dev); -out_clk: - clk_disable_unprepare(rng_clk); return ret; } static void nmk_rng_remove(struct amba_device *dev) { amba_release_regions(dev); - clk_disable_unprepare(rng_clk); } static const struct amba_id nmk_rng_ids[] = { From 684431894e06bdc3fee8f4e33d6e718ddc474a2a Mon Sep 17 00:00:00 2001 From: Martin Kaiser Date: Tue, 4 Jul 2023 19:32:01 +0200 Subject: [PATCH 0833/2093] hwrng: pic32 - use devm_clk_get_enabled [ Upstream commit 6755ad74aac0fb1c79b14724feb81b2f6ff25847 ] Use devm_clk_get_enabled in the pic32 driver. Ensure that the clock is enabled as long as the driver is registered with the hwrng core. Fixes: 7ea39973d1e5 ("hwrng: pic32 - Use device-managed registration API") Signed-off-by: Martin Kaiser Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/pic32-rng.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/char/hw_random/pic32-rng.c b/drivers/char/hw_random/pic32-rng.c index 99c8bd0859a1..e04a054e8930 100644 --- a/drivers/char/hw_random/pic32-rng.c +++ b/drivers/char/hw_random/pic32-rng.c @@ -36,7 +36,6 @@ struct pic32_rng { void __iomem *base; struct hwrng rng; - struct clk *clk; }; /* @@ -70,6 +69,7 @@ static int pic32_rng_read(struct hwrng *rng, void *buf, size_t max, static int pic32_rng_probe(struct platform_device *pdev) { struct pic32_rng *priv; + struct clk *clk; u32 v; int ret; @@ -81,13 +81,9 @@ static int pic32_rng_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); - priv->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(priv->clk)) - return PTR_ERR(priv->clk); - - ret = clk_prepare_enable(priv->clk); - if (ret) - return ret; + clk = devm_clk_get_enabled(&pdev->dev, NULL); + if (IS_ERR(clk)) + return PTR_ERR(clk); /* enable TRNG in enhanced mode */ v = TRNGEN | TRNGMOD; @@ -98,15 +94,11 @@ static int pic32_rng_probe(struct platform_device *pdev) ret = devm_hwrng_register(&pdev->dev, &priv->rng); if (ret) - goto err_register; + return ret; platform_set_drvdata(pdev, priv); return 0; - -err_register: - clk_disable_unprepare(priv->clk); - return ret; } static int pic32_rng_remove(struct platform_device *pdev) @@ -114,7 +106,6 @@ static int pic32_rng_remove(struct platform_device *pdev) struct pic32_rng *rng = platform_get_drvdata(pdev); writel(0, rng->base + RNGCON); - clk_disable_unprepare(rng->clk); return 0; } From 39a6b4bbc57362ab5fe79c989ca0e80497be3d23 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 21 Jul 2023 17:55:33 +0300 Subject: [PATCH 0834/2093] regmap: rbtree: Use alloc_flags for memory allocations [ Upstream commit 0c8b0bf42c8cef56f7cd9cd876fbb7ece9217064 ] The kunit tests discovered a sleeping in atomic bug. The allocations in the regcache-rbtree code should use the map->alloc_flags instead of GFP_KERNEL. [ 5.005510] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:306 [ 5.005960] in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 117, name: kunit_try_catch [ 5.006219] preempt_count: 1, expected: 0 [ 5.006414] 1 lock held by kunit_try_catch/117: [ 5.006590] #0: 833b9010 (regmap_kunit:86:(config)->lock){....}-{2:2}, at: regmap_lock_spinlock+0x14/0x1c [ 5.007493] irq event stamp: 162 [ 5.007627] hardirqs last enabled at (161): [<80786738>] crng_make_state+0x1a0/0x294 [ 5.007871] hardirqs last disabled at (162): [<80c531ec>] _raw_spin_lock_irqsave+0x7c/0x80 [ 5.008119] softirqs last enabled at (0): [<801110ac>] copy_process+0x810/0x2138 [ 5.008356] softirqs last disabled at (0): [<00000000>] 0x0 [ 5.008688] CPU: 0 PID: 117 Comm: kunit_try_catch Tainted: G N 6.4.4-rc3-g0e8d2fdfb188 #1 [ 5.009011] Hardware name: Generic DT based system [ 5.009277] unwind_backtrace from show_stack+0x18/0x1c [ 5.009497] show_stack from dump_stack_lvl+0x38/0x5c [ 5.009676] dump_stack_lvl from __might_resched+0x188/0x2d0 [ 5.009860] __might_resched from __kmem_cache_alloc_node+0x1dc/0x25c [ 5.010061] __kmem_cache_alloc_node from kmalloc_trace+0x30/0xc8 [ 5.010254] kmalloc_trace from regcache_rbtree_write+0x26c/0x468 [ 5.010446] regcache_rbtree_write from _regmap_write+0x88/0x140 [ 5.010634] _regmap_write from regmap_write+0x44/0x68 [ 5.010803] regmap_write from basic_read_write+0x8c/0x270 [ 5.010980] basic_read_write from kunit_try_run_case+0x48/0xa0 Fixes: 28644c809f44 ("regmap: Add the rbtree cache support") Reported-by: Guenter Roeck Closes: https://lore.kernel.org/all/ee59d128-413c-48ad-a3aa-d9d350c80042@roeck-us.net/ Signed-off-by: Dan Carpenter Tested-by: Guenter Roeck Link: https://lore.kernel.org/r/58f12a07-5f4b-4a8f-ab84-0a42d1908cb9@moroto.mountain Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/base/regmap/regcache-rbtree.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index fabf87058d80..ae6b8788d5f3 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -277,7 +277,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, blk = krealloc(rbnode->block, blklen * map->cache_word_size, - GFP_KERNEL); + map->alloc_flags); if (!blk) return -ENOMEM; @@ -286,7 +286,7 @@ static int regcache_rbtree_insert_to_block(struct regmap *map, if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) { present = krealloc(rbnode->cache_present, BITS_TO_LONGS(blklen) * sizeof(*present), - GFP_KERNEL); + map->alloc_flags); if (!present) return -ENOMEM; @@ -320,7 +320,7 @@ regcache_rbtree_node_alloc(struct regmap *map, unsigned int reg) const struct regmap_range *range; int i; - rbnode = kzalloc(sizeof(*rbnode), GFP_KERNEL); + rbnode = kzalloc(sizeof(*rbnode), map->alloc_flags); if (!rbnode) return NULL; @@ -346,13 +346,13 @@ regcache_rbtree_node_alloc(struct regmap *map, unsigned int reg) } rbnode->block = kmalloc_array(rbnode->blklen, map->cache_word_size, - GFP_KERNEL); + map->alloc_flags); if (!rbnode->block) goto err_free; rbnode->cache_present = kcalloc(BITS_TO_LONGS(rbnode->blklen), sizeof(*rbnode->cache_present), - GFP_KERNEL); + map->alloc_flags); if (!rbnode->cache_present) goto err_free_block; From 6bf4ccafb35677d110d642c82d4f0b473885260a Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 15 Jul 2023 21:42:57 +0800 Subject: [PATCH 0835/2093] wifi: rtw89: debug: Fix error handling in rtw89_debug_priv_btc_manual_set() [ Upstream commit 59b4cc439f184c5eaa34161ec67af1e16ffabed4 ] If there is a failure during kstrtobool_from_user() rtw89_debug_priv_btc_manual_set should return a negative error code instead of returning the count directly. Fix this bug by returning an error code instead of a count after a failed call of the function "kstrtobool_from_user". Moreover I omitted the label "out" with this source code correction. Fixes: e3ec7017f6a2 ("rtw89: add Realtek 802.11ax driver") Signed-off-by: Zhang Shurong Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/tencent_1C09B99BD7DA9CAD18B00C8F0F050F540607@qq.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtw89/debug.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index ec0af903961f..3a8fe60d0bb7 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -2302,12 +2302,14 @@ static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp, struct rtw89_dev *rtwdev = debugfs_priv->rtwdev; struct rtw89_btc *btc = &rtwdev->btc; bool btc_manual; + int ret; - if (kstrtobool_from_user(user_buf, count, &btc_manual)) - goto out; + ret = kstrtobool_from_user(user_buf, count, &btc_manual); + if (ret) + return ret; btc->ctrl.manual = btc_manual; -out: + return count; } From 328b85e7b14ff08f0f38932288bce1391dd4b311 Mon Sep 17 00:00:00 2001 From: Ming Yen Hsieh Date: Thu, 18 May 2023 22:08:14 +0800 Subject: [PATCH 0836/2093] wifi: mt76: mt7921: fix non-PSC channel scan fail [ Upstream commit 0e5911bb7cc92c00dda9b4d635c1266b7ca915c6 ] Due to the scan command may only request legacy bands and PSC channel in 6GHz band, we are unable to scan the APs on non-PSC channel in this case. Enable WIPHY_FLAG_SPLIT_SCAN_6GHZ to support non-PSC channel (obtained during scan on legacy bands) in 6GHz scan request. Fixes: 50ac15a511e3 ("mt76: mt7921: add 6GHz support") Signed-off-by: Ming Yen Hsieh Signed-off-by: Deren Wu Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7921/init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index 4ad66b344383..c997b8d3ea59 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -80,7 +80,8 @@ mt7921_init_wiphy(struct ieee80211_hw *hw) wiphy->max_sched_scan_ssids = MT76_CONNAC_MAX_SCHED_SCAN_SSID; wiphy->max_match_sets = MT76_CONNAC_MAX_SCAN_MATCH; wiphy->max_sched_scan_reqs = 1; - wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH; + wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH | + WIPHY_FLAG_SPLIT_SCAN_6GHZ; wiphy->reg_notifier = mt7921_regd_notifier; wiphy->features |= NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR | From 99331d7c6ee25f914ff5e9ac76ab7e594b32e865 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:05 +0200 Subject: [PATCH 0837/2093] udp: re-score reuseport groups when connected sockets are present [ Upstream commit f0ea27e7bfe1c34e1f451a63eb68faa1d4c3a86d ] Contrary to TCP, UDP reuseport groups can contain TCP_ESTABLISHED sockets. To support these properly we remember whether a group has a connected socket and skip the fast reuseport early-return. In effect we continue scoring all reuseport sockets and then choose the one with the highest score. The current code fails to re-calculate the score for the result of lookup_reuseport. According to Kuniyuki Iwashima: 1) SO_INCOMING_CPU is set -> selected sk might have +1 score 2) BPF prog returns ESTABLISHED and/or SO_INCOMING_CPU sk -> selected sk will have more than 8 Using the old score could trigger more lookups depending on the order that sockets are created. sk -> sk (SO_INCOMING_CPU) -> sk (ESTABLISHED) | | `-> select the next SO_INCOMING_CPU sk | `-> select itself (We should save this lookup) Fixes: efc6b6f6c311 ("udp: Improve load balancing for SO_REUSEPORT.") Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-1-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- net/ipv4/udp.c | 20 +++++++++++++++----- net/ipv6/udp.c | 19 ++++++++++++++----- 2 files changed, 29 insertions(+), 10 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 956d6797c76f..42c1f7d9a980 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -445,14 +445,24 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - result = lookup_reuseport(net, sk, skb, - saddr, sport, daddr, hnum); + badness = score; + result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + if (!result) { + result = sk; + continue; + } + /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk)) + if (!reuseport_has_conns(sk)) return result; - result = result ? : sk; - badness = score; + /* Reuseport logic returned an error, keep original score. */ + if (IS_ERR(result)) + continue; + + badness = compute_score(result, net, saddr, sport, + daddr, hnum, dif, sdif); + } } return result; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 27348172b25b..64b36c2ba774 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -193,14 +193,23 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - result = lookup_reuseport(net, sk, skb, - saddr, sport, daddr, hnum); + badness = score; + result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + if (!result) { + result = sk; + continue; + } + /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk)) + if (!reuseport_has_conns(sk)) return result; - result = result ? : sk; - badness = score; + /* Reuseport logic returned an error, keep original score. */ + if (IS_ERR(result)) + continue; + + badness = compute_score(sk, net, saddr, sport, + daddr, hnum, dif, sdif); } } return result; From c0ce0fb76610d5fad31f56f2ca8241a2a6717a1b Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:06 +0200 Subject: [PATCH 0838/2093] bpf: reject unhashed sockets in bpf_sk_assign [ Upstream commit 67312adc96b5a585970d03b62412847afe2c6b01 ] The semantics for bpf_sk_assign are as follows: sk = some_lookup_func() bpf_sk_assign(skb, sk) bpf_sk_release(sk) That is, the sk is not consumed by bpf_sk_assign. The function therefore needs to make sure that sk lives long enough to be consumed from __inet_lookup_skb. The path through the stack for a TCPv4 packet is roughly: netif_receive_skb_core: takes RCU read lock __netif_receive_skb_core: sch_handle_ingress: tcf_classify: bpf_sk_assign() deliver_ptype_list_skb: deliver_skb: ip_packet_type->func == ip_rcv: ip_rcv_core: ip_rcv_finish_core: dst_input: ip_local_deliver: ip_local_deliver_finish: ip_protocol_deliver_rcu: tcp_v4_rcv: __inet_lookup_skb: skb_steal_sock The existing helper takes advantage of the fact that everything happens in the same RCU critical section: for sockets with SOCK_RCU_FREE set bpf_sk_assign never takes a reference. skb_steal_sock then checks SOCK_RCU_FREE again and does sock_put if necessary. This approach assumes that SOCK_RCU_FREE is never set on a sk between bpf_sk_assign and skb_steal_sock, but this invariant is violated by unhashed UDP sockets. A new UDP socket is created in TCP_CLOSE state but without SOCK_RCU_FREE set. That flag is only added in udp_lib_get_port() which happens when a socket is bound. When bpf_sk_assign was added it wasn't possible to access unhashed UDP sockets from BPF, so this wasn't a problem. This changed in commit 0c48eefae712 ("sock_map: Lift socket state restriction for datagram sockets"), but the helper wasn't adjusted accordingly. The following sequence of events will therefore lead to a refcount leak: 1. Add socket(AF_INET, SOCK_DGRAM) to a sockmap. 2. Pull socket out of sockmap and bpf_sk_assign it. Since SOCK_RCU_FREE is not set we increment the refcount. 3. bind() or connect() the socket, setting SOCK_RCU_FREE. 4. skb_steal_sock will now set refcounted = false due to SOCK_RCU_FREE. 5. tcp_v4_rcv() skips sock_put(). Fix the problem by rejecting unhashed sockets in bpf_sk_assign(). This matches the behaviour of __inet_lookup_skb which is ultimately the goal of bpf_sk_assign(). Fixes: cf7fbe660f2d ("bpf: Add socket assign support") Cc: Joe Stringer Signed-off-by: Lorenz Bauer Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-2-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index 419ce7c61bd6..9fd7c88b5db4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7259,6 +7259,8 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) return -ENETUNREACH; if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) return -ESOCKTNOSUPPORT; + if (sk_unhashed(sk)) + return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; From f5f7aa2b6b8f4f8c5449228896db6ba9631ee391 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 23 Jul 2023 16:03:50 +0800 Subject: [PATCH 0839/2093] wifi: mt76: testmode: add nla_policy for MT76_TM_ATTR_TX_LENGTH [ Upstream commit 74f12d511625e603fac8c0c2b6872e687e56dd61 ] It seems that the nla_policy in mt76_tm_policy is missed for attribute MT76_TM_ATTR_TX_LENGTH. This patch adds the correct description to make sure the u32 val = nla_get_u32(tb[MT76_TM_ATTR_TX_LENGTH]); in function mt76_testmode_cmd() is safe and will not result in out-of-attribute read. Fixes: f0efa8621550 ("mt76: add API for testmode support") Signed-off-by: Lin Ma Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/testmode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/mediatek/mt76/testmode.c b/drivers/net/wireless/mediatek/mt76/testmode.c index 0accc71a91c9..4644dace9bb3 100644 --- a/drivers/net/wireless/mediatek/mt76/testmode.c +++ b/drivers/net/wireless/mediatek/mt76/testmode.c @@ -8,6 +8,7 @@ const struct nla_policy mt76_tm_policy[NUM_MT76_TM_ATTRS] = { [MT76_TM_ATTR_RESET] = { .type = NLA_FLAG }, [MT76_TM_ATTR_STATE] = { .type = NLA_U8 }, [MT76_TM_ATTR_TX_COUNT] = { .type = NLA_U32 }, + [MT76_TM_ATTR_TX_LENGTH] = { .type = NLA_U32 }, [MT76_TM_ATTR_TX_RATE_MODE] = { .type = NLA_U8 }, [MT76_TM_ATTR_TX_RATE_NSS] = { .type = NLA_U8 }, [MT76_TM_ATTR_TX_RATE_IDX] = { .type = NLA_U8 }, From ce60bfc24c882dc4dd5316dbddc6e1e2117a4be2 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 22 Jul 2023 23:49:09 +0800 Subject: [PATCH 0840/2093] spi: tegra20-sflash: fix to check return value of platform_get_irq() in tegra_sflash_probe() [ Upstream commit 29a449e765ff70a5bd533be94babb6d36985d096 ] The platform_get_irq might be failed and return a negative result. So there should have an error handling code. Fixed this by adding an error handling code. Fixes: 8528547bcc33 ("spi: tegra: add spi driver for sflash controller") Signed-off-by: Zhang Shurong Link: https://lore.kernel.org/r/tencent_71FC162D589E4788C2152AAC84CD8D5C6D06@qq.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-tegra20-sflash.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c index 220ee08c4a06..d4bebb431417 100644 --- a/drivers/spi/spi-tegra20-sflash.c +++ b/drivers/spi/spi-tegra20-sflash.c @@ -455,7 +455,11 @@ static int tegra_sflash_probe(struct platform_device *pdev) goto exit_free_master; } - tsd->irq = platform_get_irq(pdev, 0); + ret = platform_get_irq(pdev, 0); + if (ret < 0) + goto exit_free_master; + tsd->irq = ret; + ret = request_irq(tsd->irq, tegra_sflash_isr, 0, dev_name(&pdev->dev), tsd); if (ret < 0) { From 2dd5c7f4200abfa542ac1e85e53aa892e4299a16 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Tue, 4 Jul 2023 11:23:37 +0200 Subject: [PATCH 0841/2093] can: gs_usb: gs_usb_receive_bulk_callback(): count RX overflow errors also in case of OOM [ Upstream commit 6c8bc15f02b85bc8f47074110d8fd8caf7a1e42d ] In case of an RX overflow error from the CAN controller and an OOM where no skb can be allocated, the error counters are not incremented. Fix this by first incrementing the error counters and then allocate the skb. Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices") Link: https://lore.kernel.org/all/20230718-gs_usb-cleanups-v1-7-c3b9154ec605@pengutronix.de Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/usb/gs_usb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5858cbafbc96..264a0f764e01 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -626,6 +626,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) } if (hf->flags & GS_CAN_FLAG_OVERFLOW) { + stats->rx_over_errors++; + stats->rx_errors++; + skb = alloc_can_err_skb(netdev, &cf); if (!skb) goto resubmit_urb; @@ -633,8 +636,6 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) cf->can_id |= CAN_ERR_CRTL; cf->len = CAN_ERR_DLC; cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; - stats->rx_over_errors++; - stats->rx_errors++; netif_rx(skb); } From 49b6db89ab287f443e6fd9aa178780d76c8f1f60 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Thu, 27 Jul 2023 02:35:06 +0800 Subject: [PATCH 0842/2093] wifi: mt76: mt7915: fix power-limits while chan_switch [ Upstream commit 6c0570bc21ec2073890aa252c8420ca7bec402e4 ] If user changes the channel without completely disabling the interface the txpower_sku values reported track the old channel the device was operating on. If user bounces the interface the correct power tables are applied. mt7915_sku_group_len array gets updated before the channel switch happens so it uses data from the old channel. Fixes: ecb187a74e18 ("mt76: mt7915: rework the flow of txpower setting") Fixes: f1d962369d56 ("mt76: mt7915: implement HE per-rate tx power support") Reported-By: Chad Monroe Tested-by: Chad Monroe Signed-off-by: Allen Ye Signed-off-by: Ryder Lee Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7915/main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index bda26bd62412..3280843ea856 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -455,7 +455,8 @@ static int mt7915_config(struct ieee80211_hw *hw, u32 changed) ieee80211_wake_queues(hw); } - if (changed & IEEE80211_CONF_CHANGE_POWER) { + if (changed & (IEEE80211_CONF_CHANGE_POWER | + IEEE80211_CONF_CHANGE_CHANNEL)) { ret = mt7915_mcu_set_txpower_sku(phy); if (ret) return ret; From 3975e21d4d01efaf0296ded40d11c06589c49245 Mon Sep 17 00:00:00 2001 From: Polaris Pi Date: Sun, 23 Jul 2023 07:07:41 +0000 Subject: [PATCH 0843/2093] wifi: mwifiex: Fix OOB and integer underflow when rx packets [ Upstream commit 11958528161731c58e105b501ed60b83a91ea941 ] Make sure mwifiex_process_mgmt_packet, mwifiex_process_sta_rx_packet and mwifiex_process_uap_rx_packet, mwifiex_uap_queue_bridged_pkt and mwifiex_process_rx_packet not out-of-bounds access the skb->data buffer. Fixes: 2dbaf751b1de ("mwifiex: report received management frames to cfg80211") Signed-off-by: Polaris Pi Reviewed-by: Matthew Wang Reviewed-by: Brian Norris Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230723070741.1544662-1-pinkperfect2021@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/sta_rx.c | 11 ++++++++++- .../net/wireless/marvell/mwifiex/uap_txrx.c | 19 +++++++++++++++++++ drivers/net/wireless/marvell/mwifiex/util.c | 10 +++++++--- 3 files changed, 36 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c index 13659b02ba88..f2899d53a43f 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c @@ -86,6 +86,14 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv, rx_pkt_len = le16_to_cpu(local_rx_pd->rx_pkt_length); rx_pkt_hdr = (void *)local_rx_pd + rx_pkt_off; + if (sizeof(*rx_pkt_hdr) + rx_pkt_off > skb->len) { + mwifiex_dbg(priv->adapter, ERROR, + "wrong rx packet offset: len=%d, rx_pkt_off=%d\n", + skb->len, rx_pkt_off); + priv->stats.rx_dropped++; + dev_kfree_skb_any(skb); + } + if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, sizeof(bridge_tunnel_header))) || (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header, @@ -194,7 +202,8 @@ int mwifiex_process_sta_rx_packet(struct mwifiex_private *priv, rx_pkt_hdr = (void *)local_rx_pd + rx_pkt_offset; - if ((rx_pkt_offset + rx_pkt_length) > (u16) skb->len) { + if ((rx_pkt_offset + rx_pkt_length) > skb->len || + sizeof(rx_pkt_hdr->eth803_hdr) + rx_pkt_offset > skb->len) { mwifiex_dbg(adapter, ERROR, "wrong rx packet: len=%d, rx_pkt_offset=%d, rx_pkt_length=%d\n", skb->len, rx_pkt_offset, rx_pkt_length); diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c index e495f7eaea03..04ff051f5d18 100644 --- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c +++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c @@ -103,6 +103,15 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv, return; } + if (sizeof(*rx_pkt_hdr) + + le16_to_cpu(uap_rx_pd->rx_pkt_offset) > skb->len) { + mwifiex_dbg(adapter, ERROR, + "wrong rx packet offset: len=%d,rx_pkt_offset=%d\n", + skb->len, le16_to_cpu(uap_rx_pd->rx_pkt_offset)); + priv->stats.rx_dropped++; + dev_kfree_skb_any(skb); + } + if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, sizeof(bridge_tunnel_header))) || (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header, @@ -367,6 +376,16 @@ int mwifiex_process_uap_rx_packet(struct mwifiex_private *priv, rx_pkt_type = le16_to_cpu(uap_rx_pd->rx_pkt_type); rx_pkt_hdr = (void *)uap_rx_pd + le16_to_cpu(uap_rx_pd->rx_pkt_offset); + if (le16_to_cpu(uap_rx_pd->rx_pkt_offset) + + sizeof(rx_pkt_hdr->eth803_hdr) > skb->len) { + mwifiex_dbg(adapter, ERROR, + "wrong rx packet for struct ethhdr: len=%d, offset=%d\n", + skb->len, le16_to_cpu(uap_rx_pd->rx_pkt_offset)); + priv->stats.rx_dropped++; + dev_kfree_skb_any(skb); + return 0; + } + ether_addr_copy(ta, rx_pkt_hdr->eth803_hdr.h_source); if ((le16_to_cpu(uap_rx_pd->rx_pkt_offset) + diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c index 94c2d219835d..745b1d925b21 100644 --- a/drivers/net/wireless/marvell/mwifiex/util.c +++ b/drivers/net/wireless/marvell/mwifiex/util.c @@ -393,11 +393,15 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv, } rx_pd = (struct rxpd *)skb->data; + pkt_len = le16_to_cpu(rx_pd->rx_pkt_length); + if (pkt_len < sizeof(struct ieee80211_hdr) + sizeof(pkt_len)) { + mwifiex_dbg(priv->adapter, ERROR, "invalid rx_pkt_length"); + return -1; + } skb_pull(skb, le16_to_cpu(rx_pd->rx_pkt_offset)); skb_pull(skb, sizeof(pkt_len)); - - pkt_len = le16_to_cpu(rx_pd->rx_pkt_length); + pkt_len -= sizeof(pkt_len); ieee_hdr = (void *)skb->data; if (ieee80211_is_mgmt(ieee_hdr->frame_control)) { @@ -410,7 +414,7 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv, skb->data + sizeof(struct ieee80211_hdr), pkt_len - sizeof(struct ieee80211_hdr)); - pkt_len -= ETH_ALEN + sizeof(pkt_len); + pkt_len -= ETH_ALEN; rx_pd->rx_pkt_length = cpu_to_le16(pkt_len); cfg80211_rx_mgmt(&priv->wdev, priv->roc_cfg.chan.center_freq, From c015029dfc891a7aaab47f0c823c1451166b26b6 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Mon, 31 Jul 2023 10:43:07 +0300 Subject: [PATCH 0844/2093] wifi: mwifiex: fix error recovery in PCIE buffer descriptor management [ Upstream commit 288c63d5cb4667a51a04668b3e2bb0ea499bc5f4 ] Add missing 'kfree_skb()' in 'mwifiex_init_rxq_ring()' and never do 'kfree(card->rxbd_ring_vbase)' because this area is DMAed and should be released with 'dma_free_coherent()'. The latter is performed in 'mwifiex_pcie_delete_rxbd_ring()', which is now called to recover from possible errors in 'mwifiex_pcie_create_rxbd_ring()'. Likewise for 'mwifiex_pcie_init_evt_ring()', 'kfree(card->evtbd_ring_vbase)' 'mwifiex_pcie_delete_evtbd_ring()' and 'mwifiex_pcie_create_rxbd_ring()'. Fixes: d930faee141b ("mwifiex: add support for Marvell pcie8766 chipset") Signed-off-by: Dmitry Antipov Acked-by: Brian Norris Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230731074334.56463-1-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/pcie.c | 25 ++++++++++++++------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c index 9a698a16a8f3..6697132ecc97 100644 --- a/drivers/net/wireless/marvell/mwifiex/pcie.c +++ b/drivers/net/wireless/marvell/mwifiex/pcie.c @@ -189,6 +189,8 @@ static int mwifiex_pcie_probe_of(struct device *dev) } static void mwifiex_pcie_work(struct work_struct *work); +static int mwifiex_pcie_delete_rxbd_ring(struct mwifiex_adapter *adapter); +static int mwifiex_pcie_delete_evtbd_ring(struct mwifiex_adapter *adapter); static int mwifiex_map_pci_memory(struct mwifiex_adapter *adapter, struct sk_buff *skb, @@ -792,14 +794,15 @@ static int mwifiex_init_rxq_ring(struct mwifiex_adapter *adapter) if (!skb) { mwifiex_dbg(adapter, ERROR, "Unable to allocate skb for RX ring.\n"); - kfree(card->rxbd_ring_vbase); return -ENOMEM; } if (mwifiex_map_pci_memory(adapter, skb, MWIFIEX_RX_DATA_BUF_SIZE, - DMA_FROM_DEVICE)) - return -1; + DMA_FROM_DEVICE)) { + kfree_skb(skb); + return -ENOMEM; + } buf_pa = MWIFIEX_SKB_DMA_ADDR(skb); @@ -849,7 +852,6 @@ static int mwifiex_pcie_init_evt_ring(struct mwifiex_adapter *adapter) if (!skb) { mwifiex_dbg(adapter, ERROR, "Unable to allocate skb for EVENT buf.\n"); - kfree(card->evtbd_ring_vbase); return -ENOMEM; } skb_put(skb, MAX_EVENT_SIZE); @@ -857,8 +859,7 @@ static int mwifiex_pcie_init_evt_ring(struct mwifiex_adapter *adapter) if (mwifiex_map_pci_memory(adapter, skb, MAX_EVENT_SIZE, DMA_FROM_DEVICE)) { kfree_skb(skb); - kfree(card->evtbd_ring_vbase); - return -1; + return -ENOMEM; } buf_pa = MWIFIEX_SKB_DMA_ADDR(skb); @@ -1058,6 +1059,7 @@ static int mwifiex_pcie_delete_txbd_ring(struct mwifiex_adapter *adapter) */ static int mwifiex_pcie_create_rxbd_ring(struct mwifiex_adapter *adapter) { + int ret; struct pcie_service_card *card = adapter->card; const struct mwifiex_pcie_card_reg *reg = card->pcie.reg; @@ -1096,7 +1098,10 @@ static int mwifiex_pcie_create_rxbd_ring(struct mwifiex_adapter *adapter) (u32)((u64)card->rxbd_ring_pbase >> 32), card->rxbd_ring_size); - return mwifiex_init_rxq_ring(adapter); + ret = mwifiex_init_rxq_ring(adapter); + if (ret) + mwifiex_pcie_delete_rxbd_ring(adapter); + return ret; } /* @@ -1127,6 +1132,7 @@ static int mwifiex_pcie_delete_rxbd_ring(struct mwifiex_adapter *adapter) */ static int mwifiex_pcie_create_evtbd_ring(struct mwifiex_adapter *adapter) { + int ret; struct pcie_service_card *card = adapter->card; const struct mwifiex_pcie_card_reg *reg = card->pcie.reg; @@ -1161,7 +1167,10 @@ static int mwifiex_pcie_create_evtbd_ring(struct mwifiex_adapter *adapter) (u32)((u64)card->evtbd_ring_pbase >> 32), card->evtbd_ring_size); - return mwifiex_pcie_init_evt_ring(adapter); + ret = mwifiex_pcie_init_evt_ring(adapter); + if (ret) + mwifiex_pcie_delete_evtbd_ring(adapter); + return ret; } /* From 90978b2ff422b07724468ad2ff686dd50288b309 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Wed, 2 Aug 2023 08:39:06 +0100 Subject: [PATCH 0845/2093] selftests/bpf: fix static assert compilation issue for test_cls_*.c [ Upstream commit 416c6d01244ecbf0abfdb898fd091b50ef951b48 ] commit bdeeed3498c7 ("libbpf: fix offsetof() and container_of() to work with CO-RE") ...was backported to stable trees such as 5.15. The problem is that with older LLVM/clang (14/15) - which is often used for older kernels - we see compilation failures in BPF selftests now: In file included from progs/test_cls_redirect_subprogs.c:2: progs/test_cls_redirect.c:90:2: error: static assertion expression is not an integral constant expression sizeof(flow_ports_t) != ^~~~~~~~~~~~~~~~~~~~~~~ progs/test_cls_redirect.c:91:3: note: cast that performs the conversions of a reinterpret_cast is not allowed in a constant expression offsetofend(struct bpf_sock_tuple, ipv4.dport) - ^ progs/test_cls_redirect.c:32:3: note: expanded from macro 'offsetofend' (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) ^ tools/testing/selftests/bpf/tools/include/bpf/bpf_helpers.h:86:33: note: expanded from macro 'offsetof' ^ In file included from progs/test_cls_redirect_subprogs.c:2: progs/test_cls_redirect.c:95:2: error: static assertion expression is not an integral constant expression sizeof(flow_ports_t) != ^~~~~~~~~~~~~~~~~~~~~~~ progs/test_cls_redirect.c:96:3: note: cast that performs the conversions of a reinterpret_cast is not allowed in a constant expression offsetofend(struct bpf_sock_tuple, ipv6.dport) - ^ progs/test_cls_redirect.c:32:3: note: expanded from macro 'offsetofend' (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) ^ tools/testing/selftests/bpf/tools/include/bpf/bpf_helpers.h:86:33: note: expanded from macro 'offsetof' ^ 2 errors generated. make: *** [Makefile:594: tools/testing/selftests/bpf/test_cls_redirect_subprogs.bpf.o] Error 1 The problem is the new offsetof() does not play nice with static asserts. Given that the context is a static assert (and CO-RE relocation is not needed at compile time), offsetof() usage can be replaced by restoring the original offsetof() definition as __builtin_offsetof(). Fixes: bdeeed3498c7 ("libbpf: fix offsetof() and container_of() to work with CO-RE") Reported-by: Colm Harrington Signed-off-by: Alan Maguire Tested-by: Yipeng Zou Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230802073906.3197480-1-alan.maguire@oracle.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/progs/test_cls_redirect.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h index 76eab0aacba0..233b089d1fba 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -12,6 +12,15 @@ #include #include +/* offsetof() is used in static asserts, and the libbpf-redefined CO-RE + * friendly version breaks compilation for older clang versions <= 15 + * when invoked in a static assert. Restore original here. + */ +#ifdef offsetof +#undef offsetof +#define offsetof(type, member) __builtin_offsetof(type, member) +#endif + struct gre_base_hdr { uint16_t flags; uint16_t protocol; From 6c7182b9c87e0bc4b1b5c207ab31080e90ff866e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 16 Jun 2023 02:16:21 +0200 Subject: [PATCH 0846/2093] kbuild: rust_is_available: remove -v option [ Upstream commit d824d2f98565e7c4cb1b862c230198fbe1a968be ] The -v option is passed when this script is invoked from Makefile, but not when invoked from Kconfig. As you can see in scripts/Kconfig.include, the 'success' macro suppresses stdout and stderr anyway, so this script does not need to be quiet. Signed-off-by: Masahiro Yamada Reviewed-by: Miguel Ojeda Tested-by: Miguel Ojeda Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230109061436.3146442-1-masahiroy@kernel.org [ Reworded prefix to match the others in the patch series. ] Reviewed-by: Martin Rodriguez Reboredo Link: https://lore.kernel.org/r/20230616001631.463536-2-ojeda@kernel.org Signed-off-by: Miguel Ojeda Stable-dep-of: dee3a6b819c9 ("kbuild: rust_is_available: fix version check when CC has multiple arguments") Signed-off-by: Sasha Levin --- Makefile | 4 +- scripts/rust_is_available.sh | 96 +++++++++++++++--------------------- 2 files changed, 42 insertions(+), 58 deletions(-) diff --git a/Makefile b/Makefile index 82aaa3ae7395..c627e0bdb19f 100644 --- a/Makefile +++ b/Makefile @@ -1291,7 +1291,7 @@ prepare0: archprepare # All the preparing.. prepare: prepare0 ifdef CONFIG_RUST - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh -v + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh $(Q)$(MAKE) $(build)=rust endif @@ -1817,7 +1817,7 @@ $(DOC_TARGETS): # "Is Rust available?" target PHONY += rustavailable rustavailable: - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh -v && echo "Rust is available!" + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!" # Documentation target # diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index aebbf1913970..f43a010eaf30 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -2,8 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 # # Tests whether a suitable Rust toolchain is available. -# -# Pass `-v` for human output and more checks (as warnings). set -e @@ -23,21 +21,17 @@ get_canonical_version() # Check that the Rust compiler exists. if ! command -v "$RUSTC" >/dev/null; then - if [ "$1" = -v ]; then - echo >&2 "***" - echo >&2 "*** Rust compiler '$RUSTC' could not be found." - echo >&2 "***" - fi + echo >&2 "***" + echo >&2 "*** Rust compiler '$RUSTC' could not be found." + echo >&2 "***" exit 1 fi # Check that the Rust bindings generator exists. if ! command -v "$BINDGEN" >/dev/null; then - if [ "$1" = -v ]; then - echo >&2 "***" - echo >&2 "*** Rust bindings generator '$BINDGEN' could not be found." - echo >&2 "***" - fi + echo >&2 "***" + echo >&2 "*** Rust bindings generator '$BINDGEN' could not be found." + echo >&2 "***" exit 1 fi @@ -53,16 +47,14 @@ rust_compiler_min_version=$($min_tool_version rustc) rust_compiler_cversion=$(get_canonical_version $rust_compiler_version) rust_compiler_min_cversion=$(get_canonical_version $rust_compiler_min_version) if [ "$rust_compiler_cversion" -lt "$rust_compiler_min_cversion" ]; then - if [ "$1" = -v ]; then - echo >&2 "***" - echo >&2 "*** Rust compiler '$RUSTC' is too old." - echo >&2 "*** Your version: $rust_compiler_version" - echo >&2 "*** Minimum version: $rust_compiler_min_version" - echo >&2 "***" - fi + echo >&2 "***" + echo >&2 "*** Rust compiler '$RUSTC' is too old." + echo >&2 "*** Your version: $rust_compiler_version" + echo >&2 "*** Minimum version: $rust_compiler_min_version" + echo >&2 "***" exit 1 fi -if [ "$1" = -v ] && [ "$rust_compiler_cversion" -gt "$rust_compiler_min_cversion" ]; then +if [ "$rust_compiler_cversion" -gt "$rust_compiler_min_cversion" ]; then echo >&2 "***" echo >&2 "*** Rust compiler '$RUSTC' is too new. This may or may not work." echo >&2 "*** Your version: $rust_compiler_version" @@ -82,16 +74,14 @@ rust_bindings_generator_min_version=$($min_tool_version bindgen) rust_bindings_generator_cversion=$(get_canonical_version $rust_bindings_generator_version) rust_bindings_generator_min_cversion=$(get_canonical_version $rust_bindings_generator_min_version) if [ "$rust_bindings_generator_cversion" -lt "$rust_bindings_generator_min_cversion" ]; then - if [ "$1" = -v ]; then - echo >&2 "***" - echo >&2 "*** Rust bindings generator '$BINDGEN' is too old." - echo >&2 "*** Your version: $rust_bindings_generator_version" - echo >&2 "*** Minimum version: $rust_bindings_generator_min_version" - echo >&2 "***" - fi + echo >&2 "***" + echo >&2 "*** Rust bindings generator '$BINDGEN' is too old." + echo >&2 "*** Your version: $rust_bindings_generator_version" + echo >&2 "*** Minimum version: $rust_bindings_generator_min_version" + echo >&2 "***" exit 1 fi -if [ "$1" = -v ] && [ "$rust_bindings_generator_cversion" -gt "$rust_bindings_generator_min_cversion" ]; then +if [ "$rust_bindings_generator_cversion" -gt "$rust_bindings_generator_min_cversion" ]; then echo >&2 "***" echo >&2 "*** Rust bindings generator '$BINDGEN' is too new. This may or may not work." echo >&2 "*** Your version: $rust_bindings_generator_version" @@ -110,13 +100,11 @@ bindgen_libclang_min_version=$($min_tool_version llvm) bindgen_libclang_cversion=$(get_canonical_version $bindgen_libclang_version) bindgen_libclang_min_cversion=$(get_canonical_version $bindgen_libclang_min_version) if [ "$bindgen_libclang_cversion" -lt "$bindgen_libclang_min_cversion" ]; then - if [ "$1" = -v ]; then - echo >&2 "***" - echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN') is too old." - echo >&2 "*** Your version: $bindgen_libclang_version" - echo >&2 "*** Minimum version: $bindgen_libclang_min_version" - echo >&2 "***" - fi + echo >&2 "***" + echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN') is too old." + echo >&2 "*** Your version: $bindgen_libclang_version" + echo >&2 "*** Minimum version: $bindgen_libclang_min_version" + echo >&2 "***" exit 1 fi @@ -125,21 +113,19 @@ fi # # In the future, we might be able to perform a full version check, see # https://github.com/rust-lang/rust-bindgen/issues/2138. -if [ "$1" = -v ]; then - cc_name=$($(dirname $0)/cc-version.sh "$CC" | cut -f1 -d' ') - if [ "$cc_name" = Clang ]; then - clang_version=$( \ - LC_ALL=C "$CC" --version 2>/dev/null \ - | sed -nE '1s:.*version ([0-9]+\.[0-9]+\.[0-9]+).*:\1:p' - ) - if [ "$clang_version" != "$bindgen_libclang_version" ]; then - echo >&2 "***" - echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN')" - echo >&2 "*** version does not match Clang's. This may be a problem." - echo >&2 "*** libclang version: $bindgen_libclang_version" - echo >&2 "*** Clang version: $clang_version" - echo >&2 "***" - fi +cc_name=$($(dirname $0)/cc-version.sh "$CC" | cut -f1 -d' ') +if [ "$cc_name" = Clang ]; then + clang_version=$( \ + LC_ALL=C "$CC" --version 2>/dev/null \ + | sed -nE '1s:.*version ([0-9]+\.[0-9]+\.[0-9]+).*:\1:p' + ) + if [ "$clang_version" != "$bindgen_libclang_version" ]; then + echo >&2 "***" + echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN')" + echo >&2 "*** version does not match Clang's. This may be a problem." + echo >&2 "*** libclang version: $bindgen_libclang_version" + echo >&2 "*** Clang version: $clang_version" + echo >&2 "***" fi fi @@ -150,11 +136,9 @@ rustc_sysroot=$("$RUSTC" $KRUSTFLAGS --print sysroot) rustc_src=${RUST_LIB_SRC:-"$rustc_sysroot/lib/rustlib/src/rust/library"} rustc_src_core="$rustc_src/core/src/lib.rs" if [ ! -e "$rustc_src_core" ]; then - if [ "$1" = -v ]; then - echo >&2 "***" - echo >&2 "*** Source code for the 'core' standard library could not be found" - echo >&2 "*** at '$rustc_src_core'." - echo >&2 "***" - fi + echo >&2 "***" + echo >&2 "*** Source code for the 'core' standard library could not be found" + echo >&2 "*** at '$rustc_src_core'." + echo >&2 "***" exit 1 fi From bb15fb4e497ec19d4234474f39dc9ad27f06e2fd Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Fri, 16 Jun 2023 02:16:22 +0200 Subject: [PATCH 0847/2093] kbuild: rust_is_available: fix version check when CC has multiple arguments [ Upstream commit dee3a6b819c96fc8b1907577f585fd66f5c0fefe ] rust_is_available.sh uses cc-version.sh to identify which C compiler is in use, as scripts/Kconfig.include does. cc-version.sh isn't designed to be able to handle multiple arguments in one variable, i.e. "ccache clang". Its invocation in rust_is_available.sh quotes "$CC", which makes $1 == "ccache clang" instead of the intended $1 == ccache & $2 == clang. cc-version.sh could also be changed to handle having "ccache clang" as one argument, but it only has the one consumer upstream, making it simpler to fix the caller here. Signed-off-by: Russell Currey Fixes: 78521f3399ab ("scripts: add `rust_is_available.sh`") Link: https://github.com/Rust-for-Linux/linux/pull/873 [ Reworded title prefix and reflow line to 75 columns. ] Reviewed-by: Martin Rodriguez Reboredo Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230616001631.463536-3-ojeda@kernel.org Signed-off-by: Miguel Ojeda Signed-off-by: Sasha Levin --- scripts/rust_is_available.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index f43a010eaf30..0c9be438e4cd 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -113,10 +113,10 @@ fi # # In the future, we might be able to perform a full version check, see # https://github.com/rust-lang/rust-bindgen/issues/2138. -cc_name=$($(dirname $0)/cc-version.sh "$CC" | cut -f1 -d' ') +cc_name=$($(dirname $0)/cc-version.sh $CC | cut -f1 -d' ') if [ "$cc_name" = Clang ]; then clang_version=$( \ - LC_ALL=C "$CC" --version 2>/dev/null \ + LC_ALL=C $CC --version 2>/dev/null \ | sed -nE '1s:.*version ([0-9]+\.[0-9]+\.[0-9]+).*:\1:p' ) if [ "$clang_version" != "$bindgen_libclang_version" ]; then From 4f8c55ae5d58337b0eb5f8159aeebd70161b8ff3 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 16 Jun 2023 02:16:25 +0200 Subject: [PATCH 0848/2093] kbuild: rust_is_available: add check for `bindgen` invocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 52cae7f28ed6c3992489f16bb355f5b623f0912e ] `scripts/rust_is_available.sh` calls `bindgen` with a special header in order to check whether the `libclang` version in use is suitable. However, the invocation itself may fail if, for instance, `bindgen` cannot locate `libclang`. This is fine for Kconfig (since the script will still fail and therefore disable Rust as it should), but it is pretty confusing for users of the `rustavailable` target given the error will be unrelated: ./scripts/rust_is_available.sh: 21: arithmetic expression: expecting primary: "100000 * + 100 * + " make: *** [Makefile:1816: rustavailable] Error 2 Instead, run the `bindgen` invocation independently in a previous step, saving its output and return code. If it fails, then show the user a proper error message. Otherwise, continue as usual with the saved output. Since the previous patch we show a reference to the docs, and the docs now explain how `bindgen` looks for `libclang`, thus the error message can leverage the documentation, avoiding duplication here (and making users aware of the setup guide in the documentation). Reported-by: Nick Desaulniers Link: https://lore.kernel.org/rust-for-linux/CAKwvOdm5JT4wbdQQYuW+RT07rCi6whGBM2iUAyg8A1CmLXG6Nw@mail.gmail.com/ Reported-by: François Valenduc Closes: https://github.com/Rust-for-Linux/linux/issues/934 Reported-by: Alexandru Radovici Closes: https://github.com/Rust-for-Linux/linux/pull/921 Reported-by: Matthew Leach Closes: https://lore.kernel.org/rust-for-linux/20230507084116.1099067-1-dev@mattleach.net/ Fixes: 78521f3399ab ("scripts: add `rust_is_available.sh`") Reviewed-by: Martin Rodriguez Reboredo Reviewed-by: Masahiro Yamada Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230616001631.463536-6-ojeda@kernel.org Signed-off-by: Miguel Ojeda Signed-off-by: Sasha Levin --- scripts/rust_is_available.sh | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index 0c9be438e4cd..c965895d80b9 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -90,8 +90,28 @@ if [ "$rust_bindings_generator_cversion" -gt "$rust_bindings_generator_min_cvers fi # Check that the `libclang` used by the Rust bindings generator is suitable. +# +# In order to do that, first invoke `bindgen` to get the `libclang` version +# found by `bindgen`. This step may already fail if, for instance, `libclang` +# is not found, thus inform the user in such a case. +bindgen_libclang_output=$( \ + LC_ALL=C "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_libclang.h 2>&1 >/dev/null +) || bindgen_libclang_code=$? +if [ -n "$bindgen_libclang_code" ]; then + echo >&2 "***" + echo >&2 "*** Running '$BINDGEN' to check the libclang version (used by the Rust" + echo >&2 "*** bindings generator) failed with code $bindgen_libclang_code. This may be caused by" + echo >&2 "*** a failure to locate libclang. See output and docs below for details:" + echo >&2 "***" + echo >&2 "$bindgen_libclang_output" + echo >&2 "***" + exit 1 +fi + +# `bindgen` returned successfully, thus use the output to check that the version +# of the `libclang` found by the Rust bindings generator is suitable. bindgen_libclang_version=$( \ - LC_ALL=C "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_libclang.h 2>&1 >/dev/null \ + echo "$bindgen_libclang_output" \ | grep -F 'clang version ' \ | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \ | head -n 1 \ From 6fc09c8d765ee8f0ca37e29fa96498e77307a5df Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 16 Jun 2023 02:16:27 +0200 Subject: [PATCH 0849/2093] kbuild: rust_is_available: fix confusion when a version appears in the path [ Upstream commit 9eb7e20e0c5cd069457845f965b3e8a7d736ecb7 ] `bindgen`'s output for `libclang`'s version check contains paths, which in turn may contain strings that look like version numbers [1][2]: .../6.1.0-dev/.../rust_is_available_bindgen_libclang.h:2:9: warning: clang version 11.1.0 [-W#pragma-messages], err: false which the script will pick up as the version instead of the latter. It is also the case that versions may appear after the actual version (e.g. distribution's version text), which was the reason behind `head` [3]: .../rust-is-available-bindgen-libclang.h:2:9: warning: clang version 13.0.0 (Fedora 13.0.0-3.fc35) [-W#pragma-messages], err: false Thus instead ask for a match after the `clang version` string. Reported-by: Jordan Isaacs Closes: https://github.com/Rust-for-Linux/linux/issues/942 [1] Reported-by: "Ethan D. Twardy" Closes: https://lore.kernel.org/rust-for-linux/20230528131802.6390-2-ethan.twardy@gmail.com/ [2] Reported-by: Tiago Lam Closes: https://github.com/Rust-for-Linux/linux/pull/789 [3] Fixes: 78521f3399ab ("scripts: add `rust_is_available.sh`") Reviewed-by: Martin Rodriguez Reboredo Reviewed-by: Ethan Twardy Tested-by: Ethan Twardy Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230616001631.463536-8-ojeda@kernel.org Signed-off-by: Miguel Ojeda Signed-off-by: Sasha Levin --- scripts/rust_is_available.sh | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index c965895d80b9..7a925d2b20fc 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -112,9 +112,7 @@ fi # of the `libclang` found by the Rust bindings generator is suitable. bindgen_libclang_version=$( \ echo "$bindgen_libclang_output" \ - | grep -F 'clang version ' \ - | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \ - | head -n 1 \ + | sed -nE 's:.*clang version ([0-9]+\.[0-9]+\.[0-9]+).*:\1:p' ) bindgen_libclang_min_version=$($min_tool_version llvm) bindgen_libclang_cversion=$(get_canonical_version $bindgen_libclang_version) From 501f77cfce8a60d583ce20a0c3f3a3eee3e5521a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 31 Jul 2023 18:54:54 +0200 Subject: [PATCH 0850/2093] crypto: stm32 - Properly handle pm_runtime_get failing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit aec48805163338f8413118796c1dd035661b9140 ] If pm_runtime_get() (disguised as pm_runtime_resume_and_get()) fails, this means the clk wasn't prepared and enabled. Returning early in this case however is wrong as then the following resource frees are skipped and this is never catched up. So do all the cleanups but clk_disable_unprepare(). Also don't emit a warning, as stm32_hash_runtime_resume() already emitted one. Note that the return value of stm32_hash_remove() is mostly ignored by the device core. The only effect of returning zero instead of an error value is to suppress another warning in platform_remove(). So return 0 even if pm_runtime_resume_and_get() failed. Fixes: 8b4d566de6a5 ("crypto: stm32/hash - Add power management support") Signed-off-by: Uwe Kleine-König Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/stm32/stm32-hash.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c index d33006d43f76..e3f765434d64 100644 --- a/drivers/crypto/stm32/stm32-hash.c +++ b/drivers/crypto/stm32/stm32-hash.c @@ -1566,9 +1566,7 @@ static int stm32_hash_remove(struct platform_device *pdev) if (!hdev) return -ENODEV; - ret = pm_runtime_resume_and_get(hdev->dev); - if (ret < 0) - return ret; + ret = pm_runtime_get_sync(hdev->dev); stm32_hash_unregister_algs(hdev); @@ -1584,7 +1582,8 @@ static int stm32_hash_remove(struct platform_device *pdev) pm_runtime_disable(hdev->dev); pm_runtime_put_noidle(hdev->dev); - clk_disable_unprepare(hdev->clk); + if (ret >= 0) + clk_disable_unprepare(hdev->clk); return 0; } From c4cb61c5f976183c07d16b0071f0c60bc212ef1f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 3 Aug 2023 17:59:28 +0800 Subject: [PATCH 0851/2093] crypto: api - Use work queue in crypto_destroy_instance [ Upstream commit 9ae4577bc077a7e32c3c7d442c95bc76865c0f17 ] The function crypto_drop_spawn expects to be called in process context. However, when an instance is unregistered while it still has active users, the last user may cause the instance to be freed in atomic context. Fix this by delaying the freeing to a work queue. Fixes: 6bfd48096ff8 ("[CRYPTO] api: Added spawns") Reported-by: Florent Revest Reported-by: syzbot+d769eed29cc42d75e2a3@syzkaller.appspotmail.com Reported-by: syzbot+610ec0671f51e838436e@syzkaller.appspotmail.com Signed-off-by: Herbert Xu Tested-by: Florent Revest Acked-by: Florent Revest Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/algapi.c | 16 ++++++++++++++-- include/crypto/algapi.h | 3 +++ 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/crypto/algapi.c b/crypto/algapi.c index 8c3a869cc43a..5dc9ccdd5a51 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "internal.h" @@ -74,15 +75,26 @@ static void crypto_free_instance(struct crypto_instance *inst) inst->alg.cra_type->free(inst); } -static void crypto_destroy_instance(struct crypto_alg *alg) +static void crypto_destroy_instance_workfn(struct work_struct *w) { - struct crypto_instance *inst = (void *)alg; + struct crypto_instance *inst = container_of(w, struct crypto_instance, + free_work); struct crypto_template *tmpl = inst->tmpl; crypto_free_instance(inst); crypto_tmpl_put(tmpl); } +static void crypto_destroy_instance(struct crypto_alg *alg) +{ + struct crypto_instance *inst = container_of(alg, + struct crypto_instance, + alg); + + INIT_WORK(&inst->free_work, crypto_destroy_instance_workfn); + schedule_work(&inst->free_work); +} + /* * This function adds a spawn to the list secondary_spawns which * will be used at the end of crypto_remove_spawns to unregister diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 224b86064708..939a3196bf00 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -12,6 +12,7 @@ #include #include #include +#include #include @@ -60,6 +61,8 @@ struct crypto_instance { struct crypto_spawn *spawns; }; + struct work_struct free_work; + void *__ctx[] CRYPTO_MINALIGN_ATTR; }; From 9246d9310cd6d8e94219ac9f6c5ace8bb52bc76c Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Wed, 26 Jul 2023 21:30:00 +0800 Subject: [PATCH 0852/2093] Bluetooth: nokia: fix value check in nokia_bluetooth_serdev_probe() [ Upstream commit e8b5aed31355072faac8092ead4938ddec3111fd ] in nokia_bluetooth_serdev_probe(), check the return value of clk_prepare_enable() and return the error code if clk_prepare_enable() returns an unexpected value. Fixes: 7bb318680e86 ("Bluetooth: add nokia driver") Signed-off-by: Yuanjun Gong Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_nokia.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index 05f7f6de6863..97da0b2bfd17 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -734,7 +734,11 @@ static int nokia_bluetooth_serdev_probe(struct serdev_device *serdev) return err; } - clk_prepare_enable(sysclk); + err = clk_prepare_enable(sysclk); + if (err) { + dev_err(dev, "could not enable sysclk: %d", err); + return err; + } btdev->sysclk_speed = clk_get_rate(sysclk); clk_disable_unprepare(sysclk); From 94617b736c25091b60e514e2e7aeafcbbee6b700 Mon Sep 17 00:00:00 2001 From: Min Li Date: Mon, 7 Aug 2023 19:07:41 +0800 Subject: [PATCH 0853/2093] Bluetooth: Fix potential use-after-free when clear keys [ Upstream commit 3673952cf0c6cf81b06c66a0b788abeeb02ff3ae ] Similar to commit c5d2b6fa26b5 ("Bluetooth: Fix use-after-free in hci_remove_ltk/hci_remove_irk"). We can not access k after kfree_rcu() call. Fixes: d7d41682efc2 ("Bluetooth: Fix Suspicious RCU usage warnings") Signed-off-by: Min Li Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/hci_core.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d034bf2a999e..26884447d72b 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1074,9 +1074,9 @@ void hci_uuids_clear(struct hci_dev *hdev) void hci_link_keys_clear(struct hci_dev *hdev) { - struct link_key *key; + struct link_key *key, *tmp; - list_for_each_entry(key, &hdev->link_keys, list) { + list_for_each_entry_safe(key, tmp, &hdev->link_keys, list) { list_del_rcu(&key->list); kfree_rcu(key, rcu); } @@ -1084,9 +1084,9 @@ void hci_link_keys_clear(struct hci_dev *hdev) void hci_smp_ltks_clear(struct hci_dev *hdev) { - struct smp_ltk *k; + struct smp_ltk *k, *tmp; - list_for_each_entry(k, &hdev->long_term_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } @@ -1094,9 +1094,9 @@ void hci_smp_ltks_clear(struct hci_dev *hdev) void hci_smp_irks_clear(struct hci_dev *hdev) { - struct smp_irk *k; + struct smp_irk *k, *tmp; - list_for_each_entry(k, &hdev->identity_resolving_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } @@ -1104,9 +1104,9 @@ void hci_smp_irks_clear(struct hci_dev *hdev) void hci_blocked_keys_clear(struct hci_dev *hdev) { - struct blocked_key *b; + struct blocked_key *b, *tmp; - list_for_each_entry(b, &hdev->blocked_keys, list) { + list_for_each_entry_safe(b, tmp, &hdev->blocked_keys, list) { list_del_rcu(&b->list); kfree_rcu(b, rcu); } From bd39b55240475409b0fa7b87e7a850c640b70c3a Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 30 Jun 2023 15:33:15 -0700 Subject: [PATCH 0854/2093] Bluetooth: hci_sync: Don't double print name in add/remove adv_monitor [ Upstream commit 6f55eea116ba3646fb5fbb31de703f8cf79d8214 ] The hci_add_adv_monitor() hci_remove_adv_monitor() functions call bt_dev_dbg() to print some debug statements. The bt_dev_dbg() macro automatically adds in the device's name. That means that we shouldn't include the name in the bt_dev_dbg() calls. Suggested-by: Luiz Augusto von Dentz Signed-off-by: Douglas Anderson Signed-off-by: Luiz Augusto von Dentz Stable-dep-of: a2bcd2b63271 ("Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_add_adv_monitor()") Signed-off-by: Sasha Levin --- net/bluetooth/hci_core.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 26884447d72b..561e8a77f64c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1949,14 +1949,14 @@ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: - bt_dev_dbg(hdev, "%s add monitor %d status %d", hdev->name, + bt_dev_dbg(hdev, "add monitor %d status %d", monitor->handle, status); /* Message was not forwarded to controller - not an error */ break; case HCI_ADV_MONITOR_EXT_MSFT: status = msft_add_monitor_pattern(hdev, monitor); - bt_dev_dbg(hdev, "%s add monitor %d msft status %d", hdev->name, + bt_dev_dbg(hdev, "add monitor %d msft status %d", monitor->handle, status); break; } @@ -1976,15 +1976,15 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ - bt_dev_dbg(hdev, "%s remove monitor %d status %d", hdev->name, + bt_dev_dbg(hdev, "remove monitor %d status %d", monitor->handle, status); goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); - bt_dev_dbg(hdev, "%s remove monitor %d msft status %d", - hdev->name, handle, status); + bt_dev_dbg(hdev, "remove monitor %d msft status %d", + handle, status); break; } From 81d8e9f59df63b8358751c1ffed9f1cf5c796909 Mon Sep 17 00:00:00 2001 From: Manish Mandlik Date: Fri, 4 Aug 2023 11:14:45 -0700 Subject: [PATCH 0855/2093] Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_add_adv_monitor() [ Upstream commit a2bcd2b63271a93a695fabbfbf459c603d956d48 ] KSAN reports use-after-free in hci_add_adv_monitor(). While adding an adv monitor, hci_add_adv_monitor() calls -> msft_add_monitor_pattern() calls -> msft_add_monitor_sync() calls -> msft_le_monitor_advertisement_cb() calls in an error case -> hci_free_adv_monitor() which frees the *moniter. This is referenced by bt_dev_dbg() in hci_add_adv_monitor(). Fix the bt_dev_dbg() by using handle instead of monitor->handle. Fixes: b747a83690c8 ("Bluetooth: hci_sync: Refactor add Adv Monitor") Signed-off-by: Manish Mandlik Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/hci_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 561e8a77f64c..146553c0054f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1957,7 +1957,7 @@ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) case HCI_ADV_MONITOR_EXT_MSFT: status = msft_add_monitor_pattern(hdev, monitor); bt_dev_dbg(hdev, "add monitor %d msft status %d", - monitor->handle, status); + handle, status); break; } From d6702008fc9c151ba867d7dc13d99ba606cd0487 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 11 Aug 2023 10:55:29 +0800 Subject: [PATCH 0856/2093] net: tcp: fix unexcepted socket die when snd_wnd is 0 [ Upstream commit e89688e3e97868451a5d05b38a9d2633d6785cd4 ] In tcp_retransmit_timer(), a window shrunk connection will be regarded as timeout if 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX'. This is not right all the time. The retransmits will become zero-window probes in tcp_retransmit_timer() if the 'snd_wnd==0'. Therefore, the icsk->icsk_rto will come up to TCP_RTO_MAX sooner or later. However, the timer can be delayed and be triggered after 122877ms, not TCP_RTO_MAX, as I tested. Therefore, 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX' is always true once the RTO come up to TCP_RTO_MAX, and the socket will die. Fix this by replacing the 'tcp_jiffies32' with '(u32)icsk->icsk_timeout', which is exact the timestamp of the timeout. However, "tp->rcv_tstamp" can restart from idle, then tp->rcv_tstamp could already be a long time (minutes or hours) in the past even on the first RTO. So we double check the timeout with the duration of the retransmission. Meanwhile, making "2 * TCP_RTO_MAX" as the timeout to avoid the socket dying too soon. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/netdev/CADxym3YyMiO+zMD4zj03YPM3FBi-1LHi6gSD2XT8pyAMM096pg@mail.gmail.com/ Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/tcp_timer.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index cf354c29ec12..44b49f7d1a9e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -441,6 +441,22 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) req->timeout << req->num_timeout, TCP_RTO_MAX); } +static bool tcp_rtx_probe0_timed_out(const struct sock *sk, + const struct sk_buff *skb) +{ + const struct tcp_sock *tp = tcp_sk(sk); + const int timeout = TCP_RTO_MAX * 2; + u32 rcv_delta, rtx_delta; + + rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + if (rcv_delta <= timeout) + return false; + + rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - + (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); + + return rtx_delta > timeout; +} /** * tcp_retransmit_timer() - The TCP retransmit timeout handler @@ -506,7 +522,7 @@ void tcp_retransmit_timer(struct sock *sk) tp->snd_una, tp->snd_nxt); } #endif - if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_rtx_probe0_timed_out(sk, skb)) { tcp_write_err(sk); goto out; } From eafa3465c8d94273ab0beb1247472496477755bc Mon Sep 17 00:00:00 2001 From: Yipeng Zou Date: Mon, 14 Aug 2023 11:14:34 +0800 Subject: [PATCH 0857/2093] selftests/bpf: Fix repeat option when kfunc_call verification fails [ Upstream commit 811915db674f8daf19bb4fcb67da9017235ce26d ] There is no way where topts.repeat can be set to 1 when tc_test fails. Fix the typo where the break statement slipped by one line. Fixes: fb66223a244f ("selftests/bpf: add test for accessing ctx from syscall program type") Signed-off-by: Yipeng Zou Signed-off-by: Daniel Borkmann Reviewed-by: Li Zetao Link: https://lore.kernel.org/bpf/20230814031434.3077944-1-zouyipeng@huawei.com Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/prog_tests/kfunc_call.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 5af1ee8f0e6e..36071f3f15ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -171,8 +171,8 @@ static void verify_fail(struct kfunc_test_params *param) case tc_test: topts.data_in = &pkt_v4; topts.data_size_in = sizeof(pkt_v4); - break; topts.repeat = 1; + break; } skel = kfunc_call_fail__open_opts(&opts); From 8d61adfb59181de5a5eaaf264f501aa2f66b7f42 Mon Sep 17 00:00:00 2001 From: Yipeng Zou Date: Mon, 14 Aug 2023 11:07:27 +0800 Subject: [PATCH 0858/2093] selftests/bpf: Clean up fmod_ret in bench_rename test script MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 83a89c4b6ae93481d3f618aba6a29d89208d26ed ] Running the bench_rename test script, the following error occurs: # ./benchs/run_bench_rename.sh base : 0.819 ± 0.012M/s kprobe : 0.538 ± 0.009M/s kretprobe : 0.503 ± 0.004M/s rawtp : 0.779 ± 0.020M/s fentry : 0.726 ± 0.007M/s fexit : 0.691 ± 0.007M/s benchmark 'rename-fmodret' not found The bench_rename_fmodret has been removed in commit b000def2e052 ("selftests: Remove fmod_ret from test_overhead"), thus remove it from the runners in the test script. Fixes: b000def2e052 ("selftests: Remove fmod_ret from test_overhead") Signed-off-by: Yipeng Zou Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230814030727.3010390-1-zouyipeng@huawei.com Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/benchs/run_bench_rename.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh index 16f774b1cdbe..7b281dbe4165 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh @@ -2,7 +2,7 @@ set -eufo pipefail -for i in base kprobe kretprobe rawtp fentry fexit fmodret +for i in base kprobe kretprobe rawtp fentry fexit do summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-) printf "%-10s: %s\n" $i "$summary" From 0f50641222f5f4f5a5dfd90e0798fa72286e057d Mon Sep 17 00:00:00 2001 From: Abel Wu Date: Mon, 14 Aug 2023 15:09:11 +0800 Subject: [PATCH 0859/2093] net-memcg: Fix scope of sockmem pressure indicators [ Upstream commit ac8a52962164a50e693fa021d3564d7745b83a7f ] Now there are two indicators of socket memory pressure sit inside struct mem_cgroup, socket_pressure and tcpmem_pressure, indicating memory reclaim pressure in memcg->memory and ->tcpmem respectively. When in legacy mode (cgroupv1), the socket memory is charged into ->tcpmem which is independent of ->memory, so socket_pressure has nothing to do with socket's pressure at all. Things could be worse by taking socket_pressure into consideration in legacy mode, as a pressure in ->memory can lead to premature reclamation/throttling in socket. While for the default mode (cgroupv2), the socket memory is charged into ->memory, and ->tcpmem/->tcpmem_pressure are simply not used. So {socket,tcpmem}_pressure are only used in default/legacy mode respectively for indicating socket memory pressure. This patch fixes the pieces of code that make mixed use of both. Fixes: 8e8ae645249b ("mm: memcontrol: hook up vmpressure to socket pressure") Signed-off-by: Abel Wu Acked-by: Shakeel Butt Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/memcontrol.h | 9 +++++++-- mm/vmpressure.c | 8 ++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e03976302956..099521835cd1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -283,6 +283,11 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; + /* + * Hint of reclaim pressure for socket memroy management. Note + * that this indicator should NOT be used in legacy cgroup mode + * where socket memory is accounted/charged separately. + */ unsigned long socket_pressure; /* Legacy tcp memory accounting */ @@ -1704,8 +1709,8 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) - return true; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return !!memcg->tcpmem_pressure; do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index b52644771cc4..22c6689d9302 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -244,6 +244,14 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (mem_cgroup_disabled()) return; + /* + * The in-kernel users only care about the reclaim efficiency + * for this @memcg rather than the whole subtree, and there + * isn't and won't be any in-kernel user in a legacy cgroup. + */ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) + return; + vmpr = memcg_to_vmpressure(memcg); /* From 841d2fffd09f56f72136e1bd371f42b4cc92dbb5 Mon Sep 17 00:00:00 2001 From: Przemek Kitszel Date: Tue, 8 Aug 2023 17:54:15 -0400 Subject: [PATCH 0860/2093] ice: ice_aq_check_events: fix off-by-one check when filling buffer [ Upstream commit e1e8a142c43336e3d25bfa1cb3a4ae7d00875c48 ] Allow task's event buffer to be filled also in the case that it's size is exactly the size of the message. Fixes: d69ea414c9b4 ("ice: implement device flash update via devlink") Reviewed-by: Jacob Keller Signed-off-by: Przemek Kitszel Reviewed-by: Simon Horman Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_main.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 7a00d297be3a..3f98781e74b2 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1356,6 +1356,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, struct ice_rq_event_info *event) { + struct ice_rq_event_info *task_ev; struct ice_aq_task *task; bool found = false; @@ -1364,15 +1365,15 @@ static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, if (task->state || task->opcode != opcode) continue; - memcpy(&task->event->desc, &event->desc, sizeof(event->desc)); - task->event->msg_len = event->msg_len; + task_ev = task->event; + memcpy(&task_ev->desc, &event->desc, sizeof(event->desc)); + task_ev->msg_len = event->msg_len; /* Only copy the data buffer if a destination was set */ - if (task->event->msg_buf && - task->event->buf_len > event->buf_len) { - memcpy(task->event->msg_buf, event->msg_buf, + if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) { + memcpy(task_ev->msg_buf, event->msg_buf, event->buf_len); - task->event->buf_len = event->buf_len; + task_ev->buf_len = event->buf_len; } task->state = ICE_AQ_TASK_COMPLETE; From 92651ce45ba1d97d3a52d5cf39f7646f7a395bf2 Mon Sep 17 00:00:00 2001 From: Gaurav Jain Date: Tue, 8 Aug 2023 12:55:25 +0200 Subject: [PATCH 0861/2093] crypto: caam - fix unchecked return value error [ Upstream commit e30685204711a6be40dec2622606950ccd37dafe ] error: Unchecked return value (CHECKED_RETURN) check_return: Calling sg_miter_next without checking return value fix: added check if(!sg_miter_next) Fixes: 8a2a0dd35f2e ("crypto: caam - strip input zeros from RSA input buffer") Signed-off-by: Gaurav Jain Signed-off-by: Meenakshi Aggarwal Reviewed-by: Gaurav Jain Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/caam/caampkc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c index 886727576710..51b48b57266a 100644 --- a/drivers/crypto/caam/caampkc.c +++ b/drivers/crypto/caam/caampkc.c @@ -223,7 +223,9 @@ static int caam_rsa_count_leading_zeros(struct scatterlist *sgl, if (len && *buff) break; - sg_miter_next(&miter); + if (!sg_miter_next(&miter)) + break; + buff = miter.addr; len = miter.length; From 0159a21b9d8e0519f94f1e6f096d0388ff893602 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 10 Aug 2023 12:22:08 -0700 Subject: [PATCH 0862/2093] hwrng: iproc-rng200 - Implement suspend and resume calls [ Upstream commit 8e03dd62e5be811efbf0cbeba47e79e793519105 ] Chips such as BCM7278 support system wide suspend/resume which will cause the HWRNG block to lose its state and reset to its power on reset register values. We need to cleanup and re-initialize the HWRNG for it to be functional coming out of a system suspend cycle. Fixes: c3577f6100ca ("hwrng: iproc-rng200 - Add support for BCM7278") Signed-off-by: Florian Fainelli Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/iproc-rng200.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/drivers/char/hw_random/iproc-rng200.c b/drivers/char/hw_random/iproc-rng200.c index 06bc060534d8..c0df053cbe4b 100644 --- a/drivers/char/hw_random/iproc-rng200.c +++ b/drivers/char/hw_random/iproc-rng200.c @@ -182,6 +182,8 @@ static int iproc_rng200_probe(struct platform_device *pdev) return PTR_ERR(priv->base); } + dev_set_drvdata(dev, priv); + priv->rng.name = "iproc-rng200"; priv->rng.read = iproc_rng200_read; priv->rng.init = iproc_rng200_init; @@ -199,6 +201,28 @@ static int iproc_rng200_probe(struct platform_device *pdev) return 0; } +static int __maybe_unused iproc_rng200_suspend(struct device *dev) +{ + struct iproc_rng200_dev *priv = dev_get_drvdata(dev); + + iproc_rng200_cleanup(&priv->rng); + + return 0; +} + +static int __maybe_unused iproc_rng200_resume(struct device *dev) +{ + struct iproc_rng200_dev *priv = dev_get_drvdata(dev); + + iproc_rng200_init(&priv->rng); + + return 0; +} + +static const struct dev_pm_ops iproc_rng200_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(iproc_rng200_suspend, iproc_rng200_resume) +}; + static const struct of_device_id iproc_rng200_of_match[] = { { .compatible = "brcm,bcm2711-rng200", }, { .compatible = "brcm,bcm7211-rng200", }, @@ -212,6 +236,7 @@ static struct platform_driver iproc_rng200_driver = { .driver = { .name = "iproc-rng200", .of_match_table = iproc_rng200_of_match, + .pm = &iproc_rng200_pm_ops, }, .probe = iproc_rng200_probe, }; From 065d5f17096ec9161180e2c890afdff4dc6125f2 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Thu, 17 Aug 2023 19:58:11 -0700 Subject: [PATCH 0863/2093] lwt: Fix return values of BPF xmit ops [ Upstream commit 29b22badb7a84b783e3a4fffca16f7768fb31205 ] BPF encap ops can return different types of positive values, such like NET_RX_DROP, NET_XMIT_CN, NETDEV_TX_BUSY, and so on, from function skb_do_redirect and bpf_lwt_xmit_reroute. At the xmit hook, such return values would be treated implicitly as LWTUNNEL_XMIT_CONTINUE in ip(6)_finish_output2. When this happens, skbs that have been freed would continue to the neighbor subsystem, causing use-after-free bug and kernel crashes. To fix the incorrect behavior, skb_do_redirect return values can be simply discarded, the same as tc-egress behavior. On the other hand, bpf_lwt_xmit_reroute returns useful errors to local senders, e.g. PMTU information. Thus convert its return values to avoid the conflict with LWTUNNEL_XMIT_CONTINUE. Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure") Reported-by: Jordan Griege Suggested-by: Martin KaFai Lau Suggested-by: Stanislav Fomichev Signed-off-by: Yan Zhai Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/0d2b878186cfe215fec6b45769c1cd0591d3628d.1692326837.git.yan@cloudflare.com Signed-off-by: Sasha Levin --- net/core/lwt_bpf.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 8b6b5e72b217..4a0797f0a154 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -60,9 +60,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, ret = BPF_OK; } else { skb_reset_mac_header(skb); - ret = skb_do_redirect(skb); - if (ret == 0) - ret = BPF_REDIRECT; + skb_do_redirect(skb); + ret = BPF_REDIRECT; } break; @@ -255,7 +254,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) err = dst_output(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(err)) - return err; + return net_xmit_errno(err); /* ip[6]_finish_output2 understand LWTUNNEL_XMIT_DONE */ return LWTUNNEL_XMIT_DONE; From a485a4bd8238609491a237eed5409541557d4773 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Thu, 17 Aug 2023 19:58:14 -0700 Subject: [PATCH 0864/2093] lwt: Check LWTUNNEL_XMIT_CONTINUE strictly [ Upstream commit a171fbec88a2c730b108c7147ac5e7b2f5a02b47 ] LWTUNNEL_XMIT_CONTINUE is implicitly assumed in ip(6)_finish_output2, such that any positive return value from a xmit hook could cause unexpected continue behavior, despite that related skb may have been freed. This could be error-prone for future xmit hook ops. One of the possible errors is to return statuses of dst_output directly. To make the code safer, redefine LWTUNNEL_XMIT_CONTINUE value to distinguish from dst_output statuses and check the continue condition explicitly. Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure") Suggested-by: Dan Carpenter Signed-off-by: Yan Zhai Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/96b939b85eda00e8df4f7c080f770970a4c5f698.1692326837.git.yan@cloudflare.com Signed-off-by: Sasha Levin --- include/net/lwtunnel.h | 5 ++++- net/ipv4/ip_output.c | 2 +- net/ipv6/ip6_output.c | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 6f15e6fa154e..53bd2d02a4f0 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -16,9 +16,12 @@ #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) #define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) +/* LWTUNNEL_XMIT_CONTINUE should be distinguishable from dst_output return + * values (NET_XMIT_xxx and NETDEV_TX_xxx in linux/netdevice.h) for safety. + */ enum { LWTUNNEL_XMIT_DONE, - LWTUNNEL_XMIT_CONTINUE, + LWTUNNEL_XMIT_CONTINUE = 0x100, }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index acfe58d2f1dd..ebd2cea5b7d7 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -214,7 +214,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 95a55c6630ad..34192f7a166f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -112,7 +112,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } From 844d60cc5efc73da54897179418ee50a836528e6 Mon Sep 17 00:00:00 2001 From: Artem Chernyshev Date: Thu, 3 Aug 2023 17:54:17 +0300 Subject: [PATCH 0865/2093] fs: ocfs2: namei: check return value of ocfs2_add_entry() [ Upstream commit 6b72e5f9e79360fce4f2be7fe81159fbdf4256a5 ] Process result of ocfs2_add_entry() in case we have an error value. Found by Linux Verification Center (linuxtesting.org) with SVACE. Link: https://lkml.kernel.org/r/20230803145417.177649-1-artem.chernyshev@red-soft.ru Fixes: ccd979bdbce9 ("[PATCH] OCFS2: The Second Oracle Cluster Filesystem") Signed-off-by: Artem Chernyshev Reviewed-by: Joseph Qi Cc: Artem Chernyshev Cc: Joel Becker Cc: Kurt Hackel Cc: Mark Fasheh Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/namei.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 1c7ac433667d..04a8505bd97a 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1535,6 +1535,10 @@ static int ocfs2_rename(struct user_namespace *mnt_userns, status = ocfs2_add_entry(handle, new_dentry, old_inode, OCFS2_I(old_inode)->ip_blkno, new_dir_bh, &target_insert); + if (status < 0) { + mlog_errno(status); + goto bail; + } } old_inode->i_ctime = current_time(old_inode); From 9257a1d6f27222d4c453e6404750066e4060f72d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 19 Aug 2023 04:06:46 +0000 Subject: [PATCH 0866/2093] net: annotate data-races around sk->sk_lingertime [ Upstream commit bc1fb82ae11753c5dec53c667a055dc37796dbd2 ] sk_getsockopt() runs locklessly. This means sk->sk_lingertime can be read while other threads are changing its value. Other reads also happen without socket lock being held, and must be annotated. Remove preprocessor logic using BITS_PER_LONG, compilers are smart enough to figure this by themselves. v2: fixed a clang W=1 (-Wtautological-constant-out-of-range-compare) warning (Jakub) Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/bluetooth/iso.c | 2 +- net/bluetooth/sco.c | 2 +- net/core/sock.c | 18 +++++++++--------- net/sched/em_meta.c | 2 +- net/smc/af_smc.c | 2 +- 5 files changed, 13 insertions(+), 13 deletions(-) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 699e4f400df2..5cd2e775915b 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1394,7 +1394,7 @@ static int iso_sock_release(struct socket *sock) iso_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1755f91a66f6..6d4168cfeb56 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1255,7 +1255,7 @@ static int sco_sock_release(struct socket *sock) sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); diff --git a/net/core/sock.c b/net/core/sock.c index 8b91d9f91133..fc475845c94d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -793,7 +793,7 @@ EXPORT_SYMBOL(sock_set_reuseport); void sock_no_linger(struct sock *sk) { lock_sock(sk); - sk->sk_lingertime = 0; + WRITE_ONCE(sk->sk_lingertime, 0); sock_set_flag(sk, SOCK_LINGER); release_sock(sk); } @@ -1219,15 +1219,15 @@ int sk_setsockopt(struct sock *sk, int level, int optname, ret = -EFAULT; break; } - if (!ling.l_onoff) + if (!ling.l_onoff) { sock_reset_flag(sk, SOCK_LINGER); - else { -#if (BITS_PER_LONG == 32) - if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) - sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; + } else { + unsigned long t_sec = ling.l_linger; + + if (t_sec >= MAX_SCHEDULE_TIMEOUT / HZ) + WRITE_ONCE(sk->sk_lingertime, MAX_SCHEDULE_TIMEOUT); else -#endif - sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; + WRITE_ONCE(sk->sk_lingertime, t_sec * HZ); sock_set_flag(sk, SOCK_LINGER); } break; @@ -1678,7 +1678,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); - v.ling.l_linger = sk->sk_lingertime / HZ; + v.ling.l_linger = READ_ONCE(sk->sk_lingertime) / HZ; break; case SO_BSDCOMPAT: diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index b1f1b49d35ed..6f2f135aab67 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -502,7 +502,7 @@ META_COLLECTOR(int_sk_lingertime) *err = -1; return; } - dst->value = sk->sk_lingertime / HZ; + dst->value = READ_ONCE(sk->sk_lingertime) / HZ; } META_COLLECTOR(int_sk_err_qlen) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 84219c5121bc..f774d840759d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1807,7 +1807,7 @@ void smc_close_non_accepted(struct sock *sk) lock_sock(sk); if (!sk->sk_lingertime) /* wait for peer closing */ - sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT; + WRITE_ONCE(sk->sk_lingertime, SMC_MAX_STREAM_WAIT_TIMEOUT); __smc_release(smc); release_sock(sk); sock_put(sk); /* sock_hold above */ From 84081b4baafb49211193c6a056d5aee9c0e6ab8e Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Wed, 2 Aug 2023 19:07:15 +0300 Subject: [PATCH 0867/2093] wifi: mwifiex: fix memory leak in mwifiex_histogram_read() [ Upstream commit 9c8fd72a5c2a031cbc680a2990107ecd958ffcdb ] Always free the zeroed page on return from 'mwifiex_histogram_read()'. Fixes: cbf6e05527a7 ("mwifiex: add rx histogram statistics support") Acked-by: Brian Norris Signed-off-by: Dmitry Antipov Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230802160726.85545-1-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/debugfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c index bda53cb91f37..63f232c72337 100644 --- a/drivers/net/wireless/marvell/mwifiex/debugfs.c +++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c @@ -253,8 +253,11 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf, if (!p) return -ENOMEM; - if (!priv || !priv->hist_data) - return -EFAULT; + if (!priv || !priv->hist_data) { + ret = -EFAULT; + goto free_and_exit; + } + phist_data = priv->hist_data; p += sprintf(p, "\n" @@ -309,6 +312,8 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf, ret = simple_read_from_buffer(ubuf, count, ppos, (char *)page, (unsigned long)p - page); +free_and_exit: + free_page(page); return ret; } From cde525d6117848c1bfce8edd37d30b55a2e3bc7f Mon Sep 17 00:00:00 2001 From: Polaris Pi Date: Thu, 10 Aug 2023 08:39:11 +0000 Subject: [PATCH 0868/2093] wifi: mwifiex: Fix missed return in oob checks failed path [ Upstream commit 2785851c627f2db05f9271f7f63661b5dbd95c4c ] Add missed return in mwifiex_uap_queue_bridged_pkt() and mwifiex_process_rx_packet(). Fixes: 119585281617 ("wifi: mwifiex: Fix OOB and integer underflow when rx packets") Signed-off-by: Polaris Pi Reported-by: Dmitry Antipov Acked-by: Brian Norris Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230810083911.3725248-1-pinkperfect2021@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/sta_rx.c | 1 + drivers/net/wireless/marvell/mwifiex/uap_txrx.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c index f2899d53a43f..65420ad67416 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c @@ -92,6 +92,7 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv, skb->len, rx_pkt_off); priv->stats.rx_dropped++; dev_kfree_skb_any(skb); + return -1; } if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c index 04ff051f5d18..c1b8d41dd753 100644 --- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c +++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c @@ -110,6 +110,7 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv, skb->len, le16_to_cpu(uap_rx_pd->rx_pkt_offset)); priv->stats.rx_dropped++; dev_kfree_skb_any(skb); + return; } if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, From ef67f3a959a75c793668ca6db14afaed69645ea7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 2 May 2023 12:25:29 -0500 Subject: [PATCH 0869/2093] ARM: dts: Add .dts files missing from the build [ Upstream commit 86684c2481b6e6a46c2282acee13554e34e66071 ] Comparing .dts files to built .dtb files yielded a few .dts files which are never built. Add them to the build. Signed-off-by: Rob Herring Stable-dep-of: 92632115fb57 ("samples/bpf: fix bio latency check with tracepoint") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/Makefile | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 6aa7dc4db2fc..df6d905eeb87 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -331,6 +331,7 @@ dtb-$(CONFIG_MACH_KIRKWOOD) += \ kirkwood-iconnect.dtb \ kirkwood-iomega_ix2_200.dtb \ kirkwood-is2.dtb \ + kirkwood-km_fixedeth.dtb \ kirkwood-km_kirkwood.dtb \ kirkwood-l-50.dtb \ kirkwood-laplug.dtb \ @@ -861,7 +862,10 @@ dtb-$(CONFIG_ARCH_OMAP3) += \ am3517-craneboard.dtb \ am3517-evm.dtb \ am3517_mt_ventoux.dtb \ + logicpd-torpedo-35xx-devkit.dtb \ logicpd-torpedo-37xx-devkit.dtb \ + logicpd-torpedo-37xx-devkit-28.dtb \ + logicpd-som-lv-35xx-devkit.dtb \ logicpd-som-lv-37xx-devkit.dtb \ omap3430-sdp.dtb \ omap3-beagle.dtb \ @@ -1527,6 +1531,8 @@ dtb-$(CONFIG_MACH_ARMADA_38X) += \ armada-388-helios4.dtb \ armada-388-rd.dtb dtb-$(CONFIG_MACH_ARMADA_39X) += \ + armada-390-db.dtb \ + armada-395-gp.dtb \ armada-398-db.dtb dtb-$(CONFIG_MACH_ARMADA_XP) += \ armada-xp-axpwifiap.dtb \ @@ -1556,6 +1562,7 @@ dtb-$(CONFIG_MACH_DOVE) += \ dtb-$(CONFIG_ARCH_MEDIATEK) += \ mt2701-evb.dtb \ mt6580-evbp1.dtb \ + mt6582-prestigio-pmt5008-3g.dtb \ mt6589-aquaris5.dtb \ mt6589-fairphone-fp1.dtb \ mt6592-evb.dtb \ @@ -1608,6 +1615,7 @@ dtb-$(CONFIG_ARCH_ASPEED) += \ aspeed-bmc-intel-s2600wf.dtb \ aspeed-bmc-inspur-fp5280g2.dtb \ aspeed-bmc-inspur-nf5280m6.dtb \ + aspeed-bmc-inspur-on5263m5.dtb \ aspeed-bmc-lenovo-hr630.dtb \ aspeed-bmc-lenovo-hr855xg2.dtb \ aspeed-bmc-microsoft-olympus.dtb \ From c813db76bc1531ae33d9d748ef9d211d802ae580 Mon Sep 17 00:00:00 2001 From: "Daniel T. Lee" Date: Fri, 18 Aug 2023 18:01:16 +0900 Subject: [PATCH 0870/2093] samples/bpf: fix bio latency check with tracepoint [ Upstream commit 92632115fb57ff9e368f256913e96d6fd5abf5ab ] Recently, a new tracepoint for the block layer, specifically the block_io_start/done tracepoints, was introduced in commit 5a80bd075f3b ("block: introduce block_io_start/block_io_done tracepoints"). Previously, the kprobe entry used for this purpose was quite unstable and inherently broke relevant probes [1]. Now that a stable tracepoint is available, this commit replaces the bio latency check with it. One of the changes made during this replacement is the key used for the hash table. Since 'struct request' cannot be used as a hash key, the approach taken follows that which was implemented in bcc/biolatency [2]. (uses dev:sector for the key) [1]: https://github.com/iovisor/bcc/issues/4261 [2]: https://github.com/iovisor/bcc/pull/4691 Fixes: 450b7879e345 ("block: move blk_account_io_{start,done} to blk-mq.c") Signed-off-by: Daniel T. Lee Link: https://lore.kernel.org/r/20230818090119.477441-7-danieltimlee@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- samples/bpf/tracex3_kern.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index bde6591cb20c..af235bd6615b 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -11,6 +11,12 @@ #include #include +struct start_key { + dev_t dev; + u32 _pad; + sector_t sector; +}; + struct { __uint(type, BPF_MAP_TYPE_HASH); __type(key, long); @@ -18,16 +24,17 @@ struct { __uint(max_entries, 4096); } my_map SEC(".maps"); -/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe - * example will no longer be meaningful - */ -SEC("kprobe/blk_mq_start_request") -int bpf_prog1(struct pt_regs *ctx) +/* from /sys/kernel/tracing/events/block/block_io_start/format */ +SEC("tracepoint/block/block_io_start") +int bpf_prog1(struct trace_event_raw_block_rq *ctx) { - long rq = PT_REGS_PARM1(ctx); u64 val = bpf_ktime_get_ns(); + struct start_key key = { + .dev = ctx->dev, + .sector = ctx->sector + }; - bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY); + bpf_map_update_elem(&my_map, &key, &val, BPF_ANY); return 0; } @@ -49,21 +56,26 @@ struct { __uint(max_entries, SLOTS); } lat_map SEC(".maps"); -SEC("kprobe/__blk_account_io_done") -int bpf_prog2(struct pt_regs *ctx) +/* from /sys/kernel/tracing/events/block/block_io_done/format */ +SEC("tracepoint/block/block_io_done") +int bpf_prog2(struct trace_event_raw_block_rq *ctx) { - long rq = PT_REGS_PARM1(ctx); + struct start_key key = { + .dev = ctx->dev, + .sector = ctx->sector + }; + u64 *value, l, base; u32 index; - value = bpf_map_lookup_elem(&my_map, &rq); + value = bpf_map_lookup_elem(&my_map, &key); if (!value) return 0; u64 cur_time = bpf_ktime_get_ns(); u64 delta = cur_time - *value; - bpf_map_delete_elem(&my_map, &rq); + bpf_map_delete_elem(&my_map, &key); /* the lines below are computing index = log10(delta)*10 * using integer arithmetic From 7984c381bbc1c4522d23a7c08886340376a6c5c5 Mon Sep 17 00:00:00 2001 From: "Daniel T. Lee" Date: Fri, 18 Aug 2023 18:01:17 +0900 Subject: [PATCH 0871/2093] samples/bpf: fix broken map lookup probe [ Upstream commit d93a7cf6ca2cfcd7de5d06f753ce8d5e863316ac ] In the commit 7c4cd051add3 ("bpf: Fix syscall's stackmap lookup potential deadlock"), a potential deadlock issue was addressed, which resulted in *_map_lookup_elem not triggering BPF programs. (prior to lookup, bpf_disable_instrumentation() is used) To resolve the broken map lookup probe using "htab_map_lookup_elem", this commit introduces an alternative approach. Instead, it utilize "bpf_map_copy_value" and apply a filter specifically for the hash table with map_type. Signed-off-by: Daniel T. Lee Fixes: 7c4cd051add3 ("bpf: Fix syscall's stackmap lookup potential deadlock") Link: https://lore.kernel.org/r/20230818090119.477441-8-danieltimlee@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- samples/bpf/tracex6_kern.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c index acad5712d8b4..fd602c2774b8 100644 --- a/samples/bpf/tracex6_kern.c +++ b/samples/bpf/tracex6_kern.c @@ -2,6 +2,8 @@ #include #include #include +#include +#include struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -45,13 +47,24 @@ int bpf_prog1(struct pt_regs *ctx) return 0; } -SEC("kprobe/htab_map_lookup_elem") -int bpf_prog2(struct pt_regs *ctx) +/* + * Since *_map_lookup_elem can't be expected to trigger bpf programs + * due to potential deadlocks (bpf_disable_instrumentation), this bpf + * program will be attached to bpf_map_copy_value (which is called + * from map_lookup_elem) and will only filter the hashtable type. + */ +SEC("kprobe/bpf_map_copy_value") +int BPF_KPROBE(bpf_prog2, struct bpf_map *map) { u32 key = bpf_get_smp_processor_id(); struct bpf_perf_event_value *val, buf; + enum bpf_map_type type; int error; + type = BPF_CORE_READ(map, map_type); + if (type != BPF_MAP_TYPE_HASH) + return 0; + error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf)); if (error) return 0; From 8ba31f946a6d2bae305dcc953c2ef0f6db94dd79 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Tue, 25 Apr 2023 22:26:06 +0300 Subject: [PATCH 0872/2093] wifi: ath9k: fix races between ath9k_wmi_cmd and ath9k_wmi_ctrl_rx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b674fb513e2e7a514fcde287c0f73915d393fdb6 ] Currently, the synchronization between ath9k_wmi_cmd() and ath9k_wmi_ctrl_rx() is exposed to a race condition which, although being rather unlikely, can lead to invalid behaviour of ath9k_wmi_cmd(). Consider the following scenario: CPU0 CPU1 ath9k_wmi_cmd(...) mutex_lock(&wmi->op_mutex) ath9k_wmi_cmd_issue(...) wait_for_completion_timeout(...) --- timeout --- /* the callback is being processed * before last_seq_id became zero */ ath9k_wmi_ctrl_rx(...) spin_lock_irqsave(...) /* wmi->last_seq_id check here * doesn't detect timeout yet */ spin_unlock_irqrestore(...) /* last_seq_id is zeroed to * indicate there was a timeout */ wmi->last_seq_id = 0 mutex_unlock(&wmi->op_mutex) return -ETIMEDOUT ath9k_wmi_cmd(...) mutex_lock(&wmi->op_mutex) /* the buffer is replaced with * another one */ wmi->cmd_rsp_buf = rsp_buf wmi->cmd_rsp_len = rsp_len ath9k_wmi_cmd_issue(...) spin_lock_irqsave(...) spin_unlock_irqrestore(...) wait_for_completion_timeout(...) /* the continuation of the * callback left after the first * ath9k_wmi_cmd call */ ath9k_wmi_rsp_callback(...) /* copying data designated * to already timeouted * WMI command into an * inappropriate wmi_cmd_buf */ memcpy(...) complete(&wmi->cmd_wait) /* awakened by the bogus callback * => invalid return result */ mutex_unlock(&wmi->op_mutex) return 0 To fix this, update last_seq_id on timeout path inside ath9k_wmi_cmd() under the wmi_lock. Move ath9k_wmi_rsp_callback() under wmi_lock inside ath9k_wmi_ctrl_rx() so that the wmi->cmd_wait can be completed only for initially designated wmi_cmd call, otherwise the path would be rejected with last_seq_id check. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Signed-off-by: Fedor Pchelkin Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230425192607.18015-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/wmi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index d652c647d56b..04f363cb90fe 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -242,10 +242,10 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb, spin_unlock_irqrestore(&wmi->wmi_lock, flags); goto free_skb; } - spin_unlock_irqrestore(&wmi->wmi_lock, flags); /* WMI command response */ ath9k_wmi_rsp_callback(wmi, skb); + spin_unlock_irqrestore(&wmi->wmi_lock, flags); free_skb: kfree_skb(skb); @@ -308,8 +308,8 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id, struct ath_common *common = ath9k_hw_common(ah); u16 headroom = sizeof(struct htc_frame_hdr) + sizeof(struct wmi_cmd_hdr); + unsigned long time_left, flags; struct sk_buff *skb; - unsigned long time_left; int ret = 0; if (ah->ah_flags & AH_UNPLUGGED) @@ -345,7 +345,9 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id, if (!time_left) { ath_dbg(common, WMI, "Timeout waiting for WMI command: %s\n", wmi_cmd_to_name(cmd_id)); + spin_lock_irqsave(&wmi->wmi_lock, flags); wmi->last_seq_id = 0; + spin_unlock_irqrestore(&wmi->wmi_lock, flags); mutex_unlock(&wmi->op_mutex); return -ETIMEDOUT; } From 4c340bfddce658f8690c07b9bb18a4685fd96bd4 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Tue, 25 Apr 2023 22:26:07 +0300 Subject: [PATCH 0873/2093] wifi: ath9k: protect WMI command response buffer replacement with a lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 454994cfa9e4c18b6df9f78b60db8eadc20a6c25 ] If ath9k_wmi_cmd() has exited with a timeout, it is possible that during next ath9k_wmi_cmd() call the wmi_rsp callback for previous wmi command writes to new wmi->cmd_rsp_buf and makes a completion. This results in an invalid ath9k_wmi_cmd() return value. Move the replacement of WMI command response buffer and length under wmi_lock. Note that last_seq_id value is updated there, too. Thus, the buffer cannot be written to by a belated wmi_rsp callback because that path is properly rejected by the last_seq_id check. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Signed-off-by: Fedor Pchelkin Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230425192607.18015-2-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/wmi.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index 04f363cb90fe..1476b42b52a9 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -283,7 +283,8 @@ int ath9k_wmi_connect(struct htc_target *htc, struct wmi *wmi, static int ath9k_wmi_cmd_issue(struct wmi *wmi, struct sk_buff *skb, - enum wmi_cmd_id cmd, u16 len) + enum wmi_cmd_id cmd, u16 len, + u8 *rsp_buf, u32 rsp_len) { struct wmi_cmd_hdr *hdr; unsigned long flags; @@ -293,6 +294,11 @@ static int ath9k_wmi_cmd_issue(struct wmi *wmi, hdr->seq_no = cpu_to_be16(++wmi->tx_seq_id); spin_lock_irqsave(&wmi->wmi_lock, flags); + + /* record the rsp buffer and length */ + wmi->cmd_rsp_buf = rsp_buf; + wmi->cmd_rsp_len = rsp_len; + wmi->last_seq_id = wmi->tx_seq_id; spin_unlock_irqrestore(&wmi->wmi_lock, flags); @@ -333,11 +339,7 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id, goto out; } - /* record the rsp buffer and length */ - wmi->cmd_rsp_buf = rsp_buf; - wmi->cmd_rsp_len = rsp_len; - - ret = ath9k_wmi_cmd_issue(wmi, skb, cmd_id, cmd_len); + ret = ath9k_wmi_cmd_issue(wmi, skb, cmd_id, cmd_len, rsp_buf, rsp_len); if (ret) goto out; From 4381d6083254bdef420a660dc8c41dea7f7d3f88 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Wed, 9 Aug 2023 11:31:51 +0800 Subject: [PATCH 0874/2093] wifi: nl80211/cfg80211: add forgotten nla_policy for BSS color attribute [ Upstream commit 218d690c49b7e9c94ad0d317adbdd4af846ea0dc ] The previous commit dd3e4fc75b4a ("nl80211/cfg80211: add BSS color to NDP ranging parameters") adds a parameter for NDP ranging by introducing a new attribute type named NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR. However, the author forgot to also describe the nla_policy at nl80211_pmsr_ftm_req_attr_policy (net/wireless/nl80211.c). Just complement it to avoid malformed attribute that causes out-of-attribute access. Fixes: dd3e4fc75b4a ("nl80211/cfg80211: add BSS color to NDP ranging parameters") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230809033151.768910-1-linma@zju.edu.cn Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/nl80211.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c2363d44a1ff..12c7c89d5be1 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -323,6 +323,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK] = { .type = NLA_FLAG }, + [NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR] = { .type = NLA_U8 }, }; static const struct nla_policy From 7930fa4ca871d17e55b15825d335bf353c1acfdf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 23 Jun 2023 17:24:00 +0200 Subject: [PATCH 0875/2093] mac80211: make ieee80211_tx_info padding explicit [ Upstream commit a7a2ef0c4b3efbd7d6f3fabd87dbbc0b3f2de5af ] While looking at a bug, I got rather confused by the layout of the 'status' field in ieee80211_tx_info. Apparently, the intention is that status_driver_data[] is used for driver specific data, and fills up the size of the union to 40 bytes, just like the other ones. This is indeed what actually happens, but only because of the combination of two mistakes: - "void *status_driver_data[18 / sizeof(void *)];" is intended to be 18 bytes long but is actually two bytes shorter because of rounding-down in the division, to a multiple of the pointer size (4 bytes or 8 bytes). - The other fields combined are intended to be 22 bytes long, but are actually 24 bytes because of padding in front of the unaligned tx_time member, and in front of the pointer array. The two mistakes cancel out. so the size ends up fine, but it seems more helpful to make this explicit, by having a multiple of 8 bytes in the size calculation and explicitly describing the padding. Fixes: ea5907db2a9cc ("mac80211: fix struct ieee80211_tx_info size") Fixes: 02219b3abca59 ("mac80211: add WMM admission control support") Signed-off-by: Arnd Bergmann Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20230623152443.2296825-2-arnd@kernel.org Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- include/net/mac80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 8a338c33118f..43173204d6d5 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1141,9 +1141,11 @@ struct ieee80211_tx_info { u8 ampdu_ack_len; u8 ampdu_len; u8 antenna; + u8 pad; u16 tx_time; u8 flags; - void *status_driver_data[18 / sizeof(void *)]; + u8 pad2; + void *status_driver_data[16 / sizeof(void *)]; } status; struct { struct ieee80211_tx_rate driver_rates[ From 7e7197e4d6a1bc72a774590d8765909f898be1dc Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Mon, 14 Aug 2023 12:49:57 +0300 Subject: [PATCH 0876/2093] wifi: mwifiex: avoid possible NULL skb pointer dereference [ Upstream commit 35a7a1ce7c7d61664ee54f5239a1f120ab95a87e ] In 'mwifiex_handle_uap_rx_forward()', always check the value returned by 'skb_copy()' to avoid potential NULL pointer dereference in 'mwifiex_uap_queue_bridged_pkt()', and drop original skb in case of copying failure. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 838e4f449297 ("mwifiex: improve uAP RX handling") Acked-by: Brian Norris Signed-off-by: Dmitry Antipov Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230814095041.16416-1-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/uap_txrx.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c index c1b8d41dd753..b8b9a0fcb19c 100644 --- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c +++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c @@ -253,7 +253,15 @@ int mwifiex_handle_uap_rx_forward(struct mwifiex_private *priv, if (is_multicast_ether_addr(ra)) { skb_uap = skb_copy(skb, GFP_ATOMIC); - mwifiex_uap_queue_bridged_pkt(priv, skb_uap); + if (likely(skb_uap)) { + mwifiex_uap_queue_bridged_pkt(priv, skb_uap); + } else { + mwifiex_dbg(adapter, ERROR, + "failed to copy skb for uAP\n"); + priv->stats.rx_dropped++; + dev_kfree_skb_any(skb); + return -1; + } } else { if (mwifiex_get_sta_entry(priv, ra)) { /* Requeue Intra-BSS packet */ From a33ae132eec218fa6588e932ec48209b4c410680 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Wed, 23 Aug 2023 11:46:37 +0800 Subject: [PATCH 0877/2093] Bluetooth: btusb: Do not call kfree_skb() under spin_lock_irqsave() [ Upstream commit 2a05334d7f91ff189692089c05fc48cc1d8204de ] It is not allowed to call kfree_skb() from hardware interrupt context or with hardware interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: baac6276c0a9 ("Bluetooth: btusb: handle mSBC audio over USB Endpoints") Signed-off-by: Jinjie Ruan Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index d6f405763c56..f2062c2a28da 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -1984,7 +1984,7 @@ static int btusb_switch_alt_setting(struct hci_dev *hdev, int new_alts) * alternate setting. */ spin_lock_irqsave(&data->rxlock, flags); - kfree_skb(data->sco_skb); + dev_kfree_skb_irq(data->sco_skb); data->sco_skb = NULL; spin_unlock_irqrestore(&data->rxlock, flags); From 4a8fadcf37485e17d5a51a0f8c06e1c644d3ea05 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 10 Aug 2023 09:32:41 +0000 Subject: [PATCH 0878/2093] arm64: mm: use ptep_clear() instead of pte_clear() in clear_flush() [ Upstream commit 00de2c9f26b15f1a6f2af516dd8ec5f8d28189b7 ] In clear_flush(), the original pte may be a present entry, so we should use ptep_clear() to let page_table_check track the pte clearing operation, otherwise it may cause false positive in subsequent set_pte_at(). Link: https://lkml.kernel.org/r/20230810093241.1181142-1-qi.zheng@linux.dev Fixes: 42b2547137f5 ("arm64/mm: enable ARCH_SUPPORTS_PAGE_TABLE_CHECK") Signed-off-by: Qi Zheng Acked-by: Will Deacon Cc: Catalin Marinas Cc: Kefeng Wang Cc: Muchun Song Cc: Pasha Tatashin Cc: Qi Zheng Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- arch/arm64/mm/hugetlbpage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 35e9a468d13e..134dcf6bc650 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -236,7 +236,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) - pte_clear(mm, addr, ptep); + ptep_clear(mm, addr, ptep); flush_tlb_range(&vma, saddr, addr); } From 90e7778660c9a0975b24858f3be6a92bb09ae326 Mon Sep 17 00:00:00 2001 From: Wang Ming Date: Thu, 13 Jul 2023 11:03:44 +0800 Subject: [PATCH 0879/2093] wifi: ath9k: use IS_ERR() with debugfs_create_dir() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1e4134610d93271535ecf900a676e1f094e9944c ] The debugfs_create_dir() function returns error pointers, it never returns NULL. Most incorrect error checks were fixed, but the one in ath9k_htc_init_debug() was forgotten. Fix the remaining error check. Fixes: e5facc75fa91 ("ath9k_htc: Cleanup HTC debugfs") Signed-off-by: Wang Ming Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230713030358.12379-1-machel@vivo.com Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/htc_drv_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c index b3ed65e5c4da..c55aab01fff5 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c @@ -491,7 +491,7 @@ int ath9k_htc_init_debug(struct ath_hw *ah) priv->debug.debugfs_phy = debugfs_create_dir(KBUILD_MODNAME, priv->hw->wiphy->debugfsdir); - if (!priv->debug.debugfs_phy) + if (IS_ERR(priv->debug.debugfs_phy)) return -ENOMEM; ath9k_cmn_spectral_init_debug(&priv->spec_priv, priv->debug.debugfs_phy); From cb09afe905cbf72ec30e7ac7604e8b7df3ee5d80 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 23 Aug 2023 08:18:14 -0700 Subject: [PATCH 0880/2093] ice: avoid executing commands on other ports when driving sync [ Upstream commit 0aacec49c29e7c5b1487e859b0c0a42388c34092 ] The ice hardware has a synchronization mechanism used to drive the simultaneous application of commands on both PHY ports and the source timer in the MAC. When issuing a sync via ice_ptp_exec_tmr_cmd(), the hardware will simultaneously apply the commands programmed for the main timer and each PHY port. Neither the main timer command register, nor the PHY port command registers auto clear on command execution. During the execution of a timer command intended for a single port on E822 devices, such as those used to configure a PHY during link up, the driver is not correctly clearing the previous commands. This results in unintentionally executing the last programmed command on the main timer and other PHY ports whenever performing reconfiguration on E822 ports after link up. This results in unintended side effects on other timers, depending on what command was previously programmed. To fix this, the driver must ensure that the main timer and all other PHY ports are properly initialized to perform no action. The enumeration for timer commands does not include an enumeration value for doing nothing. Introduce ICE_PTP_NOP for this purpose. When writing a timer command to hardware, leave the command bits set to zero which indicates that no operation should be performed on that port. Modify ice_ptp_one_port_cmd() to always initialize all ports. For all ports other than the one being configured, write their timer command register to ICE_PTP_NOP. This ensures that no side effect happens on the timer command. To fix this for the PHY ports, modify ice_ptp_one_port_cmd() to always initialize all other ports to ICE_PTP_NOP. This ensures that no side effects happen on the other ports. Call ice_ptp_src_cmd() with a command value if ICE_PTP_NOP in ice_sync_phy_timer_e822() and ice_start_phy_timer_e822(). With both of these changes, the driver should no longer execute a stale command on the main timer or another PHY port when reconfiguring one of the PHY ports after link up. Fixes: 3a7496234d17 ("ice: implement basic E822 PTP support") Signed-off-by: Siddaraju DH Signed-off-by: Jacob Keller Tested-by: Sunitha Mekala (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 55 +++++++++++++++++++-- drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 3 +- 2 files changed, 52 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 772b1f566d6e..813acd6a4b46 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -131,6 +131,8 @@ static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) case READ_TIME: cmd_val |= GLTSYN_CMD_READ_TIME; break; + case ICE_PTP_NOP: + break; } wr32(hw, GLTSYN_CMD, cmd_val); @@ -1200,18 +1202,18 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) } /** - * ice_ptp_one_port_cmd - Prepare a single PHY port for a timer command + * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command * @hw: pointer to HW struct * @port: Port to which cmd has to be sent * @cmd: Command to be sent to the port * * Prepare the requested port for an upcoming timer sync command. * - * Note there is no equivalent of this operation on E810, as that device - * always handles all external PHYs internally. + * Do not use this function directly. If you want to configure exactly one + * port, use ice_ptp_one_port_cmd() instead. */ static int -ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) +ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { u32 cmd_val, val; u8 tmr_idx; @@ -1235,6 +1237,8 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) case ADJ_TIME_AT_TIME: cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME; break; + case ICE_PTP_NOP: + break; } /* Tx case */ @@ -1280,6 +1284,39 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) return 0; } +/** + * ice_ptp_one_port_cmd - Prepare one port for a timer command + * @hw: pointer to the HW struct + * @configured_port: the port to configure with configured_cmd + * @configured_cmd: timer command to prepare on the configured_port + * + * Prepare the configured_port for the configured_cmd, and prepare all other + * ports for ICE_PTP_NOP. This causes the configured_port to execute the + * desired command while all other ports perform no operation. + */ +static int +ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, + enum ice_ptp_tmr_cmd configured_cmd) +{ + u8 port; + + for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + enum ice_ptp_tmr_cmd cmd; + int err; + + if (port == configured_port) + cmd = configured_cmd; + else + cmd = ICE_PTP_NOP; + + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); + if (err) + return err; + } + + return 0; +} + /** * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command * @hw: pointer to the HW struct @@ -1296,7 +1333,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_ptp_one_port_cmd(hw, port, cmd); + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); if (err) return err; } @@ -2245,6 +2282,9 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) goto err_unlock; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + /* Issue the sync to activate the time adjustment */ ice_ptp_exec_tmr_cmd(hw); @@ -2371,6 +2411,9 @@ ice_start_phy_timer_e822(struct ice_hw *hw, u8 port, bool bypass) if (err) return err; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + ice_ptp_exec_tmr_cmd(hw); err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); @@ -2914,6 +2957,8 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) case ADJ_TIME_AT_TIME: cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; break; + case ICE_PTP_NOP: + return 0; } /* Read, modify, write */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 2bda64c76abc..071f545aa85e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -9,7 +9,8 @@ enum ice_ptp_tmr_cmd { INIT_INCVAL, ADJ_TIME, ADJ_TIME_AT_TIME, - READ_TIME + READ_TIME, + ICE_PTP_NOP, }; enum ice_ptp_serdes { From ec9538da6ce4059716088a697675081b83c43048 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Thu, 24 Aug 2023 14:43:36 +0800 Subject: [PATCH 0881/2093] net: arcnet: Do not call kfree_skb() under local_irq_disable() [ Upstream commit 786c96e92fb9e854cb8b0cb7399bb2fb28e15c4b ] It is not allowed to call kfree_skb() from hardware interrupt context or with hardware interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under local_irq_disable(). Compile tested only. Fixes: 05fcd31cc472 ("arcnet: add err_skb package for package status feedback") Signed-off-by: Jinjie Ruan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/arcnet/arcnet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 1bad1866ae46..a48220f91a2d 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -468,7 +468,7 @@ static void arcnet_reply_tasklet(struct tasklet_struct *t) ret = sock_queue_err_skb(sk, ackskb); if (ret) - kfree_skb(ackskb); + dev_kfree_skb_irq(ackskb); local_irq_enable(); }; From 2fc240094031dd71b4dbfa0ff533e43047280e7f Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Thu, 24 Aug 2023 15:43:08 +0200 Subject: [PATCH 0882/2093] mlxsw: i2c: Fix chunk size setting in output mailbox buffer [ Upstream commit 146c7c330507c0384bf29d567186632bfe975927 ] The driver reads commands output from the output mailbox. If the size of the output mailbox is not a multiple of the transaction / block size, then the driver will not issue enough read transactions to read the entire output, which can result in driver initialization errors. Fix by determining the number of transactions using DIV_ROUND_UP(). Fixes: 3029a693beda ("mlxsw: i2c: Allow flexible setting of I2C transactions size") Signed-off-by: Vadim Pasternak Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/i2c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index f5f5f8dc3d19..26e05f129e35 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -444,7 +444,7 @@ mlxsw_i2c_cmd(struct device *dev, u16 opcode, u32 in_mod, size_t in_mbox_size, } else { /* No input mailbox is case of initialization query command. */ reg_size = MLXSW_I2C_MAX_DATA_SIZE; - num = reg_size / mlxsw_i2c->block_size; + num = DIV_ROUND_UP(reg_size, mlxsw_i2c->block_size); if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) { dev_err(&client->dev, "Could not acquire lock"); From 6406a95c4a5e8a60e283bc705fad21895a257adb Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Thu, 24 Aug 2023 15:43:09 +0200 Subject: [PATCH 0883/2093] mlxsw: i2c: Limit single transaction buffer size [ Upstream commit d7248f1cc835bd80e936dc5b2d94b149bdd0077d ] Maximum size of buffer is obtained from underlying I2C adapter and in case adapter allows I2C transaction buffer size greater than 100 bytes, transaction will fail due to firmware limitation. As a result driver will fail initialization. Limit the maximum size of transaction buffer by 100 bytes to fit to firmware. Remove unnecessary calculation: max_t(u16, MLXSW_I2C_BLK_DEF, quirk_size). This condition can not happened. Fixes: 3029a693beda ("mlxsw: i2c: Allow flexible setting of I2C transactions size") Signed-off-by: Vadim Pasternak Reviewed-by: Petr Machata Signed-off-by: Petr Machata Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/i2c.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 26e05f129e35..3beefc167da9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -48,6 +48,7 @@ #define MLXSW_I2C_MBOX_SIZE_BITS 12 #define MLXSW_I2C_ADDR_BUF_SIZE 4 #define MLXSW_I2C_BLK_DEF 32 +#define MLXSW_I2C_BLK_MAX 100 #define MLXSW_I2C_RETRY 5 #define MLXSW_I2C_TIMEOUT_MSECS 5000 #define MLXSW_I2C_MAX_DATA_SIZE 256 @@ -653,7 +654,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, return -EOPNOTSUPP; } - mlxsw_i2c->block_size = max_t(u16, MLXSW_I2C_BLK_DEF, + mlxsw_i2c->block_size = min_t(u16, MLXSW_I2C_BLK_MAX, min_t(u16, quirks->max_read_len, quirks->max_write_len)); } else { From 8b2fb4b671b3c4574a705570e2feadbb47896a69 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Thu, 24 Aug 2023 15:43:10 +0200 Subject: [PATCH 0884/2093] mlxsw: core_hwmon: Adjust module label names based on MTCAP sensor counter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3fc134a07438055fc93ce1bbacf2702ddd09500c ] Transceiver module temperature sensors are indexed after ASIC and platform sensors. The current label printing method does not take this into account and simply prints the index of the transceiver module sensor. On new systems that have platform sensors this results in incorrect (shifted) transceiver module labels being printed: $ sensors [...] front panel 002: +37.0°C (crit = +70.0°C, emerg = +75.0°C) front panel 003: +47.0°C (crit = +70.0°C, emerg = +75.0°C) [...] Fix by taking the sensor count into account. After the fix: $ sensors [...] front panel 001: +37.0°C (crit = +70.0°C, emerg = +75.0°C) front panel 002: +47.0°C (crit = +70.0°C, emerg = +75.0°C) [...] Fixes: a53779de6a0e ("mlxsw: core: Add QSFP module temperature label attribute to hwmon") Signed-off-by: Vadim Pasternak Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 70735068cf29..0fd290d776ff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -405,7 +405,8 @@ mlxsw_hwmon_module_temp_label_show(struct device *dev, container_of(attr, struct mlxsw_hwmon_attr, dev_attr); return sprintf(buf, "front panel %03u\n", - mlxsw_hwmon_attr->type_index); + mlxsw_hwmon_attr->type_index + 1 - + mlxsw_hwmon_attr->mlxsw_hwmon_dev->sensor_count); } static ssize_t From 23a7b872898b8106e0c58e0a8ef8d3404952ae0d Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 24 Aug 2023 21:44:54 +0100 Subject: [PATCH 0885/2093] hwmon: (tmp513) Fix the channel number in tmp51x_is_visible() [ Upstream commit d103337e38e7e64c3d915029e947b1cb0b512737 ] The supported channels for this driver are {0..3}. Fix the incorrect channel in tmp51x_is_visible(). Reported-by: Guenter Roeck Closes: https://lore.kernel.org/all/ea0eccc0-a29f-41e4-9049-a1a13f8b16f1@roeck-us.net/ Fixes: 59dfa75e5d82 ("hwmon: Add driver for Texas Instruments TMP512/513 sensor chips.") Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230824204456.401580-2-biju.das.jz@bp.renesas.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/tmp513.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/tmp513.c b/drivers/hwmon/tmp513.c index 7d5f7441aceb..b9a93ee9c236 100644 --- a/drivers/hwmon/tmp513.c +++ b/drivers/hwmon/tmp513.c @@ -434,7 +434,7 @@ static umode_t tmp51x_is_visible(const void *_data, switch (type) { case hwmon_temp: - if (data->id == tmp512 && channel == 4) + if (data->id == tmp512 && channel == 3) return 0; switch (attr) { case hwmon_temp_input: From 80de42d9af977633fec915c8477fd00238f7b64c Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Sat, 13 May 2023 14:21:39 +0530 Subject: [PATCH 0886/2093] octeontx2-pf: Refactor schedular queue alloc/free calls [ Upstream commit 6b4b2ded9c4282deea421eef144ab0ced954721c ] 1. Upon txschq free request, the transmit schedular config in hardware is not getting reset. This patch adds necessary changes to do the same. 2. Current implementation calls txschq alloc during interface initialization and in response handler updates the default txschq array. This creates a problem for htb offload where txsch alloc will be called for every tc class. This patch addresses the issue by reading txschq response in mbox caller function instead in the response handler. 3. Current otx2_txschq_stop routine tries to free all txschq nodes allocated to the interface. This creates a problem for htb offload. This patch introduces the otx2_txschq_free_one to free txschq in a given level. Signed-off-by: Hariprasad Kelam Signed-off-by: Naveen Mamindlapalli Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller Stable-dep-of: a9ac2e187795 ("octeontx2-pf: Fix PFC TX scheduler free") Signed-off-by: Sasha Levin --- .../ethernet/marvell/octeontx2/af/rvu_nix.c | 45 +++++++++++++ .../marvell/octeontx2/nic/otx2_common.c | 67 ++++++++++++------- .../marvell/octeontx2/nic/otx2_common.h | 3 +- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 13 +--- .../ethernet/marvell/octeontx2/nic/otx2_vf.c | 4 -- 5 files changed, 94 insertions(+), 38 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 5541e284cd3f..c85e0180d96d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -1691,6 +1691,42 @@ handle_txschq_shaper_update(struct rvu *rvu, int blkaddr, int nixlf, return true; } +static void nix_reset_tx_schedule(struct rvu *rvu, int blkaddr, + int lvl, int schq) +{ + u64 tlx_parent = 0, tlx_schedule = 0; + + switch (lvl) { + case NIX_TXSCH_LVL_TL2: + tlx_parent = NIX_AF_TL2X_PARENT(schq); + tlx_schedule = NIX_AF_TL2X_SCHEDULE(schq); + break; + case NIX_TXSCH_LVL_TL3: + tlx_parent = NIX_AF_TL3X_PARENT(schq); + tlx_schedule = NIX_AF_TL3X_SCHEDULE(schq); + break; + case NIX_TXSCH_LVL_TL4: + tlx_parent = NIX_AF_TL4X_PARENT(schq); + tlx_schedule = NIX_AF_TL4X_SCHEDULE(schq); + break; + case NIX_TXSCH_LVL_MDQ: + /* no need to reset SMQ_CFG as HW clears this CSR + * on SMQ flush + */ + tlx_parent = NIX_AF_MDQX_PARENT(schq); + tlx_schedule = NIX_AF_MDQX_SCHEDULE(schq); + break; + default: + return; + } + + if (tlx_parent) + rvu_write64(rvu, blkaddr, tlx_parent, 0x0); + + if (tlx_schedule) + rvu_write64(rvu, blkaddr, tlx_schedule, 0x0); +} + /* Disable shaping of pkts by a scheduler queue * at a given scheduler level. */ @@ -2040,6 +2076,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu, pfvf_map[schq] = TXSCH_MAP(pcifunc, 0); nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); } for (idx = 0; idx < req->schq[lvl]; idx++) { @@ -2049,6 +2086,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu, pfvf_map[schq] = TXSCH_MAP(pcifunc, 0); nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); } } @@ -2137,6 +2175,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc) continue; nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); nix_clear_tx_xoff(rvu, blkaddr, lvl, schq); + nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); } } nix_clear_tx_xoff(rvu, blkaddr, NIX_TXSCH_LVL_TL1, @@ -2175,6 +2214,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc) for (schq = 0; schq < txsch->schq.max; schq++) { if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) continue; + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); rvu_free_rsrc(&txsch->schq, schq); txsch->pfvf_map[schq] = TXSCH_MAP(0, NIX_TXSCHQ_FREE); } @@ -2234,6 +2274,9 @@ static int nix_txschq_free_one(struct rvu *rvu, */ nix_clear_tx_xoff(rvu, blkaddr, lvl, schq); + nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); + nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); + /* Flush if it is a SMQ. Onus of disabling * TL2/3 queue links before SMQ flush is on user */ @@ -2243,6 +2286,8 @@ static int nix_txschq_free_one(struct rvu *rvu, goto err; } + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); + /* Free the resource */ rvu_free_rsrc(&txsch->schq, schq); txsch->pfvf_map[schq] = TXSCH_MAP(0, NIX_TXSCHQ_FREE); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 8a41ad8ca04f..dd97731f8169 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -716,7 +716,8 @@ EXPORT_SYMBOL(otx2_smq_flush); int otx2_txsch_alloc(struct otx2_nic *pfvf) { struct nix_txsch_alloc_req *req; - int lvl; + struct nix_txsch_alloc_rsp *rsp; + int lvl, schq, rc; /* Get memory to put this msg */ req = otx2_mbox_alloc_msg_nix_txsch_alloc(&pfvf->mbox); @@ -726,33 +727,68 @@ int otx2_txsch_alloc(struct otx2_nic *pfvf) /* Request one schq per level */ for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) req->schq[lvl] = 1; + rc = otx2_sync_mbox_msg(&pfvf->mbox); + if (rc) + return rc; - return otx2_sync_mbox_msg(&pfvf->mbox); + rsp = (struct nix_txsch_alloc_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr); + if (IS_ERR(rsp)) + return PTR_ERR(rsp); + + /* Setup transmit scheduler list */ + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) + for (schq = 0; schq < rsp->schq[lvl]; schq++) + pfvf->hw.txschq_list[lvl][schq] = + rsp->schq_list[lvl][schq]; + + pfvf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl; + + return 0; } -int otx2_txschq_stop(struct otx2_nic *pfvf) +void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq) { struct nix_txsch_free_req *free_req; - int lvl, schq, err; + int err; mutex_lock(&pfvf->mbox.lock); - /* Free the transmit schedulers */ + free_req = otx2_mbox_alloc_msg_nix_txsch_free(&pfvf->mbox); if (!free_req) { mutex_unlock(&pfvf->mbox.lock); - return -ENOMEM; + netdev_err(pfvf->netdev, + "Failed alloc txschq free req\n"); + return; } - free_req->flags = TXSCHQ_FREE_ALL; + free_req->schq_lvl = lvl; + free_req->schq = schq; + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + netdev_err(pfvf->netdev, + "Failed stop txschq %d at level %d\n", schq, lvl); + } + mutex_unlock(&pfvf->mbox.lock); +} + +void otx2_txschq_stop(struct otx2_nic *pfvf) +{ + int lvl, schq; + + /* free non QOS TLx nodes */ + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) + otx2_txschq_free_one(pfvf, lvl, + pfvf->hw.txschq_list[lvl][0]); /* Clear the txschq list */ for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { for (schq = 0; schq < MAX_TXSCHQ_PER_FUNC; schq++) pfvf->hw.txschq_list[lvl][schq] = 0; } - return err; + } void otx2_sqb_flush(struct otx2_nic *pfvf) @@ -1629,21 +1665,6 @@ void mbox_handler_cgx_fec_stats(struct otx2_nic *pfvf, pfvf->hw.cgx_fec_uncorr_blks += rsp->fec_uncorr_blks; } -void mbox_handler_nix_txsch_alloc(struct otx2_nic *pf, - struct nix_txsch_alloc_rsp *rsp) -{ - int lvl, schq; - - /* Setup transmit scheduler list */ - for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) - for (schq = 0; schq < rsp->schq[lvl]; schq++) - pf->hw.txschq_list[lvl][schq] = - rsp->schq_list[lvl][schq]; - - pf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl; -} -EXPORT_SYMBOL(mbox_handler_nix_txsch_alloc); - void mbox_handler_npa_lf_alloc(struct otx2_nic *pfvf, struct npa_lf_alloc_rsp *rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 241016ca64d0..8a9793b06769 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -917,7 +917,8 @@ int otx2_config_nix(struct otx2_nic *pfvf); int otx2_config_nix_queues(struct otx2_nic *pfvf); int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool pfc_en); int otx2_txsch_alloc(struct otx2_nic *pfvf); -int otx2_txschq_stop(struct otx2_nic *pfvf); +void otx2_txschq_stop(struct otx2_nic *pfvf); +void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq); void otx2_sqb_flush(struct otx2_nic *pfvf); int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, dma_addr_t *dma); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index c236dba80ff1..17e546d0d7e5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -791,10 +791,6 @@ static void otx2_process_pfaf_mbox_msg(struct otx2_nic *pf, case MBOX_MSG_NIX_LF_ALLOC: mbox_handler_nix_lf_alloc(pf, (struct nix_lf_alloc_rsp *)msg); break; - case MBOX_MSG_NIX_TXSCH_ALLOC: - mbox_handler_nix_txsch_alloc(pf, - (struct nix_txsch_alloc_rsp *)msg); - break; case MBOX_MSG_NIX_BP_ENABLE: mbox_handler_nix_bp_enable(pf, (struct nix_bp_cfg_rsp *)msg); break; @@ -1517,8 +1513,7 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) otx2_free_cq_res(pf); otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false); err_free_txsch: - if (otx2_txschq_stop(pf)) - dev_err(pf->dev, "%s failed to stop TX schedulers\n", __func__); + otx2_txschq_stop(pf); err_free_sq_ptrs: otx2_sq_free_sqbs(pf); err_free_rq_ptrs: @@ -1553,15 +1548,13 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) struct mbox *mbox = &pf->mbox; struct otx2_cq_queue *cq; struct msg_req *req; - int qidx, err; + int qidx; /* Ensure all SQE are processed */ otx2_sqb_flush(pf); /* Stop transmission */ - err = otx2_txschq_stop(pf); - if (err) - dev_err(pf->dev, "RVUPF: Failed to stop/free TX schedulers\n"); + otx2_txschq_stop(pf); #ifdef CONFIG_DCB if (pf->pfc_en) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 53366dbfbf27..f8f0c01f62a1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -70,10 +70,6 @@ static void otx2vf_process_vfaf_mbox_msg(struct otx2_nic *vf, case MBOX_MSG_NIX_LF_ALLOC: mbox_handler_nix_lf_alloc(vf, (struct nix_lf_alloc_rsp *)msg); break; - case MBOX_MSG_NIX_TXSCH_ALLOC: - mbox_handler_nix_txsch_alloc(vf, - (struct nix_txsch_alloc_rsp *)msg); - break; case MBOX_MSG_NIX_BP_ENABLE: mbox_handler_nix_bp_enable(vf, (struct nix_bp_cfg_rsp *)msg); break; From 1b7f266e021909e7903af2fe94659bb64fcb6cd5 Mon Sep 17 00:00:00 2001 From: Suman Ghosh Date: Thu, 24 Aug 2023 13:40:30 +0530 Subject: [PATCH 0887/2093] octeontx2-pf: Fix PFC TX scheduler free [ Upstream commit a9ac2e18779597f280d68a5b5f5bdd51a34080fa ] During PFC TX schedulers free, flag TXSCHQ_FREE_ALL was being set which caused free up all schedulers other than the PFC schedulers. This patch fixes that to free only the PFC Tx schedulers. Fixes: 99c969a83d82 ("octeontx2-pf: Add egress PFC support") Signed-off-by: Suman Ghosh Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230824081032.436432-2-sumang@marvell.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../ethernet/marvell/octeontx2/nic/otx2_common.c | 1 + .../ethernet/marvell/octeontx2/nic/otx2_dcbnl.c | 15 ++++----------- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index dd97731f8169..011355e73696 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -773,6 +773,7 @@ void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq) mutex_unlock(&pfvf->mbox.lock); } +EXPORT_SYMBOL(otx2_txschq_free_one); void otx2_txschq_stop(struct otx2_nic *pfvf) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index ccaf97bb1ce0..6492749dd7c8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -125,19 +125,12 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf) static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio) { - struct nix_txsch_free_req *free_req; + int lvl; - mutex_lock(&pfvf->mbox.lock); /* free PFC TLx nodes */ - free_req = otx2_mbox_alloc_msg_nix_txsch_free(&pfvf->mbox); - if (!free_req) { - mutex_unlock(&pfvf->mbox.lock); - return -ENOMEM; - } - - free_req->flags = TXSCHQ_FREE_ALL; - otx2_sync_mbox_msg(&pfvf->mbox); - mutex_unlock(&pfvf->mbox.lock); + for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++) + otx2_txschq_free_one(pfvf, lvl, + pfvf->pfc_schq_list[lvl][prio]); pfvf->pfc_alloc_status[prio] = false; return 0; From ea701e0eba7ef3a965d772e8ca89c22706c9835a Mon Sep 17 00:00:00 2001 From: Suman Ghosh Date: Thu, 24 Aug 2023 13:40:32 +0530 Subject: [PATCH 0888/2093] cteonxt2-pf: Fix backpressure config for multiple PFC priorities to work simultaneously [ Upstream commit 597d0ec0e4ca6a912affea4cc94df08959e9ec74 ] MAC (CGX or RPM) asserts backpressure at TL3 or TL2 node of the egress hierarchical scheduler tree depending on link level config done. If there are multiple PFC priorities enabled at a time and for all such flows to backoff, each priority will have to assert backpressure at different TL3/TL2 scheduler nodes and these flows will need to submit egress pkts to these nodes. Current PFC configuration has an issue where in only one backpressure scheduler node is being allocated which is resulting in only one PFC priority to work. This patch fixes this issue. Fixes: 99c969a83d82 ("octeontx2-pf: Add egress PFC support") Signed-off-by: Suman Ghosh Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230824081032.436432-4-sumang@marvell.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index 6492749dd7c8..bfddbff7bcdf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -70,7 +70,7 @@ static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio) * link config level. These rest of the scheduler can be * same as hw.txschq_list. */ - for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++) + for (lvl = 0; lvl <= pfvf->hw.txschq_link_cfg_lvl; lvl++) req->schq[lvl] = 1; rc = otx2_sync_mbox_msg(&pfvf->mbox); @@ -83,7 +83,7 @@ static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio) return PTR_ERR(rsp); /* Setup transmit scheduler list */ - for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++) { + for (lvl = 0; lvl <= pfvf->hw.txschq_link_cfg_lvl; lvl++) { if (!rsp->schq[lvl]) return -ENOSPC; @@ -128,7 +128,7 @@ static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio) int lvl; /* free PFC TLx nodes */ - for (lvl = 0; lvl < pfvf->hw.txschq_link_cfg_lvl; lvl++) + for (lvl = 0; lvl <= pfvf->hw.txschq_link_cfg_lvl; lvl++) otx2_txschq_free_one(pfvf, lvl, pfvf->pfc_schq_list[lvl][prio]); From 85da5ec0681e05ffbde7b24b3f7750102ef55882 Mon Sep 17 00:00:00 2001 From: Alex Austin Date: Thu, 24 Aug 2023 17:46:57 +0100 Subject: [PATCH 0889/2093] sfc: Check firmware supports Ethernet PTP filter [ Upstream commit c4413a20fa6d7c4888009fb7dd391685f196cd36 ] Not all firmware variants support RSS filters. Do not fail all PTP functionality when raw ethernet PTP filters fail to insert. Fixes: e4616f64726b ("sfc: support PTP over Ethernet") Signed-off-by: Alex Austin Acked-by: Edward Cree Reviewed-by: Pieter Jansen van Vuuren Link: https://lore.kernel.org/r/20230824164657.42379-1-alex.austin@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/ptp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index eaef4a15008a..692c7f132e9f 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1387,7 +1387,8 @@ static int efx_ptp_insert_multicast_filters(struct efx_nic *efx) goto fail; rc = efx_ptp_insert_eth_filter(efx); - if (rc < 0) + /* Not all firmware variants support this filter */ + if (rc < 0 && rc != -EPROTONOSUPPORT) goto fail; } From a1e820fc7808e42b990d224f40e9b4895503ac40 Mon Sep 17 00:00:00 2001 From: Budimir Markovic Date: Thu, 24 Aug 2023 01:49:05 -0700 Subject: [PATCH 0890/2093] net/sched: sch_hfsc: Ensure inner classes have fsc curve [ Upstream commit b3d26c5702c7d6c45456326e56d2ccf3f103e60f ] HFSC assumes that inner classes have an fsc curve, but it is currently possible for classes without an fsc curve to become parents. This leads to bugs including a use-after-free. Don't allow non-root classes without HFSC_FSC to become parents. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Budimir Markovic Signed-off-by: Budimir Markovic Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230824084905.422-1-markovicbudimir@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_hfsc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 70b0c5873d32..61d52594ff6d 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1012,6 +1012,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (parent == NULL) return -ENOENT; } + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC"); + return -EINVAL; + } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; From 45107f9ca8633b4475c17e8a767067a880a92ab2 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 24 Aug 2023 09:50:59 -0700 Subject: [PATCH 0891/2093] netrom: Deny concurrent connect(). [ Upstream commit c2f8fd7949603efb03908e05abbf7726748c8de3 ] syzkaller reported null-ptr-deref [0] related to AF_NETROM. This is another self-accept issue from the strace log. [1] syz-executor creates an AF_NETROM socket and calls connect(), which is blocked at that time. Then, sk->sk_state is TCP_SYN_SENT and sock->state is SS_CONNECTING. [pid 5059] socket(AF_NETROM, SOCK_SEQPACKET, 0) = 4 [pid 5059] connect(4, {sa_family=AF_NETROM, sa_data="..." Another thread calls connect() concurrently, which finally fails with -EINVAL. However, the problem here is the socket state is reset even while the first connect() is blocked. [pid 5060] connect(4, NULL, 0 [pid 5060] <... connect resumed>) = -1 EINVAL (Invalid argument) As sk->state is TCP_CLOSE and sock->state is SS_UNCONNECTED, the following listen() succeeds. Then, the first connect() looks up itself as a listener and puts skb into the queue with skb->sk itself. As a result, the next accept() gets another FD of itself as 3, and the first connect() finishes. [pid 5060] listen(4, 0 [pid 5060] <... listen resumed>) = 0 [pid 5060] accept(4, NULL, NULL [pid 5060] <... accept resumed>) = 3 [pid 5059] <... connect resumed>) = 0 Then, accept4() is called but blocked, which causes the general protection fault later. [pid 5059] accept4(4, NULL, 0x20000400, SOCK_NONBLOCK After that, another self-accept occurs by accept() and writev(). [pid 5060] accept(4, NULL, NULL [pid 5061] writev(3, [{iov_base=...}] [pid 5061] <... writev resumed>) = 99 [pid 5060] <... accept resumed>) = 6 Finally, the leader thread close()s all FDs. Since the three FDs reference the same socket, nr_release() does the cleanup for it three times, and the remaining accept4() causes the following fault. [pid 5058] close(3) = 0 [pid 5058] close(4) = 0 [pid 5058] close(5) = -1 EBADF (Bad file descriptor) [pid 5058] close(6) = 0 [pid 5058] <... exit_group resumed>) = ? [ 83.456055][ T5059] general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN To avoid the issue, we need to return an error for connect() if another connect() is in progress, as done in __inet_stream_connect(). [0]: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] CPU: 0 PID: 5059 Comm: syz-executor.0 Not tainted 6.5.0-rc5-syzkaller-00194-gace0ab3a4b54 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 RIP: 0010:__lock_acquire+0x109/0x5de0 kernel/locking/lockdep.c:5012 Code: 45 85 c9 0f 84 cc 0e 00 00 44 8b 05 11 6e 23 0b 45 85 c0 0f 84 be 0d 00 00 48 ba 00 00 00 00 00 fc ff df 4c 89 d1 48 c1 e9 03 <80> 3c 11 00 0f 85 e8 40 00 00 49 81 3a a0 69 48 90 0f 84 96 0d 00 RSP: 0018:ffffc90003d6f9e0 EFLAGS: 00010006 RAX: ffff8880244c8000 RBX: 1ffff920007adf6c RCX: 0000000000000003 RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000018 RBP: 0000000000000001 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000018 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f51d519a6c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f51d5158d58 CR3: 000000002943f000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: lock_acquire kernel/locking/lockdep.c:5761 [inline] lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x3a/0x50 kernel/locking/spinlock.c:162 prepare_to_wait+0x47/0x380 kernel/sched/wait.c:269 nr_accept+0x20d/0x650 net/netrom/af_netrom.c:798 do_accept+0x3a6/0x570 net/socket.c:1872 __sys_accept4_file net/socket.c:1913 [inline] __sys_accept4+0x99/0x120 net/socket.c:1943 __do_sys_accept4 net/socket.c:1954 [inline] __se_sys_accept4 net/socket.c:1951 [inline] __x64_sys_accept4+0x96/0x100 net/socket.c:1951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f51d447cae9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f51d519a0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000120 RAX: ffffffffffffffda RBX: 00007f51d459bf80 RCX: 00007f51d447cae9 RDX: 0000000020000400 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007f51d44c847a R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000800 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007f51d459bf80 R15: 00007ffc25c34e48 Link: https://syzkaller.appspot.com/text?tag=CrashLog&x=152cdb63a80000 [1] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+666c97e4686410e79649@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=666c97e4686410e79649 Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/netrom/af_netrom.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 5a4cb796150f..ec5747969f96 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -660,6 +660,11 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, goto out_release; } + if (sock->state == SS_CONNECTING) { + err = -EALREADY; + goto out_release; + } + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; From aa449fa41e1044fa542b0026d5855886eb7c9b89 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 15 Jun 2023 17:28:17 +0200 Subject: [PATCH 0892/2093] drm/bridge: tc358764: Fix debug print parameter order [ Upstream commit 7f947be02aab5b154427cb5b0fffe858fc387b02 ] The debug print parameters were swapped in the output and they were printed as decimal values, both the hardware address and the value. Update the debug print to print the parameters in correct order, and use hexadecimal print for both address and value. Fixes: f38b7cca6d0e ("drm/bridge: tc358764: Add DSI to LVDS bridge driver") Signed-off-by: Marek Vasut Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230615152817.359420-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358764.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/tc358764.c b/drivers/gpu/drm/bridge/tc358764.c index 53259c12d777..e0f583a88789 100644 --- a/drivers/gpu/drm/bridge/tc358764.c +++ b/drivers/gpu/drm/bridge/tc358764.c @@ -176,7 +176,7 @@ static void tc358764_read(struct tc358764 *ctx, u16 addr, u32 *val) if (ret >= 0) le32_to_cpus(val); - dev_dbg(ctx->dev, "read: %d, addr: %d\n", addr, *val); + dev_dbg(ctx->dev, "read: addr=0x%04x data=0x%08x\n", addr, *val); } static void tc358764_write(struct tc358764 *ctx, u16 addr, u32 val) From 25193037e08339bcb01026f739880a1d3e7873d9 Mon Sep 17 00:00:00 2001 From: Phil Elwell Date: Wed, 21 Jun 2023 16:32:29 +0100 Subject: [PATCH 0893/2093] ASoC: cs43130: Fix numerator/denominator mixup [ Upstream commit a9e7c964cea4fb1541cc81a11d1b2fd135f4cf38 ] In converting to using the standard u16_fract type, commit [1] made the obvious mistake and failed to take account of the difference in numerator and denominator ordering, breaking all uses of the cs43130 codec. Fix it. [1] commit e14bd35ef446 ("ASoC: cs43130: Re-use generic struct u16_fract") Fixes: e14bd35ef446 ("ASoC: cs43130: Re-use generic struct u16_fract") Signed-off-by: Phil Elwell Reviewed-by: Andy Shevchenko Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20230621153229.1944132-1-phil@raspberrypi.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/cs43130.h | 138 ++++++++++++++++++------------------- 1 file changed, 69 insertions(+), 69 deletions(-) diff --git a/sound/soc/codecs/cs43130.h b/sound/soc/codecs/cs43130.h index 1dd893674313..90e8895275e7 100644 --- a/sound/soc/codecs/cs43130.h +++ b/sound/soc/codecs/cs43130.h @@ -381,88 +381,88 @@ struct cs43130_clk_gen { /* frm_size = 16 */ static const struct cs43130_clk_gen cs43130_16_clk_gen[] = { - { 22579200, 32000, .v = { 441, 10, }, }, - { 22579200, 44100, .v = { 32, 1, }, }, - { 22579200, 48000, .v = { 147, 5, }, }, - { 22579200, 88200, .v = { 16, 1, }, }, - { 22579200, 96000, .v = { 147, 10, }, }, - { 22579200, 176400, .v = { 8, 1, }, }, - { 22579200, 192000, .v = { 147, 20, }, }, - { 22579200, 352800, .v = { 4, 1, }, }, - { 22579200, 384000, .v = { 147, 40, }, }, - { 24576000, 32000, .v = { 48, 1, }, }, - { 24576000, 44100, .v = { 5120, 147, }, }, - { 24576000, 48000, .v = { 32, 1, }, }, - { 24576000, 88200, .v = { 2560, 147, }, }, - { 24576000, 96000, .v = { 16, 1, }, }, - { 24576000, 176400, .v = { 1280, 147, }, }, - { 24576000, 192000, .v = { 8, 1, }, }, - { 24576000, 352800, .v = { 640, 147, }, }, - { 24576000, 384000, .v = { 4, 1, }, }, + { 22579200, 32000, .v = { 10, 441, }, }, + { 22579200, 44100, .v = { 1, 32, }, }, + { 22579200, 48000, .v = { 5, 147, }, }, + { 22579200, 88200, .v = { 1, 16, }, }, + { 22579200, 96000, .v = { 10, 147, }, }, + { 22579200, 176400, .v = { 1, 8, }, }, + { 22579200, 192000, .v = { 20, 147, }, }, + { 22579200, 352800, .v = { 1, 4, }, }, + { 22579200, 384000, .v = { 40, 147, }, }, + { 24576000, 32000, .v = { 1, 48, }, }, + { 24576000, 44100, .v = { 147, 5120, }, }, + { 24576000, 48000, .v = { 1, 32, }, }, + { 24576000, 88200, .v = { 147, 2560, }, }, + { 24576000, 96000, .v = { 1, 16, }, }, + { 24576000, 176400, .v = { 147, 1280, }, }, + { 24576000, 192000, .v = { 1, 8, }, }, + { 24576000, 352800, .v = { 147, 640, }, }, + { 24576000, 384000, .v = { 1, 4, }, }, }; /* frm_size = 32 */ static const struct cs43130_clk_gen cs43130_32_clk_gen[] = { - { 22579200, 32000, .v = { 441, 20, }, }, - { 22579200, 44100, .v = { 16, 1, }, }, - { 22579200, 48000, .v = { 147, 10, }, }, - { 22579200, 88200, .v = { 8, 1, }, }, - { 22579200, 96000, .v = { 147, 20, }, }, - { 22579200, 176400, .v = { 4, 1, }, }, - { 22579200, 192000, .v = { 147, 40, }, }, - { 22579200, 352800, .v = { 2, 1, }, }, - { 22579200, 384000, .v = { 147, 80, }, }, - { 24576000, 32000, .v = { 24, 1, }, }, - { 24576000, 44100, .v = { 2560, 147, }, }, - { 24576000, 48000, .v = { 16, 1, }, }, - { 24576000, 88200, .v = { 1280, 147, }, }, - { 24576000, 96000, .v = { 8, 1, }, }, - { 24576000, 176400, .v = { 640, 147, }, }, - { 24576000, 192000, .v = { 4, 1, }, }, - { 24576000, 352800, .v = { 320, 147, }, }, - { 24576000, 384000, .v = { 2, 1, }, }, + { 22579200, 32000, .v = { 20, 441, }, }, + { 22579200, 44100, .v = { 1, 16, }, }, + { 22579200, 48000, .v = { 10, 147, }, }, + { 22579200, 88200, .v = { 1, 8, }, }, + { 22579200, 96000, .v = { 20, 147, }, }, + { 22579200, 176400, .v = { 1, 4, }, }, + { 22579200, 192000, .v = { 40, 147, }, }, + { 22579200, 352800, .v = { 1, 2, }, }, + { 22579200, 384000, .v = { 80, 147, }, }, + { 24576000, 32000, .v = { 1, 24, }, }, + { 24576000, 44100, .v = { 147, 2560, }, }, + { 24576000, 48000, .v = { 1, 16, }, }, + { 24576000, 88200, .v = { 147, 1280, }, }, + { 24576000, 96000, .v = { 1, 8, }, }, + { 24576000, 176400, .v = { 147, 640, }, }, + { 24576000, 192000, .v = { 1, 4, }, }, + { 24576000, 352800, .v = { 147, 320, }, }, + { 24576000, 384000, .v = { 1, 2, }, }, }; /* frm_size = 48 */ static const struct cs43130_clk_gen cs43130_48_clk_gen[] = { - { 22579200, 32000, .v = { 147, 100, }, }, - { 22579200, 44100, .v = { 32, 3, }, }, - { 22579200, 48000, .v = { 49, 5, }, }, - { 22579200, 88200, .v = { 16, 3, }, }, - { 22579200, 96000, .v = { 49, 10, }, }, - { 22579200, 176400, .v = { 8, 3, }, }, - { 22579200, 192000, .v = { 49, 20, }, }, - { 22579200, 352800, .v = { 4, 3, }, }, - { 22579200, 384000, .v = { 49, 40, }, }, - { 24576000, 32000, .v = { 16, 1, }, }, - { 24576000, 44100, .v = { 5120, 441, }, }, - { 24576000, 48000, .v = { 32, 3, }, }, - { 24576000, 88200, .v = { 2560, 441, }, }, - { 24576000, 96000, .v = { 16, 3, }, }, - { 24576000, 176400, .v = { 1280, 441, }, }, - { 24576000, 192000, .v = { 8, 3, }, }, - { 24576000, 352800, .v = { 640, 441, }, }, - { 24576000, 384000, .v = { 4, 3, }, }, + { 22579200, 32000, .v = { 100, 147, }, }, + { 22579200, 44100, .v = { 3, 32, }, }, + { 22579200, 48000, .v = { 5, 49, }, }, + { 22579200, 88200, .v = { 3, 16, }, }, + { 22579200, 96000, .v = { 10, 49, }, }, + { 22579200, 176400, .v = { 3, 8, }, }, + { 22579200, 192000, .v = { 20, 49, }, }, + { 22579200, 352800, .v = { 3, 4, }, }, + { 22579200, 384000, .v = { 40, 49, }, }, + { 24576000, 32000, .v = { 1, 16, }, }, + { 24576000, 44100, .v = { 441, 5120, }, }, + { 24576000, 48000, .v = { 3, 32, }, }, + { 24576000, 88200, .v = { 441, 2560, }, }, + { 24576000, 96000, .v = { 3, 16, }, }, + { 24576000, 176400, .v = { 441, 1280, }, }, + { 24576000, 192000, .v = { 3, 8, }, }, + { 24576000, 352800, .v = { 441, 640, }, }, + { 24576000, 384000, .v = { 3, 4, }, }, }; /* frm_size = 64 */ static const struct cs43130_clk_gen cs43130_64_clk_gen[] = { - { 22579200, 32000, .v = { 441, 40, }, }, - { 22579200, 44100, .v = { 8, 1, }, }, - { 22579200, 48000, .v = { 147, 20, }, }, - { 22579200, 88200, .v = { 4, 1, }, }, - { 22579200, 96000, .v = { 147, 40, }, }, - { 22579200, 176400, .v = { 2, 1, }, }, - { 22579200, 192000, .v = { 147, 80, }, }, + { 22579200, 32000, .v = { 40, 441, }, }, + { 22579200, 44100, .v = { 1, 8, }, }, + { 22579200, 48000, .v = { 20, 147, }, }, + { 22579200, 88200, .v = { 1, 4, }, }, + { 22579200, 96000, .v = { 40, 147, }, }, + { 22579200, 176400, .v = { 1, 2, }, }, + { 22579200, 192000, .v = { 80, 147, }, }, { 22579200, 352800, .v = { 1, 1, }, }, - { 24576000, 32000, .v = { 12, 1, }, }, - { 24576000, 44100, .v = { 1280, 147, }, }, - { 24576000, 48000, .v = { 8, 1, }, }, - { 24576000, 88200, .v = { 640, 147, }, }, - { 24576000, 96000, .v = { 4, 1, }, }, - { 24576000, 176400, .v = { 320, 147, }, }, - { 24576000, 192000, .v = { 2, 1, }, }, - { 24576000, 352800, .v = { 160, 147, }, }, + { 24576000, 32000, .v = { 1, 12, }, }, + { 24576000, 44100, .v = { 147, 1280, }, }, + { 24576000, 48000, .v = { 1, 8, }, }, + { 24576000, 88200, .v = { 147, 640, }, }, + { 24576000, 96000, .v = { 1, 4, }, }, + { 24576000, 176400, .v = { 147, 320, }, }, + { 24576000, 192000, .v = { 1, 2, }, }, + { 24576000, 352800, .v = { 147, 160, }, }, { 24576000, 384000, .v = { 1, 1, }, }, }; From 622789ebe197ed58702051432d545c628ac04509 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Fri, 30 Jun 2023 19:08:18 +0800 Subject: [PATCH 0894/2093] quota: factor out dquot_write_dquot() [ Upstream commit 024128477809f8073d870307c8157b8826ebfd08 ] Refactor out dquot_write_dquot() to reduce duplicate code. Signed-off-by: Baokun Li Signed-off-by: Jan Kara Message-Id: <20230630110822.3881712-2-libaokun1@huawei.com> Stable-dep-of: dabc8b207566 ("quota: fix dqput() to follow the guarantees dquot_srcu should provide") Signed-off-by: Sasha Levin --- fs/quota/dquot.c | 39 ++++++++++++++++----------------------- 1 file changed, 16 insertions(+), 23 deletions(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 46dca88d89c3..5541960ad025 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -628,6 +628,18 @@ int dquot_scan_active(struct super_block *sb, } EXPORT_SYMBOL(dquot_scan_active); +static inline int dquot_write_dquot(struct dquot *dquot) +{ + int ret = dquot->dq_sb->dq_op->write_dquot(dquot); + if (ret < 0) { + quota_error(dquot->dq_sb, "Can't write quota structure " + "(error %d). Quota may get out of sync!", ret); + /* Clear dirty bit anyway to avoid infinite loop. */ + clear_dquot_dirty(dquot); + } + return ret; +} + /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { @@ -658,16 +670,9 @@ int dquot_writeback_dquots(struct super_block *sb, int type) * use count */ dqgrab(dquot); spin_unlock(&dq_list_lock); - err = sb->dq_op->write_dquot(dquot); - if (err) { - /* - * Clear dirty bit anyway to avoid infinite - * loop here. - */ - clear_dquot_dirty(dquot); - if (!ret) - ret = err; - } + err = dquot_write_dquot(dquot); + if (err && !ret) + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } @@ -765,8 +770,6 @@ static struct shrinker dqcache_shrinker = { */ void dqput(struct dquot *dquot) { - int ret; - if (!dquot) return; #ifdef CONFIG_QUOTA_DEBUG @@ -794,17 +797,7 @@ void dqput(struct dquot *dquot) if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); /* Commit dquot before releasing */ - ret = dquot->dq_sb->dq_op->write_dquot(dquot); - if (ret < 0) { - quota_error(dquot->dq_sb, "Can't write quota structure" - " (error %d). Quota may get out of sync!", - ret); - /* - * We clear dirty bit anyway, so that we avoid - * infinite loop here - */ - clear_dquot_dirty(dquot); - } + dquot_write_dquot(dquot); goto we_slept; } if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { From fdcc50d506f3703ea6b09005db657942c3a50361 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Fri, 30 Jun 2023 19:08:19 +0800 Subject: [PATCH 0895/2093] quota: rename dquot_active() to inode_quota_active() [ Upstream commit 4b9bdfa16535de8f49bf954aeed0f525ee2fc322 ] Now we have a helper function dquot_dirty() to determine if dquot has DQ_MOD_B bit. dquot_active() can easily be misunderstood as a helper function to determine if dquot has DQ_ACTIVE_B bit. So we avoid this by renaming it to inode_quota_active() and later on we will add the helper function dquot_active() to determine if dquot has DQ_ACTIVE_B bit. Signed-off-by: Baokun Li Signed-off-by: Jan Kara Message-Id: <20230630110822.3881712-3-libaokun1@huawei.com> Stable-dep-of: dabc8b207566 ("quota: fix dqput() to follow the guarantees dquot_srcu should provide") Signed-off-by: Sasha Levin --- fs/quota/dquot.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 5541960ad025..f9f0610b504d 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1418,7 +1418,7 @@ static int info_bdq_free(struct dquot *dquot, qsize_t space) return QUOTA_NL_NOWARN; } -static int dquot_active(const struct inode *inode) +static int inode_quota_active(const struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -1441,7 +1441,7 @@ static int __dquot_initialize(struct inode *inode, int type) qsize_t rsv; int ret = 0; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; dquots = i_dquot(inode); @@ -1549,7 +1549,7 @@ bool dquot_initialize_needed(struct inode *inode) struct dquot **dquots; int i; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return false; dquots = i_dquot(inode); @@ -1660,7 +1660,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int reserve = flags & DQUOT_SPACE_RESERVE; struct dquot **dquots; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; @@ -1730,7 +1730,7 @@ int dquot_alloc_inode(struct inode *inode) struct dquot_warn warn[MAXQUOTAS]; struct dquot * const *dquots; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; @@ -1773,7 +1773,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) struct dquot **dquots; int cnt, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); @@ -1815,7 +1815,7 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) struct dquot **dquots; int cnt, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); @@ -1859,7 +1859,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) struct dquot **dquots; int reserve = flags & DQUOT_SPACE_RESERVE, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; @@ -1914,7 +1914,7 @@ void dquot_free_inode(struct inode *inode) struct dquot * const *dquots; int index; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return; dquots = i_dquot(inode); @@ -2086,7 +2086,7 @@ int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode, struct super_block *sb = inode->i_sb; int ret; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; if (i_uid_needs_update(mnt_userns, iattr, inode)) { From d57af071cf408c08a1c9df1545d043e42ef6b19c Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Fri, 30 Jun 2023 19:08:20 +0800 Subject: [PATCH 0896/2093] quota: add new helper dquot_active() [ Upstream commit 33bcfafc48cb186bc4bbcea247feaa396594229e ] Add new helper function dquot_active() to make the code more concise. Signed-off-by: Baokun Li Signed-off-by: Jan Kara Message-Id: <20230630110822.3881712-4-libaokun1@huawei.com> Stable-dep-of: dabc8b207566 ("quota: fix dqput() to follow the guarantees dquot_srcu should provide") Signed-off-by: Sasha Levin --- fs/quota/dquot.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f9f0610b504d..e4a19a893d85 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -336,6 +336,11 @@ static void wait_on_dquot(struct dquot *dquot) mutex_unlock(&dquot->dq_lock); } +static inline int dquot_active(struct dquot *dquot) +{ + return test_bit(DQ_ACTIVE_B, &dquot->dq_flags); +} + static inline int dquot_dirty(struct dquot *dquot) { return test_bit(DQ_MOD_B, &dquot->dq_flags); @@ -351,14 +356,14 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) { int ret = 1; - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (!dquot_active(dquot)) return 0; if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags); /* If quota is dirty already, we don't have to acquire dq_list_lock */ - if (test_bit(DQ_MOD_B, &dquot->dq_flags)) + if (dquot_dirty(dquot)) return 1; spin_lock(&dq_list_lock); @@ -440,7 +445,7 @@ int dquot_acquire(struct dquot *dquot) smp_mb__before_atomic(); set_bit(DQ_READ_B, &dquot->dq_flags); /* Instantiate dquot if needed */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) { + if (!dquot_active(dquot) && !dquot->dq_off) { ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); /* Write the info if needed */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { @@ -482,7 +487,7 @@ int dquot_commit(struct dquot *dquot) goto out_lock; /* Inactive dquot can be only if there was error during read/init * => we have better not writing it */ - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (dquot_active(dquot)) ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); else ret = -EIO; @@ -597,7 +602,7 @@ int dquot_scan_active(struct super_block *sb, spin_lock(&dq_list_lock); list_for_each_entry(dquot, &inuse_list, dq_inuse) { - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (!dquot_active(dquot)) continue; if (dquot->dq_sb != sb) continue; @@ -612,7 +617,7 @@ int dquot_scan_active(struct super_block *sb, * outstanding call and recheck the DQ_ACTIVE_B after that. */ wait_on_dquot(dquot); - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (dquot_active(dquot)) { ret = fn(dquot, priv); if (ret < 0) goto out; @@ -663,7 +668,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dquot = list_first_entry(&dirty, struct dquot, dq_dirty); - WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); + WARN_ON(!dquot_active(dquot)); /* Now we have active dquot from which someone is * holding reference so we can safely just increase @@ -800,7 +805,7 @@ void dqput(struct dquot *dquot) dquot_write_dquot(dquot); goto we_slept; } - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (dquot_active(dquot)) { spin_unlock(&dq_list_lock); dquot->dq_sb->dq_op->release_dquot(dquot); goto we_slept; @@ -901,7 +906,7 @@ struct dquot *dqget(struct super_block *sb, struct kqid qid) * already finished or it will be canceled due to dq_count > 1 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (!dquot_active(dquot)) { int err; err = sb->dq_op->acquire_dquot(dquot); From 3027e200dd58d5b437f16634dbbd355b29ffe0a6 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Fri, 30 Jun 2023 19:08:21 +0800 Subject: [PATCH 0897/2093] quota: fix dqput() to follow the guarantees dquot_srcu should provide [ Upstream commit dabc8b20756601b9e1cc85a81d47d3f98ed4d13a ] The dquot_mark_dquot_dirty() using dquot references from the inode should be protected by dquot_srcu. quota_off code takes care to call synchronize_srcu(&dquot_srcu) to not drop dquot references while they are used by other users. But dquot_transfer() breaks this assumption. We call dquot_transfer() to drop the last reference of dquot and add it to free_dquots, but there may still be other users using the dquot at this time, as shown in the function graph below: cpu1 cpu2 _________________|_________________ wb_do_writeback CHOWN(1) ... ext4_da_update_reserve_space dquot_claim_block ... dquot_mark_dquot_dirty // try to dirty old quota test_bit(DQ_ACTIVE_B, &dquot->dq_flags) // still ACTIVE if (test_bit(DQ_MOD_B, &dquot->dq_flags)) // test no dirty, wait dq_list_lock ... dquot_transfer __dquot_transfer dqput_all(transfer_from) // rls old dquot dqput // last dqput dquot_release clear_bit(DQ_ACTIVE_B, &dquot->dq_flags) atomic_dec(&dquot->dq_count) put_dquot_last(dquot) list_add_tail(&dquot->dq_free, &free_dquots) // add the dquot to free_dquots if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags)) add dqi_dirty_list // add released dquot to dirty_list This can cause various issues, such as dquot being destroyed by dqcache_shrink_scan() after being added to free_dquots, which can trigger a UAF in dquot_mark_dquot_dirty(); or after dquot is added to free_dquots and then to dirty_list, it is added to free_dquots again after dquot_writeback_dquots() is executed, which causes the free_dquots list to be corrupted and triggers a UAF when dqcache_shrink_scan() is called for freeing dquot twice. As Honza said, we need to fix dquot_transfer() to follow the guarantees dquot_srcu should provide. But calling synchronize_srcu() directly from dquot_transfer() is too expensive (and mostly unnecessary). So we add dquot whose last reference should be dropped to the new global dquot list releasing_dquots, and then queue work item which would call synchronize_srcu() and after that perform the final cleanup of all the dquots on releasing_dquots. Fixes: 4580b30ea887 ("quota: Do not dirty bad dquots") Suggested-by: Jan Kara Signed-off-by: Baokun Li Signed-off-by: Jan Kara Message-Id: <20230630110822.3881712-5-libaokun1@huawei.com> Signed-off-by: Sasha Levin --- fs/quota/dquot.c | 96 +++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 78 insertions(+), 18 deletions(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index e4a19a893d85..53b65c5300fd 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -225,13 +225,22 @@ static void put_quota_format(struct quota_format_type *fmt) /* * Dquot List Management: - * The quota code uses four lists for dquot management: the inuse_list, - * free_dquots, dqi_dirty_list, and dquot_hash[] array. A single dquot - * structure may be on some of those lists, depending on its current state. + * The quota code uses five lists for dquot management: the inuse_list, + * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array. + * A single dquot structure may be on some of those lists, depending on + * its current state. * * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * + * When the last reference of a dquot will be dropped, the dquot will be + * added to releasing_dquots. We'd then queue work item which would call + * synchronize_srcu() and after that perform the final cleanup of all the + * dquots on the list. Both releasing_dquots and free_dquots use the + * dq_free list_head in the dquot struct. When a dquot is removed from + * releasing_dquots, a reference count is always subtracted, and if + * dq_count == 0 at that point, the dquot will be added to the free_dquots. + * * Unused dquots (dq_count == 0) are added to the free_dquots list when freed, * and this list is searched whenever we need an available dquot. Dquots are * removed from the list as soon as they are used again, and @@ -250,6 +259,7 @@ static void put_quota_format(struct quota_format_type *fmt) static LIST_HEAD(inuse_list); static LIST_HEAD(free_dquots); +static LIST_HEAD(releasing_dquots); static unsigned int dq_hash_bits, dq_hash_mask; static struct hlist_head *dquot_hash; @@ -260,6 +270,9 @@ static qsize_t inode_get_rsv_space(struct inode *inode); static qsize_t __inode_get_rsv_space(struct inode *inode); static int __dquot_initialize(struct inode *inode, int type); +static void quota_release_workfn(struct work_struct *work); +static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn); + static inline unsigned int hashfn(const struct super_block *sb, struct kqid qid) { @@ -305,12 +318,18 @@ static inline void put_dquot_last(struct dquot *dquot) dqstats_inc(DQST_FREE_DQUOTS); } +static inline void put_releasing_dquots(struct dquot *dquot) +{ + list_add_tail(&dquot->dq_free, &releasing_dquots); +} + static inline void remove_free_dquot(struct dquot *dquot) { if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); - dqstats_dec(DQST_FREE_DQUOTS); + if (!atomic_read(&dquot->dq_count)) + dqstats_dec(DQST_FREE_DQUOTS); } static inline void put_inuse(struct dquot *dquot) @@ -552,6 +571,8 @@ static void invalidate_dquots(struct super_block *sb, int type) struct dquot *dquot, *tmp; restart: + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) { if (dquot->dq_sb != sb) @@ -560,6 +581,12 @@ static void invalidate_dquots(struct super_block *sb, int type) continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { + /* dquot in releasing_dquots, flush and retry */ + if (!list_empty(&dquot->dq_free)) { + spin_unlock(&dq_list_lock); + goto restart; + } + atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* @@ -770,6 +797,49 @@ static struct shrinker dqcache_shrinker = { .seeks = DEFAULT_SEEKS, }; +/* + * Safely release dquot and put reference to dquot. + */ +static void quota_release_workfn(struct work_struct *work) +{ + struct dquot *dquot; + struct list_head rls_head; + + spin_lock(&dq_list_lock); + /* Exchange the list head to avoid livelock. */ + list_replace_init(&releasing_dquots, &rls_head); + spin_unlock(&dq_list_lock); + +restart: + synchronize_srcu(&dquot_srcu); + spin_lock(&dq_list_lock); + while (!list_empty(&rls_head)) { + dquot = list_first_entry(&rls_head, struct dquot, dq_free); + /* Dquot got used again? */ + if (atomic_read(&dquot->dq_count) > 1) { + remove_free_dquot(dquot); + atomic_dec(&dquot->dq_count); + continue; + } + if (dquot_dirty(dquot)) { + spin_unlock(&dq_list_lock); + /* Commit dquot before releasing */ + dquot_write_dquot(dquot); + goto restart; + } + if (dquot_active(dquot)) { + spin_unlock(&dq_list_lock); + dquot->dq_sb->dq_op->release_dquot(dquot); + goto restart; + } + /* Dquot is inactive and clean, now move it to free list */ + remove_free_dquot(dquot); + atomic_dec(&dquot->dq_count); + put_dquot_last(dquot); + } + spin_unlock(&dq_list_lock); +} + /* * Put reference to dquot */ @@ -786,7 +856,7 @@ void dqput(struct dquot *dquot) } #endif dqstats_inc(DQST_DROPS); -we_slept: + spin_lock(&dq_list_lock); if (atomic_read(&dquot->dq_count) > 1) { /* We have more than one user... nothing to do */ @@ -798,25 +868,15 @@ void dqput(struct dquot *dquot) spin_unlock(&dq_list_lock); return; } + /* Need to release dquot? */ - if (dquot_dirty(dquot)) { - spin_unlock(&dq_list_lock); - /* Commit dquot before releasing */ - dquot_write_dquot(dquot); - goto we_slept; - } - if (dquot_active(dquot)) { - spin_unlock(&dq_list_lock); - dquot->dq_sb->dq_op->release_dquot(dquot); - goto we_slept; - } - atomic_dec(&dquot->dq_count); #ifdef CONFIG_QUOTA_DEBUG /* sanity check */ BUG_ON(!list_empty(&dquot->dq_free)); #endif - put_dquot_last(dquot); + put_releasing_dquots(dquot); spin_unlock(&dq_list_lock); + queue_delayed_work(system_unbound_wq, "a_release_work, 1); } EXPORT_SYMBOL(dqput); From a9fa161b8356a16048e77ad02acfb339d247d6d3 Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Thu, 3 Nov 2022 22:29:31 -0400 Subject: [PATCH 0898/2093] drm/amd/display: Do not set drr on pipe commit [ Upstream commit e101bf95ea87ccc03ac2f48dfc0757c6364ff3c7 ] [WHY] Writing to DRR registers such as OTG_V_TOTAL_MIN on the same frame as a pipe commit can cause underflow. [HOW] Move DMUB p-state delegate into optimze_bandwidth; enabling FAMS sets optimized_required. This change expects that Freesync requests are blocked when optimized_required is true. Reviewed-by: Rodrigo Siqueira Signed-off-by: Wesley Chalmers Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 6 ++++++ drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c | 7 +++++++ 2 files changed, 13 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 4ef632864948..21fae818ca28 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2032,6 +2032,12 @@ void dcn20_optimize_bandwidth( if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + dc_dmub_srv_p_state_delegate(dc, + true, context); + context->bw_ctx.bw.dcn.clk.p_state_change_support = true; + } + dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index a1b312483d7f..c97d3e81a83d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -987,11 +987,18 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, void dcn30_prepare_bandwidth(struct dc *dc, struct dc_state *context) { + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + dc->optimized_required = true; + context->bw_ctx.bw.dcn.clk.p_state_change_support = false; + } + if (dc->clk_mgr->dc_mode_softmax_enabled) if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 && context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); + + dc_dmub_srv_p_state_delegate(dc, false, context); } From c2c6dfc04237ccca464f20aae5688859a318c602 Mon Sep 17 00:00:00 2001 From: Sui Jingfeng Date: Sun, 9 Jul 2023 18:05:14 +0800 Subject: [PATCH 0899/2093] drm/hyperv: Fix a compilation issue because of not including screen_info.h [ Upstream commit 8d1077cf2e43b15fefd76ebec2b71541eb27ef2c ] Fixes the following build errors on arm64: drivers/video/fbdev/hyperv_fb.c: In function 'hvfb_getmem': >> drivers/video/fbdev/hyperv_fb.c:1033:24: error: 'screen_info' undeclared (first use in this function) 1033 | base = screen_info.lfb_base; | ^~~~~~~~~~~ drivers/video/fbdev/hyperv_fb.c:1033:24: note: each undeclared identifier is reported only once for each function it appears in >> drivers/gpu/drm/hyperv/hyperv_drm_drv.c:75:54: error: 'screen_info' undeclared (first use in this function) 75 | drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, | ^~~~~~~~~~~ drivers/gpu/drm/hyperv/hyperv_drm_drv.c:75:54: note: each undeclared identifier is reported only once for each function it appears in Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202307090823.nxnT8Kk5-lkp@intel.com/ Fixes: 81d2393485f0 ("fbdev/hyperv-fb: Do not set struct fb_info.apertures") Fixes: 8b0d13545b09 ("efi: Do not include from EFI header") Signed-off-by: Sui Jingfeng Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230709100514.703759-1-suijingfeng@loongson.cn Signed-off-by: Sasha Levin --- drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index 29ee0814bccc..68050409dd26 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include From 7bdeb7679f4cd30a15c172ee8fb2520c82463aa2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 30 Jun 2023 21:48:36 -0700 Subject: [PATCH 0900/2093] ASoC: stac9766: fix build errors with REGMAP_AC97 [ Upstream commit c70064b96f509daa78f57992aeabcf274fb2fed4 ] Select REGMAP_AC97 to fix these build errors: ERROR: modpost: "regmap_ac97_default_volatile" [sound/soc/codecs/snd-soc-stac9766.ko] undefined! ERROR: modpost: "__regmap_init_ac97" [sound/soc/codecs/snd-soc-stac9766.ko] undefined! Fixes: 6bbf787bb70c ("ASoC: stac9766: Convert to regmap") Signed-off-by: Randy Dunlap Cc: Lars-Peter Clausen Cc: Mark Brown Cc: Liam Girdwood Cc: alsa-devel@alsa-project.org Link: https://lore.kernel.org/r/20230701044836.18789-1-rdunlap@infradead.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 965ae55fa160..0904827e2f3d 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1552,6 +1552,7 @@ config SND_SOC_STA529 config SND_SOC_STAC9766 tristate depends on SND_SOC_AC97_BUS + select REGMAP_AC97 config SND_SOC_STI_SAS tristate "codec Audio support for STI SAS codec" From fb4a774a662790cb39db19ece6f6c6fe94b969e9 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Mon, 29 May 2023 10:41:15 +0200 Subject: [PATCH 0901/2093] soc: qcom: ocmem: Add OCMEM hardware version print [ Upstream commit e81a16e77259294cd4ff0a9c1fbe5aa0e311a47d ] It might be useful to know what hardware version of the OCMEM block the SoC contains. Add a debug print for that. Signed-off-by: Luca Weiss Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230509-ocmem-hwver-v3-1-e51f3488e0f4@z3ntu.xyz Stable-dep-of: a7b484b1c933 ("soc: qcom: ocmem: Fix NUM_PORTS & NUM_MACROS macros") Signed-off-by: Sasha Levin --- drivers/soc/qcom/ocmem.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index c92d26b73e6f..7197d9fe0946 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -76,6 +76,10 @@ struct ocmem { #define OCMEM_REG_GFX_MPU_START 0x00001004 #define OCMEM_REG_GFX_MPU_END 0x00001008 +#define OCMEM_HW_VERSION_MAJOR(val) FIELD_GET(GENMASK(31, 28), val) +#define OCMEM_HW_VERSION_MINOR(val) FIELD_GET(GENMASK(27, 16), val) +#define OCMEM_HW_VERSION_STEP(val) FIELD_GET(GENMASK(15, 0), val) + #define OCMEM_HW_PROFILE_NUM_PORTS(val) FIELD_PREP(0x0000000f, (val)) #define OCMEM_HW_PROFILE_NUM_MACROS(val) FIELD_PREP(0x00003f00, (val)) @@ -355,6 +359,12 @@ static int ocmem_dev_probe(struct platform_device *pdev) } } + reg = ocmem_read(ocmem, OCMEM_REG_HW_VERSION); + dev_dbg(dev, "OCMEM hardware version: %lu.%lu.%lu\n", + OCMEM_HW_VERSION_MAJOR(reg), + OCMEM_HW_VERSION_MINOR(reg), + OCMEM_HW_VERSION_STEP(reg)); + reg = ocmem_read(ocmem, OCMEM_REG_HW_PROFILE); ocmem->num_ports = OCMEM_HW_PROFILE_NUM_PORTS(reg); ocmem->num_macros = OCMEM_HW_PROFILE_NUM_MACROS(reg); From ba7ff6085b80c03ae872057bce173d2426917dd1 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Wed, 14 Jun 2023 18:35:47 +0200 Subject: [PATCH 0902/2093] soc: qcom: ocmem: Fix NUM_PORTS & NUM_MACROS macros [ Upstream commit a7b484b1c9332a1ee12e8799d62a11ee3f8e0801 ] Since we're using these two macros to read a value from a register, we need to use the FIELD_GET instead of the FIELD_PREP macro, otherwise we're getting wrong values. So instead of: [ 3.111779] ocmem fdd00000.sram: 2 ports, 1 regions, 512 macros, not interleaved we now get the correct value of: [ 3.129672] ocmem fdd00000.sram: 2 ports, 1 regions, 2 macros, not interleaved Fixes: 88c1e9404f1d ("soc: qcom: add OCMEM driver") Reviewed-by: Caleb Connolly Reviewed-by: Konrad Dybcio Signed-off-by: Luca Weiss Link: https://lore.kernel.org/r/20230506-msm8226-ocmem-v3-1-79da95a2581f@z3ntu.xyz Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/ocmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index 7197d9fe0946..27c668eac964 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -80,8 +80,8 @@ struct ocmem { #define OCMEM_HW_VERSION_MINOR(val) FIELD_GET(GENMASK(27, 16), val) #define OCMEM_HW_VERSION_STEP(val) FIELD_GET(GENMASK(15, 0), val) -#define OCMEM_HW_PROFILE_NUM_PORTS(val) FIELD_PREP(0x0000000f, (val)) -#define OCMEM_HW_PROFILE_NUM_MACROS(val) FIELD_PREP(0x00003f00, (val)) +#define OCMEM_HW_PROFILE_NUM_PORTS(val) FIELD_GET(0x0000000f, (val)) +#define OCMEM_HW_PROFILE_NUM_MACROS(val) FIELD_GET(0x00003f00, (val)) #define OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE 0x00010000 #define OCMEM_HW_PROFILE_INTERLEAVING 0x00020000 From e2040c1101385bffaea56e54bc549e11e9f816e4 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 14 Jun 2023 13:35:37 +0200 Subject: [PATCH 0903/2093] arm64: dts: qcom: sm6350: Fix ZAP region [ Upstream commit 44bcded2be4fe9b9d0b6e48075c9947b75c0af63 ] The previous ZAP region definition was wrong. Fix it. Note this is not a device-specific fixup, but a fixup to the generic PIL load address. Fixes: 5f82b9cda61e ("arm64: dts: qcom: Add SM6350 device tree") Signed-off-by: Konrad Dybcio Reviewed-by: Luca Weiss Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230315-topic-lagoon_gpu-v2-6-afcdfb18bb13@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6350.dtsi | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 35f621ef9da5..34c8de4f43fb 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -306,11 +306,6 @@ pil_ipa_gsi_mem: memory@8b710000 { no-map; }; - pil_gpu_mem: memory@8b715400 { - reg = <0 0x8b715400 0 0x2000>; - no-map; - }; - pil_modem_mem: memory@8b800000 { reg = <0 0x8b800000 0 0xf800000>; no-map; @@ -331,6 +326,11 @@ removed_region: memory@c0000000 { no-map; }; + pil_gpu_mem: memory@f0d00000 { + reg = <0 0xf0d00000 0 0x1000>; + no-map; + }; + debug_region: memory@ffb00000 { reg = <0 0xffb00000 0 0xc0000>; no-map; From d244c92988ab1a0d4950f098e3e6400c11000cac Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 15 Jun 2023 17:48:52 +0200 Subject: [PATCH 0904/2093] arm64: dts: qcom: sm8250: correct dynamic power coefficients [ Upstream commit 775a5283c25d160b2a1359018c447bc518096547 ] sm8250 faces the same problem with its Energy Model as sdm845. The energy cost of LITTLE cores is reported to be higher than medium or big cores EM computes the energy with formula: energy = OPP's cost / maximum cpu capacity * utilization On v6.4-rc6 we have: max capacity of CPU0 = 284 capacity of CPU0's OPP(1612800 Hz) = 253 cost of CPU0's OPP(1612800 Hz) = 191704 max capacity of CPU4 = 871 capacity of CPU4's OPP(710400 Hz) = 255 cost of CPU4's OPP(710400 Hz) = 343217 Both OPPs have almost the same compute capacity but the estimated energy per unit of utilization will be estimated to: energy CPU0 = 191704 / 284 * 1 = 675 energy CPU4 = 343217 / 871 * 1 = 394 EM estimates that little CPU0 will consume 71% more than medium CPU4 for the same compute capacity. According to [1], little consumes 25% less than medium core for Coremark benchmark at those OPPs for the same duration. Set the dynamic-power-coefficient of CPU0-3 to 105 to fix the energy model for little CPUs. [1] https://github.com/kdrag0n/freqbench/tree/master/results/sm8250/k30s Fixes: 6aabed5526ee ("arm64: dts: qcom: sm8250: Add CPU capacities and energy model") Signed-off-by: Vincent Guittot Link: https://lore.kernel.org/r/20230615154852.130076-1-vincent.guittot@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8250.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index e93955525a10..c27f88c9f7b2 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -99,7 +99,7 @@ CPU0: cpu@0 { reg = <0x0 0x0>; enable-method = "psci"; capacity-dmips-mhz = <448>; - dynamic-power-coefficient = <205>; + dynamic-power-coefficient = <105>; next-level-cache = <&L2_0>; power-domains = <&CPU_PD0>; power-domain-names = "psci"; @@ -123,7 +123,7 @@ CPU1: cpu@100 { reg = <0x0 0x100>; enable-method = "psci"; capacity-dmips-mhz = <448>; - dynamic-power-coefficient = <205>; + dynamic-power-coefficient = <105>; next-level-cache = <&L2_100>; power-domains = <&CPU_PD1>; power-domain-names = "psci"; @@ -144,7 +144,7 @@ CPU2: cpu@200 { reg = <0x0 0x200>; enable-method = "psci"; capacity-dmips-mhz = <448>; - dynamic-power-coefficient = <205>; + dynamic-power-coefficient = <105>; next-level-cache = <&L2_200>; power-domains = <&CPU_PD2>; power-domain-names = "psci"; @@ -165,7 +165,7 @@ CPU3: cpu@300 { reg = <0x0 0x300>; enable-method = "psci"; capacity-dmips-mhz = <448>; - dynamic-power-coefficient = <205>; + dynamic-power-coefficient = <105>; next-level-cache = <&L2_300>; power-domains = <&CPU_PD3>; power-domain-names = "psci"; From 537346ff2a6060d1e40bd42128e43729aaf772f9 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 17 Jun 2023 19:15:28 +0200 Subject: [PATCH 0905/2093] arm64: dts: qcom: msm8916-l8150: correct light sensor VDDIO supply [ Upstream commit 6a541eaa6e8e5283efb993ae7a947bede8d01fa5 ] liteon,ltr559 light sensor takes VDDIO, not VIO, supply: msm8916-longcheer-l8150.dtb: light-sensor@23: 'vio-supply' does not match any of the regexes: 'pinctrl-[0-9]+' Fixes: 3016af34ef8d ("arm64: dts: qcom: msm8916-longcheer-l8150: Add light and proximity sensor") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Nikita Travkin Link: https://lore.kernel.org/r/20230617171541.286957-2-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts index d85e7f7c0835..75f7b4f35fe8 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts +++ b/arch/arm64/boot/dts/qcom/msm8916-longcheer-l8150.dts @@ -163,7 +163,7 @@ light-sensor@23 { pinctrl-0 = <&light_int_default>; vdd-supply = <&pm8916_l17>; - vio-supply = <&pm8916_l6>; + vddio-supply = <&pm8916_l6>; }; gyroscope@68 { From 4a36d16cdf3c47b2a60c6f04cfb71ba6a6f15f76 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 20 Jun 2023 13:05:34 +0200 Subject: [PATCH 0906/2093] arm64: dts: qcom: sm8250-edo: Add gpio line names for TLMM [ Upstream commit 40b398beabdfe0e9088b13976e56b1dc706fe851 ] Sony ever so graciously provides GPIO line names in their downstream kernel (though sometimes they are not 100% accurate and you can judge that by simply looking at them and with what drivers they are used). Add these to the PDX203&206 DTSIs to better document the hardware. Diff between 203 and 206: < "CAM_PWR_A_CS", > "FRONTC_PWR_EN", < "CAM4_MCLK", < "TOF_RST_N", > "NC", > "NC", < "WLC_I2C_SDA", < "WLC_I2C_SCL", /* GPIO_120 */ > "NC", > "NC", < "WLC_INT_N", > "NC", Which makes sense, as 203 has a 3D iToF, slightly different camera power wiring and WLC (WireLess Charging). Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230614-topic-edo_pinsgpiopmic-v2-1-6f90bba54c53@linaro.org Signed-off-by: Bjorn Andersson Stable-dep-of: a422c6a91a66 ("arm64: dts: qcom: sm8250-edo: Rectify gpio-keys") Signed-off-by: Sasha Levin --- .../qcom/sm8250-sony-xperia-edo-pdx203.dts | 183 ++++++++++++++++++ .../qcom/sm8250-sony-xperia-edo-pdx206.dts | 183 ++++++++++++++++++ 2 files changed, 366 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts index 356a81698731..84104d2b2010 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts @@ -14,3 +14,186 @@ / { }; /delete-node/ &vreg_l7f_1p8; + +&tlmm { + gpio-line-names = "AP_CTI_IN", /* GPIO_0 */ + "MDM2AP_ERR_FATAL", + "AP_CTI_OUT", + "MDM2AP_STATUS", + "NFC_I2C_SDA", + "NFC_I2C_SCL", + "NFC_EN", + "NFC_CLK_REQ", + "NFC_ESE_PWR_REQ", + "DVDT_WRT_DET_AND", + "SPK_AMP_RESET_N", /* GPIO_10 */ + "SPK_AMP_INT_N", + "APPS_I2C_1_SDA", + "APPS_I2C_1_SCL", + "NC", + "TX_GTR_THRES_IN", + "HST_BT_UART_CTS", + "HST_BT_UART_RFR", + "HST_BT_UART_TX", + "HST_BT_UART_RX", + "HST_WLAN_EN", /* GPIO_20 */ + "HST_BT_EN", + "RGBC_IR_PWR_EN", + "FP_INT_N", + "NC", + "NC", + "NC", + "NC", + "NFC_ESE_SPI_MISO", + "NFC_ESE_SPI_MOSI", + "NFC_ESE_SPI_SCLK", /* GPIO_30 */ + "NFC_ESE_SPI_CS_N", + "WCD_RST_N", + "NC", + "SDM_DEBUG_UART_TX", + "SDM_DEBUG_UART_RX", + "TS_I2C_SDA", + "TS_I2C_SCL", + "TS_INT_N", + "FP_SPI_MISO", /* GPIO_40 */ + "FP_SPI_MOSI", + "FP_SPI_SCLK", + "FP_SPI_CS_N", + "APPS_I2C_0_SDA", + "APPS_I2C_0_SCL", + "DISP_ERR_FG", + "UIM2_DETECT_EN", + "NC", + "NC", + "NC", /* GPIO_50 */ + "NC", + "MDM_UART_CTS", + "MDM_UART_RFR", + "MDM_UART_TX", + "MDM_UART_RX", + "AP2MDM_STATUS", + "AP2MDM_ERR_FATAL", + "MDM_IPC_HS_UART_TX", + "MDM_IPC_HS_UART_RX", + "NC", /* GPIO_60 */ + "NC", + "NC", + "NC", + "NC", + "USB_CC_DIR", + "DISP_VSYNC", + "NC", + "NC", + "CAM_PWR_B_CS", + "NC", /* GPIO_70 */ + "CAM_PWR_A_CS", + "SBU_SW_SEL", + "SBU_SW_OE", + "FP_RESET_N", + "FP_RESET_N", + "DISP_RESET_N", + "DEBUG_GPIO0", + "TRAY_DET", + "CAM2_RST_N", + "PCIE0_RST_N", + "PCIE0_CLK_REQ_N", /* GPIO_80 */ + "PCIE0_WAKE_N", + "DVDT_ENABLE", + "DVDT_WRT_DET_OR", + "NC", + "PCIE2_RST_N", + "PCIE2_CLK_REQ_N", + "PCIE2_WAKE_N", + "MDM_VFR_IRQ0", + "MDM_VFR_IRQ1", + "SW_SERVICE", /* GPIO_90 */ + "CAM_SOF", + "CAM1_RST_N", + "CAM0_RST_N", + "CAM0_MCLK", + "CAM1_MCLK", + "CAM2_MCLK", + "CAM3_MCLK", + "CAM4_MCLK", + "TOF_RST_N", + "NC", /* GPIO_100 */ + "CCI0_I2C_SDA", + "CCI0_I2C_SCL", + "CCI1_I2C_SDA", + "CCI1_I2C_SCL_", + "CCI2_I2C_SDA", + "CCI2_I2C_SCL", + "CCI3_I2C_SDA", + "CCI3_I2C_SCL", + "CAM3_RST_N", + "NFC_DWL_REQ", /* GPIO_110 */ + "NFC_IRQ", + "XVS", + "NC", + "RF_ID_EXTENSION", + "SPK_AMP_I2C_SDA", + "SPK_AMP_I2C_SCL", + "NC", + "NC", + "WLC_I2C_SDA", + "WLC_I2C_SCL", /* GPIO_120 */ + "ACC_COVER_OPEN", + "ALS_PROX_INT_N", + "ACCEL_INT", + "WLAN_SW_CTRL", + "CAMSENSOR_I2C_SDA", + "CAMSENSOR_I2C_SCL", + "UDON_SWITCH_SEL", + "WDOG_DISABLE", + "BAROMETER_INT", + "NC", /* GPIO_130 */ + "NC", + "FORCED_USB_BOOT", + "NC", + "NC", + "WLC_INT_N", + "NC", + "NC", + "RGBC_IR_INT", + "NC", + "NC", /* GPIO_140 */ + "NC", + "BT_SLIMBUS_CLK", + "BT_SLIMBUS_DATA", + "HW_ID_0", + "HW_ID_1", + "WCD_SWR_TX_CLK", + "WCD_SWR_TX_DATA0", + "WCD_SWR_TX_DATA1", + "WCD_SWR_RX_CLK", + "WCD_SWR_RX_DATA0", /* GPIO_150 */ + "WCD_SWR_RX_DATA1", + "SDM_DMIC_CLK1", + "SDM_DMIC_DATA1", + "SDM_DMIC_CLK2", + "SDM_DMIC_DATA2", + "SPK_AMP_I2S_CLK", + "SPK_AMP_I2S_WS", + "SPK_AMP_I2S_ASP_DIN", + "SPK_AMP_I2S_ASP_DOUT", + "COMPASS_I2C_SDA", /* GPIO_160 */ + "COMPASS_I2C_SCL", + "NC", + "NC", + "SSC_SPI_1_MISO", + "SSC_SPI_1_MOSI", + "SSC_SPI_1_CLK", + "SSC_SPI_1_CS_N", + "NC", + "NC", + "SSC_SENSOR_I2C_SDA", /* GPIO_170 */ + "SSC_SENSOR_I2C_SCL", + "NC", + "NC", + "NC", + "NC", + "HST_BLE_SNS_UART6_TX", + "HST_BLE_SNS_UART6_RX", + "HST_WLAN_UART_TX", + "HST_WLAN_UART_RX"; +}; diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts index 5ecf7dafb2ec..4b15de5e65e9 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts @@ -30,6 +30,189 @@ g-assist-key { }; }; +&tlmm { + gpio-line-names = "AP_CTI_IN", /* GPIO_0 */ + "MDM2AP_ERR_FATAL", + "AP_CTI_OUT", + "MDM2AP_STATUS", + "NFC_I2C_SDA", + "NFC_I2C_SCL", + "NFC_EN", + "NFC_CLK_REQ", + "NFC_ESE_PWR_REQ", + "DVDT_WRT_DET_AND", + "SPK_AMP_RESET_N", /* GPIO_10 */ + "SPK_AMP_INT_N", + "APPS_I2C_1_SDA", + "APPS_I2C_1_SCL", + "NC", + "TX_GTR_THRES_IN", + "HST_BT_UART_CTS", + "HST_BT_UART_RFR", + "HST_BT_UART_TX", + "HST_BT_UART_RX", + "HST_WLAN_EN", /* GPIO_20 */ + "HST_BT_EN", + "RGBC_IR_PWR_EN", + "FP_INT_N", + "NC", + "NC", + "NC", + "NC", + "NFC_ESE_SPI_MISO", + "NFC_ESE_SPI_MOSI", + "NFC_ESE_SPI_SCLK", /* GPIO_30 */ + "NFC_ESE_SPI_CS_N", + "WCD_RST_N", + "NC", + "SDM_DEBUG_UART_TX", + "SDM_DEBUG_UART_RX", + "TS_I2C_SDA", + "TS_I2C_SCL", + "TS_INT_N", + "FP_SPI_MISO", /* GPIO_40 */ + "FP_SPI_MOSI", + "FP_SPI_SCLK", + "FP_SPI_CS_N", + "APPS_I2C_0_SDA", + "APPS_I2C_0_SCL", + "DISP_ERR_FG", + "UIM2_DETECT_EN", + "NC", + "NC", + "NC", /* GPIO_50 */ + "NC", + "MDM_UART_CTS", + "MDM_UART_RFR", + "MDM_UART_TX", + "MDM_UART_RX", + "AP2MDM_STATUS", + "AP2MDM_ERR_FATAL", + "MDM_IPC_HS_UART_TX", + "MDM_IPC_HS_UART_RX", + "NC", /* GPIO_60 */ + "NC", + "NC", + "NC", + "NC", + "USB_CC_DIR", + "DISP_VSYNC", + "NC", + "NC", + "CAM_PWR_B_CS", + "NC", /* GPIO_70 */ + "FRONTC_PWR_EN", + "SBU_SW_SEL", + "SBU_SW_OE", + "FP_RESET_N", + "FP_RESET_N", + "DISP_RESET_N", + "DEBUG_GPIO0", + "TRAY_DET", + "CAM2_RST_N", + "PCIE0_RST_N", + "PCIE0_CLK_REQ_N", /* GPIO_80 */ + "PCIE0_WAKE_N", + "DVDT_ENABLE", + "DVDT_WRT_DET_OR", + "NC", + "PCIE2_RST_N", + "PCIE2_CLK_REQ_N", + "PCIE2_WAKE_N", + "MDM_VFR_IRQ0", + "MDM_VFR_IRQ1", + "SW_SERVICE", /* GPIO_90 */ + "CAM_SOF", + "CAM1_RST_N", + "CAM0_RST_N", + "CAM0_MCLK", + "CAM1_MCLK", + "CAM2_MCLK", + "CAM3_MCLK", + "NC", + "NC", + "NC", /* GPIO_100 */ + "CCI0_I2C_SDA", + "CCI0_I2C_SCL", + "CCI1_I2C_SDA", + "CCI1_I2C_SCL_", + "CCI2_I2C_SDA", + "CCI2_I2C_SCL", + "CCI3_I2C_SDA", + "CCI3_I2C_SCL", + "CAM3_RST_N", + "NFC_DWL_REQ", /* GPIO_110 */ + "NFC_IRQ", + "XVS", + "NC", + "RF_ID_EXTENSION", + "SPK_AMP_I2C_SDA", + "SPK_AMP_I2C_SCL", + "NC", + "NC", + "NC", + "NC", + "ACC_COVER_OPEN", + "ALS_PROX_INT_N", + "ACCEL_INT", + "WLAN_SW_CTRL", + "CAMSENSOR_I2C_SDA", + "CAMSENSOR_I2C_SCL", + "UDON_SWITCH_SEL", + "WDOG_DISABLE", + "BAROMETER_INT", + "NC", /* GPIO_130 */ + "NC", + "FORCED_USB_BOOT", + "NC", + "NC", + "NC", + "NC", + "NC", + "RGBC_IR_INT", + "NC", + "NC", /* GPIO_140 */ + "NC", + "BT_SLIMBUS_CLK", + "BT_SLIMBUS_DATA", + "HW_ID_0", + "HW_ID_1", + "WCD_SWR_TX_CLK", + "WCD_SWR_TX_DATA0", + "WCD_SWR_TX_DATA1", + "WCD_SWR_RX_CLK", + "WCD_SWR_RX_DATA0", /* GPIO_150 */ + "WCD_SWR_RX_DATA1", + "SDM_DMIC_CLK1", + "SDM_DMIC_DATA1", + "SDM_DMIC_CLK2", + "SDM_DMIC_DATA2", + "SPK_AMP_I2S_CLK", + "SPK_AMP_I2S_WS", + "SPK_AMP_I2S_ASP_DIN", + "SPK_AMP_I2S_ASP_DOUT", + "COMPASS_I2C_SDA", /* GPIO_160 */ + "COMPASS_I2C_SCL", + "NC", + "NC", + "SSC_SPI_1_MISO", + "SSC_SPI_1_MOSI", + "SSC_SPI_1_CLK", + "SSC_SPI_1_CS_N", + "NC", + "NC", + "SSC_SENSOR_I2C_SDA", /* GPIO_170 */ + "SSC_SENSOR_I2C_SCL", + "NC", + "NC", + "NC", + "NC", + "HST_BLE_SNS_UART6_TX", + "HST_BLE_SNS_UART6_RX", + "HST_WLAN_UART_TX", + "HST_WLAN_UART_RX"; +}; + &vreg_l2f_1p3 { regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; From 7852d207882cc4f1a9560927e564672e22d4c5f8 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 20 Jun 2023 13:05:35 +0200 Subject: [PATCH 0907/2093] arm64: dts: qcom: sm8250-edo: Add GPIO line names for PMIC GPIOs [ Upstream commit 6b8a63350752c6a5e4b54f2de6174084652cd3cd ] Sony ever so graciously provides GPIO line names in their downstream kernel (though sometimes they are not 100% accurate and you can judge that by simply looking at them and with what drivers they are used). Add these to the PDX203&206 DTSIs to better document the hardware. Diff between 203 and 206: pm8009_gpios < "CAM_PWR_LD_EN", > "NC", pm8150_gpios < "NC", > "G_ASSIST_N", < "WLC_EN_N", /* GPIO_10 */ > "NC", /* GPIO_10 */ Which is due to 5 II having an additional Google Assistant hardware button and 1 II having a wireless charger & different camera wiring to accommodate the additional 3D iToF sensor. Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230614-topic-edo_pinsgpiopmic-v2-2-6f90bba54c53@linaro.org Signed-off-by: Bjorn Andersson Stable-dep-of: a422c6a91a66 ("arm64: dts: qcom: sm8250-edo: Rectify gpio-keys") Signed-off-by: Sasha Levin --- .../qcom/sm8250-sony-xperia-edo-pdx203.dts | 50 +++++++++++++++++++ .../qcom/sm8250-sony-xperia-edo-pdx206.dts | 50 +++++++++++++++++++ 2 files changed, 100 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts index 84104d2b2010..62590c6bd306 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx203.dts @@ -15,6 +15,56 @@ / { /delete-node/ &vreg_l7f_1p8; +&pm8009_gpios { + gpio-line-names = "NC", /* GPIO_1 */ + "CAM_PWR_LD_EN", + "WIDEC_PWR_EN", + "NC"; +}; + +&pm8150_gpios { + gpio-line-names = "VOL_DOWN_N", /* GPIO_1 */ + "OPTION_2", + "NC", + "PM_SLP_CLK_IN", + "OPTION_1", + "NC", + "NC", + "SP_ARI_PWR_ALARM", + "NC", + "NC"; /* GPIO_10 */ +}; + +&pm8150b_gpios { + gpio-line-names = "SNAPSHOT_N", /* GPIO_1 */ + "FOCUS_N", + "NC", + "NC", + "RF_LCD_ID_EN", + "NC", + "NC", + "LCD_ID", + "NC", + "WLC_EN_N", /* GPIO_10 */ + "NC", + "RF_ID"; +}; + +&pm8150l_gpios { + gpio-line-names = "NC", /* GPIO_1 */ + "PM3003A_EN", + "NC", + "NC", + "NC", + "AUX2_THERM", + "BB_HP_EN", + "FP_LDO_EN", + "PMX_RESET_N", + "AUX3_THERM", /* GPIO_10 */ + "DTV_PWR_EN", + "PM3003A_MODE"; +}; + &tlmm { gpio-line-names = "AP_CTI_IN", /* GPIO_0 */ "MDM2AP_ERR_FATAL", diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts index 4b15de5e65e9..65bad39ecda8 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts @@ -30,6 +30,56 @@ g-assist-key { }; }; +&pm8009_gpios { + gpio-line-names = "NC", /* GPIO_1 */ + "NC", + "WIDEC_PWR_EN", + "NC"; +}; + +&pm8150_gpios { + gpio-line-names = "VOL_DOWN_N", /* GPIO_1 */ + "OPTION_2", + "NC", + "PM_SLP_CLK_IN", + "OPTION_1", + "G_ASSIST_N", + "NC", + "SP_ARI_PWR_ALARM", + "NC", + "NC"; /* GPIO_10 */ +}; + +&pm8150b_gpios { + gpio-line-names = "SNAPSHOT_N", /* GPIO_1 */ + "FOCUS_N", + "NC", + "NC", + "RF_LCD_ID_EN", + "NC", + "NC", + "LCD_ID", + "NC", + "NC", /* GPIO_10 */ + "NC", + "RF_ID"; +}; + +&pm8150l_gpios { + gpio-line-names = "NC", /* GPIO_1 */ + "PM3003A_EN", + "NC", + "NC", + "NC", + "AUX2_THERM", + "BB_HP_EN", + "FP_LDO_EN", + "PMX_RESET_N", + "NC", /* GPIO_10 */ + "NC", + "PM3003A_MODE"; +}; + &tlmm { gpio-line-names = "AP_CTI_IN", /* GPIO_0 */ "MDM2AP_ERR_FATAL", From 4c7477d0daaa66a1ea897e8e08d1c37d8bcf892d Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 20 Jun 2023 13:05:37 +0200 Subject: [PATCH 0908/2093] arm64: dts: qcom: sm8250-edo: Rectify gpio-keys [ Upstream commit a422c6a91a667b309ca1a6c08b30dbfcf7d4e866 ] Set up the corresponding GPIOs properly and add the leftover hardware buttons to mark this piece of the puzzle complete. Fixes: 46e14907c716 ("arm64: dts: qcom: sm8250-edo: Add hardware keys") Reviewed-by: Marijn Suijten Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230614-topic-edo_pinsgpiopmic-v2-4-6f90bba54c53@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- .../qcom/sm8250-sony-xperia-edo-pdx206.dts | 10 ++++ .../boot/dts/qcom/sm8250-sony-xperia-edo.dtsi | 54 ++++++++++++++++--- 2 files changed, 58 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts index 65bad39ecda8..0e50661c1b4c 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo-pdx206.dts @@ -20,6 +20,8 @@ &framebuffer { }; &gpio_keys { + pinctrl-0 = <&focus_n &snapshot_n &vol_down_n &g_assist_n>; + g-assist-key { label = "Google Assistant Key"; linux,code = ; @@ -48,6 +50,14 @@ &pm8150_gpios { "SP_ARI_PWR_ALARM", "NC", "NC"; /* GPIO_10 */ + + g_assist_n: g-assist-n-state { + pins = "gpio6"; + function = "normal"; + power-source = <1>; + bias-pull-up; + input-enable; + }; }; &pm8150b_gpios { diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi index 390b90a8ddf7..259798a95974 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi @@ -51,12 +51,26 @@ framebuffer: framebuffer@9c000000 { gpio_keys: gpio-keys { compatible = "gpio-keys"; - /* - * Camera focus (light press) and camera snapshot (full press) - * seem not to work properly.. Adding the former one stalls the CPU - * and the latter kills the volume down key for whatever reason. In any - * case, they are both on &pm8150b_gpios: camera focus(2), camera snapshot(1). - */ + pinctrl-0 = <&focus_n &snapshot_n &vol_down_n>; + pinctrl-names = "default"; + + key-camera-focus { + label = "Camera Focus"; + linux,code = ; + gpios = <&pm8150b_gpios 2 GPIO_ACTIVE_LOW>; + debounce-interval = <15>; + linux,can-disable; + gpio-key,wakeup; + }; + + key-camera-snapshot { + label = "Camera Snapshot"; + linux,code = ; + gpios = <&pm8150b_gpios 1 GPIO_ACTIVE_LOW>; + debounce-interval = <15>; + linux,can-disable; + gpio-key,wakeup; + }; key-vol-down { label = "Volume Down"; @@ -546,6 +560,34 @@ &pcie2_phy { vdda-pll-supply = <&vreg_l9a_1p2>; }; +&pm8150_gpios { + vol_down_n: vol-down-n-state { + pins = "gpio1"; + function = "normal"; + power-source = <0>; + bias-pull-up; + input-enable; + }; +}; + +&pm8150b_gpios { + snapshot_n: snapshot-n-state { + pins = "gpio1"; + function = "normal"; + power-source = <0>; + bias-pull-up; + input-enable; + }; + + focus_n: focus-n-state { + pins = "gpio2"; + function = "normal"; + power-source = <0>; + bias-pull-up; + input-enable; + }; +}; + &pon_pwrkey { status = "okay"; }; From e5bf98ceac1ebca2dab6e5afdc89f5e7b4be9619 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 20 Jun 2023 13:39:14 -0700 Subject: [PATCH 0909/2093] arm64: dts: qcom: sc8280xp-crd: Correct vreg_misc_3p3 GPIO [ Upstream commit 9566b5271f68bdf6e69b7c511850e3fb75cd18be ] The vreg_misc_3p3 regulator is controlled by PMC8280_1 GPIO 2, not 1, on the CRD. Fixes: ccd3517faf18 ("arm64: dts: qcom: sc8280xp: Add reference device") Signed-off-by: Bjorn Andersson Reviewed-by: Johan Hovold Tested-by: Johan Hovold Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230620203915.141337-1-quic_bjorande@quicinc.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sc8280xp-crd.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts index 5e30349efd20..38ec8acb7c40 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts @@ -57,7 +57,7 @@ vreg_misc_3p3: regulator-misc-3p3 { regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpio = <&pmc8280_1_gpios 1 GPIO_ACTIVE_HIGH>; + gpio = <&pmc8280_1_gpios 2 GPIO_ACTIVE_HIGH>; enable-active-high; pinctrl-names = "default"; @@ -364,7 +364,7 @@ edp_bl_reg_en: edp-bl-reg-en-state { }; misc_3p3_reg_en: misc-3p3-reg-en-state { - pins = "gpio1"; + pins = "gpio2"; function = "normal"; }; }; From 82c3d3490b6bcd27df7603489d6ebab5239b2858 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 22 Jun 2023 17:56:16 +0200 Subject: [PATCH 0910/2093] arm64: dts: qcom: sc8280xp: Add missing SCM interconnect [ Upstream commit 0a69ccf20b0837db857abfc94d7e3bacf1cb771b ] The SCM interconnect path was missing. Add it. Fixes: 152d1faf1e2f ("arm64: dts: qcom: add SC8280XP platform") Signed-off-by: Konrad Dybcio Reviewed-by: Johan Hovold Tested-by: Johan Hovold Link: https://lore.kernel.org/r/20230622-topic-8280scmicc-v1-2-6ef318919ea5@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 1afc960bab5c..405835ad28bc 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -396,6 +396,7 @@ CLUSTER_SLEEP_0: cluster-sleep-0 { firmware { scm: scm { compatible = "qcom,scm-sc8280xp", "qcom,scm"; + interconnects = <&aggre2_noc MASTER_CRYPTO 0 &mc_virt SLAVE_EBI1 0>; }; }; From 8622340505dc0b733a59211e1d5bd6fb9938e99e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 27 Jun 2023 18:24:27 +0200 Subject: [PATCH 0911/2093] arm64: dts: qcom: msm8996: Add missing interrupt to the USB2 controller [ Upstream commit 36541089c4733355ed844c67eebd0c3936953454 ] The interrupt line was previously not described. Take care of that. Fixes: 1e39255ed29d ("arm64: dts: msm8996: Add device node for qcom,dwc3") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230627-topic-more_bindings-v1-11-6b4b6cd081e5@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 9d6ec59d1cd3..7e381d8257ba 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -3292,6 +3292,9 @@ usb2: usb@76f8800 { #size-cells = <1>; ranges; + interrupts = ; + interrupt-names = "hs_phy_irq"; + clocks = <&gcc GCC_PERIPH_NOC_USB20_AHB_CLK>, <&gcc GCC_USB20_MASTER_CLK>, <&gcc GCC_USB20_MOCK_UTMI_CLK>, From c97633eaf571f67b2b1e6a33156f1f66df451f6a Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 27 Jun 2023 19:27:50 +0200 Subject: [PATCH 0912/2093] arm64: dts: qcom: sdm845-tama: Set serial indices and stdout-path [ Upstream commit 9acc60c3e2d449243e4c2126e3b56f1c4f7fd3bc ] UART6 is used for debug (routed via uSD pins) and UART9 is connected to the bluetooth chip. Set indexed aliases to make the GENI UART driver happy and route serial traffic through the debug uart by default. Fixes: 30a7f99befc6 ("arm64: dts: qcom: Add support for SONY Xperia XZ2 / XZ2C / XZ3 (Tama platform)") Signed-off-by: Konrad Dybcio Reviewed-by: Marijn Suijten Link: https://lore.kernel.org/r/20230627-topic-tama_uart-v1-1-0fa790248db8@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi b/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi index 51ee42e3c995..d6918e6d1979 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi @@ -14,6 +14,15 @@ / { qcom,msm-id = <321 0x20001>; /* SDM845 v2.1 */ qcom,board-id = <8 0>; + aliases { + serial0 = &uart6; + serial1 = &uart9; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + gpio-keys { compatible = "gpio-keys"; From 0c32fba73549aa5b790f4f9b37f1d8a8fb01e9ed Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 5 Jul 2023 15:36:22 +0200 Subject: [PATCH 0913/2093] arm64: dts: qcom: sm8350: Fix CPU idle state residency times [ Upstream commit 91ce3693e2fb685f31d39605a5ad1fbd940804da ] The present values look to have been copypasted from 8150 or 8180. Fix that. Fixes: 07ddb302811e ("arm64: dts: qcom: sm8350: Add CPU topology and idle-states") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230705-topic-sm8350_fixes-v1-2-0f69f70ccb6a@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8350.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 7fd1c3f71c0f..b91247856f9d 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -236,8 +236,8 @@ LITTLE_CPU_SLEEP_0: cpu-sleep-0-0 { compatible = "arm,idle-state"; idle-state-name = "silver-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; - entry-latency-us = <355>; - exit-latency-us = <909>; + entry-latency-us = <360>; + exit-latency-us = <531>; min-residency-us = <3934>; local-timer-stop; }; @@ -246,8 +246,8 @@ BIG_CPU_SLEEP_0: cpu-sleep-1-0 { compatible = "arm,idle-state"; idle-state-name = "gold-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; - entry-latency-us = <241>; - exit-latency-us = <1461>; + entry-latency-us = <702>; + exit-latency-us = <1061>; min-residency-us = <4488>; local-timer-stop; }; From db336dcb0127ae9f9857b37c47f6daf04ea9398e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 5 Jul 2023 15:36:23 +0200 Subject: [PATCH 0914/2093] arm64: dts: qcom: sm8350: Add missing LMH interrupts to cpufreq [ Upstream commit 951151c2bb548e0f6b2c40ab4c48675f5342c914 ] Add the missing interrupts that communicate the hardware-managed throttling to Linux. Fixes: ccbb3abb23a5 ("arm64: dts: qcom: sm8350: Add cpufreq node") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230705-topic-sm8350_fixes-v1-3-0f69f70ccb6a@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8350.dtsi | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index b91247856f9d..0b5a1841d607 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -2072,6 +2072,13 @@ cpufreq_hw: cpufreq@18591000 { <0 0x18593000 0 0x1000>; reg-names = "freq-domain0", "freq-domain1", "freq-domain2"; + interrupts = , + , + ; + interrupt-names = "dcvsh-irq-0", + "dcvsh-irq-1", + "dcvsh-irq-2"; + clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_GPLL0>; clock-names = "xo", "alternate"; From 8fd3533f4bcecee35d856845f7bddf26267d902f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 6 Jul 2023 18:35:37 +0200 Subject: [PATCH 0915/2093] arm64: dts: qcom: sm8350: Use proper CPU compatibles [ Upstream commit 4390730cc12af25f7c997f477795f5f4200149c0 ] The Kryo names (once again) turned out to be fake. The CPUs report: 0x412fd050 (CA55 r2p0) (0 - 3) 0x411fd410 (CA78 r1p1) (4 - 6) 0x411fd440 (CX1 r1p1) (7) Use the compatibles that reflect that. Fixes: b7e8f433a673 ("arm64: dts: qcom: Add basic devicetree support for SM8350 SoC") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230706-topic-sm8350-cpu-compat-v1-1-f8d6a1869781@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8350.dtsi | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 0b5a1841d607..b3245b13b261 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -63,7 +63,7 @@ cpus { CPU0: cpu@0 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a55"; reg = <0x0 0x0>; enable-method = "psci"; next-level-cache = <&L2_0>; @@ -82,7 +82,7 @@ L3_0: l3-cache { CPU1: cpu@100 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a55"; reg = <0x0 0x100>; enable-method = "psci"; next-level-cache = <&L2_100>; @@ -98,7 +98,7 @@ L2_100: l2-cache { CPU2: cpu@200 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a55"; reg = <0x0 0x200>; enable-method = "psci"; next-level-cache = <&L2_200>; @@ -114,7 +114,7 @@ L2_200: l2-cache { CPU3: cpu@300 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a55"; reg = <0x0 0x300>; enable-method = "psci"; next-level-cache = <&L2_300>; @@ -130,7 +130,7 @@ L2_300: l2-cache { CPU4: cpu@400 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a78"; reg = <0x0 0x400>; enable-method = "psci"; next-level-cache = <&L2_400>; @@ -146,7 +146,7 @@ L2_400: l2-cache { CPU5: cpu@500 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a78"; reg = <0x0 0x500>; enable-method = "psci"; next-level-cache = <&L2_500>; @@ -163,7 +163,7 @@ L2_500: l2-cache { CPU6: cpu@600 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-a78"; reg = <0x0 0x600>; enable-method = "psci"; next-level-cache = <&L2_600>; @@ -179,7 +179,7 @@ L2_600: l2-cache { CPU7: cpu@700 { device_type = "cpu"; - compatible = "qcom,kryo685"; + compatible = "arm,cortex-x1"; reg = <0x0 0x700>; enable-method = "psci"; next-level-cache = <&L2_700>; From 0f52060fa1db1d9bf060b1af7e25db9ab0f797bf Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 7 Jul 2023 15:30:21 +0300 Subject: [PATCH 0916/2093] arm64: dts: qcom: pm8350: fix thermal zone name [ Upstream commit 64f19c06f704846db5e4885ca63c689d9bef5723 ] The name of the thermal zone in pm8350.dtsi (pm8350c-thermal) conflicts with the thermal zone in pm8350c.dtsi. Rename the thermal zone according to the chip name. Fixes: 7a79b95f4288 ("arm64: dts: qcom: pm8350: add temp sensor and thermal zone config") Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230707123027.1510723-3-dmitry.baryshkov@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pm8350.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/pm8350.dtsi b/arch/arm64/boot/dts/qcom/pm8350.dtsi index 2dfeb99300d7..9ed9ba23e81e 100644 --- a/arch/arm64/boot/dts/qcom/pm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8350.dtsi @@ -8,7 +8,7 @@ / { thermal-zones { - pm8350_thermal: pm8350c-thermal { + pm8350_thermal: pm8350-thermal { polling-delay-passive = <100>; polling-delay = <0>; thermal-sensors = <&pm8350_temp_alarm>; From de4688dcc0f6ae0b145a8d799d483c84434ca154 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 7 Jul 2023 15:30:22 +0300 Subject: [PATCH 0917/2093] arm64: dts: qcom: pm8350b: fix thermal zone name [ Upstream commit aad41d9e6c44dfe299cddab97528a5333f17bdfe ] The name of the thermal zone in pm8350b.dtsi (pm8350c-thermal) conflicts with the thermal zone in pm8350c.dtsi. Rename the thermal zone according to the chip name. Fixes: 5c1399299d9d ("arm64: dts: qcom: pm8350b: add temp sensor and thermal zone config") Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230707123027.1510723-4-dmitry.baryshkov@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pm8350b.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/pm8350b.dtsi b/arch/arm64/boot/dts/qcom/pm8350b.dtsi index f1c7bd9d079c..05c105898892 100644 --- a/arch/arm64/boot/dts/qcom/pm8350b.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8350b.dtsi @@ -8,7 +8,7 @@ / { thermal-zones { - pm8350b_thermal: pm8350c-thermal { + pm8350b_thermal: pm8350b-thermal { polling-delay-passive = <100>; polling-delay = <0>; thermal-sensors = <&pm8350b_temp_alarm>; From 5aa1969ce7c42a5beb5b72913367c65e542a2d23 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 7 Jul 2023 15:30:23 +0300 Subject: [PATCH 0918/2093] arm64: dts: qcom: pmr735b: fix thermal zone name [ Upstream commit 99f8cf491d546cd668236f573c7d846d3e94f2d6 ] The name of the thermal zone in pmr735b.dtsi (pmr735a-thermal) conflicts with the thermal zone in pmr735a.dtsi. Rename the thermal zone according to the chip name. Fixes: 6f3426b3dea4 ("arm64: dts: qcom: pmr735b: add temp sensor and thermal zone config") Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230707123027.1510723-5-dmitry.baryshkov@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pmr735b.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/pmr735b.dtsi b/arch/arm64/boot/dts/qcom/pmr735b.dtsi index ec24c4478005..f7473e247322 100644 --- a/arch/arm64/boot/dts/qcom/pmr735b.dtsi +++ b/arch/arm64/boot/dts/qcom/pmr735b.dtsi @@ -8,7 +8,7 @@ / { thermal-zones { - pmr735a_thermal: pmr735a-thermal { + pmr735b_thermal: pmr735b-thermal { polling-delay-passive = <100>; polling-delay = <0>; thermal-sensors = <&pmr735b_temp_alarm>; From c755b194d793c4f6cbdda8fb232d67379529dba1 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 7 Jul 2023 15:30:24 +0300 Subject: [PATCH 0919/2093] arm64: dts: qcom: pmk8350: fix ADC-TM compatible string [ Upstream commit 435a73d7377ceb29c1a22d2711dd85c831b40c45 ] The commit b2de43136058 ("arm64: dts: qcom: pmk8350: Add peripherals for pmk8350") for the ADC TM (thermal monitoring device) have used the compatible string from the vendor kernel ("qcom,adc-tm7"). Use the proper compatible string that is defined in the upstream kernel ("qcom,spmi-adc-tm5-gen2"). Fixes: b2de43136058 ("arm64: dts: qcom: pmk8350: Add peripherals for pmk8350") Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230707123027.1510723-6-dmitry.baryshkov@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pmk8350.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/pmk8350.dtsi b/arch/arm64/boot/dts/qcom/pmk8350.dtsi index f0d256d99e62..29cfb6fca9bf 100644 --- a/arch/arm64/boot/dts/qcom/pmk8350.dtsi +++ b/arch/arm64/boot/dts/qcom/pmk8350.dtsi @@ -44,7 +44,7 @@ pmk8350_vadc: adc@3100 { }; pmk8350_adc_tm: adc-tm@3400 { - compatible = "qcom,adc-tm7"; + compatible = "qcom,spmi-adc-tm5-gen2"; reg = <0x3400>; interrupts = <0x0 0x34 0x0 IRQ_TYPE_EDGE_RISING>; #address-cells = <1>; From e8d6e54daf1aa26db20dbd20b28938f1e19a326f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 4 Jul 2023 14:23:17 +0200 Subject: [PATCH 0920/2093] arm64: dts: qcom: sm8250: Mark PCIe hosts as DMA coherent [ Upstream commit 339d38a436f30d0f874815eafc7de2257346bf26 ] The PCIe hosts on SM8250 are cache-coherent. Mark them as such. Fixes: e53bdfc00977 ("arm64: dts: qcom: sm8250: Add PCIe support") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230704-topic-8250_pcie_dmac-v1-1-799603a980b0@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8250.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index c27f88c9f7b2..4d9b30f0b284 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -1862,6 +1862,7 @@ pcie0: pci@1c00000 { pinctrl-names = "default"; pinctrl-0 = <&pcie0_default_state>; + dma-coherent; status = "disabled"; }; @@ -1968,6 +1969,7 @@ pcie1: pci@1c08000 { pinctrl-names = "default"; pinctrl-0 = <&pcie1_default_state>; + dma-coherent; status = "disabled"; }; @@ -2076,6 +2078,7 @@ pcie2: pci@1c10000 { pinctrl-names = "default"; pinctrl-0 = <&pcie2_default_state>; + dma-coherent; status = "disabled"; }; From e62c091b6dfa522b399bc8919ac4af3580bc17e0 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 27 Sep 2022 00:44:37 +0200 Subject: [PATCH 0921/2093] ARM: dts: stm32: Rename mdio0 to mdio [ Upstream commit a306d8962a24f4e8385853793fd58f9792c7aa61 ] Replace "mdio0" node with "mdio" to match mdio.yaml DT schema. Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Stable-dep-of: 0ee0ef38aa9f ("ARM: dts: stm32: Add missing detach mailbox for emtrion emSBC-Argon") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi | 2 +- arch/arm/boot/dts/stm32mp157c-ev1.dts | 2 +- arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts | 2 +- arch/arm/boot/dts/stm32mp157c-odyssey.dts | 2 +- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 2 +- arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 2 +- arch/arm/boot/dts/stm32mp15xx-dhcor-drc-compact.dtsi | 2 +- arch/arm/boot/dts/stm32mp15xx-dkx.dtsi | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index d540550f7da2..7d11c50b9e40 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -173,7 +173,7 @@ ðernet0 { phy-handle = <&phy0>; st,eth-ref-clk-sel; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index 050c3c27a420..b72d5e8aa466 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -144,7 +144,7 @@ ðernet0 { max-speed = <1000>; phy-handle = <&phy0>; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; diff --git a/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts b/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts index e8d2ec41d537..cb00ce7cec8b 100644 --- a/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts +++ b/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts @@ -112,7 +112,7 @@ ðernet0 { phy-handle = <ðphy>; status = "okay"; - mdio0 { + mdio { compatible = "snps,dwmac-mdio"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp157c-odyssey.dts b/arch/arm/boot/dts/stm32mp157c-odyssey.dts index ed66d25b8bf3..a8b3f7a54703 100644 --- a/arch/arm/boot/dts/stm32mp157c-odyssey.dts +++ b/arch/arm/boot/dts/stm32mp157c-odyssey.dts @@ -41,7 +41,7 @@ ðernet0 { assigned-clock-rates = <125000000>; /* Clock PLL4 to 750Mhz in ATF/U-Boot */ st,eth-clk-sel; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index d3b85a8764d7..c06edd2eacb0 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -125,7 +125,7 @@ ðernet0 { max-speed = <100>; phy-handle = <&phy0>; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index f068e4fcc404..dae602b7a54d 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -151,7 +151,7 @@ ðernet0 { max-speed = <1000>; phy-handle = <&phy0>; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-drc-compact.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-drc-compact.dtsi index bb4ac6c13cbd..39af79dc654c 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-drc-compact.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-drc-compact.dtsi @@ -78,7 +78,7 @@ ðernet0 { max-speed = <1000>; phy-handle = <&phy0>; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; diff --git a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi index fdc48536e97d..73a6a7b278b9 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi @@ -141,7 +141,7 @@ ðernet0 { max-speed = <1000>; phy-handle = <&phy0>; - mdio0 { + mdio { #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; From a5274a79ef3a41922b86dcb7e793c9d2279e15d5 Mon Sep 17 00:00:00 2001 From: Pierre-Yves MORDRET Date: Mon, 3 Apr 2023 10:01:06 +0200 Subject: [PATCH 0922/2093] ARM: dts: stm32: YAML validation fails for Argon Boards [ Upstream commit fc8d2b21bc5d5d7a6eadaa8c2a5d2e6856689480 ] "make dtbs_check" gives following output : stm32mp157c-emstamp-argon.dtb: gpu@59000000: 'contiguous-area' does not match any of the regexes: 'pinctrl-[0-9]+' From schema: Documentation/devicetree/bindings/gpu/vivante,gc.yaml Signed-off-by: Pierre-Yves MORDRET Signed-off-by: Alexandre Torgue Stable-dep-of: 0ee0ef38aa9f ("ARM: dts: stm32: Add missing detach mailbox for emtrion emSBC-Argon") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi | 9 --------- 1 file changed, 9 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index 7d11c50b9e40..b01470a9a3d5 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -68,11 +68,6 @@ retram: retram@38000000 { reg = <0x38000000 0x10000>; no-map; }; - - gpu_reserved: gpu@dc000000 { - reg = <0xdc000000 0x4000000>; - no-map; - }; }; led: gpio_leds { @@ -183,10 +178,6 @@ phy0: ethernet-phy@0 { }; }; -&gpu { - contiguous-area = <&gpu_reserved>; -}; - &hash1 { status = "okay"; }; From 0746cab4768d92e6cf21467083fffdca9ec1b34d Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 30 May 2023 14:45:34 +0200 Subject: [PATCH 0923/2093] ARM: dts: stm32: adopt generic iio bindings for adc channels on emstamp-argon [ Upstream commit c46e9b6cc98245f7264a8d15394d1f95d433abec ] Use STM32 ADC generic bindings instead of legacy bindings on emtrion GmbH Argon boards. The STM32 ADC specific binding to declare channels has been deprecated, hence adopt the generic IIO channels bindings, instead. The STM32MP151 device tree now exposes internal channels using the generic binding. This makes the change mandatory here to avoid a mixed use of legacy and generic binding, which is not supported by the driver. Signed-off-by: Olivier Moysan Signed-off-by: Alexandre Torgue Stable-dep-of: 0ee0ef38aa9f ("ARM: dts: stm32: Add missing detach mailbox for emtrion emSBC-Argon") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index b01470a9a3d5..94e38141af67 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -97,9 +97,11 @@ &adc { adc1: adc@0 { pinctrl-names = "default"; pinctrl-0 = <&adc1_in6_pins_a>; - st,min-sample-time-nsecs = <5000>; - st,adc-channels = <6>; status = "disabled"; + channel@6 { + reg = <6>; + st,min-sample-time-ns = <5000>; + }; }; adc2: adc@100 { From aa72079a1952d07b0574d257ac3ec2302fe35303 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 18 May 2023 03:12:42 +0200 Subject: [PATCH 0924/2093] ARM: dts: stm32: Add missing detach mailbox for emtrion emSBC-Argon [ Upstream commit 0ee0ef38aa9f75f21b51f729dd42b2e932515188 ] Add missing "detach" mailbox to this board to permit the CPU to inform the remote processor on a detach. This signal allows the remote processor firmware to stop IPC communication and to reinitialize the resources for a re-attach. Without this mailbox, detach is not possible and kernel log contains the following warning to, so make sure all the STM32MP15xx platform DTs are in sync regarding the mailboxes to fix the detach issue and the warning: " stm32-rproc 10000000.m4: mbox_request_channel_byname() could not locate channel named "detach" " Fixes: 6257dfc1c412 ("ARM: dts: stm32: Add coprocessor detach mbox on stm32mp15x-dkx boards") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index 94e38141af67..fd89542c69c9 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -368,8 +368,8 @@ &iwdg2 { &m4_rproc { memory-region = <&retram>, <&mcuram>, <&mcuram2>, <&vdev0vring0>, <&vdev0vring1>, <&vdev0buffer>; - mboxes = <&ipcc 0>, <&ipcc 1>, <&ipcc 2>; - mbox-names = "vq0", "vq1", "shutdown"; + mboxes = <&ipcc 0>, <&ipcc 1>, <&ipcc 2>, <&ipcc 3>; + mbox-names = "vq0", "vq1", "shutdown", "detach"; interrupt-parent = <&exti>; interrupts = <68 1>; interrupt-names = "wdg"; From c0929f2bbd68e69c370e60fb23ac46357c321613 Mon Sep 17 00:00:00 2001 From: Pierre-Yves MORDRET Date: Mon, 3 Apr 2023 09:58:31 +0200 Subject: [PATCH 0925/2093] ARM: dts: stm32: YAML validation fails for Odyssey Boards [ Upstream commit 84a34e1862aae43e4dcdfb743a7dd3ade1fe4a3c ] "make dtbs_check" gives following output : stm32mp157c-odyssey.dt.yaml: gpu@59000000: 'contiguous-area' does not match any of the regexes: 'pinctrl-[0-9]+' From schema: Documentation/devicetree/bindings/gpu/vivante,gc.yaml Signed-off-by: Pierre-Yves MORDRET Signed-off-by: Alexandre Torgue Stable-dep-of: 966f04a89d77 ("ARM: dts: stm32: Add missing detach mailbox for Odyssey SoM") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi b/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi index 2d9461006810..e22871dc580c 100644 --- a/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi @@ -62,11 +62,6 @@ retram: retram@38000000 { reg = <0x38000000 0x10000>; no-map; }; - - gpu_reserved: gpu@d4000000 { - reg = <0xd4000000 0x4000000>; - no-map; - }; }; led { @@ -80,11 +75,6 @@ led-blue { }; }; -&gpu { - contiguous-area = <&gpu_reserved>; - status = "okay"; -}; - &i2c2 { pinctrl-names = "default"; pinctrl-0 = <&i2c2_pins_a>; From 9d77a7fc5d04f8a281c46a1924cb811aaa505b8c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 18 May 2023 03:12:43 +0200 Subject: [PATCH 0926/2093] ARM: dts: stm32: Add missing detach mailbox for Odyssey SoM [ Upstream commit 966f04a89d77548e673de2c400abe0b2cf5c15db ] Add missing "detach" mailbox to this board to permit the CPU to inform the remote processor on a detach. This signal allows the remote processor firmware to stop IPC communication and to reinitialize the resources for a re-attach. Without this mailbox, detach is not possible and kernel log contains the following warning to, so make sure all the STM32MP15xx platform DTs are in sync regarding the mailboxes to fix the detach issue and the warning: " stm32-rproc 10000000.m4: mbox_request_channel_byname() could not locate channel named "detach" " Fixes: 6257dfc1c412 ("ARM: dts: stm32: Add coprocessor detach mbox on stm32mp15x-dkx boards") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi b/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi index e22871dc580c..cf7485251490 100644 --- a/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-odyssey-som.dtsi @@ -230,8 +230,8 @@ &iwdg2 { &m4_rproc { memory-region = <&retram>, <&mcuram>, <&mcuram2>, <&vdev0vring0>, <&vdev0vring1>, <&vdev0buffer>; - mboxes = <&ipcc 0>, <&ipcc 1>, <&ipcc 2>; - mbox-names = "vq0", "vq1", "shutdown"; + mboxes = <&ipcc 0>, <&ipcc 1>, <&ipcc 2>, <&ipcc 3>; + mbox-names = "vq0", "vq1", "shutdown", "detach"; interrupt-parent = <&exti>; interrupts = <68 1>; status = "okay"; From e3c7b7ce7cd6297ae6d71846ff984fbc59439083 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 30 May 2023 14:45:37 +0200 Subject: [PATCH 0927/2093] ARM: dts: stm32: Update to generic ADC channel binding on DHSOM systems [ Upstream commit 9bcfc3cdc903485a52c6f471f4ae96a41fa51803 ] The generic ADC channel binding is recommended over legacy one, update the DT to the modern binding. No functional change. For further details, see commit which adds the generic binding to STM32 ADC binding document: '664b9879f56e ("dt-bindings: iio: stm32-adc: add generic channel binding")' Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Stable-dep-of: deb7edbc27a6 ("ARM: dts: stm32: Add missing detach mailbox for DHCOM SoM") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 18 +++++---- .../boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 38 +++++++++++++++---- 2 files changed, 40 insertions(+), 16 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index c06edd2eacb0..e61df23d361a 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -80,17 +80,19 @@ &adc { vdda-supply = <&vdda>; vref-supply = <&vdda>; status = "okay"; +}; - adc1: adc@0 { - st,min-sample-time-nsecs = <5000>; - st,adc-channels = <0>; - status = "okay"; +&adc1 { + channel@0 { + reg = <0>; + st,min-sample-time-ns = <5000>; }; +}; - adc2: adc@100 { - st,adc-channels = <1>; - st,min-sample-time-nsecs = <5000>; - status = "okay"; +&adc2 { + channel@1 { + reg = <1>; + st,min-sample-time-ns = <5000>; }; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index dae602b7a54d..b7ba43865514 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -112,17 +112,39 @@ &adc { vdda-supply = <&vdda>; vref-supply = <&vdda>; status = "okay"; +}; - adc1: adc@0 { - st,adc-channels = <0 1 6>; - st,min-sample-time-nsecs = <5000>; - status = "okay"; +&adc1 { + channel@0 { + reg = <0>; + st,min-sample-time-ns = <5000>; }; - adc2: adc@100 { - st,adc-channels = <0 1 2>; - st,min-sample-time-nsecs = <5000>; - status = "okay"; + channel@1 { + reg = <1>; + st,min-sample-time-ns = <5000>; + }; + + channel@6 { + reg = <6>; + st,min-sample-time-ns = <5000>; + }; +}; + +&adc2 { + channel@0 { + reg = <0>; + st,min-sample-time-ns = <5000>; + }; + + channel@1 { + reg = <1>; + st,min-sample-time-ns = <5000>; + }; + + channel@2 { + reg = <2>; + st,min-sample-time-ns = <5000>; }; }; From 0765a80c160d5d058d43c1f7a27123773dbf256e Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 11 Jul 2023 15:09:07 +0200 Subject: [PATCH 0928/2093] ARM: dts: stm32: Add missing detach mailbox for DHCOM SoM [ Upstream commit deb7edbc27a6ec4d8f5edfd8519b7ed13cbd2a52 ] Add missing "detach" mailbox to this board to permit the CPU to inform the remote processor on a detach. This signal allows the remote processor firmware to stop IPC communication and to reinitialize the resources for a re-attach. Without this mailbox, detach is not possible and kernel log contains the following warning to, so make sure all the STM32MP15xx platform DTs are in sync regarding the mailboxes to fix the detach issue and the warning: " stm32-rproc 10000000.m4: mbox_request_channel_byname() could not locate channel named "detach" " Fixes: 6257dfc1c412 ("ARM: dts: stm32: Add coprocessor detach mbox on stm32mp15x-dkx boards") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index e61df23d361a..74a11ccc5333 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -416,8 +416,8 @@ &iwdg2 { &m4_rproc { memory-region = <&retram>, <&mcuram>, <&mcuram2>, <&vdev0vring0>, <&vdev0vring1>, <&vdev0buffer>; - mboxes = <&ipcc 0>, <&ipcc 1>, <&ipcc 2>; - mbox-names = "vq0", "vq1", "shutdown"; + mboxes = <&ipcc 0>, <&ipcc 1>, <&ipcc 2>, <&ipcc 3>; + mbox-names = "vq0", "vq1", "shutdown", "detach"; interrupt-parent = <&exti>; interrupts = <68 1>; status = "okay"; From 1f3b03863ef54de8013c902924f2382ad58d0196 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Tue, 20 Jun 2023 08:03:29 -0500 Subject: [PATCH 0929/2093] firmware: ti_sci: Use system_state to determine polling [ Upstream commit 9225bcdedf16297a346082e7d23b0e8434aa98ed ] Commit b9e8a7d950ff ("firmware: ti_sci: Switch transport to polled mode during system suspend") aims to resolve issues with tisci operations during system suspend operation. However, the system may enter a no_irq stage in various other usage modes, including power-off and restart. To determine if polling mode is appropriate, use the system_state instead. While at this, drop the unused is_suspending state variable and related helpers. Fixes: b9e8a7d950ff ("firmware: ti_sci: Switch transport to polled mode during system suspend") Reported-by: Francesco Dolcini Reported-by: Wadim Egorov Tested-by: Francesco Dolcini # Toradex Verdin AM62 Link: https://lore.kernel.org/r/20230620130329.4120443-1-nm@ti.com Closes: https://lore.kernel.org/all/ZGeHMjlnob2GFyHF@francesco-nb.int.toradex.com/ Signed-off-by: Nishanth Menon Signed-off-by: Sasha Levin --- drivers/firmware/ti_sci.c | 36 ++---------------------------------- 1 file changed, 2 insertions(+), 34 deletions(-) diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index 6281e7153b47..4c550cfbc086 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -97,7 +97,6 @@ struct ti_sci_desc { * @node: list head * @host_id: Host ID * @users: Number of users of this instance - * @is_suspending: Flag set to indicate in suspend path. */ struct ti_sci_info { struct device *dev; @@ -116,7 +115,6 @@ struct ti_sci_info { u8 host_id; /* protected by ti_sci_list_mutex */ int users; - bool is_suspending; }; #define cl_to_ti_sci_info(c) container_of(c, struct ti_sci_info, cl) @@ -418,14 +416,14 @@ static inline int ti_sci_do_xfer(struct ti_sci_info *info, ret = 0; - if (!info->is_suspending) { + if (system_state <= SYSTEM_RUNNING) { /* And we wait for the response. */ timeout = msecs_to_jiffies(info->desc->max_rx_timeout_ms); if (!wait_for_completion_timeout(&xfer->done, timeout)) ret = -ETIMEDOUT; } else { /* - * If we are suspending, we cannot use wait_for_completion_timeout + * If we are !running, we cannot use wait_for_completion_timeout * during noirq phase, so we must manually poll the completion. */ ret = read_poll_timeout_atomic(try_wait_for_completion, done_state, @@ -3282,35 +3280,6 @@ static int tisci_reboot_handler(struct notifier_block *nb, unsigned long mode, return NOTIFY_BAD; } -static void ti_sci_set_is_suspending(struct ti_sci_info *info, bool is_suspending) -{ - info->is_suspending = is_suspending; -} - -static int ti_sci_suspend(struct device *dev) -{ - struct ti_sci_info *info = dev_get_drvdata(dev); - /* - * We must switch operation to polled mode now as drivers and the genpd - * layer may make late TI SCI calls to change clock and device states - * from the noirq phase of suspend. - */ - ti_sci_set_is_suspending(info, true); - - return 0; -} - -static int ti_sci_resume(struct device *dev) -{ - struct ti_sci_info *info = dev_get_drvdata(dev); - - ti_sci_set_is_suspending(info, false); - - return 0; -} - -static DEFINE_SIMPLE_DEV_PM_OPS(ti_sci_pm_ops, ti_sci_suspend, ti_sci_resume); - /* Description for K2G */ static const struct ti_sci_desc ti_sci_pmmc_k2g_desc = { .default_host_id = 2, @@ -3519,7 +3488,6 @@ static struct platform_driver ti_sci_driver = { .driver = { .name = "ti-sci", .of_match_table = of_match_ptr(ti_sci_of_match), - .pm = &ti_sci_pm_ops, }, }; module_platform_driver(ti_sci_driver); From fd28ce30b525bccba4504499de625085a6def1c6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 7 Jul 2023 13:11:51 +0200 Subject: [PATCH 0930/2093] drm/amdgpu: avoid integer overflow warning in amdgpu_device_resize_fb_bar() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 822130b5e8834ab30ad410cf19a582e5014b9a85 ] On 32-bit architectures comparing a resource against a value larger than U32_MAX can cause a warning: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1344:18: error: result of comparison of constant 4294967296 with expression of type 'resource_size_t' (aka 'unsigned int') is always false [-Werror,-Wtautological-constant-out-of-range-compare] res->start > 0x100000000ull) ~~~~~~~~~~ ^ ~~~~~~~~~~~~~~ As gcc does not warn about this in dead code, add an IS_ENABLED() check at the start of the function. This will always return success but not actually resize the BAR on 32-bit architectures without high memory, which is exactly what we want here, as the driver can fall back to bank switching the VRAM access. Fixes: 31b8adab3247 ("drm/amdgpu: require a root bus window above 4GB for BAR resize") Reviewed-by: Christian König Signed-off-by: Arnd Bergmann Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e6427a00cf6d..9aac9e755609 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1212,6 +1212,9 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev) u16 cmd; int r; + if (!IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT)) + return 0; + /* Bypass for VF */ if (amdgpu_sriov_vf(adev)) return 0; From ee1d740374aa73fb32857685eb05167ad87458cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 7 Jul 2023 13:40:02 +0200 Subject: [PATCH 0931/2093] ARM: dts: BCM53573: Drop nonexistent #usb-cells MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 05d2c3d552b8c92fc397377d9d1112fc58e2cd59 ] Such property simply doesn't exist (is not documented or used anywhere). This fixes: arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dtb: usb@d000: Unevaluated properties are not allowed ('#usb-cells' was unexpected) From schema: Documentation/devicetree/bindings/usb/generic-ohci.yaml Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230707114004.2740-2-zajec5@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm53573.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/boot/dts/bcm53573.dtsi b/arch/arm/boot/dts/bcm53573.dtsi index 3f03a381db0f..3cb71829e859 100644 --- a/arch/arm/boot/dts/bcm53573.dtsi +++ b/arch/arm/boot/dts/bcm53573.dtsi @@ -156,8 +156,6 @@ ehci_port2: port@2 { }; ohci: usb@d000 { - #usb-cells = <0>; - compatible = "generic-ohci"; reg = <0xd000 0x1000>; interrupt-parent = <&gic>; From ab5154ae26c446136827451e907db45d7b92a76f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 7 Jul 2023 13:40:03 +0200 Subject: [PATCH 0932/2093] ARM: dts: BCM53573: Add cells sizes to PCIe node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3392ef368d9b04622fe758b1079b512664b6110a ] This fixes: arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dtb: pcie@2000: '#address-cells' is a required property From schema: /lib/python3.10/site-packages/dtschema/schemas/pci/pci-bus.yaml arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dtb: pcie@2000: '#size-cells' is a required property From schema: /lib/python3.10/site-packages/dtschema/schemas/pci/pci-bus.yaml Two properties that need to be added later are "device_type" and "ranges". Adding "device_type" on its own causes a new warning and the value of "ranges" needs to be determined yet. Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230707114004.2740-3-zajec5@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm53573.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/boot/dts/bcm53573.dtsi b/arch/arm/boot/dts/bcm53573.dtsi index 3cb71829e859..eed1a6147f0b 100644 --- a/arch/arm/boot/dts/bcm53573.dtsi +++ b/arch/arm/boot/dts/bcm53573.dtsi @@ -127,6 +127,9 @@ uart0: serial@300 { pcie0: pcie@2000 { reg = <0x00002000 0x1000>; + + #address-cells = <3>; + #size-cells = <2>; }; usb2: usb2@4000 { From f5ff6897094fa161be55786cb9e5d5b1bf7a9049 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 7 Jul 2023 13:40:04 +0200 Subject: [PATCH 0933/2093] ARM: dts: BCM53573: Use updated "spi-gpio" binding properties MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2c0fd6b3d0778ceab40205315ccef74568490f17 ] Switch away from deprecated properties. This fixes: arch/arm/boot/dts/broadcom/bcm947189acdbmr.dtb: spi: gpio-sck: False schema does not allow [[3, 21, 0]] From schema: Documentation/devicetree/bindings/spi/spi-gpio.yaml arch/arm/boot/dts/broadcom/bcm947189acdbmr.dtb: spi: gpio-miso: False schema does not allow [[3, 22, 0]] From schema: Documentation/devicetree/bindings/spi/spi-gpio.yaml arch/arm/boot/dts/broadcom/bcm947189acdbmr.dtb: spi: gpio-mosi: False schema does not allow [[3, 23, 0]] From schema: Documentation/devicetree/bindings/spi/spi-gpio.yaml arch/arm/boot/dts/broadcom/bcm947189acdbmr.dtb: spi: 'sck-gpios' is a required property From schema: Documentation/devicetree/bindings/spi/spi-gpio.yaml arch/arm/boot/dts/broadcom/bcm947189acdbmr.dtb: spi: Unevaluated properties are not allowed ('gpio-miso', 'gpio-mosi', 'gpio-sck' were unexpected) From schema: Documentation/devicetree/bindings/spi/spi-gpio.yaml Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230707114004.2740-4-zajec5@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm947189acdbmr.dts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/bcm947189acdbmr.dts b/arch/arm/boot/dts/bcm947189acdbmr.dts index 16e70a264faf..458bb6e2f572 100644 --- a/arch/arm/boot/dts/bcm947189acdbmr.dts +++ b/arch/arm/boot/dts/bcm947189acdbmr.dts @@ -60,9 +60,9 @@ button-wps { spi { compatible = "spi-gpio"; num-chipselects = <1>; - gpio-sck = <&chipcommon 21 0>; - gpio-miso = <&chipcommon 22 0>; - gpio-mosi = <&chipcommon 23 0>; + sck-gpios = <&chipcommon 21 0>; + miso-gpios = <&chipcommon 22 0>; + mosi-gpios = <&chipcommon 23 0>; cs-gpios = <&chipcommon 24 0>; #address-cells = <1>; #size-cells = <0>; From 0f0e6963705a9da7a138216077855cd8f26170a9 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 3 Jul 2023 12:36:17 +0100 Subject: [PATCH 0934/2093] arm64: tegra: Fix HSUART for Jetson AGX Orin [ Upstream commit 861dbb2b15b1049113887fb95e856f7123eea0cc ] After commit 71de0a054d0e ("arm64: tegra: Drop serial clock-names and reset-names") was applied, the HSUART failed to probe and the following error is seen: serial-tegra 3100000.serial: Couldn't get the reset serial-tegra: probe of 3100000.serial failed with error -2 Commit 71de0a054d0e ("arm64: tegra: Drop serial clock-names and reset-names") is correct because the "reset-names" property is not needed for 8250 UARTs. However, the "reset-names" is required for the HSUART and should have been populated as part of commit ff578db7b693 ("arm64: tegra: Enable UART instance on 40-pin header") that enabled the HSUART for Jetson AGX Orin. Fix this by populating the "reset-names" property for the HSUART on Jetson AGX Orin. Fixes: ff578db7b693 ("arm64: tegra: Enable UART instance on 40-pin header") Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts index 57ab75328814..f094011be9ed 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts @@ -2004,6 +2004,7 @@ interrupt-controller@2a40000 { serial@3100000 { compatible = "nvidia,tegra194-hsuart"; + reset-names = "serial"; status = "okay"; }; From 6fd913f0f63f8b3ea9f8af2e97abcec24a9cd713 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 11 Jul 2023 08:30:11 +0200 Subject: [PATCH 0935/2093] arm64: dts: qcom: sm8250-sony-xperia: correct GPIO keys wakeup again [ Upstream commit b8fbeea0253211d97c579eae787274633d3eaf0d ] gpio-keys,wakeup is a deprecated property: m8250-sony-xperia-edo-pdx206.dtb: gpio-keys: key-camera-focus: Unevaluated properties are not allowed ('gpio-key,wakeup' was unexpected) Fixes: a422c6a91a66 ("arm64: dts: qcom: sm8250-edo: Rectify gpio-keys") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230711063011.16222-1-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi index 259798a95974..3b710c6a326a 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi @@ -60,7 +60,7 @@ key-camera-focus { gpios = <&pm8150b_gpios 2 GPIO_ACTIVE_LOW>; debounce-interval = <15>; linux,can-disable; - gpio-key,wakeup; + wakeup-source; }; key-camera-snapshot { @@ -69,7 +69,7 @@ key-camera-snapshot { gpios = <&pm8150b_gpios 1 GPIO_ACTIVE_LOW>; debounce-interval = <15>; linux,can-disable; - gpio-key,wakeup; + wakeup-source; }; key-vol-down { From cd1ba241d21ece6fcf3a6e28e3b98c01750bda9d Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jun 2023 22:00:25 +0200 Subject: [PATCH 0936/2093] arm64: dts: qcom: pm6150l: Add missing short interrupt [ Upstream commit 7e1f024ef0d1da456f61d00f01dc3287ede915b3 ] Add the missing short interrupt. This fixes the schema warning: wled@d800: interrupt-names: ['ovp'] is too short Fixes: fe508ced49dd ("arm64: dts: qcom: pm6150l: Add wled node") Signed-off-by: Konrad Dybcio Reviewed-by: Luca Weiss Link: https://lore.kernel.org/r/20230626-topic-bindingsfixups-v1-3-254ae8642e69@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pm6150l.dtsi | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/pm6150l.dtsi b/arch/arm64/boot/dts/qcom/pm6150l.dtsi index f02c223ef448..06d729ff65a9 100644 --- a/arch/arm64/boot/dts/qcom/pm6150l.dtsi +++ b/arch/arm64/boot/dts/qcom/pm6150l.dtsi @@ -75,8 +75,9 @@ pm6150l_lsid5: pmic@5 { pm6150l_wled: leds@d800 { compatible = "qcom,pm6150l-wled"; reg = <0xd800>, <0xd900>; - interrupts = <0x5 0xd8 0x1 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "ovp"; + interrupts = <0x5 0xd8 0x1 IRQ_TYPE_EDGE_RISING>, + <0x5 0xd8 0x2 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "ovp", "short"; label = "backlight"; status = "disabled"; From 31fe89ccf5a032a736c7ac5b82040b8f1a2d482e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jun 2023 22:00:26 +0200 Subject: [PATCH 0937/2093] arm64: dts: qcom: pm660l: Add missing short interrupt [ Upstream commit 9a4ac09db3c7413e334b4abd6b2f6de8930dd781 ] Add the missing short interrupt. This fixes the schema warning: wled@d800: interrupt-names: ['ovp'] is too short Fixes: 7b56a804e58b ("arm64: dts: qcom: pm660l: Add WLED support") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230626-topic-bindingsfixups-v1-4-254ae8642e69@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pm660l.dtsi | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/pm660l.dtsi b/arch/arm64/boot/dts/qcom/pm660l.dtsi index 8aa0a5078772..88606b996d69 100644 --- a/arch/arm64/boot/dts/qcom/pm660l.dtsi +++ b/arch/arm64/boot/dts/qcom/pm660l.dtsi @@ -74,8 +74,9 @@ pm660l_lpg: pwm { pm660l_wled: leds@d800 { compatible = "qcom,pm660l-wled"; reg = <0xd800>, <0xd900>; - interrupts = <0x3 0xd8 0x1 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "ovp"; + interrupts = <0x3 0xd8 0x1 IRQ_TYPE_EDGE_RISING>, + <0x3 0xd8 0x2 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "ovp", "short"; label = "backlight"; status = "disabled"; From ee5e1d6480efdc179777a91c92affe85ae6d1633 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jun 2023 22:00:28 +0200 Subject: [PATCH 0938/2093] arm64: dts: qcom: pmi8994: Add missing OVP interrupt [ Upstream commit 8db94432690371b1736e9a2566a9b3d8a73d5a97 ] Add the missing OVP interrupt. This fixes the schema warning: wled@d800: interrupt-names: ['short'] is too short Fixes: 37aa540cbd30 ("arm64: dts: qcom: pmi8994: Add WLED node") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230626-topic-bindingsfixups-v1-6-254ae8642e69@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/pmi8994.dtsi | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/pmi8994.dtsi b/arch/arm64/boot/dts/qcom/pmi8994.dtsi index 82b60e988d0f..49902a3e161d 100644 --- a/arch/arm64/boot/dts/qcom/pmi8994.dtsi +++ b/arch/arm64/boot/dts/qcom/pmi8994.dtsi @@ -54,8 +54,9 @@ pmi8994_spmi_regulators: regulators { pmi8994_wled: wled@d800 { compatible = "qcom,pmi8994-wled"; reg = <0xd800>, <0xd900>; - interrupts = <3 0xd8 0x02 IRQ_TYPE_EDGE_RISING>; - interrupt-names = "short"; + interrupts = <0x3 0xd8 0x1 IRQ_TYPE_EDGE_RISING>, + <0x3 0xd8 0x2 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "ovp", "short"; qcom,cabc; qcom,external-pfet; status = "disabled"; From 800bf8a2226e45179cf46da24c166d38a733a46f Mon Sep 17 00:00:00 2001 From: Diogo Ivo Date: Fri, 14 Jul 2023 11:10:17 +0100 Subject: [PATCH 0939/2093] arm64: tegra: Fix HSUART for Smaug [ Upstream commit 590bfe51838f6345a6a3288507661dc9b7208464 ] After commit 71de0a054d0e ("arm64: tegra: Drop serial clock-names and reset-names") was applied, the HSUART failed to probe and the following error is seen: serial-tegra 70006300.serial: Couldn't get the reset serial-tegra: probe of 70006300.serial failed with error -2 Commit 71de0a054d0e ("arm64: tegra: Drop serial clock-names and reset-names") is correct because the "reset-names" property is not needed for 8250 UARTs. However, the "reset-names" is required for the HSUART and should have been populated as part of commit a63c0cd83720c ("arm64: dts: tegra: smaug: Add Bluetooth node") that enabled the HSUART for the Pixel C. Fix this by populating the "reset-names" property for the HSUART on the Pixel C. Fixes: a63c0cd83720 ("arm64: dts: tegra: smaug: Add Bluetooth node") Signed-off-by: Diogo Ivo Reviewed-by: Jon Hunter Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/nvidia/tegra210-smaug.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts index 7c569695b705..2b4dbfac84a7 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts +++ b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts @@ -1312,6 +1312,7 @@ serial@70006000 { uartd: serial@70006300 { compatible = "nvidia,tegra30-hsuart"; + reset-names = "serial"; status = "okay"; bluetooth { From 7db90dd1c5a45025cca496b743957abfa15022b3 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 14 Apr 2023 16:38:10 +0200 Subject: [PATCH 0940/2093] drm/etnaviv: fix dumping of active MMU context [ Upstream commit 20faf2005ec85fa1a6acc9a74ff27de667f90576 ] gpu->mmu_context is the MMU context of the last job in the HW queue, which isn't necessarily the same as the context from the bad job. Dump the MMU context from the scheduler determined bad submit to make it work as intended. Fixes: 17e4660ae3d7 ("drm/etnaviv: implement per-process address spaces on MMUv2") Signed-off-by: Lucas Stach Reviewed-by: Christian Gmeiner Signed-off-by: Sasha Levin --- drivers/gpu/drm/etnaviv/etnaviv_dump.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index f418e0b75772..0edcf8ceb4a7 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -125,9 +125,9 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) return; etnaviv_dump_core = false; - mutex_lock(&gpu->mmu_context->lock); + mutex_lock(&submit->mmu_context->lock); - mmu_size = etnaviv_iommu_dump_size(gpu->mmu_context); + mmu_size = etnaviv_iommu_dump_size(submit->mmu_context); /* We always dump registers, mmu, ring, hanging cmdbuf and end marker */ n_obj = 5; @@ -157,7 +157,7 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); if (!iter.start) { - mutex_unlock(&gpu->mmu_context->lock); + mutex_unlock(&submit->mmu_context->lock); dev_warn(gpu->dev, "failed to allocate devcoredump file\n"); return; } @@ -169,18 +169,18 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) memset(iter.hdr, 0, iter.data - iter.start); etnaviv_core_dump_registers(&iter, gpu); - etnaviv_core_dump_mmu(&iter, gpu->mmu_context, mmu_size); + etnaviv_core_dump_mmu(&iter, submit->mmu_context, mmu_size); etnaviv_core_dump_mem(&iter, ETDUMP_BUF_RING, gpu->buffer.vaddr, gpu->buffer.size, etnaviv_cmdbuf_get_va(&gpu->buffer, - &gpu->mmu_context->cmdbuf_mapping)); + &submit->mmu_context->cmdbuf_mapping)); etnaviv_core_dump_mem(&iter, ETDUMP_BUF_CMD, submit->cmdbuf.vaddr, submit->cmdbuf.size, etnaviv_cmdbuf_get_va(&submit->cmdbuf, - &gpu->mmu_context->cmdbuf_mapping)); + &submit->mmu_context->cmdbuf_mapping)); - mutex_unlock(&gpu->mmu_context->lock); + mutex_unlock(&submit->mmu_context->lock); /* Reserve space for the bomap */ if (n_bomap_pages) { From e5e0ec8ff16089a0801cd6a1748003697b6b901f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 7 Jul 2023 11:42:38 +0200 Subject: [PATCH 0941/2093] block: cleanup queue_wc_store [ Upstream commit c4e21bcd0f9d01f9c5d6c52007f5541871a5b1de ] Get rid of the local queue_wc_store variable and handling setting and clearing the QUEUE_FLAG_WC flag diretly instead the if / else if. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230707094239.107968-2-hch@lst.de Signed-off-by: Jens Axboe Stable-dep-of: 43c9835b144c ("block: don't allow enabling a cache on devices that don't support it") Signed-off-by: Sasha Levin --- block/blk-sysfs.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e71b3b43927c..4f34525bafac 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -528,21 +528,13 @@ static ssize_t queue_wc_show(struct request_queue *q, char *page) static ssize_t queue_wc_store(struct request_queue *q, const char *page, size_t count) { - int set = -1; - if (!strncmp(page, "write back", 10)) - set = 1; + blk_queue_flag_set(QUEUE_FLAG_WC, q); else if (!strncmp(page, "write through", 13) || !strncmp(page, "none", 4)) - set = 0; - - if (set == -1) - return -EINVAL; - - if (set) - blk_queue_flag_set(QUEUE_FLAG_WC, q); - else blk_queue_flag_clear(QUEUE_FLAG_WC, q); + else + return -EINVAL; return count; } From 00c0b2825bb5df26c339cef1d32db6a8755de203 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 7 Jul 2023 11:42:39 +0200 Subject: [PATCH 0942/2093] block: don't allow enabling a cache on devices that don't support it [ Upstream commit 43c9835b144c7ce29efe142d662529662a9eb376 ] Currently the write_cache attribute allows enabling the QUEUE_FLAG_WC flag on devices that never claimed the capability. Fix that by adding a QUEUE_FLAG_HW_WC flag that is set by blk_queue_write_cache and guards re-enabling the cache through sysfs. Note that any rescan that calls blk_queue_write_cache will still re-enable the write cache as in the current code. Fixes: 93e9d8e836cb ("block: add ability to flag write back caching on a device") Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230707094239.107968-3-hch@lst.de Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-settings.c | 7 +++++-- block/blk-sysfs.c | 11 +++++++---- include/linux/blkdev.h | 1 + 3 files changed, 13 insertions(+), 6 deletions(-) diff --git a/block/blk-settings.c b/block/blk-settings.c index 291cf9df7fc2..86ff375c00ce 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -824,10 +824,13 @@ EXPORT_SYMBOL(blk_set_queue_depth); */ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) { - if (wc) + if (wc) { + blk_queue_flag_set(QUEUE_FLAG_HW_WC, q); blk_queue_flag_set(QUEUE_FLAG_WC, q); - else + } else { + blk_queue_flag_clear(QUEUE_FLAG_HW_WC, q); blk_queue_flag_clear(QUEUE_FLAG_WC, q); + } if (fua) blk_queue_flag_set(QUEUE_FLAG_FUA, q); else diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 4f34525bafac..a582ea0da74f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -528,13 +528,16 @@ static ssize_t queue_wc_show(struct request_queue *q, char *page) static ssize_t queue_wc_store(struct request_queue *q, const char *page, size_t count) { - if (!strncmp(page, "write back", 10)) + if (!strncmp(page, "write back", 10)) { + if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags)) + return -EINVAL; blk_queue_flag_set(QUEUE_FLAG_WC, q); - else if (!strncmp(page, "write through", 13) || - !strncmp(page, "none", 4)) + } else if (!strncmp(page, "write through", 13) || + !strncmp(page, "none", 4)) { blk_queue_flag_clear(QUEUE_FLAG_WC, q); - else + } else { return -EINVAL; + } return count; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 427e79ac7219..57674b3c5877 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -565,6 +565,7 @@ struct request_queue { #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ +#define QUEUE_FLAG_HW_WC 18 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ From d309b170ea704f8d2bff661228a2a4b16eae2d46 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 10 Jul 2023 09:36:14 +0200 Subject: [PATCH 0943/2093] x86/mm: Fix PAT bit missing from page protection modify mask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 548cb932051fb6232ac983ed6673dae7bdf3cf4c ] Visible glitches have been observed when running graphics applications on Linux under Xen hypervisor. Those observations have been confirmed with failures from kms_pwrite_crc Intel GPU test that verifies data coherency of DRM frame buffer objects using hardware CRC checksums calculated by display controllers, exposed to userspace via debugfs. Affected processing paths have then been identified with new IGT test variants that mmap the objects using different methods and caching modes [1]. When running as a Xen PV guest, Linux uses Xen provided PAT configuration which is different from its native one. In particular, Xen specific PTE encoding of write-combining caching, likely used by graphics applications, differs from the Linux default one found among statically defined minimal set of supported modes. Since Xen defines PTE encoding of the WC mode as _PAGE_PAT, it no longer belongs to the minimal set, depends on correct handling of _PAGE_PAT bit, and can be mismatched with write-back caching. When a user calls mmap() for a DRM buffer object, DRM device specific .mmap file operation, called from mmap_region(), takes care of setting PTE encoding bits in a vm_page_prot field of an associated virtual memory area structure. Unfortunately, _PAGE_PAT bit is not preserved when the vma's .vm_flags are then applied to .vm_page_prot via vm_set_page_prot(). Bits to be preserved are determined with _PAGE_CHG_MASK symbol that doesn't cover _PAGE_PAT. As a consequence, WB caching is requested instead of WC when running under Xen (also, WP is silently changed to WT, and UC downgraded to UC_MINUS). When running on bare metal, WC is not affected, but WP and WT extra modes are unintentionally replaced with WC and UC, respectively. WP and WT modes, encoded with _PAGE_PAT bit set, were introduced by commit 281d4078bec3 ("x86: Make page cache mode a real type"). Care was taken to extend _PAGE_CACHE_MASK symbol with that additional bit, but that symbol has never been used for identification of bits preserved when applying page protection flags. Support for all cache modes under Xen, including the problematic WC mode, was then introduced by commit 47591df50512 ("xen: Support Xen pv-domains using PAT"). The issue needs to be fixed by including _PAGE_PAT bit into a bitmask used by pgprot_modify() for selecting bits to be preserved. We can do that either internally to pgprot_modify() (as initially proposed), or by making _PAGE_PAT a part of _PAGE_CHG_MASK. If we go for the latter then, since _PAGE_PAT is the same as _PAGE_PSE, we need to note that _HPAGE_CHG_MASK -- a huge pmds' counterpart of _PAGE_CHG_MASK, introduced by commit c489f1257b8c ("thp: add pmd_modify"), defined as (_PAGE_CHG_MASK | _PAGE_PSE) -- will no longer differ from _PAGE_CHG_MASK. If such modification of _PAGE_CHG_MASK was irrelevant to its users then one might wonder why that new _HPAGE_CHG_MASK symbol was introduced instead of reusing the existing one with that otherwise irrelevant bit (_PAGE_PSE in that case) added. Add _PAGE_PAT to _PAGE_CHG_MASK and _PAGE_PAT_LARGE to _HPAGE_CHG_MASK for symmetry. Split out common bits from both symbols to a common symbol for clarity. [ dhansen: tweak the solution changelog description ] [1] https://gitlab.freedesktop.org/drm/igt-gpu-tools/-/commit/0f0754413f14 Fixes: 281d4078bec3 ("x86: Make page cache mode a real type") Signed-off-by: Janusz Krzysztofik Signed-off-by: Dave Hansen Reviewed-by: Andi Shyti Reviewed-by: Juergen Gross Tested-by: Marek Marczykowski-Górecki Link: https://gitlab.freedesktop.org/drm/intel/-/issues/7648 Link: https://lore.kernel.org/all/20230710073613.8006-2-janusz.krzysztofik%40linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/include/asm/pgtable_types.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index aa174fed3a71..f6116b66f289 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -125,11 +125,12 @@ * instance, and is *not* included in this mask since * pte_modify() does modify it. */ -#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ - _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \ - _PAGE_UFFD_WP) -#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) +#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ + _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |\ + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \ + _PAGE_UFFD_WP) +#define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) +#define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) /* * The cache modes defined here are used to translate between pure SW usage From ba1ca2cf4d0083990ef279dc3aeb0dde7efe9752 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 10 Jul 2023 17:09:27 +0800 Subject: [PATCH 0944/2093] drm/bridge: anx7625: Use common macros for DP power sequencing commands MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2ba776f903cb7157e80b5f314fb0b4faf6ea6958 ] The DRM DP code has macros for the DP power sequencing commands. Use them in the anx7625 driver instead of raw numbers. Fixes: 548b512e144f ("drm/bridge: anx7625: send DPCD command to downstream") Fixes: 27f26359de9b ("drm/bridge: anx7625: Set downstream sink into normal status") Signed-off-by: Chen-Yu Tsai Reviewed-by: Nícolas F. R. A. Prado Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230710090929.1873646-1-wenst@chromium.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/analogix/anx7625.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 213263ad6a06..36ec9dedadfe 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -933,8 +933,8 @@ static void anx7625_dp_start(struct anx7625_data *ctx) dev_dbg(dev, "set downstream sink into normal\n"); /* Downstream sink enter into normal mode */ - data = 1; - ret = anx7625_aux_trans(ctx, DP_AUX_NATIVE_WRITE, 0x000600, 1, &data); + data = DP_SET_POWER_D0; + ret = anx7625_aux_trans(ctx, DP_AUX_NATIVE_WRITE, DP_SET_POWER, 1, &data); if (ret < 0) dev_err(dev, "IO error : set sink into normal mode fail\n"); @@ -973,8 +973,8 @@ static void anx7625_dp_stop(struct anx7625_data *ctx) dev_dbg(dev, "notify downstream enter into standby\n"); /* Downstream monitor enter into standby mode */ - data = 2; - ret |= anx7625_aux_trans(ctx, DP_AUX_NATIVE_WRITE, 0x000600, 1, &data); + data = DP_SET_POWER_D3; + ret |= anx7625_aux_trans(ctx, DP_AUX_NATIVE_WRITE, DP_SET_POWER, 1, &data); if (ret < 0) DRM_DEV_ERROR(dev, "IO error : mute video fail\n"); From 075ee661ba670dab83f8d890d352ee2c92f953fe Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 10 Jul 2023 17:12:01 +0800 Subject: [PATCH 0945/2093] drm/bridge: anx7625: Use common macros for HDCP capabilities MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 41639b3a8b0f1f194dfe0577d99db70613f78626 ] The DRM DP code has macros for the DP HDCP capabilities. Use them in the anx7625 driver instead of raw numbers. Fixes: cd1637c7e480 ("drm/bridge: anx7625: add HDCP support") Suggested-by: Nícolas F. R. A. Prado Signed-off-by: Chen-Yu Tsai Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230710091203.1874317-1-wenst@chromium.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/analogix/anx7625.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 36ec9dedadfe..cf86cc05b7fc 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -874,11 +874,11 @@ static int anx7625_hdcp_enable(struct anx7625_data *ctx) } /* Read downstream capability */ - ret = anx7625_aux_trans(ctx, DP_AUX_NATIVE_READ, 0x68028, 1, &bcap); + ret = anx7625_aux_trans(ctx, DP_AUX_NATIVE_READ, DP_AUX_HDCP_BCAPS, 1, &bcap); if (ret < 0) return ret; - if (!(bcap & 0x01)) { + if (!(bcap & DP_BCAPS_HDCP_CAPABLE)) { pr_warn("downstream not support HDCP 1.4, cap(%x).\n", bcap); return 0; } From 4e184a73203c0036fdf0a2ef702ea2ea79871cc4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 13 Jul 2023 17:29:25 +0200 Subject: [PATCH 0946/2093] ARM: dts: samsung: s3c6410-mini6410: correct ethernet reg addresses (split) [ Upstream commit cf0cb2af6a18f28b84f9f1416bff50ca60d6e98a ] The davicom,dm9000 Ethernet Controller accepts two reg addresses. Fixes: a43736deb47d ("ARM: dts: Add dts file for S3C6410-based Mini6410 board") Reviewed-by: Alim Akhtar Link: https://lore.kernel.org/r/20230713152926.82884-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm/boot/dts/s3c6410-mini6410.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts index 17097da36f5e..0b07b3c31960 100644 --- a/arch/arm/boot/dts/s3c6410-mini6410.dts +++ b/arch/arm/boot/dts/s3c6410-mini6410.dts @@ -51,7 +51,7 @@ srom-cs1-bus@18000000 { ethernet@18000000 { compatible = "davicom,dm9000"; - reg = <0x18000000 0x2 0x18000004 0x2>; + reg = <0x18000000 0x2>, <0x18000004 0x2>; interrupt-parent = <&gpn>; interrupts = <7 IRQ_TYPE_LEVEL_HIGH>; davicom,no-eeprom; From 9a91a5466ab14f919d9a9411c55a1886dd6cab2e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 21 Apr 2023 11:57:21 +0200 Subject: [PATCH 0947/2093] ARM: dts: s5pv210: add dummy 5V regulator for backlight on SMDKv210 [ Upstream commit b77904ba177a9c67b6dbc3637fdf1faa22df6e5c ] Backlight is supplied by DC5V regulator. The DTS has no PMIC node, so just add a regulator-fixed to solve it and fix dtbs_check warning: s5pv210-smdkv210.dtb: backlight: 'power-supply' is a required property Link: https://lore.kernel.org/r/20230421095721.31857-4-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Stable-dep-of: 982655cb0e7f ("ARM: dts: samsung: s5pv210-smdkv210: correct ethernet reg addresses (split)") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/s5pv210-smdkv210.dts | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm/boot/dts/s5pv210-smdkv210.dts b/arch/arm/boot/dts/s5pv210-smdkv210.dts index fbae768d65e2..6e26c67e0a26 100644 --- a/arch/arm/boot/dts/s5pv210-smdkv210.dts +++ b/arch/arm/boot/dts/s5pv210-smdkv210.dts @@ -55,6 +55,14 @@ backlight { default-brightness-level = <6>; pinctrl-names = "default"; pinctrl-0 = <&pwm3_out>; + power-supply = <&dc5v_reg>; + }; + + dc5v_reg: regulator-0 { + compatible = "regulator-fixed"; + regulator-name = "DC5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; }; }; From 1a73147347432feebfaa3fa08e5c473d1512eee3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 13 Jul 2023 17:29:26 +0200 Subject: [PATCH 0948/2093] ARM: dts: samsung: s5pv210-smdkv210: correct ethernet reg addresses (split) [ Upstream commit 982655cb0e7f18934d7532c32366e574ad61dbd7 ] The davicom,dm9000 Ethernet Controller accepts two reg addresses. Fixes: b672b27d232e ("ARM: dts: Add Device tree for s5pc110/s5pv210 boards") Reviewed-by: Alim Akhtar Link: https://lore.kernel.org/r/20230713152926.82884-2-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm/boot/dts/s5pv210-smdkv210.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/s5pv210-smdkv210.dts b/arch/arm/boot/dts/s5pv210-smdkv210.dts index 6e26c67e0a26..901e7197b136 100644 --- a/arch/arm/boot/dts/s5pv210-smdkv210.dts +++ b/arch/arm/boot/dts/s5pv210-smdkv210.dts @@ -41,7 +41,7 @@ pmic_ap_clk: clock-0 { ethernet@a8000000 { compatible = "davicom,dm9000"; - reg = <0xA8000000 0x2 0xA8000002 0x2>; + reg = <0xa8000000 0x2>, <0xa8000002 0x2>; interrupt-parent = <&gph1>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; local-mac-address = [00 00 de ad be ef]; From b9fa4e10b5cfba228b1d7cec60d722cb3618694c Mon Sep 17 00:00:00 2001 From: Bogdan Togorean Date: Wed, 19 Jul 2023 09:01:43 +0300 Subject: [PATCH 0949/2093] drm: adv7511: Fix low refresh rate register for ADV7533/5 [ Upstream commit d281eeaa4de2636ff0c8e6ae387bb07b50e5fcbb ] For ADV7533 and ADV7535 low refresh rate is selected using bits [3:2] of 0x4a main register. So depending on ADV model write 0xfb or 0x4a register. Fixes: 2437e7cd88e8 ("drm/bridge: adv7533: Initial support for ADV7533") Reviewed-by: Robert Foss Reviewed-by: Nuno Sa Signed-off-by: Bogdan Togorean Signed-off-by: Alexandru Ardelean Reviewed-by: Frieder Schrempf Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230719060143.63649-1-alex@shruggie.ro Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/adv7511/adv7511_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 78b72739e5c3..9f9874acfb2b 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -786,8 +786,13 @@ static void adv7511_mode_set(struct adv7511 *adv7511, else low_refresh_rate = ADV7511_LOW_REFRESH_RATE_NONE; - regmap_update_bits(adv7511->regmap, 0xfb, - 0x6, low_refresh_rate << 1); + if (adv7511->type == ADV7511) + regmap_update_bits(adv7511->regmap, 0xfb, + 0x6, low_refresh_rate << 1); + else + regmap_update_bits(adv7511->regmap, 0x4a, + 0xc, low_refresh_rate << 2); + regmap_update_bits(adv7511->regmap, 0x17, 0x60, (vsync_polarity << 6) | (hsync_polarity << 5)); From a80621bb23dc388e03f5d807c34bdc9050bb20c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 13 Jul 2023 13:11:45 +0200 Subject: [PATCH 0950/2093] ARM: dts: BCM53573: Fix Ethernet info for Luxul devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 44ad8207806973f4e4f7d870fff36cc01f494250 ] Both Luxul's XAP devices (XAP-810 and XAP-1440) are access points that use a non-default design. They don't include switch but have a single Ethernet port and BCM54210E PHY connected to the Ethernet controller's MDIO bus. Support for those devices regressed due to two changes: 1. Describing MDIO bus with switch After commit 9fb90ae6cae7 ("ARM: dts: BCM53573: Describe on-SoC BCM53125 rev 4 switch") Linux stopped probing for MDIO devices. 2. Dropping hardcoded BCM54210E delays In commit fea7fda7f50a ("net: phy: broadcom: Fix RGMII delays configuration for BCM54210E") support for other PHY modes was added but that requires a proper "phy-mode" value in DT. Both above changes are correct (they don't need to be reverted or anything) but they need this fix for DT data to be correct and for Linux to work properly. Fixes: 9fb90ae6cae7 ("ARM: dts: BCM53573: Describe on-SoC BCM53125 rev 4 switch") Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230713111145.14864-1-zajec5@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts | 13 +++++++++++++ arch/arm/boot/dts/bcm47189-luxul-xap-810.dts | 13 +++++++++++++ 2 files changed, 26 insertions(+) diff --git a/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts b/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts index e20b6d2eb274..1e23e0a80781 100644 --- a/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts +++ b/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts @@ -46,3 +46,16 @@ button-restart { }; }; }; + +&gmac0 { + phy-mode = "rgmii"; + phy-handle = <&bcm54210e>; + + mdio { + /delete-node/ switch@1e; + + bcm54210e: ethernet-phy@0 { + reg = <0>; + }; + }; +}; diff --git a/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts b/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts index 9d863570fcf3..5dbb950c8113 100644 --- a/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts +++ b/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts @@ -83,3 +83,16 @@ pcie0_chipcommon: chipcommon@0 { }; }; }; + +&gmac0 { + phy-mode = "rgmii"; + phy-handle = <&bcm54210e>; + + mdio { + /delete-node/ switch@1e; + + bcm54210e: ethernet-phy@0 { + reg = <0>; + }; + }; +}; From 4aaced381c69dd76266e52d2b4e7239dac4cf3c5 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 20 Jul 2023 11:10:48 +0530 Subject: [PATCH 0951/2093] arm64: dts: qcom: sdm845: Add missing RPMh power domain to GCC [ Upstream commit 4b6ea15c0a1122422b44bf6c47a3c22fc8d46777 ] GCC and it's GDSCs are under the RPMh CX power domain. So let's add the missing RPMh power domain to the GCC node. Fixes: 6d4cf750d03a ("arm64: dts: sdm845: Add minimal dts/dtsi files for sdm845 SoC and MTP") Reviewed-by: Konrad Dybcio Co-developed-by: Krzysztof Kozlowski Signed-off-by: Krzysztof Kozlowski Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230720054100.9940-4-manivannan.sadhasivam@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index b7ba70857d0a..375c86633b5b 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -1099,6 +1099,7 @@ gcc: clock-controller@100000 { #clock-cells = <1>; #reset-cells = <1>; #power-domain-cells = <1>; + power-domains = <&rpmhpd SDM845_CX>; }; qfprom@784000 { From 5ccd294df2650e60d364b453bc6fc0333079f86f Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 20 Jul 2023 11:10:49 +0530 Subject: [PATCH 0952/2093] arm64: dts: qcom: sdm845: Fix the min frequency of "ice_core_clk" [ Upstream commit bbbef6e24bc4493602df68b052f6f48d48e3184a ] Minimum frequency of the "ice_core_clk" should be 75MHz as specified in the downstream vendor devicetree. So fix it! https://git.codelinaro.org/clo/la/kernel/msm-4.9/-/blob/LA.UM.7.3.r1-09300-sdm845.0/arch/arm64/boot/dts/qcom/sdm845.dtsi Fixes: 433f9a57298f ("arm64: dts: sdm845: add Inline Crypto Engine registers and clock") Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230720054100.9940-5-manivannan.sadhasivam@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 375c86633b5b..52c9f5639f8a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -2521,7 +2521,7 @@ ufs_mem_hc: ufshc@1d84000 { <0 0>, <0 0>, <0 0>, - <0 300000000>; + <75000000 300000000>; status = "disabled"; }; From 13f5c43e0921427e71bbb6b01f6ff66e746467a1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Jul 2023 13:53:31 +0200 Subject: [PATCH 0953/2093] arm64: dts: qcom: msm8996-gemini: fix touchscreen VIO supply [ Upstream commit 21fc24ee9c5943732c9ae538766c9be93d70d936 ] According to bindings and Linux driver, there is no VDDA but VIO supply. Fixes: 4ac46b3682c5 ("arm64: dts: qcom: msm8996: xiaomi-gemini: Add support for Xiaomi Mi 5") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230720115335.137354-2-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts index 4e5264f4116a..3bbafb68ba5c 100644 --- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts +++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts @@ -81,7 +81,7 @@ synaptics@20 { #size-cells = <0>; interrupt-parent = <&tlmm>; interrupts = <125 IRQ_TYPE_LEVEL_LOW>; - vdda-supply = <&vreg_l6a_1p8>; + vio-supply = <&vreg_l6a_1p8>; vdd-supply = <&vdd_3v2_tp>; reset-gpios = <&tlmm 89 GPIO_ACTIVE_LOW>; From 8dcc23191a6d2181855422741d73a96d91526c87 Mon Sep 17 00:00:00 2001 From: Srinivasan Shanmugam Date: Sun, 23 Jul 2023 12:29:14 +0530 Subject: [PATCH 0954/2093] drm/amdgpu: Update min() to min_t() in 'amdgpu_info_ioctl' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a0cc8e1512ad72c9f97cdcb76d42715730adaf62 ] Fixes the following: WARNING: min() should probably be min_t(size_t, size, sizeof(ip)) + ret = copy_to_user(out, &ip, min((size_t)size, sizeof(ip))); And other style fixes: WARNING: Prefer 'unsigned int' to bare use of 'unsigned' WARNING: Missing a blank line after declarations Cc: Christian König Cc: Alex Deucher Signed-off-by: Srinivasan Shanmugam Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 4e42dcb1950f..9e3313dd956a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -554,6 +554,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) crtc = (struct drm_crtc *)minfo->crtcs[i]; if (crtc && crtc->base.id == info->mode_crtc.id) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + ui32 = amdgpu_crtc->crtc_id; found = 1; break; @@ -572,7 +573,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (ret) return ret; - ret = copy_to_user(out, &ip, min((size_t)size, sizeof(ip))); + ret = copy_to_user(out, &ip, min_t(size_t, size, sizeof(ip))); return ret ? -EFAULT : 0; } case AMDGPU_INFO_HW_IP_COUNT: { @@ -718,17 +719,18 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ? -EFAULT : 0; } case AMDGPU_INFO_READ_MMR_REG: { - unsigned n, alloc_size; + unsigned int n, alloc_size; uint32_t *regs; - unsigned se_num = (info->read_mmr_reg.instance >> + unsigned int se_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SE_INDEX_SHIFT) & AMDGPU_INFO_MMR_SE_INDEX_MASK; - unsigned sh_num = (info->read_mmr_reg.instance >> + unsigned int sh_num = (info->read_mmr_reg.instance >> AMDGPU_INFO_MMR_SH_INDEX_SHIFT) & AMDGPU_INFO_MMR_SH_INDEX_MASK; /* set full masks if the userspace set all bits - * in the bitfields */ + * in the bitfields + */ if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; else if (se_num >= AMDGPU_GFX_MAX_SE) @@ -852,7 +854,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return ret; } case AMDGPU_INFO_VCE_CLOCK_TABLE: { - unsigned i; + unsigned int i; struct drm_amdgpu_info_vce_clock_table vce_clk_table = {}; struct amd_vce_state *vce_state; From 3db392257008860fd6f9c22e083b2b789eec3f0c Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Tue, 31 Jan 2023 13:17:09 +0800 Subject: [PATCH 0955/2093] md: Factor out is_md_suspended helper [ Upstream commit d19329133d25ad3dc32f8a62635692cb2f189014 ] This helper function will be used in next patch. It's easy for understanding. Signed-off-by: Xiao Ni Signed-off-by: Song Liu Stable-dep-of: e24ed04389f9 ("md: restore 'noio_flag' for the last mddev_resume()") Signed-off-by: Sasha Levin --- drivers/md/md.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 45daba0eb931..abb6c03c85b2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -368,6 +368,13 @@ EXPORT_SYMBOL_GPL(md_new_event); static LIST_HEAD(all_mddevs); static DEFINE_SPINLOCK(all_mddevs_lock); +static bool is_md_suspended(struct mddev *mddev) +{ + if (mddev->suspended) + return true; + else + return false; +} /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is * being suspended pending a reconfiguration. @@ -377,7 +384,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock); */ static bool is_suspended(struct mddev *mddev, struct bio *bio) { - if (mddev->suspended) + if (is_md_suspended(mddev)) return true; if (bio_data_dir(bio) != WRITE) return false; @@ -422,7 +429,7 @@ void md_handle_request(struct mddev *mddev, struct bio *bio) goto check_suspended; } - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) + if (atomic_dec_and_test(&mddev->active_io) && is_md_suspended(mddev)) wake_up(&mddev->sb_wait); } EXPORT_SYMBOL(md_handle_request); @@ -6238,7 +6245,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes); static void mddev_detach(struct mddev *mddev) { md_bitmap_wait_behind_writes(mddev); - if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) { + if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); } @@ -8548,7 +8555,7 @@ bool md_write_start(struct mddev *mddev, struct bio *bi) return true; wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) || - mddev->suspended); + is_md_suspended(mddev)); if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) { percpu_ref_put(&mddev->writes_pending); return false; @@ -9276,7 +9283,7 @@ void md_check_recovery(struct mddev *mddev) wake_up(&mddev->sb_wait); } - if (mddev->suspended) + if (is_md_suspended(mddev)) return; if (mddev->bitmap) From 835cbfebc1c54c0e8a1ffedaf48381178d390135 Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Tue, 31 Jan 2023 13:17:10 +0800 Subject: [PATCH 0956/2093] md: Change active_io to percpu [ Upstream commit 72adae23a72cb12e2ef0dcd7c0aa042867f27998 ] Now the type of active_io is atomic. It's used to count how many ios are in the submitting process and it's added and decreased very time. But it only needs to check if it's zero when suspending the raid. So we can switch atomic to percpu to improve the performance. After switching active_io to percpu type, we use the state of active_io to judge if the raid device is suspended. And we don't need to wake up ->sb_wait in md_handle_request anymore. It's done in the callback function which is registered when initing active_io. The argument mddev->suspended is only used to count how many users are trying to set raid to suspend state. Signed-off-by: Xiao Ni Signed-off-by: Song Liu Stable-dep-of: e24ed04389f9 ("md: restore 'noio_flag' for the last mddev_resume()") Signed-off-by: Sasha Levin --- drivers/md/md.c | 43 ++++++++++++++++++++++++------------------- drivers/md/md.h | 2 +- 2 files changed, 25 insertions(+), 20 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index abb6c03c85b2..1c44294c625a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -370,10 +370,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock); static bool is_md_suspended(struct mddev *mddev) { - if (mddev->suspended) - return true; - else - return false; + return percpu_ref_is_dying(&mddev->active_io); } /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is @@ -400,12 +397,10 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio) void md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: - rcu_read_lock(); if (is_suspended(mddev, bio)) { DEFINE_WAIT(__wait); /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { - rcu_read_unlock(); bio_wouldblock_error(bio); return; } @@ -414,23 +409,19 @@ void md_handle_request(struct mddev *mddev, struct bio *bio) TASK_UNINTERRUPTIBLE); if (!is_suspended(mddev, bio)) break; - rcu_read_unlock(); schedule(); - rcu_read_lock(); } finish_wait(&mddev->sb_wait, &__wait); } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); + if (!percpu_ref_tryget_live(&mddev->active_io)) + goto check_suspended; if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); + percpu_ref_put(&mddev->active_io); goto check_suspended; } - if (atomic_dec_and_test(&mddev->active_io) && is_md_suspended(mddev)) - wake_up(&mddev->sb_wait); + percpu_ref_put(&mddev->active_io); } EXPORT_SYMBOL(md_handle_request); @@ -478,11 +469,10 @@ void mddev_suspend(struct mddev *mddev) lockdep_assert_held(&mddev->reconfig_mutex); if (mddev->suspended++) return; - synchronize_rcu(); wake_up(&mddev->sb_wait); set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags); - smp_mb__after_atomic(); - wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0); + percpu_ref_kill(&mddev->active_io); + wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); mddev->pers->quiesce(mddev, 1); clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags); wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags)); @@ -500,6 +490,7 @@ void mddev_resume(struct mddev *mddev) lockdep_assert_held(&mddev->reconfig_mutex); if (--mddev->suspended) return; + percpu_ref_resurrect(&mddev->active_io); wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); @@ -678,7 +669,6 @@ void mddev_init(struct mddev *mddev) timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0); atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); - atomic_set(&mddev->active_io, 0); spin_lock_init(&mddev->lock); atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); @@ -5786,6 +5776,12 @@ static void md_safemode_timeout(struct timer_list *t) } static int start_dirty_degraded; +static void active_io_release(struct percpu_ref *ref) +{ + struct mddev *mddev = container_of(ref, struct mddev, active_io); + + wake_up(&mddev->sb_wait); +} int md_run(struct mddev *mddev) { @@ -5866,10 +5862,15 @@ int md_run(struct mddev *mddev) nowait = nowait && bdev_nowait(rdev->bdev); } + err = percpu_ref_init(&mddev->active_io, active_io_release, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL); + if (err) + return err; + if (!bioset_initialized(&mddev->bio_set)) { err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) - return err; + goto exit_active_io; } if (!bioset_initialized(&mddev->sync_set)) { err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); @@ -6057,6 +6058,8 @@ int md_run(struct mddev *mddev) bioset_exit(&mddev->sync_set); exit_bio_set: bioset_exit(&mddev->bio_set); +exit_active_io: + percpu_ref_exit(&mddev->active_io); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6283,6 +6286,7 @@ void md_stop(struct mddev *mddev) */ __md_stop_writes(mddev); __md_stop(mddev); + percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); } @@ -7852,6 +7856,7 @@ static void md_free_disk(struct gendisk *disk) struct mddev *mddev = disk->private_data; percpu_ref_exit(&mddev->writes_pending); + percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); diff --git a/drivers/md/md.h b/drivers/md/md.h index b4e2d8b87b61..64f8182a3dfc 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -315,7 +315,7 @@ struct mddev { unsigned long sb_flags; int suspended; - atomic_t active_io; + struct percpu_ref active_io; int ro; int sysfs_active; /* set when sysfs deletes * are happening, so run/ From 097f30f0cef875b668c6f6896920c6c360e0082b Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Wed, 28 Jun 2023 09:29:31 +0800 Subject: [PATCH 0957/2093] md: restore 'noio_flag' for the last mddev_resume() [ Upstream commit e24ed04389f9619e0aaef615a8948633c182a8b0 ] memalloc_noio_save() is called for the first mddev_suspend(), and repeated mddev_suspend() only increase 'suspended'. However, memalloc_noio_restore() is also called for the first mddev_resume(), which means that memory reclaim will be enabled before the last mddev_resume() is called, while the array is still suspended. Fix this problem by restore 'noio_flag' for the last mddev_resume(). Fixes: 78f57ef9d50a ("md: use memalloc scope APIs in mddev_suspend()/mddev_resume()") Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20230628012931.88911-3-yukuai1@huaweicloud.com Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/md.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 1c44294c625a..443837fe6291 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -485,11 +485,13 @@ EXPORT_SYMBOL_GPL(mddev_suspend); void mddev_resume(struct mddev *mddev) { - /* entred the memalloc scope from mddev_suspend() */ - memalloc_noio_restore(mddev->noio_flag); lockdep_assert_held(&mddev->reconfig_mutex); if (--mddev->suspended) return; + + /* entred the memalloc scope from mddev_suspend() */ + memalloc_noio_restore(mddev->noio_flag); + percpu_ref_resurrect(&mddev->active_io); wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); From 27acd8c131836f058ffeb06200662bc8df697613 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Sat, 1 Jul 2023 16:05:28 +0800 Subject: [PATCH 0958/2093] md/raid10: factor out dereference_rdev_and_rrdev() [ Upstream commit b99f8fd2d91eb734f13098aa1cf337edaca454b7 ] Factor out a helper to get 'rdev' and 'replacement' from config->mirrors. Just to make code cleaner and prepare to fix the bug of io loss while 'replacement' replace 'rdev'. There is no functional change. Signed-off-by: Li Nan Link: https://lore.kernel.org/r/20230701080529.2684932-3-linan666@huaweicloud.com Signed-off-by: Song Liu Stable-dep-of: 673643490b9a ("md/raid10: use dereference_rdev_and_rrdev() to get devices") Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d2098fcd6a27..49bb79f48f36 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1317,6 +1317,25 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, } } +static struct md_rdev *dereference_rdev_and_rrdev(struct raid10_info *mirror, + struct md_rdev **prrdev) +{ + struct md_rdev *rdev, *rrdev; + + rrdev = rcu_dereference(mirror->replacement); + /* + * Read replacement first to prevent reading both rdev and + * replacement as NULL during replacement replace rdev. + */ + smp_mb(); + rdev = rcu_dereference(mirror->rdev); + if (rdev == rrdev) + rrdev = NULL; + + *prrdev = rrdev; + return rdev; +} + static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio) { int i; @@ -1460,15 +1479,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, int d = r10_bio->devs[i].devnum; struct md_rdev *rdev, *rrdev; - rrdev = rcu_dereference(conf->mirrors[d].replacement); - /* - * Read replacement first to prevent reading both rdev and - * replacement as NULL during replacement replace rdev. - */ - smp_mb(); - rdev = rcu_dereference(conf->mirrors[d].rdev); - if (rdev == rrdev) - rrdev = NULL; + rdev = dereference_rdev_and_rrdev(&conf->mirrors[d], &rrdev); if (rdev && (test_bit(Faulty, &rdev->flags))) rdev = NULL; if (rrdev && (test_bit(Faulty, &rrdev->flags))) From 3829cb3caeda17dab0bdac52e81f61597742c234 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Sat, 1 Jul 2023 16:05:29 +0800 Subject: [PATCH 0959/2093] md/raid10: use dereference_rdev_and_rrdev() to get devices [ Upstream commit 673643490b9a0eb3b25633abe604f62b8f63dba1 ] Commit 2ae6aaf76912 ("md/raid10: fix io loss while replacement replace rdev") reads replacement first to prevent io loss. However, there are same issue in wait_blocked_dev() and raid10_handle_discard(), too. Fix it by using dereference_rdev_and_rrdev() to get devices. Fixes: d30588b2731f ("md/raid10: improve raid10 discard request") Fixes: f2e7e269a752 ("md/raid10: pull the code that wait for blocked dev into one function") Signed-off-by: Li Nan Link: https://lore.kernel.org/r/20230701080529.2684932-4-linan666@huaweicloud.com Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 49bb79f48f36..7b318e7e8d45 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1346,11 +1346,9 @@ static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio) blocked_rdev = NULL; rcu_read_lock(); for (i = 0; i < conf->copies; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[i].replacement); - if (rdev == rrdev) - rrdev = NULL; + struct md_rdev *rdev, *rrdev; + + rdev = dereference_rdev_and_rrdev(&conf->mirrors[i], &rrdev); if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { atomic_inc(&rdev->nr_pending); blocked_rdev = rdev; @@ -1786,10 +1784,9 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio) */ rcu_read_lock(); for (disk = 0; disk < geo->raid_disks; disk++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); + struct md_rdev *rdev, *rrdev; + rdev = dereference_rdev_and_rrdev(&conf->mirrors[disk], &rrdev); r10_bio->devs[disk].bio = NULL; r10_bio->devs[disk].repl_bio = NULL; From e970bc3828b70cad08d7b11206508c6c921b11f5 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 6 Jul 2023 16:37:26 +0800 Subject: [PATCH 0960/2093] md/md-bitmap: remove unnecessary local variable in backlog_store() [ Upstream commit b4d129640f194ffc4cc64c3e97f98ae944c072e8 ] Local variable is definied first in the beginning of backlog_store(), there is no need to define it again. Fixes: 8c13ab115b57 ("md/bitmap: don't set max_write_behind if there is no write mostly device") Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20230706083727.608914-2-yukuai1@huaweicloud.com Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/md-bitmap.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 8bbeeec70905..8553f028825a 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2504,8 +2504,6 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len) mddev_destroy_serial_pool(mddev, NULL, false); } else if (backlog && !mddev->serial_info_pool) { /* serial_info_pool is needed since backlog is not zero */ - struct md_rdev *rdev; - rdev_for_each(rdev, mddev) mddev_create_serial_pool(mddev, rdev, false); } From f9b9c6b0d45153144a1d7710d7b34fcb386c1576 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 6 Jul 2023 16:37:27 +0800 Subject: [PATCH 0961/2093] md/md-bitmap: hold 'reconfig_mutex' in backlog_store() [ Upstream commit 44abfa6a95df425c0660d56043020b67e6d93ab8 ] Several reasons why 'reconfig_mutex' should be held: 1) rdev_for_each() is not safe to be called without the lock, because rdev can be removed concurrently. 2) mddev_destroy_serial_pool() and mddev_create_serial_pool() should not be called concurrently. 3) mddev_suspend() from mddev_destroy/create_serial_pool() should be protected by the lock. Fixes: 10c92fca636e ("md-bitmap: create and destroy wb_info_pool with the change of backlog") Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20230706083727.608914-3-yukuai1@huaweicloud.com Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/md-bitmap.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 8553f028825a..5200bba63708 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2481,6 +2481,10 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len) if (backlog > COUNTER_MAX) return -EINVAL; + rv = mddev_lock(mddev); + if (rv) + return rv; + /* * Without write mostly device, it doesn't make sense to set * backlog for max_write_behind. @@ -2494,6 +2498,7 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len) if (!has_write_mostly) { pr_warn_ratelimited("%s: can't set backlog, no write mostly device available\n", mdname(mddev)); + mddev_unlock(mddev); return -EINVAL; } @@ -2509,6 +2514,8 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len) } if (old_mwb != backlog) md_bitmap_update_sb(mddev->bitmap); + + mddev_unlock(mddev); return len; } From 508383dc278cbb2875a5f4fccdf770af4f85a39a Mon Sep 17 00:00:00 2001 From: Ryan McCann Date: Fri, 7 Jul 2023 18:24:40 -0700 Subject: [PATCH 0962/2093] drm/msm: Update dev core dump to not print backwards [ Upstream commit 903705111d863ed8ccf73465da77d232fc422ec1 ] Device core dump add block method adds hardware blocks to dumping queue with stack behavior which causes the hardware blocks to be printed in reverse order. Change the addition to dumping queue data structure from "list_add" to "list_add_tail" for FIFO queue behavior. Fixes: 98659487b845 ("drm/msm: add support to take dpu snapshot") Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Signed-off-by: Ryan McCann Patchwork: https://patchwork.freedesktop.org/patch/546200/ Link: https://lore.kernel.org/r/20230622-devcoredump_patch-v5-1-67e8b66c4723@quicinc.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index acfe1b31e079..add72bbc28b1 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -192,5 +192,5 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len, new_blk->base_addr = base_addr; msm_disp_state_dump_regs(&new_blk->state, new_blk->size, base_addr); - list_add(&new_blk->node, &disp_state->blocks); + list_add_tail(&new_blk->node, &disp_state->blocks); } From 4ab834ff9fbf8857a7804359db862c6e14838152 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Mon, 10 Jul 2023 11:23:49 +0800 Subject: [PATCH 0963/2093] drm/tegra: dpaux: Fix incorrect return value of platform_get_irq [ Upstream commit 2a1ca44b654346cadfc538c4fb32eecd8daf3140 ] When platform_get_irq fails, we should return dpaux->irq instead of -ENXIO. Fixes: 6b6b604215c6 ("drm/tegra: Add eDP support") Signed-off-by: Yangtao Li Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20230710032355.72914-13-frank.li@vivo.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/tegra/dpaux.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index 7dc681e2ee90..d773ef485418 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -468,7 +468,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) dpaux->irq = platform_get_irq(pdev, 0); if (dpaux->irq < 0) - return -ENXIO; + return dpaux->irq; if (!pdev->dev.pm_domain) { dpaux->rst = devm_reset_control_get(&pdev->dev, "dpaux"); From 43cc228099c514467b8074d7ede6673cef9f33b9 Mon Sep 17 00:00:00 2001 From: Ruan Jinjie Date: Thu, 27 Jul 2023 16:02:46 +0800 Subject: [PATCH 0964/2093] of: unittest: fix null pointer dereferencing in of_unittest_find_node_by_name() [ Upstream commit d6ce4f0ea19c32f10867ed93d8386924326ab474 ] when kmalloc() fail to allocate memory in kasprintf(), name or full_name will be NULL, strcmp() will cause null pointer dereference. Fixes: 0d638a07d3a1 ("of: Convert to using %pOF instead of full_name") Signed-off-by: Ruan Jinjie Link: https://lore.kernel.org/r/20230727080246.519539-1-ruanjinjie@huawei.com Signed-off-by: Rob Herring Signed-off-by: Sasha Levin --- drivers/of/unittest.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 9be6ed47a1ce..b815b8862e18 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -70,7 +70,7 @@ static void __init of_unittest_find_node_by_name(void) np = of_find_node_by_path("/testcase-data"); name = kasprintf(GFP_KERNEL, "%pOF", np); - unittest(np && !strcmp("/testcase-data", name), + unittest(np && name && !strcmp("/testcase-data", name), "find /testcase-data failed\n"); of_node_put(np); kfree(name); @@ -81,14 +81,14 @@ static void __init of_unittest_find_node_by_name(void) np = of_find_node_by_path("/testcase-data/phandle-tests/consumer-a"); name = kasprintf(GFP_KERNEL, "%pOF", np); - unittest(np && !strcmp("/testcase-data/phandle-tests/consumer-a", name), + unittest(np && name && !strcmp("/testcase-data/phandle-tests/consumer-a", name), "find /testcase-data/phandle-tests/consumer-a failed\n"); of_node_put(np); kfree(name); np = of_find_node_by_path("testcase-alias"); name = kasprintf(GFP_KERNEL, "%pOF", np); - unittest(np && !strcmp("/testcase-data", name), + unittest(np && name && !strcmp("/testcase-data", name), "find testcase-alias failed\n"); of_node_put(np); kfree(name); @@ -99,7 +99,7 @@ static void __init of_unittest_find_node_by_name(void) np = of_find_node_by_path("testcase-alias/phandle-tests/consumer-a"); name = kasprintf(GFP_KERNEL, "%pOF", np); - unittest(np && !strcmp("/testcase-data/phandle-tests/consumer-a", name), + unittest(np && name && !strcmp("/testcase-data/phandle-tests/consumer-a", name), "find testcase-alias/phandle-tests/consumer-a failed\n"); of_node_put(np); kfree(name); @@ -1379,6 +1379,8 @@ static void attach_node_and_children(struct device_node *np) const char *full_name; full_name = kasprintf(GFP_KERNEL, "%pOF", np); + if (!full_name) + return; if (!strcmp(full_name, "/__local_fixups__") || !strcmp(full_name, "/__fixups__")) { From 976eca4cbd3794d789ae40d5212af7181592e79b Mon Sep 17 00:00:00 2001 From: Zeyan Li Date: Thu, 27 Jul 2023 10:53:21 +0800 Subject: [PATCH 0965/2093] arm64: dts: qcom: sm8150: Fix the I2C7 interrupt [ Upstream commit f9568d22ce06192a7e14bda3a29dc216659554ff ] I2C6 and I2C7 use the same interrupts, which is incorrect. In the downstream kernel, I2C7 has interrupts of 608 instead of 607. Fixes: 81bee6953b58 ("arm64: dts: qcom: sm8150: add i2c nodes") Signed-off-by: Zeyan Li Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/SY7P282MB378712225CBCEA95FE71554DB201A@SY7P282MB3787.AUSP282.PROD.OUTLOOK.COM Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8150.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 78ae4b9eaa10..f049fb42e3ca 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -1196,7 +1196,7 @@ i2c7: i2c@89c000 { dma-names = "tx", "rx"; pinctrl-names = "default"; pinctrl-0 = <&qup_i2c7_default>; - interrupts = ; + interrupts = ; #address-cells = <1>; #size-cells = <0>; status = "disabled"; From 0ef736fec61422794c4a991d46c4ec212b01d8d1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 23 Jul 2023 21:54:14 +0200 Subject: [PATCH 0966/2093] ARM: dts: BCM53573: Fix Tenda AC9 switch CPU port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7141209db9c335ab261a17933809a3e660ebdc12 ] Primary Ethernet interface is connected to the port 8 (not 5). Fixes: 64612828628c ("ARM: dts: BCM53573: Add Tenda AC9 switch ports") Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230723195416.7831-1-zajec5@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm47189-tenda-ac9.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/bcm47189-tenda-ac9.dts b/arch/arm/boot/dts/bcm47189-tenda-ac9.dts index 55b92645b0f1..b7c7bf0be76f 100644 --- a/arch/arm/boot/dts/bcm47189-tenda-ac9.dts +++ b/arch/arm/boot/dts/bcm47189-tenda-ac9.dts @@ -135,8 +135,8 @@ port@4 { label = "lan4"; }; - port@5 { - reg = <5>; + port@8 { + reg = <8>; label = "cpu"; ethernet = <&gmac0>; }; From d544c89bb1cdc74d048a79e0659e4c14a81c6e1b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 17 Jul 2023 15:25:40 +0200 Subject: [PATCH 0967/2093] drm/armada: Fix off-by-one error in armada_overlay_get_property() [ Upstream commit 5f0d984053f74983a287100a9519b2fabb785fb5 ] As ffs() returns one more than the index of the first bit set (zero means no bits set), the color key mode value is shifted one position too much. Fix this by using FIELD_GET() instead. Fixes: c96103b6c49ff9a8 ("drm/armada: move colorkey properties into overlay plane state") Signed-off-by: Geert Uytterhoeven Reviewed-by: Russell King (Oracle) Signed-off-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/a4d779d954a7515ddbbf31cb0f0d8184c0e7c879.1689600265.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- drivers/gpu/drm/armada/armada_overlay.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c index f21eb8fb76d8..3b9bd8ecda13 100644 --- a/drivers/gpu/drm/armada/armada_overlay.c +++ b/drivers/gpu/drm/armada/armada_overlay.c @@ -4,6 +4,8 @@ * Rewritten from the dovefb driver, and Armada510 manuals. */ +#include + #include #include #include @@ -445,8 +447,8 @@ static int armada_overlay_get_property(struct drm_plane *plane, drm_to_overlay_state(state)->colorkey_ug, drm_to_overlay_state(state)->colorkey_vb, 0); } else if (property == priv->colorkey_mode_prop) { - *val = (drm_to_overlay_state(state)->colorkey_mode & - CFG_CKMODE_MASK) >> ffs(CFG_CKMODE_MASK); + *val = FIELD_GET(CFG_CKMODE_MASK, + drm_to_overlay_state(state)->colorkey_mode); } else if (property == priv->brightness_prop) { *val = drm_to_overlay_state(state)->brightness + 256; } else if (property == priv->contrast_prop) { From 4174f889c4c1354240ba35d9332c1a2d493931e1 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 17 Mar 2022 09:18:30 +0100 Subject: [PATCH 0968/2093] drm/repaper: Reduce temporary buffer size in repaper_fb_dirty() [ Upstream commit fedf429e071f6dbbe7a69dfc342492e037692018 ] As the temporary buffer is no longer used to store 8-bit grayscale data, its size can be reduced to the size needed to store the monochrome bitmap data. Fixes: 24c6bedefbe71de9 ("drm/repaper: Use format helper for xrgb8888 to monochrome conversion") Signed-off-by: Geert Uytterhoeven Reviewed-by: Javier Martinez Canillas Signed-off-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220317081830.1211400-6-geert@linux-m68k.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/tiny/repaper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index e62f4d16b2c6..7e2b0e224135 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -533,7 +533,7 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb) DRM_DEBUG("Flushing [FB:%d] st=%ums\n", fb->base.id, epd->factored_stage_time); - buf = kmalloc_array(fb->width, fb->height, GFP_KERNEL); + buf = kmalloc(fb->width * fb->height / 8, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto out_exit; From 92eaa1840301bf46bc886758588e3b3a07163d6c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 9 Jul 2023 15:49:14 +0200 Subject: [PATCH 0969/2093] drm/panel: simple: Add missing connector type and pixel format for AUO T215HVN01 [ Upstream commit 7a675a8fa598edb29a664a91adb80f0340649f6f ] The connector type and pixel format are missing for this panel, add them to prevent various drivers from failing to determine either of those parameters. Fixes: 7ee933a1d5c4 ("drm/panel: simple: Add support for AUO T215HVN01") Signed-off-by: Marek Vasut Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20230709134914.449328-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-simple.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 5e067ba7e5fb..0e8622ccd3a0 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1159,7 +1159,9 @@ static const struct panel_desc auo_t215hvn01 = { .delay = { .disable = 5, .unprepare = 1000, - } + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .connector_type = DRM_MODE_CONNECTOR_LVDS, }; static const struct drm_display_mode avic_tm070ddh03_mode = { From 9b372d2fdc4496d44931b194af0a2b4da7531729 Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Tue, 11 Jul 2023 12:44:47 -0400 Subject: [PATCH 0970/2093] ima: Remove deprecated IMA_TRUSTED_KEYRING Kconfig [ Upstream commit 5087fd9e80e539d2163accd045b73da64de7de95 ] Time to remove "IMA_TRUSTED_KEYRING". Fixes: f4dc37785e9b ("integrity: define '.evm' as a builtin 'trusted' keyring") # v4.5+ Signed-off-by: Nayna Jain Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/Kconfig | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 60a511c6b583..c17660bf5f34 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -248,18 +248,6 @@ config IMA_APPRAISE_MODSIG The modsig keyword can be used in the IMA policy to allow a hook to accept such signatures. -config IMA_TRUSTED_KEYRING - bool "Require all keys on the .ima keyring be signed (deprecated)" - depends on IMA_APPRAISE && SYSTEM_TRUSTED_KEYRING - depends on INTEGRITY_ASYMMETRIC_KEYS - select INTEGRITY_TRUSTED_KEYRING - default y - help - This option requires that all keys added to the .ima - keyring be signed by a key on the system trusted keyring. - - This option is deprecated in favor of INTEGRITY_TRUSTED_KEYRING - config IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY bool "Permit keys validly signed by a built-in or secondary CA cert (EXPERIMENTAL)" depends on SYSTEM_TRUSTED_KEYRING From 3b1f1999a3006e8adf3eaae96850666d03aeea23 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 7 Jun 2023 10:05:29 +0800 Subject: [PATCH 0971/2093] drm: xlnx: zynqmp_dpsub: Add missing check for dma_set_mask [ Upstream commit 1832fba7f9780aff67c96ad30f397c2d76141833 ] Add check for dma_set_mask() and return the error if it fails. Fixes: d76271d22694 ("drm: xlnx: DRM/KMS driver for Xilinx ZynqMP DisplayPort Subsystem") Signed-off-by: Jiasheng Jiang Reviewed-by: Laurent Pinchart Reviewed-by: Tomi Valkeinen Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/gpu/drm/xlnx/zynqmp_dpsub.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c index 1de2d927c32b..fcaa958d841c 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c @@ -201,7 +201,9 @@ static int zynqmp_dpsub_probe(struct platform_device *pdev) dpsub->dev = &pdev->dev; platform_set_drvdata(pdev, dpsub); - dma_set_mask(dpsub->dev, DMA_BIT_MASK(ZYNQMP_DISP_MAX_DMA_BIT)); + ret = dma_set_mask(dpsub->dev, DMA_BIT_MASK(ZYNQMP_DISP_MAX_DMA_BIT)); + if (ret) + return ret; /* Try the reserved memory. Proceed if there's none. */ of_reserved_mem_device_init(&pdev->dev); From 0cd481c27b0337b67e87ac46a408eb438db86edc Mon Sep 17 00:00:00 2001 From: Chen Jiahao Date: Tue, 1 Aug 2023 17:48:07 +0800 Subject: [PATCH 0972/2093] soc: qcom: smem: Fix incompatible types in comparison [ Upstream commit 5f908786cf44fcb397cfe0f322ef2f41b0909e2a ] This patch fixes the following sparse error: drivers/soc/qcom/smem.c:738:30: error: incompatible types in comparison expression (different add ress spaces): drivers/soc/qcom/smem.c:738:30: void * drivers/soc/qcom/smem.c:738:30: void [noderef] __iomem * In addr_in_range(), "base" is of type void __iomem *, converting void *addr to the same type to fix above sparse error. Fixes: 20bb6c9de1b7 ("soc: qcom: smem: map only partitions used by local HOST") Signed-off-by: Chen Jiahao Link: https://lore.kernel.org/r/20230801094807.4146779-1-chenjiahao16@huawei.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/soc/qcom/smem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c index 4f163d62942c..af8d90efd91f 100644 --- a/drivers/soc/qcom/smem.c +++ b/drivers/soc/qcom/smem.c @@ -723,7 +723,7 @@ EXPORT_SYMBOL(qcom_smem_get_free_space); static bool addr_in_range(void __iomem *base, size_t size, void *addr) { - return base && (addr >= base && addr < base + size); + return base && ((void __iomem *)addr >= base && (void __iomem *)addr < base + size); } /** From 2965015006ef18ca96d2eab9ebe6bca884c63291 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 Aug 2023 22:45:21 +0200 Subject: [PATCH 0973/2093] drm/msm/mdp5: Don't leak some plane state [ Upstream commit fd0ad3b2365c1c58aa5a761c18efc4817193beb6 ] Apparently no one noticed that mdp5 plane states leak like a sieve ever since we introduced plane_state->commit refcount a few years ago in 21a01abbe32a ("drm/atomic: Fix freeing connector/plane state too early by tracking commits, v3.") Fix it by using the right helpers. Fixes: 21a01abbe32a ("drm/atomic: Fix freeing connector/plane state too early by tracking commits, v3.") Cc: Maarten Lankhorst Cc: Daniel Vetter Cc: Rob Clark Cc: Abhinav Kumar Cc: Dmitry Baryshkov Cc: linux-arm-msm@vger.kernel.org Cc: freedreno@lists.freedesktop.org Reported-and-tested-by: dorum@noisolation.com Cc: dorum@noisolation.com Signed-off-by: Daniel Vetter Reviewed-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/551236/ Link: https://lore.kernel.org/r/20230803204521.928582-1-daniel.vetter@ffwll.ch Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index bd2c4ac45601..0d5ff03cb091 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -130,8 +130,7 @@ static void mdp5_plane_destroy_state(struct drm_plane *plane, { struct mdp5_plane_state *pstate = to_mdp5_plane_state(state); - if (state->fb) - drm_framebuffer_put(state->fb); + __drm_atomic_helper_plane_destroy_state(state); kfree(pstate); } From bd3a6b6d5dd863dbbe17985c7612159cf4533cad Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 15 Jul 2023 22:13:38 +0800 Subject: [PATCH 0974/2093] firmware: meson_sm: fix to avoid potential NULL pointer dereference [ Upstream commit f2ed165619c16577c02b703a114a1f6b52026df4 ] of_match_device() may fail and returns a NULL pointer. Fix this by checking the return value of of_match_device. Fixes: 8cde3c2153e8 ("firmware: meson_sm: Rework driver as a proper platform driver") Signed-off-by: Zhang Shurong Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/tencent_AA08AAA6C4F34D53ADCE962E188A879B8206@qq.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- drivers/firmware/meson/meson_sm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/meson/meson_sm.c b/drivers/firmware/meson/meson_sm.c index 77aa5c6398aa..d081a6312627 100644 --- a/drivers/firmware/meson/meson_sm.c +++ b/drivers/firmware/meson/meson_sm.c @@ -292,6 +292,8 @@ static int __init meson_sm_probe(struct platform_device *pdev) return -ENOMEM; chip = of_match_device(meson_sm_ids, dev)->data; + if (!chip) + return -EINVAL; if (chip->cmd_shmem_in_base) { fw->sm_shmem_in_base = meson_sm_map_shmem(chip->cmd_shmem_in_base, From d1994bb5947ccef26364911c4090ef1caf19f02c Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 2 Aug 2023 13:04:19 +0300 Subject: [PATCH 0975/2093] drm/msm/dpu: fix the irq index in dpu_encoder_phys_wb_wait_for_commit_done [ Upstream commit d93cf453f51da168f4410ba73656f1e862096973 ] Since commit 1e7ac595fa46 ("drm/msm/dpu: pass irq to dpu_encoder_helper_wait_for_irq()") the dpu_encoder_phys_wb_wait_for_commit_done expects the IRQ index rather than the IRQ index in phys_enc->intr table, however writeback got the older invocation in place. This was unnoticed for several releases, but now it's time to fix it. Fixes: d7d0e73f7de3 ("drm/msm/dpu: introduce the dpu_encoder_phys_* for writeback") Signed-off-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/550924/ Link: https://lore.kernel.org/r/20230802100426.4184892-2-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 62f6ff6abf41..42c7e378d504 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -460,7 +460,8 @@ static int dpu_encoder_phys_wb_wait_for_commit_done( wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt; wait_info.timeout_ms = KICKOFF_TIMEOUT_MS; - ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_WB_DONE, + ret = dpu_encoder_helper_wait_for_irq(phys_enc, + phys_enc->irq[INTR_IDX_WB_DONE], dpu_encoder_phys_wb_done_irq, &wait_info); if (ret == -ETIMEDOUT) _dpu_encoder_phys_wb_handle_wbdone_timeout(phys_enc); From d41ceafe3d24b76aaa43cfab999335dbb24140af Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 6 Jul 2023 08:52:39 +0300 Subject: [PATCH 0976/2093] smackfs: Prevent underflow in smk_set_cipso() [ Upstream commit 3ad49d37cf5759c3b8b68d02e3563f633d9c1aee ] There is a upper bound to "catlen" but no lower bound to prevent negatives. I don't see that this necessarily causes a problem but we may as well be safe. Fixes: e114e473771c ("Smack: Simplified Mandatory Access Control Kernel") Signed-off-by: Dan Carpenter Signed-off-by: Casey Schaufler Signed-off-by: Sasha Levin --- security/smack/smackfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 4b58526450d4..da7db9e22ce7 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -896,7 +896,7 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, } ret = sscanf(rule, "%d", &catlen); - if (ret != 1 || catlen > SMACK_CIPSO_MAXCATNUM) + if (ret != 1 || catlen < 0 || catlen > SMACK_CIPSO_MAXCATNUM) goto out; if (format == SMK_FIXED24_FMT && From f27dff881f0b8f1a5bc64d48a19802dd520bc482 Mon Sep 17 00:00:00 2001 From: Yang Wang Date: Tue, 1 Aug 2023 16:53:23 +0800 Subject: [PATCH 0977/2093] drm/amd/pm: fix variable dereferenced issue in amdgpu_device_attr_create() [ Upstream commit 25e6373a5b8efc623443f2699d2b929bf3067d76 ] - fix variable ('attr') dereferenced issue. - using condition check instead of BUG_ON(). Fixes: 4e01847c38f7 ("drm/amdgpu: optimize amdgpu device attribute code") Cc: Dan Carpenter Signed-off-by: Yang Wang Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/amdgpu_pm.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 7d613118cb71..8472013ff38a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2072,15 +2072,19 @@ static int amdgpu_device_attr_create(struct amdgpu_device *adev, uint32_t mask, struct list_head *attr_list) { int ret = 0; - struct device_attribute *dev_attr = &attr->dev_attr; - const char *name = dev_attr->attr.name; enum amdgpu_device_attr_states attr_states = ATTR_STATE_SUPPORTED; struct amdgpu_device_attr_entry *attr_entry; + struct device_attribute *dev_attr; + const char *name; int (*attr_update)(struct amdgpu_device *adev, struct amdgpu_device_attr *attr, uint32_t mask, enum amdgpu_device_attr_states *states) = default_attr_update; - BUG_ON(!attr); + if (!attr) + return -EINVAL; + + dev_attr = &attr->dev_attr; + name = dev_attr->attr.name; attr_update = attr->attr_update ? attr->attr_update : default_attr_update; From 607eda339b609e451bb7a9af3e6770bf38761269 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 20 Jun 2023 20:23:19 -0300 Subject: [PATCH 0978/2093] drm/msm/a2xx: Call adreno_gpu_init() earlier [ Upstream commit db07ce5da8b26bfeaf437a676ae49bd3bb1eace6 ] The adreno_is_a20x() and adreno_is_a225() functions rely on the GPU revision, but such information is retrieved inside adreno_gpu_init(), which is called afterwards. Fix this problem by caling adreno_gpu_init() earlier, so that the GPU information revision is available when adreno_is_a20x() and adreno_is_a225() run. Tested on a imx53-qsb board. Fixes: 21af872cd8c6 ("drm/msm/adreno: add a2xx") Signed-off-by: Fabio Estevam Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/543456/ Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a2xx_gpu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 6c9a747eb4ad..2428d6ac5fe9 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -521,6 +521,10 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) gpu->perfcntrs = perfcntrs; gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + if (ret) + goto fail; + if (adreno_is_a20x(adreno_gpu)) adreno_gpu->registers = a200_registers; else if (adreno_is_a225(adreno_gpu)) @@ -528,10 +532,6 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) else adreno_gpu->registers = a220_registers; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); - if (ret) - goto fail; - if (!gpu->aspace) { dev_err(dev->dev, "No memory protection without MMU\n"); if (!allow_vram_carveout) { From 9ca08adb75fb40a8f742c371927ee73f9dc753bf Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 8 Aug 2023 20:14:35 +0800 Subject: [PATCH 0979/2093] audit: fix possible soft lockup in __audit_inode_child() [ Upstream commit b59bc6e37237e37eadf50cd5de369e913f524463 ] Tracefs or debugfs maybe cause hundreds to thousands of PATH records, too many PATH records maybe cause soft lockup. For example: 1. CONFIG_KASAN=y && CONFIG_PREEMPTION=n 2. auditctl -a exit,always -S open -k key 3. sysctl -w kernel.watchdog_thresh=5 4. mkdir /sys/kernel/debug/tracing/instances/test There may be a soft lockup as follows: watchdog: BUG: soft lockup - CPU#45 stuck for 7s! [mkdir:15498] Kernel panic - not syncing: softlockup: hung tasks Call trace: dump_backtrace+0x0/0x30c show_stack+0x20/0x30 dump_stack+0x11c/0x174 panic+0x27c/0x494 watchdog_timer_fn+0x2bc/0x390 __run_hrtimer+0x148/0x4fc __hrtimer_run_queues+0x154/0x210 hrtimer_interrupt+0x2c4/0x760 arch_timer_handler_phys+0x48/0x60 handle_percpu_devid_irq+0xe0/0x340 __handle_domain_irq+0xbc/0x130 gic_handle_irq+0x78/0x460 el1_irq+0xb8/0x140 __audit_inode_child+0x240/0x7bc tracefs_create_file+0x1b8/0x2a0 trace_create_file+0x18/0x50 event_create_dir+0x204/0x30c __trace_add_new_event+0xac/0x100 event_trace_add_tracer+0xa0/0x130 trace_array_create_dir+0x60/0x140 trace_array_create+0x1e0/0x370 instance_mkdir+0x90/0xd0 tracefs_syscall_mkdir+0x68/0xa0 vfs_mkdir+0x21c/0x34c do_mkdirat+0x1b4/0x1d4 __arm64_sys_mkdirat+0x4c/0x60 el0_svc_common.constprop.0+0xa8/0x240 do_el0_svc+0x8c/0xc0 el0_svc+0x20/0x30 el0_sync_handler+0xb0/0xb4 el0_sync+0x160/0x180 Therefore, we add cond_resched() to __audit_inode_child() to fix it. Fixes: 5195d8e217a7 ("audit: dynamically allocate audit_names when not enough space is in the names array") Signed-off-by: Gaosheng Cui Signed-off-by: Paul Moore Signed-off-by: Sasha Levin --- kernel/auditsc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 9f8c05228d6d..a2240f54fc22 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2456,6 +2456,8 @@ void __audit_inode_child(struct inode *parent, } } + cond_resched(); + /* is there a matching child entry? */ list_for_each_entry(n, &context->names_list, list) { /* can only match entries that have a name */ From 9183c4fe9141e6575c801aad2d9fa23b4855d763 Mon Sep 17 00:00:00 2001 From: Zhiguo Niu Date: Thu, 3 Aug 2023 19:12:42 +0800 Subject: [PATCH 0980/2093] block/mq-deadline: use correct way to throttling write requests [ Upstream commit d47f9717e5cfd0dd8c0ba2ecfa47c38d140f1bb6 ] The original formula was inaccurate: dd->async_depth = max(1UL, 3 * q->nr_requests / 4); For write requests, when we assign a tags from sched_tags, data->shallow_depth will be passed to sbitmap_find_bit, see the following code: nr = sbitmap_find_bit_in_word(&sb->map[index], min_t (unsigned int, __map_depth(sb, index), depth), alloc_hint, wrap); The smaller of data->shallow_depth and __map_depth(sb, index) will be used as the maximum range when allocating bits. For a mmc device (one hw queue, deadline I/O scheduler): q->nr_requests = sched_tags = 128, so according to the previous calculation method, dd->async_depth = data->shallow_depth = 96, and the platform is 64bits with 8 cpus, sched_tags.bitmap_tags.sb.shift=5, sb.maps[]=32/32/32/32, 32 is smaller than 96, whether it is a read or a write I/O, tags can be allocated to the maximum range each time, which has not throttling effect. In addition, refer to the methods of bfg/kyber I/O scheduler, limit ratiois are calculated base on sched_tags.bitmap_tags.sb.shift. This patch can throttle write requests really. Fixes: 07757588e507 ("block/mq-deadline: Reserve 25% of scheduler tags for synchronous requests") Signed-off-by: Zhiguo Niu Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/1691061162-22898-1-git-send-email-zhiguo.niu@unisoc.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/mq-deadline.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/mq-deadline.c b/block/mq-deadline.c index f10c2a0d18d4..55e26065c2e2 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -622,8 +622,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; + unsigned int shift = tags->bitmap_tags.sb.shift; - dd->async_depth = max(1UL, 3 * q->nr_requests / 4); + dd->async_depth = max(1U, 3 * (1U << shift) / 4); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); } From 0c323430e470c922af54cebf1134d7b62144ecfa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 9 Aug 2023 13:21:41 +0100 Subject: [PATCH 0981/2093] io_uring: fix drain stalls by invalid SQE [ Upstream commit cfdbaa3a291d6fd2cb4a1a70d74e63b4abc2f5ec ] cq_extra is protected by ->completion_lock, which io_get_sqe() misses. The bug is harmless as it doesn't happen in real life, requires invalid SQ index array and racing with submission, and only messes up the userspace, i.e. stall requests execution but will be cleaned up on ring destruction. Fixes: 15641e427070f ("io_uring: don't cache number of dropped SQEs") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/66096d54651b1a60534bb2023f2947f09f50ef73.1691538547.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index b0e47fe1eb4b..e15abe26a0e6 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2240,7 +2240,9 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) } /* drop invalid entries */ + spin_lock(&ctx->completion_lock); ctx->cq_extra--; + spin_unlock(&ctx->completion_lock); WRITE_ONCE(ctx->rings->sq_dropped, READ_ONCE(ctx->rings->sq_dropped) + 1); return NULL; From b625a6eaf2bf4ec7f962a26805b6d1927e3e8442 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Tue, 25 Jul 2023 09:32:24 +0200 Subject: [PATCH 0982/2093] drm/mediatek: dp: Add missing error checks in mtk_dp_parse_capabilities [ Upstream commit cfc146137a9f12e883ba64bc496b6da4d23f26d5 ] If reading the RX capabilities fails the training pattern will be set wrongly: add error checking for drm_dp_read_dpcd_caps() and return if anything went wrong with it. While at it, also add a less critical error check when writing to clear the ESI0 IRQ vector. Fixes: f70ac097a2cf ("drm/mediatek: Add MT8195 Embedded DisplayPort driver") Signed-off-by: AngeloGioacchino Del Regno Tested-by: Chen-Yu Tsai Reviewed-by: Alexandre Mergnat Reviewed-by: CK Hu Link: https://patchwork.kernel.org/project/dri-devel/patch/20230725073234.55892-2-angelogioacchino.delregno@collabora.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_dp.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 007af69e5026..4c249939a6c3 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -1588,7 +1588,9 @@ static int mtk_dp_parse_capabilities(struct mtk_dp *mtk_dp) u8 val; ssize_t ret; - drm_dp_read_dpcd_caps(&mtk_dp->aux, mtk_dp->rx_cap); + ret = drm_dp_read_dpcd_caps(&mtk_dp->aux, mtk_dp->rx_cap); + if (ret < 0) + return ret; if (drm_dp_tps4_supported(mtk_dp->rx_cap)) mtk_dp->train_info.channel_eq_pattern = DP_TRAINING_PATTERN_4; @@ -1615,10 +1617,13 @@ static int mtk_dp_parse_capabilities(struct mtk_dp *mtk_dp) return ret == 0 ? -EIO : ret; } - if (val) - drm_dp_dpcd_writeb(&mtk_dp->aux, - DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0, - val); + if (val) { + ret = drm_dp_dpcd_writeb(&mtk_dp->aux, + DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0, + val); + if (ret < 0) + return ret; + } } return 0; From 635051576f0ef5ee056bac6ac8d0c8405c49ce6a Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 4 Aug 2023 13:38:01 +0300 Subject: [PATCH 0983/2093] bus: ti-sysc: Fix build warning for 64-bit build [ Upstream commit e1e1e9bb9d943ec690670a609a5f660ca10eaf85 ] Fix "warning: cast from pointer to integer of different size" on 64-bit builds. Note that this is a cosmetic fix at this point as the driver is not yet used for 64-bit systems. Fixes: feaa8baee82a ("bus: ti-sysc: Implement SoC revision handling") Reviewed-by: Dhruva Gole Reviewed-by: Nishanth Menon Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 9b7268bae66a..0c933788d857 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3125,7 +3125,7 @@ static int sysc_init_static_data(struct sysc *ddata) match = soc_device_match(sysc_soc_match); if (match && match->data) - sysc_soc->soc = (int)match->data; + sysc_soc->soc = (enum sysc_soc)match->data; /* * Check and warn about possible old incomplete dtb. We now want to see From 4d6a25792fc1b7b434d855d317e4d77b3cab7cae Mon Sep 17 00:00:00 2001 From: "Jason-JH.Lin" Date: Fri, 14 Jul 2023 17:49:05 +0800 Subject: [PATCH 0984/2093] drm/mediatek: Remove freeing not dynamic allocated memory [ Upstream commit 27b9e2ea3f2757da26bb8280e46f7fdbb1acb219 ] Fixing the coverity issue of: mtk_drm_cmdq_pkt_destroy frees address of mtk_crtc->cmdq_handle So remove the free function. Fixes: 7627122fd1c0 ("drm/mediatek: Add cmdq_handle in mtk_crtc") Signed-off-by: Jason-JH.Lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: CK Hu Reviewed-by: Alexandre Mergnat Link: https://patchwork.kernel.org/project/dri-devel/patch/20230714094908.13087-2-jason-jh.lin@mediatek.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 5071f1263216..14ddfe3a6be7 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -115,10 +115,9 @@ static int mtk_drm_cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt * dma_addr_t dma_addr; pkt->va_base = kzalloc(size, GFP_KERNEL); - if (!pkt->va_base) { - kfree(pkt); + if (!pkt->va_base) return -ENOMEM; - } + pkt->buf_size = size; pkt->cl = (void *)client; @@ -128,7 +127,6 @@ static int mtk_drm_cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt * if (dma_mapping_error(dev, dma_addr)) { dev_err(dev, "dma map failed, size=%u\n", (u32)(u64)size); kfree(pkt->va_base); - kfree(pkt); return -ENOMEM; } @@ -144,7 +142,6 @@ static void mtk_drm_cmdq_pkt_destroy(struct cmdq_pkt *pkt) dma_unmap_single(client->chan->mbox->dev, pkt->pa_base, pkt->buf_size, DMA_TO_DEVICE); kfree(pkt->va_base); - kfree(pkt); } #endif From 1e47d1ac20e3b0025ecd0ab0f698d82c1c37eee7 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 11 Aug 2023 13:01:16 +0200 Subject: [PATCH 0985/2093] ARM: dts: qcom: ipq4019: correct SDHCI XO clock [ Upstream commit b5ed7a5c1fdb3981713f7b637b72aa390c3db036 ] Using GCC_DCD_XO_CLK as the XO clock for SDHCI controller is not correct, it seems that I somehow made a mistake of passing it instead of the fixed XO clock. Fixes: 04b3b72b5b8f ("ARM: dts: qcom: ipq4019: Add SDHCI controller node") Signed-off-by: Robert Marko Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230811110150.229966-1-robert.marko@sartura.hr Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm/boot/dts/qcom-ipq4019.dtsi | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom-ipq4019.dtsi index 02e13d8c222a..b5e0ed4923b5 100644 --- a/arch/arm/boot/dts/qcom-ipq4019.dtsi +++ b/arch/arm/boot/dts/qcom-ipq4019.dtsi @@ -228,9 +228,12 @@ sdhci: mmc@7824900 { interrupts = , ; interrupt-names = "hc_irq", "pwr_irq"; bus-width = <8>; - clocks = <&gcc GCC_SDCC1_AHB_CLK>, <&gcc GCC_SDCC1_APPS_CLK>, - <&gcc GCC_DCD_XO_CLK>; - clock-names = "iface", "core", "xo"; + clocks = <&gcc GCC_SDCC1_AHB_CLK>, + <&gcc GCC_SDCC1_APPS_CLK>, + <&xo>; + clock-names = "iface", + "core", + "xo"; status = "disabled"; }; From 867aa88c9efa512aaf3902ea2cbe4f2ae1a4d2d0 Mon Sep 17 00:00:00 2001 From: Sui Jingfeng Date: Thu, 6 Jul 2023 21:40:00 +0800 Subject: [PATCH 0986/2093] drm/mediatek: Fix potential memory leak if vmap() fail [ Upstream commit 379091e0f6d179d1a084c65de90fa44583b14a70 ] Also return -ENOMEM if such a failure happens, the implement should take responsibility for the error handling. Fixes: 3df64d7b0a4f ("drm/mediatek: Implement gem prime vmap/vunmap function") Reviewed-by: Matthias Brugger Reviewed-by: Alexandre Mergnat Signed-off-by: Sui Jingfeng Reviewed-by: CK Hu Reviewed-by: AngeloGioacchino Del Regno Link: https://patchwork.kernel.org/project/dri-devel/patch/20230706134000.130098-1-suijingfeng@loongson.cn/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_gem.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 6c204ccfb9ec..1d0374a577a5 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -242,7 +242,11 @@ int mtk_drm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP, pgprot_writecombine(PAGE_KERNEL)); - + if (!mtk_gem->kvaddr) { + kfree(sgt); + kfree(mtk_gem->pages); + return -ENOMEM; + } out: kfree(sgt); iosys_map_set_vaddr(map, mtk_gem->kvaddr); From 67b4726cb87ea46022381061461d80dd030e2721 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Sat, 12 Aug 2023 00:47:33 +0100 Subject: [PATCH 0987/2093] arm64: dts: qcom: apq8016-sbc: Fix ov5640 regulator supply names [ Upstream commit 43a684580819e7f35b6cb38236be63c4cba26ef4 ] The ov5640 driver expects DOVDD, AVDD and DVDD as regulator supply names. The ov5640 has depended on these names since the driver was committed upstream in 2017. Similarly apq8016-sbc.dtsi has had completely different regulator names since its own initial commit in 2020. Perhaps the regulators were left on in previous 410c bootloaders. In any case today on 6.5 we won't switch on the ov5640 without correctly naming the regulators. Fixes: 39e0ce6cd1bf ("arm64: dts: qcom: apq8016-sbc: Add CCI/Sensor nodes") Signed-off-by: Bryan O'Donoghue Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230811234738.2859417-3-bryan.odonoghue@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/apq8016-sbc.dts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts index e3e90ad92cc5..9650ae70c872 100644 --- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dts +++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dts @@ -289,9 +289,9 @@ camera_rear@3b { clock-names = "xclk"; clock-frequency = <23880000>; - vdddo-supply = <&camera_vdddo_1v8>; - vdda-supply = <&camera_vdda_2v8>; - vddd-supply = <&camera_vddd_1v5>; + DOVDD-supply = <&camera_vdddo_1v8>; + AVDD-supply = <&camera_vdda_2v8>; + DVDD-supply = <&camera_vddd_1v5>; /* No camera mezzanine by default */ status = "disabled"; From cab4cdb2a4bdff2c58043769763f22875b7ad8c9 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 9 Aug 2023 21:20:24 +0200 Subject: [PATCH 0988/2093] arm64: dts: qcom: msm8998: Drop bus clock reference from MMSS SMMU [ Upstream commit a3ce236364b82688ca4c7605f63c4efd68e9589c ] The MMSS SMMU has been abusingly consuming the exposed RPM interconnect clock. Drop it. Fixes: 05ce21b54423 ("arm64: dts: qcom: msm8998: Configure the multimedia subsystem iommu") Reviewed-by: Jeffrey Hugo Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230531-topic-8998_mmssclk-v3-1-ba1b1fd9ee75@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8998.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 29c60bb56ed5..3d6c7940d2a0 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -2418,10 +2418,10 @@ mmss_smmu: iommu@cd00000 { clocks = <&mmcc MNOC_AHB_CLK>, <&mmcc BIMC_SMMU_AHB_CLK>, - <&rpmcc RPM_SMD_MMAXI_CLK>, <&mmcc BIMC_SMMU_AXI_CLK>; - clock-names = "iface-mm", "iface-smmu", - "bus-mm", "bus-smmu"; + clock-names = "iface-mm", + "iface-smmu", + "bus-smmu"; #global-interrupts = <0>; interrupts = From c6035ee015b90a47ee37288fb3195d97eb6fc885 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 9 Aug 2023 21:20:25 +0200 Subject: [PATCH 0989/2093] arm64: dts: qcom: msm8998: Add missing power domain to MMSS SMMU [ Upstream commit 7f828f3207142351750e9545527341425187de7b ] The MMSS SMMU has its own power domain. Attach it so that we can drop the "keep it always-on" hack. Fixes: 05ce21b54423 ("arm64: dts: qcom: msm8998: Configure the multimedia subsystem iommu") Reviewed-by: Jeffrey Hugo Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230531-topic-8998_mmssclk-v3-2-ba1b1fd9ee75@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8998.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 3d6c7940d2a0..b00b8164c4aa 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -2445,6 +2445,8 @@ mmss_smmu: iommu@cd00000 { , , ; + + power-domains = <&mmcc BIMC_SMMU_GDSC>; }; remoteproc_adsp: remoteproc@17300000 { From b386c3e16956c1993de64076b53b3d289e36a58b Mon Sep 17 00:00:00 2001 From: David Wronek Date: Sat, 5 Aug 2023 15:09:37 +0200 Subject: [PATCH 0990/2093] arm64: dts: qcom: msm8996: Fix dsi1 interrupts [ Upstream commit bd3b4ac11845b428996cfd2c7b8302ba6a07340d ] Fix IRQ flags mismatch which was keeping dsi1 from probing by changing interrupts = <4> to interrupts = <5>. Fixes: 2752bb7d9b58 ("arm64: dts: qcom: msm8996: add second DSI interface") Signed-off-by: David Wronek Acked-by: Yassine Oudjana Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230805130936.359860-2-davidwronek@gmail.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 7e381d8257ba..9de2248a385a 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -1063,7 +1063,7 @@ dsi1: dsi@996000 { reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4>; + interrupts = <5>; clocks = <&mmcc MDSS_MDP_CLK>, <&mmcc MDSS_BYTE1_CLK>, From 5abfee5e40764b8db1ea38610028a251c99edd56 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 3 Aug 2023 15:05:26 +0200 Subject: [PATCH 0991/2093] arm64: dts: qcom: sc8280xp-x13s: Unreserve NC pins [ Upstream commit 7868ed0144b33903e16a50485775f669c109e41a ] Pins 83-86 and 158-160 are NC, so there's no point in keeping them reserved. Take care of that. Fixes: 32c231385ed4 ("arm64: dts: qcom: sc8280xp: add Lenovo Thinkpad X13s devicetree") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230803-topic-x13s_pin-v1-1-fae792274e89@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index b2b744bb8a53..49d15432aeab 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -347,7 +347,7 @@ edp_bl_pwm: edp-bl-pwm-state { }; &tlmm { - gpio-reserved-ranges = <70 2>, <74 6>, <83 4>, <125 2>, <128 2>, <154 7>; + gpio-reserved-ranges = <70 2>, <74 6>, <125 2>, <128 2>, <154 4>; kybd_default: kybd-default-state { disable { From 26bf790b8e99863a9caa9af764f1d1571547a63c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 15 Aug 2023 08:49:05 +0300 Subject: [PATCH 0992/2093] bus: ti-sysc: Fix cast to enum warning [ Upstream commit de44bf2f7683347f75690ef6cf61a1d5ba8f0891 ] Fix warning for "cast to smaller integer type 'enum sysc_soc' from 'const void *'". Cc: Nishanth Menon Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202308150723.ziuGCdM3-lkp@intel.com/ Fixes: e1e1e9bb9d94 ("bus: ti-sysc: Fix build warning for 64-bit build") Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 0c933788d857..ac36b01cf6d5 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3125,7 +3125,7 @@ static int sysc_init_static_data(struct sysc *ddata) match = soc_device_match(sysc_soc_match); if (match && match->data) - sysc_soc->soc = (enum sysc_soc)match->data; + sysc_soc->soc = (enum sysc_soc)(uintptr_t)match->data; /* * Check and warn about possible old incomplete dtb. We now want to see From ac9e103f282a7854f3274ef5ff0742fbbe8d7d6b Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sat, 8 Jul 2023 17:17:27 +0800 Subject: [PATCH 0993/2093] md/raid5-cache: fix a deadlock in r5l_exit_log() [ Upstream commit a705b11b358dee677aad80630e7608b2d5f56691 ] Commit b13015af94cf ("md/raid5-cache: Clear conf->log after finishing work") introduce a new problem: // caller hold reconfig_mutex r5l_exit_log flush_work(&log->disable_writeback_work) r5c_disable_writeback_async wait_event /* * conf->log is not NULL, and mddev_trylock() * will fail, wait_event() can never pass. */ conf->log = NULL Fix this problem by setting 'config->log' to NULL before wake_up() as it used to be, so that wait_event() from r5c_disable_writeback_async() can exist. In the meantime, move forward md_unregister_thread() so that null-ptr-deref this commit fixed can still be fixed. Fixes: b13015af94cf ("md/raid5-cache: Clear conf->log after finishing work") Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20230708091727.1417894-1-yukuai1@huaweicloud.com Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/raid5-cache.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 832d8566e165..477e3ae17545 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -3166,12 +3166,15 @@ void r5l_exit_log(struct r5conf *conf) { struct r5l_log *log = conf->log; - /* Ensure disable_writeback_work wakes up and exits */ - wake_up(&conf->mddev->sb_wait); - flush_work(&log->disable_writeback_work); md_unregister_thread(&log->reclaim_thread); + /* + * 'reconfig_mutex' is held by caller, set 'confg->log' to NULL to + * ensure disable_writeback_work wakes up and exits. + */ conf->log = NULL; + wake_up(&conf->mddev->sb_wait); + flush_work(&log->disable_writeback_work); mempool_exit(&log->meta_pool); bioset_exit(&log->bs); From 711fb92606208a8626b785da4f9f23d648a5b6c8 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 8 Aug 2023 18:49:12 +0800 Subject: [PATCH 0994/2093] md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid() [ Upstream commit 0d0bd28c500173bfca78aa840f8f36d261ef1765 ] r5l_flush_stripe_to_raid() will check if the list 'flushing_ios' is empty, and then submit 'flush_bio', however, r5l_log_flush_endio() is clearing the list first and then clear the bio, which will cause null-ptr-deref: T1: submit flush io raid5d handle_active_stripes r5l_flush_stripe_to_raid // list is empty // add 'io_end_ios' to the list bio_init submit_bio // io1 T2: io1 is done r5l_log_flush_endio list_splice_tail_init // clear the list T3: submit new flush io ... r5l_flush_stripe_to_raid // list is empty // add 'io_end_ios' to the list bio_init bio_uninit // clear bio->bi_blkg submit_bio // null-ptr-deref Fix this problem by clearing bio before clearing the list in r5l_log_flush_endio(). Fixes: 0dd00cba99c3 ("raid5-cache: fully initialize flush_bio when needed") Reported-and-tested-by: Corey Hickey Closes: https://lore.kernel.org/all/cddd7213-3dfd-4ab7-a3ac-edd54d74a626@fatooh.org/ Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/raid5-cache.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 477e3ae17545..eb66d0bfe39d 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1260,14 +1260,13 @@ static void r5l_log_flush_endio(struct bio *bio) if (bio->bi_status) md_error(log->rdev->mddev, log->rdev); + bio_uninit(bio); spin_lock_irqsave(&log->io_list_lock, flags); list_for_each_entry(io, &log->flushing_ios, log_sibling) r5l_io_run_stripes(io); list_splice_tail_init(&log->flushing_ios, &log->finished_ios); spin_unlock_irqrestore(&log->io_list_lock, flags); - - bio_uninit(bio); } /* From bc82cd1e7ff28e35b144c73bbc9af2fbfd1ab540 Mon Sep 17 00:00:00 2001 From: Vlad Karpovich Date: Tue, 15 Aug 2023 12:29:08 -0500 Subject: [PATCH 0995/2093] firmware: cs_dsp: Fix new control name check [ Upstream commit 7ac1102b227b36550452b663fd39ab1c09378a95 ] Before adding a new FW control, its name is checked against existing controls list. But the string length in strncmp used to compare controls names is taken from the list, so if beginnings of the controls are matching, then the new control is not created. For example, if CAL_R control already exists, CAL_R_SELECTED is not created. The fix is to compare string lengths as well. Fixes: 6477960755fb ("ASoC: wm_adsp: Move check for control existence") Signed-off-by: Vlad Karpovich Link: https://lore.kernel.org/r/20230815172908.3454056-1-vkarpovi@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/firmware/cirrus/cs_dsp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 81cc3d0f6eec..81c5f94b1be1 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -939,7 +939,8 @@ static int cs_dsp_create_control(struct cs_dsp *dsp, ctl->alg_region.alg == alg_region->alg && ctl->alg_region.type == alg_region->type) { if ((!subname && !ctl->subname) || - (subname && !strncmp(ctl->subname, subname, ctl->subname_len))) { + (subname && (ctl->subname_len == subname_len) && + !strncmp(ctl->subname, subname, ctl->subname_len))) { if (!ctl->enabled) ctl->enabled = 1; return 0; From c227aa141660ec3a79bbb4d090029e52ad552fef Mon Sep 17 00:00:00 2001 From: Mariusz Tkaczyk Date: Mon, 6 Mar 2023 14:03:17 +0100 Subject: [PATCH 0996/2093] md: add error_handlers for raid0 and linear [ Upstream commit c31fea2f8e2a72c817f318016bbc327095175a9f ] After the commit 9631abdbf406c("md: Set MD_BROKEN for RAID1 and RAID10") MD_BROKEN must be set if array is failed because state_store() checks it. If it is set then -EBUSY is returned to userspace. For raid0 and linear MD_BROKEN is not set by error_handler(). As a result mdadm is unable to trigger clean-up actions. It is a regression. This patch adds appropriate error_handler for raid0 and linear. The error handler sets MD_BROKEN for this device. Reviewed-by: Xiao Ni Signed-off-by: Mariusz Tkaczyk Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230306130317.3418-1-mariusz.tkaczyk@linux.intel.com Stable-dep-of: 319ff40a5427 ("md/raid0: Fix performance regression for large sequential writes") Signed-off-by: Sasha Levin --- drivers/md/md-linear.c | 14 +++++++++++++- drivers/md/md.c | 3 +++ drivers/md/md.h | 10 ++-------- drivers/md/raid0.c | 14 +++++++++++++- 4 files changed, 31 insertions(+), 10 deletions(-) diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 6e7797b4e738..4eb72b9dd933 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -223,7 +223,8 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) bio_sector < start_sector)) goto out_of_bounds; - if (unlikely(is_mddev_broken(tmp_dev->rdev, "linear"))) { + if (unlikely(is_rdev_broken(tmp_dev->rdev))) { + md_error(mddev, tmp_dev->rdev); bio_io_error(bio); return true; } @@ -270,6 +271,16 @@ static void linear_status (struct seq_file *seq, struct mddev *mddev) seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); } +static void linear_error(struct mddev *mddev, struct md_rdev *rdev) +{ + if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) { + char *md_name = mdname(mddev); + + pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n", + md_name, rdev->bdev); + } +} + static void linear_quiesce(struct mddev *mddev, int state) { } @@ -286,6 +297,7 @@ static struct md_personality linear_personality = .hot_add_disk = linear_add, .size = linear_size, .quiesce = linear_quiesce, + .error_handler = linear_error, }; static int __init linear_init (void) diff --git a/drivers/md/md.c b/drivers/md/md.c index 443837fe6291..b65d8bf54924 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7992,6 +7992,9 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) return; mddev->pers->error_handler(mddev, rdev); + if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR) + return; + if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); sysfs_notify_dirent_safe(rdev->sysfs_state); diff --git a/drivers/md/md.h b/drivers/md/md.h index 64f8182a3dfc..4f0b48097455 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -790,15 +790,9 @@ extern void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev, struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr); struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev); -static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type) +static inline bool is_rdev_broken(struct md_rdev *rdev) { - if (!disk_live(rdev->bdev->bd_disk)) { - if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags)) - pr_warn("md: %s: %s array has a missing/failed member\n", - mdname(rdev->mddev), md_type); - return true; - } - return false; + return !disk_live(rdev->bdev->bd_disk); } static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 0f7c3b3c62b2..d1ac73fcd852 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -615,8 +615,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) return true; } - if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) { + if (unlikely(is_rdev_broken(tmp_dev))) { bio_io_error(bio); + md_error(mddev, tmp_dev); return true; } @@ -638,6 +639,16 @@ static void raid0_status(struct seq_file *seq, struct mddev *mddev) return; } +static void raid0_error(struct mddev *mddev, struct md_rdev *rdev) +{ + if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) { + char *md_name = mdname(mddev); + + pr_crit("md/raid0%s: Disk failure on %pg detected, failing array.\n", + md_name, rdev->bdev); + } +} + static void *raid0_takeover_raid45(struct mddev *mddev) { struct md_rdev *rdev; @@ -813,6 +824,7 @@ static struct md_personality raid0_personality= .size = raid0_size, .takeover = raid0_takeover, .quiesce = raid0_quiesce, + .error_handler = raid0_error, }; static int __init raid0_init (void) From cd1dd83888d7c6ce4f92dc18b207c3f34a0c529a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 14 Aug 2023 11:27:07 +0200 Subject: [PATCH 0997/2093] md/raid0: Factor out helper for mapping and submitting a bio [ Upstream commit af50e20afb401cc203bd2a9ff62ece0ae4976103 ] Factor out helper function for mapping and submitting a bio out of raid0_make_request(). We will use it later for submitting both parts of a split bio. Signed-off-by: Jan Kara Reviewed-by: Yu Kuai Link: https://lore.kernel.org/r/20230814092720.3931-1-jack@suse.cz Signed-off-by: Song Liu Stable-dep-of: 319ff40a5427 ("md/raid0: Fix performance regression for large sequential writes") Signed-off-by: Sasha Levin --- drivers/md/raid0.c | 83 +++++++++++++++++++++++----------------------- 1 file changed, 42 insertions(+), 41 deletions(-) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index d1ac73fcd852..d3c55f2e9b18 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -557,14 +557,51 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) bio_endio(bio); } -static bool raid0_make_request(struct mddev *mddev, struct bio *bio) +static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio) { struct r0conf *conf = mddev->private; struct strip_zone *zone; struct md_rdev *tmp_dev; - sector_t bio_sector; + sector_t bio_sector = bio->bi_iter.bi_sector; + sector_t sector = bio_sector; + + if (bio->bi_pool != &mddev->bio_set) + md_account_bio(mddev, &bio); + + zone = find_zone(mddev->private, §or); + switch (conf->layout) { + case RAID0_ORIG_LAYOUT: + tmp_dev = map_sector(mddev, zone, bio_sector, §or); + break; + case RAID0_ALT_MULTIZONE_LAYOUT: + tmp_dev = map_sector(mddev, zone, sector, §or); + break; + default: + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); + bio_io_error(bio); + return; + } + + if (unlikely(is_rdev_broken(tmp_dev))) { + bio_io_error(bio); + md_error(mddev, tmp_dev); + return; + } + + bio_set_dev(bio, tmp_dev->bdev); + bio->bi_iter.bi_sector = sector + zone->dev_start + + tmp_dev->data_offset; + + if (mddev->gendisk) + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), + bio_sector); + mddev_check_write_zeroes(mddev, bio); + submit_bio_noacct(bio); +} + +static bool raid0_make_request(struct mddev *mddev, struct bio *bio) +{ sector_t sector; - sector_t orig_sector; unsigned chunk_sects; unsigned sectors; @@ -577,8 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) return true; } - bio_sector = bio->bi_iter.bi_sector; - sector = bio_sector; + sector = bio->bi_iter.bi_sector; chunk_sects = mddev->chunk_sectors; sectors = chunk_sects - @@ -586,9 +622,6 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) ? (sector & (chunk_sects-1)) : sector_div(sector, chunk_sects)); - /* Restore due to sector_div */ - sector = bio_sector; - if (sectors < bio_sectors(bio)) { struct bio *split = bio_split(bio, sectors, GFP_NOIO, &mddev->bio_set); @@ -597,39 +630,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio = split; } - if (bio->bi_pool != &mddev->bio_set) - md_account_bio(mddev, &bio); - - orig_sector = sector; - zone = find_zone(mddev->private, §or); - switch (conf->layout) { - case RAID0_ORIG_LAYOUT: - tmp_dev = map_sector(mddev, zone, orig_sector, §or); - break; - case RAID0_ALT_MULTIZONE_LAYOUT: - tmp_dev = map_sector(mddev, zone, sector, §or); - break; - default: - WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); - bio_io_error(bio); - return true; - } - - if (unlikely(is_rdev_broken(tmp_dev))) { - bio_io_error(bio); - md_error(mddev, tmp_dev); - return true; - } - - bio_set_dev(bio, tmp_dev->bdev); - bio->bi_iter.bi_sector = sector + zone->dev_start + - tmp_dev->data_offset; - - if (mddev->gendisk) - trace_block_bio_remap(bio, disk_devt(mddev->gendisk), - bio_sector); - mddev_check_write_zeroes(mddev, bio); - submit_bio_noacct(bio); + raid0_map_submit_bio(mddev, bio); return true; } From cc54fa43de67632789a2b0e5767a46f32f5e7937 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 14 Aug 2023 11:27:08 +0200 Subject: [PATCH 0998/2093] md/raid0: Fix performance regression for large sequential writes [ Upstream commit 319ff40a542736d67e5bce18635de35d0e7a0bff ] Commit f00d7c85be9e ("md/raid0: fix up bio splitting.") among other things changed how bio that needs to be split is submitted. Before this commit, we have split the bio, mapped and submitted each part. After this commit, we map only the first part of the split bio and submit the second part unmapped. Due to bio sorting in __submit_bio_noacct() this results in the following request ordering: 9,0 18 1181 0.525037895 15995 Q WS 1479315464 + 63392 Split off chunk-sized (1024 sectors) request: 9,0 18 1182 0.629019647 15995 X WS 1479315464 / 1479316488 Request is unaligned to the chunk so it's split in raid0_make_request(). This is the first part mapped and punted to bio_list: 8,0 18 7053 0.629020455 15995 A WS 739921928 + 1016 <- (9,0) 1479315464 Now raid0_make_request() returns, second part is postponed on bio_list. __submit_bio_noacct() resorts the bio_list, mapped request is submitted to the underlying device: 8,0 18 7054 0.629022782 15995 G WS 739921928 + 1016 Now we take another request from the bio_list which is the remainder of the original huge request. Split off another chunk-sized bit from it and the situation repeats: 9,0 18 1183 0.629024499 15995 X WS 1479316488 / 1479317512 8,16 18 6998 0.629025110 15995 A WS 739921928 + 1016 <- (9,0) 1479316488 8,16 18 6999 0.629026728 15995 G WS 739921928 + 1016 ... 9,0 18 1184 0.629032940 15995 X WS 1479317512 / 1479318536 [libnetacq-write] 8,0 18 7059 0.629033294 15995 A WS 739922952 + 1016 <- (9,0) 1479317512 8,0 18 7060 0.629033902 15995 G WS 739922952 + 1016 ... This repeats until we consume the whole original huge request. Now we finally get to processing the second parts of the split off requests (in reverse order): 8,16 18 7181 0.629161384 15995 A WS 739952640 + 8 <- (9,0) 1479377920 8,0 18 7239 0.629162140 15995 A WS 739952640 + 8 <- (9,0) 1479376896 8,16 18 7186 0.629163881 15995 A WS 739951616 + 8 <- (9,0) 1479375872 8,0 18 7242 0.629164421 15995 A WS 739951616 + 8 <- (9,0) 1479374848 ... I guess it is obvious that this IO pattern is extremely inefficient way to perform sequential IO. It also makes bio_list to grow to rather long lengths. Change raid0_make_request() to map both parts of the split bio. Since we know we are provided with at most chunk-sized bios, we will always need to split the incoming bio at most once. Fixes: f00d7c85be9e ("md/raid0: fix up bio splitting.") Signed-off-by: Jan Kara Reviewed-by: Yu Kuai Link: https://lore.kernel.org/r/20230814092720.3931-2-jack@suse.cz Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/raid0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index d3c55f2e9b18..595856948dff 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -626,7 +626,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) struct bio *split = bio_split(bio, sectors, GFP_NOIO, &mddev->bio_set); bio_chain(split, bio); - submit_bio_noacct(bio); + raid0_map_submit_bio(mddev, bio); bio = split; } From c4b06324fc4410e14d27ab56c91a2387f8a88a53 Mon Sep 17 00:00:00 2001 From: David Jeffery Date: Wed, 16 Aug 2023 14:13:55 -0400 Subject: [PATCH 0999/2093] md: raid0: account for split bio in iostat accounting [ Upstream commit cc22b5407e9ca76adb7efeed843146510b1b72a5 ] When a bio is split by md raid0, the newly created bio will not be tracked by md for I/O accounting. Only the portion of I/O still assigned to the original bio which was reduced by the split will be accounted for. This results in md iostat data sometimes showing I/O values far below the actual amount of data being sent through md. md_account_bio() needs to be called for all bio generated by the bio split. A simple example of the issue was generated using a raid0 device on partitions to the same device. Since all raid0 I/O then goes to one device, it makes it easy to see a gap between the md device and its sd storage. Reading an lvm device on top of the md device, the iostat output (some 0 columns and extra devices removed to make the data more compact) was: Device tps kB_read/s kB_wrtn/s kB_dscd/s kB_read md2 0.00 0.00 0.00 0.00 0 sde 0.00 0.00 0.00 0.00 0 md2 1364.00 411496.00 0.00 0.00 411496 sde 1734.00 646144.00 0.00 0.00 646144 md2 1699.00 510680.00 0.00 0.00 510680 sde 2155.00 802784.00 0.00 0.00 802784 md2 803.00 241480.00 0.00 0.00 241480 sde 1016.00 377888.00 0.00 0.00 377888 md2 0.00 0.00 0.00 0.00 0 sde 0.00 0.00 0.00 0.00 0 I/O was generated doing large direct I/O reads (12M) with dd to a linear lvm volume on top of the 4 leg raid0 device. The md2 reads were showing as roughly 2/3 of the reads to the sde device containing all of md2's raid partitions. The sum of reads to sde was 1826816 kB, which was the expected amount as it was the amount read by dd. With the patch, the total reads from md will match the reads from sde and be consistent with the amount of I/O generated. Fixes: 10764815ff47 ("md: add io accounting for raid0 and raid5") Signed-off-by: David Jeffery Tested-by: Laurence Oberman Reviewed-by: Laurence Oberman Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230816181433.13289-1-djeffery@redhat.com Signed-off-by: Sasha Levin --- drivers/md/raid0.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 595856948dff..7c6a0b4437d8 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -565,8 +565,7 @@ static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio) sector_t bio_sector = bio->bi_iter.bi_sector; sector_t sector = bio_sector; - if (bio->bi_pool != &mddev->bio_set) - md_account_bio(mddev, &bio); + md_account_bio(mddev, &bio); zone = find_zone(mddev->private, §or); switch (conf->layout) { From b13b0c84a4afbdb34866094938aa6163a70d6c94 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Wed, 23 Aug 2023 13:03:39 +0530 Subject: [PATCH 1000/2093] ASoC: SOF: amd: clear dsp to host interrupt status [ Upstream commit 38592ae6dc9f84b7a994c43de2136b8115ca30f6 ] DSP_SW_INTR_STAT_OFFSET is a common interrupt register which will be accessed by both ACP firmware and driver. This register contains register bits corresponds to host to dsp interrupts and vice versa. when dsp to host interrupt is reported, only clear dsp to host interrupt bit in DSP_SW_INTR_STAT_OFFSET. Fixes: 2e7c6652f9b8 ("ASoC: SOF: amd: Fix for handling spurious interrupts from DSP") Signed-off-by: Vijendar Mukunda Link: https://lore.kernel.org/r/20230823073340.2829821-7-Vijendar.Mukunda@amd.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/amd/acp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index 8afd67ba1e5a..f8d2372a758f 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -349,9 +349,9 @@ static irqreturn_t acp_irq_handler(int irq, void *dev_id) unsigned int val; val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET); - if (val) { - val |= ACP_DSP_TO_HOST_IRQ; - snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET, val); + if (val & ACP_DSP_TO_HOST_IRQ) { + snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET, + ACP_DSP_TO_HOST_IRQ); return IRQ_WAKE_THREAD; } From 3fb210cd521c9efcb211e9f5ce40fc907200bf13 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 28 Jul 2023 10:50:28 +0200 Subject: [PATCH 1001/2093] of: overlay: Call of_changeset_init() early [ Upstream commit a9515ff4fb142b690a0d2b58782b15903b990dba ] When of_overlay_fdt_apply() fails, the changeset may be partially applied, and the caller is still expected to call of_overlay_remove() to clean up this partial state. However, of_overlay_apply() calls of_resolve_phandles() before init_overlay_changeset(). Hence if the overlay fails to apply due to an unresolved symbol, the overlay_changeset.cset.entries list is still uninitialized, and cleanup will crash with a NULL-pointer dereference in overlay_removal_is_ok(). Fix this by moving the call to of_changeset_init() from init_overlay_changeset() to of_overlay_fdt_apply(), where all other early initialization is done. Fixes: f948d6d8b792bb90 ("of: overlay: avoid race condition between applying multiple overlays") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/4f1d6d74b61cba2599026adb6d1948ae559ce91f.1690533838.git.geert+renesas@glider.be Signed-off-by: Rob Herring Signed-off-by: Sasha Levin --- drivers/of/overlay.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 5289975bad70..4402871b5c0c 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -752,8 +752,6 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs) if (!of_node_is_root(ovcs->overlay_root)) pr_debug("%s() ovcs->overlay_root is not root\n", __func__); - of_changeset_init(&ovcs->cset); - cnt = 0; /* fragment nodes */ @@ -1013,6 +1011,7 @@ int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, INIT_LIST_HEAD(&ovcs->ovcs_list); list_add_tail(&ovcs->ovcs_list, &ovcs_list); + of_changeset_init(&ovcs->cset); /* * Must create permanent copy of FDT because of_fdt_unflatten_tree() From 53996463f8c35dd66a13453c1d3d8f6f695f4973 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 28 Jul 2023 10:50:29 +0200 Subject: [PATCH 1002/2093] of: unittest: Fix overlay type in apply/revert check [ Upstream commit 6becf8f845ae1f0b1cfed395bbeccbd23654162d ] The removal check in of_unittest_apply_revert_overlay_check() always uses the platform device overlay type, while it should use the actual overlay type, as passed as a parameter to the function. This has no impact on any current test, as all tests calling of_unittest_apply_revert_overlay_check() use the platform device overlay type. Fixes: d5e75500ca401d31 ("of: unitest: Add I2C overlay unit tests.") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/ba0234c41ba808f10112094f88792beeb6dbaedf.1690533838.git.geert+renesas@glider.be Signed-off-by: Rob Herring Signed-off-by: Sasha Levin --- drivers/of/unittest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index b815b8862e18..edd2342598e4 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -2062,7 +2062,7 @@ static int __init of_unittest_apply_revert_overlay_check(int overlay_nr, of_unittest_untrack_overlay(save_ovcs_id); /* unittest device must be again in before state */ - if (of_unittest_device_exists(unittest_nr, PDEV_OVERLAY) != before) { + if (of_unittest_device_exists(unittest_nr, ovtype) != before) { unittest(0, "%s with device @\"%s\" %s\n", overlay_name_from_nr(overlay_nr), unittest_path(unittest_nr, ovtype), From abbd28d04c365708ec4bc700fb442213ee32e0dd Mon Sep 17 00:00:00 2001 From: Su Hui Date: Wed, 23 Aug 2023 10:52:13 +0800 Subject: [PATCH 1003/2093] ALSA: ac97: Fix possible error value of *rac97 [ Upstream commit 67de40c9df94037769967ba28c7d951afb45b7fb ] Before committing 79597c8bf64c, *rac97 always be NULL if there is an error. When error happens, make sure *rac97 is NULL is safer. For examble, in snd_vortex_mixer(): err = snd_ac97_mixer(pbus, &ac97, &vortex->codec); vortex->isquad = ((vortex->codec == NULL) ? 0 : (vortex->codec->ext_id&0x80)); If error happened but vortex->codec isn't NULL, this may cause some problems. Move the judgement order to be clearer and better. Fixes: 79597c8bf64c ("ALSA: ac97: Fix possible NULL dereference in snd_ac97_mixer") Suggested-by: Christophe JAILLET Acked-by: Christophe JAILLET Signed-off-by: Su Hui Link: https://lore.kernel.org/r/20230823025212.1000961-1-suhui@nfschina.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/ac97/ac97_codec.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c index 534ea7a256ec..606b318f34e5 100644 --- a/sound/pci/ac97/ac97_codec.c +++ b/sound/pci/ac97/ac97_codec.c @@ -2070,10 +2070,9 @@ int snd_ac97_mixer(struct snd_ac97_bus *bus, struct snd_ac97_template *template, .dev_disconnect = snd_ac97_dev_disconnect, }; - if (!rac97) - return -EINVAL; - if (snd_BUG_ON(!bus || !template)) + if (snd_BUG_ON(!bus || !template || !rac97)) return -EINVAL; + *rac97 = NULL; if (snd_BUG_ON(template->num >= 4)) return -EINVAL; if (bus->codec[template->num]) From 2e7d90a81b9cee4103d2c2bb9b6be60fae74806a Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Mon, 19 Jun 2023 17:28:02 +0800 Subject: [PATCH 1004/2093] ipmi:ssif: Add check for kstrdup [ Upstream commit c5586d0f711e9744d0cade39b0c4a2d116a333ca ] Add check for the return value of kstrdup() and return the error if it fails in order to avoid NULL pointer dereference. Fixes: c4436c9149c5 ("ipmi_ssif: avoid registering duplicate ssif interface") Signed-off-by: Jiasheng Jiang Message-Id: <20230619092802.35384-1-jiasheng@iscas.ac.cn> Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_ssif.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index d48061ec27dd..e94d0750d5cc 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -1603,6 +1603,11 @@ static int ssif_add_infos(struct i2c_client *client) info->addr_src = SI_ACPI; info->client = client; info->adapter_name = kstrdup(client->adapter->name, GFP_KERNEL); + if (!info->adapter_name) { + kfree(info); + return -ENOMEM; + } + info->binfo.addr = client->addr; list_add_tail(&info->link, &ssif_infos); return 0; From 74a1194cce60a90723d0fe148863c18931a31153 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Mon, 19 Jun 2023 11:43:33 -0500 Subject: [PATCH 1005/2093] ipmi:ssif: Fix a memory leak when scanning for an adapter [ Upstream commit b8d72e32e1453d37ee5c8a219f24e7eeadc471ef ] The adapter scan ssif_info_find() sets info->adapter_name if the adapter info came from SMBIOS, as it's not set in that case. However, this function can be called more than once, and it will leak the adapter name if it had already been set. So check for NULL before setting it. Fixes: c4436c9149c5 ("ipmi_ssif: avoid registering duplicate ssif interface") Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_ssif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index e94d0750d5cc..248459f97c67 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -1403,7 +1403,7 @@ static struct ssif_addr_info *ssif_info_find(unsigned short addr, restart: list_for_each_entry(info, &ssif_infos, link) { if (info->binfo.addr == addr) { - if (info->addr_src == SI_SMBIOS) + if (info->addr_src == SI_SMBIOS && !info->adapter_name) info->adapter_name = kstrdup(adapter_name, GFP_KERNEL); From 6ace98cb617bafb506c8b76a98e91e3051271494 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 14 Jun 2023 13:35:32 +0200 Subject: [PATCH 1006/2093] clk: qcom: gpucc-sm6350: Introduce index-based clk lookup [ Upstream commit f6f89d194e4ddcfe197ac8a05ed4161f642a5c68 ] Add the nowadays-prefered and marginally faster way of looking up parent clocks in the device tree. It also allows for clock-names-independent operation, so long as the order (which is enforced by schema) is kept. Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230315-topic-lagoon_gpu-v2-1-afcdfb18bb13@linaro.org Signed-off-by: Bjorn Andersson Stable-dep-of: 743913b343a3 ("clk: qcom: gpucc-sm6350: Fix clock source names") Signed-off-by: Sasha Levin --- drivers/clk/qcom/gpucc-sm6350.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/clk/qcom/gpucc-sm6350.c b/drivers/clk/qcom/gpucc-sm6350.c index ef15185a99c3..a9887d1f0ed7 100644 --- a/drivers/clk/qcom/gpucc-sm6350.c +++ b/drivers/clk/qcom/gpucc-sm6350.c @@ -24,6 +24,12 @@ #define CX_GMU_CBCR_WAKE_MASK 0xF #define CX_GMU_CBCR_WAKE_SHIFT 8 +enum { + DT_BI_TCXO, + DT_GPLL0_OUT_MAIN, + DT_GPLL0_OUT_MAIN_DIV, +}; + enum { P_BI_TCXO, P_GPLL0_OUT_MAIN, @@ -61,6 +67,7 @@ static struct clk_alpha_pll gpu_cc_pll0 = { .hw.init = &(struct clk_init_data){ .name = "gpu_cc_pll0", .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, .fw_name = "bi_tcxo", }, .num_parents = 1, @@ -104,6 +111,7 @@ static struct clk_alpha_pll gpu_cc_pll1 = { .hw.init = &(struct clk_init_data){ .name = "gpu_cc_pll1", .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, .fw_name = "bi_tcxo", }, .num_parents = 1, @@ -121,11 +129,11 @@ static const struct parent_map gpu_cc_parent_map_0[] = { }; static const struct clk_parent_data gpu_cc_parent_data_0[] = { - { .fw_name = "bi_tcxo" }, + { .index = DT_BI_TCXO, .fw_name = "bi_tcxo" }, { .hw = &gpu_cc_pll0.clkr.hw }, { .hw = &gpu_cc_pll1.clkr.hw }, - { .fw_name = "gcc_gpu_gpll0_clk" }, - { .fw_name = "gcc_gpu_gpll0_div_clk" }, + { .index = DT_GPLL0_OUT_MAIN, .fw_name = "gcc_gpu_gpll0_clk" }, + { .index = DT_GPLL0_OUT_MAIN_DIV, .fw_name = "gcc_gpu_gpll0_div_clk" }, }; static const struct parent_map gpu_cc_parent_map_1[] = { @@ -138,12 +146,12 @@ static const struct parent_map gpu_cc_parent_map_1[] = { }; static const struct clk_parent_data gpu_cc_parent_data_1[] = { - { .fw_name = "bi_tcxo" }, + { .index = DT_BI_TCXO, .fw_name = "bi_tcxo" }, { .hw = &crc_div.hw }, { .hw = &gpu_cc_pll0.clkr.hw }, { .hw = &gpu_cc_pll1.clkr.hw }, { .hw = &gpu_cc_pll1.clkr.hw }, - { .fw_name = "gcc_gpu_gpll0_clk" }, + { .index = DT_GPLL0_OUT_MAIN, .fw_name = "gcc_gpu_gpll0_clk" }, }; static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = { From 9cba16beca66ad2e66e3a5952f2ccff98375d4fd Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 14 Jun 2023 13:35:33 +0200 Subject: [PATCH 1007/2093] clk: qcom: gpucc-sm6350: Fix clock source names [ Upstream commit 743913b343a3ec2510fe3c0dfaff03d049659922 ] fw_name for GCC inputs didn't match the bindings. Fix it. Fixes: 013804a727a0 ("clk: qcom: Add GPU clock controller driver for SM6350") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230315-topic-lagoon_gpu-v2-2-afcdfb18bb13@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gpucc-sm6350.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/qcom/gpucc-sm6350.c b/drivers/clk/qcom/gpucc-sm6350.c index a9887d1f0ed7..0bcbba2a2943 100644 --- a/drivers/clk/qcom/gpucc-sm6350.c +++ b/drivers/clk/qcom/gpucc-sm6350.c @@ -132,8 +132,8 @@ static const struct clk_parent_data gpu_cc_parent_data_0[] = { { .index = DT_BI_TCXO, .fw_name = "bi_tcxo" }, { .hw = &gpu_cc_pll0.clkr.hw }, { .hw = &gpu_cc_pll1.clkr.hw }, - { .index = DT_GPLL0_OUT_MAIN, .fw_name = "gcc_gpu_gpll0_clk" }, - { .index = DT_GPLL0_OUT_MAIN_DIV, .fw_name = "gcc_gpu_gpll0_div_clk" }, + { .index = DT_GPLL0_OUT_MAIN, .fw_name = "gcc_gpu_gpll0_clk_src" }, + { .index = DT_GPLL0_OUT_MAIN_DIV, .fw_name = "gcc_gpu_gpll0_div_clk_src" }, }; static const struct parent_map gpu_cc_parent_map_1[] = { @@ -151,7 +151,7 @@ static const struct clk_parent_data gpu_cc_parent_data_1[] = { { .hw = &gpu_cc_pll0.clkr.hw }, { .hw = &gpu_cc_pll1.clkr.hw }, { .hw = &gpu_cc_pll1.clkr.hw }, - { .index = DT_GPLL0_OUT_MAIN, .fw_name = "gcc_gpu_gpll0_clk" }, + { .index = DT_GPLL0_OUT_MAIN, .fw_name = "gcc_gpu_gpll0_clk_src" }, }; static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = { From 747848b4afeae3da9ca62c48ac800869d68f7442 Mon Sep 17 00:00:00 2001 From: Andrew Halaney Date: Thu, 13 Apr 2023 14:15:39 -0500 Subject: [PATCH 1008/2093] clk: qcom: gcc-sc8280xp: Add EMAC GDSCs [ Upstream commit 32c2f2a46db1322caaf78d5ea747ed5c56d2e353 ] Add the EMAC GDSCs to allow the EMAC hardware to be enabled. Acked-by: Stephen Boyd Reviewed-by: Konrad Dybcio Tested-by: Brian Masney Signed-off-by: Andrew Halaney Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230413191541.1073027-2-ahalaney@redhat.com Stable-dep-of: 2fd02de27054 ("clk: qcom: gcc-sc8280xp: Add missing GDSC flags") Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc8280xp.c | 18 ++++++++++++++++++ include/dt-bindings/clock/qcom,gcc-sc8280xp.h | 2 ++ 2 files changed, 20 insertions(+) diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index b3198784e1c3..04a99dbaa57e 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -6873,6 +6873,22 @@ static struct gdsc usb30_sec_gdsc = { .pwrsts = PWRSTS_RET_ON, }; +static struct gdsc emac_0_gdsc = { + .gdscr = 0xaa004, + .pd = { + .name = "emac_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc emac_1_gdsc = { + .gdscr = 0xba004, + .pd = { + .name = "emac_1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + static struct clk_regmap *gcc_sc8280xp_clocks[] = { [GCC_AGGRE_NOC_PCIE0_TUNNEL_AXI_CLK] = &gcc_aggre_noc_pcie0_tunnel_axi_clk.clkr, [GCC_AGGRE_NOC_PCIE1_TUNNEL_AXI_CLK] = &gcc_aggre_noc_pcie1_tunnel_axi_clk.clkr, @@ -7351,6 +7367,8 @@ static struct gdsc *gcc_sc8280xp_gdscs[] = { [USB30_MP_GDSC] = &usb30_mp_gdsc, [USB30_PRIM_GDSC] = &usb30_prim_gdsc, [USB30_SEC_GDSC] = &usb30_sec_gdsc, + [EMAC_0_GDSC] = &emac_0_gdsc, + [EMAC_1_GDSC] = &emac_1_gdsc, }; static const struct clk_rcg_dfs_data gcc_dfs_clocks[] = { diff --git a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h index cb2fb638825c..721105ea4fad 100644 --- a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h +++ b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h @@ -492,5 +492,7 @@ #define USB30_MP_GDSC 9 #define USB30_PRIM_GDSC 10 #define USB30_SEC_GDSC 11 +#define EMAC_0_GDSC 12 +#define EMAC_1_GDSC 13 #endif From 06d3a7e03c615a453ee6ab7f38b363213c9e1ab2 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jun 2023 19:48:06 +0200 Subject: [PATCH 1009/2093] clk: qcom: gcc-sc8280xp: Add missing GDSC flags [ Upstream commit 2fd02de27054576a4a8c89302e2f77122c55e957 ] All of the 8280's GCC GDSCs can and should use the retain registers so as not to lose their state when entering lower power modes. Fixes: d65d005f9a6c ("clk: qcom: add sc8280xp GCC driver") Signed-off-by: Konrad Dybcio Acked-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230620-topic-sc8280_gccgdsc-v2-1-562c1428c10d@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc8280xp.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index 04a99dbaa57e..43c518e5c986 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -6760,7 +6760,7 @@ static struct gdsc pcie_0_tunnel_gdsc = { .name = "pcie_0_tunnel_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE, + .flags = VOTABLE | RETAIN_FF_ENABLE, }; static struct gdsc pcie_1_tunnel_gdsc = { @@ -6771,7 +6771,7 @@ static struct gdsc pcie_1_tunnel_gdsc = { .name = "pcie_1_tunnel_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE, + .flags = VOTABLE | RETAIN_FF_ENABLE, }; /* @@ -6786,7 +6786,7 @@ static struct gdsc pcie_2a_gdsc = { .name = "pcie_2a_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE | ALWAYS_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, }; static struct gdsc pcie_2b_gdsc = { @@ -6797,7 +6797,7 @@ static struct gdsc pcie_2b_gdsc = { .name = "pcie_2b_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE | ALWAYS_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, }; static struct gdsc pcie_3a_gdsc = { @@ -6808,7 +6808,7 @@ static struct gdsc pcie_3a_gdsc = { .name = "pcie_3a_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE | ALWAYS_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, }; static struct gdsc pcie_3b_gdsc = { @@ -6819,7 +6819,7 @@ static struct gdsc pcie_3b_gdsc = { .name = "pcie_3b_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE | ALWAYS_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, }; static struct gdsc pcie_4_gdsc = { @@ -6830,7 +6830,7 @@ static struct gdsc pcie_4_gdsc = { .name = "pcie_4_gdsc", }, .pwrsts = PWRSTS_OFF_ON, - .flags = VOTABLE | ALWAYS_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, }; static struct gdsc ufs_card_gdsc = { @@ -6839,6 +6839,7 @@ static struct gdsc ufs_card_gdsc = { .name = "ufs_card_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE, }; static struct gdsc ufs_phy_gdsc = { @@ -6847,6 +6848,7 @@ static struct gdsc ufs_phy_gdsc = { .name = "ufs_phy_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE, }; static struct gdsc usb30_mp_gdsc = { @@ -6855,6 +6857,7 @@ static struct gdsc usb30_mp_gdsc = { .name = "usb30_mp_gdsc", }, .pwrsts = PWRSTS_RET_ON, + .flags = RETAIN_FF_ENABLE, }; static struct gdsc usb30_prim_gdsc = { @@ -6863,6 +6866,7 @@ static struct gdsc usb30_prim_gdsc = { .name = "usb30_prim_gdsc", }, .pwrsts = PWRSTS_RET_ON, + .flags = RETAIN_FF_ENABLE, }; static struct gdsc usb30_sec_gdsc = { @@ -6871,6 +6875,7 @@ static struct gdsc usb30_sec_gdsc = { .name = "usb30_sec_gdsc", }, .pwrsts = PWRSTS_RET_ON, + .flags = RETAIN_FF_ENABLE, }; static struct gdsc emac_0_gdsc = { @@ -6879,6 +6884,7 @@ static struct gdsc emac_0_gdsc = { .name = "emac_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE, }; static struct gdsc emac_1_gdsc = { @@ -6887,6 +6893,7 @@ static struct gdsc emac_1_gdsc = { .name = "emac_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE, }; static struct clk_regmap *gcc_sc8280xp_clocks[] = { From 57fc62c506906a4a3b498b78f176c3a08b432b13 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jun 2023 19:48:07 +0200 Subject: [PATCH 1010/2093] dt-bindings: clock: qcom,gcc-sc8280xp: Add missing GDSCs [ Upstream commit 9eba4db02a88e7a810aabd70f7a6960f184f391f ] There are 10 more GDSCs that we've not been caring about, and by extension (and perhaps even more importantly), not putting to sleep. Add them. Fixes: a66a82f2a55e ("dt-bindings: clock: Add Qualcomm SC8280XP GCC bindings") Acked-by: Rob Herring Signed-off-by: Konrad Dybcio Acked-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230620-topic-sc8280_gccgdsc-v2-2-562c1428c10d@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- include/dt-bindings/clock/qcom,gcc-sc8280xp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h index 721105ea4fad..845491591784 100644 --- a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h +++ b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h @@ -494,5 +494,15 @@ #define USB30_SEC_GDSC 11 #define EMAC_0_GDSC 12 #define EMAC_1_GDSC 13 +#define USB4_1_GDSC 14 +#define USB4_GDSC 15 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC 16 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC 17 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF0_GDSC 18 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF1_GDSC 19 +#define HLOS1_VOTE_TURING_MMU_TBU0_GDSC 20 +#define HLOS1_VOTE_TURING_MMU_TBU1_GDSC 21 +#define HLOS1_VOTE_TURING_MMU_TBU2_GDSC 22 +#define HLOS1_VOTE_TURING_MMU_TBU3_GDSC 23 #endif From eb613f81d0342e6ee6ac58f1e538a929fbab18d4 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 26 Jun 2023 19:48:08 +0200 Subject: [PATCH 1011/2093] clk: qcom: gcc-sc8280xp: Add missing GDSCs [ Upstream commit 4712eb7ff85bd3dd09c6668b8de4080e02b3eea9 ] There are 10 more GDSCs that we've not been caring about, and by extension (and perhaps even more importantly), not putting to sleep. Add them. Fixes: d65d005f9a6c ("clk: qcom: add sc8280xp GCC driver") Signed-off-by: Konrad Dybcio Acked-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230620-topic-sc8280_gccgdsc-v2-3-562c1428c10d@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc8280xp.c | 100 ++++++++++++++++++++++++++++++++ 1 file changed, 100 insertions(+) diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index 43c518e5c986..57bbd609151c 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -6896,6 +6896,96 @@ static struct gdsc emac_1_gdsc = { .flags = RETAIN_FF_ENABLE, }; +static struct gdsc usb4_1_gdsc = { + .gdscr = 0xb8004, + .pd = { + .name = "usb4_1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE, +}; + +static struct gdsc usb4_gdsc = { + .gdscr = 0x2a004, + .pd = { + .name = "usb4_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = RETAIN_FF_ENABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { + .gdscr = 0x7d050, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = { + .gdscr = 0x7d058, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf0_gdsc = { + .gdscr = 0x7d054, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf1_gdsc = { + .gdscr = 0x7d06c, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_turing_mmu_tbu0_gdsc = { + .gdscr = 0x7d05c, + .pd = { + .name = "hlos1_vote_turing_mmu_tbu0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_turing_mmu_tbu1_gdsc = { + .gdscr = 0x7d060, + .pd = { + .name = "hlos1_vote_turing_mmu_tbu1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_turing_mmu_tbu2_gdsc = { + .gdscr = 0x7d0a0, + .pd = { + .name = "hlos1_vote_turing_mmu_tbu2_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_turing_mmu_tbu3_gdsc = { + .gdscr = 0x7d0a4, + .pd = { + .name = "hlos1_vote_turing_mmu_tbu3_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + static struct clk_regmap *gcc_sc8280xp_clocks[] = { [GCC_AGGRE_NOC_PCIE0_TUNNEL_AXI_CLK] = &gcc_aggre_noc_pcie0_tunnel_axi_clk.clkr, [GCC_AGGRE_NOC_PCIE1_TUNNEL_AXI_CLK] = &gcc_aggre_noc_pcie1_tunnel_axi_clk.clkr, @@ -7376,6 +7466,16 @@ static struct gdsc *gcc_sc8280xp_gdscs[] = { [USB30_SEC_GDSC] = &usb30_sec_gdsc, [EMAC_0_GDSC] = &emac_0_gdsc, [EMAC_1_GDSC] = &emac_1_gdsc, + [USB4_1_GDSC] = &usb4_1_gdsc, + [USB4_GDSC] = &usb4_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF0_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF1_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf1_gdsc, + [HLOS1_VOTE_TURING_MMU_TBU0_GDSC] = &hlos1_vote_turing_mmu_tbu0_gdsc, + [HLOS1_VOTE_TURING_MMU_TBU1_GDSC] = &hlos1_vote_turing_mmu_tbu1_gdsc, + [HLOS1_VOTE_TURING_MMU_TBU2_GDSC] = &hlos1_vote_turing_mmu_tbu2_gdsc, + [HLOS1_VOTE_TURING_MMU_TBU3_GDSC] = &hlos1_vote_turing_mmu_tbu3_gdsc, }; static const struct clk_rcg_dfs_data gcc_dfs_clocks[] = { From 7618133eda26e3a5d68f1d297d55e463072ffdcf Mon Sep 17 00:00:00 2001 From: Alibek Omarov Date: Wed, 14 Jun 2023 16:47:50 +0300 Subject: [PATCH 1012/2093] clk: rockchip: rk3568: Fix PLL rate setting for 78.75MHz [ Upstream commit dafebd0f9a4f56b10d7fbda0bff1f540d16a2ea4 ] PLL rate on RK356x is calculated through the simple formula: ((24000000 / _refdiv) * _fbdiv) / (_postdiv1 * _postdiv2) The PLL rate setting for 78.75MHz seems to be copied from 96MHz so this patch fixes it and configures it properly. Signed-off-by: Alibek Omarov Fixes: 842f4cb72639 ("clk: rockchip: Add more PLL rates for rk3568") Reviewed-by: Sascha Hauer Link: https://lore.kernel.org/r/20230614134750.1056293-1-a1ba.omarov@gmail.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- drivers/clk/rockchip/clk-rk3568.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c index f85902e2590c..2f54f630c8b6 100644 --- a/drivers/clk/rockchip/clk-rk3568.c +++ b/drivers/clk/rockchip/clk-rk3568.c @@ -81,7 +81,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = { RK3036_PLL_RATE(108000000, 2, 45, 5, 1, 1, 0), RK3036_PLL_RATE(100000000, 1, 150, 6, 6, 1, 0), RK3036_PLL_RATE(96000000, 1, 96, 6, 4, 1, 0), - RK3036_PLL_RATE(78750000, 1, 96, 6, 4, 1, 0), + RK3036_PLL_RATE(78750000, 4, 315, 6, 4, 1, 0), RK3036_PLL_RATE(74250000, 2, 99, 4, 4, 1, 0), { /* sentinel */ }, }; From c53d53006d7fd178866a0e2239e6dd73ba9e6d2e Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Sat, 11 Mar 2023 14:34:53 +0100 Subject: [PATCH 1013/2093] PCI: apple: Initialize pcie->nvecs before use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d8650c0c2aa2e413594e4cb0faafa9958c1d7782 ] The apple_pcie_setup_port() function computes ilog2(pcie->nvecs) to set up the number of MSIs available for each port. However, it's called before apple_msi_init(), which initializes pcie->nvecs. Luckily, pcie->nvecs is part of kzalloc()-ed structure and, as such, initialized as zero. ilog2(0) happens to be 0xffffffff which then simply configures more MSIs in hardware than we have. This doesn't break anything because we never hand out those vectors. Thus, swap the order of the two calls so that the correctly initialized value is then used. [kwilczynski: commit log] Link: https://lore.kernel.org/linux-pci/20230311133453.63246-1-sven@svenpeter.dev Fixes: 476c41ed4597 ("PCI: apple: Implement MSI support") Signed-off-by: Sven Peter Signed-off-by: Krzysztof Wilczyński Reviewed-by: Marc Zyngier Reviewed-by: Alyssa Rosenzweig Reviewed-by: Eric Curtin Signed-off-by: Sasha Levin --- drivers/pci/controller/pcie-apple.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index 66f37e403a09..2340dab6cd5b 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -783,6 +783,10 @@ static int apple_pcie_init(struct pci_config_window *cfg) cfg->priv = pcie; INIT_LIST_HEAD(&pcie->ports); + ret = apple_msi_init(pcie); + if (ret) + return ret; + for_each_child_of_node(dev->of_node, of_port) { ret = apple_pcie_setup_port(pcie, of_port); if (ret) { @@ -792,7 +796,7 @@ static int apple_pcie_init(struct pci_config_window *cfg) } } - return apple_msi_init(pcie); + return 0; } static int apple_pcie_probe(struct platform_device *pdev) From d96da888dcd7edbea54e0bad7d6b20d9138d7e86 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 27 Jun 2023 19:40:36 +0530 Subject: [PATCH 1014/2093] PCI: qcom-ep: Switch MHI bus master clock off during L1SS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b9cbc06049cb6b7a322d708c2098195fb9fdcc4c ] Currently, as part of the qcom_pcie_perst_deassert() function, instead of writing the updated value to clear PARF_MSTR_AXI_CLK_EN, the variable "val" is re-read. This must be fixed to ensure that the master clock supplied to the MHI bus is correctly gated during L1.1/L1.2 to save power. Thus, replace the line that re-reads "val" with a line that writes the updated value to the register to clear PARF_MSTR_AXI_CLK_EN. [kwilczynski: commit log] Fixes: c457ac029e44 ("PCI: qcom-ep: Gate Master AXI clock to MHI bus during L1SS") Link: https://lore.kernel.org/linux-pci/20230627141036.11600-1-manivannan.sadhasivam@linaro.org Reported-by: Krzysztof Wilczyński Signed-off-by: Manivannan Sadhasivam Signed-off-by: Krzysztof Wilczyński Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-qcom-ep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c index 6d0d1b759ca2..d4c566c1c872 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-ep.c +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -410,7 +410,7 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci) /* Gate Master AXI clock to MHI bus during L1SS */ val = readl_relaxed(pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); val &= ~PARF_MSTR_AXI_CLK_EN; - val = readl_relaxed(pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); + writel_relaxed(val, pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); dw_pcie_ep_init_notify(&pcie_ep->pci.ep); From 4a43285900cd4e686f7e9113876a3697b206f180 Mon Sep 17 00:00:00 2001 From: Minjie Du Date: Wed, 12 Jul 2023 18:22:46 +0800 Subject: [PATCH 1015/2093] drivers: clk: keystone: Fix parameter judgment in _of_pll_clk_init() [ Upstream commit a995c50db887ef97f3160775aef7d772635a6f6e ] The function clk_register_pll() may return NULL or an ERR_PTR. Don't treat an ERR_PTR as valid. Signed-off-by: Minjie Du Link: https://lore.kernel.org/r/20230712102246.10348-1-duminjie@vivo.com Fixes: b9e0d40c0d83 ("clk: keystone: add Keystone PLL clock driver") [sboyd@kernel.org: Reword commit text] Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/keystone/pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/keystone/pll.c b/drivers/clk/keystone/pll.c index d59a7621bb20..ee5c72369334 100644 --- a/drivers/clk/keystone/pll.c +++ b/drivers/clk/keystone/pll.c @@ -209,7 +209,7 @@ static void __init _of_pll_clk_init(struct device_node *node, bool pllctrl) } clk = clk_register_pll(NULL, node->name, parent_name, pll_data); - if (clk) { + if (!IS_ERR_OR_NULL(clk)) { of_clk_add_provider(node, of_clk_src_simple_get, clk); return; } From d96799ee3b78962c80e4b6653734f488f999ca09 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 26 Jul 2023 11:29:42 -0700 Subject: [PATCH 1016/2093] PCI/DOE: Fix destroy_work_on_stack() race [ Upstream commit e3a3a097eaebaf234a482b4d2f9f18fe989208c1 ] The following debug object splat was observed in testing: ODEBUG: free active (active state 0) object: 0000000097d23782 object type: work_struct hint: doe_statemachine_work+0x0/0x510 WARNING: CPU: 1 PID: 71 at lib/debugobjects.c:514 debug_print_object+0x7d/0xb0 ... Workqueue: pci 0000:36:00.0 DOE [1 doe_statemachine_work RIP: 0010:debug_print_object+0x7d/0xb0 ... Call Trace: ? debug_print_object+0x7d/0xb0 ? __pfx_doe_statemachine_work+0x10/0x10 debug_object_free.part.0+0x11b/0x150 doe_statemachine_work+0x45e/0x510 process_one_work+0x1d4/0x3c0 This occurs because destroy_work_on_stack() was called after signaling the completion in the calling thread. This creates a race between destroy_work_on_stack() and the task->work struct going out of scope in pci_doe(). Signal the work complete after destroying the work struct. This is safe because signal_task_complete() is the final thing the work item does and the workqueue code is careful not to access the work struct after. Fixes: abf04be0e707 ("PCI/DOE: Fix memory leak with CONFIG_DEBUG_OBJECTS=y") Link: https://lore.kernel.org/r/20230726-doe-fix-v1-1-af07e614d4dd@intel.com Signed-off-by: Ira Weiny Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Wunner Acked-by: Dan Williams Signed-off-by: Sasha Levin --- drivers/pci/doe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index e5e9b287b976..c1776f82b7fc 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -223,8 +223,8 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas static void signal_task_complete(struct pci_doe_task *task, int rv) { task->rv = rv; - task->complete(task); destroy_work_on_stack(&task->work); + task->complete(task); } static void signal_task_abort(struct pci_doe_task *task, int rv) From d1a5f22abab4488ab8818580571e0bdb7abc5e1c Mon Sep 17 00:00:00 2001 From: Zhang Jianhua Date: Sat, 22 Jul 2023 15:31:07 +0000 Subject: [PATCH 1017/2093] clk: sunxi-ng: Modify mismatched function name [ Upstream commit 075d9ca5b4e17f84fd1c744a405e69ec743be7f0 ] No functional modification involved. drivers/clk/sunxi-ng/ccu_mmc_timing.c:54: warning: expecting prototype for sunxi_ccu_set_mmc_timing_mode(). Prototype was for sunxi_ccu_get_mmc_timing_mode() instead Fixes: f6f64ed868d3 ("clk: sunxi-ng: Add interface to query or configure MMC timing modes.") Signed-off-by: Zhang Jianhua Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/20230722153107.2078179-1-chris.zjh@huawei.com Signed-off-by: Jernej Skrabec Signed-off-by: Sasha Levin --- drivers/clk/sunxi-ng/ccu_mmc_timing.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu_mmc_timing.c b/drivers/clk/sunxi-ng/ccu_mmc_timing.c index de33414fc5c2..c6a6ce98ca03 100644 --- a/drivers/clk/sunxi-ng/ccu_mmc_timing.c +++ b/drivers/clk/sunxi-ng/ccu_mmc_timing.c @@ -43,7 +43,7 @@ int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode) EXPORT_SYMBOL_GPL(sunxi_ccu_set_mmc_timing_mode); /** - * sunxi_ccu_set_mmc_timing_mode: Get the current MMC clock timing mode + * sunxi_ccu_get_mmc_timing_mode: Get the current MMC clock timing mode * @clk: clock to query * * Returns 0 if the clock is in old timing mode, > 0 if it is in From 8f43c4000cdf99e1063d53c412e2b6df3b37e4cf Mon Sep 17 00:00:00 2001 From: David Wronek Date: Sun, 23 Jul 2023 21:05:02 +0200 Subject: [PATCH 1018/2093] clk: qcom: gcc-sc7180: Fix up gcc_sdcc2_apps_clk_src [ Upstream commit fd0b5ba87ad5709f0fd3d2bc4b7870494a75f96a ] Set .flags = CLK_OPS_PARENT_ENABLE to fix "gcc_sdcc2_apps_clk_src: rcg didn't update its configuration" error. Fixes: 17269568f726 ("clk: qcom: Add Global Clock controller (GCC) driver for SC7180") Signed-off-by: David Wronek Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230723190725.1619193-2-davidwronek@gmail.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sc7180.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c index 2d3980251e78..5822db4f4f35 100644 --- a/drivers/clk/qcom/gcc-sc7180.c +++ b/drivers/clk/qcom/gcc-sc7180.c @@ -667,6 +667,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_5, .num_parents = ARRAY_SIZE(gcc_parent_data_5), + .flags = CLK_OPS_PARENT_ENABLE, .ops = &clk_rcg2_floor_ops, }, }; From d5fc7d681320c239e5116263cfc71fdbddbde9b9 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Tue, 25 Jul 2023 16:04:27 +0800 Subject: [PATCH 1019/2093] EDAC/igen6: Fix the issue of no error events [ Upstream commit ce53ad81ed36c24aff075f94474adecfabfcf239 ] Current igen6_edac checks for pending errors before the registration of the error handler. However, there is a possibility that the error occurs during the registration process, leading to unhandled pending errors and no future error events. This issue can be reproduced by repeatedly injecting errors during the loading of the igen6_edac. Fix this issue by moving the pending error handler after the registration of the error handler, ensuring that no pending errors are left unhandled. Fixes: 10590a9d4f23 ("EDAC/igen6: Add EDAC driver for Intel client SoCs using IBECC") Reported-by: Ee Wey Lim Tested-by: Ee Wey Lim Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://lore.kernel.org/r/20230725080427.23883-1-qiuxu.zhuo@intel.com Signed-off-by: Sasha Levin --- drivers/edac/igen6_edac.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index a07bbfd075d0..8ec70da8d84f 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -27,7 +27,7 @@ #include "edac_mc.h" #include "edac_module.h" -#define IGEN6_REVISION "v2.5" +#define IGEN6_REVISION "v2.5.1" #define EDAC_MOD_STR "igen6_edac" #define IGEN6_NMI_NAME "igen6_ibecc" @@ -1216,9 +1216,6 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&ecclog_work, ecclog_work_cb); init_irq_work(&ecclog_irq_work, ecclog_irq_work_cb); - /* Check if any pending errors before registering the NMI handler */ - ecclog_handler(); - rc = register_err_handler(); if (rc) goto fail3; @@ -1230,6 +1227,9 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto fail4; } + /* Check if any pending errors before/during the registration of the error handler */ + ecclog_handler(); + igen6_debug_setup(); return 0; fail4: From 772ca4bc1d0d21320ef2ecc0f9e4f90ea85a035d Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 1 Aug 2023 22:31:55 +0800 Subject: [PATCH 1020/2093] ext4: correct grp validation in ext4_mb_good_group [ Upstream commit a9ce5993a0f5c0887c8a1b4ffa3b8046fbcfdc93 ] Group corruption check will access memory of grp and will trigger kernel crash if grp is NULL. So do NULL check before corruption check. Fixes: 5354b2af3406 ("ext4: allow ext4_get_group_info() to fail") Signed-off-by: Kemeng Shi Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20230801143204.2284343-2-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 88ed64ebae3e..20d02cc0a17a 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2401,7 +2401,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp)) + if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; From e0f5698757ab786830a59a80dc8054b08c7cd400 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 1 Aug 2023 22:31:56 +0800 Subject: [PATCH 1021/2093] ext4: avoid potential data overflow in next_linear_group [ Upstream commit 60c672b7f2d1e5dd1774f2399b355c9314e709f8 ] ngroups is ext4_group_t (unsigned int) while next_linear_group treat it in int. If ngroups is bigger than max number described by int, it will be treat as a negative number. Then "return group + 1 >= ngroups ? 0 : group + 1;" may keep returning 0. Switch int to ext4_group_t in next_linear_group to fix the overflow. Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") Signed-off-by: Kemeng Shi Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20230801143204.2284343-3-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 20d02cc0a17a..016925b1a090 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -966,8 +966,9 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac) * Return next linear group for allocation. If linear traversal should not be * performed, this function just returns the same group */ -static int -next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) +static ext4_group_t +next_linear_group(struct ext4_allocation_context *ac, ext4_group_t group, + ext4_group_t ngroups) { if (!should_optimize_scan(ac)) goto inc_and_return; From cc16a50d5088e21ba84133b9183075fa8bfdea86 Mon Sep 17 00:00:00 2001 From: Patrick Whewell Date: Wed, 2 Aug 2023 14:04:00 -0700 Subject: [PATCH 1022/2093] clk: qcom: gcc-sm8250: Fix gcc_sdcc2_apps_clk_src [ Upstream commit 783cb693828ce487cf0bc6ad16cbcf2caae6f8d9 ] GPLL9 is not on by default, which causes a "gcc_sdcc2_apps_clk_src: rcg didn't update its configuration" error when booting. Set .flags = CLK_OPS_PARENT_ENABLE to fix the error. Fixes: 3e5770921a88 ("clk: qcom: gcc: Add global clock controller driver for SM8250") Reviewed-by: Konrad Dybcio Reviewed-by: Bryan O'Donoghue Signed-off-by: Patrick Whewell Reviewed-by: Vinod Koul Link: https://lore.kernel.org/r/20230802210359.408-1-patrick.whewell@sightlineapplications.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sm8250.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/qcom/gcc-sm8250.c b/drivers/clk/qcom/gcc-sm8250.c index a0ba37656b07..30bd56146107 100644 --- a/drivers/clk/qcom/gcc-sm8250.c +++ b/drivers/clk/qcom/gcc-sm8250.c @@ -721,6 +721,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_4, .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .flags = CLK_OPS_PARENT_ENABLE, .ops = &clk_rcg2_floor_ops, }, }; From fef33ca5e28c876ddeddd586d090fd872a06fca7 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Tue, 18 Jul 2023 06:55:29 -0700 Subject: [PATCH 1023/2093] kvm/vfio: Prepare for accepting vfio device fd [ Upstream commit 2f99073a722beef5f74f3b0f32bda227ba3df1e0 ] This renames kvm_vfio_group related helpers to prepare for accepting vfio device fd. No functional change is intended. Reviewed-by: Kevin Tian Reviewed-by: Eric Auger Reviewed-by: Jason Gunthorpe Tested-by: Terrence Xu Tested-by: Nicolin Chen Tested-by: Matthew Rosato Tested-by: Yanting Jiang Tested-by: Shameer Kolothum Tested-by: Zhenzhong Duan Signed-off-by: Yi Liu Link: https://lore.kernel.org/r/20230718135551.6592-5-yi.l.liu@intel.com Signed-off-by: Alex Williamson Stable-dep-of: 9e0f4f2918c2 ("kvm/vfio: ensure kvg instance stays around in kvm_vfio_group_add()") Signed-off-by: Sasha Levin --- virt/kvm/vfio.c | 115 ++++++++++++++++++++++++------------------------ 1 file changed, 58 insertions(+), 57 deletions(-) diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 9584eb57e0ed..af3d0cf06e4c 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -21,7 +21,7 @@ #include #endif -struct kvm_vfio_group { +struct kvm_vfio_file { struct list_head node; struct file *file; #ifdef CONFIG_SPAPR_TCE_IOMMU @@ -30,7 +30,7 @@ struct kvm_vfio_group { }; struct kvm_vfio { - struct list_head group_list; + struct list_head file_list; struct mutex lock; bool noncoherent; }; @@ -98,34 +98,35 @@ static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file) } static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm, - struct kvm_vfio_group *kvg) + struct kvm_vfio_file *kvf) { - if (WARN_ON_ONCE(!kvg->iommu_group)) + if (WARN_ON_ONCE(!kvf->iommu_group)) return; - kvm_spapr_tce_release_iommu_group(kvm, kvg->iommu_group); - iommu_group_put(kvg->iommu_group); - kvg->iommu_group = NULL; + kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group); + iommu_group_put(kvf->iommu_group); + kvf->iommu_group = NULL; } #endif /* - * Groups can use the same or different IOMMU domains. If the same then - * adding a new group may change the coherency of groups we've previously - * been told about. We don't want to care about any of that so we retest - * each group and bail as soon as we find one that's noncoherent. This - * means we only ever [un]register_noncoherent_dma once for the whole device. + * Groups/devices can use the same or different IOMMU domains. If the same + * then adding a new group/device may change the coherency of groups/devices + * we've previously been told about. We don't want to care about any of + * that so we retest each group/device and bail as soon as we find one that's + * noncoherent. This means we only ever [un]register_noncoherent_dma once + * for the whole device. */ static void kvm_vfio_update_coherency(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; bool noncoherent = false; - struct kvm_vfio_group *kvg; + struct kvm_vfio_file *kvf; mutex_lock(&kv->lock); - list_for_each_entry(kvg, &kv->group_list, node) { - if (!kvm_vfio_file_enforced_coherent(kvg->file)) { + list_for_each_entry(kvf, &kv->file_list, node) { + if (!kvm_vfio_file_enforced_coherent(kvf->file)) { noncoherent = true; break; } @@ -143,10 +144,10 @@ static void kvm_vfio_update_coherency(struct kvm_device *dev) mutex_unlock(&kv->lock); } -static int kvm_vfio_group_add(struct kvm_device *dev, unsigned int fd) +static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; - struct kvm_vfio_group *kvg; + struct kvm_vfio_file *kvf; struct file *filp; int ret; @@ -162,27 +163,27 @@ static int kvm_vfio_group_add(struct kvm_device *dev, unsigned int fd) mutex_lock(&kv->lock); - list_for_each_entry(kvg, &kv->group_list, node) { - if (kvg->file == filp) { + list_for_each_entry(kvf, &kv->file_list, node) { + if (kvf->file == filp) { ret = -EEXIST; goto err_unlock; } } - kvg = kzalloc(sizeof(*kvg), GFP_KERNEL_ACCOUNT); - if (!kvg) { + kvf = kzalloc(sizeof(*kvf), GFP_KERNEL_ACCOUNT); + if (!kvf) { ret = -ENOMEM; goto err_unlock; } - kvg->file = filp; - list_add_tail(&kvg->node, &kv->group_list); + kvf->file = filp; + list_add_tail(&kvf->node, &kv->file_list); kvm_arch_start_assignment(dev->kvm); mutex_unlock(&kv->lock); - kvm_vfio_file_set_kvm(kvg->file, dev->kvm); + kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); return 0; @@ -193,10 +194,10 @@ static int kvm_vfio_group_add(struct kvm_device *dev, unsigned int fd) return ret; } -static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd) +static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; - struct kvm_vfio_group *kvg; + struct kvm_vfio_file *kvf; struct fd f; int ret; @@ -208,18 +209,18 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd) mutex_lock(&kv->lock); - list_for_each_entry(kvg, &kv->group_list, node) { - if (kvg->file != f.file) + list_for_each_entry(kvf, &kv->file_list, node) { + if (kvf->file != f.file) continue; - list_del(&kvg->node); + list_del(&kvf->node); kvm_arch_end_assignment(dev->kvm); #ifdef CONFIG_SPAPR_TCE_IOMMU - kvm_spapr_tce_release_vfio_group(dev->kvm, kvg); + kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif - kvm_vfio_file_set_kvm(kvg->file, NULL); - fput(kvg->file); - kfree(kvg); + kvm_vfio_file_set_kvm(kvf->file, NULL); + fput(kvf->file); + kfree(kvf); ret = 0; break; } @@ -234,12 +235,12 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd) } #ifdef CONFIG_SPAPR_TCE_IOMMU -static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev, - void __user *arg) +static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, + void __user *arg) { struct kvm_vfio_spapr_tce param; struct kvm_vfio *kv = dev->private; - struct kvm_vfio_group *kvg; + struct kvm_vfio_file *kvf; struct fd f; int ret; @@ -254,20 +255,20 @@ static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev, mutex_lock(&kv->lock); - list_for_each_entry(kvg, &kv->group_list, node) { - if (kvg->file != f.file) + list_for_each_entry(kvf, &kv->file_list, node) { + if (kvf->file != f.file) continue; - if (!kvg->iommu_group) { - kvg->iommu_group = kvm_vfio_file_iommu_group(kvg->file); - if (WARN_ON_ONCE(!kvg->iommu_group)) { + if (!kvf->iommu_group) { + kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file); + if (WARN_ON_ONCE(!kvf->iommu_group)) { ret = -EIO; goto err_fdput; } } ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd, - kvg->iommu_group); + kvf->iommu_group); break; } @@ -278,8 +279,8 @@ static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev, } #endif -static int kvm_vfio_set_group(struct kvm_device *dev, long attr, - void __user *arg) +static int kvm_vfio_set_file(struct kvm_device *dev, long attr, + void __user *arg) { int32_t __user *argp = arg; int32_t fd; @@ -288,16 +289,16 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, case KVM_DEV_VFIO_GROUP_ADD: if (get_user(fd, argp)) return -EFAULT; - return kvm_vfio_group_add(dev, fd); + return kvm_vfio_file_add(dev, fd); case KVM_DEV_VFIO_GROUP_DEL: if (get_user(fd, argp)) return -EFAULT; - return kvm_vfio_group_del(dev, fd); + return kvm_vfio_file_del(dev, fd); #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: - return kvm_vfio_group_set_spapr_tce(dev, arg); + return kvm_vfio_file_set_spapr_tce(dev, arg); #endif } @@ -309,8 +310,8 @@ static int kvm_vfio_set_attr(struct kvm_device *dev, { switch (attr->group) { case KVM_DEV_VFIO_GROUP: - return kvm_vfio_set_group(dev, attr->attr, - u64_to_user_ptr(attr->addr)); + return kvm_vfio_set_file(dev, attr->attr, + u64_to_user_ptr(attr->addr)); } return -ENXIO; @@ -339,16 +340,16 @@ static int kvm_vfio_has_attr(struct kvm_device *dev, static void kvm_vfio_release(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; - struct kvm_vfio_group *kvg, *tmp; + struct kvm_vfio_file *kvf, *tmp; - list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) { + list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) { #ifdef CONFIG_SPAPR_TCE_IOMMU - kvm_spapr_tce_release_vfio_group(dev->kvm, kvg); + kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif - kvm_vfio_file_set_kvm(kvg->file, NULL); - fput(kvg->file); - list_del(&kvg->node); - kfree(kvg); + kvm_vfio_file_set_kvm(kvf->file, NULL); + fput(kvf->file); + list_del(&kvf->node); + kfree(kvf); kvm_arch_end_assignment(dev->kvm); } @@ -382,7 +383,7 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type) if (!kv) return -ENOMEM; - INIT_LIST_HEAD(&kv->group_list); + INIT_LIST_HEAD(&kv->file_list); mutex_init(&kv->lock); dev->private = kv; From a4ff4b54f38825a9cdbdd1d70d2341af99ff67e6 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 14 Jul 2023 15:45:32 -0700 Subject: [PATCH 1024/2093] kvm/vfio: ensure kvg instance stays around in kvm_vfio_group_add() [ Upstream commit 9e0f4f2918c2ff145d3dedee862d9919a6ed5812 ] kvm_vfio_group_add() creates kvg instance, links it to kv->group_list, and calls kvm_vfio_file_set_kvm() with kvg->file as an argument after dropping kv->lock. If we race group addition and deletion calls, kvg instance may get freed by the time we get around to calling kvm_vfio_file_set_kvm(). Previous iterations of the code did not reference kvg->file outside of the critical section, but used a temporary variable. Still, they had similar problem of the file reference being owned by kvg structure and potential for kvm_vfio_group_del() dropping it before kvm_vfio_group_add() had a chance to complete. Fix this by moving call to kvm_vfio_file_set_kvm() under the protection of kv->lock. We already call it while holding the same lock when vfio group is being deleted, so it should be safe here as well. Fixes: 2fc1bec15883 ("kvm: set/clear kvm to/from vfio_group when group add/delete") Reviewed-by: Alex Williamson Signed-off-by: Dmitry Torokhov Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20230714224538.404793-1-dmitry.torokhov@gmail.com Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- virt/kvm/vfio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index af3d0cf06e4c..365d30779768 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -180,10 +180,10 @@ static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) list_add_tail(&kvf->node, &kv->file_list); kvm_arch_start_assignment(dev->kvm); + kvm_vfio_file_set_kvm(kvf->file, dev->kvm); mutex_unlock(&kv->lock); - kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); return 0; From a1801d14a89110f0f2341afcbc4c726c703afbb3 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Fri, 28 Jul 2023 09:57:38 +0200 Subject: [PATCH 1025/2093] clk: qcom: reset: Use the correct type of sleep/delay based on length [ Upstream commit 181b66ee7cdd824797fc99b53bec29cf5630a04f ] Use the fsleep() helper that (based on the length of the delay, see: [1]) chooses the correct sleep/delay functions. [1] https://www.kernel.org/doc/Documentation/timers/timers-howto.txt Fixes: 2cb8a39b6781 ("clk: qcom: reset: Allow specifying custom reset delay") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230726-topic-qcom_reset-v3-1-5958facd5db2@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/reset.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index 0e914ec7aeae..e45e32804d2c 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -16,7 +16,8 @@ static int qcom_reset(struct reset_controller_dev *rcdev, unsigned long id) struct qcom_reset_controller *rst = to_qcom_reset_controller(rcdev); rcdev->ops->assert(rcdev, id); - udelay(rst->reset_map[id].udelay ?: 1); /* use 1 us as default */ + fsleep(rst->reset_map[id].udelay ?: 1); /* use 1 us as default */ + rcdev->ops->deassert(rcdev, id); return 0; } From 9daefd22756ee1f93fc9a9fadd631f5a645ffa7b Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Fri, 4 Aug 2023 16:09:30 +0200 Subject: [PATCH 1026/2093] clk: qcom: gcc-sm6350: Fix gcc_sdcc2_apps_clk_src [ Upstream commit df04d166d1f346dbf740bbea64a3bed3e7f14c8d ] GPLL7 is not on by default, which causes a "gcc_sdcc2_apps_clk_src: rcg didn't update its configuration" error when booting. Set .flags = CLK_OPS_PARENT_ENABLE to fix the error. Fixes: 131abae905df ("clk: qcom: Add SM6350 GCC driver") Signed-off-by: Luca Weiss Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230804-sm6350-sdcc2-v1-1-3d946927d37d@fairphone.com Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sm6350.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/qcom/gcc-sm6350.c b/drivers/clk/qcom/gcc-sm6350.c index 9b4e4bb05963..cf4a7b6e0b23 100644 --- a/drivers/clk/qcom/gcc-sm6350.c +++ b/drivers/clk/qcom/gcc-sm6350.c @@ -641,6 +641,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_8, .num_parents = ARRAY_SIZE(gcc_parent_data_8), + .flags = CLK_OPS_PARENT_ENABLE, .ops = &clk_rcg2_floor_ops, }, }; From f3229c9cb634aa3f7c300c4ec9e311f747fc371f Mon Sep 17 00:00:00 2001 From: Daire McNamara Date: Fri, 28 Jul 2023 14:13:55 +0100 Subject: [PATCH 1027/2093] PCI: microchip: Correct the DED and SEC interrupt bit offsets [ Upstream commit 6d473a5a26136edf55c435a1c433e52910e03926 ] The SEC and DED interrupt bits are laid out the wrong way round so the SEC interrupt handler attempts to mask, unmask, and clear the DED interrupt and vice versa. Correct the bit offsets so that each interrupt handler operates properly. Link: https://lore.kernel.org/r/20230728131401.1615724-2-daire.mcnamara@microchip.com Fixes: 6f15a9c9f941 ("PCI: microchip: Add Microchip PolarFire PCIe controller driver") Signed-off-by: Daire McNamara Signed-off-by: Lorenzo Pieralisi Reviewed-by: Conor Dooley Signed-off-by: Sasha Levin --- drivers/pci/controller/pcie-microchip-host.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/controller/pcie-microchip-host.c b/drivers/pci/controller/pcie-microchip-host.c index 7263d175b5ad..5ba101efd932 100644 --- a/drivers/pci/controller/pcie-microchip-host.c +++ b/drivers/pci/controller/pcie-microchip-host.c @@ -167,12 +167,12 @@ #define EVENT_PCIE_DLUP_EXIT 2 #define EVENT_SEC_TX_RAM_SEC_ERR 3 #define EVENT_SEC_RX_RAM_SEC_ERR 4 -#define EVENT_SEC_AXI2PCIE_RAM_SEC_ERR 5 -#define EVENT_SEC_PCIE2AXI_RAM_SEC_ERR 6 +#define EVENT_SEC_PCIE2AXI_RAM_SEC_ERR 5 +#define EVENT_SEC_AXI2PCIE_RAM_SEC_ERR 6 #define EVENT_DED_TX_RAM_DED_ERR 7 #define EVENT_DED_RX_RAM_DED_ERR 8 -#define EVENT_DED_AXI2PCIE_RAM_DED_ERR 9 -#define EVENT_DED_PCIE2AXI_RAM_DED_ERR 10 +#define EVENT_DED_PCIE2AXI_RAM_DED_ERR 9 +#define EVENT_DED_AXI2PCIE_RAM_DED_ERR 10 #define EVENT_LOCAL_DMA_END_ENGINE_0 11 #define EVENT_LOCAL_DMA_END_ENGINE_1 12 #define EVENT_LOCAL_DMA_ERROR_ENGINE_0 13 From 8562df72cff2d125ee3eff966bfeece782005422 Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Mon, 10 Apr 2023 20:34:11 +0800 Subject: [PATCH 1028/2093] PCI: Mark NVIDIA T4 GPUs to avoid bus reset [ Upstream commit d5af729dc2071273f14cbb94abbc60608142fd83 ] NVIDIA T4 GPUs do not work with SBR. This problem is found when the T4 card is direct attached to a Root Port only. Avoid bus reset by marking T4 GPUs PCI_DEV_FLAGS_NO_BUS_RESET. Fixes: 4c207e7121fa ("PCI: Mark some NVIDIA GPUs to avoid bus reset") Link: https://lore.kernel.org/r/2dcebea53a6eb9bd212ec6d8974af2e5e0333ef6.1681129861.git.wuzongyong@linux.alibaba.com Signed-off-by: Wu Zongyong Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 472fa2c8ebce..d6fe44a5270d 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3631,7 +3631,7 @@ static void quirk_no_bus_reset(struct pci_dev *dev) */ static void quirk_nvidia_no_bus_reset(struct pci_dev *dev) { - if ((dev->device & 0xffc0) == 0x2340) + if ((dev->device & 0xffc0) == 0x2340 || dev->device == 0x1eb8) quirk_no_bus_reset(dev); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, From 8a5e87f9e93c67e45b3abe12e81752edda2c0511 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 21 Jun 2023 13:04:09 +0300 Subject: [PATCH 1029/2093] pinctrl: mcp23s08: check return value of devm_kasprintf() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f941714a7c7698eadb59bc27d34d6d6f38982705 ] devm_kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: 0f04a81784fe ("pinctrl: mcp23s08: Split to three parts: core, I²C, SPI") Signed-off-by: Claudiu Beznea Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230621100409.1608395-1-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-mcp23s08_spi.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c index 9ae10318f6f3..ea059b9c5542 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c +++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c @@ -91,18 +91,28 @@ static int mcp23s08_spi_regmap_init(struct mcp23s08 *mcp, struct device *dev, mcp->reg_shift = 0; mcp->chip.ngpio = 8; mcp->chip.label = devm_kasprintf(dev, GFP_KERNEL, "mcp23s08.%d", addr); + if (!mcp->chip.label) + return -ENOMEM; config = &mcp23x08_regmap; name = devm_kasprintf(dev, GFP_KERNEL, "%d", addr); + if (!name) + return -ENOMEM; + break; case MCP_TYPE_S17: mcp->reg_shift = 1; mcp->chip.ngpio = 16; mcp->chip.label = devm_kasprintf(dev, GFP_KERNEL, "mcp23s17.%d", addr); + if (!mcp->chip.label) + return -ENOMEM; config = &mcp23x17_regmap; name = devm_kasprintf(dev, GFP_KERNEL, "%d", addr); + if (!name) + return -ENOMEM; + break; case MCP_TYPE_S18: From 3108f7c7888401c8afdae2605705fcb3f81ff631 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Mon, 26 Sep 2022 14:57:10 -0700 Subject: [PATCH 1030/2093] PCI: Allow drivers to request exclusive config regions [ Upstream commit 278294798ac9118412c9624a801d3f20f2279363 ] PCI config space access from user space has traditionally been unrestricted with writes being an understood risk for device operation. Unfortunately, device breakage or odd behavior from config writes lacks indicators that can leave driver writers confused when evaluating failures. This is especially true with the new PCIe Data Object Exchange (DOE) mailbox protocol where backdoor shenanigans from user space through things such as vendor defined protocols may affect device operation without complete breakage. A prior proposal restricted read and writes completely.[1] Greg and Bjorn pointed out that proposal is flawed for a couple of reasons. First, lspci should always be allowed and should not interfere with any device operation. Second, setpci is a valuable tool that is sometimes necessary and it should not be completely restricted.[2] Finally methods exist for full lock of device access if required. Even though access should not be restricted it would be nice for driver writers to be able to flag critical parts of the config space such that interference from user space can be detected. Introduce pci_request_config_region_exclusive() to mark exclusive config regions. Such regions trigger a warning and kernel taint if accessed via user space. Create pci_warn_once() to restrict the user from spamming the log. [1] https://lore.kernel.org/all/161663543465.1867664.5674061943008380442.stgit@dwillia2-desk3.amr.corp.intel.com/ [2] https://lore.kernel.org/all/YF8NGeGv9vYcMfTV@kroah.com/ Cc: Bjorn Helgaas Cc: Greg Kroah-Hartman Reviewed-by: Jonathan Cameron Suggested-by: Dan Williams Signed-off-by: Ira Weiny Acked-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20220926215711.2893286-2-ira.weiny@intel.com Signed-off-by: Dan Williams Stable-dep-of: 5e70d0acf082 ("PCI: Add locking to RMW PCI Express Capability Register accessors") Signed-off-by: Sasha Levin --- drivers/pci/pci-sysfs.c | 7 +++++++ drivers/pci/probe.c | 6 ++++++ include/linux/ioport.h | 2 ++ include/linux/pci.h | 17 +++++++++++++++++ kernel/resource.c | 13 ++++++++----- 5 files changed, 40 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index ba38fc47d35e..dd0d9d9bc509 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -756,6 +756,13 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj, if (ret) return ret; + if (resource_is_exclusive(&dev->driver_exclusive_resource, off, + count)) { + pci_warn_once(dev, "%s: Unexpected write to kernel-exclusive config offset %llx", + current->comm, off); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } + if (off > dev->cfg_size) return 0; if (off + count > dev->cfg_size) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 7170516298b0..e3a1dc6432bc 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2306,6 +2306,12 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) INIT_LIST_HEAD(&dev->bus_list); dev->dev.type = &pci_dev_type; dev->bus = pci_bus_get(bus); + dev->driver_exclusive_resource = (struct resource) { + .name = "PCI Exclusive", + .start = 0, + .end = -1, + }; + #ifdef CONFIG_PCI_MSI raw_spin_lock_init(&dev->msi_lock); #endif diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 27642ca15d93..4ae3c541ea6f 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -318,6 +318,8 @@ extern void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n); extern int iomem_map_sanity_check(resource_size_t addr, unsigned long size); extern bool iomem_is_exclusive(u64 addr); +extern bool resource_is_exclusive(struct resource *resource, u64 addr, + resource_size_t size); extern int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, diff --git a/include/linux/pci.h b/include/linux/pci.h index 9f617ffdb863..4ea8de6890be 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -409,6 +409,7 @@ struct pci_dev { */ unsigned int irq; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */ + struct resource driver_exclusive_resource; /* driver exclusive resource ranges */ bool match_driver; /* Skip attaching driver */ @@ -1408,6 +1409,21 @@ int pci_request_selected_regions(struct pci_dev *, int, const char *); int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *); void pci_release_selected_regions(struct pci_dev *, int); +static inline __must_check struct resource * +pci_request_config_region_exclusive(struct pci_dev *pdev, unsigned int offset, + unsigned int len, const char *name) +{ + return __request_region(&pdev->driver_exclusive_resource, offset, len, + name, IORESOURCE_EXCLUSIVE); +} + +static inline void pci_release_config_region(struct pci_dev *pdev, + unsigned int offset, + unsigned int len) +{ + __release_region(&pdev->driver_exclusive_resource, offset, len); +} + /* drivers/pci/bus.c */ void pci_add_resource(struct list_head *resources, struct resource *res); void pci_add_resource_offset(struct list_head *resources, struct resource *res, @@ -2487,6 +2503,7 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #define pci_crit(pdev, fmt, arg...) dev_crit(&(pdev)->dev, fmt, ##arg) #define pci_err(pdev, fmt, arg...) dev_err(&(pdev)->dev, fmt, ##arg) #define pci_warn(pdev, fmt, arg...) dev_warn(&(pdev)->dev, fmt, ##arg) +#define pci_warn_once(pdev, fmt, arg...) dev_warn_once(&(pdev)->dev, fmt, ##arg) #define pci_notice(pdev, fmt, arg...) dev_notice(&(pdev)->dev, fmt, ##arg) #define pci_info(pdev, fmt, arg...) dev_info(&(pdev)->dev, fmt, ##arg) #define pci_dbg(pdev, fmt, arg...) dev_dbg(&(pdev)->dev, fmt, ##arg) diff --git a/kernel/resource.c b/kernel/resource.c index 1aeeededdd4c..8f52f8800965 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1693,18 +1693,15 @@ static int strict_iomem_checks; * * Returns true if exclusive to the kernel, otherwise returns false. */ -bool iomem_is_exclusive(u64 addr) +bool resource_is_exclusive(struct resource *root, u64 addr, resource_size_t size) { const unsigned int exclusive_system_ram = IORESOURCE_SYSTEM_RAM | IORESOURCE_EXCLUSIVE; bool skip_children = false, err = false; - int size = PAGE_SIZE; struct resource *p; - addr = addr & PAGE_MASK; - read_lock(&resource_lock); - for_each_resource(&iomem_resource, p, skip_children) { + for_each_resource(root, p, skip_children) { if (p->start >= addr + size) break; if (p->end < addr) { @@ -1743,6 +1740,12 @@ bool iomem_is_exclusive(u64 addr) return err; } +bool iomem_is_exclusive(u64 addr) +{ + return resource_is_exclusive(&iomem_resource, addr & PAGE_MASK, + PAGE_SIZE); +} + struct resource_entry *resource_list_create_entry(struct resource *res, size_t extra_size) { From f2d7da8fafed03cf468cd399cec7d80fbe4bab11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:04:53 +0300 Subject: [PATCH 1031/2093] PCI: Add locking to RMW PCI Express Capability Register accessors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5e70d0acf0825f439079736080350371f8d6699a ] Many places in the kernel write the Link Control and Root Control PCI Express Capability Registers without proper concurrency control and this could result in losing the changes one of the writers intended to make. Add pcie_cap_lock spinlock into the struct pci_dev and use it to protect bit changes made in the RMW capability accessors. Protect only a selected set of registers by differentiating the RMW accessor internally to locked/unlocked variants using a wrapper which has the same signature as pcie_capability_clear_and_set_word(). As the Capability Register (pos) given to the wrapper is always a constant, the compiler should be able to simplify all the dead-code away. So far only the Link Control Register (ASPM, hotplug, link retraining, various drivers) and the Root Control Register (AER & PME) seem to require RMW locking. Suggested-by: Lukas Wunner Fixes: c7f486567c1d ("PCI PM: PCIe PME root port service driver") Fixes: f12eb72a268b ("PCI/ASPM: Use PCI Express Capability accessors") Fixes: 7d715a6c1ae5 ("PCI: add PCI Express ASPM support") Fixes: affa48de8417 ("staging/rdma/hfi1: Add support for enabling/disabling PCIe ASPM") Fixes: 849a9366cba9 ("misc: rtsx: Add support new chip rts5228 mmc: rtsx: Add support MMC_CAP2_NO_MMC") Fixes: 3d1e7aa80d1c ("misc: rtsx: Use pcie_capability_clear_and_set_word() for PCI_EXP_LNKCTL") Fixes: c0e5f4e73a71 ("misc: rtsx: Add support for RTS5261") Fixes: 3df4fce739e2 ("misc: rtsx: separate aspm mode into MODE_REG and MODE_CFG") Fixes: 121e9c6b5c4c ("misc: rtsx: modify and fix init_hw function") Fixes: 19f3bd548f27 ("mfd: rtsx: Remove LCTLR defination") Fixes: 773ccdfd9cc6 ("mfd: rtsx: Read vendor setting from config space") Fixes: 8275b77a1513 ("mfd: rts5249: Add support for RTS5250S power saving") Fixes: 5da4e04ae480 ("misc: rtsx: Add support for RTS5260") Fixes: 0f49bfbd0f2e ("tg3: Use PCI Express Capability accessors") Fixes: 5e7dfd0fb94a ("tg3: Prevent corruption at 10 / 100Mbps w CLKREQ") Fixes: b726e493e8dc ("r8169: sync existing 8168 device hardware start sequences with vendor driver") Fixes: e6de30d63eb1 ("r8169: more 8168dp support.") Fixes: 8a06127602de ("Bluetooth: hci_bcm4377: Add new driver for BCM4377 PCIe boards") Fixes: 6f461f6c7c96 ("e1000e: enable/disable ASPM L0s and L1 and ERT according to hardware errata") Fixes: 1eae4eb2a1c7 ("e1000e: Disable L1 ASPM power savings for 82573 mobile variants") Fixes: 8060e169e02f ("ath9k: Enable extended synch for AR9485 to fix L0s recovery issue") Fixes: 69ce674bfa69 ("ath9k: do btcoex ASPM disabling at initialization time") Fixes: f37f05503575 ("mt76: mt76x2e: disable pcie_aspm by default") Link: https://lore.kernel.org/r/20230717120503.15276-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Reviewed-by: "Rafael J. Wysocki" Signed-off-by: Sasha Levin --- drivers/pci/access.c | 20 +++++++++++++++++--- drivers/pci/probe.c | 1 + include/linux/pci.h | 34 ++++++++++++++++++++++++++++++++-- 3 files changed, 50 insertions(+), 5 deletions(-) diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 708c7529647f..3d20f9c51efe 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -491,8 +491,8 @@ int pcie_capability_write_dword(struct pci_dev *dev, int pos, u32 val) } EXPORT_SYMBOL(pcie_capability_write_dword); -int pcie_capability_clear_and_set_word(struct pci_dev *dev, int pos, - u16 clear, u16 set) +int pcie_capability_clear_and_set_word_unlocked(struct pci_dev *dev, int pos, + u16 clear, u16 set) { int ret; u16 val; @@ -506,7 +506,21 @@ int pcie_capability_clear_and_set_word(struct pci_dev *dev, int pos, return ret; } -EXPORT_SYMBOL(pcie_capability_clear_and_set_word); +EXPORT_SYMBOL(pcie_capability_clear_and_set_word_unlocked); + +int pcie_capability_clear_and_set_word_locked(struct pci_dev *dev, int pos, + u16 clear, u16 set) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&dev->pcie_cap_lock, flags); + ret = pcie_capability_clear_and_set_word_unlocked(dev, pos, clear, set); + spin_unlock_irqrestore(&dev->pcie_cap_lock, flags); + + return ret; +} +EXPORT_SYMBOL(pcie_capability_clear_and_set_word_locked); int pcie_capability_clear_and_set_dword(struct pci_dev *dev, int pos, u32 clear, u32 set) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index e3a1dc6432bc..843e4a58788e 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2312,6 +2312,7 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) .end = -1, }; + spin_lock_init(&dev->pcie_cap_lock); #ifdef CONFIG_PCI_MSI raw_spin_lock_init(&dev->msi_lock); #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 4ea8de6890be..eccaf1abea79 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -466,6 +466,7 @@ struct pci_dev { pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ + spinlock_t pcie_cap_lock; /* Protects RMW ops in capability accessors */ u32 saved_config_space[16]; /* Config space saved at suspend time */ struct hlist_head saved_cap_space; int rom_attr_enabled; /* Display of ROM attribute enabled? */ @@ -1209,11 +1210,40 @@ int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val); int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val); int pcie_capability_write_word(struct pci_dev *dev, int pos, u16 val); int pcie_capability_write_dword(struct pci_dev *dev, int pos, u32 val); -int pcie_capability_clear_and_set_word(struct pci_dev *dev, int pos, - u16 clear, u16 set); +int pcie_capability_clear_and_set_word_unlocked(struct pci_dev *dev, int pos, + u16 clear, u16 set); +int pcie_capability_clear_and_set_word_locked(struct pci_dev *dev, int pos, + u16 clear, u16 set); int pcie_capability_clear_and_set_dword(struct pci_dev *dev, int pos, u32 clear, u32 set); +/** + * pcie_capability_clear_and_set_word - RMW accessor for PCI Express Capability Registers + * @dev: PCI device structure of the PCI Express device + * @pos: PCI Express Capability Register + * @clear: Clear bitmask + * @set: Set bitmask + * + * Perform a Read-Modify-Write (RMW) operation using @clear and @set + * bitmasks on PCI Express Capability Register at @pos. Certain PCI Express + * Capability Registers are accessed concurrently in RMW fashion, hence + * require locking which is handled transparently to the caller. + */ +static inline int pcie_capability_clear_and_set_word(struct pci_dev *dev, + int pos, + u16 clear, u16 set) +{ + switch (pos) { + case PCI_EXP_LNKCTL: + case PCI_EXP_RTCTL: + return pcie_capability_clear_and_set_word_locked(dev, pos, + clear, set); + default: + return pcie_capability_clear_and_set_word_unlocked(dev, pos, + clear, set); + } +} + static inline int pcie_capability_set_word(struct pci_dev *dev, int pos, u16 set) { From 952da7c6e199664c794b2039d80e20c1e1977422 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:04:55 +0300 Subject: [PATCH 1032/2093] PCI: pciehp: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5f75f96c61039151c193775d776fde42477eace1 ] As hotplug is not the only driver touching LNKCTL, use the RMW capability accessor which handles concurrent changes correctly. Suggested-by: Lukas Wunner Fixes: 7f822999e12a ("PCI: pciehp: Add Disable/enable link functions") Link: https://lore.kernel.org/r/20230717120503.15276-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Acked-by: "Rafael J. Wysocki" Signed-off-by: Sasha Levin --- drivers/pci/hotplug/pciehp_hpc.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 112c8f401ac4..358f077284cb 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -332,17 +332,11 @@ int pciehp_check_link_status(struct controller *ctrl) static int __pciehp_link_set(struct controller *ctrl, bool enable) { struct pci_dev *pdev = ctrl_dev(ctrl); - u16 lnk_ctrl; - pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &lnk_ctrl); + pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_LD, + enable ? 0 : PCI_EXP_LNKCTL_LD); - if (enable) - lnk_ctrl &= ~PCI_EXP_LNKCTL_LD; - else - lnk_ctrl |= PCI_EXP_LNKCTL_LD; - - pcie_capability_write_word(pdev, PCI_EXP_LNKCTL, lnk_ctrl); - ctrl_dbg(ctrl, "%s: lnk_ctrl = %x\n", __func__, lnk_ctrl); return 0; } From 6c88c9d9c63045603acc8cc3790ee8ba5b978973 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:04:56 +0300 Subject: [PATCH 1033/2093] PCI/ASPM: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e09060b3b6b4661278ff8e1b7b81a37d5ea86eae ] Don't assume that the device is fully under the control of ASPM and use RMW capability accessors which do proper locking to avoid losing concurrent updates to the register values. If configuration fails in pcie_aspm_configure_common_clock(), the function attempts to restore the old PCI_EXP_LNKCTL_CCC settings. Store only the old PCI_EXP_LNKCTL_CCC bit for the relevant devices rather than the content of the whole LNKCTL registers. It aligns better with how pcie_lnkctl_clear_and_set() expects its parameter and makes the code more obvious to understand. Suggested-by: Lukas Wunner Fixes: 2a42d9dba784 ("PCIe: ASPM: Break out of endless loop waiting for PCI config bits to switch") Fixes: 7d715a6c1ae5 ("PCI: add PCI Express ASPM support") Link: https://lore.kernel.org/r/20230717120503.15276-5-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Acked-by: "Rafael J. Wysocki" Signed-off-by: Sasha Levin --- drivers/pci/pcie/aspm.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 07166a4ec27a..7e89cdbd446f 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -250,7 +250,7 @@ static int pcie_retrain_link(struct pcie_link_state *link) static void pcie_aspm_configure_common_clock(struct pcie_link_state *link) { int same_clock = 1; - u16 reg16, parent_reg, child_reg[8]; + u16 reg16, ccc, parent_old_ccc, child_old_ccc[8]; struct pci_dev *child, *parent = link->pdev; struct pci_bus *linkbus = parent->subordinate; /* @@ -272,6 +272,7 @@ static void pcie_aspm_configure_common_clock(struct pcie_link_state *link) /* Port might be already in common clock mode */ pcie_capability_read_word(parent, PCI_EXP_LNKCTL, ®16); + parent_old_ccc = reg16 & PCI_EXP_LNKCTL_CCC; if (same_clock && (reg16 & PCI_EXP_LNKCTL_CCC)) { bool consistent = true; @@ -288,34 +289,29 @@ static void pcie_aspm_configure_common_clock(struct pcie_link_state *link) pci_info(parent, "ASPM: current common clock configuration is inconsistent, reconfiguring\n"); } + ccc = same_clock ? PCI_EXP_LNKCTL_CCC : 0; /* Configure downstream component, all functions */ list_for_each_entry(child, &linkbus->devices, bus_list) { pcie_capability_read_word(child, PCI_EXP_LNKCTL, ®16); - child_reg[PCI_FUNC(child->devfn)] = reg16; - if (same_clock) - reg16 |= PCI_EXP_LNKCTL_CCC; - else - reg16 &= ~PCI_EXP_LNKCTL_CCC; - pcie_capability_write_word(child, PCI_EXP_LNKCTL, reg16); + child_old_ccc[PCI_FUNC(child->devfn)] = reg16 & PCI_EXP_LNKCTL_CCC; + pcie_capability_clear_and_set_word(child, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CCC, ccc); } /* Configure upstream component */ - pcie_capability_read_word(parent, PCI_EXP_LNKCTL, ®16); - parent_reg = reg16; - if (same_clock) - reg16 |= PCI_EXP_LNKCTL_CCC; - else - reg16 &= ~PCI_EXP_LNKCTL_CCC; - pcie_capability_write_word(parent, PCI_EXP_LNKCTL, reg16); + pcie_capability_clear_and_set_word(parent, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CCC, ccc); if (pcie_retrain_link(link)) { /* Training failed. Restore common clock configurations */ pci_err(parent, "ASPM: Could not configure common clock\n"); list_for_each_entry(child, &linkbus->devices, bus_list) - pcie_capability_write_word(child, PCI_EXP_LNKCTL, - child_reg[PCI_FUNC(child->devfn)]); - pcie_capability_write_word(parent, PCI_EXP_LNKCTL, parent_reg); + pcie_capability_clear_and_set_word(child, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CCC, + child_old_ccc[PCI_FUNC(child->devfn)]); + pcie_capability_clear_and_set_word(parent, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_CCC, parent_old_ccc); } } From 402e73f64597a971101479bcbe94353c3c54b577 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Fri, 11 Aug 2023 19:35:53 +0200 Subject: [PATCH 1034/2093] clk: qcom: gcc-sm8450: Use floor ops for SDCC RCGs [ Upstream commit a27ac3806b0a0e6954fb5967223b8635242e5b8f ] Use the floor ops to prevent warnings like this at suspend exit and boot: mmc0: Card appears overclocked; req 800000 Hz, actual 25000000 Hz Fixes: db0c944ee92b ("clk: qcom: Add clock driver for SM8450") Signed-off-by: Konrad Dybcio Reviewed-by: Vinod Koul Link: https://lore.kernel.org/r/20230811-topic-8450_clk-v1-1-88031478d548@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sm8450.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/gcc-sm8450.c b/drivers/clk/qcom/gcc-sm8450.c index 666efa5ff978..59c567e76d65 100644 --- a/drivers/clk/qcom/gcc-sm8450.c +++ b/drivers/clk/qcom/gcc-sm8450.c @@ -904,7 +904,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_7, .num_parents = ARRAY_SIZE(gcc_parent_data_7), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; @@ -926,7 +926,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; From e1139dea2c02ca80f350cd794fa169312a860a10 Mon Sep 17 00:00:00 2001 From: Ye Li Date: Sun, 25 Jun 2023 20:33:39 +0800 Subject: [PATCH 1035/2093] clk: imx: pllv4: Fix SPLL2 MULT range [ Upstream commit 3f0cdb945471f1abd1cf4d172190e9c489c5052a ] The SPLL2 on iMX8ULP is different with other frac PLLs, it can support VCO from 650Mhz to 1Ghz. According to RM, the MULT is using a range from 27 to 54, not some fixed values. If using current PLL implementation, some clock rate can't be supported. Fix the issue by adding new type for the SPLL2 and use MULT range to replace MULT table Fixes: 5f0601c47c33 ("clk: imx: Update the pllv4 to support imx8ulp") Reviewed-by: Peng Fan Reviewed-by: Jacky Bai Signed-off-by: Ye Li Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230625123340.4067536-1-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-pllv4.c | 44 +++++++++++++++++++++++++++++-------- drivers/clk/imx/clk.h | 1 + 2 files changed, 36 insertions(+), 9 deletions(-) diff --git a/drivers/clk/imx/clk-pllv4.c b/drivers/clk/imx/clk-pllv4.c index 6e7e34571fc8..9b136c951762 100644 --- a/drivers/clk/imx/clk-pllv4.c +++ b/drivers/clk/imx/clk-pllv4.c @@ -44,11 +44,15 @@ struct clk_pllv4 { u32 cfg_offset; u32 num_offset; u32 denom_offset; + bool use_mult_range; }; /* Valid PLL MULT Table */ static const int pllv4_mult_table[] = {33, 27, 22, 20, 17, 16}; +/* Valid PLL MULT range, (max, min) */ +static const int pllv4_mult_range[] = {54, 27}; + #define to_clk_pllv4(__hw) container_of(__hw, struct clk_pllv4, hw) #define LOCK_TIMEOUT_US USEC_PER_MSEC @@ -94,17 +98,30 @@ static unsigned long clk_pllv4_recalc_rate(struct clk_hw *hw, static long clk_pllv4_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) { + struct clk_pllv4 *pll = to_clk_pllv4(hw); unsigned long parent_rate = *prate; unsigned long round_rate, i; u32 mfn, mfd = DEFAULT_MFD; bool found = false; u64 temp64; + u32 mult; - for (i = 0; i < ARRAY_SIZE(pllv4_mult_table); i++) { - round_rate = parent_rate * pllv4_mult_table[i]; - if (rate >= round_rate) { + if (pll->use_mult_range) { + temp64 = (u64)rate; + do_div(temp64, parent_rate); + mult = temp64; + if (mult >= pllv4_mult_range[1] && + mult <= pllv4_mult_range[0]) { + round_rate = parent_rate * mult; found = true; - break; + } + } else { + for (i = 0; i < ARRAY_SIZE(pllv4_mult_table); i++) { + round_rate = parent_rate * pllv4_mult_table[i]; + if (rate >= round_rate) { + found = true; + break; + } } } @@ -138,14 +155,20 @@ static long clk_pllv4_round_rate(struct clk_hw *hw, unsigned long rate, return round_rate + (u32)temp64; } -static bool clk_pllv4_is_valid_mult(unsigned int mult) +static bool clk_pllv4_is_valid_mult(struct clk_pllv4 *pll, unsigned int mult) { int i; /* check if mult is in valid MULT table */ - for (i = 0; i < ARRAY_SIZE(pllv4_mult_table); i++) { - if (pllv4_mult_table[i] == mult) + if (pll->use_mult_range) { + if (mult >= pllv4_mult_range[1] && + mult <= pllv4_mult_range[0]) return true; + } else { + for (i = 0; i < ARRAY_SIZE(pllv4_mult_table); i++) { + if (pllv4_mult_table[i] == mult) + return true; + } } return false; @@ -160,7 +183,7 @@ static int clk_pllv4_set_rate(struct clk_hw *hw, unsigned long rate, mult = rate / parent_rate; - if (!clk_pllv4_is_valid_mult(mult)) + if (!clk_pllv4_is_valid_mult(pll, mult)) return -EINVAL; if (parent_rate <= MAX_MFD) @@ -227,10 +250,13 @@ struct clk_hw *imx_clk_hw_pllv4(enum imx_pllv4_type type, const char *name, pll->base = base; - if (type == IMX_PLLV4_IMX8ULP) { + if (type == IMX_PLLV4_IMX8ULP || + type == IMX_PLLV4_IMX8ULP_1GHZ) { pll->cfg_offset = IMX8ULP_PLL_CFG_OFFSET; pll->num_offset = IMX8ULP_PLL_NUM_OFFSET; pll->denom_offset = IMX8ULP_PLL_DENOM_OFFSET; + if (type == IMX_PLLV4_IMX8ULP_1GHZ) + pll->use_mult_range = true; } else { pll->cfg_offset = PLL_CFG_OFFSET; pll->num_offset = PLL_NUM_OFFSET; diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index dd49f90110e8..fb59131395f0 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -46,6 +46,7 @@ enum imx_pll14xx_type { enum imx_pllv4_type { IMX_PLLV4_IMX7ULP, IMX_PLLV4_IMX8ULP, + IMX_PLLV4_IMX8ULP_1GHZ, }; enum imx_pfdv2_type { From fcaf148b20f0eedb877f50ff6f922f42383e32ab Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 25 Jun 2023 20:33:40 +0800 Subject: [PATCH 1036/2093] clk: imx: imx8ulp: update SPLL2 type [ Upstream commit 7653a59be8af043adc4c09473975a860e6055ff9 ] The SPLL2 on iMX8ULP is different with other frac PLLs, it can support VCO from 650Mhz to 1Ghz. Following the changes to pllv4, use the new type IMX_PLLV4_IMX8ULP_1GHZ. Fixes: c43a801a5789 ("clk: imx: Add clock driver for imx8ulp") Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230625123340.4067536-2-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8ulp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8ulp.c b/drivers/clk/imx/clk-imx8ulp.c index ca0e4a3aa454..fa9121b3cf36 100644 --- a/drivers/clk/imx/clk-imx8ulp.c +++ b/drivers/clk/imx/clk-imx8ulp.c @@ -167,7 +167,7 @@ static int imx8ulp_clk_cgc1_init(struct platform_device *pdev) clks[IMX8ULP_CLK_SPLL2_PRE_SEL] = imx_clk_hw_mux_flags("spll2_pre_sel", base + 0x510, 0, 1, pll_pre_sels, ARRAY_SIZE(pll_pre_sels), CLK_SET_PARENT_GATE); clks[IMX8ULP_CLK_SPLL3_PRE_SEL] = imx_clk_hw_mux_flags("spll3_pre_sel", base + 0x610, 0, 1, pll_pre_sels, ARRAY_SIZE(pll_pre_sels), CLK_SET_PARENT_GATE); - clks[IMX8ULP_CLK_SPLL2] = imx_clk_hw_pllv4(IMX_PLLV4_IMX8ULP, "spll2", "spll2_pre_sel", base + 0x500); + clks[IMX8ULP_CLK_SPLL2] = imx_clk_hw_pllv4(IMX_PLLV4_IMX8ULP_1GHZ, "spll2", "spll2_pre_sel", base + 0x500); clks[IMX8ULP_CLK_SPLL3] = imx_clk_hw_pllv4(IMX_PLLV4_IMX8ULP, "spll3", "spll3_pre_sel", base + 0x600); clks[IMX8ULP_CLK_SPLL3_VCODIV] = imx_clk_hw_divider("spll3_vcodiv", "spll3", base + 0x604, 0, 6); From cc7e04d7ff9252d9be9cfd314e1f5c3ae631255f Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Mon, 31 Jul 2023 16:21:49 +0200 Subject: [PATCH 1037/2093] clk: imx8mp: fix sai4 clock [ Upstream commit c30f600f1f41dcf5ef0fb02e9a201f9b2e8f31bd ] The reference manual don't mention a SAI4 hardware block. This would be clock slice 78 which is skipped (TRM, page 237). Remove any reference to this clock to align the driver with the reality. Fixes: 9c140d992676 ("clk: imx: Add support for i.MX8MP clock driver") Acked-by: Stephen Boyd Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20230731142150.3186650-1-m.felsch@pengutronix.de Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mp.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 05c02f4e2a14..3d0d8f2c02dc 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -177,10 +177,6 @@ static const char * const imx8mp_sai3_sels[] = {"osc_24m", "audio_pll1_out", "au "video_pll1_out", "sys_pll1_133m", "osc_hdmi", "clk_ext3", "clk_ext4", }; -static const char * const imx8mp_sai4_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", - "clk_ext1", "clk_ext2", }; - static const char * const imx8mp_sai5_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", "video_pll1_out", "sys_pll1_133m", "osc_hdmi", "clk_ext2", "clk_ext3", }; @@ -566,7 +562,6 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_SAI1] = imx8m_clk_hw_composite("sai1", imx8mp_sai1_sels, ccm_base + 0xa580); hws[IMX8MP_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mp_sai2_sels, ccm_base + 0xa600); hws[IMX8MP_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mp_sai3_sels, ccm_base + 0xa680); - hws[IMX8MP_CLK_SAI4] = imx8m_clk_hw_composite("sai4", imx8mp_sai4_sels, ccm_base + 0xa700); hws[IMX8MP_CLK_SAI5] = imx8m_clk_hw_composite("sai5", imx8mp_sai5_sels, ccm_base + 0xa780); hws[IMX8MP_CLK_SAI6] = imx8m_clk_hw_composite("sai6", imx8mp_sai6_sels, ccm_base + 0xa800); hws[IMX8MP_CLK_ENET_QOS] = imx8m_clk_hw_composite("enet_qos", imx8mp_enet_qos_sels, ccm_base + 0xa880); From dd9241fc4b19ce18c8babb9e7b7dd3b590a281e3 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Mon, 7 Aug 2023 10:22:00 +0200 Subject: [PATCH 1038/2093] clk: imx: composite-8m: fix clock pauses when set_rate would be a no-op [ Upstream commit 4dd432d985ef258e3bc436e568fba4b987b59171 ] Reconfiguring the clock divider to the exact same value is observed on an i.MX8MN to often cause a longer than usual clock pause, probably because the divider restarts counting whenever the register is rewritten. This issue doesn't show up normally, because the clock framework will take care to not call set_rate when the clock rate is the same. However, when we reconfigure an upstream clock, the common code will call set_rate with the newly calculated rate on all children, e.g.: - sai5 is running normally and divides Audio PLL out by 16. - Audio PLL rate is increased by 32Hz (glitch-free kdiv change) - rates for children are recalculated and rates are set recursively - imx8m_clk_composite_divider_set_rate(sai5) is called with 32/16 = 2Hz more - imx8m_clk_composite_divider_set_rate computes same divider as before - divider register is written, so it restarts counting from zero and MCLK is briefly paused, so instead of e.g. 40ns, MCLK is low for 120ns. Some external clock consumers can be upset by such unexpected clock pauses, so let's make sure we only rewrite the divider value when the value to be written is actually different. Fixes: d3ff9728134e ("clk: imx: Add imx composite clock") Signed-off-by: Ahmad Fatoum Reviewed-by: Peng Fan Link: https://lore.kernel.org/r/20230807082201.2332746-1-a.fatoum@pengutronix.de Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-composite-8m.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index cbf0d7955a00..3e9a092e136c 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -97,7 +97,7 @@ static int imx8m_clk_composite_divider_set_rate(struct clk_hw *hw, int prediv_value; int div_value; int ret; - u32 val; + u32 orig, val; ret = imx8m_clk_composite_compute_dividers(rate, parent_rate, &prediv_value, &div_value); @@ -106,13 +106,15 @@ static int imx8m_clk_composite_divider_set_rate(struct clk_hw *hw, spin_lock_irqsave(divider->lock, flags); - val = readl(divider->reg); - val &= ~((clk_div_mask(divider->width) << divider->shift) | - (clk_div_mask(PCG_DIV_WIDTH) << PCG_DIV_SHIFT)); + orig = readl(divider->reg); + val = orig & ~((clk_div_mask(divider->width) << divider->shift) | + (clk_div_mask(PCG_DIV_WIDTH) << PCG_DIV_SHIFT)); val |= (u32)(prediv_value - 1) << divider->shift; val |= (u32)(div_value - 1) << PCG_DIV_SHIFT; - writel(val, divider->reg); + + if (val != orig) + writel(val, divider->reg); spin_unlock_irqrestore(divider->lock, flags); From aae5a866d3971753f6a7131d7d1313dc13511f8c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 9 Aug 2023 10:01:43 +0200 Subject: [PATCH 1039/2093] powerpc/radix: Move some functions into #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE [ Upstream commit 4a9dd8f292efd614f0a18452e6474fe19ae17b47 ] With skiboot_defconfig, Clang reports: CC arch/powerpc/mm/book3s64/radix_tlb.o arch/powerpc/mm/book3s64/radix_tlb.c:419:20: error: unused function '_tlbie_pid_lpid' [-Werror,-Wunused-function] static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, ^ arch/powerpc/mm/book3s64/radix_tlb.c:663:20: error: unused function '_tlbie_va_range_lpid' [-Werror,-Wunused-function] static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, ^ This is because those functions are only called from functions enclosed in a #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE Move below functions inside that #ifdef * __tlbie_pid_lpid(unsigned long pid, * __tlbie_va_lpid(unsigned long va, unsigned long pid, * fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) * _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, * fixup_tlbie_va_range_lpid(unsigned long va, * __tlbie_va_range_lpid(unsigned long start, unsigned long end, * _tlbie_va_range_lpid(unsigned long start, unsigned long end, Fixes: f0c6fbbb9050 ("KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202307260802.Mjr99P5O-lkp@intel.com/ Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/3d72efd39f986ee939d068af69fdce28bd600766.1691568093.git.christophe.leroy@csgroup.eu Signed-off-by: Sasha Levin --- arch/powerpc/mm/book3s64/radix_tlb.c | 240 ++++++++++++++------------- 1 file changed, 121 insertions(+), 119 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 6d7a1ef723e6..a8ba04dcb20f 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -127,21 +127,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric) trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbie_pid_lpid(unsigned long pid, - unsigned long lpid, - unsigned long ric) -{ - unsigned long rb, rs, prs, r; - - rb = PPC_BIT(53); /* IS = 1 */ - rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); - prs = 1; /* process scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); -} static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -202,23 +187,6 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, - unsigned long lpid, - unsigned long ap, unsigned long ric) -{ - unsigned long rb, rs, prs, r; - - rb = va & ~(PPC_BITMASK(52, 63)); - rb |= ap << PPC_BITLSHIFT(58); - rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); - prs = 1; /* process scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); -} - static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap, unsigned long ric) { @@ -264,22 +232,6 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid, } } -static inline void fixup_tlbie_va_range_lpid(unsigned long va, - unsigned long pid, - unsigned long lpid, - unsigned long ap) -{ - if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); - } - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); - } -} - static inline void fixup_tlbie_pid(unsigned long pid) { /* @@ -299,26 +251,6 @@ static inline void fixup_tlbie_pid(unsigned long pid) } } -static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) -{ - /* - * We can use any address for the invalidation, pick one which is - * probably unused as an optimisation. - */ - unsigned long va = ((1UL << 52) - 1); - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); - } - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), - RIC_FLUSH_TLB); - } -} - static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap) { @@ -416,31 +348,6 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, - unsigned long ric) -{ - asm volatile("ptesync" : : : "memory"); - - /* - * Workaround the fact that the "ric" argument to __tlbie_pid - * must be a compile-time contraint to match the "i" constraint - * in the asm statement. - */ - switch (ric) { - case RIC_FLUSH_TLB: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); - fixup_tlbie_pid_lpid(pid, lpid); - break; - case RIC_FLUSH_PWC: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - break; - case RIC_FLUSH_ALL: - default: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); - fixup_tlbie_pid_lpid(pid, lpid); - } - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} struct tlbiel_pid { unsigned long pid; unsigned long ric; @@ -566,20 +473,6 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end, fixup_tlbie_va_range(addr - page_size, pid, ap); } -static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, - unsigned long pid, unsigned long lpid, - unsigned long page_size, - unsigned long psize) -{ - unsigned long addr; - unsigned long ap = mmu_get_ap(psize); - - for (addr = start; addr < end; addr += page_size) - __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); - - fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); -} - static __always_inline void _tlbie_va(unsigned long va, unsigned long pid, unsigned long psize, unsigned long ric) { @@ -660,18 +553,6 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, - unsigned long pid, unsigned long lpid, - unsigned long page_size, - unsigned long psize, bool also_pwc) -{ - asm volatile("ptesync" : : : "memory"); - if (also_pwc) - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} - static inline void _tlbiel_va_range_multicast(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, @@ -1476,6 +1357,127 @@ void radix__flush_tlb_all(void) } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +static __always_inline void __tlbie_pid_lpid(unsigned long pid, + unsigned long lpid, + unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = PPC_BIT(53); /* IS = 1 */ + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, + unsigned long lpid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), + RIC_FLUSH_TLB); + } +} + +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, + unsigned long ric) +{ + asm volatile("ptesync" : : : "memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); + fixup_tlbie_pid_lpid(pid, lpid); + break; + case RIC_FLUSH_PWC: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); + fixup_tlbie_pid_lpid(pid, lpid); + } + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + +static inline void fixup_tlbie_va_range_lpid(unsigned long va, + unsigned long pid, + unsigned long lpid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); + } +} + +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize) +{ + unsigned long addr; + unsigned long ap = mmu_get_ap(psize); + + for (addr = start; addr < end; addr += page_size) + __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); + + fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); +} + +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + asm volatile("ptesync" : : : "memory"); + if (also_pwc) + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + /* * Performs process-scoped invalidations for a given LPID * as part of H_RPT_INVALIDATE hcall. From f6f300ecc196d243c02adeb9ee0c62c677c24bfb Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Tue, 1 Aug 2023 11:53:52 -0400 Subject: [PATCH 1040/2093] vfio/type1: fix cap_migration information leak [ Upstream commit cd24e2a60af633f157d7e59c0a6dba64f131c0b1 ] Fix an information leak where an uninitialized hole in struct vfio_iommu_type1_info_cap_migration on the stack is exposed to userspace. The definition of struct vfio_iommu_type1_info_cap_migration contains a hole as shown in this pahole(1) output: struct vfio_iommu_type1_info_cap_migration { struct vfio_info_cap_header header; /* 0 8 */ __u32 flags; /* 8 4 */ /* XXX 4 bytes hole, try to pack */ __u64 pgsize_bitmap; /* 16 8 */ __u64 max_dirty_bitmap_size; /* 24 8 */ /* size: 32, cachelines: 1, members: 4 */ /* sum members: 28, holes: 1, sum holes: 4 */ /* last cacheline: 32 bytes */ }; The cap_mig variable is filled in without initializing the hole: static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu, struct vfio_info_cap *caps) { struct vfio_iommu_type1_info_cap_migration cap_mig; cap_mig.header.id = VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION; cap_mig.header.version = 1; cap_mig.flags = 0; /* support minimum pgsize */ cap_mig.pgsize_bitmap = (size_t)1 << __ffs(iommu->pgsize_bitmap); cap_mig.max_dirty_bitmap_size = DIRTY_BITMAP_SIZE_MAX; return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig)); } The structure is then copied to a temporary location on the heap. At this point it's already too late and ioctl(VFIO_IOMMU_GET_INFO) copies it to userspace later: int vfio_info_add_capability(struct vfio_info_cap *caps, struct vfio_info_cap_header *cap, size_t size) { struct vfio_info_cap_header *header; header = vfio_info_cap_add(caps, size, cap->id, cap->version); if (IS_ERR(header)) return PTR_ERR(header); memcpy(header + 1, cap + 1, size - sizeof(*header)); return 0; } This issue was found by code inspection. Signed-off-by: Stefan Hajnoczi Reviewed-by: Kevin Tian Fixes: ad721705d09c ("vfio iommu: Add migration capability to report supported features") Link: https://lore.kernel.org/r/20230801155352.1391945-1-stefanha@redhat.com Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/vfio_iommu_type1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 009ba186652a..18a2dbbc7779 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -2822,7 +2822,7 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu, static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu, struct vfio_info_cap *caps) { - struct vfio_iommu_type1_info_cap_migration cap_mig; + struct vfio_iommu_type1_info_cap_migration cap_mig = {}; cap_mig.header.id = VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION; cap_mig.header.version = 1; From 500a6ff9c2a81348fe0f04e2deb758145e8ab94e Mon Sep 17 00:00:00 2001 From: Konstantin Meskhidze Date: Thu, 17 Aug 2023 19:59:45 +0800 Subject: [PATCH 1041/2093] nvdimm: Fix memleak of pmu attr_groups in unregister_nvdimm_pmu() [ Upstream commit 85ae42c72142346645e63c33835da947dfa008b3 ] Memory pointed by 'nd_pmu->pmu.attr_groups' is allocated in function 'register_nvdimm_pmu' and is lost after 'kfree(nd_pmu)' call in function 'unregister_nvdimm_pmu'. Fixes: 0fab1ba6ad6b ("drivers/nvdimm: Add perf interface to expose nvdimm performance stats") Co-developed-by: Ivanov Mikhail Signed-off-by: Konstantin Meskhidze Reviewed-by: Jeff Moyer Link: https://lore.kernel.org/r/20230817115945.771826-1-konstantin.meskhidze@huawei.com Signed-off-by: Dave Jiang Signed-off-by: Sasha Levin --- drivers/nvdimm/nd_perf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvdimm/nd_perf.c b/drivers/nvdimm/nd_perf.c index 433bbb68ae64..14881c4e03e6 100644 --- a/drivers/nvdimm/nd_perf.c +++ b/drivers/nvdimm/nd_perf.c @@ -324,6 +324,7 @@ void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) { perf_pmu_unregister(&nd_pmu->pmu); nvdimm_pmu_free_hotplug_memory(nd_pmu); + kfree(nd_pmu->pmu.attr_groups); kfree(nd_pmu); } EXPORT_SYMBOL_GPL(unregister_nvdimm_pmu); From ab8094db59e18d4664e38c4d91ea070c4c01c451 Mon Sep 17 00:00:00 2001 From: Konstantin Meskhidze Date: Thu, 17 Aug 2023 19:41:03 +0800 Subject: [PATCH 1042/2093] nvdimm: Fix dereference after free in register_nvdimm_pmu() [ Upstream commit 08ca6906a4b7e48f8e93b7c1f49a742a415be6d5 ] 'nd_pmu->pmu.attr_groups' is dereferenced in function 'nvdimm_pmu_free_hotplug_memory' call after it has been freed. Because in function 'nvdimm_pmu_free_hotplug_memory' memory pointed by the fields of 'nd_pmu->pmu.attr_groups' is deallocated it is necessary to call 'kfree' after 'nvdimm_pmu_free_hotplug_memory'. Fixes: 0fab1ba6ad6b ("drivers/nvdimm: Add perf interface to expose nvdimm performance stats") Co-developed-by: Ivanov Mikhail Signed-off-by: Konstantin Meskhidze Reviewed-by: Jeff Moyer Link: https://lore.kernel.org/r/20230817114103.754977-1-konstantin.meskhidze@huawei.com Signed-off-by: Dave Jiang Signed-off-by: Sasha Levin --- drivers/nvdimm/nd_perf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/nd_perf.c b/drivers/nvdimm/nd_perf.c index 14881c4e03e6..2b6dc80d8fb5 100644 --- a/drivers/nvdimm/nd_perf.c +++ b/drivers/nvdimm/nd_perf.c @@ -308,8 +308,8 @@ int register_nvdimm_pmu(struct nvdimm_pmu *nd_pmu, struct platform_device *pdev) rc = perf_pmu_register(&nd_pmu->pmu, nd_pmu->pmu.name, -1); if (rc) { - kfree(nd_pmu->pmu.attr_groups); nvdimm_pmu_free_hotplug_memory(nd_pmu); + kfree(nd_pmu->pmu.attr_groups); return rc; } From 1d58a924698923fee197820ce6030ac250548fd5 Mon Sep 17 00:00:00 2001 From: Sourabh Jain Date: Tue, 4 Jul 2023 10:37:15 +0530 Subject: [PATCH 1043/2093] powerpc/fadump: reset dump area size if fadump memory reserve fails [ Upstream commit d1eb75e0dfed80d2d85b664e28a39f65b290ab55 ] In case fadump_reserve_mem() fails to reserve memory, the reserve_dump_area_size variable will retain the reserve area size. This will lead to /sys/kernel/fadump/mem_reserved node displaying an incorrect memory reserved by fadump. To fix this problem, reserve dump area size variable is set to 0 if fadump failed to reserve memory. Fixes: 8255da95e545 ("powerpc/fadump: release all the memory above boot memory size") Signed-off-by: Sourabh Jain Acked-by: Mahesh Salgaonkar Signed-off-by: Michael Ellerman Link: https://msgid.link/20230704050715.203581-1-sourabhjain@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/fadump.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index ea0a073abd96..3ff2da7b120b 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -654,6 +654,7 @@ int __init fadump_reserve_mem(void) return ret; error_out: fw_dump.fadump_enabled = 0; + fw_dump.reserve_dump_area_size = 0; return 0; } From ed6483fac4281408d6252476ff59589fa5dd1b05 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 18 Aug 2023 10:59:44 +0200 Subject: [PATCH 1044/2093] powerpc/perf: Convert fsl_emb notifier to state machine callbacks [ Upstream commit 34daf445f82bd3a4df852bb5f1dffd792ac830a0 ] CC arch/powerpc/perf/core-fsl-emb.o arch/powerpc/perf/core-fsl-emb.c:675:6: error: no previous prototype for 'hw_perf_event_setup' [-Werror=missing-prototypes] 675 | void hw_perf_event_setup(int cpu) | ^~~~~~~~~~~~~~~~~~~ Looks like fsl_emb was completely missed by commit 3f6da3905398 ("perf: Rework and fix the arch CPU-hotplug hooks") So, apply same changes as commit 3f6da3905398 ("perf: Rework and fix the arch CPU-hotplug hooks") then commit 57ecde42cc74 ("powerpc/perf: Convert book3s notifier to state machine callbacks") While at it, also fix following error: arch/powerpc/perf/core-fsl-emb.c: In function 'perf_event_interrupt': arch/powerpc/perf/core-fsl-emb.c:648:13: error: variable 'found' set but not used [-Werror=unused-but-set-variable] 648 | int found = 0; | ^~~~~ Fixes: 3f6da3905398 ("perf: Rework and fix the arch CPU-hotplug hooks") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/603e1facb32608f88f40b7d7b9094adc50e7b2dc.1692349125.git.christophe.leroy@csgroup.eu Signed-off-by: Sasha Levin --- arch/powerpc/perf/core-fsl-emb.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c index ee721f420a7b..1a53ab08447c 100644 --- a/arch/powerpc/perf/core-fsl-emb.c +++ b/arch/powerpc/perf/core-fsl-emb.c @@ -645,7 +645,6 @@ static void perf_event_interrupt(struct pt_regs *regs) struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; unsigned long val; - int found = 0; for (i = 0; i < ppmu->n_counter; ++i) { event = cpuhw->event[i]; @@ -654,7 +653,6 @@ static void perf_event_interrupt(struct pt_regs *regs) if ((int)val < 0) { if (event) { /* event has overflowed */ - found = 1; record_and_restart(event, val, regs); } else { /* @@ -672,11 +670,13 @@ static void perf_event_interrupt(struct pt_regs *regs) isync(); } -void hw_perf_event_setup(int cpu) +static int fsl_emb_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); memset(cpuhw, 0, sizeof(*cpuhw)); + + return 0; } int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) @@ -689,6 +689,8 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) pmu->name); perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW); + cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare", + fsl_emb_pmu_prepare_cpu, NULL); return 0; } From a0f0daf60bc1d3d78afded5931a56a015f2a17e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:04:57 +0300 Subject: [PATCH 1045/2093] drm/amdgpu: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ce7d88110b9ed5f33fe79ea6d4ed049fb0e57bce ] Don't assume that only the driver would be accessing LNKCTL. ASPM policy changes can trigger write to LNKCTL outside of driver's control. And in the case of upstream bridge, the driver does not even own the device it's changing the registers for. Use RMW capability accessors which do proper locking to avoid losing concurrent updates to the register value. Suggested-by: Lukas Wunner Fixes: a2e73f56fa62 ("drm/amdgpu: Add support for CIK parts") Fixes: 62a37553414a ("drm/amdgpu: add si implementation v10") Link: https://lore.kernel.org/r/20230717120503.15276-6-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Acked-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/cik.c | 36 +++++++++----------------------- drivers/gpu/drm/amd/amdgpu/si.c | 36 +++++++++----------------------- 2 files changed, 20 insertions(+), 52 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index de6d10390ab2..9be6da37032a 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1574,17 +1574,8 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev) u16 bridge_cfg2, gpu_cfg2; u32 max_lw, current_lw, tmp; - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &bridge_cfg); - pcie_capability_read_word(adev->pdev, PCI_EXP_LNKCTL, - &gpu_cfg); - - tmp16 = bridge_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(root, PCI_EXP_LNKCTL, tmp16); - - tmp16 = gpu_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(adev->pdev, PCI_EXP_LNKCTL, - tmp16); + pcie_capability_set_word(root, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); + pcie_capability_set_word(adev->pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); tmp = RREG32_PCIE(ixPCIE_LC_STATUS1); max_lw = (tmp & PCIE_LC_STATUS1__LC_DETECTED_LINK_WIDTH_MASK) >> @@ -1637,21 +1628,14 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev) msleep(100); /* linkctl */ - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (bridge_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(root, PCI_EXP_LNKCTL, - tmp16); - - pcie_capability_read_word(adev->pdev, - PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (gpu_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(adev->pdev, - PCI_EXP_LNKCTL, - tmp16); + pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + bridge_cfg & + PCI_EXP_LNKCTL_HAWD); + pcie_capability_clear_and_set_word(adev->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + gpu_cfg & + PCI_EXP_LNKCTL_HAWD); /* linkctl2 */ pcie_capability_read_word(root, PCI_EXP_LNKCTL2, diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index 7f99e130acd0..fd34c2100bd9 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -2276,17 +2276,8 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) u16 bridge_cfg2, gpu_cfg2; u32 max_lw, current_lw, tmp; - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &bridge_cfg); - pcie_capability_read_word(adev->pdev, PCI_EXP_LNKCTL, - &gpu_cfg); - - tmp16 = bridge_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(root, PCI_EXP_LNKCTL, tmp16); - - tmp16 = gpu_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(adev->pdev, PCI_EXP_LNKCTL, - tmp16); + pcie_capability_set_word(root, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); + pcie_capability_set_word(adev->pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); tmp = RREG32_PCIE(PCIE_LC_STATUS1); max_lw = (tmp & LC_DETECTED_LINK_WIDTH_MASK) >> LC_DETECTED_LINK_WIDTH_SHIFT; @@ -2331,21 +2322,14 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) mdelay(100); - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (bridge_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(root, PCI_EXP_LNKCTL, - tmp16); - - pcie_capability_read_word(adev->pdev, - PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (gpu_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(adev->pdev, - PCI_EXP_LNKCTL, - tmp16); + pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + bridge_cfg & + PCI_EXP_LNKCTL_HAWD); + pcie_capability_clear_and_set_word(adev->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + gpu_cfg & + PCI_EXP_LNKCTL_HAWD); pcie_capability_read_word(root, PCI_EXP_LNKCTL2, &tmp16); From 433330fb1296119d74cc5c8f1e05b5829ddc52f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:04:58 +0300 Subject: [PATCH 1046/2093] drm/radeon: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7189576e8a829130192b33c5b64e8a475369c776 ] Don't assume that only the driver would be accessing LNKCTL. ASPM policy changes can trigger write to LNKCTL outside of driver's control. And in the case of upstream bridge, the driver does not even own the device it's changing the registers for. Use RMW capability accessors which do proper locking to avoid losing concurrent updates to the register value. Suggested-by: Lukas Wunner Fixes: 8a7cd27679d0 ("drm/radeon/cik: add support for pcie gen1/2/3 switching") Fixes: b9d305dfb66c ("drm/radeon: implement pcie gen2/3 support for SI") Link: https://lore.kernel.org/r/20230717120503.15276-7-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Acked-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/cik.c | 36 ++++++++++------------------------- drivers/gpu/drm/radeon/si.c | 37 ++++++++++-------------------------- 2 files changed, 20 insertions(+), 53 deletions(-) diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 5819737c21c6..a6f3c811ceb8 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -9534,17 +9534,8 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev) u16 bridge_cfg2, gpu_cfg2; u32 max_lw, current_lw, tmp; - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &bridge_cfg); - pcie_capability_read_word(rdev->pdev, PCI_EXP_LNKCTL, - &gpu_cfg); - - tmp16 = bridge_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(root, PCI_EXP_LNKCTL, tmp16); - - tmp16 = gpu_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(rdev->pdev, PCI_EXP_LNKCTL, - tmp16); + pcie_capability_set_word(root, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); + pcie_capability_set_word(rdev->pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); tmp = RREG32_PCIE_PORT(PCIE_LC_STATUS1); max_lw = (tmp & LC_DETECTED_LINK_WIDTH_MASK) >> LC_DETECTED_LINK_WIDTH_SHIFT; @@ -9591,21 +9582,14 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev) msleep(100); /* linkctl */ - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (bridge_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(root, PCI_EXP_LNKCTL, - tmp16); - - pcie_capability_read_word(rdev->pdev, - PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (gpu_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(rdev->pdev, - PCI_EXP_LNKCTL, - tmp16); + pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + bridge_cfg & + PCI_EXP_LNKCTL_HAWD); + pcie_capability_clear_and_set_word(rdev->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + gpu_cfg & + PCI_EXP_LNKCTL_HAWD); /* linkctl2 */ pcie_capability_read_word(root, PCI_EXP_LNKCTL2, diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 8d5e4b25609d..a91012447b56 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -7131,17 +7131,8 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev) u16 bridge_cfg2, gpu_cfg2; u32 max_lw, current_lw, tmp; - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &bridge_cfg); - pcie_capability_read_word(rdev->pdev, PCI_EXP_LNKCTL, - &gpu_cfg); - - tmp16 = bridge_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(root, PCI_EXP_LNKCTL, tmp16); - - tmp16 = gpu_cfg | PCI_EXP_LNKCTL_HAWD; - pcie_capability_write_word(rdev->pdev, PCI_EXP_LNKCTL, - tmp16); + pcie_capability_set_word(root, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); + pcie_capability_set_word(rdev->pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_HAWD); tmp = RREG32_PCIE(PCIE_LC_STATUS1); max_lw = (tmp & LC_DETECTED_LINK_WIDTH_MASK) >> LC_DETECTED_LINK_WIDTH_SHIFT; @@ -7188,22 +7179,14 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev) msleep(100); /* linkctl */ - pcie_capability_read_word(root, PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (bridge_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(root, - PCI_EXP_LNKCTL, - tmp16); - - pcie_capability_read_word(rdev->pdev, - PCI_EXP_LNKCTL, - &tmp16); - tmp16 &= ~PCI_EXP_LNKCTL_HAWD; - tmp16 |= (gpu_cfg & PCI_EXP_LNKCTL_HAWD); - pcie_capability_write_word(rdev->pdev, - PCI_EXP_LNKCTL, - tmp16); + pcie_capability_clear_and_set_word(root, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + bridge_cfg & + PCI_EXP_LNKCTL_HAWD); + pcie_capability_clear_and_set_word(rdev->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_HAWD, + gpu_cfg & + PCI_EXP_LNKCTL_HAWD); /* linkctl2 */ pcie_capability_read_word(root, PCI_EXP_LNKCTL2, From 7f4c9c44d1b9b8f7fd8e96e546e4695c39758155 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:04:59 +0300 Subject: [PATCH 1047/2093] net/mlx5: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 30de872537bda526664d7a20b646adfb3e7ce6e6 ] Don't assume that only the driver would be accessing LNKCTL of the upstream bridge. ASPM policy changes can trigger write to LNKCTL outside of driver's control. Use RMW capability accessors which do proper locking to avoid losing concurrent updates to the register value. Suggested-by: Lukas Wunner Fixes: eabe8e5e88f5 ("net/mlx5: Handle sync reset now event") Link: https://lore.kernel.org/r/20230717120503.15276-8-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Reviewed-by: Moshe Shemesh Reviewed-by: Simon Horman Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index d219f8417d93..dec1492da74d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -319,16 +319,11 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) pci_cfg_access_lock(sdev); } /* PCI link toggle */ - err = pci_read_config_word(bridge, cap + PCI_EXP_LNKCTL, ®16); - if (err) - return err; - reg16 |= PCI_EXP_LNKCTL_LD; - err = pci_write_config_word(bridge, cap + PCI_EXP_LNKCTL, reg16); + err = pcie_capability_set_word(bridge, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LD); if (err) return err; msleep(500); - reg16 &= ~PCI_EXP_LNKCTL_LD; - err = pci_write_config_word(bridge, cap + PCI_EXP_LNKCTL, reg16); + err = pcie_capability_clear_word(bridge, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LD); if (err) return err; From 811ec8bc68f338531b131165bbd1da61a41fbc67 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:05:00 +0300 Subject: [PATCH 1048/2093] wifi: ath11k: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6c1b6bdb34aaf8f94f65a9cae1d63490320c11bc ] Don't assume that only the driver would be accessing LNKCTL. ASPM policy changes can trigger write to LNKCTL outside of driver's control. Use RMW capability accessors which do proper locking to avoid losing concurrent updates to the register value. On restore, clear the ASPMC field properly. Suggested-by: Lukas Wunner Fixes: e9603f4bdcc0 ("ath11k: pci: disable ASPM L0sLs before downloading firmware") Link: https://lore.kernel.org/r/20230717120503.15276-9-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Reviewed-by: Simon Horman Acked-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index 3c6005ab9a71..3953ebd551bf 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -582,8 +582,8 @@ static void ath11k_pci_aspm_disable(struct ath11k_pci *ab_pci) u16_get_bits(ab_pci->link_ctl, PCI_EXP_LNKCTL_ASPM_L1)); /* disable L0s and L1 */ - pcie_capability_write_word(ab_pci->pdev, PCI_EXP_LNKCTL, - ab_pci->link_ctl & ~PCI_EXP_LNKCTL_ASPMC); + pcie_capability_clear_word(ab_pci->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPMC); set_bit(ATH11K_PCI_ASPM_RESTORE, &ab_pci->flags); } @@ -591,8 +591,10 @@ static void ath11k_pci_aspm_disable(struct ath11k_pci *ab_pci) static void ath11k_pci_aspm_restore(struct ath11k_pci *ab_pci) { if (test_and_clear_bit(ATH11K_PCI_ASPM_RESTORE, &ab_pci->flags)) - pcie_capability_write_word(ab_pci->pdev, PCI_EXP_LNKCTL, - ab_pci->link_ctl); + pcie_capability_clear_and_set_word(ab_pci->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPMC, + ab_pci->link_ctl & + PCI_EXP_LNKCTL_ASPMC); } static int ath11k_pci_power_up(struct ath11k_base *ab) From e12e13952b0c38acde74c27cc1ccf5c0321dcc4f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 17 Jul 2023 15:05:02 +0300 Subject: [PATCH 1049/2093] wifi: ath10k: Use RMW accessors for changing LNKCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f139492a09f15254fa261245cdbd65555cdf39e3 ] Don't assume that only the driver would be accessing LNKCTL. ASPM policy changes can trigger write to LNKCTL outside of driver's control. Use RMW capability accessors which does proper locking to avoid losing concurrent updates to the register value. On restore, clear the ASPMC field properly. Suggested-by: Lukas Wunner Fixes: 76d870ed09ab ("ath10k: enable ASPM") Link: https://lore.kernel.org/r/20230717120503.15276-11-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Reviewed-by: Simon Horman Acked-by: Kalle Valo Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/pci.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 728d607289c3..522691ba4c5d 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -1963,8 +1963,9 @@ static int ath10k_pci_hif_start(struct ath10k *ar) ath10k_pci_irq_enable(ar); ath10k_pci_rx_post(ar); - pcie_capability_write_word(ar_pci->pdev, PCI_EXP_LNKCTL, - ar_pci->link_ctl); + pcie_capability_clear_and_set_word(ar_pci->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPMC, + ar_pci->link_ctl & PCI_EXP_LNKCTL_ASPMC); return 0; } @@ -2821,8 +2822,8 @@ static int ath10k_pci_hif_power_up(struct ath10k *ar, pcie_capability_read_word(ar_pci->pdev, PCI_EXP_LNKCTL, &ar_pci->link_ctl); - pcie_capability_write_word(ar_pci->pdev, PCI_EXP_LNKCTL, - ar_pci->link_ctl & ~PCI_EXP_LNKCTL_ASPMC); + pcie_capability_clear_word(ar_pci->pdev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_ASPMC); /* * Bring the target up cleanly. From 886959f425b6a936a30b82a297ae3aecb3b8230f Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Thu, 6 Apr 2023 15:16:52 -0400 Subject: [PATCH 1050/2093] NFSv4.2: Rework scratch handling for READ_PLUS [ Upstream commit fbd2a05f29a95d5b42b294bf47e55a711424965b ] Instead of using a tiny, static scratch buffer, we should use a kmalloc()-ed buffer that is allocated when checking for read plus usage. This lets us use the buffer before decoding any part of the READ_PLUS operation instead of setting it right before segment decoding, meaning it should be a little more robust. Signed-off-by: Anna Schumaker Stable-dep-of: bb05a617f06b ("NFSv4.2: Fix READ_PLUS smatch warnings") Signed-off-by: Sasha Levin --- fs/nfs/nfs42xdr.c | 4 ++-- fs/nfs/nfs4proc.c | 17 ++++++++++++----- include/linux/nfs_xdr.h | 1 + 3 files changed, 15 insertions(+), 7 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 2fd465cab631..08c1dd094f01 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1121,7 +1121,6 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) uint32_t segments; struct read_plus_segment *segs; int status, i; - char scratch_buf[16]; __be32 *p; status = decode_op_hdr(xdr, OP_READ_PLUS); @@ -1142,7 +1141,6 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) if (!segs) return -ENOMEM; - xdr_set_scratch_buffer(xdr, &scratch_buf, sizeof(scratch_buf)); status = -EIO; for (i = 0; i < segments; i++) { status = decode_read_plus_segment(xdr, &segs[i]); @@ -1347,6 +1345,8 @@ static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp, struct compound_hdr hdr; int status; + xdr_set_scratch_buffer(xdr, res->scratch, sizeof(res->scratch)); + status = decode_compound_hdr(xdr, &hdr); if (status) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1044305e7799..3f96ccc386c3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5446,6 +5446,8 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { + if (hdr->res.scratch) + kfree(hdr->res.scratch); if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) @@ -5459,17 +5461,22 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) } #if defined CONFIG_NFS_V4_2 && defined CONFIG_NFS_V4_2_READ_PLUS -static void nfs42_read_plus_support(struct nfs_pgio_header *hdr, +static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr, struct rpc_message *msg) { /* Note: We don't use READ_PLUS with pNFS yet */ - if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) + if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) { msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS]; + hdr->res.scratch = kmalloc(32, GFP_KERNEL); + return hdr->res.scratch != NULL; + } + return false; } #else -static void nfs42_read_plus_support(struct nfs_pgio_header *hdr, +static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr, struct rpc_message *msg) { + return false; } #endif /* CONFIG_NFS_V4_2 */ @@ -5479,8 +5486,8 @@ static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr, hdr->timestamp = jiffies; if (!hdr->pgio_done_cb) hdr->pgio_done_cb = nfs4_read_done_cb; - msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; - nfs42_read_plus_support(hdr, msg); + if (!nfs42_read_plus_support(hdr, msg)) + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0); } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e86cf6642d21..2fd973d188c4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -670,6 +670,7 @@ struct nfs_pgio_res { struct { unsigned int replen; /* used by read */ int eof; /* used by read */ + void * scratch; /* used by read */ }; struct { struct nfs_writeverf * verf; /* used by write */ From 5c47974263e8d3a6bbee987148bfba07f5cf803d Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 24 May 2023 17:27:08 -0400 Subject: [PATCH 1051/2093] NFSv4.2: Fix READ_PLUS smatch warnings [ Upstream commit bb05a617f06b7a882e19c4f475b8e37f14d9ceac ] Smatch reports: fs/nfs/nfs42xdr.c:1131 decode_read_plus() warn: missing error code? 'status' Which Dan suggests to fix by doing a hardcoded "return 0" from the "if (segments == 0)" check. Additionally, smatch reports that the "status = -EIO" assignment is not used. This patch addresses both these issues. Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202305222209.6l5VM2lL-lkp@intel.com/ Fixes: d3b00a802c845 ("NFS: Replace the READ_PLUS decoding code") Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs42xdr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 08c1dd094f01..ae034a1c53ef 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1135,13 +1135,12 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) res->eof = be32_to_cpup(p++); segments = be32_to_cpup(p++); if (segments == 0) - return status; + return 0; segs = kmalloc_array(segments, sizeof(*segs), GFP_KERNEL); if (!segs) return -ENOMEM; - status = -EIO; for (i = 0; i < segments; i++) { status = decode_read_plus_segment(xdr, &segs[i]); if (status < 0) From fccdafa51de000f81833cbaa7aba7e592a9130d1 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 30 Nov 2022 13:15:26 -0500 Subject: [PATCH 1052/2093] NFSv4.2: Fix up READ_PLUS alignment [ Upstream commit f8527028a7e52da884055c401abc04e0b0c84285 ] Assume that the first segment will be a DATA segment, and place the data directly into the xdr pages so it doesn't need to be shifted. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust Stable-dep-of: 8d18f6c5bb86 ("NFSv4.2: Fix READ_PLUS size calculations") Signed-off-by: Sasha Levin --- fs/nfs/nfs42xdr.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index ae034a1c53ef..ef3b150970ff 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -47,13 +47,14 @@ #define decode_deallocate_maxsz (op_decode_hdr_maxsz) #define encode_read_plus_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + 3) -#define NFS42_READ_PLUS_SEGMENT_SIZE (1 /* data_content4 */ + \ +#define NFS42_READ_PLUS_DATA_SEGMENT_SIZE \ + (1 /* data_content4 */ + \ 2 /* data_info4.di_offset */ + \ - 2 /* data_info4.di_length */) + 1 /* data_info4.di_length */) #define decode_read_plus_maxsz (op_decode_hdr_maxsz + \ 1 /* rpr_eof */ + \ 1 /* rpr_contents count */ + \ - 2 * NFS42_READ_PLUS_SEGMENT_SIZE) + NFS42_READ_PLUS_DATA_SEGMENT_SIZE) #define encode_seek_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ 2 /* offset */ + \ From 18d51547fe2f693f2a3ad604865a371bbe585c2e Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 31 May 2023 17:02:54 -0400 Subject: [PATCH 1053/2093] NFSv4.2: Fix READ_PLUS size calculations [ Upstream commit 8d18f6c5bb864d97a730f471c56cdecf313efe64 ] I bump the decode_read_plus_maxsz to account for hole segments, but I need to subtract out this increase when calling rpc_prepare_reply_pages() so the common case of single data segment replies can be directly placed into the xdr pages without needing to be shifted around. Reported-by: Chuck Lever Fixes: d3b00a802c845 ("NFS: Replace the READ_PLUS decoding code") Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs42xdr.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index ef3b150970ff..75765382cc0e 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -51,10 +51,16 @@ (1 /* data_content4 */ + \ 2 /* data_info4.di_offset */ + \ 1 /* data_info4.di_length */) +#define NFS42_READ_PLUS_HOLE_SEGMENT_SIZE \ + (1 /* data_content4 */ + \ + 2 /* data_info4.di_offset */ + \ + 2 /* data_info4.di_length */) +#define READ_PLUS_SEGMENT_SIZE_DIFF (NFS42_READ_PLUS_HOLE_SEGMENT_SIZE - \ + NFS42_READ_PLUS_DATA_SEGMENT_SIZE) #define decode_read_plus_maxsz (op_decode_hdr_maxsz + \ 1 /* rpr_eof */ + \ 1 /* rpr_contents count */ + \ - NFS42_READ_PLUS_DATA_SEGMENT_SIZE) + NFS42_READ_PLUS_HOLE_SEGMENT_SIZE) #define encode_seek_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ 2 /* offset */ + \ @@ -781,8 +787,8 @@ static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req, encode_putfh(xdr, args->fh, &hdr); encode_read_plus(xdr, args, &hdr); - rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->count, hdr.replen); + rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->count, + hdr.replen - READ_PLUS_SEGMENT_SIZE_DIFF); encode_nops(&hdr); } From a5b6b008e35822e6cd6748e315b7fb8ee532f445 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 23 Aug 2023 15:53:16 +1000 Subject: [PATCH 1054/2093] powerpc: Don't include lppaca.h in paca.h [ Upstream commit 1aa000667669fa855853decbb1c69e974d8ff716 ] By adding a forward declaration for struct lppaca we can untangle paca.h and lppaca.h. Also move get_lppaca() into lppaca.h for consistency. Add includes of lppaca.h to some files that need it. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230823055317.751786-3-mpe@ellerman.id.au Stable-dep-of: eac030b22ea1 ("powerpc/pseries: Rework lppaca_shared_proc() to avoid DEBUG_PREEMPT") Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/lppaca.h | 4 ++++ arch/powerpc/include/asm/paca.h | 6 +----- arch/powerpc/include/asm/paravirt.h | 1 + arch/powerpc/include/asm/plpar_wrappers.h | 1 + arch/powerpc/kvm/book3s_hv_ras.c | 1 + arch/powerpc/mm/book3s64/slb.c | 1 + arch/powerpc/xmon/xmon.c | 1 + 7 files changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 34d44cb17c87..fe278172e9d4 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -134,6 +134,10 @@ static inline bool lppaca_shared_proc(struct lppaca *l) return !!(l->__old_status & LPPACA_OLD_SHARED_PROC); } +#ifdef CONFIG_PPC_PSERIES +#define get_lppaca() (get_paca()->lppaca_ptr) +#endif + /* * SLB shadow buffer structure as defined in the PAPR. The save_area * contains adjacent ESID and VSID pairs for each shadowed SLB. The diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 0ab3511a47d7..183b5a251804 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #ifdef CONFIG_PPC_BOOK3E_64 @@ -47,14 +46,11 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */ #define get_paca() local_paca #endif -#ifdef CONFIG_PPC_PSERIES -#define get_lppaca() (get_paca()->lppaca_ptr) -#endif - #define get_slb_shadow() (get_paca()->slb_shadow_ptr) struct task_struct; struct rtas_args; +struct lppaca; /* * Defines the layout of the paca. diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index f5ba1a3c41f8..e08513d73119 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -6,6 +6,7 @@ #include #ifdef CONFIG_PPC64 #include +#include #include #endif diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 8239c0af5eb2..fe3d0ea0058a 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -9,6 +9,7 @@ #include #include +#include #include static inline long poll_pending(void) diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index ccfd96965630..82be6d87514b 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 6956f637a38c..f2708c8629a5 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index bd8e80936f44..cd692f399cd1 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -58,6 +58,7 @@ #ifdef CONFIG_PPC64 #include #include +#include #endif #include "nonstdio.h" From 4c8568cf4c45b415854195c8832b557cdefba57a Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Wed, 23 Aug 2023 15:53:17 +1000 Subject: [PATCH 1055/2093] powerpc/pseries: Rework lppaca_shared_proc() to avoid DEBUG_PREEMPT [ Upstream commit eac030b22ea12cdfcbb2e941c21c03964403c63f ] lppaca_shared_proc() takes a pointer to the lppaca which is typically accessed through get_lppaca(). With DEBUG_PREEMPT enabled, this leads to checking if preemption is enabled, for example: BUG: using smp_processor_id() in preemptible [00000000] code: grep/10693 caller is lparcfg_data+0x408/0x19a0 CPU: 4 PID: 10693 Comm: grep Not tainted 6.5.0-rc3 #2 Call Trace: dump_stack_lvl+0x154/0x200 (unreliable) check_preemption_disabled+0x214/0x220 lparcfg_data+0x408/0x19a0 ... This isn't actually a problem however, as it does not matter which lppaca is accessed, the shared proc state will be the same. vcpudispatch_stats_procfs_init() already works around this by disabling preemption, but the lparcfg code does not, erroring any time /proc/powerpc/lparcfg is accessed with DEBUG_PREEMPT enabled. Instead of disabling preemption on the caller side, rework lppaca_shared_proc() to not take a pointer and instead directly access the lppaca, bypassing any potential preemption checks. Fixes: f13c13a00512 ("powerpc: Stop using non-architected shared_proc field in lppaca") Signed-off-by: Russell Currey [mpe: Rework to avoid needing a definition in paca.h and lppaca.h] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230823055317.751786-4-mpe@ellerman.id.au Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/lppaca.h | 11 +++++++++-- arch/powerpc/platforms/pseries/lpar.c | 10 +--------- arch/powerpc/platforms/pseries/lparcfg.c | 4 ++-- arch/powerpc/platforms/pseries/setup.c | 2 +- drivers/cpuidle/cpuidle-pseries.c | 8 +------- 5 files changed, 14 insertions(+), 21 deletions(-) diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index fe278172e9d4..ee1488d38fdc 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -45,6 +45,7 @@ #include #include #include +#include /* * The lppaca is the "virtual processor area" registered with the hypervisor, @@ -127,14 +128,20 @@ struct lppaca { */ #define LPPACA_OLD_SHARED_PROC 2 -static inline bool lppaca_shared_proc(struct lppaca *l) +#ifdef CONFIG_PPC_PSERIES +/* + * All CPUs should have the same shared proc value, so directly access the PACA + * to avoid false positives from DEBUG_PREEMPT. + */ +static inline bool lppaca_shared_proc(void) { + struct lppaca *l = local_paca->lppaca_ptr; + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return false; return !!(l->__old_status & LPPACA_OLD_SHARED_PROC); } -#ifdef CONFIG_PPC_PSERIES #define get_lppaca() (get_paca()->lppaca_ptr) #endif diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 97ef6499e501..2c2812a87d47 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -638,16 +638,8 @@ static const struct proc_ops vcpudispatch_stats_freq_proc_ops = { static int __init vcpudispatch_stats_procfs_init(void) { - /* - * Avoid smp_processor_id while preemptible. All CPUs should have - * the same value for lppaca_shared_proc. - */ - preempt_disable(); - if (!lppaca_shared_proc(get_lppaca())) { - preempt_enable(); + if (!lppaca_shared_proc()) return 0; - } - preempt_enable(); if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL, &vcpudispatch_stats_proc_ops)) diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 63fd925ccbb8..ca10a3682c46 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -205,7 +205,7 @@ static void parse_ppp_data(struct seq_file *m) ppp_data.active_system_procs); /* pool related entries are appropriate for shared configs */ - if (lppaca_shared_proc(get_lppaca())) { + if (lppaca_shared_proc()) { unsigned long pool_idle_time, pool_procs; seq_printf(m, "pool=%d\n", ppp_data.pool_num); @@ -616,7 +616,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) partition_potential_processors); seq_printf(m, "shared_processor_mode=%d\n", - lppaca_shared_proc(get_lppaca())); + lppaca_shared_proc()); #ifdef CONFIG_PPC_64S_HASH_MMU if (!radix_enabled()) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8ef3270515a9..a0701dbdb134 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -846,7 +846,7 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - if (lppaca_shared_proc(get_lppaca())) { + if (lppaca_shared_proc()) { static_branch_enable(&shared_processor); pv_spinlocks_init(); #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c index 7e7ab5597d7a..0590001db653 100644 --- a/drivers/cpuidle/cpuidle-pseries.c +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -410,13 +410,7 @@ static int __init pseries_idle_probe(void) return -ENODEV; if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - /* - * Use local_paca instead of get_lppaca() since - * preemption is not disabled, and it is not required in - * fact, since lppaca_ptr does not need to be the value - * associated to the current CPU, it can be from any CPU. - */ - if (lppaca_shared_proc(local_paca->lppaca_ptr)) { + if (lppaca_shared_proc()) { cpuidle_state_table = shared_states; max_idle_state = ARRAY_SIZE(shared_states); } else { From ebbfe48dd15f4c6b6ce57309f0c14c95aa2ce472 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 24 Jul 2023 11:08:46 +0300 Subject: [PATCH 1056/2093] nfs/blocklayout: Use the passed in gfp flags [ Upstream commit 08b45fcb2d4675f6182fe0edc0d8b1fe604051fa ] This allocation should use the passed in GFP_ flags instead of GFP_KERNEL. One places where this matters is in filelayout_pg_init_write() which uses GFP_NOFS as the allocation flags. Fixes: 5c83746a0cf2 ("pnfs/blocklayout: in-kernel GETDEVICEINFO XDR parsing") Signed-off-by: Dan Carpenter Reviewed-by: Christoph Hellwig Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/blocklayout/dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index fea5f8821da5..ce2ea6239797 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -402,7 +402,7 @@ bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->concat.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; @@ -431,7 +431,7 @@ bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->stripe.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; From 4515f1676d8dcb45e2ee38b3d5c9334f3efabc04 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 9 May 2023 19:15:59 +1000 Subject: [PATCH 1057/2093] powerpc/pseries: Fix hcall tracepoints with JUMP_LABEL=n [ Upstream commit 750bd41aeaeb1f0e0128aa4f8fcd6dd759713641 ] With JUMP_LABEL=n, hcall_tracepoint_refcount's address is being tested instead of its value. This results in the tracing slowpath always being taken unnecessarily. Fixes: 9a10ccb29c0a2 ("powerpc/pseries: move hcall_tracepoint_refcount out of .toc") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230509091600.70994-1-npiggin@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/hvCall.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 762eb15d3bd4..fc50b9c27c1b 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -89,6 +89,7 @@ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ LOAD_REG_ADDR(r12, hcall_tracepoint_refcount) ; \ + ld r12,0(r12); \ std r12,32(r1); \ cmpdi r12,0; \ bne- LABEL; \ From e83f5e21089b10e2a59d96ae7c28502748ff8b64 Mon Sep 17 00:00:00 2001 From: Liang He Date: Wed, 22 Mar 2023 11:04:23 +0800 Subject: [PATCH 1058/2093] powerpc/mpc5xxx: Add missing fwnode_handle_put() [ Upstream commit b9bbbf4979073d5536b7650decd37fcb901e6556 ] In mpc5xxx_fwnode_get_bus_frequency(), we should add fwnode_handle_put() when break out of the iteration fwnode_for_each_parent_node() as it will automatically increase and decrease the refcounter. Fixes: de06fba62af6 ("powerpc/mpc5xxx: Switch mpc5xxx_get_bus_frequency() to use fwnode") Signed-off-by: Liang He Signed-off-by: Michael Ellerman Link: https://msgid.link/20230322030423.1855440-1-windhl@126.com Signed-off-by: Sasha Levin --- arch/powerpc/sysdev/mpc5xxx_clocks.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/sysdev/mpc5xxx_clocks.c b/arch/powerpc/sysdev/mpc5xxx_clocks.c index c5bf7e1b3780..58cee28e2399 100644 --- a/arch/powerpc/sysdev/mpc5xxx_clocks.c +++ b/arch/powerpc/sysdev/mpc5xxx_clocks.c @@ -25,8 +25,10 @@ unsigned long mpc5xxx_fwnode_get_bus_frequency(struct fwnode_handle *fwnode) fwnode_for_each_parent_node(fwnode, parent) { ret = fwnode_property_read_u32(parent, "bus-frequency", &bus_freq); - if (!ret) + if (!ret) { + fwnode_handle_put(parent); return bus_freq; + } } return 0; From f17d5efaafba3d5f02f0373f7c5f44711d676f3e Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Wed, 22 Mar 2023 14:53:22 +1100 Subject: [PATCH 1059/2093] powerpc/iommu: Fix notifiers being shared by PCI and VIO buses [ Upstream commit c37b6908f7b2bd24dcaaf14a180e28c9132b9c58 ] fail_iommu_setup() registers the fail_iommu_bus_notifier struct to both PCI and VIO buses. struct notifier_block is a linked list node, so this causes any notifiers later registered to either bus type to also be registered to the other since they share the same node. This causes issues in (at least) the vgaarb code, which registers a notifier for PCI buses. pci_notify() ends up being called on a vio device, converted with to_pci_dev() even though it's not a PCI device, and finally makes a bad access in vga_arbiter_add_pci_device() as discovered with KASAN: BUG: KASAN: slab-out-of-bounds in vga_arbiter_add_pci_device+0x60/0xe00 Read of size 4 at addr c000000264c26fdc by task swapper/0/1 Call Trace: dump_stack_lvl+0x1bc/0x2b8 (unreliable) print_report+0x3f4/0xc60 kasan_report+0x244/0x698 __asan_load4+0xe8/0x250 vga_arbiter_add_pci_device+0x60/0xe00 pci_notify+0x88/0x444 notifier_call_chain+0x104/0x320 blocking_notifier_call_chain+0xa0/0x140 device_add+0xac8/0x1d30 device_register+0x58/0x80 vio_register_device_node+0x9ac/0xce0 vio_bus_scan_register_devices+0xc4/0x13c __machine_initcall_pseries_vio_device_init+0x94/0xf0 do_one_initcall+0x12c/0xaa8 kernel_init_freeable+0xa48/0xba8 kernel_init+0x64/0x400 ret_from_kernel_thread+0x5c/0x64 Fix this by creating separate notifier_block structs for each bus type. Fixes: d6b9a81b2a45 ("powerpc: IOMMU fault injection") Reported-by: Nageswara R Sastry Signed-off-by: Russell Currey Tested-by: Nageswara R Sastry Reviewed-by: Andrew Donnellan [mpe: Add #ifdef to fix CONFIG_IBMVIO=n build] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230322035322.328709-1-ruscur@russell.cc Signed-off-by: Sasha Levin --- arch/powerpc/kernel/iommu.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index b8b7a189cd3c..a612abe4bfd5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -171,17 +171,28 @@ static int fail_iommu_bus_notify(struct notifier_block *nb, return 0; } -static struct notifier_block fail_iommu_bus_notifier = { +/* + * PCI and VIO buses need separate notifier_block structs, since they're linked + * list nodes. Sharing a notifier_block would mean that any notifiers later + * registered for PCI buses would also get called by VIO buses and vice versa. + */ +static struct notifier_block fail_iommu_pci_bus_notifier = { .notifier_call = fail_iommu_bus_notify }; +#ifdef CONFIG_IBMVIO +static struct notifier_block fail_iommu_vio_bus_notifier = { + .notifier_call = fail_iommu_bus_notify +}; +#endif + static int __init fail_iommu_setup(void) { #ifdef CONFIG_PCI - bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier); + bus_register_notifier(&pci_bus_type, &fail_iommu_pci_bus_notifier); #endif #ifdef CONFIG_IBMVIO - bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier); + bus_register_notifier(&vio_bus_type, &fail_iommu_vio_bus_notifier); #endif return 0; From b648f57175815919d2ccd1b152ba1d03a8886598 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 28 Jun 2023 21:20:11 +0800 Subject: [PATCH 1060/2093] ext4: fix unttached inode after power cut with orphan file feature enabled [ Upstream commit 1524773425ae8113b0b782886366e68656b34e53 ] Running generic/475(filesystem consistent tests after power cut) could easily trigger unattached inode error while doing fsck: Unattached zero-length inode 39405. Clear? no Unattached inode 39405 Connect to /lost+found? no Above inconsistence is caused by following process: P1 P2 ext4_create inode = ext4_new_inode_start_handle // itable records nlink=1 ext4_add_nondir err = ext4_add_entry // ENOSPC ext4_append ext4_bread ext4_getblk ext4_map_blocks // returns ENOSPC drop_nlink(inode) // won't be updated into disk inode ext4_orphan_add(handle, inode) ext4_orphan_file_add ext4_journal_stop(handle) jbd2_journal_commit_transaction // commit success >> power cut << ext4_fill_super ext4_load_and_init_journal // itable records nlink=1 ext4_orphan_cleanup ext4_process_orphan if (inode->i_nlink) // true, inode won't be deleted Then, allocated inode will be reserved on disk and corresponds to no dentries, so e2fsck reports 'unattached inode' problem. The problem won't happen if orphan file feature is disabled, because ext4_orphan_add() will update disk inode in orphan list mode. There are several places not updating disk inode while putting inode into orphan area, such as ext4_add_nondir(), ext4_symlink() and whiteout in ext4_rename(). Fix it by updating inode into disk in all error branches of these places. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217605 Fixes: 02f310fcf47f ("ext4: Speedup ext4 orphan inode handling") Signed-off-by: Zhihao Cheng Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230628132011.650383-1-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/namei.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 0e1aeb9cb4a7..6a08fc31a66d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2799,6 +2799,7 @@ static int ext4_add_nondir(handle_t *handle, return err; } drop_nlink(inode); + ext4_mark_inode_dirty(handle, inode); ext4_orphan_add(handle, inode); unlock_new_inode(inode); return err; @@ -3436,6 +3437,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, err_drop_inode: clear_nlink(inode); + ext4_mark_inode_dirty(handle, inode); ext4_orphan_add(handle, inode); unlock_new_inode(inode); if (handle) @@ -4021,6 +4023,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, ext4_resetent(handle, &old, old.inode->i_ino, old_file_type); drop_nlink(whiteout); + ext4_mark_inode_dirty(handle, whiteout); ext4_orphan_add(handle, whiteout); } unlock_new_inode(whiteout); From f27f759f4cd490593cc7527b03fcec3aa4dbc2e7 Mon Sep 17 00:00:00 2001 From: Alexei Filippov Date: Sat, 19 Aug 2023 20:32:16 +0300 Subject: [PATCH 1061/2093] jfs: validate max amount of blocks before allocation. [ Upstream commit 0225e10972fa809728b8d4c1bd2772b3ec3fdb57 ] The lack of checking bmp->db_max_freebud in extBalloc() can lead to shift out of bounds, so this patch prevents undefined behavior, because bmp->db_max_freebud == -1 only if there is no free space. Signed-off-by: Aleksei Filippov Signed-off-by: Dave Kleikamp Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+5f088f29593e6b4c8db8@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?id=01abadbd6ae6a08b1f1987aa61554c6b3ac19ff2 Signed-off-by: Sasha Levin --- fs/jfs/jfs_extent.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index ae99a7e232ee..a82751e6c47f 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -311,6 +311,11 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) * blocks in the map. in that case, we'll start off with the * maximum free. */ + + /* give up if no space left */ + if (bmp->db_maxfreebud == -1) + return -ENOSPC; + max = (s64) 1 << bmp->db_maxfreebud; if (*nblocks >= max && *nblocks > nbperpage) nb = nblks = (max > nbperpage) ? max : nbperpage; From 02a29a2455b08a4cad2b1c8b9a90092e00033b19 Mon Sep 17 00:00:00 2001 From: Su Hui Date: Fri, 4 Aug 2023 09:26:57 +0800 Subject: [PATCH 1062/2093] fs: lockd: avoid possible wrong NULL parameter [ Upstream commit de8d38cf44bac43e83bad28357ba84784c412752 ] clang's static analysis warning: fs/lockd/mon.c: line 293, column 2: Null pointer passed as 2nd argument to memory copy function. Assuming 'hostname' is NULL and calling 'nsm_create_handle()', this will pass NULL as 2nd argument to memory copy function 'memcpy()'. So return NULL if 'hostname' is invalid. Fixes: 77a3ef33e2de ("NSM: More clean up of nsm_get_handle()") Signed-off-by: Su Hui Reviewed-by: Nick Desaulniers Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/lockd/mon.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1d9488cf0534..87a0f207df0b 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -276,6 +276,9 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, { struct nsm_handle *new; + if (!hostname) + return NULL; + new = kzalloc(sizeof(*new) + hostname_len + 1, GFP_KERNEL); if (unlikely(new == NULL)) return NULL; From 6d08bd22fa2941a4d5ef45ed115dd00e484a93d7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 16 Aug 2023 10:20:52 -0400 Subject: [PATCH 1063/2093] NFSD: da_addr_body field missing in some GETDEVICEINFO replies [ Upstream commit 6372e2ee629894433fe6107d7048536a3280a284 ] The XDR specification in RFC 8881 looks like this: struct device_addr4 { layouttype4 da_layout_type; opaque da_addr_body<>; }; struct GETDEVICEINFO4resok { device_addr4 gdir_device_addr; bitmap4 gdir_notification; }; union GETDEVICEINFO4res switch (nfsstat4 gdir_status) { case NFS4_OK: GETDEVICEINFO4resok gdir_resok4; case NFS4ERR_TOOSMALL: count4 gdir_mincount; default: void; }; Looking at nfsd4_encode_getdeviceinfo() .... When the client provides a zero gd_maxcount, then the Linux NFS server implementation encodes the da_layout_type field and then skips the da_addr_body field completely, proceeding directly to encode gdir_notification field. There does not appear to be an option in the specification to skip encoding da_addr_body. Moreover, Section 18.40.3 says: > If the client wants to just update or turn off notifications, it > MAY send a GETDEVICEINFO operation with gdia_maxcount set to zero. > In that event, if the device ID is valid, the reply's da_addr_body > field of the gdir_device_addr field will be of zero length. Since the layout drivers are responsible for encoding the da_addr_body field, put this fix inside the ->encode_getdeviceinfo methods. Fixes: 9cf514ccfacb ("nfsd: implement pNFS operations") Reviewed-by: Christoph Hellwig Cc: Tom Haynes Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/blocklayoutxdr.c | 9 +++++++++ fs/nfsd/flexfilelayoutxdr.c | 9 +++++++++ fs/nfsd/nfs4xdr.c | 25 +++++++++++-------------- 3 files changed, 29 insertions(+), 14 deletions(-) diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 442543304930..2455dc8be18a 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -82,6 +82,15 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, int len = sizeof(__be32), ret, i; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + p = xdr_reserve_space(xdr, len + sizeof(__be32)); if (!p) return nfserr_resource; diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index e81d2a5cf381..bb205328e043 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -85,6 +85,15 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, int addr_len; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + /* len + padding for two strings */ addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; ver_len = 20; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 8f90a87ee9ca..89a579be042e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4571,20 +4571,17 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(gdev->gd_layout_type); - /* If maxcount is 0 then just update notifications */ - if (gdev->gd_maxcount != 0) { - ops = nfsd4_layout_ops[gdev->gd_layout_type]; - nfserr = ops->encode_getdeviceinfo(xdr, gdev); - if (nfserr) { - /* - * We don't bother to burden the layout drivers with - * enforcing gd_maxcount, just tell the client to - * come back with a bigger buffer if it's not enough. - */ - if (xdr->buf->len + 4 > gdev->gd_maxcount) - goto toosmall; - return nfserr; - } + ops = nfsd4_layout_ops[gdev->gd_layout_type]; + nfserr = ops->encode_getdeviceinfo(xdr, gdev); + if (nfserr) { + /* + * We don't bother to burden the layout drivers with + * enforcing gd_maxcount, just tell the client to + * come back with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + 4 > gdev->gd_maxcount) + goto toosmall; + return nfserr; } if (gdev->gd_notify_types) { From fdbc9637bf8284c3a9641a12887658c37d2366e3 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 22 Aug 2023 14:22:38 -0400 Subject: [PATCH 1064/2093] NFS: Guard against READDIR loop when entry names exceed MAXNAMELEN [ Upstream commit f67b55b6588bcf9316a1e6e8d529100a5aa3ebe6 ] Commit 64cfca85bacd asserts the only valid return values for nfs2/3_decode_dirent should not include -ENAMETOOLONG, but for a server that sends a filename3 which exceeds MAXNAMELEN in a READDIR response the client's behavior will be to endlessly retry the operation. We could map -ENAMETOOLONG into -EBADCOOKIE, but that would produce truncated listings without any error. The client should return an error for this case to clearly assert that the server implementation must be corrected. Fixes: 64cfca85bacd ("NFS: Return valid errors from nfs2/3_decode_dirent()") Signed-off-by: Benjamin Coddington Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs2xdr.c | 2 +- fs/nfs/nfs3xdr.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 05c3b4b2b3dd..c19093814296 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -949,7 +949,7 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_filename_inline(xdr, &entry->name, &entry->len); if (unlikely(error)) - return -EAGAIN; + return error == -ENAMETOOLONG ? -ENAMETOOLONG : -EAGAIN; /* * The type (size and byte order) of nfscookie isn't defined in diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 3b0b650c9c5a..60f032be805a 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1991,7 +1991,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_inline_filename3(xdr, &entry->name, &entry->len); if (unlikely(error)) - return -EAGAIN; + return error == -ENAMETOOLONG ? -ENAMETOOLONG : -EAGAIN; error = decode_cookie3(xdr, &new_cookie); if (unlikely(error)) From 4030ace74d8b8ec9920c26b2a0969cd24bb5d3c8 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Thu, 24 Aug 2023 16:43:53 -0400 Subject: [PATCH 1065/2093] NFSv4.2: fix handling of COPY ERR_OFFLOAD_NO_REQ [ Upstream commit 5690eed941ab7e33c3c3d6b850100cabf740f075 ] If the client sent a synchronous copy and the server replied with ERR_OFFLOAD_NO_REQ indicating that it wants an asynchronous copy instead, the client should retry with asynchronous copy. Fixes: 539f57b3e0fd ("NFS handle COPY ERR_OFFLOAD_NO_REQS") Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs42proc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 7c33bba179d2..d903ea10410c 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -470,8 +470,9 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, continue; } break; - } else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) { - args.sync = true; + } else if (err == -NFS4ERR_OFFLOAD_NO_REQS && + args.sync != res.synchronous) { + args.sync = res.synchronous; dst_exception.retry = 1; continue; } else if ((err == -ESTALE || From 590b45e5cd1202e81c691f5b66f21a2afd7dba0a Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 30 Aug 2023 14:31:31 -0400 Subject: [PATCH 1066/2093] pNFS: Fix assignment of xprtdata.cred [ Upstream commit c4a123d2e8c4dc91d581ee7d05c0cd51a0273fab ] The comma at the end of the line was leftover from an earlier refactor of the _nfs4_pnfs_v3_ds_connect() function. This is technically valid C, so the compilers didn't catch it, but if I'm understanding how it works correctly it assigns the return value of rpc_clnt_add_xprtr() to xprtdata.cred. Reported-by: Olga Kornievskaia Fixes: a12f996d3413 ("NFSv4/pNFS: Use connections to a DS that are all of the same protocol family") Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/pnfs_nfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 5d035dd2d7bf..47a8da3f5c9f 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -943,7 +943,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, * Test this address for session trunking and * add as an alias */ - xprtdata.cred = nfs4_get_clid_cred(clp), + xprtdata.cred = nfs4_get_clid_cred(clp); rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, rpc_clnt_setup_test_and_add_xprt, &rpcdata); From 8199a46af2ea7b65a0ad24db3fdee1b7034005c1 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 27 Jun 2023 10:35:00 -0400 Subject: [PATCH 1067/2093] cgroup/cpuset: Inherit parent's load balance state in v2 [ Upstream commit c8c926200c55454101f072a4b16c9ff5b8c9e56f ] Since commit f28e22441f35 ("cgroup/cpuset: Add a new isolated cpus.partition type"), the CS_SCHED_LOAD_BALANCE bit of a v2 cpuset can be on or off. The child cpusets of a partition root must have the same setting as its parent or it may screw up the rebuilding of sched domains. Fix this problem by making sure the a child v2 cpuset will follows its parent cpuset load balance state unless the child cpuset is a new partition root itself. Fixes: f28e22441f35 ("cgroup/cpuset: Add a new isolated cpus.partition type") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/cgroup/cpuset.c | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index db3e05b6b4dd..79e6a5d4c29a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1606,11 +1606,16 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, } /* - * Skip the whole subtree if the cpumask remains the same - * and has no partition root state and force flag not set. + * Skip the whole subtree if + * 1) the cpumask remains the same, + * 2) has no partition root state, + * 3) force flag not set, and + * 4) for v2 load balance state same as its parent. */ if (!cp->partition_root_state && !force && - cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { + cpumask_equal(tmp->new_cpus, cp->effective_cpus) && + (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || + (is_sched_load_balance(parent) == is_sched_load_balance(cp)))) { pos_css = css_rightmost_descendant(pos_css); continue; } @@ -1693,6 +1698,20 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, update_tasks_cpumask(cp, tmp->new_cpus); + /* + * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE + * from parent if current cpuset isn't a valid partition root + * and their load balance states differ. + */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + !is_partition_valid(cp) && + (is_sched_load_balance(parent) != is_sched_load_balance(cp))) { + if (is_sched_load_balance(parent)) + set_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); + else + clear_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); + } + /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. @@ -3213,6 +3232,14 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cs->use_parent_ecpus = true; parent->child_ecpus_count++; } + + /* + * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated + */ + if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + !is_sched_load_balance(parent)) + clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); + spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) From 5643c936d1b80f85b0d85a91a991601855a050e9 Mon Sep 17 00:00:00 2001 From: Minjie Du Date: Thu, 6 Jul 2023 10:27:03 +0800 Subject: [PATCH 1068/2093] RDMA/qedr: Remove a duplicate assignment in irdma_query_ah() [ Upstream commit 65e02e840847158c7ee48ca8e6e91062b0f78662 ] Delete a duplicate statement from this function implementation. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Minjie Du Acked-by: Alok Prasad Link: https://lore.kernel.org/r/20230706022704.1260-1-duminjie@vivo.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/irdma/verbs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 6a8bb6ed4bf4..5962261f1b15 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -4354,7 +4354,6 @@ static int irdma_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr) ah_attr->grh.traffic_class = ah->sc_ah.ah_info.tc_tos; ah_attr->grh.hop_limit = ah->sc_ah.ah_info.hop_ttl; ah_attr->grh.sgid_index = ah->sgid_index; - ah_attr->grh.sgid_index = ah->sgid_index; memcpy(&ah_attr->grh.dgid, &ah->dgid, sizeof(ah_attr->grh.dgid)); } From 79e2cc5c4c10a71a06da47a7cc14b7e2891de57a Mon Sep 17 00:00:00 2001 From: "Guoniu.zhou" Date: Mon, 12 Jun 2023 04:43:40 +0200 Subject: [PATCH 1069/2093] media: ov5640: fix low resolution image abnormal issue [ Upstream commit a828002f38c5ee49d3f0c0e64c0f0caa1aec8dc2 ] OV5640 will output abnormal image data when work at low resolution (320x240, 176x144 and 160x120) after switching from high resolution, such as 1080P, the time interval between high and low switching must be less than 1000ms in order to OV5640 don't enter suspend state during the time. The reason is by 0x3824 value don't restore to initialize value when do resolution switching. In high resolution setting array, 0x3824 is set to 0x04, but low resolution setting array remove 0x3824 in commit db15c1957a2d ("media: ov5640: Remove duplicated mode settings"). So when do resolution switching from high to low, such as 1080P to 320x240, and the time interval is less than auto suspend delay time which means global initialize setting array will not be loaded, the output image data are abnormal. Hence move 0x3824 from ov5640_init_setting[] table to ov5640_setting_low_res[] table and also move 0x4407 0x460b, 0x460c to avoid same issue. Fixes: db15c1957a2d ("media: ov5640: Remove duplicated mode settings") Signed-off-by: Guoniu.zhou Reviewed-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov5640.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index 267f514023e7..cc23ff2067f6 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -557,9 +557,7 @@ static const struct reg_value ov5640_init_setting[] = { {0x4001, 0x02, 0, 0}, {0x4004, 0x02, 0, 0}, {0x3000, 0x00, 0, 0}, {0x3002, 0x1c, 0, 0}, {0x3004, 0xff, 0, 0}, {0x3006, 0xc3, 0, 0}, {0x302e, 0x08, 0, 0}, {0x4300, 0x3f, 0, 0}, - {0x501f, 0x00, 0, 0}, {0x4407, 0x04, 0, 0}, - {0x440e, 0x00, 0, 0}, {0x460b, 0x35, 0, 0}, {0x460c, 0x22, 0, 0}, - {0x4837, 0x0a, 0, 0}, {0x3824, 0x02, 0, 0}, + {0x501f, 0x00, 0, 0}, {0x440e, 0x00, 0, 0}, {0x4837, 0x0a, 0, 0}, {0x5000, 0xa7, 0, 0}, {0x5001, 0xa3, 0, 0}, {0x5180, 0xff, 0, 0}, {0x5181, 0xf2, 0, 0}, {0x5182, 0x00, 0, 0}, {0x5183, 0x14, 0, 0}, {0x5184, 0x25, 0, 0}, {0x5185, 0x24, 0, 0}, {0x5186, 0x09, 0, 0}, @@ -623,7 +621,8 @@ static const struct reg_value ov5640_setting_low_res[] = { {0x3a0a, 0x00, 0, 0}, {0x3a0b, 0xf6, 0, 0}, {0x3a0e, 0x03, 0, 0}, {0x3a0d, 0x04, 0, 0}, {0x3a14, 0x03, 0, 0}, {0x3a15, 0xd8, 0, 0}, {0x4001, 0x02, 0, 0}, {0x4004, 0x02, 0, 0}, - {0x4407, 0x04, 0, 0}, {0x5001, 0xa3, 0, 0}, + {0x4407, 0x04, 0, 0}, {0x460b, 0x35, 0, 0}, {0x460c, 0x22, 0, 0}, + {0x3824, 0x02, 0, 0}, {0x5001, 0xa3, 0, 0}, }; static const struct reg_value ov5640_setting_720P_1280_720[] = { From d7d47edf78c9ba9075aff34bf95452bdad8e04bd Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 18 Jun 2023 20:17:40 +0200 Subject: [PATCH 1070/2093] media: ad5820: Drop unsupported ad5823 from i2c_ and of_device_id tables [ Upstream commit f126ff7e4024f6704e6ec0d4137037568708a3c7 ] The supported ad5820 and ad5821 VCMs both use a single 16 bit register which is written by sending 2 bytes with the data directly after sending the i2c-client address. The ad5823 OTOH has a more typical i2c / smbus device setup with multiple 8 bit registers where the first byte send after the i2c-client address is the register address and the actual data only starts from the second byte after the i2c-client address. The ad5823 i2c_ and of_device_id-s was added at the same time as the ad5821 ids with as rationale: """ Some camera modules also refer that AD5823 is a replacement of AD5820: https://download.kamami.com/p564094-OV8865_DS.pdf """ The AD5823 may be an electrical and functional replacement of the AD5820, but from a software pov it is not compatible at all and it is going to need its own driver, drop its id from the ad5820 driver. Fixes: b8bf73136bae ("media: ad5820: Add support for ad5821 and ad5823") Cc: Pavel Machek Cc: Ricardo Ribalda Delgado Signed-off-by: Hans de Goede Reviewed-by: Ricardo Ribalda Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ad5820.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/media/i2c/ad5820.c b/drivers/media/i2c/ad5820.c index a12fedcc3a1c..088c29c4e252 100644 --- a/drivers/media/i2c/ad5820.c +++ b/drivers/media/i2c/ad5820.c @@ -356,7 +356,6 @@ static void ad5820_remove(struct i2c_client *client) static const struct i2c_device_id ad5820_id_table[] = { { "ad5820", 0 }, { "ad5821", 0 }, - { "ad5823", 0 }, { } }; MODULE_DEVICE_TABLE(i2c, ad5820_id_table); @@ -364,7 +363,6 @@ MODULE_DEVICE_TABLE(i2c, ad5820_id_table); static const struct of_device_id ad5820_of_table[] = { { .compatible = "adi,ad5820" }, { .compatible = "adi,ad5821" }, - { .compatible = "adi,ad5823" }, { } }; MODULE_DEVICE_TABLE(of, ad5820_of_table); From aeb79a1778cb13b87b8ac3b99c43d798619f9d62 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 15 Jun 2023 12:30:30 +0200 Subject: [PATCH 1071/2093] media: i2c: tvp5150: check return value of devm_kasprintf() [ Upstream commit 26ce7054d804be73935b9268d6e0ecf2fbbc8aef ] devm_kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: 0556f1d580d4 ("media: tvp5150: add input source selection of_graph support") Signed-off-by: Claudiu Beznea Reviewed-by: Marco Felsch Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/tvp5150.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c index 859f1cb2fa74..84f87c016f9b 100644 --- a/drivers/media/i2c/tvp5150.c +++ b/drivers/media/i2c/tvp5150.c @@ -2068,6 +2068,10 @@ static int tvp5150_parse_dt(struct tvp5150 *decoder, struct device_node *np) tvpc->ent.name = devm_kasprintf(dev, GFP_KERNEL, "%s %s", v4l2c->name, v4l2c->label ? v4l2c->label : ""); + if (!tvpc->ent.name) { + ret = -ENOMEM; + goto err_free; + } } ep_np = of_graph_get_endpoint_by_regs(np, TVP5150_PAD_VID_OUT, 0); From 25afb3e03bf8ab02567af4b6ffbfd6250a91a9f8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 14 Jun 2023 20:31:05 +0200 Subject: [PATCH 1072/2093] media: v4l2-core: Fix a potential resource leak in v4l2_fwnode_parse_link() [ Upstream commit d7b13edd4cb4bfa335b6008ab867ac28582d3e5c ] If fwnode_graph_get_remote_endpoint() fails, 'fwnode' is known to be NULL, so fwnode_handle_put() is a no-op. Release the reference taken from a previous fwnode_graph_get_port_parent() call instead. Also handle fwnode_graph_get_port_parent() failures. In order to fix these issues, add an error handling path to the function and the needed gotos. Fixes: ca50c197bd96 ("[media] v4l: fwnode: Support generic fwnode for parsing standardised properties") Signed-off-by: Christophe JAILLET Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/v4l2-core/v4l2-fwnode.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c index 3d85a8600f57..69c8b3b65686 100644 --- a/drivers/media/v4l2-core/v4l2-fwnode.c +++ b/drivers/media/v4l2-core/v4l2-fwnode.c @@ -551,19 +551,29 @@ int v4l2_fwnode_parse_link(struct fwnode_handle *fwnode, link->local_id = fwep.id; link->local_port = fwep.port; link->local_node = fwnode_graph_get_port_parent(fwnode); + if (!link->local_node) + return -ENOLINK; fwnode = fwnode_graph_get_remote_endpoint(fwnode); - if (!fwnode) { - fwnode_handle_put(fwnode); - return -ENOLINK; - } + if (!fwnode) + goto err_put_local_node; fwnode_graph_parse_endpoint(fwnode, &fwep); link->remote_id = fwep.id; link->remote_port = fwep.port; link->remote_node = fwnode_graph_get_port_parent(fwnode); + if (!link->remote_node) + goto err_put_remote_endpoint; return 0; + +err_put_remote_endpoint: + fwnode_handle_put(fwnode); + +err_put_local_node: + fwnode_handle_put(link->local_node); + + return -ENOLINK; } EXPORT_SYMBOL_GPL(v4l2_fwnode_parse_link); From 13ed255248dfbbb7f23f9170c7a537fb9ca22c73 Mon Sep 17 00:00:00 2001 From: Daniel Marcovitch Date: Fri, 9 Jun 2023 10:51:45 +0000 Subject: [PATCH 1073/2093] iommu/amd/iommu_v2: Fix pasid_state refcount dec hit 0 warning on pasid unbind [ Upstream commit 534103bcd52ca9c1fecbc70e717b4a538dc4ded8 ] When unbinding pasid - a race condition exists vs outstanding page faults. To prevent this, the pasid_state object contains a refcount. * set to 1 on pasid bind * incremented on each ppr notification start * decremented on each ppr notification done * decremented on pasid unbind Since refcount_dec assumes that refcount will never reach 0: the current implementation causes the following to be invoked on pasid unbind: REFCOUNT_WARN("decrement hit 0; leaking memory") Fix this issue by changing refcount_dec to refcount_dec_and_test to explicitly handle refcount=1. Fixes: 8bc54824da4e ("iommu/amd: Convert from atomic_t to refcount_t on pasid_state->count") Signed-off-by: Daniel Marcovitch Signed-off-by: Vasant Hegde Link: https://lore.kernel.org/r/20230609105146.7773-2-vasant.hegde@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd/iommu_v2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c index 75355ddca657..4caa023048a0 100644 --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -262,8 +262,8 @@ static void put_pasid_state(struct pasid_state *pasid_state) static void put_pasid_state_wait(struct pasid_state *pasid_state) { - refcount_dec(&pasid_state->count); - wait_event(pasid_state->wq, !refcount_read(&pasid_state->count)); + if (!refcount_dec_and_test(&pasid_state->count)) + wait_event(pasid_state->wq, !refcount_read(&pasid_state->count)); free_pasid_state(pasid_state); } From 92e2dcf9412fe43e283a0f03672ca936da667b6b Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Sat, 17 Jun 2023 18:25:45 +0000 Subject: [PATCH 1074/2093] iommu: rockchip: Fix directory table address encoding [ Upstream commit 6df63b7ebdaf5fcd75dceedf6967d0761e56eca1 ] The physical address to the directory table is currently encoded using the following bit layout for IOMMU v2. 31:12 - Address bit 31:0 11: 4 - Address bit 39:32 This is also the bit layout used by the vendor kernel. However, testing has shown that addresses to the directory/page tables and memory pages are all encoded using the same bit layout. IOMMU v1: 31:12 - Address bit 31:0 IOMMU v2: 31:12 - Address bit 31:0 11: 8 - Address bit 35:32 7: 4 - Address bit 39:36 Change to use the mk_dtentries ops to encode the directory table address correctly. The value written to DTE_ADDR may include the valid bit set, a bit that is ignored and DTE_ADDR reg read it back as 0. This also update the bit layout comment for the page address and the number of nybbles that are read back for DTE_ADDR comment. These changes render the dte_addr_phys and dma_addr_dte ops unused and is removed. Fixes: 227014b33f62 ("iommu: rockchip: Add internal ops to handle variants") Fixes: c55356c534aa ("iommu: rockchip: Add support for iommu v2") Fixes: c987b65a574f ("iommu/rockchip: Fix physical address decoding") Signed-off-by: Jonas Karlman Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20230617182540.3091374-2-jonas@kwiboo.se Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/rockchip-iommu.c | 43 ++++------------------------------ 1 file changed, 5 insertions(+), 38 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index f7e9b56be174..43bb577a26e5 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -98,8 +98,6 @@ struct rk_iommu_ops { phys_addr_t (*pt_address)(u32 dte); u32 (*mk_dtentries)(dma_addr_t pt_dma); u32 (*mk_ptentries)(phys_addr_t page, int prot); - phys_addr_t (*dte_addr_phys)(u32 addr); - u32 (*dma_addr_dte)(dma_addr_t dt_dma); u64 dma_bit_mask; }; @@ -277,8 +275,8 @@ static u32 rk_mk_pte(phys_addr_t page, int prot) /* * In v2: * 31:12 - Page address bit 31:0 - * 11:9 - Page address bit 34:32 - * 8:4 - Page address bit 39:35 + * 11: 8 - Page address bit 35:32 + * 7: 4 - Page address bit 39:36 * 3 - Security * 2 - Writable * 1 - Readable @@ -505,7 +503,7 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu) /* * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY - * and verifying that upper 5 nybbles are read back. + * and verifying that upper 5 (v1) or 7 (v2) nybbles are read back. */ for (i = 0; i < iommu->num_mmu; i++) { dte_addr = rk_ops->pt_address(DTE_ADDR_DUMMY); @@ -530,33 +528,6 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu) return 0; } -static inline phys_addr_t rk_dte_addr_phys(u32 addr) -{ - return (phys_addr_t)addr; -} - -static inline u32 rk_dma_addr_dte(dma_addr_t dt_dma) -{ - return dt_dma; -} - -#define DT_HI_MASK GENMASK_ULL(39, 32) -#define DTE_BASE_HI_MASK GENMASK(11, 4) -#define DT_SHIFT 28 - -static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr) -{ - u64 addr64 = addr; - return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) | - ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT); -} - -static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma) -{ - return (dt_dma & RK_DTE_PT_ADDRESS_MASK) | - ((dt_dma & DT_HI_MASK) >> DT_SHIFT); -} - static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova) { void __iomem *base = iommu->bases[index]; @@ -576,7 +547,7 @@ static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova) page_offset = rk_iova_page_offset(iova); mmu_dte_addr = rk_iommu_read(base, RK_MMU_DTE_ADDR); - mmu_dte_addr_phys = rk_ops->dte_addr_phys(mmu_dte_addr); + mmu_dte_addr_phys = rk_ops->pt_address(mmu_dte_addr); dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index); dte_addr = phys_to_virt(dte_addr_phys); @@ -966,7 +937,7 @@ static int rk_iommu_enable(struct rk_iommu *iommu) for (i = 0; i < iommu->num_mmu; i++) { rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, - rk_ops->dma_addr_dte(rk_domain->dt_dma)); + rk_ops->mk_dtentries(rk_domain->dt_dma)); rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE); rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK); } @@ -1373,8 +1344,6 @@ static struct rk_iommu_ops iommu_data_ops_v1 = { .pt_address = &rk_dte_pt_address, .mk_dtentries = &rk_mk_dte, .mk_ptentries = &rk_mk_pte, - .dte_addr_phys = &rk_dte_addr_phys, - .dma_addr_dte = &rk_dma_addr_dte, .dma_bit_mask = DMA_BIT_MASK(32), }; @@ -1382,8 +1351,6 @@ static struct rk_iommu_ops iommu_data_ops_v2 = { .pt_address = &rk_dte_pt_address_v2, .mk_dtentries = &rk_mk_dte_v2, .mk_ptentries = &rk_mk_pte_v2, - .dte_addr_phys = &rk_dte_addr_phys_v2, - .dma_addr_dte = &rk_dma_addr_dte_v2, .dma_bit_mask = DMA_BIT_MASK(40), }; From 90e0ea8e9b26613147922132467a36c0d5d7659f Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Mon, 27 Feb 2023 18:24:08 +0800 Subject: [PATCH 1075/2093] drivers: usb: smsusb: fix error handling code in smsusb_init_device [ Upstream commit b9c7141f384097fa4fa67d2f72e5731d628aef7c ] The previous commit 4b208f8b561f ("[media] siano: register media controller earlier")moves siano_media_device_register before smscore_register_device, and adds corresponding error handling code if smscore_register_device fails. However, it misses the following error handling code of smsusb_init_device. Fix this by moving error handling code at the end of smsusb_init_device and adding a goto statement in the following error handling parts. Fixes: 4b208f8b561f ("[media] siano: register media controller earlier") Signed-off-by: Dongliang Mu Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/siano/smsusb.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c index 640737d3b8ae..8a39cac76c58 100644 --- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -455,12 +455,7 @@ static int smsusb_init_device(struct usb_interface *intf, int board_id) rc = smscore_register_device(¶ms, &dev->coredev, 0, mdev); if (rc < 0) { pr_err("smscore_register_device(...) failed, rc %d\n", rc); - smsusb_term_device(intf); -#ifdef CONFIG_MEDIA_CONTROLLER_DVB - media_device_unregister(mdev); -#endif - kfree(mdev); - return rc; + goto err_unregister_device; } smscore_set_board_id(dev->coredev, board_id); @@ -477,8 +472,7 @@ static int smsusb_init_device(struct usb_interface *intf, int board_id) rc = smsusb_start_streaming(dev); if (rc < 0) { pr_err("smsusb_start_streaming(...) failed\n"); - smsusb_term_device(intf); - return rc; + goto err_unregister_device; } dev->state = SMSUSB_ACTIVE; @@ -486,13 +480,20 @@ static int smsusb_init_device(struct usb_interface *intf, int board_id) rc = smscore_start_device(dev->coredev); if (rc < 0) { pr_err("smscore_start_device(...) failed\n"); - smsusb_term_device(intf); - return rc; + goto err_unregister_device; } pr_debug("device 0x%p created\n", dev); return rc; + +err_unregister_device: + smsusb_term_device(intf); +#ifdef CONFIG_MEDIA_CONTROLLER_DVB + media_device_unregister(mdev); +#endif + kfree(mdev); + return rc; } static int smsusb_probe(struct usb_interface *intf, From 323ee5fc980bf4ef87f047ee6624dc915d221682 Mon Sep 17 00:00:00 2001 From: Daniil Dulov Date: Fri, 24 Mar 2023 06:38:32 -0700 Subject: [PATCH 1076/2093] media: dib7000p: Fix potential division by zero [ Upstream commit a1db7b2c5533fc67e2681eb5efc921a67bc7d5b8 ] Variable loopdiv can be assigned 0, then it is used as a denominator, without checking it for 0. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 713d54a8bd81 ("[media] DiB7090: add support for the dib7090 based") Signed-off-by: Daniil Dulov Signed-off-by: Hans Verkuil [hverkuil: (bw != NULL) -> bw] Signed-off-by: Sasha Levin --- drivers/media/dvb-frontends/dib7000p.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c index a90d2f51868f..632534eff0ff 100644 --- a/drivers/media/dvb-frontends/dib7000p.c +++ b/drivers/media/dvb-frontends/dib7000p.c @@ -497,7 +497,7 @@ static int dib7000p_update_pll(struct dvb_frontend *fe, struct dibx000_bandwidth prediv = reg_1856 & 0x3f; loopdiv = (reg_1856 >> 6) & 0x3f; - if ((bw != NULL) && (bw->pll_prediv != prediv || bw->pll_ratio != loopdiv)) { + if (loopdiv && bw && (bw->pll_prediv != prediv || bw->pll_ratio != loopdiv)) { dprintk("Updating pll (prediv: old = %d new = %d ; loopdiv : old = %d new = %d)\n", prediv, bw->pll_prediv, loopdiv, bw->pll_ratio); reg_1856 &= 0xf000; reg_1857 = dib7000p_read_word(state, 1857); From 2b6e20ef0585a467c24c7e4fde28518e5b33225a Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 29 May 2023 07:58:36 +0200 Subject: [PATCH 1077/2093] media: dvb-usb: m920x: Fix a potential memory leak in m920x_i2c_xfer() [ Upstream commit ea9ef6c2e001c5dc94bee35ebd1c8a98621cf7b8 ] 'read' is freed when it is known to be NULL, but not when a read error occurs. Revert the logic to avoid a small leak, should a m920x_read() call fail. Fixes: a2ab06d7c4d6 ("media: m920x: don't use stack on USB reads") Signed-off-by: Christophe JAILLET Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/m920x.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/media/usb/dvb-usb/m920x.c b/drivers/media/usb/dvb-usb/m920x.c index 548199cd86f6..11f4f0455f15 100644 --- a/drivers/media/usb/dvb-usb/m920x.c +++ b/drivers/media/usb/dvb-usb/m920x.c @@ -277,7 +277,6 @@ static int m920x_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int nu char *read = kmalloc(1, GFP_KERNEL); if (!read) { ret = -ENOMEM; - kfree(read); goto unlock; } @@ -288,8 +287,10 @@ static int m920x_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int nu if ((ret = m920x_read(d->udev, M9206_I2C, 0x0, 0x20 | stop, - read, 1)) != 0) + read, 1)) != 0) { + kfree(read); goto unlock; + } msg[i].buf[j] = read[0]; } From a96892a40fcef5f12c4e649be75106957a177e02 Mon Sep 17 00:00:00 2001 From: Daniil Dulov Date: Fri, 2 Jun 2023 01:55:01 -0700 Subject: [PATCH 1078/2093] media: cx24120: Add retval check for cx24120_message_send() [ Upstream commit 96002c0ac824e1773d3f706b1f92e2a9f2988047 ] If cx24120_message_send() returns error, we should keep local struct unchanged. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 5afc9a25be8d ("[media] Add support for TechniSat Skystar S2") Signed-off-by: Daniil Dulov Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/dvb-frontends/cx24120.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c index d8acd582c711..0f778660c72b 100644 --- a/drivers/media/dvb-frontends/cx24120.c +++ b/drivers/media/dvb-frontends/cx24120.c @@ -973,7 +973,9 @@ static void cx24120_set_clock_ratios(struct dvb_frontend *fe) cmd.arg[8] = (clock_ratios_table[idx].rate >> 8) & 0xff; cmd.arg[9] = (clock_ratios_table[idx].rate >> 0) & 0xff; - cx24120_message_send(state, &cmd); + ret = cx24120_message_send(state, &cmd); + if (ret != 0) + return; /* Calculate ber window rates for stat work */ cx24120_calculate_ber_window(state, clock_ratios_table[idx].rate); From 79a1a8f83869e31980231064c38bc4175761d71f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 17 Jul 2023 11:12:12 -0400 Subject: [PATCH 1079/2093] RDMA/siw: Fabricate a GID on tun and loopback devices [ Upstream commit bad5b6e34ffbaacc77ad28a0f482e33b3929e635 ] LOOPBACK and NONE (tunnel) devices have all-zero MAC addresses. Currently, siw_device_create() falls back to copying the IB device's name in those cases, because an all-zero MAC address breaks the RDMA core address resolution mechanism. However, at the point when siw_device_create() constructs a GID, the ib_device::name field is uninitialized, leaving the MAC address to remain in an all-zero state. Fabricate a random artificial GID for such devices, and ensure this artificial GID is returned for all device query operations. Link: https://lore.kernel.org/r/168960673260.3007.12378736853793339110.stgit@manet.1015granger.net Reported-by: Tom Talpey Fixes: a2d36b02c15d ("RDMA/siw: Enable siw on tunnel devices") Reviewed-by: Bernard Metzler Reviewed-by: Tom Talpey Signed-off-by: Chuck Lever Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw.h | 1 + drivers/infiniband/sw/siw/siw_main.c | 22 ++++++++-------------- drivers/infiniband/sw/siw/siw_verbs.c | 4 ++-- 3 files changed, 11 insertions(+), 16 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 2f3a9cda3850..8b4a710b82bc 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -74,6 +74,7 @@ struct siw_device { u32 vendor_part_id; int numa_node; + char raw_gid[ETH_ALEN]; /* physical port state (only one port per device) */ enum ib_port_state state; diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 65b5cda5457b..f45600d169ae 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -75,8 +75,7 @@ static int siw_device_register(struct siw_device *sdev, const char *name) return rv; } - siw_dbg(base_dev, "HWaddr=%pM\n", sdev->netdev->dev_addr); - + siw_dbg(base_dev, "HWaddr=%pM\n", sdev->raw_gid); return 0; } @@ -313,24 +312,19 @@ static struct siw_device *siw_device_create(struct net_device *netdev) return NULL; base_dev = &sdev->base_dev; - sdev->netdev = netdev; - if (netdev->type != ARPHRD_LOOPBACK && netdev->type != ARPHRD_NONE) { - addrconf_addr_eui48((unsigned char *)&base_dev->node_guid, - netdev->dev_addr); + if (netdev->addr_len) { + memcpy(sdev->raw_gid, netdev->dev_addr, + min_t(unsigned int, netdev->addr_len, ETH_ALEN)); } else { /* - * This device does not have a HW address, - * but connection mangagement lib expects gid != 0 + * This device does not have a HW address, but + * connection mangagement requires a unique gid. */ - size_t len = min_t(size_t, strlen(base_dev->name), 6); - char addr[6] = { }; - - memcpy(addr, base_dev->name, len); - addrconf_addr_eui48((unsigned char *)&base_dev->node_guid, - addr); + eth_random_addr(sdev->raw_gid); } + addrconf_addr_eui48((u8 *)&base_dev->node_guid, sdev->raw_gid); base_dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND); diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 906fde1a2a0d..2e4cdcd26fe0 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -157,7 +157,7 @@ int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr, attr->vendor_part_id = sdev->vendor_part_id; addrconf_addr_eui48((u8 *)&attr->sys_image_guid, - sdev->netdev->dev_addr); + sdev->raw_gid); return 0; } @@ -218,7 +218,7 @@ int siw_query_gid(struct ib_device *base_dev, u32 port, int idx, /* subnet_prefix == interface_id == 0; */ memset(gid, 0, sizeof(*gid)); - memcpy(&gid->raw[0], sdev->netdev->dev_addr, 6); + memcpy(gid->raw, sdev->raw_gid, ETH_ALEN); return 0; } From ab0719d7b6e4a068fd02ad5b9b8e578b7afaf71b Mon Sep 17 00:00:00 2001 From: Xingui Yang Date: Mon, 15 May 2023 10:41:21 +0800 Subject: [PATCH 1080/2093] scsi: hisi_sas: Fix warnings detected by sparse [ Upstream commit c0328cc595124579328462fc45d7a29a084cf357 ] This patch fixes the following warning: drivers/scsi/hisi_sas/hisi_sas_v3_hw.c:2168:43: sparse: sparse: restricted __le32 degrades to integer Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304161254.NztCVZIO-lkp@intel.com/ Signed-off-by: Xingui Yang Signed-off-by: Xiang Chen Link: https://lore.kernel.org/r/1684118481-95908-4-git-send-email-chenxiang66@hisilicon.com Signed-off-by: Martin K. Petersen Stable-dep-of: f5393a5602ca ("scsi: hisi_sas: Fix normally completed I/O analysed as failed") Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index e8a3511040af..8544c1554f5f 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2163,6 +2163,7 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, u32 trans_tx_fail_type = le32_to_cpu(record->trans_tx_fail_type); u16 sipc_rx_err_type = le16_to_cpu(record->sipc_rx_err_type); u32 dw3 = le32_to_cpu(complete_hdr->dw3); + u32 dw0 = le32_to_cpu(complete_hdr->dw0); switch (task->task_proto) { case SAS_PROTOCOL_SSP: @@ -2172,8 +2173,8 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, * but I/O information has been written to the host memory, we examine * response IU. */ - if (!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_GOOD_MSK) && - (complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) + if (!(dw0 & CMPLT_HDR_RSPNS_GOOD_MSK) && + (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) return false; ts->residual = trans_tx_fail_type; @@ -2189,7 +2190,7 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, case SAS_PROTOCOL_SATA: case SAS_PROTOCOL_STP: case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: - if ((complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && + if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && (sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) { ts->stat = SAS_PROTO_RESPONSE; } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { From dd0dadb93844c8675e953ca8f3e8d9ffd17db898 Mon Sep 17 00:00:00 2001 From: Xingui Yang Date: Tue, 11 Jul 2023 11:14:58 +0800 Subject: [PATCH 1081/2093] scsi: hisi_sas: Fix normally completed I/O analysed as failed [ Upstream commit f5393a5602cacfda2014e0ff8220e5a7564e7cd1 ] The PIO read command has no response frame and the struct iu[1024] won't be filled. I/Os which are normally completed will be treated as failed in sas_ata_task_done() when iu contains abnormal dirty data. Consequently ending_fis should not be filled by iu when the response frame hasn't been written to memory. Fixes: d380f55503ed ("scsi: hisi_sas: Don't bother clearing status buffer IU in task prep") Signed-off-by: Xingui Yang Signed-off-by: Xiang Chen Link: https://lore.kernel.org/r/1689045300-44318-2-git-send-email-chenxiang66@hisilicon.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 11 +++++++++-- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 6 ++++-- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 02575d81afca..50697672146a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2026,6 +2026,11 @@ static void slot_err_v2_hw(struct hisi_hba *hisi_hba, u16 dma_tx_err_type = le16_to_cpu(err_record->dma_tx_err_type); u16 sipc_rx_err_type = le16_to_cpu(err_record->sipc_rx_err_type); u32 dma_rx_err_type = le32_to_cpu(err_record->dma_rx_err_type); + struct hisi_sas_complete_v2_hdr *complete_queue = + hisi_hba->complete_hdr[slot->cmplt_queue]; + struct hisi_sas_complete_v2_hdr *complete_hdr = + &complete_queue[slot->cmplt_queue_slot]; + u32 dw0 = le32_to_cpu(complete_hdr->dw0); int error = -1; if (err_phase == 1) { @@ -2310,7 +2315,8 @@ static void slot_err_v2_hw(struct hisi_hba *hisi_hba, break; } } - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); } break; default: @@ -2443,7 +2449,8 @@ static void slot_complete_v2_hw(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: { ts->stat = SAS_SAM_STAT_GOOD; - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); break; } default: diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 8544c1554f5f..c0e74d768716 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2203,7 +2203,8 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, ts->stat = SAS_OPEN_REJECT; ts->open_rej_reason = SAS_OREJ_RSVD_RETRY; } - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); break; case SAS_PROTOCOL_SMP: ts->stat = SAS_SAM_STAT_CHECK_CONDITION; @@ -2330,7 +2331,8 @@ static void slot_complete_v3_hw(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_STP: case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: ts->stat = SAS_SAM_STAT_GOOD; - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); break; default: ts->stat = SAS_SAM_STAT_CHECK_CONDITION; From 6f0d0f5613d7e6d5bc12fd750c09d1de7029cd93 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Jul 2023 10:01:40 +0200 Subject: [PATCH 1082/2093] dt-bindings: extcon: maxim,max77843: restrict connector properties [ Upstream commit fb2c3f72e819254d8c76de95917e5f9ff232586c ] Do not allow any other properties in connector child, except what usb-connector.yaml evaluates. Fixes: 9729cad0278b ("dt-bindings: extcon: maxim,max77843: Add MAX77843 bindings") Signed-off-by: Krzysztof Kozlowski Signed-off-by: Chanwoo Choi Signed-off-by: Sasha Levin --- Documentation/devicetree/bindings/extcon/maxim,max77843.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml index 128960545640..55800fb0221d 100644 --- a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml @@ -23,6 +23,7 @@ properties: connector: $ref: /schemas/connector/usb-connector.yaml# + unevaluatedProperties: false ports: $ref: /schemas/graph.yaml#/properties/ports From 745f40a96c7f687e4d81b44f535661b0ff630bdb Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 13 Jun 2023 15:48:46 +0800 Subject: [PATCH 1083/2093] media: amphion: reinit vpu if reqbufs output 0 [ Upstream commit 73e3f09292a0492a3fe0f87a8170a74f12624c5e ] according to v4l2 stateful decoder document 4.5.1.3. State Machine, the state should change from seek to initialization if call VIDIOC_REQBUFS(OUTPUT, 0). so reinit the vpu decoder if reqbufs output 0 Fixes: 6de8d628df6e ("media: amphion: add v4l2 m2m vpu decoder stateful driver") Signed-off-by: Ming Qian Tested-by: Nicolas Dufresne Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vdec.c | 2 -- drivers/media/platform/amphion/vpu_v4l2.c | 7 ++++++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/amphion/vdec.c b/drivers/media/platform/amphion/vdec.c index c08b5a2bfc1d..8edb313cd635 100644 --- a/drivers/media/platform/amphion/vdec.c +++ b/drivers/media/platform/amphion/vdec.c @@ -1407,9 +1407,7 @@ static void vdec_release(struct vpu_inst *inst) { if (inst->id != VPU_INST_NULL_ID) vpu_trace(inst->dev, "[%d]\n", inst->id); - vpu_inst_lock(inst); vdec_stop(inst, true); - vpu_inst_unlock(inst); } static void vdec_cleanup(struct vpu_inst *inst) diff --git a/drivers/media/platform/amphion/vpu_v4l2.c b/drivers/media/platform/amphion/vpu_v4l2.c index a74953191c22..e5c8e1a753cc 100644 --- a/drivers/media/platform/amphion/vpu_v4l2.c +++ b/drivers/media/platform/amphion/vpu_v4l2.c @@ -404,6 +404,11 @@ static int vpu_vb2_queue_setup(struct vb2_queue *vq, for (i = 0; i < cur_fmt->num_planes; i++) psize[i] = cur_fmt->sizeimage[i]; + if (V4L2_TYPE_IS_OUTPUT(vq->type) && inst->state == VPU_CODEC_STATE_SEEK) { + vpu_trace(inst->dev, "reinit when VIDIOC_REQBUFS(OUTPUT, 0)\n"); + call_void_vop(inst, release); + } + return 0; } @@ -688,9 +693,9 @@ int vpu_v4l2_close(struct file *file) v4l2_m2m_ctx_release(inst->fh.m2m_ctx); inst->fh.m2m_ctx = NULL; } + call_void_vop(inst, release); vpu_inst_unlock(inst); - call_void_vop(inst, release); vpu_inst_unregister(inst); vpu_inst_put(inst); From 62ea218a7e7fe1222a122f5545044c76864700d0 Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 13 Jun 2023 17:14:08 +0800 Subject: [PATCH 1084/2093] media: amphion: add helper function to get id name [ Upstream commit 12cd8b8ac02525977b2e860a877add10e8ce7468 ] convert numbers into meaningful names, then it can improve the log readability Fixes: 9f599f351e86 ("media: amphion: add vpu core driver") Signed-off-by: Ming Qian Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vdec.c | 9 +-- drivers/media/platform/amphion/vpu.h | 3 + drivers/media/platform/amphion/vpu_cmds.c | 11 ++-- drivers/media/platform/amphion/vpu_dbg.c | 6 +- drivers/media/platform/amphion/vpu_helpers.c | 61 ++++++++++++++++++++ drivers/media/platform/amphion/vpu_msgs.c | 2 +- 6 files changed, 79 insertions(+), 13 deletions(-) diff --git a/drivers/media/platform/amphion/vdec.c b/drivers/media/platform/amphion/vdec.c index 8edb313cd635..b4cdd23c38af 100644 --- a/drivers/media/platform/amphion/vdec.c +++ b/drivers/media/platform/amphion/vdec.c @@ -249,7 +249,8 @@ static int vdec_update_state(struct vpu_inst *inst, enum vpu_codec_state state, vdec->state = VPU_CODEC_STATE_DYAMIC_RESOLUTION_CHANGE; if (inst->state != pre_state) - vpu_trace(inst->dev, "[%d] %d -> %d\n", inst->id, pre_state, inst->state); + vpu_trace(inst->dev, "[%d] %s -> %s\n", inst->id, + vpu_codec_state_name(pre_state), vpu_codec_state_name(inst->state)); if (inst->state == VPU_CODEC_STATE_DYAMIC_RESOLUTION_CHANGE) vdec_handle_resolution_change(inst); @@ -994,8 +995,8 @@ static int vdec_response_frame(struct vpu_inst *inst, struct vb2_v4l2_buffer *vb return -EINVAL; } - dev_dbg(inst->dev, "[%d] state = %d, alloc fs %d, tag = 0x%x\n", - inst->id, inst->state, vbuf->vb2_buf.index, vdec->seq_tag); + dev_dbg(inst->dev, "[%d] state = %s, alloc fs %d, tag = 0x%x\n", + inst->id, vpu_codec_state_name(inst->state), vbuf->vb2_buf.index, vdec->seq_tag); vpu_buf = to_vpu_vb2_buffer(vbuf); memset(&info, 0, sizeof(info)); @@ -1354,7 +1355,7 @@ static void vdec_abort(struct vpu_inst *inst) struct vpu_rpc_buffer_desc desc; int ret; - vpu_trace(inst->dev, "[%d] state = %d\n", inst->id, inst->state); + vpu_trace(inst->dev, "[%d] state = %s\n", inst->id, vpu_codec_state_name(inst->state)); vdec->aborting = true; vpu_iface_add_scode(inst, SCODE_PADDING_ABORT); diff --git a/drivers/media/platform/amphion/vpu.h b/drivers/media/platform/amphion/vpu.h index 048c23c2bf4d..deb2288d4290 100644 --- a/drivers/media/platform/amphion/vpu.h +++ b/drivers/media/platform/amphion/vpu.h @@ -353,6 +353,9 @@ void vpu_inst_record_flow(struct vpu_inst *inst, u32 flow); int vpu_core_driver_init(void); void vpu_core_driver_exit(void); +const char *vpu_id_name(u32 id); +const char *vpu_codec_state_name(enum vpu_codec_state state); + extern bool debug; #define vpu_trace(dev, fmt, arg...) \ do { \ diff --git a/drivers/media/platform/amphion/vpu_cmds.c b/drivers/media/platform/amphion/vpu_cmds.c index fa581ba6bab2..647d94554fb5 100644 --- a/drivers/media/platform/amphion/vpu_cmds.c +++ b/drivers/media/platform/amphion/vpu_cmds.c @@ -98,7 +98,7 @@ static struct vpu_cmd_t *vpu_alloc_cmd(struct vpu_inst *inst, u32 id, void *data cmd->id = id; ret = vpu_iface_pack_cmd(inst->core, cmd->pkt, inst->id, id, data); if (ret) { - dev_err(inst->dev, "iface pack cmd(%d) fail\n", id); + dev_err(inst->dev, "iface pack cmd %s fail\n", vpu_id_name(id)); vfree(cmd->pkt); vfree(cmd); return NULL; @@ -125,14 +125,14 @@ static int vpu_session_process_cmd(struct vpu_inst *inst, struct vpu_cmd_t *cmd) { int ret; - dev_dbg(inst->dev, "[%d]send cmd(0x%x)\n", inst->id, cmd->id); + dev_dbg(inst->dev, "[%d]send cmd %s\n", inst->id, vpu_id_name(cmd->id)); vpu_iface_pre_send_cmd(inst); ret = vpu_cmd_send(inst->core, cmd->pkt); if (!ret) { vpu_iface_post_send_cmd(inst); vpu_inst_record_flow(inst, cmd->id); } else { - dev_err(inst->dev, "[%d] iface send cmd(0x%x) fail\n", inst->id, cmd->id); + dev_err(inst->dev, "[%d] iface send cmd %s fail\n", inst->id, vpu_id_name(cmd->id)); } return ret; @@ -149,7 +149,8 @@ static void vpu_process_cmd_request(struct vpu_inst *inst) list_for_each_entry_safe(cmd, tmp, &inst->cmd_q, list) { list_del_init(&cmd->list); if (vpu_session_process_cmd(inst, cmd)) - dev_err(inst->dev, "[%d] process cmd(%d) fail\n", inst->id, cmd->id); + dev_err(inst->dev, "[%d] process cmd %s fail\n", + inst->id, vpu_id_name(cmd->id)); if (cmd->request) { inst->pending = (void *)cmd; break; @@ -339,7 +340,7 @@ static int vpu_session_send_cmd(struct vpu_inst *inst, u32 id, void *data) exit: if (ret) - dev_err(inst->dev, "[%d] send cmd(0x%x) fail\n", inst->id, id); + dev_err(inst->dev, "[%d] send cmd %s fail\n", inst->id, vpu_id_name(id)); return ret; } diff --git a/drivers/media/platform/amphion/vpu_dbg.c b/drivers/media/platform/amphion/vpu_dbg.c index 260f1c4b8f8d..bf8aded76e14 100644 --- a/drivers/media/platform/amphion/vpu_dbg.c +++ b/drivers/media/platform/amphion/vpu_dbg.c @@ -67,7 +67,7 @@ static int vpu_dbg_instance(struct seq_file *s, void *data) num = scnprintf(str, sizeof(str), "tgig = %d,pid = %d\n", inst->tgid, inst->pid); if (seq_write(s, str, num)) return 0; - num = scnprintf(str, sizeof(str), "state = %d\n", inst->state); + num = scnprintf(str, sizeof(str), "state = %s\n", vpu_codec_state_name(inst->state)); if (seq_write(s, str, num)) return 0; num = scnprintf(str, sizeof(str), @@ -188,9 +188,9 @@ static int vpu_dbg_instance(struct seq_file *s, void *data) if (!inst->flows[idx]) continue; - num = scnprintf(str, sizeof(str), "\t[%s]0x%x\n", + num = scnprintf(str, sizeof(str), "\t[%s] %s\n", inst->flows[idx] >= VPU_MSG_ID_NOOP ? "M" : "C", - inst->flows[idx]); + vpu_id_name(inst->flows[idx])); if (seq_write(s, str, num)) { mutex_unlock(&inst->core->cmd_lock); return 0; diff --git a/drivers/media/platform/amphion/vpu_helpers.c b/drivers/media/platform/amphion/vpu_helpers.c index e9aeb3453dfc..2e78666322f0 100644 --- a/drivers/media/platform/amphion/vpu_helpers.c +++ b/drivers/media/platform/amphion/vpu_helpers.c @@ -11,6 +11,7 @@ #include #include #include "vpu.h" +#include "vpu_defs.h" #include "vpu_core.h" #include "vpu_rpc.h" #include "vpu_helpers.h" @@ -412,3 +413,63 @@ int vpu_find_src_by_dst(struct vpu_pair *pairs, u32 cnt, u32 dst) return -EINVAL; } + +const char *vpu_id_name(u32 id) +{ + switch (id) { + case VPU_CMD_ID_NOOP: return "noop"; + case VPU_CMD_ID_CONFIGURE_CODEC: return "configure codec"; + case VPU_CMD_ID_START: return "start"; + case VPU_CMD_ID_STOP: return "stop"; + case VPU_CMD_ID_ABORT: return "abort"; + case VPU_CMD_ID_RST_BUF: return "reset buf"; + case VPU_CMD_ID_SNAPSHOT: return "snapshot"; + case VPU_CMD_ID_FIRM_RESET: return "reset firmware"; + case VPU_CMD_ID_UPDATE_PARAMETER: return "update parameter"; + case VPU_CMD_ID_FRAME_ENCODE: return "encode frame"; + case VPU_CMD_ID_SKIP: return "skip"; + case VPU_CMD_ID_FS_ALLOC: return "alloc fb"; + case VPU_CMD_ID_FS_RELEASE: return "release fb"; + case VPU_CMD_ID_TIMESTAMP: return "timestamp"; + case VPU_CMD_ID_DEBUG: return "debug"; + case VPU_MSG_ID_RESET_DONE: return "reset done"; + case VPU_MSG_ID_START_DONE: return "start done"; + case VPU_MSG_ID_STOP_DONE: return "stop done"; + case VPU_MSG_ID_ABORT_DONE: return "abort done"; + case VPU_MSG_ID_BUF_RST: return "buf reset done"; + case VPU_MSG_ID_MEM_REQUEST: return "mem request"; + case VPU_MSG_ID_PARAM_UPD_DONE: return "param upd done"; + case VPU_MSG_ID_FRAME_INPUT_DONE: return "frame input done"; + case VPU_MSG_ID_ENC_DONE: return "encode done"; + case VPU_MSG_ID_DEC_DONE: return "frame display"; + case VPU_MSG_ID_FRAME_REQ: return "fb request"; + case VPU_MSG_ID_FRAME_RELEASE: return "fb release"; + case VPU_MSG_ID_SEQ_HDR_FOUND: return "seq hdr found"; + case VPU_MSG_ID_RES_CHANGE: return "resolution change"; + case VPU_MSG_ID_PIC_HDR_FOUND: return "pic hdr found"; + case VPU_MSG_ID_PIC_DECODED: return "picture decoded"; + case VPU_MSG_ID_PIC_EOS: return "eos"; + case VPU_MSG_ID_FIFO_LOW: return "fifo low"; + case VPU_MSG_ID_BS_ERROR: return "bs error"; + case VPU_MSG_ID_UNSUPPORTED: return "unsupported"; + case VPU_MSG_ID_FIRMWARE_XCPT: return "exception"; + case VPU_MSG_ID_PIC_SKIPPED: return "skipped"; + } + return ""; +} + +const char *vpu_codec_state_name(enum vpu_codec_state state) +{ + switch (state) { + case VPU_CODEC_STATE_DEINIT: return "initialization"; + case VPU_CODEC_STATE_CONFIGURED: return "configured"; + case VPU_CODEC_STATE_START: return "start"; + case VPU_CODEC_STATE_STARTED: return "started"; + case VPU_CODEC_STATE_ACTIVE: return "active"; + case VPU_CODEC_STATE_SEEK: return "seek"; + case VPU_CODEC_STATE_STOP: return "stop"; + case VPU_CODEC_STATE_DRAIN: return "drain"; + case VPU_CODEC_STATE_DYAMIC_RESOLUTION_CHANGE: return "resolution change"; + } + return ""; +} diff --git a/drivers/media/platform/amphion/vpu_msgs.c b/drivers/media/platform/amphion/vpu_msgs.c index 92672a802b49..f9eb488d1b5e 100644 --- a/drivers/media/platform/amphion/vpu_msgs.c +++ b/drivers/media/platform/amphion/vpu_msgs.c @@ -210,7 +210,7 @@ static int vpu_session_handle_msg(struct vpu_inst *inst, struct vpu_rpc_event *m return -EINVAL; msg_id = ret; - dev_dbg(inst->dev, "[%d] receive event(0x%x)\n", inst->id, msg_id); + dev_dbg(inst->dev, "[%d] receive event(%s)\n", inst->id, vpu_id_name(msg_id)); for (i = 0; i < ARRAY_SIZE(handlers); i++) { if (handlers[i].id == msg_id) { From 715c0200b4809396998e562ce5cd0284e7314cc1 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Fri, 7 Jul 2023 17:24:14 +0800 Subject: [PATCH 1085/2093] media: mtk-jpeg: Fix use after free bug due to uncanceled work [ Upstream commit c677d7ae83141d390d1253abebafa49c962afb52 ] In mtk_jpeg_probe, &jpeg->job_timeout_work is bound with mtk_jpeg_job_timeout_work. Then mtk_jpeg_dec_device_run and mtk_jpeg_enc_device_run may be called to start the work. If we remove the module which will call mtk_jpeg_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows, which will cause a typical UAF bug. Fix it by canceling the work before cleanup in the mtk_jpeg_remove CPU0 CPU1 |mtk_jpeg_job_timeout_work mtk_jpeg_remove | v4l2_m2m_release | kfree(m2m_dev); | | | v4l2_m2m_get_curr_priv | m2m_dev->curr_ctx //use Fixes: b2f0d2724ba4 ("[media] vcodec: mediatek: Add Mediatek JPEG Decoder Driver") Signed-off-by: Zheng Wang Reviewed-by: Alexandre Mergnat Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c index 3071b61946c3..e9a4f8abd21c 100644 --- a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c @@ -1412,6 +1412,7 @@ static int mtk_jpeg_remove(struct platform_device *pdev) { struct mtk_jpeg_dev *jpeg = platform_get_drvdata(pdev); + cancel_delayed_work_sync(&jpeg->job_timeout_work); pm_runtime_disable(&pdev->dev); video_unregister_device(jpeg->vdev); v4l2_m2m_release(jpeg->m2m_dev); From 9ada33ee83dd3e296a1ba16680daecf3255097fc Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Mon, 17 Jul 2023 17:06:11 +0200 Subject: [PATCH 1086/2093] media: rkvdec: increase max supported height for H.264 [ Upstream commit f000e6ca2d60fefd02a180a57df2c4162fa0c1b7 ] After testing it is possible for the hardware to decode H264 bistream with a height up to 2560. Signed-off-by: Benjamin Gaignard Fixes: cd33c830448ba ("media: rkvdec: Add the rkvdec driver") Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/staging/media/rkvdec/rkvdec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index 82806f198074..a9bd1e71ea48 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -120,7 +120,7 @@ static const struct rkvdec_coded_fmt_desc rkvdec_coded_fmts[] = { .max_width = 4096, .step_width = 16, .min_height = 48, - .max_height = 2304, + .max_height = 2560, .step_height = 16, }, .ctrls = &rkvdec_h264_ctrls, From 3930d62f5d7c0ce39088c57fab0070df085c8f70 Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 18 Jul 2023 17:50:09 +0800 Subject: [PATCH 1087/2093] media: amphion: fix CHECKED_RETURN issues reported by coverity [ Upstream commit b237b058adbc7825da9c8f358f1ff3f0467d623a ] calling "vpu_cmd_send/vpu_get_buffer_state/vpu_session_alloc_fs" without checking return value Fixes: 9f599f351e86 ("media: amphion: add vpu core driver") Reviewed-by: Nicolas Dufresne Signed-off-by: Ming Qian Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vdec.c | 5 ++++- drivers/media/platform/amphion/vpu_cmds.c | 3 ++- drivers/media/platform/amphion/vpu_dbg.c | 11 +++++++++-- 3 files changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/media/platform/amphion/vdec.c b/drivers/media/platform/amphion/vdec.c index b4cdd23c38af..dc35a87e628e 100644 --- a/drivers/media/platform/amphion/vdec.c +++ b/drivers/media/platform/amphion/vdec.c @@ -957,6 +957,7 @@ static int vdec_response_frame_abnormal(struct vpu_inst *inst) { struct vdec_t *vdec = inst->priv; struct vpu_fs_info info; + int ret; if (!vdec->req_frame_count) return 0; @@ -964,7 +965,9 @@ static int vdec_response_frame_abnormal(struct vpu_inst *inst) memset(&info, 0, sizeof(info)); info.type = MEM_RES_FRAME; info.tag = vdec->seq_tag + 0xf0; - vpu_session_alloc_fs(inst, &info); + ret = vpu_session_alloc_fs(inst, &info); + if (ret) + return ret; vdec->req_frame_count--; return 0; diff --git a/drivers/media/platform/amphion/vpu_cmds.c b/drivers/media/platform/amphion/vpu_cmds.c index 647d94554fb5..7e137f276c3b 100644 --- a/drivers/media/platform/amphion/vpu_cmds.c +++ b/drivers/media/platform/amphion/vpu_cmds.c @@ -306,7 +306,8 @@ static void vpu_core_keep_active(struct vpu_core *core) dev_dbg(core->dev, "try to wake up\n"); mutex_lock(&core->cmd_lock); - vpu_cmd_send(core, &pkt); + if (vpu_cmd_send(core, &pkt)) + dev_err(core->dev, "fail to keep active\n"); mutex_unlock(&core->cmd_lock); } diff --git a/drivers/media/platform/amphion/vpu_dbg.c b/drivers/media/platform/amphion/vpu_dbg.c index bf8aded76e14..f105da82d92f 100644 --- a/drivers/media/platform/amphion/vpu_dbg.c +++ b/drivers/media/platform/amphion/vpu_dbg.c @@ -50,6 +50,13 @@ static char *vpu_stat_name[] = { [VPU_BUF_STATE_ERROR] = "error", }; +static inline const char *to_vpu_stat_name(int state) +{ + if (state <= VPU_BUF_STATE_ERROR) + return vpu_stat_name[state]; + return "unknown"; +} + static int vpu_dbg_instance(struct seq_file *s, void *data) { struct vpu_inst *inst = s->private; @@ -141,7 +148,7 @@ static int vpu_dbg_instance(struct seq_file *s, void *data) num = scnprintf(str, sizeof(str), "output [%2d] state = %10s, %8s\n", i, vb2_stat_name[vb->state], - vpu_stat_name[vpu_get_buffer_state(vbuf)]); + to_vpu_stat_name(vpu_get_buffer_state(vbuf))); if (seq_write(s, str, num)) return 0; } @@ -156,7 +163,7 @@ static int vpu_dbg_instance(struct seq_file *s, void *data) num = scnprintf(str, sizeof(str), "capture[%2d] state = %10s, %8s\n", i, vb2_stat_name[vb->state], - vpu_stat_name[vpu_get_buffer_state(vbuf)]); + to_vpu_stat_name(vpu_get_buffer_state(vbuf))); if (seq_write(s, str, num)) return 0; } From bddd678fd2864b435d00d51a4d3808a0d89c79de Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 18 Jul 2023 17:50:10 +0800 Subject: [PATCH 1088/2093] media: amphion: fix REVERSE_INULL issues reported by coverity [ Upstream commit 79d3bafaecc13bccab1ebbd28a15e669c5a4cdaf ] null-checking of a pointor is suggested before dereferencing it Fixes: 9f599f351e86 ("media: amphion: add vpu core driver") Reviewed-by: Nicolas Dufresne Signed-off-by: Ming Qian Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/venc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/amphion/venc.c b/drivers/media/platform/amphion/venc.c index e8cb22da938e..1df2b35c1a24 100644 --- a/drivers/media/platform/amphion/venc.c +++ b/drivers/media/platform/amphion/venc.c @@ -278,7 +278,7 @@ static int venc_g_parm(struct file *file, void *fh, struct v4l2_streamparm *parm { struct vpu_inst *inst = to_inst(file); struct venc_t *venc = inst->priv; - struct v4l2_fract *timeperframe = &parm->parm.capture.timeperframe; + struct v4l2_fract *timeperframe; if (!parm) return -EINVAL; @@ -289,6 +289,7 @@ static int venc_g_parm(struct file *file, void *fh, struct v4l2_streamparm *parm if (!vpu_helper_check_type(inst, parm->type)) return -EINVAL; + timeperframe = &parm->parm.capture.timeperframe; parm->parm.capture.capability = V4L2_CAP_TIMEPERFRAME; parm->parm.capture.readbuffers = 0; timeperframe->numerator = venc->params.frame_rate.numerator; @@ -301,7 +302,7 @@ static int venc_s_parm(struct file *file, void *fh, struct v4l2_streamparm *parm { struct vpu_inst *inst = to_inst(file); struct venc_t *venc = inst->priv; - struct v4l2_fract *timeperframe = &parm->parm.capture.timeperframe; + struct v4l2_fract *timeperframe; unsigned long n, d; if (!parm) @@ -313,6 +314,7 @@ static int venc_s_parm(struct file *file, void *fh, struct v4l2_streamparm *parm if (!vpu_helper_check_type(inst, parm->type)) return -EINVAL; + timeperframe = &parm->parm.capture.timeperframe; if (!timeperframe->numerator) timeperframe->numerator = venc->params.frame_rate.numerator; if (!timeperframe->denominator) From 60f6392bdede45e5bc966cbbe93a6597ac0c11e4 Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 18 Jul 2023 17:50:11 +0800 Subject: [PATCH 1089/2093] media: amphion: fix UNINIT issues reported by coverity [ Upstream commit c224d0497a31ea2d173e1ea16af308945bff9037 ] using uninitialized value may introduce risk Fixes: 9f599f351e86 ("media: amphion: add vpu core driver") Reviewed-by: Nicolas Dufresne Signed-off-by: Ming Qian Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vpu_msgs.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/media/platform/amphion/vpu_msgs.c b/drivers/media/platform/amphion/vpu_msgs.c index f9eb488d1b5e..d0ead051f7d1 100644 --- a/drivers/media/platform/amphion/vpu_msgs.c +++ b/drivers/media/platform/amphion/vpu_msgs.c @@ -32,7 +32,7 @@ static void vpu_session_handle_start_done(struct vpu_inst *inst, struct vpu_rpc_ static void vpu_session_handle_mem_request(struct vpu_inst *inst, struct vpu_rpc_event *pkt) { - struct vpu_pkt_mem_req_data req_data; + struct vpu_pkt_mem_req_data req_data = { 0 }; vpu_iface_unpack_msg_data(inst->core, pkt, (void *)&req_data); vpu_trace(inst->dev, "[%d] %d:%d %d:%d %d:%d\n", @@ -80,7 +80,7 @@ static void vpu_session_handle_resolution_change(struct vpu_inst *inst, struct v static void vpu_session_handle_enc_frame_done(struct vpu_inst *inst, struct vpu_rpc_event *pkt) { - struct vpu_enc_pic_info info; + struct vpu_enc_pic_info info = { 0 }; vpu_iface_unpack_msg_data(inst->core, pkt, (void *)&info); dev_dbg(inst->dev, "[%d] frame id = %d, wptr = 0x%x, size = %d\n", @@ -90,7 +90,7 @@ static void vpu_session_handle_enc_frame_done(struct vpu_inst *inst, struct vpu_ static void vpu_session_handle_frame_request(struct vpu_inst *inst, struct vpu_rpc_event *pkt) { - struct vpu_fs_info fs; + struct vpu_fs_info fs = { 0 }; vpu_iface_unpack_msg_data(inst->core, pkt, &fs); call_void_vop(inst, event_notify, VPU_MSG_ID_FRAME_REQ, &fs); @@ -107,7 +107,7 @@ static void vpu_session_handle_frame_release(struct vpu_inst *inst, struct vpu_r info.type = inst->out_format.type; call_void_vop(inst, buf_done, &info); } else if (inst->core->type == VPU_CORE_TYPE_DEC) { - struct vpu_fs_info fs; + struct vpu_fs_info fs = { 0 }; vpu_iface_unpack_msg_data(inst->core, pkt, &fs); call_void_vop(inst, event_notify, VPU_MSG_ID_FRAME_RELEASE, &fs); @@ -122,7 +122,7 @@ static void vpu_session_handle_input_done(struct vpu_inst *inst, struct vpu_rpc_ static void vpu_session_handle_pic_decoded(struct vpu_inst *inst, struct vpu_rpc_event *pkt) { - struct vpu_dec_pic_info info; + struct vpu_dec_pic_info info = { 0 }; vpu_iface_unpack_msg_data(inst->core, pkt, (void *)&info); call_void_vop(inst, get_one_frame, &info); @@ -130,7 +130,7 @@ static void vpu_session_handle_pic_decoded(struct vpu_inst *inst, struct vpu_rpc static void vpu_session_handle_pic_done(struct vpu_inst *inst, struct vpu_rpc_event *pkt) { - struct vpu_dec_pic_info info; + struct vpu_dec_pic_info info = { 0 }; struct vpu_frame_info frame; memset(&frame, 0, sizeof(frame)); From 932d84a8a808bc8f4eed85335fdafce119a60ddd Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 18 Jul 2023 17:50:12 +0800 Subject: [PATCH 1090/2093] media: amphion: fix UNUSED_VALUE issue reported by coverity [ Upstream commit cf6a06354989c41b536be8e094561ee16223cf1f ] assign value '-EINVAL' to ret, but the stored value is overwritten before it can be used Fixes: 9f599f351e86 ("media: amphion: add vpu core driver") Reviewed-by: Nicolas Dufresne Signed-off-by: Ming Qian Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vpu_cmds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/amphion/vpu_cmds.c b/drivers/media/platform/amphion/vpu_cmds.c index 7e137f276c3b..235b71398d40 100644 --- a/drivers/media/platform/amphion/vpu_cmds.c +++ b/drivers/media/platform/amphion/vpu_cmds.c @@ -315,7 +315,7 @@ static int vpu_session_send_cmd(struct vpu_inst *inst, u32 id, void *data) { unsigned long key; int sync = false; - int ret = -EINVAL; + int ret; if (inst->id < 0) return -EINVAL; From b4ee61e5a11004d5df8d0582f460dd537153405a Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Tue, 18 Jul 2023 17:50:13 +0800 Subject: [PATCH 1091/2093] media: amphion: ensure the bitops don't cross boundaries [ Upstream commit 5bd28eae48589694ff4e5badb03bf75dae695b3f ] the supported_instance_count determine the instance index range, it shouldn't exceed the bits number of instance_mask, otherwise the bitops of instance_mask may cross boundaries Fixes: 9f599f351e86 ("media: amphion: add vpu core driver") Reviewed-by: Nicolas Dufresne Signed-off-by: Ming Qian Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/amphion/vpu_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/amphion/vpu_core.c b/drivers/media/platform/amphion/vpu_core.c index be8041068268..9add73b9b45f 100644 --- a/drivers/media/platform/amphion/vpu_core.c +++ b/drivers/media/platform/amphion/vpu_core.c @@ -88,6 +88,8 @@ static int vpu_core_boot_done(struct vpu_core *core) core->supported_instance_count = min(core->supported_instance_count, count); } + if (core->supported_instance_count >= BITS_PER_TYPE(core->instance_mask)) + core->supported_instance_count = BITS_PER_TYPE(core->instance_mask); core->fw_version = fw_version; vpu_core_set_state(core, VPU_CORE_ACTIVE); From a356b60031d11d36dd2fdad365a6c24889ff8f22 Mon Sep 17 00:00:00 2001 From: Irui Wang Date: Wed, 5 Jul 2023 17:14:41 +0800 Subject: [PATCH 1092/2093] media: mediatek: vcodec: Return NULL if no vdec_fb is found [ Upstream commit dfa2d6e07432270330ae191f50a0e70636a4cd2b ] "fb_use_list" is used to store used or referenced frame buffers for vp9 stateful decoder. "NULL" should be returned when getting target frame buffer failed from "fb_use_list", not a random unexpected one. Fixes: f77e89854b3e ("[media] vcodec: mediatek: Add Mediatek VP9 Video Decoder Driver") Signed-off-by: Irui Wang Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_if.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_if.c index 70b8383f7c8e..a27a109d8d14 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_if.c +++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_if.c @@ -226,10 +226,11 @@ static struct vdec_fb *vp9_rm_from_fb_use_list(struct vdec_vp9_inst if (fb->base_y.va == addr) { list_move_tail(&node->list, &inst->available_fb_node_list); - break; + return fb; } } - return fb; + + return NULL; } static void vp9_add_to_fb_free_list(struct vdec_vp9_inst *inst, From bdc00039fd1bc1ebc9f7bebc75b13a81cd2e01bb Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 14 Jun 2023 16:05:39 +0300 Subject: [PATCH 1093/2093] media: mediatek: vcodec: fix potential double free [ Upstream commit be40f524b6edac4fb9a98ef79620fd9b9497a998 ] The "lat_buf->private_data" needs to be set to NULL to prevent a double free. How this would happen is if vdec_msg_queue_init() failed twice in a row and on the second time it failed earlier than on the first time. The vdec_msg_queue_init() function has a loop which does: for (i = 0; i < NUM_BUFFER_COUNT; i++) { Each iteration initializes one element in the msg_queue->lat_buf[] array and then the clean up function vdec_msg_queue_deinit() frees each element of the msg_queue->lat_buf[] array. This clean up code relies on the assumption that every element is either initialized or zeroed. Leaving a freed pointer which is non-zero breaks the assumption. Fixes: b199fe46f35c ("media: mtk-vcodec: Add msg queue feature for lat and core architecture") Signed-off-by: Dan Carpenter Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c index 03f8d7cd8edd..675f62814f94 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c +++ b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c @@ -246,6 +246,7 @@ void vdec_msg_queue_deinit(struct vdec_msg_queue *msg_queue, mtk_vcodec_mem_free(ctx, mem); kfree(lat_buf->private_data); + lat_buf->private_data = NULL; } } From 858322c409e0aba8f70810d23f35c482744f007c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 14 Jun 2023 16:06:47 +0300 Subject: [PATCH 1094/2093] media: mediatek: vcodec: fix resource leaks in vdec_msg_queue_init() [ Upstream commit cf10b0bb503c974ba049d6f888b21178be20a962 ] If we encounter any error in the vdec_msg_queue_init() then we need to set "msg_queue->wdma_addr.size = 0;". Normally, this is done inside the vdec_msg_queue_deinit() function. However, if the first call to allocate &msg_queue->wdma_addr fails, then the vdec_msg_queue_deinit() function is a no-op. For that situation, just set the size to zero explicitly and return. There were two other error paths which did not clean up before returning. Change those error paths to goto mem_alloc_err. Fixes: b199fe46f35c ("media: mtk-vcodec: Add msg queue feature for lat and core architecture") Fixes: 2f5d0aef37c6 ("media: mediatek: vcodec: support stateless AV1 decoder") Signed-off-by: Dan Carpenter Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c index 675f62814f94..a81212c0ade9 100644 --- a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c +++ b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c @@ -313,6 +313,7 @@ int vdec_msg_queue_init(struct vdec_msg_queue *msg_queue, err = mtk_vcodec_mem_alloc(ctx, &msg_queue->wdma_addr); if (err) { mtk_v4l2_err("failed to allocate wdma_addr buf"); + msg_queue->wdma_addr.size = 0; return -ENOMEM; } msg_queue->wdma_rptr_addr = msg_queue->wdma_addr.dma_addr; From 67b02818e209c4e544f3ada4f75383e2ca7ac5ef Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Tue, 27 Jun 2023 19:03:52 +0800 Subject: [PATCH 1095/2093] usb: phy: mxs: fix getting wrong state with mxs_phy_is_otg_host() [ Upstream commit 5eda42aebb7668b4dcff025cd3ccb0d3d7c53da6 ] The function mxs_phy_is_otg_host() will return true if OTG_ID_VALUE is 0 at USBPHY_CTRL register. However, OTG_ID_VALUE will not reflect the real state if the ID pin is float, such as Host-only or Type-C cases. The value of OTG_ID_VALUE is always 1 which means device mode. This patch will fix the issue by judging the current mode based on last_event. The controller will update last_event in time. Fixes: 7b09e67639d6 ("usb: phy: mxs: refine mxs_phy_disconnect_line") Signed-off-by: Xu Yang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20230627110353.1879477-2-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/phy/phy-mxs-usb.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c index d2836ef5d15c..9299df53eb9d 100644 --- a/drivers/usb/phy/phy-mxs-usb.c +++ b/drivers/usb/phy/phy-mxs-usb.c @@ -388,14 +388,8 @@ static void __mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool disconnect) static bool mxs_phy_is_otg_host(struct mxs_phy *mxs_phy) { - void __iomem *base = mxs_phy->phy.io_priv; - u32 phyctrl = readl(base + HW_USBPHY_CTRL); - - if (IS_ENABLED(CONFIG_USB_OTG) && - !(phyctrl & BM_USBPHY_CTRL_OTG_ID_VALUE)) - return true; - - return false; + return IS_ENABLED(CONFIG_USB_OTG) && + mxs_phy->phy.last_event == USB_EVENT_ID; } static void mxs_phy_disconnect_line(struct mxs_phy *mxs_phy, bool on) From bdc4f8f6817148a56ac1deeca8e08502178f1cfa Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 24 Jul 2023 13:08:30 -0700 Subject: [PATCH 1096/2093] scsi: RDMA/srp: Fix residual handling [ Upstream commit 89e637c19b2441aabc8dbf22a8745b932fd6996e ] Although the code for residual handling in the SRP initiator follows the SCSI documentation, that documentation has never been correct. Because scsi_finish_command() starts from the data buffer length and subtracts the residual, scsi_set_resid() must not be called if a residual overflow occurs. Hence remove the scsi_set_resid() calls from the SRP initiator if a residual overflow occurrs. Cc: Leon Romanovsky Cc: Jason Gunthorpe Fixes: 9237f04e12cc ("scsi: core: Fix scsi_get/set_resid() interface") Fixes: e714531a349f ("IB/srp: Fix residual handling") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230724200843.3376570-3-bvanassche@acm.org Acked-by: Leon Romanovsky Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/srp/ib_srp.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index b4d6a4a5ae81..a7580c4855fe 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1984,12 +1984,8 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp) if (unlikely(rsp->flags & SRP_RSP_FLAG_DIUNDER)) scsi_set_resid(scmnd, be32_to_cpu(rsp->data_in_res_cnt)); - else if (unlikely(rsp->flags & SRP_RSP_FLAG_DIOVER)) - scsi_set_resid(scmnd, -be32_to_cpu(rsp->data_in_res_cnt)); else if (unlikely(rsp->flags & SRP_RSP_FLAG_DOUNDER)) scsi_set_resid(scmnd, be32_to_cpu(rsp->data_out_res_cnt)); - else if (unlikely(rsp->flags & SRP_RSP_FLAG_DOOVER)) - scsi_set_resid(scmnd, -be32_to_cpu(rsp->data_out_res_cnt)); srp_free_req(ch, req, scmnd, be32_to_cpu(rsp->req_lim_delta)); From 2737d82760ae4c5c51000454def6633d93d69484 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Tue, 22 Nov 2022 18:11:05 +0000 Subject: [PATCH 1097/2093] scsi: iscsi: Rename iscsi_set_param() to iscsi_if_set_param() [ Upstream commit 0c26a2d7c98039e913e63f9250fde738a3f88a60 ] There are two iscsi_set_param() functions defined in libiscsi.c and scsi_transport_iscsi.c respectively which is confusing. Rename the one in scsi_transport_iscsi.c to iscsi_if_set_param(). Signed-off-by: Wenchao Hao Link: https://lore.kernel.org/r/20221122181105.4123935-1-haowenchao@huawei.com Reviewed-by: Mike Christie Reviewed-by: Lee Duncan Signed-off-by: Martin K. Petersen Stable-dep-of: 971dfcb74a80 ("scsi: iscsi: Add length check for nlattr payload") Signed-off-by: Sasha Levin --- drivers/scsi/scsi_transport_iscsi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index bf834e72595a..b9b97300e3b3 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3013,7 +3013,7 @@ iscsi_if_destroy_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev } static int -iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) +iscsi_if_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) { char *data = (char*)ev + sizeof(*ev); struct iscsi_cls_conn *conn; @@ -3966,7 +3966,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) err = -EINVAL; break; case ISCSI_UEVENT_SET_PARAM: - err = iscsi_set_param(transport, ev); + err = iscsi_if_set_param(transport, ev); break; case ISCSI_UEVENT_CREATE_CONN: case ISCSI_UEVENT_DESTROY_CONN: From bb8d101b835a13d3fb6c4380e76c5558bad690d6 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 25 Jul 2023 10:45:29 +0800 Subject: [PATCH 1098/2093] scsi: iscsi: Add length check for nlattr payload [ Upstream commit 971dfcb74a800047952f5288512b9c7ddedb050a ] The current NETLINK_ISCSI netlink parsing loop checks every nlmsg to make sure the length is bigger than sizeof(struct iscsi_uevent) and then calls iscsi_if_recv_msg(). nlh = nlmsg_hdr(skb); if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || skb->len < nlh->nlmsg_len) { break; } ... err = iscsi_if_recv_msg(skb, nlh, &group); Hence, in iscsi_if_recv_msg() the nlmsg_data can be safely converted to iscsi_uevent as the length is already checked. However, in other cases the length of nlattr payload is not checked before the payload is converted to other data structures. One example is iscsi_set_path() which converts the payload to type iscsi_path without any checks: params = (struct iscsi_path *)((char *)ev + sizeof(*ev)); Whereas iscsi_if_transport_conn() correctly checks the pdu_len: pdu_len = nlh->nlmsg_len - sizeof(*nlh) - sizeof(*ev); if ((ev->u.send_pdu.hdr_size > pdu_len) .. err = -EINVAL; To sum up, some code paths called in iscsi_if_recv_msg() do not check the length of the data (see below picture) and directly convert the data to another data structure. This could result in an out-of-bound reads and heap dirty data leakage. _________ nlmsg_len(nlh) _______________ / \ +----------+--------------+---------------------------+ | nlmsghdr | iscsi_uevent | data | +----------+--------------+---------------------------+ \ / iscsi_uevent->u.set_param.len Fix the issue by adding the length check before accessing it. To clean up the code, an additional parameter named rlen is added. The rlen is calculated at the beginning of iscsi_if_recv_msg() which avoids duplicated calculation. Fixes: ac20c7bf070d ("[SCSI] iscsi_transport: Added Ping support") Fixes: 43514774ff40 ("[SCSI] iscsi class: Add new NETLINK_ISCSI messages for cnic/bnx2i driver.") Fixes: 1d9bf13a9cf9 ("[SCSI] iscsi class: add iscsi host set param event") Fixes: 01cb225dad8d ("[SCSI] iscsi: add target discvery event to transport class") Fixes: 264faaaa1254 ("[SCSI] iscsi: add transport end point callbacks") Fixes: fd7255f51a13 ("[SCSI] iscsi: add sysfs attrs for uspace sync up") Signed-off-by: Lin Ma Link: https://lore.kernel.org/r/20230725024529.428311-1-linma@zju.edu.cn Reviewed-by: Chris Leech Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_transport_iscsi.c | 72 +++++++++++++++++------------ 1 file changed, 43 insertions(+), 29 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index b9b97300e3b3..2680de88f5bb 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3013,14 +3013,15 @@ iscsi_if_destroy_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev } static int -iscsi_if_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) +iscsi_if_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev, u32 rlen) { char *data = (char*)ev + sizeof(*ev); struct iscsi_cls_conn *conn; struct iscsi_cls_session *session; int err = 0, value = 0, state; - if (ev->u.set_param.len > PAGE_SIZE) + if (ev->u.set_param.len > rlen || + ev->u.set_param.len > PAGE_SIZE) return -EINVAL; session = iscsi_session_lookup(ev->u.set_param.sid); @@ -3117,7 +3118,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport, static int iscsi_if_transport_ep(struct iscsi_transport *transport, - struct iscsi_uevent *ev, int msg_type) + struct iscsi_uevent *ev, int msg_type, u32 rlen) { struct iscsi_endpoint *ep; int rc = 0; @@ -3125,7 +3126,10 @@ iscsi_if_transport_ep(struct iscsi_transport *transport, switch (msg_type) { case ISCSI_UEVENT_TRANSPORT_EP_CONNECT_THROUGH_HOST: case ISCSI_UEVENT_TRANSPORT_EP_CONNECT: - rc = iscsi_if_ep_connect(transport, ev, msg_type); + if (rlen < sizeof(struct sockaddr)) + rc = -EINVAL; + else + rc = iscsi_if_ep_connect(transport, ev, msg_type); break; case ISCSI_UEVENT_TRANSPORT_EP_POLL: if (!transport->ep_poll) @@ -3149,12 +3153,15 @@ iscsi_if_transport_ep(struct iscsi_transport *transport, static int iscsi_tgt_dscvr(struct iscsi_transport *transport, - struct iscsi_uevent *ev) + struct iscsi_uevent *ev, u32 rlen) { struct Scsi_Host *shost; struct sockaddr *dst_addr; int err; + if (rlen < sizeof(*dst_addr)) + return -EINVAL; + if (!transport->tgt_dscvr) return -EINVAL; @@ -3175,7 +3182,7 @@ iscsi_tgt_dscvr(struct iscsi_transport *transport, static int iscsi_set_host_param(struct iscsi_transport *transport, - struct iscsi_uevent *ev) + struct iscsi_uevent *ev, u32 rlen) { char *data = (char*)ev + sizeof(*ev); struct Scsi_Host *shost; @@ -3184,7 +3191,8 @@ iscsi_set_host_param(struct iscsi_transport *transport, if (!transport->set_host_param) return -ENOSYS; - if (ev->u.set_host_param.len > PAGE_SIZE) + if (ev->u.set_host_param.len > rlen || + ev->u.set_host_param.len > PAGE_SIZE) return -EINVAL; shost = scsi_host_lookup(ev->u.set_host_param.host_no); @@ -3201,12 +3209,15 @@ iscsi_set_host_param(struct iscsi_transport *transport, } static int -iscsi_set_path(struct iscsi_transport *transport, struct iscsi_uevent *ev) +iscsi_set_path(struct iscsi_transport *transport, struct iscsi_uevent *ev, u32 rlen) { struct Scsi_Host *shost; struct iscsi_path *params; int err; + if (rlen < sizeof(*params)) + return -EINVAL; + if (!transport->set_path) return -ENOSYS; @@ -3266,12 +3277,15 @@ iscsi_set_iface_params(struct iscsi_transport *transport, } static int -iscsi_send_ping(struct iscsi_transport *transport, struct iscsi_uevent *ev) +iscsi_send_ping(struct iscsi_transport *transport, struct iscsi_uevent *ev, u32 rlen) { struct Scsi_Host *shost; struct sockaddr *dst_addr; int err; + if (rlen < sizeof(*dst_addr)) + return -EINVAL; + if (!transport->send_ping) return -ENOSYS; @@ -3769,13 +3783,12 @@ iscsi_get_host_stats(struct iscsi_transport *transport, struct nlmsghdr *nlh) } static int iscsi_if_transport_conn(struct iscsi_transport *transport, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, u32 pdu_len) { struct iscsi_uevent *ev = nlmsg_data(nlh); struct iscsi_cls_session *session; struct iscsi_cls_conn *conn = NULL; struct iscsi_endpoint *ep; - uint32_t pdu_len; int err = 0; switch (nlh->nlmsg_type) { @@ -3860,8 +3873,6 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, break; case ISCSI_UEVENT_SEND_PDU: - pdu_len = nlh->nlmsg_len - sizeof(*nlh) - sizeof(*ev); - if ((ev->u.send_pdu.hdr_size > pdu_len) || (ev->u.send_pdu.data_size > (pdu_len - ev->u.send_pdu.hdr_size))) { err = -EINVAL; @@ -3891,6 +3902,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) struct iscsi_internal *priv; struct iscsi_cls_session *session; struct iscsi_endpoint *ep = NULL; + u32 rlen; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; @@ -3910,6 +3922,13 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) portid = NETLINK_CB(skb).portid; + /* + * Even though the remaining payload may not be regarded as nlattr, + * (like address or something else), calculate the remaining length + * here to ease following length checks. + */ + rlen = nlmsg_attrlen(nlh, sizeof(*ev)); + switch (nlh->nlmsg_type) { case ISCSI_UEVENT_CREATE_SESSION: err = iscsi_if_create_session(priv, ep, ev, @@ -3966,7 +3985,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) err = -EINVAL; break; case ISCSI_UEVENT_SET_PARAM: - err = iscsi_if_set_param(transport, ev); + err = iscsi_if_set_param(transport, ev, rlen); break; case ISCSI_UEVENT_CREATE_CONN: case ISCSI_UEVENT_DESTROY_CONN: @@ -3974,7 +3993,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) case ISCSI_UEVENT_START_CONN: case ISCSI_UEVENT_BIND_CONN: case ISCSI_UEVENT_SEND_PDU: - err = iscsi_if_transport_conn(transport, nlh); + err = iscsi_if_transport_conn(transport, nlh, rlen); break; case ISCSI_UEVENT_GET_STATS: err = iscsi_if_get_stats(transport, nlh); @@ -3983,23 +4002,22 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) case ISCSI_UEVENT_TRANSPORT_EP_POLL: case ISCSI_UEVENT_TRANSPORT_EP_DISCONNECT: case ISCSI_UEVENT_TRANSPORT_EP_CONNECT_THROUGH_HOST: - err = iscsi_if_transport_ep(transport, ev, nlh->nlmsg_type); + err = iscsi_if_transport_ep(transport, ev, nlh->nlmsg_type, rlen); break; case ISCSI_UEVENT_TGT_DSCVR: - err = iscsi_tgt_dscvr(transport, ev); + err = iscsi_tgt_dscvr(transport, ev, rlen); break; case ISCSI_UEVENT_SET_HOST_PARAM: - err = iscsi_set_host_param(transport, ev); + err = iscsi_set_host_param(transport, ev, rlen); break; case ISCSI_UEVENT_PATH_UPDATE: - err = iscsi_set_path(transport, ev); + err = iscsi_set_path(transport, ev, rlen); break; case ISCSI_UEVENT_SET_IFACE_PARAMS: - err = iscsi_set_iface_params(transport, ev, - nlmsg_attrlen(nlh, sizeof(*ev))); + err = iscsi_set_iface_params(transport, ev, rlen); break; case ISCSI_UEVENT_PING: - err = iscsi_send_ping(transport, ev); + err = iscsi_send_ping(transport, ev, rlen); break; case ISCSI_UEVENT_GET_CHAP: err = iscsi_get_chap(transport, nlh); @@ -4008,13 +4026,10 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) err = iscsi_delete_chap(transport, ev); break; case ISCSI_UEVENT_SET_FLASHNODE_PARAMS: - err = iscsi_set_flashnode_param(transport, ev, - nlmsg_attrlen(nlh, - sizeof(*ev))); + err = iscsi_set_flashnode_param(transport, ev, rlen); break; case ISCSI_UEVENT_NEW_FLASHNODE: - err = iscsi_new_flashnode(transport, ev, - nlmsg_attrlen(nlh, sizeof(*ev))); + err = iscsi_new_flashnode(transport, ev, rlen); break; case ISCSI_UEVENT_DEL_FLASHNODE: err = iscsi_del_flashnode(transport, ev); @@ -4029,8 +4044,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) err = iscsi_logout_flashnode_sid(transport, ev); break; case ISCSI_UEVENT_SET_CHAP: - err = iscsi_set_chap(transport, ev, - nlmsg_attrlen(nlh, sizeof(*ev))); + err = iscsi_set_chap(transport, ev, rlen); break; case ISCSI_UEVENT_GET_HOST_STATS: err = iscsi_get_host_stats(transport, nlh); From 85b8c282d18530e765db7bff93abf81497b19b84 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 23 Jul 2023 15:58:20 +0800 Subject: [PATCH 1099/2093] scsi: iscsi: Add strlen() check in iscsi_if_set{_host}_param() [ Upstream commit ce51c817008450ef4188471db31639d42d37a5e1 ] The functions iscsi_if_set_param() and iscsi_if_set_host_param() convert an nlattr payload to type char* and then call C string handling functions like sscanf and kstrdup: char *data = (char*)ev + sizeof(*ev); ... sscanf(data, "%d", &value); However, since the nlattr is provided by the user-space program and the nlmsg skb is allocated with GFP_KERNEL instead of GFP_ZERO flag (see netlink_alloc_large_skb() in netlink_sendmsg()), dirty data on the heap can lead to an OOB access for those string handling functions. By investigating how the bug is introduced, we find it is really interesting as the old version parsing code starting from commit fd7255f51a13 ("[SCSI] iscsi: add sysfs attrs for uspace sync up") treated the nlattr as integer bytes instead of string and had length check in iscsi_copy_param(): if (ev->u.set_param.len != sizeof(uint32_t)) BUG(); But, since the commit a54a52caad4b ("[SCSI] iscsi: fixup set/get param functions"), the code treated the nlattr as C string while forgetting to add any strlen checks(), opening the possibility of an OOB access. Fix the potential OOB by adding the strlen() check before accessing the buf. If the data passes this check, all low-level set_param handlers can safely treat this buf as legal C string. Fixes: fd7255f51a13 ("[SCSI] iscsi: add sysfs attrs for uspace sync up") Fixes: 1d9bf13a9cf9 ("[SCSI] iscsi class: add iscsi host set param event") Signed-off-by: Lin Ma Link: https://lore.kernel.org/r/20230723075820.3713119-1-linma@zju.edu.cn Reviewed-by: Chris Leech Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_transport_iscsi.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 2680de88f5bb..49dbcd67579a 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3029,6 +3029,10 @@ iscsi_if_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev, u if (!conn || !session) return -EINVAL; + /* data will be regarded as NULL-ended string, do length check */ + if (strlen(data) > ev->u.set_param.len) + return -EINVAL; + switch (ev->u.set_param.param) { case ISCSI_PARAM_SESS_RECOVERY_TMO: sscanf(data, "%d", &value); @@ -3202,6 +3206,10 @@ iscsi_set_host_param(struct iscsi_transport *transport, return -ENODEV; } + /* see similar check in iscsi_if_set_param() */ + if (strlen(data) > ev->u.set_host_param.len) + return -EINVAL; + err = transport->set_host_param(shost, ev->u.set_host_param.param, data, ev->u.set_host_param.len); scsi_host_put(shost); From 1806edae979fe13356ce4337acfe9d67f896a251 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 23 Jul 2023 15:59:38 +0800 Subject: [PATCH 1100/2093] scsi: be2iscsi: Add length check when parsing nlattrs [ Upstream commit ee0268f230f66cb472df3424f380ea668da2749a ] beiscsi_iface_set_param() parses nlattr with nla_for_each_attr and assumes every attributes can be viewed as struct iscsi_iface_param_info. This is not true because there is no any nla_policy to validate the attributes passed from the upper function iscsi_set_iface_params(). Add the nla_len check before accessing the nlattr data and return EINVAL if the length check fails. Fixes: 0e43895ec1f4 ("[SCSI] be2iscsi: adding functionality to change network settings using iscsiadm") Signed-off-by: Lin Ma Link: https://lore.kernel.org/r/20230723075938.3713864-1-linma@zju.edu.cn Reviewed-by: Chris Leech Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/be2iscsi/be_iscsi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c index 8aeaddc93b16..8d374ae863ba 100644 --- a/drivers/scsi/be2iscsi/be_iscsi.c +++ b/drivers/scsi/be2iscsi/be_iscsi.c @@ -450,6 +450,10 @@ int beiscsi_iface_set_param(struct Scsi_Host *shost, } nla_for_each_attr(attrib, data, dt_len, rm_len) { + /* ignore nla_type as it is never used */ + if (nla_len(attrib) < sizeof(*iface_param)) + return -EINVAL; + iface_param = nla_data(attrib); if (iface_param->param_type != ISCSI_NET_PARAM) From 25feffb3fbd51ae81d92c65cebc0e932663828b3 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 23 Jul 2023 16:00:53 +0800 Subject: [PATCH 1101/2093] scsi: qla4xxx: Add length check when parsing nlattrs [ Upstream commit 47cd3770e31df942e2bb925a9a855c79ed0662eb ] There are three places that qla4xxx parses nlattrs: - qla4xxx_set_chap_entry() - qla4xxx_iface_set_param() - qla4xxx_sysfs_ddb_set_param() and each of them directly converts the nlattr to specific pointer of structure without length checking. This could be dangerous as those attributes are not validated and a malformed nlattr (e.g., length 0) could result in an OOB read that leaks heap dirty data. Add the nla_len check before accessing the nlattr data and return EINVAL if the length check fails. Fixes: 26ffd7b45fe9 ("[SCSI] qla4xxx: Add support to set CHAP entries") Fixes: 1e9e2be3ee03 ("[SCSI] qla4xxx: Add flash node mgmt support") Fixes: 00c31889f751 ("[SCSI] qla4xxx: fix data alignment and use nl helpers") Signed-off-by: Lin Ma Link: https://lore.kernel.org/r/20230723080053.3714534-1-linma@zju.edu.cn Reviewed-by: Chris Leech Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla4xxx/ql4_os.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 9e849f6b0d0f..3f2f9734ee42 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -968,6 +968,11 @@ static int qla4xxx_set_chap_entry(struct Scsi_Host *shost, void *data, int len) memset(&chap_rec, 0, sizeof(chap_rec)); nla_for_each_attr(attr, data, len, rem) { + if (nla_len(attr) < sizeof(*param_info)) { + rc = -EINVAL; + goto exit_set_chap; + } + param_info = nla_data(attr); switch (param_info->param) { @@ -2750,6 +2755,11 @@ qla4xxx_iface_set_param(struct Scsi_Host *shost, void *data, uint32_t len) } nla_for_each_attr(attr, data, len, rem) { + if (nla_len(attr) < sizeof(*iface_param)) { + rval = -EINVAL; + goto exit_init_fw_cb; + } + iface_param = nla_data(attr); if (iface_param->param_type == ISCSI_NET_PARAM) { @@ -8104,6 +8114,11 @@ qla4xxx_sysfs_ddb_set_param(struct iscsi_bus_flash_session *fnode_sess, memset((void *)&chap_tbl, 0, sizeof(chap_tbl)); nla_for_each_attr(attr, data, len, rem) { + if (nla_len(attr) < sizeof(*fnode_param)) { + rc = -EINVAL; + goto exit_set_param; + } + fnode_param = nla_data(attr); switch (fnode_param->param) { From 21608d2ba56529f883a1028e8ec612454516301b Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 25 Jul 2023 18:16:23 +0100 Subject: [PATCH 1102/2093] iio: accel: adxl313: Fix adxl313_i2c_id[] table [ Upstream commit f636554c4cd1c644109cc525900a056495b86cc9 ] The .driver_data in adxl313_i2c_id[] for adxl312 and adxl314 is wrong. Fix this issue by adding corresponding adxl31x_chip_info data. Reported-by: Jonathan Cameron Closes: https://lore.kernel.org/all/20230722172832.04ad7738@jic23-huawei Fixes: a7a1c60bc4c9 ("drivers: iio: accel: adxl312 and adxl314 support") Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230725171624.331283-2-biju.das.jz@bp.renesas.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/accel/adxl313_i2c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/accel/adxl313_i2c.c b/drivers/iio/accel/adxl313_i2c.c index 99cc7fc29488..68785bd3ef2f 100644 --- a/drivers/iio/accel/adxl313_i2c.c +++ b/drivers/iio/accel/adxl313_i2c.c @@ -40,8 +40,8 @@ static const struct regmap_config adxl31x_i2c_regmap_config[] = { static const struct i2c_device_id adxl313_i2c_id[] = { { .name = "adxl312", .driver_data = (kernel_ulong_t)&adxl31x_chip_info[ADXL312] }, - { .name = "adxl313", .driver_data = (kernel_ulong_t)&adxl31x_chip_info[ADXL312] }, - { .name = "adxl314", .driver_data = (kernel_ulong_t)&adxl31x_chip_info[ADXL312] }, + { .name = "adxl313", .driver_data = (kernel_ulong_t)&adxl31x_chip_info[ADXL313] }, + { .name = "adxl314", .driver_data = (kernel_ulong_t)&adxl31x_chip_info[ADXL314] }, { } }; From 70f7513342f47bf3ebac8dc1a671ee0b6821c99a Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Tue, 25 Jul 2023 14:40:52 +0800 Subject: [PATCH 1103/2093] serial: sprd: Assign sprd_port after initialized to avoid wrong access [ Upstream commit f9608f1887568b728839d006024585ab02ef29e5 ] The global pointer 'sprd_port' may not zero when sprd_probe returns failure, that is a risk for sprd_port to be accessed afterward, and may lead to unexpected errors. For example: There are two UART ports, UART1 is used for console and configured in kernel command line, i.e. "console="; The UART1 probe failed and the memory allocated to sprd_port[1] was released, but sprd_port[1] was not set to NULL; In UART2 probe, the same virtual address was allocated to sprd_port[2], and UART2 probe process finally will go into sprd_console_setup() to register UART1 as console since it is configured as preferred console (filled to console_cmdline[]), but the console parameters (sprd_port[1]) belong to UART2. So move the sprd_port[] assignment to where the port already initialized can avoid the above issue. Fixes: b7396a38fb28 ("tty/serial: Add Spreadtrum sc9836-uart driver support") Signed-off-by: Chunyan Zhang Link: https://lore.kernel.org/r/20230725064053.235448-1-chunyan.zhang@unisoc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/sprd_serial.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c index 342a87967631..58825443529f 100644 --- a/drivers/tty/serial/sprd_serial.c +++ b/drivers/tty/serial/sprd_serial.c @@ -1132,7 +1132,7 @@ static bool sprd_uart_is_console(struct uart_port *uport) static int sprd_clk_init(struct uart_port *uport) { struct clk *clk_uart, *clk_parent; - struct sprd_uart_port *u = sprd_port[uport->line]; + struct sprd_uart_port *u = container_of(uport, struct sprd_uart_port, port); clk_uart = devm_clk_get(uport->dev, "uart"); if (IS_ERR(clk_uart)) { @@ -1175,22 +1175,22 @@ static int sprd_probe(struct platform_device *pdev) { struct resource *res; struct uart_port *up; + struct sprd_uart_port *sport; int irq; int index; int ret; index = of_alias_get_id(pdev->dev.of_node, "serial"); - if (index < 0 || index >= ARRAY_SIZE(sprd_port)) { + if (index < 0 || index >= UART_NR_MAX) { dev_err(&pdev->dev, "got a wrong serial alias id %d\n", index); return -EINVAL; } - sprd_port[index] = devm_kzalloc(&pdev->dev, sizeof(*sprd_port[index]), - GFP_KERNEL); - if (!sprd_port[index]) + sport = devm_kzalloc(&pdev->dev, sizeof(*sport), GFP_KERNEL); + if (!sport) return -ENOMEM; - up = &sprd_port[index]->port; + up = &sport->port; up->dev = &pdev->dev; up->line = index; up->type = PORT_SPRD; @@ -1221,7 +1221,7 @@ static int sprd_probe(struct platform_device *pdev) * Allocate one dma buffer to prepare for receive transfer, in case * memory allocation failure at runtime. */ - ret = sprd_rx_alloc_buf(sprd_port[index]); + ret = sprd_rx_alloc_buf(sport); if (ret) return ret; @@ -1232,14 +1232,23 @@ static int sprd_probe(struct platform_device *pdev) return ret; } } + sprd_ports_num++; + sprd_port[index] = sport; ret = uart_add_one_port(&sprd_uart_driver, up); if (ret) - sprd_remove(pdev); + goto clean_port; platform_set_drvdata(pdev, up); + return 0; + +clean_port: + sprd_port[index] = NULL; + if (--sprd_ports_num == 0) + uart_unregister_driver(&sprd_uart_driver); + sprd_rx_free_buf(sport); return ret; } From 6d209ed70f9c388727995aaece1f930fe63d402b Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Tue, 25 Jul 2023 14:40:53 +0800 Subject: [PATCH 1104/2093] serial: sprd: Fix DMA buffer leak issue [ Upstream commit cd119fdc3ee1450fbf7f78862b5de44c42b6e47f ] Release DMA buffer when _probe() returns failure to avoid memory leak. Fixes: f4487db58eb7 ("serial: sprd: Add DMA mode support") Signed-off-by: Chunyan Zhang Reviewed-by: Baolin Wang Link: https://lore.kernel.org/r/20230725064053.235448-2-chunyan.zhang@unisoc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/sprd_serial.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c index 58825443529f..9c7f71993e94 100644 --- a/drivers/tty/serial/sprd_serial.c +++ b/drivers/tty/serial/sprd_serial.c @@ -367,7 +367,7 @@ static void sprd_rx_free_buf(struct sprd_uart_port *sp) if (sp->rx_dma.virt) dma_free_coherent(sp->port.dev, SPRD_UART_RX_SIZE, sp->rx_dma.virt, sp->rx_dma.phys_addr); - + sp->rx_dma.virt = NULL; } static int sprd_rx_dma_config(struct uart_port *port, u32 burst) @@ -1229,7 +1229,7 @@ static int sprd_probe(struct platform_device *pdev) ret = uart_register_driver(&sprd_uart_driver); if (ret < 0) { pr_err("Failed to register SPRD-UART driver\n"); - return ret; + goto free_rx_buf; } } @@ -1248,6 +1248,7 @@ static int sprd_probe(struct platform_device *pdev) sprd_port[index] = NULL; if (--sprd_ports_num == 0) uart_unregister_driver(&sprd_uart_driver); +free_rx_buf: sprd_rx_free_buf(sport); return ret; } From 0ad56bf59dc38577986f77115399e06140ba7703 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 27 Jul 2023 18:11:20 -0700 Subject: [PATCH 1105/2093] x86/APM: drop the duplicate APM_MINOR_DEV macro [ Upstream commit 4ba2909638a29630a346d6c4907a3105409bee7d ] This source file already includes , which contains the same macro. It doesn't need to be defined here again. Fixes: 874bcd00f520 ("apm-emulation: move APM_MINOR_DEV to include/linux/miscdevice.h") Signed-off-by: Randy Dunlap Cc: Jiri Kosina Cc: x86@kernel.org Cc: Sohil Mehta Cc: Corentin Labbe Reviewed-by: Sohil Mehta Link: https://lore.kernel.org/r/20230728011120.759-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- arch/x86/kernel/apm_32.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 60e330cdbd17..6e38188633a4 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -238,12 +238,6 @@ extern int (*console_blank_hook)(int); #endif -/* - * The apm_bios device is one of the misc char devices. - * This is its minor number. - */ -#define APM_MINOR_DEV 134 - /* * Various options can be changed at boot time as follows: * (We allow underscores for compatibility with the modules code) From 59a4f61feccf9c5518c76d6efd1742694040d1d5 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 21 Oct 2022 15:01:05 -0500 Subject: [PATCH 1106/2093] RDMA/rxe: Split rxe_run_task() into two subroutines [ Upstream commit dccb23f6c312e4480fe32ccbc2afac1a5cac7e5e ] Split rxe_run_task(task, sched) into rxe_run_task(task) and rxe_sched_task(task). Link: https://lore.kernel.org/r/20221021200118.2163-5-rpearsonhpe@gmail.com Signed-off-by: Ian Ziemba Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe Stable-dep-of: 5d122db2ff80 ("RDMA/rxe: Fix incomplete state save in rxe_requester") Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_comp.c | 19 +++++++++++-------- drivers/infiniband/sw/rxe/rxe_net.c | 4 ++-- drivers/infiniband/sw/rxe/rxe_qp.c | 10 +++++----- drivers/infiniband/sw/rxe/rxe_req.c | 10 +++++----- drivers/infiniband/sw/rxe/rxe_resp.c | 5 ++++- drivers/infiniband/sw/rxe/rxe_task.c | 15 ++++++++++----- drivers/infiniband/sw/rxe/rxe_task.h | 7 +++---- drivers/infiniband/sw/rxe/rxe_verbs.c | 8 ++++---- 8 files changed, 44 insertions(+), 34 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index fb0c008af78c..d2a250123617 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -118,7 +118,7 @@ void retransmit_timer(struct timer_list *t) if (qp->valid) { qp->comp.timeout = 1; - rxe_run_task(&qp->comp.task, 1); + rxe_sched_task(&qp->comp.task); } } @@ -132,7 +132,10 @@ void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) if (must_sched != 0) rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_COMPLETER_SCHED); - rxe_run_task(&qp->comp.task, must_sched); + if (must_sched) + rxe_sched_task(&qp->comp.task); + else + rxe_run_task(&qp->comp.task); } static inline enum comp_state get_wqe(struct rxe_qp *qp, @@ -305,7 +308,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp, qp->comp.psn = pkt->psn; if (qp->req.wait_psn) { qp->req.wait_psn = 0; - rxe_run_task(&qp->req.task, 0); + rxe_run_task(&qp->req.task); } } return COMPST_ERROR_RETRY; @@ -452,7 +455,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) */ if (qp->req.wait_fence) { qp->req.wait_fence = 0; - rxe_run_task(&qp->req.task, 0); + rxe_run_task(&qp->req.task); } } @@ -466,7 +469,7 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp, if (qp->req.need_rd_atomic) { qp->comp.timeout_retry = 0; qp->req.need_rd_atomic = 0; - rxe_run_task(&qp->req.task, 0); + rxe_run_task(&qp->req.task); } } @@ -512,7 +515,7 @@ static inline enum comp_state complete_wqe(struct rxe_qp *qp, if (qp->req.wait_psn) { qp->req.wait_psn = 0; - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); } } @@ -646,7 +649,7 @@ int rxe_completer(void *arg) if (qp->req.wait_psn) { qp->req.wait_psn = 0; - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); } state = COMPST_DONE; @@ -714,7 +717,7 @@ int rxe_completer(void *arg) RXE_CNT_COMP_RETRY); qp->req.need_retry = 1; qp->comp.started_retry = 1; - rxe_run_task(&qp->req.task, 0); + rxe_run_task(&qp->req.task); } goto done; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 65d16024b3bf..719432808a06 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -348,7 +348,7 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb) if (unlikely(qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)) - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); rxe_put(qp); } @@ -435,7 +435,7 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, if ((qp_type(qp) != IB_QPT_RC) && (pkt->mask & RXE_END_MASK)) { pkt->wqe->state = wqe_state_done; - rxe_run_task(&qp->comp.task, 1); + rxe_sched_task(&qp->comp.task); } rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 59b2024b34ef..709c63e9773c 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -539,10 +539,10 @@ static void rxe_qp_drain(struct rxe_qp *qp) if (qp->req.state != QP_STATE_DRAINED) { qp->req.state = QP_STATE_DRAIN; if (qp_type(qp) == IB_QPT_RC) - rxe_run_task(&qp->comp.task, 1); + rxe_sched_task(&qp->comp.task); else __rxe_do_task(&qp->comp.task); - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); } } } @@ -556,13 +556,13 @@ void rxe_qp_error(struct rxe_qp *qp) qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ - rxe_run_task(&qp->resp.task, 1); + rxe_sched_task(&qp->resp.task); if (qp_type(qp) == IB_QPT_RC) - rxe_run_task(&qp->comp.task, 1); + rxe_sched_task(&qp->comp.task); else __rxe_do_task(&qp->comp.task); - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); } /* called by the modify qp verb */ diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index f63771207970..41f1d84f0acb 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -105,7 +105,7 @@ void rnr_nak_timer(struct timer_list *t) /* request a send queue retry */ qp->req.need_retry = 1; qp->req.wait_for_rnr_timer = 0; - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); } static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) @@ -608,7 +608,7 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe) * which can lead to a deadlock. So go ahead and complete * it now. */ - rxe_run_task(&qp->comp.task, 1); + rxe_sched_task(&qp->comp.task); return 0; } @@ -733,7 +733,7 @@ int rxe_requester(void *arg) qp->req.wqe_index); wqe->state = wqe_state_done; wqe->status = IB_WC_SUCCESS; - rxe_run_task(&qp->comp.task, 0); + rxe_run_task(&qp->comp.task); goto done; } payload = mtu; @@ -795,7 +795,7 @@ int rxe_requester(void *arg) rollback_state(wqe, qp, &rollback_wqe, rollback_psn); if (err == -EAGAIN) { - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); goto exit; } @@ -817,7 +817,7 @@ int rxe_requester(void *arg) qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); wqe->state = wqe_state_error; qp->req.state = QP_STATE_ERROR; - rxe_run_task(&qp->comp.task, 0); + rxe_run_task(&qp->comp.task); exit: ret = -EAGAIN; out: diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 9f65c346d843..a45202cecf2d 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -91,7 +91,10 @@ void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) must_sched = (pkt->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST) || (skb_queue_len(&qp->req_pkts) > 1); - rxe_run_task(&qp->resp.task, must_sched); + if (must_sched) + rxe_sched_task(&qp->resp.task); + else + rxe_run_task(&qp->resp.task); } static inline enum resp_states get_req(struct rxe_qp *qp, diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index 182d0532a8ab..446ee2c3d381 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -127,15 +127,20 @@ void rxe_cleanup_task(struct rxe_task *task) tasklet_kill(&task->tasklet); } -void rxe_run_task(struct rxe_task *task, int sched) +void rxe_run_task(struct rxe_task *task) { if (task->destroyed) return; - if (sched) - tasklet_schedule(&task->tasklet); - else - rxe_do_task(&task->tasklet); + rxe_do_task(&task->tasklet); +} + +void rxe_sched_task(struct rxe_task *task) +{ + if (task->destroyed) + return; + + tasklet_schedule(&task->tasklet); } void rxe_disable_task(struct rxe_task *task) diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index b3dfd970d1dc..590b1c1d7e7c 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -52,10 +52,9 @@ int __rxe_do_task(struct rxe_task *task); */ void rxe_do_task(struct tasklet_struct *t); -/* run a task, else schedule it to run as a tasklet, The decision - * to run or schedule tasklet is based on the parameter sched. - */ -void rxe_run_task(struct rxe_task *task, int sched); +void rxe_run_task(struct rxe_task *task); + +void rxe_sched_task(struct rxe_task *task); /* keep a task from scheduling */ void rxe_disable_task(struct rxe_task *task); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index be13bcb4cc40..065717c11cba 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -678,9 +678,9 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, wr = next; } - rxe_run_task(&qp->req.task, 1); + rxe_sched_task(&qp->req.task); if (unlikely(qp->req.state == QP_STATE_ERROR)) - rxe_run_task(&qp->comp.task, 1); + rxe_sched_task(&qp->comp.task); return err; } @@ -702,7 +702,7 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, if (qp->is_user) { /* Utilize process context to do protocol processing */ - rxe_run_task(&qp->req.task, 0); + rxe_run_task(&qp->req.task); return 0; } else return rxe_post_send_kernel(qp, wr, bad_wr); @@ -740,7 +740,7 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); if (qp->resp.state == QP_STATE_ERROR) - rxe_run_task(&qp->resp.task, 1); + rxe_sched_task(&qp->resp.task); return err; } From 70518f3aaf5a059b691867d7d2d46b999319656a Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 21 Jul 2023 15:07:49 -0500 Subject: [PATCH 1107/2093] RDMA/rxe: Fix incomplete state save in rxe_requester [ Upstream commit 5d122db2ff80cd2aed4dcd630befb56b51ddf947 ] If a send packet is dropped by the IP layer in rxe_requester() the call to rxe_xmit_packet() can fail with err == -EAGAIN. To recover, the state of the wqe is restored to the state before the packet was sent so it can be resent. However, the routines that save and restore the state miss a significnt part of the variable state in the wqe, the dma struct which is used to process through the sge table. And, the state is not saved before the packet is built which modifies the dma struct. Under heavy stress testing with many QPs on a fast node sending large messages to a slow node dropped packets are observed and the resent packets are corrupted because the dma struct was not restored. This patch fixes this behavior and allows the test cases to succeed. Fixes: 3050b9985024 ("IB/rxe: Fix race condition between requester and completer") Link: https://lore.kernel.org/r/20230721200748.4604-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_req.c | 49 ++++++++++++++++------------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 41f1d84f0acb..2ace1007a419 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -529,10 +529,11 @@ static void save_state(struct rxe_send_wqe *wqe, struct rxe_send_wqe *rollback_wqe, u32 *rollback_psn) { - rollback_wqe->state = wqe->state; + rollback_wqe->state = wqe->state; rollback_wqe->first_psn = wqe->first_psn; - rollback_wqe->last_psn = wqe->last_psn; - *rollback_psn = qp->req.psn; + rollback_wqe->last_psn = wqe->last_psn; + rollback_wqe->dma = wqe->dma; + *rollback_psn = qp->req.psn; } static void rollback_state(struct rxe_send_wqe *wqe, @@ -540,10 +541,11 @@ static void rollback_state(struct rxe_send_wqe *wqe, struct rxe_send_wqe *rollback_wqe, u32 rollback_psn) { - wqe->state = rollback_wqe->state; + wqe->state = rollback_wqe->state; wqe->first_psn = rollback_wqe->first_psn; - wqe->last_psn = rollback_wqe->last_psn; - qp->req.psn = rollback_psn; + wqe->last_psn = rollback_wqe->last_psn; + wqe->dma = rollback_wqe->dma; + qp->req.psn = rollback_psn; } static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt) @@ -746,6 +748,9 @@ int rxe_requester(void *arg) pkt.mask = rxe_opcode[opcode].mask; pkt.wqe = wqe; + /* save wqe state before we build and send packet */ + save_state(wqe, qp, &rollback_wqe, &rollback_psn); + av = rxe_get_av(&pkt, &ah); if (unlikely(!av)) { pr_err("qp#%d Failed no address vector\n", qp_num(qp)); @@ -778,29 +783,29 @@ int rxe_requester(void *arg) if (ah) rxe_put(ah); - /* - * To prevent a race on wqe access between requester and completer, - * wqe members state and psn need to be set before calling - * rxe_xmit_packet(). - * Otherwise, completer might initiate an unjustified retry flow. - */ - save_state(wqe, qp, &rollback_wqe, &rollback_psn); + /* update wqe state as though we had sent it */ update_wqe_state(qp, wqe, &pkt); update_wqe_psn(qp, wqe, &pkt, payload); err = rxe_xmit_packet(qp, &pkt, skb); if (err) { - qp->need_req_skb = 1; - - rollback_state(wqe, qp, &rollback_wqe, rollback_psn); - - if (err == -EAGAIN) { - rxe_sched_task(&qp->req.task); - goto exit; + if (err != -EAGAIN) { + wqe->status = IB_WC_LOC_QP_OP_ERR; + goto err; } - wqe->status = IB_WC_LOC_QP_OP_ERR; - goto err; + /* the packet was dropped so reset wqe to the state + * before we sent it so we can try to resend + */ + rollback_state(wqe, qp, &rollback_wqe, rollback_psn); + + /* force a delay until the dropped packet is freed and + * the send queue is drained below the low water mark + */ + qp->need_req_skb = 1; + + rxe_sched_task(&qp->req.task); + goto exit; } update_state(qp, &pkt); From 472f2497a4c8aa27220e276ff77d618bef482b2a Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Mon, 31 Jul 2023 10:40:32 +0200 Subject: [PATCH 1108/2093] scsi: qedf: Do not touch __user pointer in qedf_dbg_stop_io_on_error_cmd_read() directly [ Upstream commit 7d3d20dee4f648ec44e9717d5f647d594d184433 ] The qedf_dbg_stop_io_on_error_cmd_read() function invokes sprintf() directly on a __user pointer, which may crash the kernel. Avoid doing that by using a small on-stack buffer for scnprintf() and then calling simple_read_from_buffer() which does a proper copy_to_user() call. Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.") Link: https://lore.kernel.org/lkml/20230724120241.40495-1-oleksandr@redhat.com/ Link: https://lore.kernel.org/linux-scsi/20230726101236.11922-1-skashyap@marvell.com/ Cc: Saurav Kashyap Cc: Rob Evers Cc: Johannes Thumshirn Cc: David Laight Cc: Jozef Bacik Cc: Laurence Oberman Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: linux-scsi@vger.kernel.org Reviewed-by: Laurence Oberman Reviewed-by: Johannes Thumshirn Tested-by: Laurence Oberman Acked-by: Saurav Kashyap Signed-off-by: Oleksandr Natalenko Link: https://lore.kernel.org/r/20230731084034.37021-2-oleksandr@redhat.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedf/qedf_debugfs.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/qedf/qedf_debugfs.c b/drivers/scsi/qedf/qedf_debugfs.c index a3ed681c8ce3..3eb4334ac6a3 100644 --- a/drivers/scsi/qedf/qedf_debugfs.c +++ b/drivers/scsi/qedf/qedf_debugfs.c @@ -185,18 +185,17 @@ qedf_dbg_stop_io_on_error_cmd_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { int cnt; + char cbuf[7]; struct qedf_dbg_ctx *qedf_dbg = (struct qedf_dbg_ctx *)filp->private_data; struct qedf_ctx *qedf = container_of(qedf_dbg, struct qedf_ctx, dbg_ctx); QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "entered\n"); - cnt = sprintf(buffer, "%s\n", + cnt = scnprintf(cbuf, sizeof(cbuf), "%s\n", qedf->stop_io_on_error ? "true" : "false"); - cnt = min_t(int, count, cnt - *ppos); - *ppos += cnt; - return cnt; + return simple_read_from_buffer(buffer, count, ppos, cbuf, cnt); } static ssize_t From dd8ce1c9ff49cdf20cdca86553d6f619aa7852e5 Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Mon, 31 Jul 2023 10:40:33 +0200 Subject: [PATCH 1109/2093] scsi: qedf: Do not touch __user pointer in qedf_dbg_debug_cmd_read() directly [ Upstream commit 31b5991a9a91ba97237ac9da509d78eec453ff72 ] The qedf_dbg_debug_cmd_read() function invokes sprintf() directly on a __user pointer, which may crash the kernel. Avoid doing that by using a small on-stack buffer for scnprintf() and then calling simple_read_from_buffer() which does a proper copy_to_user() call. Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.") Link: https://lore.kernel.org/lkml/20230724120241.40495-1-oleksandr@redhat.com/ Link: https://lore.kernel.org/linux-scsi/20230726101236.11922-1-skashyap@marvell.com/ Cc: Saurav Kashyap Cc: Rob Evers Cc: Johannes Thumshirn Cc: David Laight Cc: Jozef Bacik Cc: Laurence Oberman Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: linux-scsi@vger.kernel.org Reviewed-by: Laurence Oberman Reviewed-by: Johannes Thumshirn Tested-by: Laurence Oberman Acked-by: Saurav Kashyap Signed-off-by: Oleksandr Natalenko Link: https://lore.kernel.org/r/20230731084034.37021-3-oleksandr@redhat.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedf/qedf_debugfs.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/qedf/qedf_debugfs.c b/drivers/scsi/qedf/qedf_debugfs.c index 3eb4334ac6a3..1c5716540e46 100644 --- a/drivers/scsi/qedf/qedf_debugfs.c +++ b/drivers/scsi/qedf/qedf_debugfs.c @@ -138,15 +138,14 @@ qedf_dbg_debug_cmd_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { int cnt; + char cbuf[32]; struct qedf_dbg_ctx *qedf_dbg = (struct qedf_dbg_ctx *)filp->private_data; QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "debug mask=0x%x\n", qedf_debug); - cnt = sprintf(buffer, "debug mask = 0x%x\n", qedf_debug); + cnt = scnprintf(cbuf, sizeof(cbuf), "debug mask = 0x%x\n", qedf_debug); - cnt = min_t(int, count, cnt - *ppos); - *ppos += cnt; - return cnt; + return simple_read_from_buffer(buffer, count, ppos, cbuf, cnt); } static ssize_t From af6fd0b3bccfe8a17132fdfabe5c93d4385cfb2c Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Mon, 31 Jul 2023 10:40:34 +0200 Subject: [PATCH 1110/2093] scsi: qedf: Do not touch __user pointer in qedf_dbg_fp_int_cmd_read() directly [ Upstream commit 25dbc20deab5165f847b4eb42f376f725a986ee8 ] The qedf_dbg_fp_int_cmd_read() function invokes sprintf() directly on a __user pointer, which may crash the kernel. Avoid doing that by vmalloc()'ating a buffer for scnprintf() and then calling simple_read_from_buffer() which does a proper copy_to_user() call. Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.") Link: https://lore.kernel.org/lkml/20230724120241.40495-1-oleksandr@redhat.com/ Link: https://lore.kernel.org/linux-scsi/20230726101236.11922-1-skashyap@marvell.com/ Cc: Saurav Kashyap Cc: Rob Evers Cc: Johannes Thumshirn Cc: David Laight Cc: Jozef Bacik Cc: Laurence Oberman Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: linux-scsi@vger.kernel.org Reviewed-by: Laurence Oberman Reviewed-by: Johannes Thumshirn Tested-by: Laurence Oberman Acked-by: Saurav Kashyap Signed-off-by: Oleksandr Natalenko Link: https://lore.kernel.org/r/20230731084034.37021-4-oleksandr@redhat.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedf/qedf_dbg.h | 2 ++ drivers/scsi/qedf/qedf_debugfs.c | 21 +++++++++++++++------ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h index f4d81127239e..5ec2b817c694 100644 --- a/drivers/scsi/qedf/qedf_dbg.h +++ b/drivers/scsi/qedf/qedf_dbg.h @@ -59,6 +59,8 @@ extern uint qedf_debug; #define QEDF_LOG_NOTICE 0x40000000 /* Notice logs */ #define QEDF_LOG_WARN 0x80000000 /* Warning logs */ +#define QEDF_DEBUGFS_LOG_LEN (2 * PAGE_SIZE) + /* Debug context structure */ struct qedf_dbg_ctx { unsigned int host_no; diff --git a/drivers/scsi/qedf/qedf_debugfs.c b/drivers/scsi/qedf/qedf_debugfs.c index 1c5716540e46..451fd236bfd0 100644 --- a/drivers/scsi/qedf/qedf_debugfs.c +++ b/drivers/scsi/qedf/qedf_debugfs.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "qedf.h" #include "qedf_dbg.h" @@ -98,7 +99,9 @@ static ssize_t qedf_dbg_fp_int_cmd_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { + ssize_t ret; size_t cnt = 0; + char *cbuf; int id; struct qedf_fastpath *fp = NULL; struct qedf_dbg_ctx *qedf_dbg = @@ -108,19 +111,25 @@ qedf_dbg_fp_int_cmd_read(struct file *filp, char __user *buffer, size_t count, QEDF_INFO(qedf_dbg, QEDF_LOG_DEBUGFS, "entered\n"); - cnt = sprintf(buffer, "\nFastpath I/O completions\n\n"); + cbuf = vmalloc(QEDF_DEBUGFS_LOG_LEN); + if (!cbuf) + return 0; + + cnt += scnprintf(cbuf + cnt, QEDF_DEBUGFS_LOG_LEN - cnt, "\nFastpath I/O completions\n\n"); for (id = 0; id < qedf->num_queues; id++) { fp = &(qedf->fp_array[id]); if (fp->sb_id == QEDF_SB_ID_NULL) continue; - cnt += sprintf((buffer + cnt), "#%d: %lu\n", id, - fp->completions); + cnt += scnprintf(cbuf + cnt, QEDF_DEBUGFS_LOG_LEN - cnt, + "#%d: %lu\n", id, fp->completions); } - cnt = min_t(int, count, cnt - *ppos); - *ppos += cnt; - return cnt; + ret = simple_read_from_buffer(buffer, count, ppos, cbuf, cnt); + + vfree(cbuf); + + return ret; } static ssize_t From ee8f58b40e4aab96a23a55bfadd03fed0af6cd93 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 2 Aug 2023 08:46:26 -0600 Subject: [PATCH 1111/2093] RDMA/irdma: Replace one-element array with flexible-array member [ Upstream commit 38313c6d2a02c28162e06753b01bd885caf9386d ] One-element and zero-length arrays are deprecated. So, replace one-element array in struct irdma_qvlist_info with flexible-array member. A patch for this was sent a while ago[1]. However, it seems that, at the time, the changes were partially folded[2][3], and the actual flexible-array transformation was omitted. This patch fixes that. The only binary difference seen before/after changes is shown below: | drivers/infiniband/hw/irdma/hw.o | @@ -868,7 +868,7 @@ | drivers/infiniband/hw/irdma/hw.c:484 (discriminator 2) | size += struct_size(iw_qvlist, qv_info, rf->msix_count); | 55b: imul $0x45c,%rdi,%rdi |- 562: add $0x10,%rdi |+ 562: add $0x4,%rdi which is, of course, expected as it reflects the mistake made while folding the patch I've mentioned above. Worth mentioning is the fact that with this change we save 12 bytes of memory, as can be inferred from the diff snapshot above. Notice that: $ pahole -C rdma_qv_info idrivers/infiniband/hw/irdma/hw.o struct irdma_qv_info { u32 v_idx; /* 0 4 */ u16 ceq_idx; /* 4 2 */ u16 aeq_idx; /* 6 2 */ u8 itr_idx; /* 8 1 */ /* size: 12, cachelines: 1, members: 4 */ /* padding: 3 */ /* last cacheline: 12 bytes */ }; Link: https://lore.kernel.org/linux-hardening/20210525230038.GA175516@embeddedor/ [1] Link: https://lore.kernel.org/linux-hardening/bf46b428deef4e9e89b0ea1704b1f0e5@intel.com/ [2] Link: https://lore.kernel.org/linux-rdma/20210520143809.819-1-shiraz.saleem@intel.com/T/#u [3] Fixes: 44d9e52977a1 ("RDMA/irdma: Implement device initialization definitions") Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/ZMpsQrZadBaJGkt4@work Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/irdma/main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index e64205839d03..9cbe64311f98 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -236,7 +236,7 @@ struct irdma_qv_info { struct irdma_qvlist_info { u32 num_vectors; - struct irdma_qv_info qv_info[1]; + struct irdma_qv_info qv_info[]; }; struct irdma_gen_ops { From 7e1476f27751920f40e488b93c97c1c779b5ca2a Mon Sep 17 00:00:00 2001 From: Ruidong Tian Date: Fri, 4 Aug 2023 16:15:14 +0800 Subject: [PATCH 1112/2093] coresight: tmc: Explicit type conversions to prevent integer overflow [ Upstream commit fd380097cdb305582b7a1f9476391330299d2c59 ] Perf cs_etm session executed unexpectedly when AUX buffer > 1G. perf record -C 0 -m ,2G -e cs_etm// -- [ perf record: Captured and wrote 2.615 MB perf.data ] Perf only collect about 2M perf data rather than 2G. This is becasuse the operation, "nr_pages << PAGE_SHIFT", in coresight tmc driver, will overflow when nr_pages >= 0x80000(correspond to 1G AUX buffer). The overflow cause buffer allocation to fail, and TMC driver will alloc minimal buffer size(1M). You can just get about 2M perf data(1M AUX buffer + perf data header) at least. Explicit convert nr_pages to 64 bit to avoid overflow. Fixes: 22f429f19c41 ("coresight: etm-perf: Add support for ETR backend") Fixes: 99443ea19e8b ("coresight: Add generic TMC sg table framework") Fixes: 2e499bbc1a92 ("coresight: tmc: implementing TMC-ETF AUX space API") Signed-off-by: Ruidong Tian Reviewed-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230804081514.120171-2-tianruidong@linux.alibaba.com Signed-off-by: Sasha Levin --- drivers/hwtracing/coresight/coresight-tmc-etf.c | 2 +- drivers/hwtracing/coresight/coresight-tmc-etr.c | 5 +++-- drivers/hwtracing/coresight/coresight-tmc.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 4c4cbd1f7258..3f207999377f 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -428,7 +428,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev, return -EINVAL; /* wrap head around to the amount of space we have */ - head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + head = handle->head & (((unsigned long)buf->nr_pages << PAGE_SHIFT) - 1); /* find the page to write to */ buf->cur = head / PAGE_SIZE; diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 368f2e5a8627..1be0e5e0e80b 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -45,7 +45,8 @@ struct etr_perf_buffer { }; /* Convert the perf index to an offset within the ETR buffer */ -#define PERF_IDX2OFF(idx, buf) ((idx) % ((buf)->nr_pages << PAGE_SHIFT)) +#define PERF_IDX2OFF(idx, buf) \ + ((idx) % ((unsigned long)(buf)->nr_pages << PAGE_SHIFT)) /* Lower limit for ETR hardware buffer */ #define TMC_ETR_PERF_MIN_BUF_SIZE SZ_1M @@ -1249,7 +1250,7 @@ alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, * than the size requested via sysfs. */ if ((nr_pages << PAGE_SHIFT) > drvdata->size) { - etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT), + etr_buf = tmc_alloc_etr_buf(drvdata, ((ssize_t)nr_pages << PAGE_SHIFT), 0, node, NULL); if (!IS_ERR(etr_buf)) goto done; diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index 66959557cf39..946aab12f980 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -325,7 +325,7 @@ ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table, static inline unsigned long tmc_sg_table_buf_size(struct tmc_sg_table *sg_table) { - return sg_table->data_pages.nr_pages << PAGE_SHIFT; + return (unsigned long)sg_table->data_pages.nr_pages << PAGE_SHIFT; } struct coresight_device *tmc_etr_get_catu_device(struct tmc_drvdata *drvdata); From ae867cab6bc97d957e6407d64f2796671513f50c Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 24 Jul 2023 12:49:22 +0200 Subject: [PATCH 1113/2093] interconnect: qcom: qcm2290: Enable sync state [ Upstream commit 4e048e9b7a160f7112069c0ec2947be15f3e8154 ] Enable the generic .sync_state callback to ensure there are no outstanding votes that would waste power. Generally one would need a bunch of interface clocks to access the QoS registers when trying to go over all possible nodes during sync_state, but QCM2290 surprisingly does not seem to require any such handling. Fixes: 1a14b1ac3935 ("interconnect: qcom: Add QCM2290 driver support") Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230720-topic-qcm2290_icc-v2-2-a2ceb9d3e713@linaro.org Signed-off-by: Georgi Djakov Signed-off-by: Sasha Levin --- drivers/interconnect/qcom/qcm2290.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/interconnect/qcom/qcm2290.c b/drivers/interconnect/qcom/qcm2290.c index a29cdb4fac03..82a2698ad66b 100644 --- a/drivers/interconnect/qcom/qcm2290.c +++ b/drivers/interconnect/qcom/qcm2290.c @@ -1355,6 +1355,7 @@ static struct platform_driver qcm2290_noc_driver = { .driver = { .name = "qnoc-qcm2290", .of_match_table = qcm2290_noc_of_match, + .sync_state = icc_sync_state, }, }; module_platform_driver(qcm2290_noc_driver); From 636f5b8a66010c0d40279a5e68ba0d98846469e2 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 24 Jul 2023 07:49:41 -0700 Subject: [PATCH 1114/2093] dma-buf/sync_file: Fix docs syntax [ Upstream commit 05d56d8079d510a2994039470f65bea85f0075ee ] Fixes the warning: include/uapi/linux/sync_file.h:77: warning: Function parameter or member 'num_fences' not described in 'sync_file_info' Fixes: 2d75c88fefb2 ("staging/android: refactor SYNC IOCTLs") Signed-off-by: Rob Clark Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/20230724145000.125880-1-robdclark@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- include/uapi/linux/sync_file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index ee2dcfb3d660..d7f7c04a6e0c 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -52,7 +52,7 @@ struct sync_fence_info { * @name: name of fence * @status: status of fence. 1: signaled 0:active <0:error * @flags: sync_file_info flags - * @num_fences number of fences in the sync_file + * @num_fences: number of fences in the sync_file * @pad: padding for 64-bit alignment, should always be zero * @sync_fence_info: pointer to array of structs sync_fence_info with all * fences in the sync_file From 58a3b87be681c9b0a07c4ab9524987e4846412eb Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 18 Jul 2023 10:03:49 +0300 Subject: [PATCH 1115/2093] driver core: test_async: fix an error code [ Upstream commit 22d2381bbd70a5853c2ee77522f4965139672db9 ] The test_platform_device_register_node() function should return error pointers instead of NULL. That is what the callers are expecting. Fixes: 57ea974fb871 ("driver core: Rewrite test_async_driver_probe to cover serialization and NUMA affinity") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/1e11ed19-e1f6-43d8-b352-474134b7c008@moroto.mountain Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/test/test_async_driver_probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c index 929410d0dd6f..3465800baa6c 100644 --- a/drivers/base/test/test_async_driver_probe.c +++ b/drivers/base/test/test_async_driver_probe.c @@ -84,7 +84,7 @@ test_platform_device_register_node(char *name, int id, int nid) pdev = platform_device_alloc(name, id); if (!pdev) - return NULL; + return ERR_PTR(-ENOMEM); if (nid != NUMA_NO_NODE) set_dev_node(&pdev->dev, nid); From 91a05d4c12ce5f286319d0c7d4e4f95d7420384e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 24 Jul 2023 14:40:46 -0300 Subject: [PATCH 1116/2093] driver core: Call dma_cleanup() on the test_remove path [ Upstream commit f429378a9bf84d79a7e2cae05d2e3384cf7d68ba ] When test_remove is enabled really_probe() does not properly pair dma_configure() with dma_remove(), it will end up calling dma_configure() twice. This corrupts the owner_cnt and renders the group unusable with VFIO/etc. Add the missing cleanup before going back to re_probe. Fixes: 25f3bcfc54bc ("driver core: Add dma_cleanup callback in bus_type") Reported-by: Zenghui Yu Tested-by: Zenghui Yu Closes: https://lore.kernel.org/all/6472f254-c3c4-8610-4a37-8d9dfdd54ce8@huawei.com/ Signed-off-by: Jason Gunthorpe Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/0-v2-4deed94e283e+40948-really_probe_dma_cleanup_jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/dd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 97ab1468a876..380a53b6aee8 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -674,6 +674,8 @@ static int really_probe(struct device *dev, struct device_driver *drv) device_remove(dev); driver_sysfs_remove(dev); + if (dev->bus && dev->bus->dma_cleanup) + dev->bus->dma_cleanup(dev); device_unbind_cleanup(dev); goto re_probe; From d3e075a3f09990cb293d475201a90da3289eaefa Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 24 Jul 2023 14:18:16 +0200 Subject: [PATCH 1117/2093] kernfs: add stub helper for kernfs_generic_poll() [ Upstream commit 79038a99445f69c5d28494dd4f8c6f0509f65b2e ] In some randconfig builds, kernfs ends up being disabled, so there is no prototype for kernfs_generic_poll() In file included from kernel/sched/build_utility.c:97: kernel/sched/psi.c:1479:3: error: implicit declaration of function 'kernfs_generic_poll' is invalid in C99 [-Werror,-Wimplicit-function-declaration] kernfs_generic_poll(t->of, wait); ^ Add a stub helper for it, as we have it for other kernfs functions. Fixes: aff037078ecae ("sched/psi: use kernfs polling functions for PSI trigger polling") Fixes: 147e1a97c4a0b ("fs: kernfs: add poll file operation") Signed-off-by: Arnd Bergmann Reviewed-by: Chengming Zhou Link: https://lore.kernel.org/r/20230724121823.1357562-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- include/linux/kernfs.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 73f5c120def8..2a36f3218b51 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -550,6 +550,10 @@ static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } +static inline __poll_t kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt) +{ return -ENOSYS; } + static inline void kernfs_notify(struct kernfs_node *kn) { } static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, From 343ccde5ade7b6fc094f0aacb42b402fbdb2d71e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 4 Aug 2023 15:28:49 +0200 Subject: [PATCH 1118/2093] extcon: cht_wc: add POWER_SUPPLY dependency [ Upstream commit d20a3a8a32e3fa564ff25da860c5fc1a97642dfe ] The driver fails to link when CONFIG_POWER_SUPPLY is disabled: x86_64-linux-ld: vmlinux.o: in function `cht_wc_extcon_psy_get_prop': extcon-intel-cht-wc.c:(.text+0x15ccda7): undefined reference to `power_supply_get_drvdata' x86_64-linux-ld: vmlinux.o: in function `cht_wc_extcon_pwrsrc_event': extcon-intel-cht-wc.c:(.text+0x15cd3e9): undefined reference to `power_supply_changed' x86_64-linux-ld: vmlinux.o: in function `cht_wc_extcon_probe': extcon-intel-cht-wc.c:(.text+0x15cd596): undefined reference to `devm_power_supply_register' It should be possible to change the driver to not require this at compile time and still provide other functions, but adding a hard Kconfig dependency does not seem to have any practical downsides and is simpler since the option is normally enabled anyway. Fixes: 66e31186cd2aa ("extcon: intel-cht-wc: Add support for registering a power_supply class-device") Signed-off-by: Arnd Bergmann Reviewed-by: Hans de Goede Signed-off-by: Chanwoo Choi Signed-off-by: Sasha Levin --- drivers/extcon/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 290186e44e6b..4dd52a6a5b48 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -62,6 +62,7 @@ config EXTCON_INTEL_CHT_WC tristate "Intel Cherrytrail Whiskey Cove PMIC extcon driver" depends on INTEL_SOC_PMIC_CHTWC depends on USB_SUPPORT + depends on POWER_SUPPLY select USB_ROLE_SWITCH help Say Y here to enable extcon support for charger detection / control From f81325a709dde58d459aa2705c3eed5e8f2dbc68 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 18 Oct 2022 10:42:58 +0800 Subject: [PATCH 1119/2093] iommu/mediatek: Remove unused "mapping" member from mtk_iommu_data [ Upstream commit 9ff894edd542618dad2fef538f8272c620a501db ] Just remove a unused variable that only is for mtk_iommu_v1. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20221018024258.19073-7-yong.wu@mediatek.com Signed-off-by: Joerg Roedel Stable-dep-of: cf69ef46dbd9 ("iommu/mediatek: Fix two IOMMU share pagetable issue") Signed-off-by: Sasha Levin --- drivers/iommu/mtk_iommu.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 2ae5a6058a34..5ff8982712e0 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -223,10 +223,7 @@ struct mtk_iommu_data { struct device *smicomm_dev; struct mtk_iommu_bank_data *bank; - - struct dma_iommu_mapping *mapping; /* For mtk_iommu_v1.c */ struct regmap *pericfg; - struct mutex mutex; /* Protect m4u_group/m4u_dom above */ /* From fadc62aa82d29fbd2a2592fb9b1d6686aab7d394 Mon Sep 17 00:00:00 2001 From: "Chengci.Xu" Date: Fri, 2 Jun 2023 17:02:22 +0800 Subject: [PATCH 1120/2093] iommu/mediatek: Fix two IOMMU share pagetable issue [ Upstream commit cf69ef46dbd980a0b1c956d668e066a73e0acd0f ] Prepare for mt8188 to fix a two IOMMU HWs share pagetable issue. We have two MM IOMMU HWs in mt8188, one is VPP-IOMMU, the other is VDO-IOMMU. The 2 MM IOMMU HWs share pagetable don't work in this case: a) VPP-IOMMU probe firstly. b) VDO-IOMMU probe. c) The master for VDO-IOMMU probe (means frstdata is vpp-iommu). d) The master in another domain probe. No matter it is vdo or vpp. Then it still create a new pagetable in step d). The problem is "frstdata->bank[0]->m4u_dom" was not initialized. Then when d) enter, it still create a new one. In this patch, we create a new variable "share_dom" for this share pgtable case, it should be helpful for readable. and put all the share pgtable logic in the mtk_iommu_domain_finalise. In mt8195, the master of VPP-IOMMU probes before than VDO-IOMMU from its dtsi node sequence, we don't see this issue in it. Prepare for mt8188. Fixes: 645b87c190c9 ("iommu/mediatek: Fix 2 HW sharing pgtable issue") Signed-off-by: Chengci.Xu Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Alexandre Mergnat Link: https://lore.kernel.org/r/20230602090227.7264-3-yong.wu@mediatek.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/mtk_iommu.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 5ff8982712e0..9673cd60c84f 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -223,6 +223,8 @@ struct mtk_iommu_data { struct device *smicomm_dev; struct mtk_iommu_bank_data *bank; + struct mtk_iommu_domain *share_dom; /* For 2 HWs share pgtable */ + struct regmap *pericfg; struct mutex mutex; /* Protect m4u_group/m4u_dom above */ @@ -574,15 +576,14 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom, struct mtk_iommu_data *data, unsigned int region_id) { + struct mtk_iommu_domain *share_dom = data->share_dom; const struct mtk_iommu_iova_region *region; - struct mtk_iommu_domain *m4u_dom; - /* Always use bank0 in sharing pgtable case */ - m4u_dom = data->bank[0].m4u_dom; - if (m4u_dom) { - dom->iop = m4u_dom->iop; - dom->cfg = m4u_dom->cfg; - dom->domain.pgsize_bitmap = m4u_dom->cfg.pgsize_bitmap; + /* Always use share domain in sharing pgtable case */ + if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE) && share_dom) { + dom->iop = share_dom->iop; + dom->cfg = share_dom->cfg; + dom->domain.pgsize_bitmap = share_dom->cfg.pgsize_bitmap; goto update_iova_region; } @@ -612,6 +613,9 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom, /* Update our support page sizes bitmap */ dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap; + if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) + data->share_dom = dom; + update_iova_region: /* Update the iova region for this domain */ region = data->plat_data->iova_region + region_id; @@ -662,7 +666,9 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, /* Data is in the frstdata in sharing pgtable case. */ frstdata = mtk_iommu_get_frst_data(hw_list); + mutex_lock(&frstdata->mutex); ret = mtk_iommu_domain_finalise(dom, frstdata, region_id); + mutex_unlock(&frstdata->mutex); if (ret) { mutex_unlock(&dom->mutex); return -ENODEV; From 117a1b903bafee02ef107c33f50d0c1cc91448c6 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 24 Jul 2023 14:36:05 -0300 Subject: [PATCH 1121/2093] iommu/sprd: Add missing force_aperture [ Upstream commit d48a51286c698f7fe8efc688f23a532f4fe9a904 ] force_aperture was intended to false only by GART drivers that have an identity translation outside the aperture. This does not describe sprd, so add the missing 'force_aperture = true'. Fixes: b23e4fc4e3fa ("iommu: add Unisoc IOMMU basic driver") Signed-off-by: Jason Gunthorpe Acked-by: Chunyan Zhang Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/sprd-iommu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index fadd2c907222..8261066de07d 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -147,6 +147,7 @@ static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) dom->domain.geometry.aperture_start = 0; dom->domain.geometry.aperture_end = SZ_256M - 1; + dom->domain.geometry.force_aperture = true; return &dom->domain; } From c48b0b30ac928bc2aec59928cbb97d7fdc3db991 Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Fri, 4 Aug 2023 09:27:08 +0800 Subject: [PATCH 1122/2093] RDMA/hns: Fix port active speed [ Upstream commit df1bcf90a66a10967a3a43510b42cb3566208011 ] HW supports a variety of different speed, but the current speed is fixed. The real speed should be querried from ethernet. Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Signed-off-by: Chengchang Tang Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20230804012711.808069-2-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 946ba1109e87..da1b33d818d8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -219,6 +219,7 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u32 port_num, unsigned long flags; enum ib_mtu mtu; u32 port; + int ret; port = port_num - 1; @@ -231,8 +232,10 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u32 port_num, IB_PORT_BOOT_MGMT_SUP; props->max_msg_sz = HNS_ROCE_MAX_MSG_LEN; props->pkey_tbl_len = 1; - props->active_width = IB_WIDTH_4X; - props->active_speed = 1; + ret = ib_get_eth_speed(ib_dev, port_num, &props->active_speed, + &props->active_width); + if (ret) + ibdev_warn(ib_dev, "failed to get speed, ret = %d.\n", ret); spin_lock_irqsave(&hr_dev->iboe.lock, flags); From 93c986805f4e7522a955b39658324c15da9f0c5a Mon Sep 17 00:00:00 2001 From: Junxian Huang Date: Fri, 4 Aug 2023 09:27:09 +0800 Subject: [PATCH 1123/2093] RDMA/hns: Fix incorrect post-send with direct wqe of wr-list [ Upstream commit 706efac4477cdb8be857f6322457de524acc02ff ] Currently, direct wqe is not supported for wr-list. RoCE driver excludes direct wqe for wr-list by judging whether the number of wr is 1. For a wr-list where the second wr is a length-error atomic wr, the post-send driver handles the first wr and adds 1 to the wr number counter firstly. While handling the second wr, the driver finds out a length error and terminates the wr handle process, remaining the counter at 1. This causes the driver mistakenly judges there is only 1 wr and thus enters the direct wqe process, carrying the current length-error atomic wqe. This patch fixes the error by adding a judgement whether the current wr is a bad wr. If so, use the normal doorbell process but not direct wqe despite the wr number is 1. Fixes: 01584a5edcc4 ("RDMA/hns: Add support of direct wqe") Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20230804012711.808069-3-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 34a270b6891a..e9a1985f7f17 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -757,7 +757,8 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, qp->sq.head += nreq; qp->next_sge = sge_idx; - if (nreq == 1 && (qp->en_flags & HNS_ROCE_QP_CAP_DIRECT_WQE)) + if (nreq == 1 && !ret && + (qp->en_flags & HNS_ROCE_QP_CAP_DIRECT_WQE)) write_dwqe(hr_dev, qp, wqe); else update_sq_db(hr_dev, qp); From 2368ce8cd5ad921c8fd56e900ae4861652660578 Mon Sep 17 00:00:00 2001 From: Junxian Huang Date: Fri, 4 Aug 2023 09:27:10 +0800 Subject: [PATCH 1124/2093] RDMA/hns: Fix inaccurate error label name in init instance [ Upstream commit c9c0bd3c177d93d80968f720304087ba83fe8f74 ] This patch fixes inaccurate error label name in init instance. Fixes: 70f92521584f ("RDMA/hns: Use the reserved loopback QPs to free MR before destroying MPT") Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20230804012711.808069-4-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index e9a1985f7f17..33980485ef5b 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -6865,14 +6865,14 @@ static int __hns_roce_hw_v2_init_instance(struct hnae3_handle *handle) ret = hns_roce_init(hr_dev); if (ret) { dev_err(hr_dev->dev, "RoCE Engine init failed!\n"); - goto error_failed_cfg; + goto error_failed_roce_init; } if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) { ret = free_mr_init(hr_dev); if (ret) { dev_err(hr_dev->dev, "failed to init free mr!\n"); - goto error_failed_roce_init; + goto error_failed_free_mr_init; } } @@ -6880,10 +6880,10 @@ static int __hns_roce_hw_v2_init_instance(struct hnae3_handle *handle) return 0; -error_failed_roce_init: +error_failed_free_mr_init: hns_roce_exit(hr_dev); -error_failed_cfg: +error_failed_roce_init: kfree(hr_dev->priv); error_failed_kzalloc: From 4dca13c30b9e7e7c426d8aa2f481ebf6f20cf872 Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Fri, 4 Aug 2023 09:27:11 +0800 Subject: [PATCH 1125/2093] RDMA/hns: Fix CQ and QP cache affinity [ Upstream commit 9e03dbea2b0634b21a45946b4f8097e0dc86ebe1 ] Currently, the affinity between QP cache and CQ cache is not considered when assigning QPN, it will affect the message rate of HW. Allocate QPN from QP cache with better CQ affinity to get better performance. Fixes: 71586dd20010 ("RDMA/hns: Create QP with selected QPN for bank load balance") Signed-off-by: Chengchang Tang Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20230804012711.808069-5-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_device.h | 1 + drivers/infiniband/hw/hns/hns_roce_qp.c | 28 ++++++++++++++++----- 2 files changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index f701cc86896b..1112afa0af55 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -97,6 +97,7 @@ #define HNS_ROCE_CQ_BANK_NUM 4 #define CQ_BANKID_SHIFT 2 +#define CQ_BANKID_MASK GENMASK(1, 0) enum { SERV_TYPE_RC, diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 0ae335fb205c..7a95f8677a02 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -170,14 +170,29 @@ static void hns_roce_ib_qp_event(struct hns_roce_qp *hr_qp, } } -static u8 get_least_load_bankid_for_qp(struct hns_roce_bank *bank) +static u8 get_affinity_cq_bank(u8 qp_bank) { - u32 least_load = bank[0].inuse; + return (qp_bank >> 1) & CQ_BANKID_MASK; +} + +static u8 get_least_load_bankid_for_qp(struct ib_qp_init_attr *init_attr, + struct hns_roce_bank *bank) +{ +#define INVALID_LOAD_QPNUM 0xFFFFFFFF + struct ib_cq *scq = init_attr->send_cq; + u32 least_load = INVALID_LOAD_QPNUM; + unsigned long cqn = 0; u8 bankid = 0; u32 bankcnt; u8 i; - for (i = 1; i < HNS_ROCE_QP_BANK_NUM; i++) { + if (scq) + cqn = to_hr_cq(scq)->cqn; + + for (i = 0; i < HNS_ROCE_QP_BANK_NUM; i++) { + if (scq && (get_affinity_cq_bank(i) != (cqn & CQ_BANKID_MASK))) + continue; + bankcnt = bank[i].inuse; if (bankcnt < least_load) { least_load = bankcnt; @@ -209,7 +224,8 @@ static int alloc_qpn_with_bankid(struct hns_roce_bank *bank, u8 bankid, return 0; } -static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) +static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, + struct ib_qp_init_attr *init_attr) { struct hns_roce_qp_table *qp_table = &hr_dev->qp_table; unsigned long num = 0; @@ -220,7 +236,7 @@ static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) num = 1; } else { mutex_lock(&qp_table->bank_mutex); - bankid = get_least_load_bankid_for_qp(qp_table->bank); + bankid = get_least_load_bankid_for_qp(init_attr, qp_table->bank); ret = alloc_qpn_with_bankid(&qp_table->bank[bankid], bankid, &num); @@ -1146,7 +1162,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev, goto err_buf; } - ret = alloc_qpn(hr_dev, hr_qp); + ret = alloc_qpn(hr_dev, hr_qp, init_attr); if (ret) { ibdev_err(ibdev, "failed to alloc QPN, ret = %d.\n", ret); goto err_qpn; From d020963638f2b918f72290afe1e4259bbdf0c2af Mon Sep 17 00:00:00 2001 From: Xiang Yang Date: Fri, 4 Aug 2023 10:25:25 +0800 Subject: [PATCH 1126/2093] IB/uverbs: Fix an potential error pointer dereference [ Upstream commit 26b7d1a27167e7adf75b150755e05d2bc123ce55 ] smatch reports the warning below: drivers/infiniband/core/uverbs_std_types_counters.c:110 ib_uverbs_handler_UVERBS_METHOD_COUNTERS_READ() error: 'uattr' dereferencing possible ERR_PTR() The return value of uattr maybe ERR_PTR(-ENOENT), fix this by checking the value of uattr before using it. Fixes: ebb6796bd397 ("IB/uverbs: Add read counters support") Signed-off-by: Xiang Yang Link: https://lore.kernel.org/r/20230804022525.1916766-1-xiangyang3@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/uverbs_std_types_counters.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/core/uverbs_std_types_counters.c b/drivers/infiniband/core/uverbs_std_types_counters.c index 999da9c79866..381aa5797641 100644 --- a/drivers/infiniband/core/uverbs_std_types_counters.c +++ b/drivers/infiniband/core/uverbs_std_types_counters.c @@ -107,6 +107,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_COUNTERS_READ)( return ret; uattr = uverbs_attr_get(attrs, UVERBS_ATTR_READ_COUNTERS_BUFF); + if (IS_ERR(uattr)) + return PTR_ERR(uattr); read_attr.ncounters = uattr->ptr_attr.len / sizeof(u64); read_attr.counters_buff = uverbs_zalloc( attrs, array_size(read_attr.ncounters, sizeof(u64))); From a30f26dc3ad9a7d3675f75ae51d320fa771181d7 Mon Sep 17 00:00:00 2001 From: Eddie James Date: Mon, 12 Jun 2023 14:56:50 -0500 Subject: [PATCH 1127/2093] fsi: aspeed: Reset master errors after CFAM reset [ Upstream commit 52300909f4670ac552bfeb33c1355b896eac8c06 ] It has been observed that sometimes the FSI master will return all 0xffs after a CFAM has been taken out of reset, without presenting any error. Resetting the FSI master errors resolves the issue. Fixes: 4a851d714ead ("fsi: aspeed: Support CFAM reset GPIO") Signed-off-by: Eddie James Link: https://lore.kernel.org/r/20230612195657.245125-8-eajames@linux.ibm.com Signed-off-by: Joel Stanley Signed-off-by: Sasha Levin --- drivers/fsi/fsi-master-aspeed.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/fsi/fsi-master-aspeed.c b/drivers/fsi/fsi-master-aspeed.c index 7cec1772820d..5eccab175e86 100644 --- a/drivers/fsi/fsi-master-aspeed.c +++ b/drivers/fsi/fsi-master-aspeed.c @@ -454,6 +454,8 @@ static ssize_t cfam_reset_store(struct device *dev, struct device_attribute *att gpiod_set_value(aspeed->cfam_reset_gpio, 1); usleep_range(900, 1000); gpiod_set_value(aspeed->cfam_reset_gpio, 0); + usleep_range(900, 1000); + opb_writel(aspeed, ctrl_base + FSI_MRESP0, cpu_to_be32(FSI_MRESP_RST_ALL_MASTER)); mutex_unlock(&aspeed->lock); trace_fsi_master_aspeed_cfam_reset(false); From d9c47d2bf3073bc78cd4f9f8a2a8c47d5d6c6031 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 22 Jun 2023 11:27:39 +0200 Subject: [PATCH 1128/2093] iommu/qcom: Disable and reset context bank before programming [ Upstream commit 9f3fef23d9b5a858a6e6d5f478bb1b6b76265e76 ] Writing the new TTBRs, TCRs and MAIRs on a previously enabled context bank may trigger a context fault, resulting in firmware driven AP resets: change the domain initialization programming sequence to disable the context bank(s) and to also clear the related fault address (CB_FAR) and fault status (CB_FSR) registers before writing new values to TTBR0/1, TCR/TCR2, MAIR0/1. Fixes: 0ae349a0f33f ("iommu/qcom: Add qcom_iommu") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230622092742.74819-4-angelogioacchino.delregno@collabora.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index 3869c3ecda8c..5b9cb9fcc352 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -273,6 +273,13 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, ctx->secure_init = true; } + /* Disable context bank before programming */ + iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0); + + /* Clear context bank fault address fault status registers */ + iommu_writel(ctx, ARM_SMMU_CB_FAR, 0); + iommu_writel(ctx, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT); + /* TTBRs */ iommu_writeq(ctx, ARM_SMMU_CB_TTBR0, pgtbl_cfg.arm_lpae_s1_cfg.ttbr | From 45e3181d7995f66057bb0627f6c2994111bb86a1 Mon Sep 17 00:00:00 2001 From: Yanfei Xu Date: Wed, 9 Aug 2023 20:48:04 +0800 Subject: [PATCH 1129/2093] iommu/vt-d: Fix to flush cache of PASID directory table [ Upstream commit 8a3b8e63f8371c1247b7aa24ff9c5312f1a6948b ] Even the PCI devices don't support pasid capability, PASID table is mandatory for a PCI device in scalable mode. However flushing cache of pasid directory table for these devices are not taken after pasid table is allocated as the "size" of table is zero. Fix it by calculating the size by page order. Found this when reading the code, no real problem encountered for now. Fixes: 194b3348bdbb ("iommu/vt-d: Fix PASID directory pointer coherency") Suggested-by: Lu Baolu Signed-off-by: Yanfei Xu Link: https://lore.kernel.org/r/20230616081045.721873-1-yanfei.xu@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/intel/pasid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index a39aab66a01b..3f03039e5cce 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -127,7 +127,7 @@ int intel_pasid_alloc_table(struct device *dev) info->pasid_table = pasid_table; if (!ecap_coherent(info->iommu->ecap)) - clflush_cache_range(pasid_table->table, size); + clflush_cache_range(pasid_table->table, (1 << order) * PAGE_SIZE); return 0; } From 6ced15ff1746006476f1407fe722911a45a7874d Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Sat, 5 Aug 2023 07:36:10 +0200 Subject: [PATCH 1130/2093] platform/x86: dell-sysman: Fix reference leak [ Upstream commit 7295a996fdab7bf83dc3d4078fa8b139b8e0a1bf ] If a duplicate attribute is found using kset_find_obj(), a reference to that attribute is returned. This means that we need to dispose it accordingly. Use kobject_put() to dispose the duplicate attribute in such a case. Compile-tested only. Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems") Signed-off-by: Armin Wolf Link: https://lore.kernel.org/r/20230805053610.7106-1-W_Armin@gmx.de Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/dell/dell-wmi-sysman/sysman.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index 0a6411a8a104..b2406a595be9 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -396,6 +396,7 @@ static int init_bios_attributes(int attr_type, const char *guid) struct kobject *attr_name_kobj; //individual attribute names union acpi_object *obj = NULL; union acpi_object *elements; + struct kobject *duplicate; struct kset *tmp_set; int min_elements; @@ -454,9 +455,11 @@ static int init_bios_attributes(int attr_type, const char *guid) else tmp_set = wmi_priv.main_dir_kset; - if (kset_find_obj(tmp_set, elements[ATTR_NAME].string.pointer)) { - pr_debug("duplicate attribute name found - %s\n", - elements[ATTR_NAME].string.pointer); + duplicate = kset_find_obj(tmp_set, elements[ATTR_NAME].string.pointer); + if (duplicate) { + pr_debug("Duplicate attribute name found - %s\n", + elements[ATTR_NAME].string.pointer); + kobject_put(duplicate); goto nextobj; } From d6610151ae22954bdec1d154022072b57a9ac487 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 12 Jun 2023 15:58:37 +0200 Subject: [PATCH 1131/2093] media: cec: core: add adap_nb_transmit_canceled() callback [ Upstream commit da53c36ddd3f118a525a04faa8c47ca471e6c467 ] A potential deadlock was found by Zheng Zhang with a local syzkaller instance. The problem is that when a non-blocking CEC transmit is canceled by calling cec_data_cancel, that in turn can call the high-level received() driver callback, which can call cec_transmit_msg() to transmit a new message. The cec_data_cancel() function is called with the adap->lock mutex held, and cec_transmit_msg() tries to take that same lock. The root cause is that the received() callback can either be used to pass on a received message (and then adap->lock is not held), or to report a canceled transmit (and then adap->lock is held). This is confusing, so create a new low-level adap_nb_transmit_canceled callback that reports back that a non-blocking transmit was canceled. And the received() callback is only called when a message is received, as was the case before commit f9d0ecbf56f4 ("media: cec: correctly pass on reply results") complicated matters. Reported-by: Zheng Zhang Signed-off-by: Hans Verkuil Fixes: f9d0ecbf56f4 ("media: cec: correctly pass on reply results") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/cec/core/cec-adap.c | 4 ++-- include/media/cec.h | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index b1512f9c5895..aed3e51d6d35 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -385,8 +385,8 @@ static void cec_data_cancel(struct cec_data *data, u8 tx_status, u8 rx_status) cec_queue_msg_monitor(adap, &data->msg, 1); if (!data->blocking && data->msg.sequence) - /* Allow drivers to process the message first */ - call_op(adap, received, &data->msg); + /* Allow drivers to react to a canceled transmit */ + call_void_op(adap, adap_nb_transmit_canceled, &data->msg); cec_data_completed(data); } diff --git a/include/media/cec.h b/include/media/cec.h index abee41ae02d0..6556cc161dc0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -121,14 +121,16 @@ struct cec_adap_ops { void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); + void (*adap_nb_transmit_canceled)(struct cec_adapter *adap, + const struct cec_msg *msg); void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); void (*adap_free)(struct cec_adapter *adap); - /* Error injection callbacks */ + /* Error injection callbacks, called without adap->lock held */ int (*error_inj_show)(struct cec_adapter *adap, struct seq_file *sf); bool (*error_inj_parse_line)(struct cec_adapter *adap, char *line); - /* High-level CEC message callback */ + /* High-level CEC message callback, called without adap->lock held */ int (*received)(struct cec_adapter *adap, struct cec_msg *msg); }; From 0294e2475092525075e1271d58f6283564a818a3 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 12 Jun 2023 15:58:38 +0200 Subject: [PATCH 1132/2093] media: cec: core: add adap_unconfigured() callback [ Upstream commit 948a77aaecf202f722cf2264025f9987e5bd5c26 ] The adap_configured() callback was called with the adap->lock mutex held if the 'configured' argument was false, and without the adap->lock mutex held if that argument was true. That was very confusing, and so split this up in a adap_unconfigured() callback and a high-level configured() callback. This also makes it easier to understand when the mutex is held: all low-level adap_* callbacks are called with the mutex held. All other callbacks are called without that mutex held. Signed-off-by: Hans Verkuil Fixes: f1b57164305d ("media: cec: add optional adap_configured callback") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/cec/core/cec-adap.c | 4 ++-- include/media/cec.h | 5 +++-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index aed3e51d6d35..4bc2a705029e 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1345,7 +1345,7 @@ static void cec_adap_unconfigure(struct cec_adapter *adap) cec_flush(adap); wake_up_interruptible(&adap->kthread_waitq); cec_post_state_event(adap); - call_void_op(adap, adap_configured, false); + call_void_op(adap, adap_unconfigured); } /* @@ -1536,7 +1536,7 @@ static int cec_config_thread_func(void *arg) adap->kthread_config = NULL; complete(&adap->config_completion); mutex_unlock(&adap->lock); - call_void_op(adap, adap_configured, true); + call_void_op(adap, configured); return 0; unconfigure: diff --git a/include/media/cec.h b/include/media/cec.h index 6556cc161dc0..9c007f83569a 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -113,12 +113,12 @@ struct cec_fh { #define CEC_FREE_TIME_TO_USEC(ft) ((ft) * 2400) struct cec_adap_ops { - /* Low-level callbacks */ + /* Low-level callbacks, called with adap->lock held */ int (*adap_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_pin_enable)(struct cec_adapter *adap, bool enable); int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); - void (*adap_configured)(struct cec_adapter *adap, bool configured); + void (*adap_unconfigured)(struct cec_adapter *adap); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); void (*adap_nb_transmit_canceled)(struct cec_adapter *adap, @@ -131,6 +131,7 @@ struct cec_adap_ops { bool (*error_inj_parse_line)(struct cec_adapter *adap, char *line); /* High-level CEC message callback, called without adap->lock held */ + void (*configured)(struct cec_adapter *adap); int (*received)(struct cec_adapter *adap, struct cec_msg *msg); }; From d52509fdb29c2e4f407aa8bcae64126de4c8dc39 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 27 Jul 2023 19:40:07 +0200 Subject: [PATCH 1133/2093] media: go7007: Remove redundant if statement [ Upstream commit f33cb49081da0ec5af0888f8ecbd566bd326eed1 ] The if statement that compares msgs[i].len != 3 is always false because it is in a code block where msg[i].len is equal to 3. The check is redundant and can be removed. As detected by cppcheck static analysis: drivers/media/usb/go7007/go7007-i2c.c:168:20: warning: Opposite inner 'if' condition leads to a dead code block. [oppositeInnerCondition] Link: https://lore.kernel.org/linux-media/20230727174007.635572-1-colin.i.king@gmail.com Fixes: 866b8695d67e ("Staging: add the go7007 video driver") Signed-off-by: Colin Ian King Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/go7007/go7007-i2c.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/media/usb/go7007/go7007-i2c.c b/drivers/media/usb/go7007/go7007-i2c.c index 38339dd2f83f..2880370e45c8 100644 --- a/drivers/media/usb/go7007/go7007-i2c.c +++ b/drivers/media/usb/go7007/go7007-i2c.c @@ -165,8 +165,6 @@ static int go7007_i2c_master_xfer(struct i2c_adapter *adapter, } else if (msgs[i].len == 3) { if (msgs[i].flags & I2C_M_RD) return -EIO; - if (msgs[i].len != 3) - return -EIO; if (go7007_i2c_xfer(go, msgs[i].addr, 0, (msgs[i].buf[0] << 8) | msgs[i].buf[1], 0x01, &msgs[i].buf[2]) < 0) From c90182cffbff274b1692757194d6225f018d9b72 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 30 May 2023 14:30:35 +0200 Subject: [PATCH 1134/2093] media: venus: hfi_venus: Only consider sys_idle_indicator on V1 [ Upstream commit 6283e4834c69fa93a108efa18c6aa09c7e626f49 ] As per information from Qualcomm [1], this property is not really supported beyond msm8916 (HFI V1) and some newer HFI versions really dislike receiving it, going as far as crashing the device. Only consider toggling it (via the module option) on HFIV1. While at it, get rid of the global static variable (which defaulted to zero) which was never explicitly assigned to for V1. Note: [1] is a reply to the actual message in question, as lore did not properly receive some of the emails.. [1] https://lore.kernel.org/lkml/955cd520-3881-0c22-d818-13fe9a47e124@linaro.org/ Fixes: 7ed9e0b3393c ("media: venus: hfi, vdec: v6 Add IS_V6() to existing IS_V4() if locations") Signed-off-by: Konrad Dybcio Signed-off-by: Stanimir Varbanov Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/hfi_venus.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index 2ad40b3945b0..bff435abd59b 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -131,7 +131,6 @@ struct venus_hfi_device { static bool venus_pkt_debug; int venus_fw_debug = HFI_DEBUG_MSG_ERROR | HFI_DEBUG_MSG_FATAL; -static bool venus_sys_idle_indicator; static bool venus_fw_low_power_mode = true; static int venus_hw_rsp_timeout = 1000; static bool venus_fw_coverage; @@ -947,17 +946,12 @@ static int venus_sys_set_default_properties(struct venus_hfi_device *hdev) if (ret) dev_warn(dev, "setting fw debug msg ON failed (%d)\n", ret); - /* - * Idle indicator is disabled by default on some 4xx firmware versions, - * enable it explicitly in order to make suspend functional by checking - * WFI (wait-for-interrupt) bit. - */ - if (IS_V4(hdev->core) || IS_V6(hdev->core)) - venus_sys_idle_indicator = true; - - ret = venus_sys_set_idle_message(hdev, venus_sys_idle_indicator); - if (ret) - dev_warn(dev, "setting idle response ON failed (%d)\n", ret); + /* HFI_PROPERTY_SYS_IDLE_INDICATOR is not supported beyond 8916 (HFI V1) */ + if (IS_V1(hdev->core)) { + ret = venus_sys_set_idle_message(hdev, false); + if (ret) + dev_warn(dev, "setting idle response ON failed (%d)\n", ret); + } ret = venus_sys_set_power_control(hdev, venus_fw_low_power_mode); if (ret) From 365ce3f86bb165cd0d92af8454bdfabe03ca0554 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 9 Jul 2023 22:23:05 -0700 Subject: [PATCH 1135/2093] docs: ABI: fix spelling/grammar in SBEFIFO timeout interface [ Upstream commit 2cd9ec2a51474d4c0b4d2a061f2de7da34eff476 ] Correct spelling problems as identified by codespell. Correct one grammar error. Fixes: 9a93de620e0a ("docs: ABI: testing: Document the SBEFIFO timeout interface") Signed-off-by: Randy Dunlap Cc: Eddie James Cc: Joel Stanley Link: https://lore.kernel.org/r/20230710052305.29611-1-rdunlap@infradead.org Signed-off-by: Joel Stanley Signed-off-by: Sasha Levin --- Documentation/ABI/testing/sysfs-bus-fsi-devices-sbefifo | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-fsi-devices-sbefifo b/Documentation/ABI/testing/sysfs-bus-fsi-devices-sbefifo index 531fe9d6b40a..c7393b4dd2d8 100644 --- a/Documentation/ABI/testing/sysfs-bus-fsi-devices-sbefifo +++ b/Documentation/ABI/testing/sysfs-bus-fsi-devices-sbefifo @@ -5,6 +5,6 @@ Description: Indicates whether or not this SBE device has experienced a timeout; i.e. the SBE did not respond within the time allotted by the driver. A value of 1 indicates that a timeout has - ocurred and no transfers have completed since the timeout. A - value of 0 indicates that no timeout has ocurred, or if one - has, more recent transfers have completed successful. + occurred and no transfers have completed since the timeout. A + value of 0 indicates that no timeout has occurred, or if one + has, more recent transfers have completed successfully. From 324da2f3ee73b82d823e09c6bde3a8d7385792ea Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 11 Aug 2023 13:44:38 -0400 Subject: [PATCH 1136/2093] USB: gadget: core: Add missing kerneldoc for vbus_work [ Upstream commit 159a98afc88e88f588077afe818081d67f50a5e0 ] Add a missing kerneldoc description of the vbus_work field in struct usb_udc. Signed-off-by: Alan Stern Fixes: 50966da807c8 ("usb: gadget: udc: core: Offload usb_udc_vbus_handler processing") Link: https://lore.kernel.org/r/1e5e7cda-b2c8-4917-9952-4354f365ede0@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 316e9cc3987b..1c0c61e8ba69 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -40,6 +40,7 @@ static struct bus_type gadget_bus_type; * @allow_connect: Indicates whether UDC is allowed to be pulled up. * Set/cleared by gadget_(un)bind_driver() after gadget driver is bound or * unbound. + * @vbus_work: work routine to handle VBUS status change notifications. * @connect_lock: protects udc->started, gadget->connect, * gadget->allow_connect and gadget->deactivate. The routines * usb_gadget_connect_locked(), usb_gadget_disconnect_locked(), From 66eb45e7d5fc843b093c035b987603735caf92d6 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 11 Aug 2023 13:47:04 -0400 Subject: [PATCH 1137/2093] USB: gadget: f_mass_storage: Fix unused variable warning [ Upstream commit 55c3e571d2a0aabef4f1354604443f1c415d2e85 ] Fix a "variable set but not used" warning in f_mass_storage.c. rc is used if verbose debugging is enabled but not otherwise. Signed-off-by: Alan Stern Fixes: d5e2b67aae79 ("USB: g_mass_storage: template f_mass_storage.c file created") Link: https://lore.kernel.org/r/cfed16c7-aa46-494b-ba84-b0e0dc99be3a@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_mass_storage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 3abf7f586e2a..7b9a4cf9b100 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -926,7 +926,7 @@ static void invalidate_sub(struct fsg_lun *curlun) { struct file *filp = curlun->filp; struct inode *inode = file_inode(filp); - unsigned long rc; + unsigned long __maybe_unused rc; rc = invalidate_mapping_pages(inode->i_mapping, 0, -1); VLDBG(curlun, "invalidate_mapping_pages -> %ld\n", rc); From 297992e5c63528e603666e36081836204fc36ec9 Mon Sep 17 00:00:00 2001 From: David Gow Date: Thu, 20 Jul 2023 14:45:09 +0200 Subject: [PATCH 1138/2093] drivers: base: Free devm resources when unregistering a device [ Upstream commit 699fb50d99039a50e7494de644f96c889279aca3 ] In the current code, devres_release_all() only gets called if the device has a bus and has been probed. This leads to issues when using bus-less or driver-less devices where the device might never get freed if a managed resource holds a reference to the device. This is happening in the DRM framework for example. We should thus call devres_release_all() in the device_del() function to make sure that the device-managed actions are properly executed when the device is unregistered, even if it has neither a bus nor a driver. This is effectively the same change than commit 2f8d16a996da ("devres: release resources on device_del()") that got reverted by commit a525a3ddeaca ("driver core: free devres in device_release") over memory leaks concerns. This patch effectively combines the two commits mentioned above to release the resources both on device_del() and device_release() and get the best of both worlds. Fixes: a525a3ddeaca ("driver core: free devres in device_release") Signed-off-by: David Gow Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20230720-kunit-devm-inconsistencies-test-v3-3-6aa7e074f373@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/base/core.c b/drivers/base/core.c index e30223c2672f..af90bfb0cc3d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3855,6 +3855,17 @@ void device_del(struct device *dev) device_platform_notify_remove(dev); device_links_purge(dev); + /* + * If a device does not have a driver attached, we need to clean + * up any managed resources. We do this in device_release(), but + * it's never called (and we leak the device) if a managed + * resource holds a reference to the device. So release all + * managed resources here, like we do in driver_detach(). We + * still need to do so again in device_release() in case someone + * adds a new resource after this point, though. + */ + devres_release_all(dev); + if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_REMOVED_DEVICE, dev); From a4cd2c3eff1840aa108920a7a530ba43fa134800 Mon Sep 17 00:00:00 2001 From: Illia Ostapyshyn Date: Tue, 13 Jun 2023 17:26:00 +0200 Subject: [PATCH 1139/2093] HID: input: Support devices sending Eraser without Invert [ Upstream commit 276e14e6c3993317257e1787e93b7166fbc30905 ] Some digitizers (notably XP-Pen Artist 24) do not report the Invert usage when erasing. This causes the device to be permanently stuck with the BTN_TOOL_RUBBER tool after sending Eraser, as Invert is the only usage that can release the tool. In this state, Touch and Inrange are no longer reported to userspace, rendering the pen unusable. Prior to commit 87562fcd1342 ("HID: input: remove the need for HID_QUIRK_INVERT"), BTN_TOOL_RUBBER was never set and Eraser events were simply translated into BTN_TOUCH without causing an inconsistent state. Introduce HID_QUIRK_NOINVERT for such digitizers and detect them during hidinput_configure_usage(). This quirk causes the tool to be released as soon as Eraser is reported as not set. Set BTN_TOOL_RUBBER in input->keybit when mapping Eraser. Fixes: 87562fcd1342 ("HID: input: remove the need for HID_QUIRK_INVERT") Co-developed-by: Nils Fuhler Signed-off-by: Nils Fuhler Signed-off-by: Illia Ostapyshyn Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-input.c | 18 ++++++++++++++++-- include/linux/hid.h | 1 + 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 3acaaca888ac..77ee5e01e611 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -961,6 +961,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel return; case 0x3c: /* Invert */ + device->quirks &= ~HID_QUIRK_NOINVERT; map_key_clear(BTN_TOOL_RUBBER); break; @@ -986,9 +987,13 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x45: /* ERASER */ /* * This event is reported when eraser tip touches the surface. - * Actual eraser (BTN_TOOL_RUBBER) is set by Invert usage when - * tool gets in proximity. + * Actual eraser (BTN_TOOL_RUBBER) is set and released either + * by Invert if tool reports proximity or by Eraser directly. */ + if (!test_bit(BTN_TOOL_RUBBER, input->keybit)) { + device->quirks |= HID_QUIRK_NOINVERT; + set_bit(BTN_TOOL_RUBBER, input->keybit); + } map_key_clear(BTN_TOUCH); break; @@ -1532,6 +1537,15 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct else if (report->tool != BTN_TOOL_RUBBER) /* value is off, tool is not rubber, ignore */ return; + else if (*quirks & HID_QUIRK_NOINVERT && + !test_bit(BTN_TOUCH, input->key)) { + /* + * There is no invert to release the tool, let hid_input + * send BTN_TOUCH with scancode and release the tool after. + */ + hid_report_release_tool(report, input, BTN_TOOL_RUBBER); + return; + } /* let hid-input set BTN_TOUCH */ break; diff --git a/include/linux/hid.h b/include/linux/hid.h index 0a1ccc68e798..784dd6b6046e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -357,6 +357,7 @@ struct hid_item { #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP BIT(18) #define HID_QUIRK_HAVE_SPECIAL_DRIVER BIT(19) #define HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE BIT(20) +#define HID_QUIRK_NOINVERT BIT(21) #define HID_QUIRK_FULLSPEED_INTERVAL BIT(28) #define HID_QUIRK_NO_INIT_REPORTS BIT(29) #define HID_QUIRK_NO_IGNORE BIT(30) From 5074c70795d4d7aeab351517d8f25472d996cd31 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 2 Aug 2023 16:47:25 +0200 Subject: [PATCH 1140/2093] media: ov5640: Enable MIPI interface in ov5640_set_power_mipi() [ Upstream commit 98cb72d3b9c5e03b10fa993752ecfcbd9c572d8c ] Set OV5640_REG_IO_MIPI_CTRL00 bit 2 to 1 instead of 0, since 1 means MIPI CSI2 interface, while 0 means CPI parallel interface. In the ov5640_set_power_mipi() the interface should obviously be set to MIPI CSI2 since this functions is used to power up the sensor when operated in MIPI CSI2 mode. The sensor should not be in CPI mode in that case. This fixes a corner case where capturing the first frame on i.MX8MN with CSI/ISI resulted in corrupted frame. Fixes: aa4bb8b8838f ("media: ov5640: Re-work MIPI startup sequence") Reviewed-by: Jacopo Mondi Tested-by: Jacopo Mondi # [Test on imx6q] Signed-off-by: Marek Vasut Tested-by: Jai Luthra # [Test on bplay, sk-am62] Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov5640.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index cc23ff2067f6..f76bcb395cff 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -2531,9 +2531,9 @@ static int ov5640_set_power_mipi(struct ov5640_dev *sensor, bool on) * "ov5640_set_stream_mipi()") * [4] = 0 : Power up MIPI HS Tx * [3] = 0 : Power up MIPI LS Rx - * [2] = 0 : MIPI interface disabled + * [2] = 1 : MIPI interface enabled */ - ret = ov5640_write_reg(sensor, OV5640_REG_IO_MIPI_CTRL00, 0x40); + ret = ov5640_write_reg(sensor, OV5640_REG_IO_MIPI_CTRL00, 0x44); if (ret) return ret; From 2b9d0a65d133d72c80b6ace7eba02ee7527bd9ae Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 25 Jul 2023 00:21:16 +0200 Subject: [PATCH 1141/2093] media: ov5640: Fix initial RESETB state and annotate timings [ Upstream commit a210df337c5f5c2cd82f36c9dbb154ec63365c80 ] The initial state of RESETB input signal of OV5640 should be asserted, i.e. the sensor should be in reset. This is not the case, make it so. Since the subsequent assertion of RESETB signal is no longer necessary and the timing of the power sequencing could be slightly adjusted, add annotations to the delays which match OV5640 datasheet rev. 2.03, both: figure 2-3 power up timing with internal DVDD figure 2-4 power up timing with external DVDD source The 5..10ms delay between PWDN assertion and RESETB assertion is not even documented in the power sequencing diagram, and with this reset fix, it is no longer even necessary. Fixes: 19a81c1426c1 ("[media] add Omnivision OV5640 sensor driver") Reported-by: Jacopo Mondi Signed-off-by: Marek Vasut Reviewed-by: Jacopo Mondi Tested-by: Jai Luthra Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov5640.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index f76bcb395cff..2ee832426736 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -2441,16 +2441,13 @@ static void ov5640_power(struct ov5640_dev *sensor, bool enable) static void ov5640_powerup_sequence(struct ov5640_dev *sensor) { if (sensor->pwdn_gpio) { - gpiod_set_value_cansleep(sensor->reset_gpio, 0); + gpiod_set_value_cansleep(sensor->reset_gpio, 1); /* camera power cycle */ ov5640_power(sensor, false); - usleep_range(5000, 10000); + usleep_range(5000, 10000); /* t2 */ ov5640_power(sensor, true); - usleep_range(5000, 10000); - - gpiod_set_value_cansleep(sensor->reset_gpio, 1); - usleep_range(1000, 2000); + usleep_range(1000, 2000); /* t3 */ gpiod_set_value_cansleep(sensor->reset_gpio, 0); } else { @@ -2458,7 +2455,7 @@ static void ov5640_powerup_sequence(struct ov5640_dev *sensor) ov5640_write_reg(sensor, OV5640_REG_SYS_CTRL0, OV5640_REG_SYS_CTRL0_SW_RST); } - usleep_range(20000, 25000); + usleep_range(20000, 25000); /* t4 */ /* * software standby: allows registers programming; From 9e6e509c08f69063488121ced53047e468d648ce Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Mon, 5 Dec 2022 15:21:45 +0000 Subject: [PATCH 1142/2093] media: i2c: ov2680: Set V4L2_CTRL_FLAG_MODIFY_LAYOUT on flips [ Upstream commit 66274280b2c745d380508dc27b9a4dfd736e5eda ] The driver changes the Bayer order based on the flips, but does not define the control correctly with the V4L2_CTRL_FLAG_MODIFY_LAYOUT flag. Add the V4L2_CTRL_FLAG_MODIFY_LAYOUT flag. Signed-off-by: Dave Stevenson Acked-by: Rui Miguel Silva Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: 7b5a42e6ae71 ("media: ov2680: Remove auto-gain and auto-exposure controls") Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index de66d3395a4d..54153bf66bdd 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -967,6 +967,8 @@ static int ov2680_v4l2_register(struct ov2680_dev *sensor) ctrls->gain->flags |= V4L2_CTRL_FLAG_VOLATILE; ctrls->exposure->flags |= V4L2_CTRL_FLAG_VOLATILE; + ctrls->vflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; + ctrls->hflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; v4l2_ctrl_auto_cluster(2, &ctrls->auto_gain, 0, true); v4l2_ctrl_auto_cluster(2, &ctrls->auto_exp, 1, true); From ef9055e9a768e94ee2febd567acfbdbe2f0d2a63 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:16 +0200 Subject: [PATCH 1143/2093] media: ov2680: Remove auto-gain and auto-exposure controls [ Upstream commit 7b5a42e6ae71927359ea67a2c22570ba97fa4059 ] Quoting the OV2680 datasheet: "3.2 exposure and gain control In the OV2680, the exposure time and gain are set manually from an external controller. The OV2680 supports manual gain and exposure control only for normal applications, no auto mode." And indeed testing with the atomisp_ov2680 fork of ov2680.c has shown that auto-exposure and auto-gain do not work. Note that the code setting the auto-exposure flag was broken, callers of ov2680_exposure_set() were directly passing !!ctrls->auto_exp->val as "bool auto_exp" value, but ctrls->auto_exp is a menu control with: enum v4l2_exposure_auto_type { V4L2_EXPOSURE_AUTO = 0, V4L2_EXPOSURE_MANUAL = 1, ... So instead of passing !!ctrls->auto_exp->val they should have been passing ctrls->auto_exp->val == V4L2_EXPOSURE_AUTO, iow the passed value was inverted of what it should have been. Also remove ov2680_g_volatile_ctrl() since without auto support the gain and exposure controls are not volatile. This also fixes the control values not being properly applied in ov2680_mode_set(). The 800x600 mode register-list also sets gain, exposure and vflip overriding the last set ctrl values. ov2680_mode_set() does call ov2680_gain_set() and ov2680_exposure_set() but did this before writing the mode register-list, so these values would still be overridden by the mode register-list. Add a v4l2_ctrl_handler_setup() call after writing the mode register-list to restore all ctrl values. Also remove the ctrls->gain->is_new check from ov2680_gain_set() so that the gain always gets restored properly. Last since ov2680_mode_set() now calls v4l2_ctrl_handler_setup(), remove the v4l2_ctrl_handler_setup() call after ov2680_mode_restore() since ov2680_mode_restore() calls ov2680_mode_set(). Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Reviewed-by: Daniel Scally Acked-by: Rui Miguel Silva Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 163 ++++--------------------------------- 1 file changed, 18 insertions(+), 145 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index 54153bf66bdd..42efd60c6a96 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -85,15 +85,8 @@ struct ov2680_mode_info { struct ov2680_ctrls { struct v4l2_ctrl_handler handler; - struct { - struct v4l2_ctrl *auto_exp; - struct v4l2_ctrl *exposure; - }; - struct { - struct v4l2_ctrl *auto_gain; - struct v4l2_ctrl *gain; - }; - + struct v4l2_ctrl *exposure; + struct v4l2_ctrl *gain; struct v4l2_ctrl *hflip; struct v4l2_ctrl *vflip; struct v4l2_ctrl *test_pattern; @@ -143,6 +136,7 @@ static const struct reg_value ov2680_setting_30fps_QUXGA_800_600[] = { {0x380e, 0x02}, {0x380f, 0x84}, {0x3811, 0x04}, {0x3813, 0x04}, {0x3814, 0x31}, {0x3815, 0x31}, {0x3820, 0xc0}, {0x4008, 0x00}, {0x4009, 0x03}, {0x4837, 0x1e}, {0x3501, 0x4e}, {0x3502, 0xe0}, + {0x3503, 0x03}, }; static const struct reg_value ov2680_setting_30fps_720P_1280_720[] = { @@ -405,69 +399,15 @@ static int ov2680_test_pattern_set(struct ov2680_dev *sensor, int value) return 0; } -static int ov2680_gain_set(struct ov2680_dev *sensor, bool auto_gain) +static int ov2680_gain_set(struct ov2680_dev *sensor, u32 gain) { - struct ov2680_ctrls *ctrls = &sensor->ctrls; - u32 gain; - int ret; - - ret = ov2680_mod_reg(sensor, OV2680_REG_R_MANUAL, BIT(1), - auto_gain ? 0 : BIT(1)); - if (ret < 0) - return ret; - - if (auto_gain || !ctrls->gain->is_new) - return 0; - - gain = ctrls->gain->val; - - ret = ov2680_write_reg16(sensor, OV2680_REG_GAIN_PK, gain); - - return 0; + return ov2680_write_reg16(sensor, OV2680_REG_GAIN_PK, gain); } -static int ov2680_gain_get(struct ov2680_dev *sensor) +static int ov2680_exposure_set(struct ov2680_dev *sensor, u32 exp) { - u32 gain; - int ret; - - ret = ov2680_read_reg16(sensor, OV2680_REG_GAIN_PK, &gain); - if (ret) - return ret; - - return gain; -} - -static int ov2680_exposure_set(struct ov2680_dev *sensor, bool auto_exp) -{ - struct ov2680_ctrls *ctrls = &sensor->ctrls; - u32 exp; - int ret; - - ret = ov2680_mod_reg(sensor, OV2680_REG_R_MANUAL, BIT(0), - auto_exp ? 0 : BIT(0)); - if (ret < 0) - return ret; - - if (auto_exp || !ctrls->exposure->is_new) - return 0; - - exp = (u32)ctrls->exposure->val; - exp <<= 4; - - return ov2680_write_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, exp); -} - -static int ov2680_exposure_get(struct ov2680_dev *sensor) -{ - int ret; - u32 exp; - - ret = ov2680_read_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, &exp); - if (ret) - return ret; - - return exp >> 4; + return ov2680_write_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, + exp << 4); } static int ov2680_stream_enable(struct ov2680_dev *sensor) @@ -482,32 +422,16 @@ static int ov2680_stream_disable(struct ov2680_dev *sensor) static int ov2680_mode_set(struct ov2680_dev *sensor) { - struct ov2680_ctrls *ctrls = &sensor->ctrls; int ret; - ret = ov2680_gain_set(sensor, false); - if (ret < 0) - return ret; - - ret = ov2680_exposure_set(sensor, false); - if (ret < 0) - return ret; - ret = ov2680_load_regs(sensor, sensor->current_mode); if (ret < 0) return ret; - if (ctrls->auto_gain->val) { - ret = ov2680_gain_set(sensor, true); - if (ret < 0) - return ret; - } - - if (ctrls->auto_exp->val == V4L2_EXPOSURE_AUTO) { - ret = ov2680_exposure_set(sensor, true); - if (ret < 0) - return ret; - } + /* Restore value of all ctrls */ + ret = __v4l2_ctrl_handler_setup(&sensor->ctrls.handler); + if (ret < 0) + return ret; sensor->mode_pending_changes = false; @@ -590,15 +514,10 @@ static int ov2680_s_power(struct v4l2_subdev *sd, int on) else ret = ov2680_power_off(sensor); - mutex_unlock(&sensor->lock); - - if (on && ret == 0) { - ret = v4l2_ctrl_handler_setup(&sensor->ctrls.handler); - if (ret < 0) - return ret; - + if (on && ret == 0) ret = ov2680_mode_restore(sensor); - } + + mutex_unlock(&sensor->lock); return ret; } @@ -794,52 +713,19 @@ static int ov2680_enum_frame_interval(struct v4l2_subdev *sd, return 0; } -static int ov2680_g_volatile_ctrl(struct v4l2_ctrl *ctrl) -{ - struct v4l2_subdev *sd = ctrl_to_sd(ctrl); - struct ov2680_dev *sensor = to_ov2680_dev(sd); - struct ov2680_ctrls *ctrls = &sensor->ctrls; - int val; - - if (!sensor->is_enabled) - return 0; - - switch (ctrl->id) { - case V4L2_CID_GAIN: - val = ov2680_gain_get(sensor); - if (val < 0) - return val; - ctrls->gain->val = val; - break; - case V4L2_CID_EXPOSURE: - val = ov2680_exposure_get(sensor); - if (val < 0) - return val; - ctrls->exposure->val = val; - break; - } - - return 0; -} - static int ov2680_s_ctrl(struct v4l2_ctrl *ctrl) { struct v4l2_subdev *sd = ctrl_to_sd(ctrl); struct ov2680_dev *sensor = to_ov2680_dev(sd); - struct ov2680_ctrls *ctrls = &sensor->ctrls; if (!sensor->is_enabled) return 0; switch (ctrl->id) { - case V4L2_CID_AUTOGAIN: - return ov2680_gain_set(sensor, !!ctrl->val); case V4L2_CID_GAIN: - return ov2680_gain_set(sensor, !!ctrls->auto_gain->val); - case V4L2_CID_EXPOSURE_AUTO: - return ov2680_exposure_set(sensor, !!ctrl->val); + return ov2680_gain_set(sensor, ctrl->val); case V4L2_CID_EXPOSURE: - return ov2680_exposure_set(sensor, !!ctrls->auto_exp->val); + return ov2680_exposure_set(sensor, ctrl->val); case V4L2_CID_VFLIP: if (sensor->is_streaming) return -EBUSY; @@ -864,7 +750,6 @@ static int ov2680_s_ctrl(struct v4l2_ctrl *ctrl) } static const struct v4l2_ctrl_ops ov2680_ctrl_ops = { - .g_volatile_ctrl = ov2680_g_volatile_ctrl, .s_ctrl = ov2680_s_ctrl, }; @@ -936,7 +821,7 @@ static int ov2680_v4l2_register(struct ov2680_dev *sensor) if (ret < 0) return ret; - v4l2_ctrl_handler_init(hdl, 7); + v4l2_ctrl_handler_init(hdl, 5); hdl->lock = &sensor->lock; @@ -948,16 +833,9 @@ static int ov2680_v4l2_register(struct ov2680_dev *sensor) ARRAY_SIZE(test_pattern_menu) - 1, 0, 0, test_pattern_menu); - ctrls->auto_exp = v4l2_ctrl_new_std_menu(hdl, ops, - V4L2_CID_EXPOSURE_AUTO, - V4L2_EXPOSURE_MANUAL, 0, - V4L2_EXPOSURE_AUTO); - ctrls->exposure = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_EXPOSURE, 0, 32767, 1, 0); - ctrls->auto_gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_AUTOGAIN, - 0, 1, 1, 1); ctrls->gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_GAIN, 0, 2047, 1, 0); if (hdl->error) { @@ -965,14 +843,9 @@ static int ov2680_v4l2_register(struct ov2680_dev *sensor) goto cleanup_entity; } - ctrls->gain->flags |= V4L2_CTRL_FLAG_VOLATILE; - ctrls->exposure->flags |= V4L2_CTRL_FLAG_VOLATILE; ctrls->vflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; ctrls->hflip->flags |= V4L2_CTRL_FLAG_MODIFY_LAYOUT; - v4l2_ctrl_auto_cluster(2, &ctrls->auto_gain, 0, true); - v4l2_ctrl_auto_cluster(2, &ctrls->auto_exp, 1, true); - sensor->sd.ctrl_handler = hdl; ret = v4l2_async_register_subdev(&sensor->sd); From 7263c39fd711da64cba94f6ebd30fcafc3b4f499 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:17 +0200 Subject: [PATCH 1144/2093] media: ov2680: Fix ov2680_bayer_order() [ Upstream commit 50a7bad4e0a37d7018ab6fe843dd84bc6b2ecf72 ] The index into ov2680_hv_flip_bayer_order[] should be 0-3, but ov2680_bayer_order() was using 0 + BIT(2) + (BIT(2) << 1) as max index, while the intention was to use: 0 + 1 + 2 as max index. Fix the index calculation in ov2680_bayer_order(), while at it also just use the ctrl values rather then reading them back using a slow i2c-read transaction. This also allows making the function void, since there now are no more i2c-reads to error check. Note the check for the ctrls being NULL is there to allow adding an ov2680_fill_format() helper later, which will call ov2680_set_bayer_order() during probe() before the ctrls are created. [Sakari Ailus: Change all users of ov2680_set_bayer_order() here] Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Reviewed-by: Daniel Scally Acked-by: Rui Miguel Silva Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 33 ++++++++++++++------------------- 1 file changed, 14 insertions(+), 19 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index 42efd60c6a96..7d072448c853 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -315,26 +315,17 @@ static void ov2680_power_down(struct ov2680_dev *sensor) usleep_range(5000, 10000); } -static int ov2680_bayer_order(struct ov2680_dev *sensor) +static void ov2680_set_bayer_order(struct ov2680_dev *sensor) { - u32 format1; - u32 format2; - u32 hv_flip; - int ret; + int hv_flip = 0; - ret = ov2680_read_reg(sensor, OV2680_REG_FORMAT1, &format1); - if (ret < 0) - return ret; + if (sensor->ctrls.vflip && sensor->ctrls.vflip->val) + hv_flip += 1; - ret = ov2680_read_reg(sensor, OV2680_REG_FORMAT2, &format2); - if (ret < 0) - return ret; - - hv_flip = (format2 & BIT(2) << 1) | (format1 & BIT(2)); + if (sensor->ctrls.hflip && sensor->ctrls.hflip->val) + hv_flip += 2; sensor->fmt.code = ov2680_hv_flip_bayer_order[hv_flip]; - - return 0; } static int ov2680_vflip_enable(struct ov2680_dev *sensor) @@ -345,7 +336,8 @@ static int ov2680_vflip_enable(struct ov2680_dev *sensor) if (ret < 0) return ret; - return ov2680_bayer_order(sensor); + ov2680_set_bayer_order(sensor); + return 0; } static int ov2680_vflip_disable(struct ov2680_dev *sensor) @@ -356,7 +348,8 @@ static int ov2680_vflip_disable(struct ov2680_dev *sensor) if (ret < 0) return ret; - return ov2680_bayer_order(sensor); + ov2680_set_bayer_order(sensor); + return 0; } static int ov2680_hflip_enable(struct ov2680_dev *sensor) @@ -367,7 +360,8 @@ static int ov2680_hflip_enable(struct ov2680_dev *sensor) if (ret < 0) return ret; - return ov2680_bayer_order(sensor); + ov2680_set_bayer_order(sensor); + return 0; } static int ov2680_hflip_disable(struct ov2680_dev *sensor) @@ -378,7 +372,8 @@ static int ov2680_hflip_disable(struct ov2680_dev *sensor) if (ret < 0) return ret; - return ov2680_bayer_order(sensor); + ov2680_set_bayer_order(sensor); + return 0; } static int ov2680_test_pattern_set(struct ov2680_dev *sensor, int value) From 6d51cdf66b9f94f6db82e3ff2d71d9d4fe631dcf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:18 +0200 Subject: [PATCH 1145/2093] media: ov2680: Fix vflip / hflip set functions [ Upstream commit d5d08ad330c9ccebc5e066fda815423a290f48b0 ] ov2680_vflip_disable() / ov2680_hflip_disable() pass BIT(0) instead of 0 as value to ov2680_mod_reg(). While fixing this also: 1. Stop having separate enable/disable functions for hflip / vflip 2. Move the is_streaming check, which is unique to hflip / vflip into the ov2680_set_?flip() functions. for a nice code cleanup. Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Reviewed-by: Daniel Scally Acked-by: Rui Miguel Silva Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 52 ++++++++++---------------------------- 1 file changed, 13 insertions(+), 39 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index 7d072448c853..c999a898dfe7 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -328,11 +328,15 @@ static void ov2680_set_bayer_order(struct ov2680_dev *sensor) sensor->fmt.code = ov2680_hv_flip_bayer_order[hv_flip]; } -static int ov2680_vflip_enable(struct ov2680_dev *sensor) +static int ov2680_set_vflip(struct ov2680_dev *sensor, s32 val) { int ret; - ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, BIT(2), BIT(2)); + if (sensor->is_streaming) + return -EBUSY; + + ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, + BIT(2), val ? BIT(2) : 0); if (ret < 0) return ret; @@ -340,35 +344,15 @@ static int ov2680_vflip_enable(struct ov2680_dev *sensor) return 0; } -static int ov2680_vflip_disable(struct ov2680_dev *sensor) +static int ov2680_set_hflip(struct ov2680_dev *sensor, s32 val) { int ret; - ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, BIT(2), BIT(0)); - if (ret < 0) - return ret; + if (sensor->is_streaming) + return -EBUSY; - ov2680_set_bayer_order(sensor); - return 0; -} - -static int ov2680_hflip_enable(struct ov2680_dev *sensor) -{ - int ret; - - ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, BIT(2), BIT(2)); - if (ret < 0) - return ret; - - ov2680_set_bayer_order(sensor); - return 0; -} - -static int ov2680_hflip_disable(struct ov2680_dev *sensor) -{ - int ret; - - ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, BIT(2), BIT(0)); + ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, + BIT(2), val ? BIT(2) : 0); if (ret < 0) return ret; @@ -722,19 +706,9 @@ static int ov2680_s_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_EXPOSURE: return ov2680_exposure_set(sensor, ctrl->val); case V4L2_CID_VFLIP: - if (sensor->is_streaming) - return -EBUSY; - if (ctrl->val) - return ov2680_vflip_enable(sensor); - else - return ov2680_vflip_disable(sensor); + return ov2680_set_vflip(sensor, ctrl->val); case V4L2_CID_HFLIP: - if (sensor->is_streaming) - return -EBUSY; - if (ctrl->val) - return ov2680_hflip_enable(sensor); - else - return ov2680_hflip_disable(sensor); + return ov2680_set_hflip(sensor, ctrl->val); case V4L2_CID_TEST_PATTERN: return ov2680_test_pattern_set(sensor, ctrl->val); default: From e0b6edf4a346a003629f4b4c7996a9fbd507f6f0 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:19 +0200 Subject: [PATCH 1146/2093] media: ov2680: Remove VIDEO_V4L2_SUBDEV_API ifdef-s [ Upstream commit 49c282d5a8c5f4d1d9088622bec792294c716010 ] VIDEO_V4L2_SUBDEV_API is now automatically selected in Kconfig for all sensor drivers. Remove the ifdef CONFIG_VIDEO_V4L2_SUBDEV_API checks. This is a preparation patch for fixing ov2680_set_fmt() which == V4L2_SUBDEV_FORMAT_TRY calls not properly filling in the passed in v4l2_mbus_framefmt struct. Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Reviewed-by: Daniel Scally Acked-by: Rui Miguel Silva Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index c999a898dfe7..de11a5fb0365 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -562,7 +562,6 @@ static int ov2680_get_fmt(struct v4l2_subdev *sd, { struct ov2680_dev *sensor = to_ov2680_dev(sd); struct v4l2_mbus_framefmt *fmt = NULL; - int ret = 0; if (format->pad != 0) return -EINVAL; @@ -570,22 +569,17 @@ static int ov2680_get_fmt(struct v4l2_subdev *sd, mutex_lock(&sensor->lock); if (format->which == V4L2_SUBDEV_FORMAT_TRY) { -#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API fmt = v4l2_subdev_get_try_format(&sensor->sd, sd_state, format->pad); -#else - ret = -EINVAL; -#endif } else { fmt = &sensor->fmt; } - if (fmt) - format->format = *fmt; + format->format = *fmt; mutex_unlock(&sensor->lock); - return ret; + return 0; } static int ov2680_set_fmt(struct v4l2_subdev *sd, @@ -594,9 +588,7 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, { struct ov2680_dev *sensor = to_ov2680_dev(sd); struct v4l2_mbus_framefmt *fmt = &format->format; -#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API struct v4l2_mbus_framefmt *try_fmt; -#endif const struct ov2680_mode_info *mode; int ret = 0; @@ -619,10 +611,8 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, } if (format->which == V4L2_SUBDEV_FORMAT_TRY) { -#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API try_fmt = v4l2_subdev_get_try_format(sd, sd_state, 0); format->format = *try_fmt; -#endif goto unlock; } @@ -780,9 +770,7 @@ static int ov2680_v4l2_register(struct ov2680_dev *sensor) v4l2_i2c_subdev_init(&sensor->sd, sensor->i2c_client, &ov2680_subdev_ops); -#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API sensor->sd.flags = V4L2_SUBDEV_FL_HAS_DEVNODE; -#endif sensor->pad.flags = MEDIA_PAD_FL_SOURCE; sensor->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR; From 90fbf01c8080de06e80f85c0a9dbb4ca86b7ab3e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:20 +0200 Subject: [PATCH 1147/2093] media: ov2680: Don't take the lock for try_fmt calls [ Upstream commit e521b9cc1a49de677f4fc65909ce4877fbf7b113 ] On ov2680_set_fmt() calls with format->which == V4L2_SUBDEV_FORMAT_TRY, ov2680_set_fmt() does not talk to the sensor. So in this case there is no need to lock the sensor->lock mutex or to check that the sensor is streaming. Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Acked-by: Rui Miguel Silva Reviewed-by: Daniel Scally Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index de11a5fb0365..4f7ff23ef897 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -595,24 +595,22 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, if (format->pad != 0) return -EINVAL; - mutex_lock(&sensor->lock); - - if (sensor->is_streaming) { - ret = -EBUSY; - goto unlock; - } - mode = v4l2_find_nearest_size(ov2680_mode_data, ARRAY_SIZE(ov2680_mode_data), width, height, fmt->width, fmt->height); - if (!mode) { - ret = -EINVAL; - goto unlock; - } + if (!mode) + return -EINVAL; if (format->which == V4L2_SUBDEV_FORMAT_TRY) { try_fmt = v4l2_subdev_get_try_format(sd, sd_state, 0); format->format = *try_fmt; + return 0; + } + + mutex_lock(&sensor->lock); + + if (sensor->is_streaming) { + ret = -EBUSY; goto unlock; } From 0790c0914059d4496eae4c4ad708cd6b20d67299 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:21 +0200 Subject: [PATCH 1148/2093] media: ov2680: Add ov2680_fill_format() helper function [ Upstream commit 6d6849b2203f3244b575ba01d3e41ee19aa2cadf ] Add a ov2680_fill_format() helper function and use this everywhere were a v4l2_mbus_framefmt struct needs to be filled in so that the driver always fills it consistently. This is a preparation patch for fixing ov2680_set_fmt() which == V4L2_SUBDEV_FORMAT_TRY calls not properly filling in the passed in v4l2_mbus_framefmt struct. Note that for ov2680_init_cfg() this now simply always fills the try_fmt struct of the passed in sd_state. This is correct because ov2680_init_cfg() is never called with a NULL sd_state so the old sd_state check is not necessary. Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Acked-by: Rui Miguel Silva Reviewed-by: Daniel Scally Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 49 +++++++++++++++++++++----------------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index 4f7ff23ef897..6e0e8d21d189 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -54,6 +54,9 @@ #define OV2680_WIDTH_MAX 1600 #define OV2680_HEIGHT_MAX 1200 +#define OV2680_DEFAULT_WIDTH 800 +#define OV2680_DEFAULT_HEIGHT 600 + enum ov2680_mode_id { OV2680_MODE_QUXGA_800_600, OV2680_MODE_720P_1280_720, @@ -315,7 +318,8 @@ static void ov2680_power_down(struct ov2680_dev *sensor) usleep_range(5000, 10000); } -static void ov2680_set_bayer_order(struct ov2680_dev *sensor) +static void ov2680_set_bayer_order(struct ov2680_dev *sensor, + struct v4l2_mbus_framefmt *fmt) { int hv_flip = 0; @@ -325,7 +329,19 @@ static void ov2680_set_bayer_order(struct ov2680_dev *sensor) if (sensor->ctrls.hflip && sensor->ctrls.hflip->val) hv_flip += 2; - sensor->fmt.code = ov2680_hv_flip_bayer_order[hv_flip]; + fmt->code = ov2680_hv_flip_bayer_order[hv_flip]; +} + +static void ov2680_fill_format(struct ov2680_dev *sensor, + struct v4l2_mbus_framefmt *fmt, + unsigned int width, unsigned int height) +{ + memset(fmt, 0, sizeof(*fmt)); + fmt->width = width; + fmt->height = height; + fmt->field = V4L2_FIELD_NONE; + fmt->colorspace = V4L2_COLORSPACE_SRGB; + ov2680_set_bayer_order(sensor, fmt); } static int ov2680_set_vflip(struct ov2680_dev *sensor, s32 val) @@ -340,7 +356,7 @@ static int ov2680_set_vflip(struct ov2680_dev *sensor, s32 val) if (ret < 0) return ret; - ov2680_set_bayer_order(sensor); + ov2680_set_bayer_order(sensor, &sensor->fmt); return 0; } @@ -356,7 +372,7 @@ static int ov2680_set_hflip(struct ov2680_dev *sensor, s32 val) if (ret < 0) return ret; - ov2680_set_bayer_order(sensor); + ov2680_set_bayer_order(sensor, &sensor->fmt); return 0; } @@ -614,10 +630,7 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, goto unlock; } - fmt->width = mode->width; - fmt->height = mode->height; - fmt->code = sensor->fmt.code; - fmt->colorspace = sensor->fmt.colorspace; + ov2680_fill_format(sensor, fmt, mode->width, mode->height); sensor->current_mode = mode; sensor->fmt = format->format; @@ -632,16 +645,11 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, static int ov2680_init_cfg(struct v4l2_subdev *sd, struct v4l2_subdev_state *sd_state) { - struct v4l2_subdev_format fmt = { - .which = sd_state ? V4L2_SUBDEV_FORMAT_TRY - : V4L2_SUBDEV_FORMAT_ACTIVE, - .format = { - .width = 800, - .height = 600, - } - }; + struct ov2680_dev *sensor = to_ov2680_dev(sd); - return ov2680_set_fmt(sd, sd_state, &fmt); + ov2680_fill_format(sensor, &sd_state->pads[0].try_fmt, + OV2680_DEFAULT_WIDTH, OV2680_DEFAULT_HEIGHT); + return 0; } static int ov2680_enum_frame_size(struct v4l2_subdev *sd, @@ -740,11 +748,8 @@ static int ov2680_mode_init(struct ov2680_dev *sensor) const struct ov2680_mode_info *init_mode; /* set initial mode */ - sensor->fmt.code = MEDIA_BUS_FMT_SBGGR10_1X10; - sensor->fmt.width = 800; - sensor->fmt.height = 600; - sensor->fmt.field = V4L2_FIELD_NONE; - sensor->fmt.colorspace = V4L2_COLORSPACE_SRGB; + ov2680_fill_format(sensor, &sensor->fmt, + OV2680_DEFAULT_WIDTH, OV2680_DEFAULT_HEIGHT); sensor->frame_interval.denominator = OV2680_FRAME_RATE; sensor->frame_interval.numerator = 1; From 85fb0b963f2b58701be7699f299924f3006ac132 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:22 +0200 Subject: [PATCH 1149/2093] media: ov2680: Fix ov2680_set_fmt() which == V4L2_SUBDEV_FORMAT_TRY not working [ Upstream commit c0e97a4b4f20639f74cd5809b42ba6cbf9736a7d ] ov2680_set_fmt() which == V4L2_SUBDEV_FORMAT_TRY was getting the try_fmt v4l2_mbus_framefmt struct from the passed in sd_state and then storing the contents of that into the return by reference format->format struct. While the right thing to do would be filling format->format based on the just looked up mode and then store the results of that in sd_state->pads[0].try_fmt . Before the previous change introducing ov2680_fill_format() this resulted in ov2680_set_fmt() which == V4L2_SUBDEV_FORMAT_TRY always returning the zero-ed out sd_state->pads[0].try_fmt in format->format breaking callers using this. After the introduction of ov2680_fill_format() which at least initializes sd_state->pads[0].try_fmt properly, format->format is now always being filled with the default 800x600 mode set by ov2680_init_cfg() independent of the actual requested mode. Move the filling of format->format with ov2680_fill_format() to before the if (which == V4L2_SUBDEV_FORMAT_TRY) and then store the filled in format->format in sd_state->pads[0].try_fmt to fix this. Note this removes the fmt local variable because IMHO having a local variable which points to a sub-struct of one of the function arguments just leads to confusion when reading the code. Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Acked-by: Rui Miguel Silva Reviewed-by: Daniel Scally Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index 6e0e8d21d189..a24344ef9852 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -603,7 +603,6 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_format *format) { struct ov2680_dev *sensor = to_ov2680_dev(sd); - struct v4l2_mbus_framefmt *fmt = &format->format; struct v4l2_mbus_framefmt *try_fmt; const struct ov2680_mode_info *mode; int ret = 0; @@ -612,14 +611,18 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, return -EINVAL; mode = v4l2_find_nearest_size(ov2680_mode_data, - ARRAY_SIZE(ov2680_mode_data), width, - height, fmt->width, fmt->height); + ARRAY_SIZE(ov2680_mode_data), + width, height, + format->format.width, + format->format.height); if (!mode) return -EINVAL; + ov2680_fill_format(sensor, &format->format, mode->width, mode->height); + if (format->which == V4L2_SUBDEV_FORMAT_TRY) { try_fmt = v4l2_subdev_get_try_format(sd, sd_state, 0); - format->format = *try_fmt; + *try_fmt = format->format; return 0; } @@ -630,8 +633,6 @@ static int ov2680_set_fmt(struct v4l2_subdev *sd, goto unlock; } - ov2680_fill_format(sensor, fmt, mode->width, mode->height); - sensor->current_mode = mode; sensor->fmt = format->format; sensor->mode_pending_changes = true; From 86a41ad0128abd1014b4c30d0efd3b0bb5726bd4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 3 Aug 2023 11:33:23 +0200 Subject: [PATCH 1150/2093] media: ov2680: Fix regulators being left enabled on ov2680_power_on() errors [ Upstream commit 84b4bd7e0d98166aa32fd470e672721190492eae ] When the ov2680_power_on() "sensor soft reset failed" path is hit during probe() the WARN() about putting an enabled regulator at drivers/regulator/core.c:2398 triggers 3 times (once for each regulator), filling dmesg with backtraces. Fix this by properly disabling the regulators on ov2680_power_on() errors. Fixes: 3ee47cad3e69 ("media: ov2680: Add Omnivision OV2680 sensor driver") Reviewed-by: Daniel Scally Acked-by: Rui Miguel Silva Signed-off-by: Hans de Goede Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2680.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index a24344ef9852..8943e4e78a0d 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -475,7 +475,7 @@ static int ov2680_power_on(struct ov2680_dev *sensor) ret = ov2680_write_reg(sensor, OV2680_REG_SOFT_RESET, 0x01); if (ret != 0) { dev_err(dev, "sensor soft reset failed\n"); - return ret; + goto err_disable_regulators; } usleep_range(1000, 2000); } else { @@ -485,7 +485,7 @@ static int ov2680_power_on(struct ov2680_dev *sensor) ret = clk_prepare_enable(sensor->xvclk); if (ret < 0) - return ret; + goto err_disable_regulators; sensor->is_enabled = true; @@ -495,6 +495,10 @@ static int ov2680_power_on(struct ov2680_dev *sensor) ov2680_stream_disable(sensor); return 0; + +err_disable_regulators: + regulator_bulk_disable(OV2680_NUM_SUPPLIES, sensor->supplies); + return ret; } static int ov2680_s_power(struct v4l2_subdev *sd, int on) From 3a2cf76cfb8f6edba79a4fe1bdce3a6d41821e98 Mon Sep 17 00:00:00 2001 From: Jacopo Mondi Date: Thu, 10 Aug 2023 15:33:37 +0200 Subject: [PATCH 1151/2093] media: i2c: rdacm21: Fix uninitialized value [ Upstream commit 33c7ae8f49e3413c81e879e1fdfcea4c5516e37b ] Fix the following smatch warning: drivers/media/i2c/rdacm21.c:373 ov10640_check_id() error: uninitialized symbol 'val'. Initialize 'val' to 0 in the ov10640_check_id() function. Fixes: 2b821698dc73 ("media: i2c: rdacm21: Power up OV10640 before OV490") Reported-by: Hans Verkuil Signed-off-by: Jacopo Mondi Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/i2c/rdacm21.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/rdacm21.c b/drivers/media/i2c/rdacm21.c index 9ccc56c30d3b..d269c541ebe4 100644 --- a/drivers/media/i2c/rdacm21.c +++ b/drivers/media/i2c/rdacm21.c @@ -351,7 +351,7 @@ static void ov10640_power_up(struct rdacm21_device *dev) static int ov10640_check_id(struct rdacm21_device *dev) { unsigned int i; - u8 val; + u8 val = 0; /* Read OV10640 ID to test communications. */ for (i = 0; i < OV10640_PID_TIMEOUT; ++i) { From 4d7e804f49a0b19ec4d5dd8ec6465088091be851 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 6 Jul 2023 10:06:14 +0800 Subject: [PATCH 1152/2093] f2fs: fix to avoid mmap vs set_compress_option case [ Upstream commit b5ab3276eb69cacf44ecfb11b2bfab73096ff4e4 ] Compression option in inode should not be changed after they have been used, however, it may happen in below race case: Thread A Thread B - f2fs_ioc_set_compress_option - check f2fs_is_mmap_file() - check get_dirty_pages() - check F2FS_HAS_BLOCKS() - f2fs_file_mmap - set_inode_flag(FI_MMAP_FILE) - fault - do_page_mkwrite - f2fs_vm_page_mkwrite - f2fs_get_block_locked - fault_dirty_shared_page - set_page_dirty - update i_compress_algorithm - update i_log_cluster_size - update i_cluster_size Avoid such race condition by covering f2fs_file_mmap() w/ i_sem lock, meanwhile add mmap file check condition in f2fs_may_compress() as well. Fixes: e1e8debec656 ("f2fs: add F2FS_IOC_SET_COMPRESS_OPTION ioctl") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/f2fs.h | 3 ++- fs/f2fs/file.c | 23 ++++++++++++++++++----- 2 files changed, 20 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 4d1e48c676fa..c2b7d0923894 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -4453,7 +4453,8 @@ static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi) static inline bool f2fs_may_compress(struct inode *inode) { if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) || - f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode)) + f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode) || + f2fs_is_mmap_file(inode)) return false; return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 7b94f047cbf7..746c71716bea 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -530,7 +530,11 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; + + f2fs_down_read(&F2FS_I(inode)->i_sem); set_inode_flag(inode, FI_MMAP_FILE); + f2fs_up_read(&F2FS_I(inode)->i_sem); + return 0; } @@ -1927,12 +1931,19 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) int err = f2fs_convert_inline_inode(inode); if (err) return err; - if (!f2fs_may_compress(inode)) + + f2fs_down_write(&F2FS_I(inode)->i_sem); + if (!f2fs_may_compress(inode) || + (S_ISREG(inode->i_mode) && + F2FS_HAS_BLOCKS(inode))) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return -EINVAL; - if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) - return -EINVAL; - if (set_compress_context(inode)) - return -EOPNOTSUPP; + } + err = set_compress_context(inode); + f2fs_up_write(&F2FS_I(inode)->i_sem); + + if (err) + return err; } } @@ -3958,6 +3969,7 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) file_start_write(filp); inode_lock(inode); + f2fs_down_write(&F2FS_I(inode)->i_sem); if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { ret = -EBUSY; goto out; @@ -3977,6 +3989,7 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) f2fs_warn(sbi, "compression algorithm is successfully set, " "but current kernel doesn't support this algorithm."); out: + f2fs_up_write(&F2FS_I(inode)->i_sem); inode_unlock(inode); file_end_write(filp); From 33d4c00725b0deefdd1d25261a414456da708251 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 29 Nov 2022 20:29:28 +0800 Subject: [PATCH 1153/2093] f2fs: judge whether discard_unit is section only when have CONFIG_BLK_DEV_ZONED [ Upstream commit b5a711acab305e04278c136c841ba37c589c16a1 ] The current logic, regardless of whether CONFIG_BLK_DEV_ZONED is enabled or not, will judge whether discard_unit is SECTION, when f2fs_sb_has_blkzoned. In fact, when CONFIG_BLK_DEV_ZONED is not enabled, this judgment is a path that will never be accessed. At this time, -EINVAL will be returned in the parse_options function, accompanied by the message "Zoned block device support is not enabled". Let's wrap this discard_unit judgment with CONFIG_BLK_DEV_ZONED. Signed-off-by: Yangtao Li Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Stable-dep-of: 2bd4df8fcbc7 ("f2fs: Only lfs mode is allowed with zoned block device feature") Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b6dad389fa14..d616ce3826e7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1285,19 +1285,18 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) * zone alignment optimization. This is optional for host-aware * devices, but mandatory for host-managed zoned block devices. */ -#ifndef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_has_blkzoned(sbi)) { - f2fs_err(sbi, "Zoned block device support is not enabled"); - return -EINVAL; - } -#endif if (f2fs_sb_has_blkzoned(sbi)) { +#ifdef CONFIG_BLK_DEV_ZONED if (F2FS_OPTION(sbi).discard_unit != DISCARD_UNIT_SECTION) { f2fs_info(sbi, "Zoned block device doesn't need small discard, set discard_unit=section by default"); F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; } +#else + f2fs_err(sbi, "Zoned block device support is not enabled"); + return -EINVAL; +#endif } #ifdef CONFIG_F2FS_FS_COMPRESSION From 3f60a36ed6e37e254cb3f015ac46ea1cee66ac1e Mon Sep 17 00:00:00 2001 From: Chunhai Guo Date: Thu, 3 Aug 2023 22:28:42 +0800 Subject: [PATCH 1154/2093] f2fs: Only lfs mode is allowed with zoned block device feature [ Upstream commit 2bd4df8fcbc72f58ce3c62ed021ab291ca42de0b ] Now f2fs support four block allocation modes: lfs, adaptive, fragment:segment, fragment:block. Only lfs mode is allowed with zoned block device feature. Fixes: 6691d940b0e0 ("f2fs: introduce fragment allocation mode mount option") Signed-off-by: Chunhai Guo Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d616ce3826e7..2046f633fe57 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -858,11 +858,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) if (!name) return -ENOMEM; if (!strcmp(name, "adaptive")) { - if (f2fs_sb_has_blkzoned(sbi)) { - f2fs_warn(sbi, "adaptive mode is not allowed with zoned block device feature"); - kfree(name); - return -EINVAL; - } F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; } else if (!strcmp(name, "lfs")) { F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; @@ -1293,6 +1288,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; } + + if (F2FS_OPTION(sbi).fs_mode != FS_MODE_LFS) { + f2fs_info(sbi, "Only lfs mode is allowed with zoned block device feature"); + return -EINVAL; + } #else f2fs_err(sbi, "Zoned block device support is not enabled"); return -EINVAL; From 0d545a8e77cbd1fbad311b18952e38e0f7672ab4 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 20 Jul 2023 19:29:53 +0800 Subject: [PATCH 1155/2093] Revert "f2fs: fix to do sanity check on extent cache correctly" [ Upstream commit 958ccbbf1ce716d77c7cfa79ace50a421c1eed73 ] syzbot reports a f2fs bug as below: UBSAN: array-index-out-of-bounds in fs/f2fs/f2fs.h:3275:19 index 1409 is out of range for type '__le32[923]' (aka 'unsigned int[923]') Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:217 [inline] __ubsan_handle_out_of_bounds+0x11c/0x150 lib/ubsan.c:348 inline_data_addr fs/f2fs/f2fs.h:3275 [inline] __recover_inline_status fs/f2fs/inode.c:113 [inline] do_read_inode fs/f2fs/inode.c:480 [inline] f2fs_iget+0x4730/0x48b0 fs/f2fs/inode.c:604 f2fs_fill_super+0x640e/0x80c0 fs/f2fs/super.c:4601 mount_bdev+0x276/0x3b0 fs/super.c:1391 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 do_new_mount+0x28f/0xae0 fs/namespace.c:3335 do_mount fs/namespace.c:3675 [inline] __do_sys_mount fs/namespace.c:3884 [inline] __se_sys_mount+0x2d9/0x3c0 fs/namespace.c:3861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The issue was bisected to: commit d48a7b3a72f121655d95b5157c32c7d555e44c05 Author: Chao Yu Date: Mon Jan 9 03:49:20 2023 +0000 f2fs: fix to do sanity check on extent cache correctly The root cause is we applied both v1 and v2 of the patch, v2 is the right fix, so it needs to revert v1 in order to fix reported issue. v1: commit d48a7b3a72f1 ("f2fs: fix to do sanity check on extent cache correctly") https://lore.kernel.org/lkml/20230109034920.492914-1-chao@kernel.org/ v2: commit 269d11948100 ("f2fs: fix to do sanity check on extent cache correctly") https://lore.kernel.org/lkml/20230207134808.1827869-1-chao@kernel.org/ Reported-by: syzbot+601018296973a481f302@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000fcf0690600e4d04d@google.com/ Fixes: d48a7b3a72f1 ("f2fs: fix to do sanity check on extent cache correctly") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/inode.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index aab3b8b3ab0a..1fc7760499f1 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -397,6 +397,12 @@ static int do_read_inode(struct inode *inode) fi->i_inline_xattr_size = 0; } + if (!sanity_check_inode(inode, node_page)) { + f2fs_put_page(node_page, 1); + f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE); + return -EFSCORRUPTED; + } + /* check data exist */ if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) __recover_inline_status(inode, node_page); @@ -459,12 +465,6 @@ static int do_read_inode(struct inode *inode) /* Need all the flag bits */ f2fs_init_read_extent_tree(inode, node_page); - if (!sanity_check_inode(inode, node_page)) { - f2fs_put_page(node_page, 1); - f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE); - return -EFSCORRUPTED; - } - if (!sanity_check_extent_cache(inode)) { f2fs_put_page(node_page, 1); f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE); From 848cd6f24aa72fc4f7cc2dbca6edb41edf059de5 Mon Sep 17 00:00:00 2001 From: Lu Jialin Date: Thu, 10 Aug 2023 11:25:28 +0000 Subject: [PATCH 1156/2093] cgroup:namespace: Remove unused cgroup_namespaces_init() [ Upstream commit 82b90b6c5b38e457c7081d50dff11ecbafc1e61a ] cgroup_namspace_init() just return 0. Therefore, there is no need to call it during start_kernel. Just remove it. Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces") Signed-off-by: Lu Jialin Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/cgroup/namespace.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c index 0d5c29879a50..144a464e45c6 100644 --- a/kernel/cgroup/namespace.c +++ b/kernel/cgroup/namespace.c @@ -149,9 +149,3 @@ const struct proc_ns_operations cgroupns_operations = { .install = cgroupns_install, .owner = cgroupns_owner, }; - -static __init int cgroup_namespaces_init(void) -{ - return 0; -} -subsys_initcall(cgroup_namespaces_init); From 5fa1552877ce2b692781672a5f53bb76b8bd49f8 Mon Sep 17 00:00:00 2001 From: Junhao He Date: Fri, 18 Aug 2023 16:40:52 +0800 Subject: [PATCH 1157/2093] coresight: trbe: Fix TRBE potential sleep in atomic context [ Upstream commit c0a232f1e19e378c5c4e5973a996392942c80090 ] smp_call_function_single() will allocate an IPI interrupt vector to the target processor and send a function call request to the interrupt vector. After the target processor receives the IPI interrupt, it will execute arm_trbe_remove_coresight_cpu() call request in the interrupt handler. According to the device_unregister() stack information, if other process is useing the device, the down_write() may sleep, and trigger deadlocks or unexpected errors. arm_trbe_remove_coresight_cpu coresight_unregister device_unregister device_del kobject_del __kobject_del sysfs_remove_dir kernfs_remove down_write ---------> it may sleep Add a helper arm_trbe_disable_cpu() to disable TRBE precpu irq and reset per TRBE. Simply call arm_trbe_remove_coresight_cpu() directly without useing the smp_call_function_single(), which is the same as registering the TRBE coresight device. Fixes: 3fbf7f011f24 ("coresight: sink: Add TRBE driver") Signed-off-by: Junhao He Link: https://lore.kernel.org/r/20230814093813.19152-2-hejunhao3@huawei.com [ Remove duplicate cpumask checks during removal ] Signed-off-by: Suzuki K Poulose [ v3 - Remove the operation of assigning NULL to cpudata->drvdata ] Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230818084052.10116-1-hejunhao3@huawei.com Signed-off-by: Sasha Levin --- drivers/hwtracing/coresight/coresight-trbe.c | 32 +++++++++++--------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c index 1fc4fd79a1c6..925f6c9cecff 100644 --- a/drivers/hwtracing/coresight/coresight-trbe.c +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -1223,6 +1223,16 @@ static void arm_trbe_enable_cpu(void *info) enable_percpu_irq(drvdata->irq, IRQ_TYPE_NONE); } +static void arm_trbe_disable_cpu(void *info) +{ + struct trbe_drvdata *drvdata = info; + struct trbe_cpudata *cpudata = this_cpu_ptr(drvdata->cpudata); + + disable_percpu_irq(drvdata->irq); + trbe_reset_local(cpudata); +} + + static void arm_trbe_register_coresight_cpu(struct trbe_drvdata *drvdata, int cpu) { struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); @@ -1324,18 +1334,12 @@ static void arm_trbe_probe_cpu(void *info) cpumask_clear_cpu(cpu, &drvdata->supported_cpus); } -static void arm_trbe_remove_coresight_cpu(void *info) +static void arm_trbe_remove_coresight_cpu(struct trbe_drvdata *drvdata, int cpu) { - int cpu = smp_processor_id(); - struct trbe_drvdata *drvdata = info; - struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); struct coresight_device *trbe_csdev = coresight_get_percpu_sink(cpu); - disable_percpu_irq(drvdata->irq); - trbe_reset_local(cpudata); if (trbe_csdev) { coresight_unregister(trbe_csdev); - cpudata->drvdata = NULL; coresight_set_percpu_sink(cpu, NULL); } } @@ -1364,8 +1368,10 @@ static int arm_trbe_remove_coresight(struct trbe_drvdata *drvdata) { int cpu; - for_each_cpu(cpu, &drvdata->supported_cpus) - smp_call_function_single(cpu, arm_trbe_remove_coresight_cpu, drvdata, 1); + for_each_cpu(cpu, &drvdata->supported_cpus) { + smp_call_function_single(cpu, arm_trbe_disable_cpu, drvdata, 1); + arm_trbe_remove_coresight_cpu(drvdata, cpu); + } free_percpu(drvdata->cpudata); return 0; } @@ -1404,12 +1410,8 @@ static int arm_trbe_cpu_teardown(unsigned int cpu, struct hlist_node *node) { struct trbe_drvdata *drvdata = hlist_entry_safe(node, struct trbe_drvdata, hotplug_node); - if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) { - struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); - - disable_percpu_irq(drvdata->irq); - trbe_reset_local(cpudata); - } + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + arm_trbe_disable_cpu(drvdata); return 0; } From f01cfec8d3456bf389918eb898eda11f46d8b1b7 Mon Sep 17 00:00:00 2001 From: Christopher Bednarz Date: Fri, 18 Aug 2023 09:48:38 -0500 Subject: [PATCH 1158/2093] RDMA/irdma: Prevent zero-length STAG registration [ Upstream commit bb6d73d9add68ad270888db327514384dfa44958 ] Currently irdma allows zero-length STAGs to be programmed in HW during the kernel mode fast register flow. Zero-length MR or STAG registration disable HW memory length checks. Improve gaps in bounds checking in irdma by preventing zero-length STAG or MR registrations except if the IB_PD_UNSAFE_GLOBAL_RKEY is set. This addresses the disclosure CVE-2023-25775. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Christopher Bednarz Signed-off-by: Shiraz Saleem Link: https://lore.kernel.org/r/20230818144838.1758-1-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/irdma/ctrl.c | 6 ++++++ drivers/infiniband/hw/irdma/type.h | 2 ++ drivers/infiniband/hw/irdma/verbs.c | 10 ++++++++-- 3 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index 6544c9c60b7d..d98bfb83c3b4 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -1061,6 +1061,9 @@ static int irdma_sc_alloc_stag(struct irdma_sc_dev *dev, u64 hdr; enum irdma_page_size page_size; + if (!info->total_len && !info->all_memory) + return -EINVAL; + if (info->page_size == 0x40000000) page_size = IRDMA_PAGE_SIZE_1G; else if (info->page_size == 0x200000) @@ -1126,6 +1129,9 @@ static int irdma_sc_mr_reg_non_shared(struct irdma_sc_dev *dev, u8 addr_type; enum irdma_page_size page_size; + if (!info->total_len && !info->all_memory) + return -EINVAL; + if (info->page_size == 0x40000000) page_size = IRDMA_PAGE_SIZE_1G; else if (info->page_size == 0x200000) diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h index d6cb94dc744c..1c7cbf7c67be 100644 --- a/drivers/infiniband/hw/irdma/type.h +++ b/drivers/infiniband/hw/irdma/type.h @@ -1015,6 +1015,7 @@ struct irdma_allocate_stag_info { bool remote_access:1; bool use_hmc_fcn_index:1; bool use_pf_rid:1; + bool all_memory:1; u8 hmc_fcn_index; }; @@ -1042,6 +1043,7 @@ struct irdma_reg_ns_stag_info { bool use_hmc_fcn_index:1; u8 hmc_fcn_index; bool use_pf_rid:1; + bool all_memory:1; }; struct irdma_fast_reg_stag_info { diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 5962261f1b15..3b8b2341981e 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2557,7 +2557,8 @@ static int irdma_hw_alloc_stag(struct irdma_device *iwdev, struct irdma_mr *iwmr) { struct irdma_allocate_stag_info *info; - struct irdma_pd *iwpd = to_iwpd(iwmr->ibmr.pd); + struct ib_pd *pd = iwmr->ibmr.pd; + struct irdma_pd *iwpd = to_iwpd(pd); int status; struct irdma_cqp_request *cqp_request; struct cqp_cmds_info *cqp_info; @@ -2573,6 +2574,7 @@ static int irdma_hw_alloc_stag(struct irdma_device *iwdev, info->stag_idx = iwmr->stag >> IRDMA_CQPSQ_STAG_IDX_S; info->pd_id = iwpd->sc_pd.pd_id; info->total_len = iwmr->len; + info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; info->remote_access = true; cqp_info->cqp_cmd = IRDMA_OP_ALLOC_STAG; cqp_info->post_sq = 1; @@ -2620,6 +2622,8 @@ static struct ib_mr *irdma_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, iwmr->type = IRDMA_MEMREG_TYPE_MEM; palloc = &iwpbl->pble_alloc; iwmr->page_cnt = max_num_sg; + /* Use system PAGE_SIZE as the sg page sizes are unknown at this point */ + iwmr->len = max_num_sg * PAGE_SIZE; err_code = irdma_get_pble(iwdev->rf->pble_rsrc, palloc, iwmr->page_cnt, false); if (err_code) @@ -2699,7 +2703,8 @@ static int irdma_hwreg_mr(struct irdma_device *iwdev, struct irdma_mr *iwmr, { struct irdma_pbl *iwpbl = &iwmr->iwpbl; struct irdma_reg_ns_stag_info *stag_info; - struct irdma_pd *iwpd = to_iwpd(iwmr->ibmr.pd); + struct ib_pd *pd = iwmr->ibmr.pd; + struct irdma_pd *iwpd = to_iwpd(pd); struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc; struct irdma_cqp_request *cqp_request; struct cqp_cmds_info *cqp_info; @@ -2718,6 +2723,7 @@ static int irdma_hwreg_mr(struct irdma_device *iwdev, struct irdma_mr *iwmr, stag_info->total_len = iwmr->len; stag_info->access_rights = irdma_get_mr_access(access); stag_info->pd_id = iwpd->sc_pd.pd_id; + stag_info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; if (stag_info->access_rights & IRDMA_ACCESS_FLAGS_ZERO_BASED) stag_info->addr_type = IRDMA_ADDR_TYPE_ZERO_BASED; else From f06c7d823ab5e62b8384f69a968664c794eae3f5 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Mon, 14 Aug 2023 10:03:25 -0400 Subject: [PATCH 1159/2093] scsi: core: Use 32-bit hostnum in scsi_host_lookup() [ Upstream commit 62ec2092095b678ff89ce4ba51c2938cd1e8e630 ] Change scsi_host_lookup() hostnum argument type from unsigned short to unsigned int to match the type used everywhere else. Fixes: 6d49f63b415c ("[SCSI] Make host_no an unsigned int") Signed-off-by: Tony Battersby Link: https://lore.kernel.org/r/a02497e7-c12b-ef15-47fc-3f0a0b00ffce@cybernetics.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hosts.c | 4 ++-- include/scsi/scsi_host.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 45a2fd6584d1..8b825364baad 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -535,7 +535,7 @@ EXPORT_SYMBOL(scsi_host_alloc); static int __scsi_host_match(struct device *dev, const void *data) { struct Scsi_Host *p; - const unsigned short *hostnum = data; + const unsigned int *hostnum = data; p = class_to_shost(dev); return p->host_no == *hostnum; @@ -552,7 +552,7 @@ static int __scsi_host_match(struct device *dev, const void *data) * that scsi_host_get() took. The put_device() below dropped * the reference from class_find_device(). **/ -struct Scsi_Host *scsi_host_lookup(unsigned short hostnum) +struct Scsi_Host *scsi_host_lookup(unsigned int hostnum) { struct device *cdev; struct Scsi_Host *shost = NULL; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index fcf25f1642a3..d27d9fb7174c 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -757,7 +757,7 @@ extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); extern int scsi_host_busy(struct Scsi_Host *shost); extern void scsi_host_put(struct Scsi_Host *t); -extern struct Scsi_Host *scsi_host_lookup(unsigned short); +extern struct Scsi_Host *scsi_host_lookup(unsigned int hostnum); extern const char *scsi_host_state_name(enum scsi_host_state); extern void scsi_host_complete_all_commands(struct Scsi_Host *shost, enum scsi_host_status status); From 5a5fb3b1754fa2b4db95f0151b4af0fb6f8918ec Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Thu, 17 Aug 2023 07:47:08 +0000 Subject: [PATCH 1160/2093] scsi: fcoe: Fix potential deadlock on &fip->ctlr_lock [ Upstream commit 1a1975551943f681772720f639ff42fbaa746212 ] There is a long call chain that &fip->ctlr_lock is acquired by isr fnic_isr_msix_wq_copy() under hard IRQ context. Thus other process context code acquiring the lock should disable IRQ, otherwise deadlock could happen if the IRQ preempts the execution while the lock is held in process context on the same CPU. [ISR] fnic_isr_msix_wq_copy() -> fnic_wq_copy_cmpl_handler() -> fnic_fcpio_cmpl_handler() -> fnic_fcpio_flogi_reg_cmpl_handler() -> fnic_flush_tx() -> fnic_send_frame() -> fcoe_ctlr_els_send() -> spin_lock_bh(&fip->ctlr_lock) [Process Context] 1. fcoe_ctlr_timer_work() -> fcoe_ctlr_flogi_send() -> spin_lock_bh(&fip->ctlr_lock) 2. fcoe_ctlr_recv_work() -> fcoe_ctlr_recv_handler() -> fcoe_ctlr_recv_els() -> fcoe_ctlr_announce() -> spin_lock_bh(&fip->ctlr_lock) 3. fcoe_ctlr_recv_work() -> fcoe_ctlr_recv_handler() -> fcoe_ctlr_recv_els() -> fcoe_ctlr_flogi_retry() -> spin_lock_bh(&fip->ctlr_lock) 4. -> fcoe_xmit() -> fcoe_ctlr_els_send() -> spin_lock_bh(&fip->ctlr_lock) spin_lock_bh() is not enough since fnic_isr_msix_wq_copy() is a hardirq. These flaws were found by an experimental static analysis tool I am developing for irq-related deadlock. The patch fix the potential deadlocks by spin_lock_irqsave() to disable hard irq. Fixes: 794d98e77f59 ("[SCSI] libfcoe: retry rejected FLOGI to another FCF if possible") Signed-off-by: Chengfeng Ye Link: https://lore.kernel.org/r/20230817074708.7509-1-dg573847474@gmail.com Reviewed-by: Davidlohr Bueso Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/fcoe/fcoe_ctlr.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index ddc048069af2..8a4124e7d204 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -319,16 +319,17 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip) { struct fcoe_fcf *sel; struct fcoe_fcf *fcf; + unsigned long flags; mutex_lock(&fip->ctlr_mutex); - spin_lock_bh(&fip->ctlr_lock); + spin_lock_irqsave(&fip->ctlr_lock, flags); kfree_skb(fip->flogi_req); fip->flogi_req = NULL; list_for_each_entry(fcf, &fip->fcfs, list) fcf->flogi_sent = 0; - spin_unlock_bh(&fip->ctlr_lock); + spin_unlock_irqrestore(&fip->ctlr_lock, flags); sel = fip->sel_fcf; if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr)) @@ -699,6 +700,7 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, { struct fc_frame *fp; struct fc_frame_header *fh; + unsigned long flags; u16 old_xid; u8 op; u8 mac[ETH_ALEN]; @@ -732,11 +734,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, op = FIP_DT_FLOGI; if (fip->mode == FIP_MODE_VN2VN) break; - spin_lock_bh(&fip->ctlr_lock); + spin_lock_irqsave(&fip->ctlr_lock, flags); kfree_skb(fip->flogi_req); fip->flogi_req = skb; fip->flogi_req_send = 1; - spin_unlock_bh(&fip->ctlr_lock); + spin_unlock_irqrestore(&fip->ctlr_lock, flags); schedule_work(&fip->timer_work); return -EINPROGRESS; case ELS_FDISC: @@ -1705,10 +1707,11 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip) static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; + unsigned long flags; int error; mutex_lock(&fip->ctlr_mutex); - spin_lock_bh(&fip->ctlr_lock); + spin_lock_irqsave(&fip->ctlr_lock, flags); LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n"); fcf = fcoe_ctlr_select(fip); if (!fcf || fcf->flogi_sent) { @@ -1719,7 +1722,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) fcoe_ctlr_solicit(fip, NULL); error = fcoe_ctlr_flogi_send_locked(fip); } - spin_unlock_bh(&fip->ctlr_lock); + spin_unlock_irqrestore(&fip->ctlr_lock, flags); mutex_unlock(&fip->ctlr_mutex); return error; } @@ -1736,8 +1739,9 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; + unsigned long flags; - spin_lock_bh(&fip->ctlr_lock); + spin_lock_irqsave(&fip->ctlr_lock, flags); fcf = fip->sel_fcf; if (!fcf || !fip->flogi_req_send) goto unlock; @@ -1764,7 +1768,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) } else /* XXX */ LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n"); unlock: - spin_unlock_bh(&fip->ctlr_lock); + spin_unlock_irqrestore(&fip->ctlr_lock, flags); } /** From 1d085c6a25fa30b7e597235c003855f0bc24d1d8 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Fri, 11 Aug 2023 19:34:57 +0200 Subject: [PATCH 1161/2093] interconnect: qcom: sm8450: Enable sync_state [ Upstream commit 16862f1b2110eca6330e5be6d804e1a08e06a202 ] Enable sync_state on sm8450 so that the interconnect votes actually mean anything and aren't just pinned to INT_MAX. Fixes: fafc114a468e ("interconnect: qcom: Add SM8450 interconnect provider driver") Signed-off-by: Konrad Dybcio Reviewed-by: Vinod Koul Link: https://lore.kernel.org/r/20230811-topic-8450_syncstate-v1-1-69ae5552a18b@linaro.org Signed-off-by: Georgi Djakov Signed-off-by: Sasha Levin --- drivers/interconnect/qcom/sm8450.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/interconnect/qcom/sm8450.c b/drivers/interconnect/qcom/sm8450.c index e64c214b4020..d6e582a02e62 100644 --- a/drivers/interconnect/qcom/sm8450.c +++ b/drivers/interconnect/qcom/sm8450.c @@ -1886,6 +1886,7 @@ static struct platform_driver qnoc_driver = { .driver = { .name = "qnoc-sm8450", .of_match_table = qnoc_of_match, + .sync_state = icc_sync_state, }, }; From e9ef8b5099d5d6a24412d75e9887bbf06af82df0 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Sat, 12 Aug 2023 01:16:15 +0200 Subject: [PATCH 1162/2093] interconnect: qcom: bcm-voter: Improve enable_mask handling [ Upstream commit a1f4170dec440f023601d57e49227b784074d218 ] We don't need all the complex arithmetic for BCMs utilizing enable_mask, as all we need to do is to determine whether there's any user (or keepalive) asking for it to be on. Separate the logic for such BCMs for a small speed boost. Suggested-by: Bjorn Andersson Reviewed-by: Bjorn Andersson Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230811-topic-icc_fix_1he-v2-1-0620af8ac133@linaro.org Signed-off-by: Georgi Djakov Stable-dep-of: 1a70ca71547b ("interconnect: qcom: bcm-voter: Use enable_maks for keepalive voting") Signed-off-by: Sasha Levin --- drivers/interconnect/qcom/bcm-voter.c | 43 ++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 7 deletions(-) diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index d5f2a6b5376b..d857eb8838b9 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -58,6 +58,36 @@ static u64 bcm_div(u64 num, u32 base) return num; } +/* BCMs with enable_mask use one-hot-encoding for on/off signaling */ +static void bcm_aggregate_mask(struct qcom_icc_bcm *bcm) +{ + struct qcom_icc_node *node; + int bucket, i; + + for (bucket = 0; bucket < QCOM_ICC_NUM_BUCKETS; bucket++) { + bcm->vote_x[bucket] = 0; + bcm->vote_y[bucket] = 0; + + for (i = 0; i < bcm->num_nodes; i++) { + node = bcm->nodes[i]; + + /* If any vote in this bucket exists, keep the BCM enabled */ + if (node->sum_avg[bucket] || node->max_peak[bucket]) { + bcm->vote_x[bucket] = 0; + bcm->vote_y[bucket] = bcm->enable_mask; + break; + } + } + } + + if (bcm->keepalive) { + bcm->vote_x[QCOM_ICC_BUCKET_AMC] = 1; + bcm->vote_x[QCOM_ICC_BUCKET_WAKE] = 1; + bcm->vote_y[QCOM_ICC_BUCKET_AMC] = 1; + bcm->vote_y[QCOM_ICC_BUCKET_WAKE] = 1; + } +} + static void bcm_aggregate(struct qcom_icc_bcm *bcm) { struct qcom_icc_node *node; @@ -83,11 +113,6 @@ static void bcm_aggregate(struct qcom_icc_bcm *bcm) temp = agg_peak[bucket] * bcm->vote_scale; bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit); - - if (bcm->enable_mask && (bcm->vote_x[bucket] || bcm->vote_y[bucket])) { - bcm->vote_x[bucket] = 0; - bcm->vote_y[bucket] = bcm->enable_mask; - } } if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 && @@ -260,8 +285,12 @@ int qcom_icc_bcm_voter_commit(struct bcm_voter *voter) return 0; mutex_lock(&voter->lock); - list_for_each_entry(bcm, &voter->commit_list, list) - bcm_aggregate(bcm); + list_for_each_entry(bcm, &voter->commit_list, list) { + if (bcm->enable_mask) + bcm_aggregate_mask(bcm); + else + bcm_aggregate(bcm); + } /* * Pre sort the BCMs based on VCD for ease of generating a command list From 93e908545361c58a092dad46999536d2c12159b0 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Sat, 12 Aug 2023 01:16:16 +0200 Subject: [PATCH 1163/2093] interconnect: qcom: bcm-voter: Use enable_maks for keepalive voting [ Upstream commit 1a70ca71547be051769f0628aa09717694f508f0 ] BCMs with an enable_mask expect to only have that specific value written to them. The current implementation only works by miracle for BCMs with enable mask == BIT(0), as the minimal vote we've been using so far just so happens to be equal to that. Use the correct value with keepalive voting. Fixes: d8630f050d3f ("interconnect: qcom: Add support for mask-based BCMs") Reported-by: Bjorn Andersson Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230811-topic-icc_fix_1he-v2-2-0620af8ac133@linaro.org Signed-off-by: Georgi Djakov Signed-off-by: Sasha Levin --- drivers/interconnect/qcom/bcm-voter.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index d857eb8838b9..a2d437a05a11 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -81,10 +81,10 @@ static void bcm_aggregate_mask(struct qcom_icc_bcm *bcm) } if (bcm->keepalive) { - bcm->vote_x[QCOM_ICC_BUCKET_AMC] = 1; - bcm->vote_x[QCOM_ICC_BUCKET_WAKE] = 1; - bcm->vote_y[QCOM_ICC_BUCKET_AMC] = 1; - bcm->vote_y[QCOM_ICC_BUCKET_WAKE] = 1; + bcm->vote_x[QCOM_ICC_BUCKET_AMC] = bcm->enable_mask; + bcm->vote_x[QCOM_ICC_BUCKET_WAKE] = bcm->enable_mask; + bcm->vote_y[QCOM_ICC_BUCKET_AMC] = bcm->enable_mask; + bcm->vote_y[QCOM_ICC_BUCKET_WAKE] = bcm->enable_mask; } } From db18d5e3eee46f2da86191d9669ac9d763ee57d8 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Thu, 17 Aug 2023 18:54:06 +0800 Subject: [PATCH 1164/2093] serial: tegra: handle clk prepare error in tegra_uart_hw_init() [ Upstream commit 5abd01145d0cc6cd1b7c2fe6ee0b9ea0fa13671e ] In tegra_uart_hw_init(), the return value of clk_prepare_enable() should be checked since it might fail. Fixes: e9ea096dd225 ("serial: tegra: add serial driver") Signed-off-by: Yi Yang Link: https://lore.kernel.org/r/20230817105406.228674-1-yiyang13@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/serial-tegra.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index c08360212aa2..7aa2b5b67001 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -999,7 +999,11 @@ static int tegra_uart_hw_init(struct tegra_uart_port *tup) tup->ier_shadow = 0; tup->current_baud = 0; - clk_prepare_enable(tup->uart_clk); + ret = clk_prepare_enable(tup->uart_clk); + if (ret) { + dev_err(tup->uport.dev, "could not enable clk\n"); + return ret; + } /* Reset the UART controller to clear all previous status.*/ reset_control_assert(tup->rst); From 81ff633a88be2482c163d3acd2801d501261ce6a Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 21 Aug 2023 10:39:27 +0800 Subject: [PATCH 1165/2093] amba: bus: fix refcount leak [ Upstream commit e312cbdc11305568554a9e18a2ea5c2492c183f3 ] commit 5de1540b7bc4 ("drivers/amba: create devices from device tree") increases the refcount of of_node, but not releases it in amba_device_release, so there is refcount leak. By using of_node_put to avoid refcount leak. Fixes: 5de1540b7bc4 ("drivers/amba: create devices from device tree") Signed-off-by: Peng Fan Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230821023928.3324283-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/amba/bus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 110a535648d2..0aa2d3111ae6 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -534,6 +534,7 @@ static void amba_device_release(struct device *dev) { struct amba_device *d = to_amba_device(dev); + of_node_put(d->dev.of_node); if (d->res.parent) release_resource(&d->res); mutex_destroy(&d->periphid_lock); From 3f39698e7e842abc9bd2bd97bf5eeda4543db758 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 21 Aug 2023 10:57:14 +0300 Subject: [PATCH 1166/2093] Revert "IB/isert: Fix incorrect release of isert connection" [ Upstream commit dfe261107c080709459c32695847eec96238852b ] Commit: 699826f4e30a ("IB/isert: Fix incorrect release of isert connection") is causing problems on OPA when DEVICE_REMOVAL is happening. ------------[ cut here ]------------ WARNING: CPU: 52 PID: 2117247 at drivers/infiniband/core/cq.c:359 ib_cq_pool_cleanup+0xac/0xb0 [ib_core] Modules linked in: nfsd nfs_acl target_core_user uio tcm_fc libfc scsi_transport_fc tcm_loop target_core_pscsi target_core_iblock target_core_file rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs rfkill rpcrdma rdma_ucm ib_srpt sunrpc ib_isert iscsi_target_mod target_core_mod opa_vnic ib_iser libiscsi ib_umad scsi_transport_iscsi rdma_cm ib_ipoib iw_cm ib_cm hfi1(-) rdmavt ib_uverbs intel_rapl_msr intel_rapl_common sb_edac ib_core x86_pkg_temp_thermal intel_powerclamp coretemp i2c_i801 mxm_wmi rapl iTCO_wdt ipmi_si iTCO_vendor_support mei_me ipmi_devintf mei intel_cstate ioatdma intel_uncore i2c_smbus joydev pcspkr lpc_ich ipmi_msghandler acpi_power_meter acpi_pad xfs libcrc32c sr_mod sd_mod cdrom t10_pi sg crct10dif_pclmul crc32_pclmul crc32c_intel drm_kms_helper drm_shmem_helper ahci libahci ghash_clmulni_intel igb drm libata dca i2c_algo_bit wmi fuse CPU: 52 PID: 2117247 Comm: modprobe Not tainted 6.5.0-rc1+ #1 Hardware name: Intel Corporation S2600CWR/S2600CW, BIOS SE5C610.86B.01.01.0014.121820151719 12/18/2015 RIP: 0010:ib_cq_pool_cleanup+0xac/0xb0 [ib_core] Code: ff 48 8b 43 40 48 8d 7b 40 48 83 e8 40 4c 39 e7 75 b3 49 83 c4 10 4d 39 fc 75 94 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc <0f> 0b eb a1 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f RSP: 0018:ffffc10bea13fc80 EFLAGS: 00010206 RAX: 000000000000010c RBX: ffff9bf5c7e66c00 RCX: 000000008020001d RDX: 000000008020001e RSI: fffff175221f9900 RDI: ffff9bf5c7e67640 RBP: ffff9bf5c7e67600 R08: ffff9bf5c7e64400 R09: 000000008020001d R10: 0000000040000000 R11: 0000000000000000 R12: ffff9bee4b1e8a18 R13: dead000000000122 R14: dead000000000100 R15: ffff9bee4b1e8a38 FS: 00007ff1e6d38740(0000) GS:ffff9bfd9fb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005652044ecc68 CR3: 0000000889b5c005 CR4: 00000000001706e0 Call Trace: ? __warn+0x80/0x130 ? ib_cq_pool_cleanup+0xac/0xb0 [ib_core] ? report_bug+0x195/0x1a0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? ib_cq_pool_cleanup+0xac/0xb0 [ib_core] disable_device+0x9d/0x160 [ib_core] __ib_unregister_device+0x42/0xb0 [ib_core] ib_unregister_device+0x22/0x30 [ib_core] rvt_unregister_device+0x20/0x90 [rdmavt] hfi1_unregister_ib_device+0x16/0xf0 [hfi1] remove_one+0x55/0x1a0 [hfi1] pci_device_remove+0x36/0xa0 device_release_driver_internal+0x193/0x200 driver_detach+0x44/0x90 bus_remove_driver+0x69/0xf0 pci_unregister_driver+0x2a/0xb0 hfi1_mod_cleanup+0xc/0x3c [hfi1] __do_sys_delete_module.constprop.0+0x17a/0x2f0 ? exit_to_user_mode_prepare+0xc4/0xd0 ? syscall_trace_enter.constprop.0+0x126/0x1a0 do_syscall_64+0x5c/0x90 ? syscall_exit_to_user_mode+0x12/0x30 ? do_syscall_64+0x69/0x90 ? syscall_exit_work+0x103/0x130 ? syscall_exit_to_user_mode+0x12/0x30 ? do_syscall_64+0x69/0x90 ? exc_page_fault+0x65/0x150 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 RIP: 0033:0x7ff1e643f5ab Code: 73 01 c3 48 8b 0d 75 a8 1b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 45 a8 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffec9103cc8 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 00005615267fdc50 RCX: 00007ff1e643f5ab RDX: 0000000000000000 RSI: 0000000000000800 RDI: 00005615267fdcb8 RBP: 00005615267fdc50 R08: 0000000000000000 R09: 0000000000000000 R10: 00007ff1e659eac0 R11: 0000000000000206 R12: 00005615267fdcb8 R13: 0000000000000000 R14: 00005615267fdcb8 R15: 00007ffec9105ff8 ---[ end trace 0000000000000000 ]--- And... restrack: ------------[ cut here ]------------ infiniband hfi1_0: BUG: RESTRACK detected leak of resources restrack: Kernel PD object allocated by ib_isert is not freed restrack: Kernel CQ object allocated by ib_core is not freed restrack: Kernel QP object allocated by rdma_cm is not freed restrack: ------------[ cut here ]------------ Fixes: 699826f4e30a ("IB/isert: Fix incorrect release of isert connection") Reported-by: Dennis Dalessandro Closes: https://lore.kernel.org/all/921cd1d9-2879-f455-1f50-0053fe6a6655@cornelisnetworks.com Link: https://lore.kernel.org/r/a27982d3235005c58f6d321f3fad5eb6e1beaf9e.1692604607.git.leonro@nvidia.com Tested-by: Dennis Dalessandro Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/isert/ib_isert.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index a7fef3ea77fe..a02a3caeaa4e 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2571,6 +2571,8 @@ static void isert_wait_conn(struct iscsit_conn *conn) isert_put_unsol_pending_cmds(conn); isert_wait4cmds(conn); isert_wait4logout(isert_conn); + + queue_work(isert_release_wq, &isert_conn->release_work); } static void isert_free_conn(struct iscsit_conn *conn) From bbd1b1b5082c9a09552477b1079ced26c610ae38 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 21 Aug 2023 21:32:53 +0800 Subject: [PATCH 1167/2093] RDMA/siw: Balance the reference of cep->kref in the error path [ Upstream commit b056327bee09e6b86683d3f709a438ccd6031d72 ] The siw_connect can go to err in below after cep is allocated successfully: 1. If siw_cm_alloc_work returns failure. In this case socket is not assoicated with cep so siw_cep_put can't be called by siw_socket_disassoc. We need to call siw_cep_put twice since cep->kref is increased once after it was initialized. 2. If siw_cm_queue_work can't find a work, which means siw_cep_get is not called in siw_cm_queue_work, so cep->kref is increased twice by siw_cep_get and when associate socket with cep after it was initialized. So we need to call siw_cep_put three times (one in siw_socket_disassoc). 3. siw_send_mpareqrep returns error, this scenario is similar as 2. So we need to remove one siw_cep_put in the error path. Fixes: 6c52fdc244b5 ("rdma/siw: connection management") Signed-off-by: Guoqing Jiang Link: https://lore.kernel.org/r/20230821133255.31111-2-guoqing.jiang@linux.dev Acked-by: Bernard Metzler Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_cm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index f88d2971c2c6..552d8271e423 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1496,7 +1496,6 @@ int siw_connect(struct iw_cm_id *id, struct iw_cm_conn_param *params) cep->cm_id = NULL; id->rem_ref(id); - siw_cep_put(cep); qp->cep = NULL; siw_cep_put(cep); From 9d9a40530383a822e5cd9a01c27b55b467d11340 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 21 Aug 2023 21:32:54 +0800 Subject: [PATCH 1168/2093] RDMA/siw: Correct wrong debug message [ Upstream commit bee024d20451e4ce04ea30099cad09f7f75d288b ] We need to print num_sle first then pbl->max_buf per the condition. Also replace mem->pbl with pbl while at it. Fixes: 303ae1cdfdf7 ("rdma/siw: application interface") Signed-off-by: Guoqing Jiang Link: https://lore.kernel.org/r/20230821133255.31111-3-guoqing.jiang@linux.dev Acked-by: Bernard Metzler Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 2e4cdcd26fe0..193f7d58d384 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -1494,7 +1494,7 @@ int siw_map_mr_sg(struct ib_mr *base_mr, struct scatterlist *sl, int num_sle, if (pbl->max_buf < num_sle) { siw_dbg_mem(mem, "too many SGE's: %d > %d\n", - mem->pbl->max_buf, num_sle); + num_sle, pbl->max_buf); return -ENOMEM; } for_each_sg(sl, slp, num_sle, i) { From cf38960386f3cc4abf395e556af915e4babcafd2 Mon Sep 17 00:00:00 2001 From: Yonatan Nachum Date: Tue, 22 Aug 2023 08:27:25 +0000 Subject: [PATCH 1169/2093] RDMA/efa: Fix wrong resources deallocation order [ Upstream commit dc202c57e9a1423aed528e4b8dc949509cd32191 ] When trying to destroy QP or CQ, we first decrease the refcount and potentially free memory regions allocated for the object and then request the device to destroy the object. If the device fails, the object isn't fully destroyed so the user/IB core can try to destroy the object again which will lead to underflow when trying to decrease an already zeroed refcount. Deallocate resources in reverse order of allocating them to safely free them. Fixes: ff6629f88c52 ("RDMA/efa: Do not delay freeing of DMA pages") Reviewed-by: Michael Margolin Reviewed-by: Yossi Leybovich Signed-off-by: Yonatan Nachum Link: https://lore.kernel.org/r/20230822082725.31719-1-ynachum@amazon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/efa/efa_verbs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index f9526a4c75b2..90d5f1a96f3e 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -443,12 +443,12 @@ int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) ibdev_dbg(&dev->ibdev, "Destroy qp[%u]\n", ibqp->qp_num); - efa_qp_user_mmap_entries_remove(qp); - err = efa_destroy_qp_handle(dev, qp->qp_handle); if (err) return err; + efa_qp_user_mmap_entries_remove(qp); + if (qp->rq_cpu_addr) { ibdev_dbg(&dev->ibdev, "qp->cpu_addr[0x%p] freed: size[%lu], dma[%pad]\n", @@ -1007,8 +1007,8 @@ int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) "Destroy cq[%d] virt[0x%p] freed: size[%lu], dma[%pad]\n", cq->cq_idx, cq->cpu_addr, cq->size, &cq->dma_addr); - efa_cq_user_mmap_entries_remove(cq); efa_destroy_cq_idx(dev, cq->cq_idx); + efa_cq_user_mmap_entries_remove(cq); if (cq->eq) { xa_erase(&dev->cqs_xa, cq->cq_idx); synchronize_irq(cq->eq->irq.irqn); From 6e59609541514d2ed3472f5bc999c55bdb6144ee Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Tue, 13 Jun 2023 03:16:35 -0700 Subject: [PATCH 1170/2093] HID: logitech-dj: Fix error handling in logi_dj_recv_switch_to_dj_mode() [ Upstream commit 6f20d3261265885f6a6be4cda49d7019728760e0 ] Presently, if a call to logi_dj_recv_send_report() fails, we do not learn about the error until after sending short HID_OUTPUT_REPORT with hid_hw_raw_request(). To handle this somewhat unlikely issue, return on error in logi_dj_recv_send_report() (minding ugly sleep workaround) and take into account the result of hid_hw_raw_request(). Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 6a9ddc897883 ("HID: logitech-dj: enable notifications on connect/disconnect") Signed-off-by: Nikita Zhandarovich Link: https://lore.kernel.org/r/20230613101635.77820-1-n.zhandarovich@fintech.ru Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-logitech-dj.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index c358778e070b..08768e5acced 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1285,6 +1285,9 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, * 50 msec should gives enough time to the receiver to be ready. */ msleep(50); + + if (retval) + return retval; } /* @@ -1306,7 +1309,7 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, buf[5] = 0x09; buf[6] = 0x00; - hid_hw_raw_request(hdev, REPORT_ID_HIDPP_SHORT, buf, + retval = hid_hw_raw_request(hdev, REPORT_ID_HIDPP_SHORT, buf, HIDPP_REPORT_SHORT_LENGTH, HID_OUTPUT_REPORT, HID_REQ_SET_REPORT); From f283805d984343b2f216e2f4c6c7af265b9542ae Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Thu, 24 Aug 2023 06:14:17 +0000 Subject: [PATCH 1171/2093] HID: uclogic: Correct devm device reference for hidinput input_dev name [ Upstream commit dd613a4e45f8d35f49a63a2064e5308fa5619e29 ] Reference the HID device rather than the input device for the devm allocation of the input_dev name. Referencing the input_dev would lead to a use-after-free when the input_dev was unregistered and subsequently fires a uevent that depends on the name. At the point of firing the uevent, the name would be freed by devres management. Use devm_kasprintf to simplify the logic for allocating memory and formatting the input_dev name string. Reported-by: syzbot+3a0ebe8a52b89c63739d@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-input/ZOZIZCND+L0P1wJc@penguin/T/ Reported-by: Maxime Ripard Closes: https://lore.kernel.org/linux-input/ZOZIZCND+L0P1wJc@penguin/T/#m443f3dce92520f74b6cf6ffa8653f9c92643d4ae Fixes: cce2dbdf258e ("HID: uclogic: name the input nodes based on their tool") Suggested-by: Maxime Ripard Suggested-by: Dmitry Torokhov Signed-off-by: Rahul Rameshbabu Reviewed-by: Maxime Ripard Link: https://lore.kernel.org/r/20230824061308.222021-2-sergeantsagara@protonmail.com Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-uclogic-core.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index bfbb51f8b5be..39114d5c55a0 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -85,10 +85,8 @@ static int uclogic_input_configured(struct hid_device *hdev, { struct uclogic_drvdata *drvdata = hid_get_drvdata(hdev); struct uclogic_params *params = &drvdata->params; - char *name; const char *suffix = NULL; struct hid_field *field; - size_t len; size_t i; const struct uclogic_params_frame *frame; @@ -146,14 +144,9 @@ static int uclogic_input_configured(struct hid_device *hdev, } } - if (suffix) { - len = strlen(hdev->name) + 2 + strlen(suffix); - name = devm_kzalloc(&hi->input->dev, len, GFP_KERNEL); - if (name) { - snprintf(name, len, "%s %s", hdev->name, suffix); - hi->input->name = name; - } - } + if (suffix) + hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, + "%s %s", hdev->name, suffix); return 0; } From 2763732ec1e68910719c75b6b896e11b6d3d622b Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Thu, 24 Aug 2023 06:14:33 +0000 Subject: [PATCH 1172/2093] HID: multitouch: Correct devm device reference for hidinput input_dev name [ Upstream commit 4794394635293a3e74591351fff469cea7ad15a2 ] Reference the HID device rather than the input device for the devm allocation of the input_dev name. Referencing the input_dev would lead to a use-after-free when the input_dev was unregistered and subsequently fires a uevent that depends on the name. At the point of firing the uevent, the name would be freed by devres management. Use devm_kasprintf to simplify the logic for allocating memory and formatting the input_dev name string. Reported-by: Maxime Ripard Closes: https://lore.kernel.org/linux-input/ZOZIZCND+L0P1wJc@penguin/T/#m443f3dce92520f74b6cf6ffa8653f9c92643d4ae Fixes: c08d46aa805b ("HID: multitouch: devm conversion") Suggested-by: Maxime Ripard Suggested-by: Dmitry Torokhov Signed-off-by: Rahul Rameshbabu Reviewed-by: Maxime Ripard Link: https://lore.kernel.org/r/20230824061308.222021-3-sergeantsagara@protonmail.com Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-multitouch.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index e31be0cb8b85..521b2ffb4244 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1594,7 +1594,6 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app) static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi) { struct mt_device *td = hid_get_drvdata(hdev); - char *name; const char *suffix = NULL; struct mt_report_data *rdata; struct mt_application *mt_application = NULL; @@ -1645,15 +1644,9 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi) break; } - if (suffix) { - name = devm_kzalloc(&hi->input->dev, - strlen(hdev->name) + strlen(suffix) + 2, - GFP_KERNEL); - if (name) { - sprintf(name, "%s %s", hdev->name, suffix); - hi->input->name = name; - } - } + if (suffix) + hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, + "%s %s", hdev->name, suffix); return 0; } From 69b8d7bf834c3fcc598aadcf78a736a871befc17 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 23 Aug 2023 13:54:21 -0500 Subject: [PATCH 1173/2093] platform/x86/amd/pmf: Fix a missing cleanup path [ Upstream commit 4dbd6e61adc7e52dd1c9165f0ccaa90806611e40 ] On systems that support slider notifications but don't otherwise support granular slider the SPS cleanup path doesn't run. This means that loading/unloading/loading leads to failures because the sysfs files don't get setup properly when reloaded. Add the missing cleanup path. Fixes: 33c9ab5b493a ("platform/x86/amd/pmf: Notify OS power slider update") Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230823185421.23959-1-mario.limonciello@amd.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/amd/pmf/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 8a38cd94a605..d10c097380c5 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -322,7 +322,8 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev) static void amd_pmf_deinit_features(struct amd_pmf_dev *dev) { - if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { + if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR) || + is_apmf_func_supported(dev, APMF_FUNC_OS_POWER_SLIDER_UPDATE)) { power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_sps(dev); } From 55a448e8d86342a09e207c58675b65213509db2f Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 18 Aug 2023 16:07:57 -0400 Subject: [PATCH 1174/2093] tick/rcu: Fix false positive "softirq work is pending" messages [ Upstream commit 96c1fa04f089a7e977a44e4e8fdc92e81be20bef ] In commit 0345691b24c0 ("tick/rcu: Stop allowing RCU_SOFTIRQ in idle") the new function report_idle_softirq() was created by breaking code out of the existing can_stop_idle_tick() for kernels v5.18 and newer. In doing so, the code essentially went from a one conditional: if (a && b && c) warn(); to a three conditional: if (!a) return; if (!b) return; if (!c) return; warn(); But that conversion got the condition for the RT specific local_bh_blocked() wrong. The original condition was: !local_bh_blocked() but the conversion failed to negate it so it ended up as: if (!local_bh_blocked()) return false; This issue lay dormant until another fixup for the same commit was added in commit a7e282c77785 ("tick/rcu: Fix bogus ratelimit condition"). This commit realized the ratelimit was essentially set to zero instead of ten, and hence *no* softirq pending messages would ever be issued. Once this commit was backported via linux-stable, both the v6.1 and v6.4 preempt-rt kernels started printing out 10 instances of this at boot: NOHZ tick-stop error: local softirq work is pending, handler #80!!! Remove the negation and return when local_bh_blocked() evaluates to true to bring the correct behaviour back. Fixes: 0345691b24c0 ("tick/rcu: Stop allowing RCU_SOFTIRQ in idle") Signed-off-by: Paul Gortmaker Signed-off-by: Thomas Gleixner Tested-by: Ahmad Fatoum Reviewed-by: Wen Yang Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20230818200757.1808398-1-paul.gortmaker@windriver.com Signed-off-by: Sasha Levin --- kernel/time/tick-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 1ad89eec2a55..798e1841d286 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1050,7 +1050,7 @@ static bool report_idle_softirq(void) return false; /* On RT, softirqs handling may be waiting on some lock */ - if (!local_bh_blocked()) + if (local_bh_blocked()) return false; pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", From ca5e8427e20d770b7b2ad0c4eafd17f4f77c7779 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 29 Aug 2023 08:07:25 -0700 Subject: [PATCH 1175/2093] x86/speculation: Mark all Skylake CPUs as vulnerable to GDS [ Upstream commit c9f4c45c8ec3f07f4f083f9750032a1ec3eab6b2 ] The Gather Data Sampling (GDS) vulnerability is common to all Skylake processors. However, the "client" Skylakes* are now in this list: https://www.intel.com/content/www/us/en/support/articles/000022396/processors.html which means they are no longer included for new vulnerabilities here: https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html or in other GDS documentation. Thus, they were not included in the original GDS mitigation patches. Mark SKYLAKE and SKYLAKE_L as vulnerable to GDS to match all the other Skylake CPUs (which include Kaby Lake). Also group the CPUs so that the ones that share the exact same vulnerabilities are next to each other. Last, move SRBDS to the end of each line. This makes it clear at a glance that SKYLAKE_X is unique. Of the five Skylakes, it is the only "server" CPU and has a different implementation from the clients of the "special register" hardware, making it immune to SRBDS. This makes the diff much harder to read, but the resulting table is worth it. I very much appreciate the report from Michael Zhivich about this issue. Despite what level of support a hardware vendor is providing, the kernel very much needs an accurate and up-to-date list of vulnerable CPUs. More reports like this are very welcome. * Client Skylakes are CPUID 406E3/506E3 which is family 6, models 0x4E and 0x5E, aka INTEL_FAM6_SKYLAKE and INTEL_FAM6_SKYLAKE_L. Reported-by: Michael Zhivich Fixes: 8974eb588283 ("x86/speculation: Add Gather Data Sampling mitigation") Signed-off-by: Dave Hansen Signed-off-by: Ingo Molnar Reviewed-by: Daniel Sneddon Cc: Linus Torvalds Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/common.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d38ae25e7c01..b723368dbc64 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1259,11 +1259,11 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), From fb34716c9ee6700bc6f2b0fdc2a46a4c534b0c93 Mon Sep 17 00:00:00 2001 From: Mikhail Kobuk Date: Fri, 25 Aug 2023 13:34:30 +0300 Subject: [PATCH 1176/2093] tracing: Remove extra space at the end of hwlat_detector/mode [ Upstream commit 2cf0dee989a8b2501929eaab29473b6b1fa11057 ] Space is printed after each mode value including the last one: $ echo \"$(sudo cat /sys/kernel/tracing/hwlat_detector/mode)\" "none [round-robin] per-cpu " Found by Linux Verification Center (linuxtesting.org) with SVACE. Link: https://lore.kernel.org/linux-trace-kernel/20230825103432.7750-1-m.kobuk@ispras.ru Cc: Masami Hiramatsu Fixes: 8fa826b7344d ("trace/hwlat: Implement the mode config option") Signed-off-by: Mikhail Kobuk Reviewed-by: Alexey Khoroshilov Acked-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace_hwlat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 2f37a6e68aa9..b791524a6536 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -635,7 +635,7 @@ static int s_mode_show(struct seq_file *s, void *v) else seq_printf(s, "%s", thread_mode_str[mode]); - if (mode != MODE_MAX) + if (mode < MODE_MAX - 1) /* if mode is any but last */ seq_puts(s, " "); return 0; From 74c85396bd73eca80b96510b4edf93b9a3aff75f Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Thu, 31 Aug 2023 21:27:39 +0800 Subject: [PATCH 1177/2093] tracing: Fix race issue between cpu buffer write and swap [ Upstream commit 3163f635b20e9e1fb4659e74f47918c9dddfe64e ] Warning happened in rb_end_commit() at code: if (RB_WARN_ON(cpu_buffer, !local_read(&cpu_buffer->committing))) WARNING: CPU: 0 PID: 139 at kernel/trace/ring_buffer.c:3142 rb_commit+0x402/0x4a0 Call Trace: ring_buffer_unlock_commit+0x42/0x250 trace_buffer_unlock_commit_regs+0x3b/0x250 trace_event_buffer_commit+0xe5/0x440 trace_event_buffer_reserve+0x11c/0x150 trace_event_raw_event_sched_switch+0x23c/0x2c0 __traceiter_sched_switch+0x59/0x80 __schedule+0x72b/0x1580 schedule+0x92/0x120 worker_thread+0xa0/0x6f0 It is because the race between writing event into cpu buffer and swapping cpu buffer through file per_cpu/cpu0/snapshot: Write on CPU 0 Swap buffer by per_cpu/cpu0/snapshot on CPU 1 -------- -------- tracing_snapshot_write() [...] ring_buffer_lock_reserve() cpu_buffer = buffer->buffers[cpu]; // 1. Suppose find 'cpu_buffer_a'; [...] rb_reserve_next_event() [...] ring_buffer_swap_cpu() if (local_read(&cpu_buffer_a->committing)) goto out_dec; if (local_read(&cpu_buffer_b->committing)) goto out_dec; buffer_a->buffers[cpu] = cpu_buffer_b; buffer_b->buffers[cpu] = cpu_buffer_a; // 2. cpu_buffer has swapped here. rb_start_commit(cpu_buffer); if (unlikely(READ_ONCE(cpu_buffer->buffer) != buffer)) { // 3. This check passed due to 'cpu_buffer->buffer' [...] // has not changed here. return NULL; } cpu_buffer_b->buffer = buffer_a; cpu_buffer_a->buffer = buffer_b; [...] // 4. Reserve event from 'cpu_buffer_a'. ring_buffer_unlock_commit() [...] cpu_buffer = buffer->buffers[cpu]; // 5. Now find 'cpu_buffer_b' !!! rb_commit(cpu_buffer) rb_end_commit() // 6. WARN for the wrong 'committing' state !!! Based on above analysis, we can easily reproduce by following testcase: ``` bash #!/bin/bash dmesg -n 7 sysctl -w kernel.panic_on_warn=1 TR=/sys/kernel/tracing echo 7 > ${TR}/buffer_size_kb echo "sched:sched_switch" > ${TR}/set_event while [ true ]; do echo 1 > ${TR}/per_cpu/cpu0/snapshot done & while [ true ]; do echo 1 > ${TR}/per_cpu/cpu0/snapshot done & while [ true ]; do echo 1 > ${TR}/per_cpu/cpu0/snapshot done & ``` To fix it, IIUC, we can use smp_call_function_single() to do the swap on the target cpu where the buffer is located, so that above race would be avoided. Link: https://lore.kernel.org/linux-trace-kernel/20230831132739.4070878-1-zhengyejian1@huawei.com Cc: Fixes: f1affcaaa861 ("tracing: Add snapshot in the per_cpu trace directories") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e581253ecc53..5d0465ae7be8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7516,6 +7516,11 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) return ret; } +static void tracing_swap_cpu_buffer(void *tr) +{ + update_max_tr_single((struct trace_array *)tr, current, smp_processor_id()); +} + static ssize_t tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) @@ -7574,13 +7579,15 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) break; - local_irq_disable(); /* Now, we're going to swap */ - if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { + local_irq_disable(); update_max_tr(tr, current, smp_processor_id(), NULL); - else - update_max_tr_single(tr, current, iter->cpu_file); - local_irq_enable(); + local_irq_enable(); + } else { + smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer, + (void *)tr, 1); + } break; default: if (tr->allocated_snapshot) { From 6453a2fbc8049985572f8b09669515fd094c9a3e Mon Sep 17 00:00:00 2001 From: William Zhang Date: Thu, 6 Jul 2023 11:29:09 -0700 Subject: [PATCH 1178/2093] mtd: rawnand: brcmnand: Fix mtd oobsize [ Upstream commit 60177390fa061c62d156f4a546e3efd90df3c183 ] brcmnand controller can only access the flash spare area up to certain bytes based on the ECC level. It can be less than the actual flash spare area size. For example, for many NAND chip supporting ECC BCH-8, it has 226 bytes spare area. But controller can only uses 218 bytes. So brcmand driver overrides the mtd oobsize with the controller's accessible spare area size. When the nand base driver utilizes the nand_device object, it resets the oobsize back to the actual flash spare aprea size from nand_memory_organization structure and controller may not able to access all the oob area as mtd advises. This change fixes the issue by overriding the oobsize in the nand_memory_organization structure to the controller's accessible spare area size. Fixes: a7ab085d7c16 ("mtd: rawnand: Initialize the nand_device object") Signed-off-by: William Zhang Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230706182909.79151-6-william.zhang@broadcom.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 2e9c2e2d9c9f..d8418d7fcc37 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -2612,6 +2612,8 @@ static int brcmnand_setup_dev(struct brcmnand_host *host) struct nand_chip *chip = &host->chip; const struct nand_ecc_props *requirements = nanddev_get_ecc_requirements(&chip->base); + struct nand_memory_organization *memorg = + nanddev_get_memorg(&chip->base); struct brcmnand_controller *ctrl = host->ctrl; struct brcmnand_cfg *cfg = &host->hwcfg; char msg[128]; @@ -2633,10 +2635,11 @@ static int brcmnand_setup_dev(struct brcmnand_host *host) if (cfg->spare_area_size > ctrl->max_oob) cfg->spare_area_size = ctrl->max_oob; /* - * Set oobsize to be consistent with controller's spare_area_size, as - * the rest is inaccessible. + * Set mtd and memorg oobsize to be consistent with controller's + * spare_area_size, as the rest is inaccessible. */ mtd->oobsize = cfg->spare_area_size * (mtd->writesize >> FC_SHIFT); + memorg->oobsize = mtd->oobsize; cfg->device_size = mtd->size; cfg->block_size = mtd->erasesize; From 50fa01243dd5491b2ca26a77b8a322045c88d88b Mon Sep 17 00:00:00 2001 From: Rex Zhang Date: Wed, 14 Jun 2023 14:27:06 +0800 Subject: [PATCH 1179/2093] dmaengine: idxd: Modify the dependence of attribute pasid_enabled [ Upstream commit 50c5e6f41d5ad7c731c31135a30d0e4f0e4fea26 ] Kernel PASID and user PASID are separately enabled. User needs to know the user PASID enabling status to decide how to use IDXD device in user space. This is done via the attribute /sys/bus/dsa/devices/dsa0/pasid_enabled. It's unnecessary for user to know the kernel PASID enabling status because user won't use the kernel PASID. But instead of showing the user PASID enabling status, the attribute shows the kernel PASID enabling status. Fix the issue by showing the user PASID enabling status in the attribute. Fixes: 42a1b73852c4 ("dmaengine: idxd: Separate user and kernel pasid enabling") Signed-off-by: Rex Zhang Acked-by: Fenghua Yu Acked-by: Dave Jiang Link: https://lore.kernel.org/r/20230614062706.1743078-1-rex.zhang@intel.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/idxd/sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 18cd8151dee0..6e1e14b376e6 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1426,7 +1426,7 @@ static ssize_t pasid_enabled_show(struct device *dev, { struct idxd_device *idxd = confdev_to_idxd(dev); - return sysfs_emit(buf, "%u\n", device_pasid_enabled(idxd)); + return sysfs_emit(buf, "%u\n", device_user_pasid_enabled(idxd)); } static DEVICE_ATTR_RO(pasid_enabled); From 0d86292e3fbb9ee75f501bb2497ea554eaa901fb Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Thu, 15 Jun 2023 17:10:17 +0000 Subject: [PATCH 1180/2093] phy/rockchip: inno-hdmi: use correct vco_div_5 macro on rk3328 [ Upstream commit 644c06dfbd0da713f772abf0a8f8581ac78e6264 ] inno_hdmi_phy_rk3328_clk_set_rate() is using the RK3228 macro when configuring vco_div_5 on RK3328. Fix this by using correct vco_div_5 macro for RK3328. Fixes: 53706a116863 ("phy: add Rockchip Innosilicon hdmi phy") Signed-off-by: Jonas Karlman Link: https://lore.kernel.org/r/20230615171005.2251032-2-jonas@kwiboo.se Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/rockchip/phy-rockchip-inno-hdmi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c index 80acca4e9e14..15339338aae3 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c @@ -790,8 +790,8 @@ static int inno_hdmi_phy_rk3328_clk_set_rate(struct clk_hw *hw, RK3328_PRE_PLL_POWER_DOWN); /* Configure pre-pll */ - inno_update_bits(inno, 0xa0, RK3228_PCLK_VCO_DIV_5_MASK, - RK3228_PCLK_VCO_DIV_5(cfg->vco_div_5_en)); + inno_update_bits(inno, 0xa0, RK3328_PCLK_VCO_DIV_5_MASK, + RK3328_PCLK_VCO_DIV_5(cfg->vco_div_5_en)); inno_write(inno, 0xa1, RK3328_PRE_PLL_PRE_DIV(cfg->prediv)); val = RK3328_SPREAD_SPECTRUM_MOD_DISABLE; From 8f0f5452cb1b683c3f7f637d717e5c8a9200c3a3 Mon Sep 17 00:00:00 2001 From: Zheng Yang Date: Thu, 15 Jun 2023 17:10:19 +0000 Subject: [PATCH 1181/2093] phy/rockchip: inno-hdmi: round fractal pixclock in rk3328 recalc_rate [ Upstream commit d5ef343c1d62bc4c4c2c393af654a41cb34b449f ] inno_hdmi_phy_rk3328_clk_recalc_rate() is returning a rate not found in the pre pll config table when the fractal divider is used. This can prevent proper power_on because a tmdsclock for the new rate is not found in the pre pll config table. Fix this by saving and returning a rounded pixel rate that exist in the pre pll config table. Fixes: 53706a116863 ("phy: add Rockchip Innosilicon hdmi phy") Signed-off-by: Zheng Yang Signed-off-by: Jonas Karlman Link: https://lore.kernel.org/r/20230615171005.2251032-3-jonas@kwiboo.se Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/rockchip/phy-rockchip-inno-hdmi.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c index 15339338aae3..15a008a1ac7b 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c @@ -745,10 +745,12 @@ unsigned long inno_hdmi_phy_rk3328_clk_recalc_rate(struct clk_hw *hw, do_div(vco, (nd * (no_a == 1 ? no_b : no_a) * no_d * 2)); } - inno->pixclock = vco; - dev_dbg(inno->dev, "%s rate %lu\n", __func__, inno->pixclock); + inno->pixclock = DIV_ROUND_CLOSEST((unsigned long)vco, 1000) * 1000; - return vco; + dev_dbg(inno->dev, "%s rate %lu vco %llu\n", + __func__, inno->pixclock, vco); + + return inno->pixclock; } static long inno_hdmi_phy_rk3328_clk_round_rate(struct clk_hw *hw, From f309ac8a4db92ba68109fa025a0ea9b3c8430597 Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Thu, 15 Jun 2023 17:10:21 +0000 Subject: [PATCH 1182/2093] phy/rockchip: inno-hdmi: do not power on rk3328 post pll on reg write [ Upstream commit 19a1d46bd699940a496d3b0d4e142ef99834988c ] inno_write is used to configure 0xaa reg, that also hold the POST_PLL_POWER_DOWN bit. When POST_PLL_REFCLK_SEL_TMDS is configured the power down bit is not taken into consideration. Fix this by keeping the power down bit until configuration is complete. Also reorder the reg write order for consistency. Fixes: 53706a116863 ("phy: add Rockchip Innosilicon hdmi phy") Signed-off-by: Jonas Karlman Link: https://lore.kernel.org/r/20230615171005.2251032-5-jonas@kwiboo.se Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/rockchip/phy-rockchip-inno-hdmi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c index 15a008a1ac7b..2556caf475c0 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c @@ -1023,9 +1023,10 @@ inno_hdmi_phy_rk3328_power_on(struct inno_hdmi_phy *inno, inno_write(inno, 0xac, RK3328_POST_PLL_FB_DIV_7_0(cfg->fbdiv)); if (cfg->postdiv == 1) { - inno_write(inno, 0xaa, RK3328_POST_PLL_REFCLK_SEL_TMDS); inno_write(inno, 0xab, RK3328_POST_PLL_FB_DIV_8(cfg->fbdiv) | RK3328_POST_PLL_PRE_DIV(cfg->prediv)); + inno_write(inno, 0xaa, RK3328_POST_PLL_REFCLK_SEL_TMDS | + RK3328_POST_PLL_POWER_DOWN); } else { v = (cfg->postdiv / 2) - 1; v &= RK3328_POST_PLL_POST_DIV_MASK; @@ -1033,7 +1034,8 @@ inno_hdmi_phy_rk3328_power_on(struct inno_hdmi_phy *inno, inno_write(inno, 0xab, RK3328_POST_PLL_FB_DIV_8(cfg->fbdiv) | RK3328_POST_PLL_PRE_DIV(cfg->prediv)); inno_write(inno, 0xaa, RK3328_POST_PLL_POST_DIV_ENABLE | - RK3328_POST_PLL_REFCLK_SEL_TMDS); + RK3328_POST_PLL_REFCLK_SEL_TMDS | + RK3328_POST_PLL_POWER_DOWN); } for (v = 0; v < 14; v++) From cae0787e408c30a575760a531ccb69a6b48bbfaf Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Mon, 19 Jun 2023 11:06:31 +0800 Subject: [PATCH 1183/2093] rpmsg: glink: Add check for kstrdup [ Upstream commit b5c9ee8296a3760760c7b5d2e305f91412adc795 ] Add check for the return value of kstrdup() and return the error if it fails in order to avoid NULL pointer dereference. Fixes: b4f8e52b89f6 ("rpmsg: Introduce Qualcomm RPM glink driver") Signed-off-by: Jiasheng Jiang Link: https://lore.kernel.org/r/20230619030631.12361-1-jiasheng@iscas.ac.cn Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- drivers/rpmsg/qcom_glink_native.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 67e7664efb0d..cb8f65c1d4e3 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -224,6 +224,10 @@ static struct glink_channel *qcom_glink_alloc_channel(struct qcom_glink *glink, channel->glink = glink; channel->name = kstrdup(name, GFP_KERNEL); + if (!channel->name) { + kfree(channel); + return ERR_PTR(-ENOMEM); + } init_completion(&channel->open_req); init_completion(&channel->open_ack); From 2804cc3508045eaa202c5f3afb0686b63672ad0b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 11 Jul 2023 09:13:34 +0300 Subject: [PATCH 1184/2093] leds: pwm: Fix error code in led_pwm_create_fwnode() [ Upstream commit cadb2de2a7fd9e955381307de3eddfcc386c208e ] Negative -EINVAL was intended, not positive EINVAL. Fix it. Fixes: 95138e01275e ("leds: pwm: Make error handling more robust") Signed-off-by: Dan Carpenter Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/a33b981a-b2c4-4dc2-b00a-626a090d2f11@moroto.mountain Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/leds-pwm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c index 6832180c1c54..cc892ecd5240 100644 --- a/drivers/leds/leds-pwm.c +++ b/drivers/leds/leds-pwm.c @@ -146,7 +146,7 @@ static int led_pwm_create_fwnode(struct device *dev, struct led_pwm_priv *priv) led.name = to_of_node(fwnode)->name; if (!led.name) { - ret = EINVAL; + ret = -EINVAL; goto err_child_out; } From a253c416e67d4de9a338c8367c69ad85bb88253c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Tue, 1 Aug 2023 14:49:31 +0200 Subject: [PATCH 1185/2093] leds: multicolor: Use rounded division when calculating color components MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 065d099f1be58187e6629273c50b948a02b7e1bf ] Given channel intensity, LED brightness and max LED brightness, the multicolor LED framework helper led_mc_calc_color_components() computes the color channel brightness as chan_brightness = brightness * chan_intensity / max_brightness Consider the situation when (brightness, intensity, max_brightness) is for example (16, 15, 255), then chan_brightness is computed to 0 although the fractional divison would give 0.94, which should be rounded to 1. Use DIV_ROUND_CLOSEST here for the division to give more realistic component computation: chan_brightness = DIV_ROUND_CLOSEST(brightness * chan_intensity, max_brightness) Fixes: 55d5d3b46b08 ("leds: multicolor: Introduce a multicolor class definition") Signed-off-by: Marek Behún Link: https://lore.kernel.org/r/20230801124931.8661-1-kabel@kernel.org Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/led-class-multicolor.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/leds/led-class-multicolor.c b/drivers/leds/led-class-multicolor.c index e317408583df..ec62a4811613 100644 --- a/drivers/leds/led-class-multicolor.c +++ b/drivers/leds/led-class-multicolor.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -19,9 +20,10 @@ int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, int i; for (i = 0; i < mcled_cdev->num_colors; i++) - mcled_cdev->subled_info[i].brightness = brightness * - mcled_cdev->subled_info[i].intensity / - led_cdev->max_brightness; + mcled_cdev->subled_info[i].brightness = + DIV_ROUND_CLOSEST(brightness * + mcled_cdev->subled_info[i].intensity, + led_cdev->max_brightness); return 0; } From f741121a2251ea09c23877388d18c3aa2189de86 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Tue, 1 Aug 2023 17:16:23 +0200 Subject: [PATCH 1186/2093] leds: Fix BUG_ON check for LED_COLOR_ID_MULTI that is always false MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c3f853184bed04105682383c2971798c572226b5 ] At the time we call BUG_ON(props.color == LED_COLOR_ID_MULTI); the props variable is still initialized to zero. Call the BUG_ON only after we parse fwnode into props. Fixes: 77dce3a22e89 ("leds: disallow /sys/class/leds/*:multi:* for now") Signed-off-by: Marek Behún Link: https://lore.kernel.org/r/20230801151623.30387-1-kabel@kernel.org Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/led-core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index 4a97cb745788..aad8bc44459f 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -419,15 +419,15 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data, struct fwnode_handle *fwnode = init_data->fwnode; const char *devicename = init_data->devicename; - /* We want to label LEDs that can produce full range of colors - * as RGB, not multicolor */ - BUG_ON(props.color == LED_COLOR_ID_MULTI); - if (!led_classdev_name) return -EINVAL; led_parse_fwnode_props(dev, fwnode, &props); + /* We want to label LEDs that can produce full range of colors + * as RGB, not multicolor */ + BUG_ON(props.color == LED_COLOR_ID_MULTI); + if (props.label) { /* * If init_data.devicename is NULL, then it indicates that From 3e313b6c470d9748232327348d4c39f03ca64367 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Wed, 2 Aug 2023 11:07:53 +0200 Subject: [PATCH 1187/2093] leds: trigger: tty: Do not use LED_ON/OFF constants, use led_blink_set_oneshot instead MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 730094577e0c37e1bc40be37cbd41f71b0a8a2a4 ] The tty LED trigger uses the obsolete LED_ON & LED_OFF constants when setting LED brightness. This is bad because the LED_ON constant is equal to 1, and so when activating the tty LED trigger on a LED class device with max_brightness greater than 1, the LED is dimmer than it can be (when max_brightness is 255, the LED is very dimm indeed; some devices translate 1/255 to 0, so the LED is OFF all the time). Instead of directly setting brightness to a specific value, use the led_blink_set_oneshot() function from LED core to configure the blink. This function takes the current configured brightness as blink brightness if not zero, and max brightness otherwise. This also changes the behavior of the TTY LED trigger. Previously if rx/tx stats kept changing, the LED was ON all the time they kept changing. With this patch the LED will blink on TTY activity. Fixes: fd4a641ac88f ("leds: trigger: implement a tty trigger") Signed-off-by: Marek Behún Link: https://lore.kernel.org/r/20230802090753.13611-1-kabel@kernel.org Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/trigger/ledtrig-tty.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/leds/trigger/ledtrig-tty.c b/drivers/leds/trigger/ledtrig-tty.c index f62db7e520b5..8ae0d2d284af 100644 --- a/drivers/leds/trigger/ledtrig-tty.c +++ b/drivers/leds/trigger/ledtrig-tty.c @@ -7,6 +7,8 @@ #include #include +#define LEDTRIG_TTY_INTERVAL 50 + struct ledtrig_tty_data { struct led_classdev *led_cdev; struct delayed_work dwork; @@ -122,17 +124,19 @@ static void ledtrig_tty_work(struct work_struct *work) if (icount.rx != trigger_data->rx || icount.tx != trigger_data->tx) { - led_set_brightness_sync(trigger_data->led_cdev, LED_ON); + unsigned long interval = LEDTRIG_TTY_INTERVAL; + + led_blink_set_oneshot(trigger_data->led_cdev, &interval, + &interval, 0); trigger_data->rx = icount.rx; trigger_data->tx = icount.tx; - } else { - led_set_brightness_sync(trigger_data->led_cdev, LED_OFF); } out: mutex_unlock(&trigger_data->mutex); - schedule_delayed_work(&trigger_data->dwork, msecs_to_jiffies(100)); + schedule_delayed_work(&trigger_data->dwork, + msecs_to_jiffies(LEDTRIG_TTY_INTERVAL * 2)); } static struct attribute *ledtrig_tty_attrs[] = { From eaf4c78982aee543c33c5b7675c2ab34b7fae646 Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Fri, 18 Aug 2023 14:42:23 +0800 Subject: [PATCH 1188/2093] mtd: spi-nor: Check bus width while setting QE bit [ Upstream commit f01d8155a92e33cdaa85d20bfbe6c441907b3c1f ] spi_nor_write_16bit_sr_and_check() should also check if bus width is 4 before setting QE bit. Fixes: 39d1e3340c73 ("mtd: spi-nor: Fix clearing of QE bit on lock()/unlock()") Suggested-by: Michael Walle Suggested-by: Tudor Ambarus Signed-off-by: Hsin-Yi Wang Reviewed-by: Michael Walle Link: https://lore.kernel.org/r/20230818064524.1229100-2-hsinyi@chromium.org Signed-off-by: Tudor Ambarus Signed-off-by: Sasha Levin --- drivers/mtd/spi-nor/core.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index dc4d86ceee44..a9000b0ebe69 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -770,21 +770,22 @@ static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1) ret = spi_nor_read_cr(nor, &sr_cr[1]); if (ret) return ret; - } else if (nor->params->quad_enable) { + } else if (spi_nor_get_protocol_width(nor->read_proto) == 4 && + spi_nor_get_protocol_width(nor->write_proto) == 4 && + nor->params->quad_enable) { /* * If the Status Register 2 Read command (35h) is not * supported, we should at least be sure we don't * change the value of the SR2 Quad Enable bit. * - * We can safely assume that when the Quad Enable method is - * set, the value of the QE bit is one, as a consequence of the - * nor->params->quad_enable() call. + * When the Quad Enable method is set and the buswidth is 4, we + * can safely assume that the value of the QE bit is one, as a + * consequence of the nor->params->quad_enable() call. * - * We can safely assume that the Quad Enable bit is present in - * the Status Register 2 at BIT(1). According to the JESD216 - * revB standard, BFPT DWORDS[15], bits 22:20, the 16-bit - * Write Status (01h) command is available just for the cases - * in which the QE bit is described in SR2 at BIT(1). + * According to the JESD216 revB standard, BFPT DWORDS[15], + * bits 22:20, the 16-bit Write Status (01h) command is + * available just for the cases in which the QE bit is + * described in SR2 at BIT(1). */ sr_cr[1] = SR2_QUAD_EN_BIT1; } else { From 222b85e748eb196f65c11fad0b70d0b7c77a1219 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Thu, 17 Aug 2023 19:58:39 +0800 Subject: [PATCH 1189/2093] mtd: rawnand: fsmc: handle clk prepare error in fsmc_nand_resume() [ Upstream commit a5a88125d00612586e941ae13e7fcf36ba8f18a7 ] In fsmc_nand_resume(), the return value of clk_prepare_enable() should be checked since it might fail. Fixes: e25da1c07dfb ("mtd: fsmc_nand: Add clk_{un}prepare() support") Signed-off-by: Yi Yang Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230817115839.10192-1-yiyang13@huawei.com Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/fsmc_nand.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 6b2bda815b88..17786e1331e6 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -1202,9 +1202,14 @@ static int fsmc_nand_suspend(struct device *dev) static int fsmc_nand_resume(struct device *dev) { struct fsmc_nand_data *host = dev_get_drvdata(dev); + int ret; if (host) { - clk_prepare_enable(host->clk); + ret = clk_prepare_enable(host->clk); + if (ret) { + dev_err(dev, "failed to enable clk\n"); + return ret; + } if (host->dev_timings) fsmc_nand_setup(host, host->dev_timings); nand_reset(&host->nand, 0); From 43a57ca7dd9073fbeae2cef9e9e61dd80062529f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 1 Aug 2023 22:15:00 -0700 Subject: [PATCH 1190/2093] um: Fix hostaudio build errors [ Upstream commit db4bfcba7bb8d10f00bba2a3da6b9a9c2a1d7b71 ] Use "select" to ensure that the required kconfig symbols are set as expected. Drop HOSTAUDIO since it is now equivalent to UML_SOUND. Set CONFIG_SOUND=m in ARCH=um defconfig files to maintain the status quo of the default configs. Allow SOUND with UML regardless of HAS_IOMEM. Otherwise there is a kconfig warning for unmet dependencies. (This was not an issue when SOUND was defined in arch/um/drivers/Kconfig. I have done 50 randconfig builds and didn't find any issues.) This fixes build errors when CONFIG_SOUND is not set: ld: arch/um/drivers/hostaudio_kern.o: in function `hostaudio_cleanup_module': hostaudio_kern.c:(.exit.text+0xa): undefined reference to `unregister_sound_mixer' ld: hostaudio_kern.c:(.exit.text+0x15): undefined reference to `unregister_sound_dsp' ld: arch/um/drivers/hostaudio_kern.o: in function `hostaudio_init_module': hostaudio_kern.c:(.init.text+0x19): undefined reference to `register_sound_dsp' ld: hostaudio_kern.c:(.init.text+0x31): undefined reference to `register_sound_mixer' ld: hostaudio_kern.c:(.init.text+0x49): undefined reference to `unregister_sound_dsp' and this kconfig warning: WARNING: unmet direct dependencies detected for SOUND Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: d886e87cb82b ("sound: make OSS sound core optional") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Closes: lore.kernel.org/r/202307141416.vxuRVpFv-lkp@intel.com Cc: Richard Weinberger Cc: Anton Ivanov Cc: Johannes Berg Cc: linux-um@lists.infradead.org Cc: Tejun Heo Cc: Takashi Iwai Cc: Jaroslav Kysela Cc: Masahiro Yamada Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Nicolas Schier Cc: linux-kbuild@vger.kernel.org Cc: alsa-devel@alsa-project.org Reviewed-by: Masahiro Yamada Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- arch/um/configs/i386_defconfig | 1 + arch/um/configs/x86_64_defconfig | 1 + arch/um/drivers/Kconfig | 16 +++------------- arch/um/drivers/Makefile | 2 +- sound/Kconfig | 2 +- 5 files changed, 7 insertions(+), 15 deletions(-) diff --git a/arch/um/configs/i386_defconfig b/arch/um/configs/i386_defconfig index c0162286d68b..c33a6880a437 100644 --- a/arch/um/configs/i386_defconfig +++ b/arch/um/configs/i386_defconfig @@ -35,6 +35,7 @@ CONFIG_TTY_CHAN=y CONFIG_XTERM_CHAN=y CONFIG_CON_CHAN="pts" CONFIG_SSL_CHAN="pts" +CONFIG_SOUND=m CONFIG_UML_SOUND=m CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/um/configs/x86_64_defconfig b/arch/um/configs/x86_64_defconfig index bec6e5d95687..df29f282b6ac 100644 --- a/arch/um/configs/x86_64_defconfig +++ b/arch/um/configs/x86_64_defconfig @@ -33,6 +33,7 @@ CONFIG_TTY_CHAN=y CONFIG_XTERM_CHAN=y CONFIG_CON_CHAN="pts" CONFIG_SSL_CHAN="pts" +CONFIG_SOUND=m CONFIG_UML_SOUND=m CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig index 5903e2b598aa..fe0210eaf9bb 100644 --- a/arch/um/drivers/Kconfig +++ b/arch/um/drivers/Kconfig @@ -111,24 +111,14 @@ config SSL_CHAN config UML_SOUND tristate "Sound support" + depends on SOUND + select SOUND_OSS_CORE help This option enables UML sound support. If enabled, it will pull in - soundcore and the UML hostaudio relay, which acts as a intermediary + the UML hostaudio relay, which acts as a intermediary between the host's dsp and mixer devices and the UML sound system. It is safe to say 'Y' here. -config SOUND - tristate - default UML_SOUND - -config SOUND_OSS_CORE - bool - default UML_SOUND - -config HOSTAUDIO - tristate - default UML_SOUND - endmenu menu "UML Network Devices" diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index 65b449c992d2..079556ec044b 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -54,7 +54,7 @@ obj-$(CONFIG_UML_NET) += net.o obj-$(CONFIG_MCONSOLE) += mconsole.o obj-$(CONFIG_MMAPPER) += mmapper_kern.o obj-$(CONFIG_BLK_DEV_UBD) += ubd.o -obj-$(CONFIG_HOSTAUDIO) += hostaudio.o +obj-$(CONFIG_UML_SOUND) += hostaudio.o obj-$(CONFIG_NULL_CHAN) += null.o obj-$(CONFIG_PORT_CHAN) += port.o obj-$(CONFIG_PTY_CHAN) += pty.o diff --git a/sound/Kconfig b/sound/Kconfig index e56d96d2b11c..1903c35d799e 100644 --- a/sound/Kconfig +++ b/sound/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig SOUND tristate "Sound card support" - depends on HAS_IOMEM + depends on HAS_IOMEM || UML help If you have a sound card in your computer, i.e. if it can say more than an occasional beep, say Y. From e351933e4a14b97003622b501581c57e77c1b8a9 Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Mon, 24 Jul 2023 14:41:08 +0000 Subject: [PATCH 1191/2093] dmaengine: ste_dma40: Add missing IRQ check in d40_probe [ Upstream commit c05ce6907b3d6e148b70f0bb5eafd61dcef1ddc1 ] Check for the return value of platform_get_irq(): if no interrupt is specified, it wouldn't make sense to call request_irq(). Fixes: 8d318a50b3d7 ("DMAENGINE: Support for ST-Ericssons DMA40 block v3") Signed-off-by: Ruan Jinjie Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20230724144108.2582917-1-ruanjinjie@huawei.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/ste_dma40.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index f093e08c23b1..3b09fdc507e0 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -3597,6 +3597,10 @@ static int __init d40_probe(struct platform_device *pdev) spin_lock_init(&base->lcla_pool.lock); base->irq = platform_get_irq(pdev, 0); + if (base->irq < 0) { + ret = base->irq; + goto destroy_cache; + } ret = request_irq(base->irq, d40_handle_interrupt, 0, D40_NAME, base); if (ret) { From 96db43aced395844a7abc9a0a5cc702513e3534a Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Wed, 9 Aug 2023 20:40:18 +0200 Subject: [PATCH 1192/2093] Drivers: hv: vmbus: Don't dereference ACPI root object handle [ Upstream commit 78e04bbff849b51b56f5925b1945db2c6e128b61 ] Since the commit referenced in the Fixes: tag below the VMBus client driver is walking the ACPI namespace up from the VMBus ACPI device to the ACPI namespace root object trying to find Hyper-V MMIO ranges. However, if it is not able to find them it ends trying to walk resources of the ACPI namespace root object itself. This object has all-ones handle, which causes a NULL pointer dereference in the ACPI code (from dereferencing this pointer with an offset). This in turn causes an oops on boot with VMBus host implementations that do not provide Hyper-V MMIO ranges in their VMBus ACPI device or its ancestors. The QEMU VMBus implementation is an example of such implementation. I guess providing these ranges is optional, since all tested Windows versions seem to be able to use VMBus devices without them. Fix this by explicitly terminating the lookup at the ACPI namespace root object. Note that Linux guests under KVM/QEMU do not use the Hyper-V PV interface by default - they only do so if the KVM PV interface is missing or disabled. Example stack trace of such oops: [ 3.710827] ? __die+0x1f/0x60 [ 3.715030] ? page_fault_oops+0x159/0x460 [ 3.716008] ? exc_page_fault+0x73/0x170 [ 3.716959] ? asm_exc_page_fault+0x22/0x30 [ 3.717957] ? acpi_ns_lookup+0x7a/0x4b0 [ 3.718898] ? acpi_ns_internalize_name+0x79/0xc0 [ 3.720018] acpi_ns_get_node_unlocked+0xb5/0xe0 [ 3.721120] ? acpi_ns_check_object_type+0xfe/0x200 [ 3.722285] ? acpi_rs_convert_aml_to_resource+0x37/0x6e0 [ 3.723559] ? down_timeout+0x3a/0x60 [ 3.724455] ? acpi_ns_get_node+0x3a/0x60 [ 3.725412] acpi_ns_get_node+0x3a/0x60 [ 3.726335] acpi_ns_evaluate+0x1c3/0x2c0 [ 3.727295] acpi_ut_evaluate_object+0x64/0x1b0 [ 3.728400] acpi_rs_get_method_data+0x2b/0x70 [ 3.729476] ? vmbus_platform_driver_probe+0x1d0/0x1d0 [hv_vmbus] [ 3.730940] ? vmbus_platform_driver_probe+0x1d0/0x1d0 [hv_vmbus] [ 3.732411] acpi_walk_resources+0x78/0xd0 [ 3.733398] vmbus_platform_driver_probe+0x9f/0x1d0 [hv_vmbus] [ 3.734802] platform_probe+0x3d/0x90 [ 3.735684] really_probe+0x19b/0x400 [ 3.736570] ? __device_attach_driver+0x100/0x100 [ 3.737697] __driver_probe_device+0x78/0x160 [ 3.738746] driver_probe_device+0x1f/0x90 [ 3.739743] __driver_attach+0xc2/0x1b0 [ 3.740671] bus_for_each_dev+0x70/0xc0 [ 3.741601] bus_add_driver+0x10e/0x210 [ 3.742527] driver_register+0x55/0xf0 [ 3.744412] ? 0xffffffffc039a000 [ 3.745207] hv_acpi_init+0x3c/0x1000 [hv_vmbus] Fixes: 7f163a6fd957 ("drivers:hv: Modify hv_vmbus to search for all MMIO ranges available.") Signed-off-by: Maciej S. Szmigiero Reviewed-by: Michael Kelley Signed-off-by: Wei Liu Link: https://lore.kernel.org/r/fd8e64ceeecfd1d95ff49021080cf699e88dbbde.1691606267.git.maciej.szmigiero@oracle.com Signed-off-by: Sasha Levin --- drivers/hv/vmbus_drv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b03cb7ae7fd3..e9c3f1e826ba 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2452,7 +2452,8 @@ static int vmbus_acpi_add(struct acpi_device *device) * Some ancestor of the vmbus acpi device (Gen1 or Gen2 * firmware) is the VMOD that has the mmio ranges. Get that. */ - for (ancestor = acpi_dev_parent(device); ancestor; + for (ancestor = acpi_dev_parent(device); + ancestor && ancestor->handle != ACPI_ROOT_OBJECT; ancestor = acpi_dev_parent(ancestor)) { result = acpi_walk_resources(ancestor->handle, METHOD_NAME__CRS, vmbus_walk_resources, NULL); From 4927edc23edccc55284a8c929323e9fa6c5ce71f Mon Sep 17 00:00:00 2001 From: Liao Chang Date: Tue, 29 Aug 2023 07:03:18 +0000 Subject: [PATCH 1193/2093] cpufreq: Fix the race condition while updating the transition_task of policy [ Upstream commit 61bfbf7951ba561dcbdd5357702d3cbc2d447812 ] The field 'transition_task' of policy structure is used to track the task which is performing the frequency transition. Using this field to print a warning once detect a case where the same task is calling _begin() again before completing the preivous frequency transition via the _end(). However, there is a potential race condition in _end() and _begin() APIs while updating the field 'transition_task' of policy, the scenario is depicted below: Task A Task B /* 1st freq transition */ Invoke _begin() { ... ... } /* 2nd freq transition */ Invoke _begin() { ... //waiting for A to ... //clear ... //transition_ongoing ... //in _end() for ... //the 1st transition | Change the frequency | | Invoke _end() { | ... | ... | transition_ongoing = false; V transition_ongoing = true; transition_task = current; transition_task = NULL; ... //A overwrites the task ... //performing the transition ... //result in error warning. } To fix this race condition, the transition_lock of policy structure is now acquired before updating policy structure in _end() API. Which ensure that only one task can update the 'transition_task' field at a time. Link: https://lore.kernel.org/all/b3c61d8a-d52d-3136-fbf0-d1de9f1ba411@huawei.com/ Fixes: ca654dc3a93d ("cpufreq: Catch double invocations of cpufreq_freq_transition_begin/end") Signed-off-by: Liao Chang Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/cpufreq/cpufreq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 285ba51b31f6..c8912756fc06 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -450,8 +450,10 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy, policy->cur, policy->cpuinfo.max_freq); + spin_lock(&policy->transition_lock); policy->transition_ongoing = false; policy->transition_task = NULL; + spin_unlock(&policy->transition_lock); wake_up(&policy->transition_wait); } From ad8900dd8a568288cf6e332ffd4f11b2e74b17f4 Mon Sep 17 00:00:00 2001 From: Yuan Yao Date: Tue, 8 Aug 2023 05:10:59 +0000 Subject: [PATCH 1194/2093] virtio_ring: fix avail_wrap_counter in virtqueue_add_packed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1acfe2c1225899eab5ab724c91b7e1eb2881b9ab ] In current packed virtqueue implementation, the avail_wrap_counter won't flip, in the case when the driver supplies a descriptor chain with a length equals to the queue size; total_sg == vq->packed.vring.num. Let’s assume the following situation: vq->packed.vring.num=4 vq->packed.next_avail_idx: 1 vq->packed.avail_wrap_counter: 0 Then the driver adds a descriptor chain containing 4 descriptors. We expect the following result with avail_wrap_counter flipped: vq->packed.next_avail_idx: 1 vq->packed.avail_wrap_counter: 1 But, the current implementation gives the following result: vq->packed.next_avail_idx: 1 vq->packed.avail_wrap_counter: 0 To reproduce the bug, you can set a packed queue size as small as possible, so that the driver is more likely to provide a descriptor chain with a length equal to the packed queue size. For example, in qemu run following commands: sudo qemu-system-x86_64 \ -enable-kvm \ -nographic \ -kernel "path/to/kernel_image" \ -m 1G \ -drive file="path/to/rootfs",if=none,id=disk \ -device virtio-blk,drive=disk \ -drive file="path/to/disk_image",if=none,id=rwdisk \ -device virtio-blk,drive=rwdisk,packed=on,queue-size=4,\ indirect_desc=off \ -append "console=ttyS0 root=/dev/vda rw init=/bin/bash" Inside the VM, create a directory and mount the rwdisk device on it. The rwdisk will hang and mount operation will not complete. This commit fixes the wrap counter error by flipping the packed.avail_wrap_counter, when start of descriptor chain equals to the end of descriptor chain (head == i). Fixes: 1ce9e6055fa0 ("virtio_ring: introduce packed ring support") Signed-off-by: Yuan Yao Message-Id: <20230808051110.3492693-1-yuanyaogoog@chromium.org> Acked-by: Jason Wang Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/virtio/virtio_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 90d514c14179..7d320f799ca1 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1449,7 +1449,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, } } - if (i < head) + if (i <= head) vq->packed.avail_wrap_counter ^= 1; /* We're using some buffers from the free list. */ From 6678912b4df1bfac6f7c80642d56dc22e23419e4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Sep 2023 04:23:38 +0000 Subject: [PATCH 1195/2093] igmp: limit igmpv3_newpack() packet size to IP_MAX_MTU commit c3b704d4a4a265660e665df51b129e8425216ed1 upstream. This is a follow up of commit 915d975b2ffa ("net: deal with integer overflows in kmalloc_reserve()") based on David Laight feedback. Back in 2010, I failed to realize malicious users could set dev->mtu to arbitrary values. This mtu has been since limited to 0x7fffffff but regardless of how big dev->mtu is, it makes no sense for igmpv3_newpack() to allocate more than IP_MAX_MTU and risk various skb fields overflows. Fixes: 57e1ab6eaddc ("igmp: refine skb allocations") Link: https://lore.kernel.org/netdev/d273628df80f45428e739274ab9ecb72@AcuMS.aculab.com/ Signed-off-by: Eric Dumazet Reported-by: David Laight Cc: Kyle Zeng Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/igmp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 81be3e0f0e70..cbc4816ed7d8 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -353,8 +353,9 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - unsigned int size = mtu; + unsigned int size; + size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); From 7ca0706c68adadf86a36b60dca090f5e9481e808 Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Tue, 5 Sep 2023 15:04:09 -0700 Subject: [PATCH 1196/2093] netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c commit 050d91c03b28ca479df13dfb02bcd2c60dd6a878 upstream. The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can lead to the use of wrong `CIDR_POS(c)` for calculating array offsets, which can lead to integer underflow. As a result, it leads to slab out-of-bound access. This patch adds back the IP_SET_HASH_WITH_NET0 macro to ip_set_hash_netportnet to address the issue. Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net") Suggested-by: Jozsef Kadlecsik Signed-off-by: Kyle Zeng Acked-by: Jozsef Kadlecsik Signed-off-by: Florian Westphal Signed-off-by: Greg Kroah-Hartman --- net/netfilter/ipset/ip_set_hash_netportnet.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 005a7ce87217..bf4f91b78e1d 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -36,6 +36,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ From bcdb4a5c42b09f7cc00bbdafece7eae177b959e9 Mon Sep 17 00:00:00 2001 From: Xiao Liang Date: Fri, 25 Aug 2023 13:33:27 +0800 Subject: [PATCH 1197/2093] netfilter: nft_exthdr: Fix non-linear header modification commit 28427f368f0e08d504ed06e74bc7cc79d6d06511 upstream. Fix skb_ensure_writable() size. Don't use nft_tcp_header_pointer() to make it explicit that pointers point to the packet (not local buffer). Fixes: 99d1712bc41c ("netfilter: exthdr: tcp option set support") Fixes: 7890cbea66e7 ("netfilter: exthdr: add support for tcp option removal") Cc: stable@vger.kernel.org Signed-off-by: Xiao Liang Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nft_exthdr.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a67ea9c3ae57..c307c57a93e5 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -238,7 +238,12 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, if (!tcph) goto err; + if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len)) + goto err; + + tcph = (struct tcphdr *)(pkt->skb->data + nft_thoff(pkt)); opt = (u8 *)tcph; + for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { union { __be16 v16; @@ -253,15 +258,6 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, if (i + optl > tcphdr_len || priv->len + priv->offset > optl) goto err; - if (skb_ensure_writable(pkt->skb, - nft_thoff(pkt) + i + priv->len)) - goto err; - - tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, - &tcphdr_len); - if (!tcph) - goto err; - offset = i + priv->offset; switch (priv->len) { @@ -325,9 +321,9 @@ static void nft_exthdr_tcp_strip_eval(const struct nft_expr *expr, if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len)) goto drop; - opt = (u8 *)nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); - if (!opt) - goto err; + tcph = (struct tcphdr *)(pkt->skb->data + nft_thoff(pkt)); + opt = (u8 *)tcph; + for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { unsigned int j; From 1c164c1e9e93b0a72a03a7edb754e3857d4e4302 Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Mon, 28 Aug 2023 10:21:07 -0300 Subject: [PATCH 1198/2093] netfilter: xt_u32: validate user space input commit 69c5d284f67089b4750d28ff6ac6f52ec224b330 upstream. The xt_u32 module doesn't validate the fields in the xt_u32 structure. An attacker may take advantage of this to trigger an OOB read by setting the size fields with a value beyond the arrays boundaries. Add a checkentry function to validate the structure. This was originally reported by the ZDI project (ZDI-CAN-18408). Fixes: 1b50b8a371e9 ("[NETFILTER]: Add u32 match") Cc: stable@vger.kernel.org Signed-off-by: Wander Lairson Costa Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/xt_u32.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c index 177b40d08098..117d4615d668 100644 --- a/net/netfilter/xt_u32.c +++ b/net/netfilter/xt_u32.c @@ -96,11 +96,32 @@ static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par) return ret ^ data->invert; } +static int u32_mt_checkentry(const struct xt_mtchk_param *par) +{ + const struct xt_u32 *data = par->matchinfo; + const struct xt_u32_test *ct; + unsigned int i; + + if (data->ntests > ARRAY_SIZE(data->tests)) + return -EINVAL; + + for (i = 0; i < data->ntests; ++i) { + ct = &data->tests[i]; + + if (ct->nnums > ARRAY_SIZE(ct->location) || + ct->nvalues > ARRAY_SIZE(ct->value)) + return -EINVAL; + } + + return 0; +} + static struct xt_match xt_u32_mt_reg __read_mostly = { .name = "u32", .revision = 0, .family = NFPROTO_UNSPEC, .match = u32_mt, + .checkentry = u32_mt_checkentry, .matchsize = sizeof(struct xt_u32), .me = THIS_MODULE, }; From 4921f9349b66da7c5a2b6418fe45e9ae0ae72924 Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Mon, 28 Aug 2023 19:12:55 -0300 Subject: [PATCH 1199/2093] netfilter: xt_sctp: validate the flag_info count commit e99476497687ef9e850748fe6d232264f30bc8f9 upstream. sctp_mt_check doesn't validate the flag_count field. An attacker can take advantage of that to trigger a OOB read and leak memory information. Add the field validation in the checkentry function. Fixes: 2e4e6a17af35 ("[NETFILTER] x_tables: Abstraction layer for {ip,ip6,arp}_tables") Cc: stable@vger.kernel.org Reported-by: Lucas Leong Signed-off-by: Wander Lairson Costa Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/xt_sctp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 680015ba7cb6..d4bf089c9e3f 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -150,6 +150,8 @@ static int sctp_mt_check(const struct xt_mtchk_param *par) { const struct xt_sctp_info *info = par->matchinfo; + if (info->flag_count > ARRAY_SIZE(info->flag_info)) + return -EINVAL; if (info->flags & ~XT_SCTP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~XT_SCTP_VALID_FLAGS) From 04c3eee4e13f60bf6f9a366ad39f88a01a57166e Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Thu, 31 Aug 2023 02:17:02 -0600 Subject: [PATCH 1200/2093] skbuff: skb_segment, Call zero copy functions before using skbuff frags commit 2ea35288c83b3d501a88bc17f2df8f176b5cc96f upstream. Commit bf5c25d60861 ("skbuff: in skb_segment, call zerocopy functions once per nskb") added the call to zero copy functions in skb_segment(). The change introduced a bug in skb_segment() because skb_orphan_frags() may possibly change the number of fragments or allocate new fragments altogether leaving nrfrags and frag to point to the old values. This can cause a panic with stacktrace like the one below. [ 193.894380] BUG: kernel NULL pointer dereference, address: 00000000000000bc [ 193.895273] CPU: 13 PID: 18164 Comm: vh-net-17428 Kdump: loaded Tainted: G O 5.15.123+ #26 [ 193.903919] RIP: 0010:skb_segment+0xb0e/0x12f0 [ 194.021892] Call Trace: [ 194.027422] [ 194.072861] tcp_gso_segment+0x107/0x540 [ 194.082031] inet_gso_segment+0x15c/0x3d0 [ 194.090783] skb_mac_gso_segment+0x9f/0x110 [ 194.095016] __skb_gso_segment+0xc1/0x190 [ 194.103131] netem_enqueue+0x290/0xb10 [sch_netem] [ 194.107071] dev_qdisc_enqueue+0x16/0x70 [ 194.110884] __dev_queue_xmit+0x63b/0xb30 [ 194.121670] bond_start_xmit+0x159/0x380 [bonding] [ 194.128506] dev_hard_start_xmit+0xc3/0x1e0 [ 194.131787] __dev_queue_xmit+0x8a0/0xb30 [ 194.138225] macvlan_start_xmit+0x4f/0x100 [macvlan] [ 194.141477] dev_hard_start_xmit+0xc3/0x1e0 [ 194.144622] sch_direct_xmit+0xe3/0x280 [ 194.147748] __dev_queue_xmit+0x54a/0xb30 [ 194.154131] tap_get_user+0x2a8/0x9c0 [tap] [ 194.157358] tap_sendmsg+0x52/0x8e0 [tap] [ 194.167049] handle_tx_zerocopy+0x14e/0x4c0 [vhost_net] [ 194.173631] handle_tx+0xcd/0xe0 [vhost_net] [ 194.176959] vhost_worker+0x76/0xb0 [vhost] [ 194.183667] kthread+0x118/0x140 [ 194.190358] ret_from_fork+0x1f/0x30 [ 194.193670] In this case calling skb_orphan_frags() updated nr_frags leaving nrfrags local variable in skb_segment() stale. This resulted in the code hitting i >= nrfrags prematurely and trying to move to next frag_skb using list_skb pointer, which was NULL, and caused kernel panic. Move the call to zero copy functions before using frags and nr_frags. Fixes: bf5c25d60861 ("skbuff: in skb_segment, call zerocopy functions once per nskb") Signed-off-by: Mohamed Khalfella Reported-by: Amit Goyal Cc: stable@vger.kernel.org Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b6c16db86c71..24bf4aa222d2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4135,21 +4135,20 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; - skb_frag_t *frag = skb_shinfo(head_skb)->frags; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); - struct sk_buff *frag_skb = head_skb; unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; + struct sk_buff *frag_skb; + skb_frag_t *frag; __be16 proto; bool csum, sg; - int nfrags = skb_shinfo(head_skb)->nr_frags; int err = -ENOMEM; int i = 0; - int pos; + int nfrags, pos; if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { @@ -4226,6 +4225,13 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); + if (skb_orphan_frags(head_skb, GFP_ATOMIC)) + return ERR_PTR(-ENOMEM); + + nfrags = skb_shinfo(head_skb)->nr_frags; + frag = skb_shinfo(head_skb)->frags; + frag_skb = head_skb; + do { struct sk_buff *nskb; skb_frag_t *nskb_frag; @@ -4246,6 +4252,10 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); + nskb = skb_clone(list_skb, GFP_ATOMIC); + if (unlikely(!nskb)) + goto err; + i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; @@ -4264,12 +4274,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, frag++; } - nskb = skb_clone(list_skb, GFP_ATOMIC); list_skb = list_skb->next; - if (unlikely(!nskb)) - goto err; - if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; @@ -4345,12 +4351,16 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & SKBFL_SHARED_FRAG; - if (skb_orphan_frags(frag_skb, GFP_ATOMIC) || - skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) + if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { + if (skb_orphan_frags(list_skb, GFP_ATOMIC) || + skb_zerocopy_clone(nskb, list_skb, + GFP_ATOMIC)) + goto err; + i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; @@ -4364,10 +4374,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, i--; frag--; } - if (skb_orphan_frags(frag_skb, GFP_ATOMIC) || - skb_zerocopy_clone(nskb, frag_skb, - GFP_ATOMIC)) - goto err; list_skb = list_skb->next; } From d2e906c725979c39ebf120a189e521ceae787d26 Mon Sep 17 00:00:00 2001 From: Radoslaw Tyl Date: Thu, 24 Aug 2023 13:46:19 -0700 Subject: [PATCH 1201/2093] igb: set max size RX buffer when store bad packet is enabled commit bb5ed01cd2428cd25b1c88a3a9cba87055eb289f upstream. Increase the RX buffer size to 3K when the SBP bit is on. The size of the RX buffer determines the number of pages allocated which may not be sufficient for receive frames larger than the set MTU size. Cc: stable@vger.kernel.org Fixes: 89eaefb61dc9 ("igb: Support RX-ALL feature flag.") Reported-by: Manfred Rudigier Signed-off-by: Radoslaw Tyl Tested-by: Arpana Arland (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/igb/igb_main.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 3e0444354632..d0ead18ec026 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4758,6 +4758,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, static void igb_set_rx_buffer_len(struct igb_adapter *adapter, struct igb_ring *rx_ring) { +#if (PAGE_SIZE < 8192) + struct e1000_hw *hw = &adapter->hw; +#endif + /* set build_skb and buffer size flags */ clear_ring_build_skb_enabled(rx_ring); clear_ring_uses_large_buffer(rx_ring); @@ -4768,10 +4772,9 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, set_ring_build_skb_enabled(rx_ring); #if (PAGE_SIZE < 8192) - if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) - return; - - set_ring_uses_large_buffer(rx_ring); + if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + rd32(E1000_RCTL) & E1000_RCTL_SBP) + set_ring_uses_large_buffer(rx_ring); #endif } From 8918025feb2f5f7c73f2495c158f22997e25cb02 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 9 Aug 2023 13:31:08 +0200 Subject: [PATCH 1202/2093] PM / devfreq: Fix leak in devfreq_dev_release() commit 5693d077595de721f9ddbf9d37f40e5409707dfe upstream. srcu_init_notifier_head() allocates resources that need to be released with a srcu_cleanup_notifier_head() call. Reported by kmemleak. Fixes: 0fe3a66410a3 ("PM / devfreq: Add new DEVFREQ_TRANSITION_NOTIFIER notifier") Cc: Signed-off-by: Boris Brezillon Reviewed-by: Dhruva Gole Signed-off-by: Chanwoo Choi Signed-off-by: Greg Kroah-Hartman --- drivers/devfreq/devfreq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 8c5f6f7fca11..fe6644f99887 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -763,6 +763,7 @@ static void devfreq_dev_release(struct device *dev) dev_pm_opp_put_opp_table(devfreq->opp_table); mutex_destroy(&devfreq->lock); + srcu_cleanup_notifier_head(&devfreq->transition_notifier_list); kfree(devfreq); } From 8ad2e7efb2ce2edc735c5249261059d8ff2b12df Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 29 Aug 2023 15:43:44 +0200 Subject: [PATCH 1203/2093] ALSA: pcm: Fix missing fixup call in compat hw_refine ioctl commit 358040e3807754944dbddf948a23c6d914297ed7 upstream. The update of rate_num/den and msbits were factored out to fixup_unreferenced_params() function to be called explicitly after the hw_refine or hw_params procedure. It's called from snd_pcm_hw_refine_user(), but it's forgotten in the PCM compat ioctl. This ended up with the incomplete rate_num/den and msbits parameters when 32bit compat ioctl is used. This patch adds the missing call in snd_pcm_ioctl_hw_params_compat(). Reported-by: Meng_Cai@novatek.com.cn Fixes: f9a076bff053 ("ALSA: pcm: calculate non-mask/non-interval parameters always when possible") Reviewed-by: Takashi Sakamoto Reviewed-by: Jaroslav Kysela Cc: Link: https://lore.kernel.org/r/20230829134344.31588-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_compat.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 42c2ada8e888..c96483091f30 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -253,10 +253,14 @@ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, goto error; } - if (refine) + if (refine) { err = snd_pcm_hw_refine(substream, data); - else + if (err < 0) + goto error; + err = fixup_unreferenced_params(substream, data); + } else { err = snd_pcm_hw_params(substream, data); + } if (err < 0) goto error; if (copy_to_user(data32, data, sizeof(*data32)) || From 3f7a4e88e40e38c0b16a4bcb599b7b1d8c81440d Mon Sep 17 00:00:00 2001 From: Zqiang Date: Mon, 4 Sep 2023 18:08:05 +0000 Subject: [PATCH 1204/2093] rcu: dump vmalloc memory info safely commit c83ad36a18c02c0f51280b50272327807916987f upstream. Currently, for double invoke call_rcu(), will dump rcu_head objects memory info, if the objects is not allocated from the slab allocator, the vmalloc_dump_obj() will be invoke and the vmap_area_lock spinlock need to be held, since the call_rcu() can be invoked in interrupt context, therefore, there is a possibility of spinlock deadlock scenarios. And in Preempt-RT kernel, the rcutorture test also trigger the following lockdep warning: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0 preempt_count: 1, expected: 0 RCU nest depth: 1, expected: 1 3 locks held by swapper/0/1: #0: ffffffffb534ee80 (fullstop_mutex){+.+.}-{4:4}, at: torture_init_begin+0x24/0xa0 #1: ffffffffb5307940 (rcu_read_lock){....}-{1:3}, at: rcu_torture_init+0x1ec7/0x2370 #2: ffffffffb536af40 (vmap_area_lock){+.+.}-{3:3}, at: find_vmap_area+0x1f/0x70 irq event stamp: 565512 hardirqs last enabled at (565511): [] __call_rcu_common+0x218/0x940 hardirqs last disabled at (565512): [] rcu_torture_init+0x20b2/0x2370 softirqs last enabled at (399112): [] __local_bh_enable_ip+0x126/0x170 softirqs last disabled at (399106): [] inet_register_protosw+0x9/0x1d0 Preemption disabled at: [] rcu_torture_init+0x1f13/0x2370 CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 6.5.0-rc4-rt2-yocto-preempt-rt+ #15 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x68/0xb0 dump_stack+0x14/0x20 __might_resched+0x1aa/0x280 ? __pfx_rcu_torture_err_cb+0x10/0x10 rt_spin_lock+0x53/0x130 ? find_vmap_area+0x1f/0x70 find_vmap_area+0x1f/0x70 vmalloc_dump_obj+0x20/0x60 mem_dump_obj+0x22/0x90 __call_rcu_common+0x5bf/0x940 ? debug_smp_processor_id+0x1b/0x30 call_rcu_hurry+0x14/0x20 rcu_torture_init+0x1f82/0x2370 ? __pfx_rcu_torture_leak_cb+0x10/0x10 ? __pfx_rcu_torture_leak_cb+0x10/0x10 ? __pfx_rcu_torture_init+0x10/0x10 do_one_initcall+0x6c/0x300 ? debug_smp_processor_id+0x1b/0x30 kernel_init_freeable+0x2b9/0x540 ? __pfx_kernel_init+0x10/0x10 kernel_init+0x1f/0x150 ret_from_fork+0x40/0x50 ? __pfx_kernel_init+0x10/0x10 ret_from_fork_asm+0x1b/0x30 The previous patch fixes this by using the deadlock-safe best-effort version of find_vm_area. However, in case of failure print the fact that the pointer was a vmalloc pointer so that we print at least something. Link: https://lkml.kernel.org/r/20230904180806.1002832-2-joel@joelfernandes.org Fixes: 98f180837a89 ("mm: Make mem_dump_obj() handle vmalloc() memory") Signed-off-by: Zqiang Signed-off-by: Joel Fernandes (Google) Reported-by: Zhen Lei Reviewed-by: Matthew Wilcox (Oracle) Cc: Paul E. McKenney Cc: Uladzislau Rezki (Sony) Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/util.c b/mm/util.c index 12984e76767e..ce3bb17c97b9 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1127,7 +1127,9 @@ void mem_dump_obj(void *object) if (vmalloc_dump_obj(object)) return; - if (virt_addr_valid(object)) + if (is_vmalloc_addr(object)) + type = "vmalloc memory"; + else if (virt_addr_valid(object)) type = "non-slab/vmalloc memory"; else if (object == NULL) type = "NULL pointer"; From 2344b13976512fab5f7d2dcc6018ebdea215c98e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 10 Aug 2023 22:45:32 -0700 Subject: [PATCH 1205/2093] printk: ringbuffer: Fix truncating buffer size min_t cast commit 53e9e33ede37a247d926db5e4a9e56b55204e66c upstream. If an output buffer size exceeded U16_MAX, the min_t(u16, ...) cast in copy_data() was causing writes to truncate. This manifested as output bytes being skipped, seen as %NUL bytes in pstore dumps when the available record size was larger than 65536. Fix the cast to no longer truncate the calculation. Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: John Ogness Reported-by: Vijay Balakrishna Link: https://lore.kernel.org/lkml/d8bb1ec7-a4c5-43a2-9de0-9643a70b899f@linux.microsoft.com/ Fixes: b6cf8b3f3312 ("printk: add lockless ringbuffer") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Tested-by: Vijay Balakrishna Tested-by: Guilherme G. Piccoli # Steam Deck Reviewed-by: Tyler Hicks (Microsoft) Tested-by: Tyler Hicks (Microsoft) Reviewed-by: John Ogness Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230811054528.never.165-kees@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/printk/printk_ringbuffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index 2b7b6ddab4f7..0bbcd1344f21 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -1735,7 +1735,7 @@ static bool copy_data(struct prb_data_ring *data_ring, if (!buf || !buf_size) return true; - data_size = min_t(u16, buf_size, len); + data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; From 157c46360cf3afc32c3864543301c6c3dd00b3a5 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 21 Jul 2023 09:01:32 -0700 Subject: [PATCH 1206/2093] scsi: core: Fix the scsi_set_resid() documentation commit f669b8a683e4ee26fa5cafe19d71cec1786b556a upstream. Because scsi_finish_command() subtracts the residual from the buffer length, residual overflows must not be reported. Reflect this in the SCSI documentation. See also commit 9237f04e12cc ("scsi: core: Fix scsi_get/set_resid() interface") Cc: Damien Le Moal Cc: Hannes Reinecke Cc: Douglas Gilbert Cc: stable@vger.kernel.org Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230721160154.874010-2-bvanassche@acm.org Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- Documentation/scsi/scsi_mid_low_api.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/scsi/scsi_mid_low_api.rst b/Documentation/scsi/scsi_mid_low_api.rst index a8c5bd15a440..edfd179b9c7c 100644 --- a/Documentation/scsi/scsi_mid_low_api.rst +++ b/Documentation/scsi/scsi_mid_low_api.rst @@ -1190,11 +1190,11 @@ Members of interest: - pointer to scsi_device object that this command is associated with. resid - - an LLD should set this signed integer to the requested + - an LLD should set this unsigned integer to the requested transfer length (i.e. 'request_bufflen') less the number of bytes that are actually transferred. 'resid' is preset to 0 so an LLD can ignore it if it cannot detect - underruns (overruns should be rare). If possible an LLD + underruns (overruns should not be reported). An LLD should set 'resid' prior to invoking 'done'. The most interesting case is data transfers from a SCSI target device (e.g. READs) that underrun. From 4245ca8f4051459beebb70f189329b670efa32a1 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 4 Sep 2023 18:08:04 +0000 Subject: [PATCH 1207/2093] mm/vmalloc: add a safer version of find_vm_area() for debug commit 0818e739b5c061b0251c30152380600fb9b84c0c upstream. It is unsafe to dump vmalloc area information when trying to do so from some contexts. Add a safer trylock version of the same function to do a best-effort VMA finding and use it from vmalloc_dump_obj(). [applied test robot feedback on unused function fix.] [applied Uladzislau feedback on locking.] Link: https://lkml.kernel.org/r/20230904180806.1002832-1-joel@joelfernandes.org Fixes: 98f180837a89 ("mm: Make mem_dump_obj() handle vmalloc() memory") Signed-off-by: Joel Fernandes (Google) Reviewed-by: Uladzislau Rezki (Sony) Reported-by: Zhen Lei Cc: Paul E. McKenney Cc: Zqiang Cc: Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmalloc.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 80bd104a4d42..67a10a04df04 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4041,14 +4041,32 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) #ifdef CONFIG_PRINTK bool vmalloc_dump_obj(void *object) { - struct vm_struct *vm; void *objp = (void *)PAGE_ALIGN((unsigned long)object); + const void *caller; + struct vm_struct *vm; + struct vmap_area *va; + unsigned long addr; + unsigned int nr_pages; - vm = find_vm_area(objp); - if (!vm) + if (!spin_trylock(&vmap_area_lock)) return false; + va = __find_vmap_area((unsigned long)objp, &vmap_area_root); + if (!va) { + spin_unlock(&vmap_area_lock); + return false; + } + + vm = va->vm; + if (!vm) { + spin_unlock(&vmap_area_lock); + return false; + } + addr = (unsigned long)vm->addr; + caller = vm->caller; + nr_pages = vm->nr_pages; + spin_unlock(&vmap_area_lock); pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", - vm->nr_pages, (unsigned long)vm->addr, vm->caller); + nr_pages, addr, caller); return true; } #endif From fea9dd8653ff39ce383c54e747bde4c39289b4ad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Aug 2023 10:47:02 +0200 Subject: [PATCH 1208/2093] cpu/hotplug: Prevent self deadlock on CPU hot-unplug commit 2b8272ff4a70b866106ae13c36be7ecbef5d5da2 upstream. Xiongfeng reported and debugged a self deadlock of the task which initiates and controls a CPU hot-unplug operation vs. the CFS bandwidth timer. CPU1 CPU2 T1 sets cfs_quota starts hrtimer cfs_bandwidth 'period_timer' T1 is migrated to CPU2 T1 initiates offlining of CPU1 Hotplug operation starts ... 'period_timer' expires and is re-enqueued on CPU1 ... take_cpu_down() CPU1 shuts down and does not handle timers anymore. They have to be migrated in the post dead hotplug steps by the control task. T1 runs the post dead offline operation T1 is scheduled out T1 waits for 'period_timer' to expire T1 waits there forever if it is scheduled out before it can execute the hrtimer offline callback hrtimers_dead_cpu(). Cure this by delegating the hotplug control operation to a worker thread on an online CPU. This takes the initiating user space task, which might be affected by the bandwidth timer, completely out of the picture. Reported-by: Xiongfeng Wang Signed-off-by: Thomas Gleixner Tested-by: Yu Liao Acked-by: Vincent Guittot Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/8e785777-03aa-99e1-d20e-e956f5685be6@huawei.com Link: https://lore.kernel.org/r/87h6oqdq0i.ffs@tglx Signed-off-by: Greg Kroah-Hartman --- kernel/cpu.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 98a7a7b1471b..f8eb1825f704 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1215,8 +1215,22 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, return ret; } +struct cpu_down_work { + unsigned int cpu; + enum cpuhp_state target; +}; + +static long __cpu_down_maps_locked(void *arg) +{ + struct cpu_down_work *work = arg; + + return _cpu_down(work->cpu, 0, work->target); +} + static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { + struct cpu_down_work work = { .cpu = cpu, .target = target, }; + /* * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. @@ -1225,7 +1239,15 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; - return _cpu_down(cpu, 0, target); + + /* + * Ensure that the control task does not run on the to be offlined + * CPU to prevent a deadlock against cfs_b->period_timer. + */ + cpu = cpumask_any_but(cpu_online_mask, cpu); + if (cpu >= nr_cpu_ids) + return -EBUSY; + return work_on_cpu(cpu, __cpu_down_maps_locked, &work); } static int cpu_down(unsigned int cpu, enum cpuhp_state target) From ceedc62a3bc89f66af64320c6ceab8e9014746c6 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sat, 29 Jul 2023 20:59:25 +0200 Subject: [PATCH 1209/2093] media: i2c: ccs: Check rules is non-NULL commit 607bcc4213d998d051541d8f10b5bbb7d546c0be upstream. Fix the following smatch warning: drivers/media/i2c/ccs/ccs-data.c:524 ccs_data_parse_rules() warn: address of NULL pointer 'rules' The CCS static data rule parser does not check an if rule has been obtained before checking for other rule types (which depend on the if rule). In practice this means parsing invalid CCS static data could lead to dereferencing a NULL pointer. Reported-by: Hans Verkuil Fixes: a6b396f410b1 ("media: ccs: Add CCS static data parser library") Cc: stable@vger.kernel.org # for 5.11 and up Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/ccs/ccs-data.c | 101 +++++++++++++++++-------------- 1 file changed, 56 insertions(+), 45 deletions(-) diff --git a/drivers/media/i2c/ccs/ccs-data.c b/drivers/media/i2c/ccs/ccs-data.c index 45f2b2f55ec5..08400edf77ce 100644 --- a/drivers/media/i2c/ccs/ccs-data.c +++ b/drivers/media/i2c/ccs/ccs-data.c @@ -464,8 +464,7 @@ static int ccs_data_parse_rules(struct bin_container *bin, rule_payload = __rule_type + 1; rule_plen2 = rule_plen - sizeof(*__rule_type); - switch (*__rule_type) { - case CCS_DATA_BLOCK_RULE_ID_IF: { + if (*__rule_type == CCS_DATA_BLOCK_RULE_ID_IF) { const struct __ccs_data_block_rule_if *__if_rules = rule_payload; const size_t __num_if_rules = @@ -514,49 +513,61 @@ static int ccs_data_parse_rules(struct bin_container *bin, rules->if_rules = if_rule; rules->num_if_rules = __num_if_rules; } - break; - } - case CCS_DATA_BLOCK_RULE_ID_READ_ONLY_REGS: - rval = ccs_data_parse_reg_rules(bin, &rules->read_only_regs, - &rules->num_read_only_regs, - rule_payload, - rule_payload + rule_plen2, - dev); - if (rval) - return rval; - break; - case CCS_DATA_BLOCK_RULE_ID_FFD: - rval = ccs_data_parse_ffd(bin, &rules->frame_format, - rule_payload, - rule_payload + rule_plen2, - dev); - if (rval) - return rval; - break; - case CCS_DATA_BLOCK_RULE_ID_MSR: - rval = ccs_data_parse_reg_rules(bin, - &rules->manufacturer_regs, - &rules->num_manufacturer_regs, - rule_payload, - rule_payload + rule_plen2, - dev); - if (rval) - return rval; - break; - case CCS_DATA_BLOCK_RULE_ID_PDAF_READOUT: - rval = ccs_data_parse_pdaf_readout(bin, - &rules->pdaf_readout, - rule_payload, - rule_payload + rule_plen2, - dev); - if (rval) - return rval; - break; - default: - dev_dbg(dev, - "Don't know how to handle rule type %u!\n", - *__rule_type); - return -EINVAL; + } else { + /* Check there was an if rule before any other rules */ + if (bin->base && !rules) + return -EINVAL; + + switch (*__rule_type) { + case CCS_DATA_BLOCK_RULE_ID_READ_ONLY_REGS: + rval = ccs_data_parse_reg_rules(bin, + rules ? + &rules->read_only_regs : NULL, + rules ? + &rules->num_read_only_regs : NULL, + rule_payload, + rule_payload + rule_plen2, + dev); + if (rval) + return rval; + break; + case CCS_DATA_BLOCK_RULE_ID_FFD: + rval = ccs_data_parse_ffd(bin, rules ? + &rules->frame_format : NULL, + rule_payload, + rule_payload + rule_plen2, + dev); + if (rval) + return rval; + break; + case CCS_DATA_BLOCK_RULE_ID_MSR: + rval = ccs_data_parse_reg_rules(bin, + rules ? + &rules->manufacturer_regs : NULL, + rules ? + &rules->num_manufacturer_regs : NULL, + rule_payload, + rule_payload + rule_plen2, + dev); + if (rval) + return rval; + break; + case CCS_DATA_BLOCK_RULE_ID_PDAF_READOUT: + rval = ccs_data_parse_pdaf_readout(bin, + rules ? + &rules->pdaf_readout : NULL, + rule_payload, + rule_payload + rule_plen2, + dev); + if (rval) + return rval; + break; + default: + dev_dbg(dev, + "Don't know how to handle rule type %u!\n", + *__rule_type); + return -EINVAL; + } } __next_rule = __next_rule + rule_hlen + rule_plen; } From 823f52daef12ff44b549f5f38af2f896512b380e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 15 Jun 2023 10:29:07 +0200 Subject: [PATCH 1210/2093] media: i2c: Add a camera sensor top level menu commit 7d3c7d2a2914e10bec3b9cdacdadb8e1f65f715a upstream. Select V4L2_FWNODE and VIDEO_V4L2_SUBDEV_API for all sensor drivers. This also adds the options to drivers that don't specifically need them, these are still seldom used drivers using old APIs. The upside is that these should now all compile --- many drivers have had missing dependencies. The "menu" is replaced by selectable "menuconfig" to select the needed V4L2_FWNODE and VIDEO_V4L2_SUBDEV_API options. Also select MEDIA_CONTROLLER which VIDEO_V4L2_SUBDEV_API effectively depends on, and add the I2C dependency to the menu. Reported-by: Hans de Goede Signed-off-by: Sakari Ailus Reviewed-by: Hans de Goede Reviewed-by: Laurent Pinchart Cc: stable@vger.kernel.org # for >= 6.1 Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/Kconfig | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index 7806d4b81716..a34afb5217eb 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -25,8 +25,15 @@ config VIDEO_IR_I2C # V4L2 I2C drivers that are related with Camera support # -menu "Camera sensor devices" - visible if MEDIA_CAMERA_SUPPORT +menuconfig VIDEO_CAMERA_SENSOR + bool "Camera sensor devices" + depends on MEDIA_CAMERA_SUPPORT && I2C + select MEDIA_CONTROLLER + select V4L2_FWNODE + select VIDEO_V4L2_SUBDEV_API + default y + +if VIDEO_CAMERA_SENSOR config VIDEO_APTINA_PLL tristate @@ -783,7 +790,7 @@ source "drivers/media/i2c/ccs/Kconfig" source "drivers/media/i2c/et8ek8/Kconfig" source "drivers/media/i2c/m5mols/Kconfig" -endmenu +endif menu "Lens drivers" visible if MEDIA_CAMERA_SUPPORT From dafe7acfedfb453b757603f9dc4922645fd40dfd Mon Sep 17 00:00:00 2001 From: Rick Wertenbroek Date: Mon, 3 Jul 2023 10:58:45 +0200 Subject: [PATCH 1211/2093] PCI: rockchip: Use 64-bit mask on MSI 64-bit PCI address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit cdb50033dd6dfcf02ae3d4ee56bc1a9555be6d36 upstream. A 32-bit mask was used on the 64-bit PCI address used for mapping MSIs. This would result in the upper 32 bits being unintentionally zeroed and MSIs getting mapped to incorrect PCI addresses if the address had any of the upper bits set. Replace 32-bit mask by appropriate 64-bit mask. [kwilczynski: use GENMASK_ULL() over GENMASK() for 32-bit compatibility] Fixes: dc73ed0f1b8b ("PCI: rockchip: Fix window mapping and address translation for endpoint") Closes: https://lore.kernel.org/linux-pci/8d19e5b7-8fa0-44a4-90e2-9bb06f5eb694@moroto.mountain Link: https://lore.kernel.org/linux-pci/20230703085845.2052008-1-rick.wertenbroek@gmail.com Reported-by: Dan Carpenter Signed-off-by: Rick Wertenbroek Signed-off-by: Krzysztof Wilczyński Reviewed-by: Damien Le Moal Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index fe0333778fd9..6111de35f84c 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -158,7 +158,9 @@ #define PCIE_RC_CONFIG_THP_CAP (PCIE_RC_CONFIG_BASE + 0x274) #define PCIE_RC_CONFIG_THP_CAP_NEXT_MASK GENMASK(31, 20) -#define PCIE_ADDR_MASK 0xffffff00 +#define MAX_AXI_IB_ROOTPORT_REGION_NUM 3 +#define MIN_AXI_ADDR_BITS_PASSED 8 +#define PCIE_ADDR_MASK GENMASK_ULL(63, MIN_AXI_ADDR_BITS_PASSED) #define PCIE_CORE_AXI_CONF_BASE 0xc00000 #define PCIE_CORE_OB_REGION_ADDR0 (PCIE_CORE_AXI_CONF_BASE + 0x0) #define PCIE_CORE_OB_REGION_ADDR0_NUM_BITS 0x3f @@ -185,8 +187,6 @@ #define AXI_WRAPPER_TYPE1_CFG 0xb #define AXI_WRAPPER_NOR_MSG 0xc -#define MAX_AXI_IB_ROOTPORT_REGION_NUM 3 -#define MIN_AXI_ADDR_BITS_PASSED 8 #define PCIE_RC_SEND_PME_OFF 0x11960 #define ROCKCHIP_VENDOR_ID 0x1d87 #define PCIE_LINK_IS_L2(x) \ From 09cb2a71b2e982015fe0464f28da1ab42b8e6375 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Thu, 29 Jun 2023 20:33:28 +0800 Subject: [PATCH 1212/2093] ipmi_si: fix a memleak in try_smi_init() commit 6cf1a126de2992b4efe1c3c4d398f8de4aed6e3f upstream. Kmemleak reported the following leak info in try_smi_init(): unreferenced object 0xffff00018ecf9400 (size 1024): comm "modprobe", pid 2707763, jiffies 4300851415 (age 773.308s) backtrace: [<000000004ca5b312>] __kmalloc+0x4b8/0x7b0 [<00000000953b1072>] try_smi_init+0x148/0x5dc [ipmi_si] [<000000006460d325>] 0xffff800081b10148 [<0000000039206ea5>] do_one_initcall+0x64/0x2a4 [<00000000601399ce>] do_init_module+0x50/0x300 [<000000003c12ba3c>] load_module+0x7a8/0x9e0 [<00000000c246fffe>] __se_sys_init_module+0x104/0x180 [<00000000eea99093>] __arm64_sys_init_module+0x24/0x30 [<0000000021b1ef87>] el0_svc_common.constprop.0+0x94/0x250 [<0000000070f4f8b7>] do_el0_svc+0x48/0xe0 [<000000005a05337f>] el0_svc+0x24/0x3c [<000000005eb248d6>] el0_sync_handler+0x160/0x164 [<0000000030a59039>] el0_sync+0x160/0x180 The problem was that when an error occurred before handlers registration and after allocating `new_smi->si_sm`, the variable wouldn't be freed in the error handling afterwards since `shutdown_smi()` hadn't been registered yet. Fix it by adding a `kfree()` in the error handling path in `try_smi_init()`. Cc: stable@vger.kernel.org # 4.19+ Fixes: 7960f18a5647 ("ipmi_si: Convert over to a shutdown handler") Signed-off-by: Yi Yang Co-developed-by: GONG, Ruiqi Signed-off-by: GONG, Ruiqi Message-Id: <20230629123328.2402075-1-gongruiqi@huaweicloud.com> Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_si_intf.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index abddd7e43a9a..5cd031f3fc97 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2082,6 +2082,11 @@ static int try_smi_init(struct smi_info *new_smi) new_smi->io.io_cleanup = NULL; } + if (rv && new_smi->si_sm) { + kfree(new_smi->si_sm); + new_smi->si_sm = NULL; + } + return rv; } From 7a7f11283392311741a5399672fd2657c7c6ff01 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 7 Jun 2023 22:12:11 -0600 Subject: [PATCH 1213/2093] ARM: OMAP2+: Fix -Warray-bounds warning in _pwrdm_state_switch() commit 847fb80cc01a54bc827b02547bb8743bdb59ddab upstream. If function pwrdm_read_prev_pwrst() returns -EINVAL, we will end up accessing array pwrdm->state_counter through negative index -22. This is wrong and the compiler is legitimately warning us about this potential problem. Fix this by sanity checking the value stored in variable _prev_ before accessing array pwrdm->state_counter. Address the following -Warray-bounds warning: arch/arm/mach-omap2/powerdomain.c:178:45: warning: array subscript -22 is below array bounds of 'unsigned int[4]' [-Warray-bounds] Link: https://github.com/KSPP/linux/issues/307 Fixes: ba20bb126940 ("OMAP: PM counter infrastructure.") Cc: stable@vger.kernel.org Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/20230607050639.LzbPn%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva Message-ID: Acked-by: Ard Biesheuvel Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap2/powerdomain.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c index 2d747f6cffe8..0eca44fc1192 100644 --- a/arch/arm/mach-omap2/powerdomain.c +++ b/arch/arm/mach-omap2/powerdomain.c @@ -174,7 +174,7 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag) break; case PWRDM_STATE_PREV: prev = pwrdm_read_prev_pwrst(pwrdm); - if (pwrdm->state != prev) + if (prev >= 0 && pwrdm->state != prev) pwrdm->state_counter[prev]++; if (prev == PWRDM_POWER_RET) _update_logic_membank_counters(pwrdm); From 4a3e0d51c3e10ef699fc201542593f4bbcd39fd3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 26 Jul 2023 22:58:17 -0400 Subject: [PATCH 1214/2093] XArray: Do not return sibling entries from xa_load() commit cbc02854331edc6dc22d8b77b6e22e38ebc7dd51 upstream. It is possible for xa_load() to observe a sibling entry pointing to another sibling entry. An example: Thread A: Thread B: xa_store_range(xa, entry, 188, 191, gfp); xa_load(xa, 191); entry = xa_entry(xa, node, 63); [entry is a sibling of 188] xa_store_range(xa, entry, 184, 191, gfp); if (xa_is_sibling(entry)) offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); [entry is now a sibling of 184] It is sufficient to go around this loop until we hit a non-sibling entry. Sibling entries always point earlier in the node, so we are guaranteed to terminate this search. Signed-off-by: Matthew Wilcox (Oracle) Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- lib/xarray.c | 2 +- tools/testing/radix-tree/multiorder.c | 68 ++++++++++++++++++++++++++- 2 files changed, 67 insertions(+), 3 deletions(-) diff --git a/lib/xarray.c b/lib/xarray.c index ea9ce1f0b386..e9bd29826e8b 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -204,7 +204,7 @@ static void *xas_descend(struct xa_state *xas, struct xa_node *node) void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; - if (xa_is_sibling(entry)) { + while (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index e00520cc6349..cffaf2245d4f 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -159,7 +159,7 @@ void multiorder_tagged_iteration(struct xarray *xa) item_kill_tree(xa); } -bool stop_iteration = false; +bool stop_iteration; static void *creator_func(void *ptr) { @@ -201,6 +201,7 @@ static void multiorder_iteration_race(struct xarray *xa) pthread_t worker_thread[num_threads]; int i; + stop_iteration = false; pthread_create(&worker_thread[0], NULL, &creator_func, xa); for (i = 1; i < num_threads; i++) pthread_create(&worker_thread[i], NULL, &iterator_func, xa); @@ -211,6 +212,61 @@ static void multiorder_iteration_race(struct xarray *xa) item_kill_tree(xa); } +static void *load_creator(void *ptr) +{ + /* 'order' is set up to ensure we have sibling entries */ + unsigned int order; + struct radix_tree_root *tree = ptr; + int i; + + rcu_register_thread(); + item_insert_order(tree, 3 << RADIX_TREE_MAP_SHIFT, 0); + item_insert_order(tree, 2 << RADIX_TREE_MAP_SHIFT, 0); + for (i = 0; i < 10000; i++) { + for (order = 1; order < RADIX_TREE_MAP_SHIFT; order++) { + unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - + (1 << order); + item_insert_order(tree, index, order); + item_delete_rcu(tree, index); + } + } + rcu_unregister_thread(); + + stop_iteration = true; + return NULL; +} + +static void *load_worker(void *ptr) +{ + unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - 1; + + rcu_register_thread(); + while (!stop_iteration) { + struct item *item = xa_load(ptr, index); + assert(!xa_is_internal(item)); + } + rcu_unregister_thread(); + + return NULL; +} + +static void load_race(struct xarray *xa) +{ + const int num_threads = sysconf(_SC_NPROCESSORS_ONLN) * 4; + pthread_t worker_thread[num_threads]; + int i; + + stop_iteration = false; + pthread_create(&worker_thread[0], NULL, &load_creator, xa); + for (i = 1; i < num_threads; i++) + pthread_create(&worker_thread[i], NULL, &load_worker, xa); + + for (i = 0; i < num_threads; i++) + pthread_join(worker_thread[i], NULL); + + item_kill_tree(xa); +} + static DEFINE_XARRAY(array); void multiorder_checks(void) @@ -218,12 +274,20 @@ void multiorder_checks(void) multiorder_iteration(&array); multiorder_tagged_iteration(&array); multiorder_iteration_race(&array); + load_race(&array); radix_tree_cpu_dead(0); } -int __weak main(void) +int __weak main(int argc, char **argv) { + int opt; + + while ((opt = getopt(argc, argv, "ls:v")) != -1) { + if (opt == 'v') + test_verbose++; + } + rcu_register_thread(); radix_tree_init(); multiorder_checks(); From 8fa9cb58445d6787e46b53dedcf69a1aef8967bb Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 9 Aug 2023 16:20:21 +0100 Subject: [PATCH 1215/2093] io_uring: break iopolling on signal commit dc314886cb3d0e4ab2858003e8de2917f8a3ccbd upstream. Don't keep spinning iopoll with a signal set. It'll eventually return back, e.g. by virtue of need_resched(), but it's not a nice user experience. Cc: stable@vger.kernel.org Fixes: def596e9557c9 ("io_uring: support for IO polling") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/eeba551e82cad12af30c3220125eb6cb244cc94c.1691594339.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index e15abe26a0e6..6d455e2428b9 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1457,6 +1457,9 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) break; nr_events += ret; ret = 0; + + if (task_sigpending(current)) + return -EINTR; } while (nr_events < min && !need_resched()); return ret; From b4ab337aad0997c7961a45e3a853b9c6fe3828d2 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 13 Jun 2023 13:06:38 +0200 Subject: [PATCH 1216/2093] backlight/gpio_backlight: Compare against struct fb_info.device commit 7b91d017f77c1bda56f27c2f4bbb70de7c6eca08 upstream. Struct gpio_backlight_platform_data refers to a platform device within the Linux device hierarchy. The test in gpio_backlight_check_fb() compares it against the fbdev device in struct fb_info.dev, which is different. Fix the test by comparing to struct fb_info.device. Fixes a bug in the backlight driver and prepares fbdev for making struct fb_info.dev optional. v2: * move renames into separate patch (Javier, Sam, Michael) Signed-off-by: Thomas Zimmermann Fixes: 8b770e3c9824 ("backlight: Add GPIO-based backlight driver") Cc: Laurent Pinchart Cc: Rich Felker Cc: John Paul Adrian Glaubitz Cc: Lee Jones Cc: Daniel Thompson Cc: Jingoo Han Cc: linux-sh@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: # v3.12+ Reviewed-by: Sam Ravnborg Reviewed-by: Daniel Thompson Link: https://patchwork.freedesktop.org/patch/msgid/20230613110953.24176-4-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/video/backlight/gpio_backlight.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c index 6f78d928f054..5c5c99f7979e 100644 --- a/drivers/video/backlight/gpio_backlight.c +++ b/drivers/video/backlight/gpio_backlight.c @@ -35,7 +35,7 @@ static int gpio_backlight_check_fb(struct backlight_device *bl, { struct gpio_backlight *gbl = bl_get_data(bl); - return gbl->fbdev == NULL || gbl->fbdev == info->dev; + return gbl->fbdev == NULL || gbl->fbdev == info->device; } static const struct backlight_ops gpio_backlight_ops = { From 83166d03a5b7bfc4c989924e1d3648379bd738a8 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 13 Jun 2023 13:06:36 +0200 Subject: [PATCH 1217/2093] backlight/bd6107: Compare against struct fb_info.device commit 992bdddaabfba19bdc77c1c7a4977b2aa41ec891 upstream. Struct bd6107_platform_data refers to a platform device within the Linux device hierarchy. The test in bd6107_backlight_check_fb() compares it against the fbdev device in struct fb_info.dev, which is different. Fix the test by comparing to struct fb_info.device. Fixes a bug in the backlight driver and prepares fbdev for making struct fb_info.dev optional. v2: * move renames into separate patch (Javier, Sam, Michael) Fixes: 67b43e590415 ("backlight: Add ROHM BD6107 backlight driver") Signed-off-by: Thomas Zimmermann Cc: Laurent Pinchart Cc: Lee Jones Cc: Daniel Thompson Cc: Jingoo Han Cc: dri-devel@lists.freedesktop.org Cc: # v3.12+ Reviewed-by: Javier Martinez Canillas Reviewed-by: Sam Ravnborg Reviewed-by: Daniel Thompson Link: https://patchwork.freedesktop.org/patch/msgid/20230613110953.24176-2-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/video/backlight/bd6107.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/bd6107.c b/drivers/video/backlight/bd6107.c index a506872d4396..94fe628dd88c 100644 --- a/drivers/video/backlight/bd6107.c +++ b/drivers/video/backlight/bd6107.c @@ -104,7 +104,7 @@ static int bd6107_backlight_check_fb(struct backlight_device *backlight, { struct bd6107 *bd = bl_get_data(backlight); - return bd->pdata->fbdev == NULL || bd->pdata->fbdev == info->dev; + return bd->pdata->fbdev == NULL || bd->pdata->fbdev == info->device; } static const struct backlight_ops bd6107_backlight_ops = { From 47636d32a0eebb45af8df30c93068df0e67f8d66 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 13 Jun 2023 13:06:40 +0200 Subject: [PATCH 1218/2093] backlight/lv5207lp: Compare against struct fb_info.device commit 1ca8819320fd84e7d95b04e7668efc5f9fe9fa5c upstream. Struct lv5207lp_platform_data refers to a platform device within the Linux device hierarchy. The test in lv5207lp_backlight_check_fb() compares it against the fbdev device in struct fb_info.dev, which is different. Fix the test by comparing to struct fb_info.device. Fixes a bug in the backlight driver and prepares fbdev for making struct fb_info.dev optional. v2: * move renames into separate patch (Javier, Sam, Michael) Fixes: 82e5c40d88f9 ("backlight: Add Sanyo LV5207LP backlight driver") Signed-off-by: Thomas Zimmermann Cc: Laurent Pinchart Cc: Yoshinori Sato Cc: Rich Felker Cc: John Paul Adrian Glaubitz Cc: Lee Jones Cc: Daniel Thompson Cc: Jingoo Han Cc: linux-sh@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: # v3.12+ Reviewed-by: Javier Martinez Canillas Reviewed-by: Sam Ravnborg Reviewed-by: Daniel Thompson Link: https://patchwork.freedesktop.org/patch/msgid/20230613110953.24176-6-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/video/backlight/lv5207lp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/lv5207lp.c b/drivers/video/backlight/lv5207lp.c index 767b800d79fa..8a027a5ea552 100644 --- a/drivers/video/backlight/lv5207lp.c +++ b/drivers/video/backlight/lv5207lp.c @@ -67,7 +67,7 @@ static int lv5207lp_backlight_check_fb(struct backlight_device *backlight, { struct lv5207lp *lv = bl_get_data(backlight); - return lv->pdata->fbdev == NULL || lv->pdata->fbdev == info->dev; + return lv->pdata->fbdev == NULL || lv->pdata->fbdev == info->device; } static const struct backlight_ops lv5207lp_backlight_ops = { From 9a9b8596c3dce99a0bac3951ed257e87f30d0445 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Tue, 22 Aug 2023 12:31:09 -0400 Subject: [PATCH 1219/2093] drm/amd/display: register edp_backlight_control() for DCN301 commit 1611917f39bee1abfc01501238db8ac19649042d upstream. As made mention of in commit 099303e9a9bd ("drm/amd/display: eDP intermittent black screen during PnP"), we need to turn off the display's backlight before powering off an eDP display. Not doing so will result in undefined behaviour according to the eDP spec. So, set DCN301's edp_backlight_control() function pointer to dce110_edp_backlight_control(). Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2765 Fixes: 9c75891feef0 ("drm/amd/display: rework recent update PHY state commit") Suggested-by: Swapnil Patel Reviewed-by: Harry Wentland Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c index 6192851c59ed..51265a812bdc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c @@ -75,6 +75,7 @@ static const struct hw_sequencer_funcs dcn301_funcs = { .get_hw_state = dcn10_get_hw_state, .clear_status_bits = dcn10_clear_status_bits, .wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect, + .edp_backlight_control = dce110_edp_backlight_control, .edp_power_control = dce110_edp_power_control, .edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready, .set_cursor_position = dcn10_set_cursor_position, From 5a8b2c1665ca1ff8d9d04eef01eed1b9fddba00b Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 24 Jul 2023 00:58:24 -0700 Subject: [PATCH 1220/2093] xtensa: PMU: fix base address for the newer hardware commit 687eb3c42f4ad81e7c947c50e2d865f692064291 upstream. With introduction of ERI access control in RG.0 base address of the PMU unit registers has changed. Add support for the new PMU configuration. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov Signed-off-by: Greg Kroah-Hartman --- arch/xtensa/include/asm/core.h | 9 +++++++++ arch/xtensa/kernel/perf_event.c | 17 +++++++++++++---- 2 files changed, 22 insertions(+), 4 deletions(-) diff --git a/arch/xtensa/include/asm/core.h b/arch/xtensa/include/asm/core.h index f856d2bcb9f3..7cef85ad9741 100644 --- a/arch/xtensa/include/asm/core.h +++ b/arch/xtensa/include/asm/core.h @@ -44,4 +44,13 @@ #define XTENSA_STACK_ALIGNMENT 16 #endif +#ifndef XCHAL_HW_MIN_VERSION +#if defined(XCHAL_HW_MIN_VERSION_MAJOR) && defined(XCHAL_HW_MIN_VERSION_MINOR) +#define XCHAL_HW_MIN_VERSION (XCHAL_HW_MIN_VERSION_MAJOR * 100 + \ + XCHAL_HW_MIN_VERSION_MINOR) +#else +#define XCHAL_HW_MIN_VERSION 0 +#endif +#endif + #endif diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c index a0d05c8598d0..183618090d05 100644 --- a/arch/xtensa/kernel/perf_event.c +++ b/arch/xtensa/kernel/perf_event.c @@ -13,17 +13,26 @@ #include #include +#include #include #include +#define XTENSA_HWVERSION_RG_2015_0 260000 + +#if XCHAL_HW_MIN_VERSION >= XTENSA_HWVERSION_RG_2015_0 +#define XTENSA_PMU_ERI_BASE 0x00101000 +#else +#define XTENSA_PMU_ERI_BASE 0x00001000 +#endif + /* Global control/status for all perf counters */ -#define XTENSA_PMU_PMG 0x1000 +#define XTENSA_PMU_PMG XTENSA_PMU_ERI_BASE /* Perf counter values */ -#define XTENSA_PMU_PM(i) (0x1080 + (i) * 4) +#define XTENSA_PMU_PM(i) (XTENSA_PMU_ERI_BASE + 0x80 + (i) * 4) /* Perf counter control registers */ -#define XTENSA_PMU_PMCTRL(i) (0x1100 + (i) * 4) +#define XTENSA_PMU_PMCTRL(i) (XTENSA_PMU_ERI_BASE + 0x100 + (i) * 4) /* Perf counter status registers */ -#define XTENSA_PMU_PMSTAT(i) (0x1180 + (i) * 4) +#define XTENSA_PMU_PMSTAT(i) (XTENSA_PMU_ERI_BASE + 0x180 + (i) * 4) #define XTENSA_PMU_PMG_PMEN 0x1 From cc9bf2d62f196ec600f9e6ea3a6ced11f54a2df9 Mon Sep 17 00:00:00 2001 From: Hongchen Zhang Date: Wed, 6 Sep 2023 22:53:09 +0800 Subject: [PATCH 1221/2093] LoongArch: mm: Add p?d_leaf() definitions commit 303be4b33562a5b689261ced1616bf16ad49efa7 upstream. When I do LTP test, LTP test case ksm06 caused panic at break_ksm_pmd_entry -> pmd_leaf (Huge page table but False) -> pte_present (panic) The reason is pmd_leaf() is not defined, So like commit 501b81046701 ("mips: mm: add p?d_leaf() definitions") add p?d_leaf() definition for LoongArch. Fixes: 09cfefb7fa70 ("LoongArch: Add memory management") Cc: stable@vger.kernel.org Acked-by: David Hildenbrand Signed-off-by: Hongchen Zhang Signed-off-by: Huacai Chen Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/include/asm/pgtable.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index e748fad82f13..f991e678ca4b 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -560,6 +560,9 @@ static inline long pmd_protnone(pmd_t pmd) } #endif /* CONFIG_NUMA_BALANCING */ +#define pmd_leaf(pmd) ((pmd_val(pmd) & _PAGE_HUGE) != 0) +#define pud_leaf(pud) ((pud_val(pud) & _PAGE_HUGE) != 0) + /* * We provide our own get_unmapped area to cope with the virtual aliasing * constraints placed on us by the cache architecture. From ad661951a98f567b9d4b9b96dde381635a68b8de Mon Sep 17 00:00:00 2001 From: Frank Li Date: Thu, 31 Aug 2023 10:13:24 -0400 Subject: [PATCH 1222/2093] i3c: master: svc: fix probe failure when no i3c device exist commit 6e13d6528be2f7e801af63c8153b87293f25d736 upstream. I3C masters are expected to support hot-join. This means at initialization time we might not yet discover any device and this should not be treated as a fatal error. During the DAA procedure which happens at probe time, if no device has joined, all CCC will be NACKed (from a bus perspective). This leads to an early return with an error code which fails the probe of the master. Let's avoid this by just telling the core through an I3C_ERROR_M2 return command code that no device was discovered, which is a valid situation. This way the master will no longer bail out and fail to probe for a wrong reason. Cc: stable@vger.kernel.org Fixes: dd3c52846d59 ("i3c: master: svc: Add Silvaco I3C master driver") Signed-off-by: Frank Li Acked-by: Miquel Raynal Link: https://lore.kernel.org/r/20230831141324.2841525-1-Frank.Li@nxp.com Signed-off-by: Alexandre Belloni Signed-off-by: Greg Kroah-Hartman --- drivers/i3c/master/svc-i3c-master.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index d47360f8a1f3..4eebf15f685a 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -782,6 +782,10 @@ static int svc_i3c_master_do_daa_locked(struct svc_i3c_master *master, */ break; } else if (SVC_I3C_MSTATUS_NACKED(reg)) { + /* No I3C devices attached */ + if (dev_nb == 0) + break; + /* * A slave device nacked the address, this is * allowed only once, DAA will be stopped and @@ -1251,11 +1255,17 @@ static int svc_i3c_master_send_ccc_cmd(struct i3c_master_controller *m, { struct svc_i3c_master *master = to_svc_i3c_master(m); bool broadcast = cmd->id < 0x80; + int ret; if (broadcast) - return svc_i3c_master_send_bdcast_ccc_cmd(master, cmd); + ret = svc_i3c_master_send_bdcast_ccc_cmd(master, cmd); else - return svc_i3c_master_send_direct_ccc_cmd(master, cmd); + ret = svc_i3c_master_send_direct_ccc_cmd(master, cmd); + + if (ret) + cmd->err = I3C_ERROR_M2; + + return ret; } static int svc_i3c_master_priv_xfers(struct i3c_dev_desc *dev, From ba0b46166b8e547024d02345a68b747841931ad2 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 7 Sep 2023 09:54:11 +0100 Subject: [PATCH 1223/2093] arm64: csum: Fix OoB access in IP checksum code for negative lengths commit 8bd795fedb8450ecbef18eeadbd23ed8fc7630f5 upstream. Although commit c2c24edb1d9c ("arm64: csum: Fix pathological zero-length calls") added an early return for zero-length input, syzkaller has popped up with an example of a _negative_ length which causes an undefined shift and an out-of-bounds read: | BUG: KASAN: slab-out-of-bounds in do_csum+0x44/0x254 arch/arm64/lib/csum.c:39 | Read of size 4294966928 at addr ffff0000d7ac0170 by task syz-executor412/5975 | | CPU: 0 PID: 5975 Comm: syz-executor412 Not tainted 6.4.0-rc4-syzkaller-g908f31f2a05b #0 | Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 | Call trace: | dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:233 | show_stack+0x2c/0x44 arch/arm64/kernel/stacktrace.c:240 | __dump_stack lib/dump_stack.c:88 [inline] | dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 | print_address_description mm/kasan/report.c:351 [inline] | print_report+0x174/0x514 mm/kasan/report.c:462 | kasan_report+0xd4/0x130 mm/kasan/report.c:572 | kasan_check_range+0x264/0x2a4 mm/kasan/generic.c:187 | __kasan_check_read+0x20/0x30 mm/kasan/shadow.c:31 | do_csum+0x44/0x254 arch/arm64/lib/csum.c:39 | csum_partial+0x30/0x58 lib/checksum.c:128 | gso_make_checksum include/linux/skbuff.h:4928 [inline] | __udp_gso_segment+0xaf4/0x1bc4 net/ipv4/udp_offload.c:332 | udp6_ufo_fragment+0x540/0xca0 net/ipv6/udp_offload.c:47 | ipv6_gso_segment+0x5cc/0x1760 net/ipv6/ip6_offload.c:119 | skb_mac_gso_segment+0x2b4/0x5b0 net/core/gro.c:141 | __skb_gso_segment+0x250/0x3d0 net/core/dev.c:3401 | skb_gso_segment include/linux/netdevice.h:4859 [inline] | validate_xmit_skb+0x364/0xdbc net/core/dev.c:3659 | validate_xmit_skb_list+0x94/0x130 net/core/dev.c:3709 | sch_direct_xmit+0xe8/0x548 net/sched/sch_generic.c:327 | __dev_xmit_skb net/core/dev.c:3805 [inline] | __dev_queue_xmit+0x147c/0x3318 net/core/dev.c:4210 | dev_queue_xmit include/linux/netdevice.h:3085 [inline] | packet_xmit+0x6c/0x318 net/packet/af_packet.c:276 | packet_snd net/packet/af_packet.c:3081 [inline] | packet_sendmsg+0x376c/0x4c98 net/packet/af_packet.c:3113 | sock_sendmsg_nosec net/socket.c:724 [inline] | sock_sendmsg net/socket.c:747 [inline] | __sys_sendto+0x3b4/0x538 net/socket.c:2144 Extend the early return to reject negative lengths as well, aligning our implementation with the generic code in lib/checksum.c Cc: Robin Murphy Fixes: 5777eaed566a ("arm64: Implement optimised checksum routine") Reported-by: syzbot+4a9f9820bd8d302e22f7@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/000000000000e0e94c0603f8d213@google.com Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/lib/csum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c index 78b87a64ca0a..2432683e48a6 100644 --- a/arch/arm64/lib/csum.c +++ b/arch/arm64/lib/csum.c @@ -24,7 +24,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) const u64 *ptr; u64 data, sum64 = 0; - if (unlikely(len == 0)) + if (unlikely(len <= 0)) return 0; offset = (unsigned long)buff & 7; From fd4d61f85e7625cb21a7eff4efa1de46503ed2c3 Mon Sep 17 00:00:00 2001 From: Vitaly Rodionov Date: Mon, 4 Sep 2023 17:00:33 +0100 Subject: [PATCH 1224/2093] ALSA: hda/cirrus: Fix broken audio on hardware with two CS42L42 codecs. commit 99bf5b0baac941176a6a3d5cef7705b29808de34 upstream. Recently in v6.3-rc1 there was a change affecting behaviour of hrtimers (commit 0c52310f260014d95c1310364379772cb74cf82d) and causing few issues on platforms with two CS42L42 codecs. Canonical/Dell has reported an issue with Vostro-3910. We need to increase this value by 15ms. Link: https://bugs.launchpad.net/somerville/+bug/2031060 Fixes: 9fb9fa18fb50 ("ALSA: hda/cirrus: Add extra 10 ms delay to allow PLL settle and lock.") Signed-off-by: Vitaly Rodionov Link: https://lore.kernel.org/r/20230904160033.908135-1-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_cs8409.c | 2 +- sound/pci/hda/patch_cs8409.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 0ba1fbcbb21e..627899959ffe 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -888,7 +888,7 @@ static void cs42l42_resume(struct sub_codec *cs42l42) /* Initialize CS42L42 companion codec */ cs8409_i2c_bulk_write(cs42l42, cs42l42->init_seq, cs42l42->init_seq_num); - usleep_range(30000, 35000); + msleep(CS42L42_INIT_TIMEOUT_MS); /* Clear interrupts, by reading interrupt status registers */ cs8409_i2c_bulk_read(cs42l42, irq_regs, ARRAY_SIZE(irq_regs)); diff --git a/sound/pci/hda/patch_cs8409.h b/sound/pci/hda/patch_cs8409.h index 2a8dfb4ff046..937e9387abdc 100644 --- a/sound/pci/hda/patch_cs8409.h +++ b/sound/pci/hda/patch_cs8409.h @@ -229,6 +229,7 @@ enum cs8409_coefficient_index_registers { #define CS42L42_I2C_SLEEP_US (2000) #define CS42L42_PDN_TIMEOUT_US (250000) #define CS42L42_PDN_SLEEP_US (2000) +#define CS42L42_INIT_TIMEOUT_MS (45) #define CS42L42_FULL_SCALE_VOL_MASK (2) #define CS42L42_FULL_SCALE_VOL_0DB (1) #define CS42L42_FULL_SCALE_VOL_MINUS6DB (0) From 25934d8f6eb2ab7982a70661508392922fb8263d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 8 Sep 2023 10:20:36 +0100 Subject: [PATCH 1225/2093] media: dvb: symbol fixup for dvb_attach() commit 86495af1171e1feec79faa9b64c05c89f46e41d1 upstream. In commit 9011e49d54dc ("modules: only allow symbol_get of EXPORT_SYMBOL_GPL modules") the use of symbol_get is properly restricted to GPL-only marked symbols. This interacts oddly with the DVB logic which only uses dvb_attach() to load the dvb driver which then uses symbol_get(). Fix this up by properly marking all of the dvb_attach attach symbols as EXPORT_SYMBOL_GPL(). Fixes: 9011e49d54dc ("modules: only allow symbol_get of EXPORT_SYMBOL_GPL modules") Cc: stable Reported-by: Stefan Lippers-Hollmann Cc: Mauro Carvalho Chehab Cc: Christoph Hellwig Cc: linux-media@vger.kernel.org Cc: linux-modules@vger.kernel.org Acked-by: Luis Chamberlain Acked-by: Hans Verkuil Link: https://lore.kernel.org/r/20230908092035.3815268-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-frontends/ascot2e.c | 2 +- drivers/media/dvb-frontends/atbm8830.c | 2 +- drivers/media/dvb-frontends/au8522_dig.c | 2 +- drivers/media/dvb-frontends/bcm3510.c | 2 +- drivers/media/dvb-frontends/cx22700.c | 2 +- drivers/media/dvb-frontends/cx22702.c | 2 +- drivers/media/dvb-frontends/cx24110.c | 2 +- drivers/media/dvb-frontends/cx24113.c | 2 +- drivers/media/dvb-frontends/cx24116.c | 2 +- drivers/media/dvb-frontends/cx24120.c | 2 +- drivers/media/dvb-frontends/cx24123.c | 2 +- drivers/media/dvb-frontends/cxd2820r_core.c | 2 +- drivers/media/dvb-frontends/cxd2841er.c | 4 ++-- drivers/media/dvb-frontends/cxd2880/cxd2880_top.c | 2 +- drivers/media/dvb-frontends/dib0070.c | 2 +- drivers/media/dvb-frontends/dib0090.c | 4 ++-- drivers/media/dvb-frontends/dib3000mb.c | 2 +- drivers/media/dvb-frontends/dib3000mc.c | 2 +- drivers/media/dvb-frontends/dib7000m.c | 2 +- drivers/media/dvb-frontends/dib7000p.c | 2 +- drivers/media/dvb-frontends/dib8000.c | 2 +- drivers/media/dvb-frontends/dib9000.c | 2 +- drivers/media/dvb-frontends/drx39xyj/drxj.c | 2 +- drivers/media/dvb-frontends/drxd_hard.c | 2 +- drivers/media/dvb-frontends/drxk_hard.c | 2 +- drivers/media/dvb-frontends/ds3000.c | 2 +- drivers/media/dvb-frontends/dvb-pll.c | 2 +- drivers/media/dvb-frontends/ec100.c | 2 +- drivers/media/dvb-frontends/helene.c | 4 ++-- drivers/media/dvb-frontends/horus3a.c | 2 +- drivers/media/dvb-frontends/isl6405.c | 2 +- drivers/media/dvb-frontends/isl6421.c | 2 +- drivers/media/dvb-frontends/isl6423.c | 2 +- drivers/media/dvb-frontends/itd1000.c | 2 +- drivers/media/dvb-frontends/ix2505v.c | 2 +- drivers/media/dvb-frontends/l64781.c | 2 +- drivers/media/dvb-frontends/lg2160.c | 2 +- drivers/media/dvb-frontends/lgdt3305.c | 2 +- drivers/media/dvb-frontends/lgdt3306a.c | 2 +- drivers/media/dvb-frontends/lgdt330x.c | 2 +- drivers/media/dvb-frontends/lgs8gxx.c | 2 +- drivers/media/dvb-frontends/lnbh25.c | 2 +- drivers/media/dvb-frontends/lnbp21.c | 4 ++-- drivers/media/dvb-frontends/lnbp22.c | 2 +- drivers/media/dvb-frontends/m88ds3103.c | 2 +- drivers/media/dvb-frontends/m88rs2000.c | 2 +- drivers/media/dvb-frontends/mb86a16.c | 2 +- drivers/media/dvb-frontends/mb86a20s.c | 2 +- drivers/media/dvb-frontends/mt312.c | 2 +- drivers/media/dvb-frontends/mt352.c | 2 +- drivers/media/dvb-frontends/nxt200x.c | 2 +- drivers/media/dvb-frontends/nxt6000.c | 2 +- drivers/media/dvb-frontends/or51132.c | 2 +- drivers/media/dvb-frontends/or51211.c | 2 +- drivers/media/dvb-frontends/s5h1409.c | 2 +- drivers/media/dvb-frontends/s5h1411.c | 2 +- drivers/media/dvb-frontends/s5h1420.c | 2 +- drivers/media/dvb-frontends/s5h1432.c | 2 +- drivers/media/dvb-frontends/s921.c | 2 +- drivers/media/dvb-frontends/si21xx.c | 2 +- drivers/media/dvb-frontends/sp887x.c | 2 +- drivers/media/dvb-frontends/stb0899_drv.c | 2 +- drivers/media/dvb-frontends/stb6000.c | 2 +- drivers/media/dvb-frontends/stb6100.c | 2 +- drivers/media/dvb-frontends/stv0288.c | 2 +- drivers/media/dvb-frontends/stv0297.c | 2 +- drivers/media/dvb-frontends/stv0299.c | 2 +- drivers/media/dvb-frontends/stv0367.c | 6 +++--- drivers/media/dvb-frontends/stv0900_core.c | 2 +- drivers/media/dvb-frontends/stv090x.c | 2 +- drivers/media/dvb-frontends/stv6110.c | 2 +- drivers/media/dvb-frontends/stv6110x.c | 2 +- drivers/media/dvb-frontends/tda10021.c | 2 +- drivers/media/dvb-frontends/tda10023.c | 2 +- drivers/media/dvb-frontends/tda10048.c | 2 +- drivers/media/dvb-frontends/tda1004x.c | 4 ++-- drivers/media/dvb-frontends/tda10086.c | 2 +- drivers/media/dvb-frontends/tda665x.c | 2 +- drivers/media/dvb-frontends/tda8083.c | 2 +- drivers/media/dvb-frontends/tda8261.c | 2 +- drivers/media/dvb-frontends/tda826x.c | 2 +- drivers/media/dvb-frontends/ts2020.c | 2 +- drivers/media/dvb-frontends/tua6100.c | 2 +- drivers/media/dvb-frontends/ves1820.c | 2 +- drivers/media/dvb-frontends/ves1x93.c | 2 +- drivers/media/dvb-frontends/zl10036.c | 2 +- drivers/media/dvb-frontends/zl10039.c | 2 +- drivers/media/dvb-frontends/zl10353.c | 2 +- drivers/media/pci/bt8xx/dst.c | 2 +- drivers/media/pci/bt8xx/dst_ca.c | 2 +- drivers/media/pci/ddbridge/ddbridge-dummy-fe.c | 2 +- drivers/media/tuners/fc0011.c | 2 +- drivers/media/tuners/fc0012.c | 2 +- drivers/media/tuners/fc0013.c | 2 +- drivers/media/tuners/max2165.c | 2 +- drivers/media/tuners/mc44s803.c | 2 +- drivers/media/tuners/mt2060.c | 2 +- drivers/media/tuners/mt2131.c | 2 +- drivers/media/tuners/mt2266.c | 2 +- drivers/media/tuners/mxl5005s.c | 2 +- drivers/media/tuners/qt1010.c | 2 +- drivers/media/tuners/tda18218.c | 2 +- drivers/media/tuners/xc2028.c | 2 +- drivers/media/tuners/xc4000.c | 2 +- drivers/media/tuners/xc5000.c | 2 +- 105 files changed, 112 insertions(+), 112 deletions(-) diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c index 9b00b56230b6..cf8e5f1bd101 100644 --- a/drivers/media/dvb-frontends/ascot2e.c +++ b/drivers/media/dvb-frontends/ascot2e.c @@ -533,7 +533,7 @@ struct dvb_frontend *ascot2e_attach(struct dvb_frontend *fe, priv->i2c_address, priv->i2c); return fe; } -EXPORT_SYMBOL(ascot2e_attach); +EXPORT_SYMBOL_GPL(ascot2e_attach); MODULE_DESCRIPTION("Sony ASCOT2E terr/cab tuner driver"); MODULE_AUTHOR("info@netup.ru"); diff --git a/drivers/media/dvb-frontends/atbm8830.c b/drivers/media/dvb-frontends/atbm8830.c index bdd16b9c5824..778c865085bf 100644 --- a/drivers/media/dvb-frontends/atbm8830.c +++ b/drivers/media/dvb-frontends/atbm8830.c @@ -489,7 +489,7 @@ struct dvb_frontend *atbm8830_attach(const struct atbm8830_config *config, return NULL; } -EXPORT_SYMBOL(atbm8830_attach); +EXPORT_SYMBOL_GPL(atbm8830_attach); MODULE_DESCRIPTION("AltoBeam ATBM8830/8831 GB20600 demodulator driver"); MODULE_AUTHOR("David T. L. Wong "); diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c index 78cafdf27961..230436bf6cbd 100644 --- a/drivers/media/dvb-frontends/au8522_dig.c +++ b/drivers/media/dvb-frontends/au8522_dig.c @@ -879,7 +879,7 @@ struct dvb_frontend *au8522_attach(const struct au8522_config *config, au8522_release_state(state); return NULL; } -EXPORT_SYMBOL(au8522_attach); +EXPORT_SYMBOL_GPL(au8522_attach); static const struct dvb_frontend_ops au8522_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c index 68b92b4419cf..b3f5c49accaf 100644 --- a/drivers/media/dvb-frontends/bcm3510.c +++ b/drivers/media/dvb-frontends/bcm3510.c @@ -835,7 +835,7 @@ struct dvb_frontend* bcm3510_attach(const struct bcm3510_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(bcm3510_attach); +EXPORT_SYMBOL_GPL(bcm3510_attach); static const struct dvb_frontend_ops bcm3510_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/cx22700.c b/drivers/media/dvb-frontends/cx22700.c index b39ff516271b..1d04c0a652b2 100644 --- a/drivers/media/dvb-frontends/cx22700.c +++ b/drivers/media/dvb-frontends/cx22700.c @@ -432,4 +432,4 @@ MODULE_DESCRIPTION("Conexant CX22700 DVB-T Demodulator driver"); MODULE_AUTHOR("Holger Waechtler"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(cx22700_attach); +EXPORT_SYMBOL_GPL(cx22700_attach); diff --git a/drivers/media/dvb-frontends/cx22702.c b/drivers/media/dvb-frontends/cx22702.c index cc6acbf6393d..61ad34b7004b 100644 --- a/drivers/media/dvb-frontends/cx22702.c +++ b/drivers/media/dvb-frontends/cx22702.c @@ -604,7 +604,7 @@ struct dvb_frontend *cx22702_attach(const struct cx22702_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(cx22702_attach); +EXPORT_SYMBOL_GPL(cx22702_attach); static const struct dvb_frontend_ops cx22702_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/cx24110.c b/drivers/media/dvb-frontends/cx24110.c index 6f99d6a27be2..9aeea089756f 100644 --- a/drivers/media/dvb-frontends/cx24110.c +++ b/drivers/media/dvb-frontends/cx24110.c @@ -653,4 +653,4 @@ MODULE_DESCRIPTION("Conexant CX24110 DVB-S Demodulator driver"); MODULE_AUTHOR("Peter Hettkamp"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(cx24110_attach); +EXPORT_SYMBOL_GPL(cx24110_attach); diff --git a/drivers/media/dvb-frontends/cx24113.c b/drivers/media/dvb-frontends/cx24113.c index dd55d314bf9a..203cb6b3f941 100644 --- a/drivers/media/dvb-frontends/cx24113.c +++ b/drivers/media/dvb-frontends/cx24113.c @@ -590,7 +590,7 @@ struct dvb_frontend *cx24113_attach(struct dvb_frontend *fe, return NULL; } -EXPORT_SYMBOL(cx24113_attach); +EXPORT_SYMBOL_GPL(cx24113_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Activates frontend debugging (default:0)"); diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c index ea8264ccbb4e..8b978a9f74a4 100644 --- a/drivers/media/dvb-frontends/cx24116.c +++ b/drivers/media/dvb-frontends/cx24116.c @@ -1133,7 +1133,7 @@ struct dvb_frontend *cx24116_attach(const struct cx24116_config *config, state->frontend.demodulator_priv = state; return &state->frontend; } -EXPORT_SYMBOL(cx24116_attach); +EXPORT_SYMBOL_GPL(cx24116_attach); /* * Initialise or wake up device diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c index 0f778660c72b..44515fdbe91d 100644 --- a/drivers/media/dvb-frontends/cx24120.c +++ b/drivers/media/dvb-frontends/cx24120.c @@ -305,7 +305,7 @@ struct dvb_frontend *cx24120_attach(const struct cx24120_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(cx24120_attach); +EXPORT_SYMBOL_GPL(cx24120_attach); static int cx24120_test_rom(struct cx24120_state *state) { diff --git a/drivers/media/dvb-frontends/cx24123.c b/drivers/media/dvb-frontends/cx24123.c index 3d84ee17e54c..539889e638cc 100644 --- a/drivers/media/dvb-frontends/cx24123.c +++ b/drivers/media/dvb-frontends/cx24123.c @@ -1096,7 +1096,7 @@ struct dvb_frontend *cx24123_attach(const struct cx24123_config *config, return NULL; } -EXPORT_SYMBOL(cx24123_attach); +EXPORT_SYMBOL_GPL(cx24123_attach); static const struct dvb_frontend_ops cx24123_ops = { .delsys = { SYS_DVBS }, diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c index 5d98222f9df0..8870aeac2872 100644 --- a/drivers/media/dvb-frontends/cxd2820r_core.c +++ b/drivers/media/dvb-frontends/cxd2820r_core.c @@ -536,7 +536,7 @@ struct dvb_frontend *cxd2820r_attach(const struct cxd2820r_config *config, return pdata.get_dvb_frontend(client); } -EXPORT_SYMBOL(cxd2820r_attach); +EXPORT_SYMBOL_GPL(cxd2820r_attach); static struct dvb_frontend *cxd2820r_get_dvb_frontend(struct i2c_client *client) { diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c index 5431f922f55e..e9d1eef40c62 100644 --- a/drivers/media/dvb-frontends/cxd2841er.c +++ b/drivers/media/dvb-frontends/cxd2841er.c @@ -3930,14 +3930,14 @@ struct dvb_frontend *cxd2841er_attach_s(struct cxd2841er_config *cfg, { return cxd2841er_attach(cfg, i2c, SYS_DVBS); } -EXPORT_SYMBOL(cxd2841er_attach_s); +EXPORT_SYMBOL_GPL(cxd2841er_attach_s); struct dvb_frontend *cxd2841er_attach_t_c(struct cxd2841er_config *cfg, struct i2c_adapter *i2c) { return cxd2841er_attach(cfg, i2c, 0); } -EXPORT_SYMBOL(cxd2841er_attach_t_c); +EXPORT_SYMBOL_GPL(cxd2841er_attach_t_c); static const struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = { .delsys = { SYS_DVBS, SYS_DVBS2 }, diff --git a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c index d5b1b3788e39..09d31c368741 100644 --- a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c +++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c @@ -1950,7 +1950,7 @@ struct dvb_frontend *cxd2880_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(cxd2880_attach); +EXPORT_SYMBOL_GPL(cxd2880_attach); MODULE_DESCRIPTION("Sony CXD2880 DVB-T2/T tuner + demod driver"); MODULE_AUTHOR("Sony Semiconductor Solutions Corporation"); diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c index cafb41dba861..9a8e7cdd2a24 100644 --- a/drivers/media/dvb-frontends/dib0070.c +++ b/drivers/media/dvb-frontends/dib0070.c @@ -762,7 +762,7 @@ struct dvb_frontend *dib0070_attach(struct dvb_frontend *fe, struct i2c_adapter fe->tuner_priv = NULL; return NULL; } -EXPORT_SYMBOL(dib0070_attach); +EXPORT_SYMBOL_GPL(dib0070_attach); MODULE_AUTHOR("Patrick Boettcher "); MODULE_DESCRIPTION("Driver for the DiBcom 0070 base-band RF Tuner"); diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c index 903da33642df..c958bcff026e 100644 --- a/drivers/media/dvb-frontends/dib0090.c +++ b/drivers/media/dvb-frontends/dib0090.c @@ -2634,7 +2634,7 @@ struct dvb_frontend *dib0090_register(struct dvb_frontend *fe, struct i2c_adapte return NULL; } -EXPORT_SYMBOL(dib0090_register); +EXPORT_SYMBOL_GPL(dib0090_register); struct dvb_frontend *dib0090_fw_register(struct dvb_frontend *fe, struct i2c_adapter *i2c, const struct dib0090_config *config) { @@ -2660,7 +2660,7 @@ struct dvb_frontend *dib0090_fw_register(struct dvb_frontend *fe, struct i2c_ada fe->tuner_priv = NULL; return NULL; } -EXPORT_SYMBOL(dib0090_fw_register); +EXPORT_SYMBOL_GPL(dib0090_fw_register); MODULE_AUTHOR("Patrick Boettcher "); MODULE_AUTHOR("Olivier Grenie "); diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c index a6c2fc4586eb..c598b2a63325 100644 --- a/drivers/media/dvb-frontends/dib3000mb.c +++ b/drivers/media/dvb-frontends/dib3000mb.c @@ -815,4 +815,4 @@ MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(dib3000mb_attach); +EXPORT_SYMBOL_GPL(dib3000mb_attach); diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c index 2e11a246aae0..c2fca8289aba 100644 --- a/drivers/media/dvb-frontends/dib3000mc.c +++ b/drivers/media/dvb-frontends/dib3000mc.c @@ -935,7 +935,7 @@ struct dvb_frontend * dib3000mc_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr kfree(st); return NULL; } -EXPORT_SYMBOL(dib3000mc_attach); +EXPORT_SYMBOL_GPL(dib3000mc_attach); static const struct dvb_frontend_ops dib3000mc_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c index 97ce97789c9e..fdb22f32e3a1 100644 --- a/drivers/media/dvb-frontends/dib7000m.c +++ b/drivers/media/dvb-frontends/dib7000m.c @@ -1434,7 +1434,7 @@ struct dvb_frontend * dib7000m_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr, kfree(st); return NULL; } -EXPORT_SYMBOL(dib7000m_attach); +EXPORT_SYMBOL_GPL(dib7000m_attach); static const struct dvb_frontend_ops dib7000m_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c index 632534eff0ff..d1e53de5206a 100644 --- a/drivers/media/dvb-frontends/dib7000p.c +++ b/drivers/media/dvb-frontends/dib7000p.c @@ -2822,7 +2822,7 @@ void *dib7000p_attach(struct dib7000p_ops *ops) return ops; } -EXPORT_SYMBOL(dib7000p_attach); +EXPORT_SYMBOL_GPL(dib7000p_attach); static const struct dvb_frontend_ops dib7000p_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c index fe19d127abb3..301d8eca7a6f 100644 --- a/drivers/media/dvb-frontends/dib8000.c +++ b/drivers/media/dvb-frontends/dib8000.c @@ -4527,7 +4527,7 @@ void *dib8000_attach(struct dib8000_ops *ops) return ops; } -EXPORT_SYMBOL(dib8000_attach); +EXPORT_SYMBOL_GPL(dib8000_attach); MODULE_AUTHOR("Olivier Grenie "); MODULE_DESCRIPTION("Driver for the DiBcom 8000 ISDB-T demodulator"); diff --git a/drivers/media/dvb-frontends/dib9000.c b/drivers/media/dvb-frontends/dib9000.c index 914ca820c174..6f81890b31ee 100644 --- a/drivers/media/dvb-frontends/dib9000.c +++ b/drivers/media/dvb-frontends/dib9000.c @@ -2546,7 +2546,7 @@ struct dvb_frontend *dib9000_attach(struct i2c_adapter *i2c_adap, u8 i2c_addr, c kfree(st); return NULL; } -EXPORT_SYMBOL(dib9000_attach); +EXPORT_SYMBOL_GPL(dib9000_attach); static const struct dvb_frontend_ops dib9000_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c index bf9e4ef35684..88860d08f9c1 100644 --- a/drivers/media/dvb-frontends/drx39xyj/drxj.c +++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c @@ -12368,7 +12368,7 @@ struct dvb_frontend *drx39xxj_attach(struct i2c_adapter *i2c) return NULL; } -EXPORT_SYMBOL(drx39xxj_attach); +EXPORT_SYMBOL_GPL(drx39xxj_attach); static const struct dvb_frontend_ops drx39xxj_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c index 9860cae65f1c..6a531937f4bb 100644 --- a/drivers/media/dvb-frontends/drxd_hard.c +++ b/drivers/media/dvb-frontends/drxd_hard.c @@ -2939,7 +2939,7 @@ struct dvb_frontend *drxd_attach(const struct drxd_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(drxd_attach); +EXPORT_SYMBOL_GPL(drxd_attach); MODULE_DESCRIPTION("DRXD driver"); MODULE_AUTHOR("Micronas"); diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c index 9807f5411996..ff864c9bb774 100644 --- a/drivers/media/dvb-frontends/drxk_hard.c +++ b/drivers/media/dvb-frontends/drxk_hard.c @@ -6833,7 +6833,7 @@ struct dvb_frontend *drxk_attach(const struct drxk_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(drxk_attach); +EXPORT_SYMBOL_GPL(drxk_attach); MODULE_DESCRIPTION("DRX-K driver"); MODULE_AUTHOR("Ralph Metzler"); diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c index 20fcf31af165..515aa7c7baf2 100644 --- a/drivers/media/dvb-frontends/ds3000.c +++ b/drivers/media/dvb-frontends/ds3000.c @@ -859,7 +859,7 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config, ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF); return &state->frontend; } -EXPORT_SYMBOL(ds3000_attach); +EXPORT_SYMBOL_GPL(ds3000_attach); static int ds3000_set_carrier_offset(struct dvb_frontend *fe, s32 carrier_offset_khz) diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c index baf2a378e565..fcf322ff8235 100644 --- a/drivers/media/dvb-frontends/dvb-pll.c +++ b/drivers/media/dvb-frontends/dvb-pll.c @@ -866,7 +866,7 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr, return NULL; } -EXPORT_SYMBOL(dvb_pll_attach); +EXPORT_SYMBOL_GPL(dvb_pll_attach); static int diff --git a/drivers/media/dvb-frontends/ec100.c b/drivers/media/dvb-frontends/ec100.c index 03bd80666cf8..2ad0a3c2f756 100644 --- a/drivers/media/dvb-frontends/ec100.c +++ b/drivers/media/dvb-frontends/ec100.c @@ -299,7 +299,7 @@ struct dvb_frontend *ec100_attach(const struct ec100_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(ec100_attach); +EXPORT_SYMBOL_GPL(ec100_attach); static const struct dvb_frontend_ops ec100_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c index 8c1310c6b0bc..c299d31dc7d2 100644 --- a/drivers/media/dvb-frontends/helene.c +++ b/drivers/media/dvb-frontends/helene.c @@ -1025,7 +1025,7 @@ struct dvb_frontend *helene_attach_s(struct dvb_frontend *fe, priv->i2c_address, priv->i2c); return fe; } -EXPORT_SYMBOL(helene_attach_s); +EXPORT_SYMBOL_GPL(helene_attach_s); struct dvb_frontend *helene_attach(struct dvb_frontend *fe, const struct helene_config *config, @@ -1061,7 +1061,7 @@ struct dvb_frontend *helene_attach(struct dvb_frontend *fe, priv->i2c_address, priv->i2c); return fe; } -EXPORT_SYMBOL(helene_attach); +EXPORT_SYMBOL_GPL(helene_attach); static int helene_probe(struct i2c_client *client, const struct i2c_device_id *id) diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c index 24bf5cbcc184..0330b78a5b3f 100644 --- a/drivers/media/dvb-frontends/horus3a.c +++ b/drivers/media/dvb-frontends/horus3a.c @@ -395,7 +395,7 @@ struct dvb_frontend *horus3a_attach(struct dvb_frontend *fe, priv->i2c_address, priv->i2c); return fe; } -EXPORT_SYMBOL(horus3a_attach); +EXPORT_SYMBOL_GPL(horus3a_attach); MODULE_DESCRIPTION("Sony HORUS3A satellite tuner driver"); MODULE_AUTHOR("Sergey Kozlov "); diff --git a/drivers/media/dvb-frontends/isl6405.c b/drivers/media/dvb-frontends/isl6405.c index 2cd69b4ff82c..7d28a743f97e 100644 --- a/drivers/media/dvb-frontends/isl6405.c +++ b/drivers/media/dvb-frontends/isl6405.c @@ -141,7 +141,7 @@ struct dvb_frontend *isl6405_attach(struct dvb_frontend *fe, struct i2c_adapter return fe; } -EXPORT_SYMBOL(isl6405_attach); +EXPORT_SYMBOL_GPL(isl6405_attach); MODULE_DESCRIPTION("Driver for lnb supply and control ic isl6405"); MODULE_AUTHOR("Hartmut Hackmann & Oliver Endriss"); diff --git a/drivers/media/dvb-frontends/isl6421.c b/drivers/media/dvb-frontends/isl6421.c index 43b0dfc6f453..2e9f6f12f849 100644 --- a/drivers/media/dvb-frontends/isl6421.c +++ b/drivers/media/dvb-frontends/isl6421.c @@ -213,7 +213,7 @@ struct dvb_frontend *isl6421_attach(struct dvb_frontend *fe, struct i2c_adapter return fe; } -EXPORT_SYMBOL(isl6421_attach); +EXPORT_SYMBOL_GPL(isl6421_attach); MODULE_DESCRIPTION("Driver for lnb supply and control ic isl6421"); MODULE_AUTHOR("Andrew de Quincey & Oliver Endriss"); diff --git a/drivers/media/dvb-frontends/isl6423.c b/drivers/media/dvb-frontends/isl6423.c index 8cd1bb88ce6e..a0d0a3834057 100644 --- a/drivers/media/dvb-frontends/isl6423.c +++ b/drivers/media/dvb-frontends/isl6423.c @@ -289,7 +289,7 @@ struct dvb_frontend *isl6423_attach(struct dvb_frontend *fe, fe->sec_priv = NULL; return NULL; } -EXPORT_SYMBOL(isl6423_attach); +EXPORT_SYMBOL_GPL(isl6423_attach); MODULE_DESCRIPTION("ISL6423 SEC"); MODULE_AUTHOR("Manu Abraham"); diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c index 1b33478653d1..f8f362f50e78 100644 --- a/drivers/media/dvb-frontends/itd1000.c +++ b/drivers/media/dvb-frontends/itd1000.c @@ -389,7 +389,7 @@ struct dvb_frontend *itd1000_attach(struct dvb_frontend *fe, struct i2c_adapter return fe; } -EXPORT_SYMBOL(itd1000_attach); +EXPORT_SYMBOL_GPL(itd1000_attach); MODULE_AUTHOR("Patrick Boettcher "); MODULE_DESCRIPTION("Integrant ITD1000 driver"); diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c index 73f27105c139..3212e333d472 100644 --- a/drivers/media/dvb-frontends/ix2505v.c +++ b/drivers/media/dvb-frontends/ix2505v.c @@ -302,7 +302,7 @@ struct dvb_frontend *ix2505v_attach(struct dvb_frontend *fe, kfree(state); return NULL; } -EXPORT_SYMBOL(ix2505v_attach); +EXPORT_SYMBOL_GPL(ix2505v_attach); module_param_named(debug, ix2505v_debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/l64781.c b/drivers/media/dvb-frontends/l64781.c index c5106a1ea1cd..fe5af2453d55 100644 --- a/drivers/media/dvb-frontends/l64781.c +++ b/drivers/media/dvb-frontends/l64781.c @@ -593,4 +593,4 @@ MODULE_DESCRIPTION("LSI L64781 DVB-T Demodulator driver"); MODULE_AUTHOR("Holger Waechtler, Marko Kohtala"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(l64781_attach); +EXPORT_SYMBOL_GPL(l64781_attach); diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c index f343066c297e..fe700aa56bff 100644 --- a/drivers/media/dvb-frontends/lg2160.c +++ b/drivers/media/dvb-frontends/lg2160.c @@ -1426,7 +1426,7 @@ struct dvb_frontend *lg2160_attach(const struct lg2160_config *config, return &state->frontend; } -EXPORT_SYMBOL(lg2160_attach); +EXPORT_SYMBOL_GPL(lg2160_attach); MODULE_DESCRIPTION("LG Electronics LG216x ATSC/MH Demodulator Driver"); MODULE_AUTHOR("Michael Krufky "); diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c index 62d743988919..60a97f1cc74e 100644 --- a/drivers/media/dvb-frontends/lgdt3305.c +++ b/drivers/media/dvb-frontends/lgdt3305.c @@ -1148,7 +1148,7 @@ struct dvb_frontend *lgdt3305_attach(const struct lgdt3305_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(lgdt3305_attach); +EXPORT_SYMBOL_GPL(lgdt3305_attach); static const struct dvb_frontend_ops lgdt3304_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c index 424311afb2bf..6dfa8b18ed67 100644 --- a/drivers/media/dvb-frontends/lgdt3306a.c +++ b/drivers/media/dvb-frontends/lgdt3306a.c @@ -1859,7 +1859,7 @@ struct dvb_frontend *lgdt3306a_attach(const struct lgdt3306a_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(lgdt3306a_attach); +EXPORT_SYMBOL_GPL(lgdt3306a_attach); #ifdef DBG_DUMP diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c index ea9ae22fd201..cb07869ea2fb 100644 --- a/drivers/media/dvb-frontends/lgdt330x.c +++ b/drivers/media/dvb-frontends/lgdt330x.c @@ -928,7 +928,7 @@ struct dvb_frontend *lgdt330x_attach(const struct lgdt330x_config *_config, return lgdt330x_get_dvb_frontend(client); } -EXPORT_SYMBOL(lgdt330x_attach); +EXPORT_SYMBOL_GPL(lgdt330x_attach); static const struct dvb_frontend_ops lgdt3302_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/lgs8gxx.c b/drivers/media/dvb-frontends/lgs8gxx.c index 30014979b985..ffaf60e16ecd 100644 --- a/drivers/media/dvb-frontends/lgs8gxx.c +++ b/drivers/media/dvb-frontends/lgs8gxx.c @@ -1043,7 +1043,7 @@ struct dvb_frontend *lgs8gxx_attach(const struct lgs8gxx_config *config, return NULL; } -EXPORT_SYMBOL(lgs8gxx_attach); +EXPORT_SYMBOL_GPL(lgs8gxx_attach); MODULE_DESCRIPTION("Legend Silicon LGS8913/LGS8GXX DMB-TH demodulator driver"); MODULE_AUTHOR("David T. L. Wong "); diff --git a/drivers/media/dvb-frontends/lnbh25.c b/drivers/media/dvb-frontends/lnbh25.c index 9ffe06cd787d..41bec050642b 100644 --- a/drivers/media/dvb-frontends/lnbh25.c +++ b/drivers/media/dvb-frontends/lnbh25.c @@ -173,7 +173,7 @@ struct dvb_frontend *lnbh25_attach(struct dvb_frontend *fe, __func__, priv->i2c_address); return fe; } -EXPORT_SYMBOL(lnbh25_attach); +EXPORT_SYMBOL_GPL(lnbh25_attach); MODULE_DESCRIPTION("ST LNBH25 driver"); MODULE_AUTHOR("info@netup.ru"); diff --git a/drivers/media/dvb-frontends/lnbp21.c b/drivers/media/dvb-frontends/lnbp21.c index e564974162d6..32593b1f75a3 100644 --- a/drivers/media/dvb-frontends/lnbp21.c +++ b/drivers/media/dvb-frontends/lnbp21.c @@ -155,7 +155,7 @@ struct dvb_frontend *lnbh24_attach(struct dvb_frontend *fe, return lnbx2x_attach(fe, i2c, override_set, override_clear, i2c_addr, LNBH24_TTX); } -EXPORT_SYMBOL(lnbh24_attach); +EXPORT_SYMBOL_GPL(lnbh24_attach); struct dvb_frontend *lnbp21_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, u8 override_set, @@ -164,7 +164,7 @@ struct dvb_frontend *lnbp21_attach(struct dvb_frontend *fe, return lnbx2x_attach(fe, i2c, override_set, override_clear, 0x08, LNBP21_ISEL); } -EXPORT_SYMBOL(lnbp21_attach); +EXPORT_SYMBOL_GPL(lnbp21_attach); MODULE_DESCRIPTION("Driver for lnb supply and control ic lnbp21, lnbh24"); MODULE_AUTHOR("Oliver Endriss, Igor M. Liplianin"); diff --git a/drivers/media/dvb-frontends/lnbp22.c b/drivers/media/dvb-frontends/lnbp22.c index b8c7145d4cef..cb4ea5d3fad4 100644 --- a/drivers/media/dvb-frontends/lnbp22.c +++ b/drivers/media/dvb-frontends/lnbp22.c @@ -125,7 +125,7 @@ struct dvb_frontend *lnbp22_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(lnbp22_attach); +EXPORT_SYMBOL_GPL(lnbp22_attach); MODULE_DESCRIPTION("Driver for lnb supply and control ic lnbp22"); MODULE_AUTHOR("Dominik Kuhlen"); diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c index 4e844b2ef597..9a0d43c7ba9e 100644 --- a/drivers/media/dvb-frontends/m88ds3103.c +++ b/drivers/media/dvb-frontends/m88ds3103.c @@ -1695,7 +1695,7 @@ struct dvb_frontend *m88ds3103_attach(const struct m88ds3103_config *cfg, *tuner_i2c_adapter = pdata.get_i2c_adapter(client); return pdata.get_dvb_frontend(client); } -EXPORT_SYMBOL(m88ds3103_attach); +EXPORT_SYMBOL_GPL(m88ds3103_attach); static const struct dvb_frontend_ops m88ds3103_ops = { .delsys = {SYS_DVBS, SYS_DVBS2}, diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c index b294ba87e934..2aa98203cd65 100644 --- a/drivers/media/dvb-frontends/m88rs2000.c +++ b/drivers/media/dvb-frontends/m88rs2000.c @@ -808,7 +808,7 @@ struct dvb_frontend *m88rs2000_attach(const struct m88rs2000_config *config, return NULL; } -EXPORT_SYMBOL(m88rs2000_attach); +EXPORT_SYMBOL_GPL(m88rs2000_attach); MODULE_DESCRIPTION("M88RS2000 DVB-S Demodulator driver"); MODULE_AUTHOR("Malcolm Priestley tvboxspy@gmail.com"); diff --git a/drivers/media/dvb-frontends/mb86a16.c b/drivers/media/dvb-frontends/mb86a16.c index 2505f1e5794e..ed08e0c2cf51 100644 --- a/drivers/media/dvb-frontends/mb86a16.c +++ b/drivers/media/dvb-frontends/mb86a16.c @@ -1848,6 +1848,6 @@ struct dvb_frontend *mb86a16_attach(const struct mb86a16_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(mb86a16_attach); +EXPORT_SYMBOL_GPL(mb86a16_attach); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Manu Abraham"); diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c index b74b9afed9a2..9f5c61d4f23c 100644 --- a/drivers/media/dvb-frontends/mb86a20s.c +++ b/drivers/media/dvb-frontends/mb86a20s.c @@ -2081,7 +2081,7 @@ struct dvb_frontend *mb86a20s_attach(const struct mb86a20s_config *config, dev_info(&i2c->dev, "Detected a Fujitsu mb86a20s frontend\n"); return &state->frontend; } -EXPORT_SYMBOL(mb86a20s_attach); +EXPORT_SYMBOL_GPL(mb86a20s_attach); static const struct dvb_frontend_ops mb86a20s_ops = { .delsys = { SYS_ISDBT }, diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c index d43a67045dbe..fb867dd8a26b 100644 --- a/drivers/media/dvb-frontends/mt312.c +++ b/drivers/media/dvb-frontends/mt312.c @@ -827,7 +827,7 @@ struct dvb_frontend *mt312_attach(const struct mt312_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(mt312_attach); +EXPORT_SYMBOL_GPL(mt312_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c index 399d5c519027..1b2889f5cf67 100644 --- a/drivers/media/dvb-frontends/mt352.c +++ b/drivers/media/dvb-frontends/mt352.c @@ -593,4 +593,4 @@ MODULE_DESCRIPTION("Zarlink MT352 DVB-T Demodulator driver"); MODULE_AUTHOR("Holger Waechtler, Daniel Mack, Antonio Mancuso"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(mt352_attach); +EXPORT_SYMBOL_GPL(mt352_attach); diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c index 200b6dbc75f8..1c549ada6ebf 100644 --- a/drivers/media/dvb-frontends/nxt200x.c +++ b/drivers/media/dvb-frontends/nxt200x.c @@ -1216,5 +1216,5 @@ MODULE_DESCRIPTION("NXT200X (ATSC 8VSB & ITU-T J.83 AnnexB 64/256 QAM) Demodulat MODULE_AUTHOR("Kirk Lapray, Michael Krufky, Jean-Francois Thibert, and Taylor Jacob"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(nxt200x_attach); +EXPORT_SYMBOL_GPL(nxt200x_attach); diff --git a/drivers/media/dvb-frontends/nxt6000.c b/drivers/media/dvb-frontends/nxt6000.c index 136918f82dda..e8d4940370dd 100644 --- a/drivers/media/dvb-frontends/nxt6000.c +++ b/drivers/media/dvb-frontends/nxt6000.c @@ -621,4 +621,4 @@ MODULE_DESCRIPTION("NxtWave NXT6000 DVB-T demodulator driver"); MODULE_AUTHOR("Florian Schirmer"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(nxt6000_attach); +EXPORT_SYMBOL_GPL(nxt6000_attach); diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c index 24de1b115158..144a1f25dec0 100644 --- a/drivers/media/dvb-frontends/or51132.c +++ b/drivers/media/dvb-frontends/or51132.c @@ -605,4 +605,4 @@ MODULE_AUTHOR("Kirk Lapray"); MODULE_AUTHOR("Trent Piepho"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(or51132_attach); +EXPORT_SYMBOL_GPL(or51132_attach); diff --git a/drivers/media/dvb-frontends/or51211.c b/drivers/media/dvb-frontends/or51211.c index ddcaea5c9941..dc60482162c5 100644 --- a/drivers/media/dvb-frontends/or51211.c +++ b/drivers/media/dvb-frontends/or51211.c @@ -551,5 +551,5 @@ MODULE_DESCRIPTION("Oren OR51211 VSB [pcHDTV HD-2000] Demodulator Driver"); MODULE_AUTHOR("Kirk Lapray"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(or51211_attach); +EXPORT_SYMBOL_GPL(or51211_attach); diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c index 3089cc174a6f..28b1dca077ea 100644 --- a/drivers/media/dvb-frontends/s5h1409.c +++ b/drivers/media/dvb-frontends/s5h1409.c @@ -981,7 +981,7 @@ struct dvb_frontend *s5h1409_attach(const struct s5h1409_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(s5h1409_attach); +EXPORT_SYMBOL_GPL(s5h1409_attach); static const struct dvb_frontend_ops s5h1409_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c index 2563a72e98b7..fc48e659c2d8 100644 --- a/drivers/media/dvb-frontends/s5h1411.c +++ b/drivers/media/dvb-frontends/s5h1411.c @@ -900,7 +900,7 @@ struct dvb_frontend *s5h1411_attach(const struct s5h1411_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(s5h1411_attach); +EXPORT_SYMBOL_GPL(s5h1411_attach); static const struct dvb_frontend_ops s5h1411_ops = { .delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B }, diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c index 6bdec2898bc8..d700de1ea6c2 100644 --- a/drivers/media/dvb-frontends/s5h1420.c +++ b/drivers/media/dvb-frontends/s5h1420.c @@ -918,7 +918,7 @@ struct dvb_frontend *s5h1420_attach(const struct s5h1420_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(s5h1420_attach); +EXPORT_SYMBOL_GPL(s5h1420_attach); static const struct dvb_frontend_ops s5h1420_ops = { .delsys = { SYS_DVBS }, diff --git a/drivers/media/dvb-frontends/s5h1432.c b/drivers/media/dvb-frontends/s5h1432.c index 956e8ee4b388..ff5d3bdf3bc6 100644 --- a/drivers/media/dvb-frontends/s5h1432.c +++ b/drivers/media/dvb-frontends/s5h1432.c @@ -355,7 +355,7 @@ struct dvb_frontend *s5h1432_attach(const struct s5h1432_config *config, return &state->frontend; } -EXPORT_SYMBOL(s5h1432_attach); +EXPORT_SYMBOL_GPL(s5h1432_attach); static const struct dvb_frontend_ops s5h1432_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/s921.c b/drivers/media/dvb-frontends/s921.c index f118d8e64103..7e461ac159fc 100644 --- a/drivers/media/dvb-frontends/s921.c +++ b/drivers/media/dvb-frontends/s921.c @@ -495,7 +495,7 @@ struct dvb_frontend *s921_attach(const struct s921_config *config, return &state->frontend; } -EXPORT_SYMBOL(s921_attach); +EXPORT_SYMBOL_GPL(s921_attach); static const struct dvb_frontend_ops s921_ops = { .delsys = { SYS_ISDBT }, diff --git a/drivers/media/dvb-frontends/si21xx.c b/drivers/media/dvb-frontends/si21xx.c index 2d29d2c4d434..210ccd356e2b 100644 --- a/drivers/media/dvb-frontends/si21xx.c +++ b/drivers/media/dvb-frontends/si21xx.c @@ -937,7 +937,7 @@ struct dvb_frontend *si21xx_attach(const struct si21xx_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(si21xx_attach); +EXPORT_SYMBOL_GPL(si21xx_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/sp887x.c b/drivers/media/dvb-frontends/sp887x.c index 146e7f2dd3c5..f59c0f96416b 100644 --- a/drivers/media/dvb-frontends/sp887x.c +++ b/drivers/media/dvb-frontends/sp887x.c @@ -624,4 +624,4 @@ MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); MODULE_DESCRIPTION("Spase sp887x DVB-T demodulator driver"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(sp887x_attach); +EXPORT_SYMBOL_GPL(sp887x_attach); diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c index 4ee6c1e1e9f7..2f4d8fb400cd 100644 --- a/drivers/media/dvb-frontends/stb0899_drv.c +++ b/drivers/media/dvb-frontends/stb0899_drv.c @@ -1638,7 +1638,7 @@ struct dvb_frontend *stb0899_attach(struct stb0899_config *config, struct i2c_ad kfree(state); return NULL; } -EXPORT_SYMBOL(stb0899_attach); +EXPORT_SYMBOL_GPL(stb0899_attach); MODULE_PARM_DESC(verbose, "Set Verbosity level"); MODULE_AUTHOR("Manu Abraham"); MODULE_DESCRIPTION("STB0899 Multi-Std frontend"); diff --git a/drivers/media/dvb-frontends/stb6000.c b/drivers/media/dvb-frontends/stb6000.c index 8c9800d577e0..d74e34677b92 100644 --- a/drivers/media/dvb-frontends/stb6000.c +++ b/drivers/media/dvb-frontends/stb6000.c @@ -232,7 +232,7 @@ struct dvb_frontend *stb6000_attach(struct dvb_frontend *fe, int addr, return fe; } -EXPORT_SYMBOL(stb6000_attach); +EXPORT_SYMBOL_GPL(stb6000_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c index 698866c4f15a..c5818a15a0d7 100644 --- a/drivers/media/dvb-frontends/stb6100.c +++ b/drivers/media/dvb-frontends/stb6100.c @@ -557,7 +557,7 @@ static void stb6100_release(struct dvb_frontend *fe) kfree(state); } -EXPORT_SYMBOL(stb6100_attach); +EXPORT_SYMBOL_GPL(stb6100_attach); MODULE_PARM_DESC(verbose, "Set Verbosity level"); MODULE_AUTHOR("Manu Abraham"); diff --git a/drivers/media/dvb-frontends/stv0288.c b/drivers/media/dvb-frontends/stv0288.c index 3ae1f3a2f142..a5581bd60f9e 100644 --- a/drivers/media/dvb-frontends/stv0288.c +++ b/drivers/media/dvb-frontends/stv0288.c @@ -590,7 +590,7 @@ struct dvb_frontend *stv0288_attach(const struct stv0288_config *config, return NULL; } -EXPORT_SYMBOL(stv0288_attach); +EXPORT_SYMBOL_GPL(stv0288_attach); module_param(debug_legacy_dish_switch, int, 0444); MODULE_PARM_DESC(debug_legacy_dish_switch, diff --git a/drivers/media/dvb-frontends/stv0297.c b/drivers/media/dvb-frontends/stv0297.c index 6d5962d5697a..9d4dbd99a5a7 100644 --- a/drivers/media/dvb-frontends/stv0297.c +++ b/drivers/media/dvb-frontends/stv0297.c @@ -710,4 +710,4 @@ MODULE_DESCRIPTION("ST STV0297 DVB-C Demodulator driver"); MODULE_AUTHOR("Dennis Noermann and Andrew de Quincey"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(stv0297_attach); +EXPORT_SYMBOL_GPL(stv0297_attach); diff --git a/drivers/media/dvb-frontends/stv0299.c b/drivers/media/dvb-frontends/stv0299.c index b5263a0ee5aa..da7ff2c2e8e5 100644 --- a/drivers/media/dvb-frontends/stv0299.c +++ b/drivers/media/dvb-frontends/stv0299.c @@ -752,4 +752,4 @@ MODULE_DESCRIPTION("ST STV0299 DVB Demodulator driver"); MODULE_AUTHOR("Ralph Metzler, Holger Waechtler, Peter Schildmann, Felix Domke, Andreas Oberritter, Andrew de Quincey, Kenneth Aafly"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(stv0299_attach); +EXPORT_SYMBOL_GPL(stv0299_attach); diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c index 95e376f23506..04556b77c16c 100644 --- a/drivers/media/dvb-frontends/stv0367.c +++ b/drivers/media/dvb-frontends/stv0367.c @@ -1750,7 +1750,7 @@ struct dvb_frontend *stv0367ter_attach(const struct stv0367_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(stv0367ter_attach); +EXPORT_SYMBOL_GPL(stv0367ter_attach); static int stv0367cab_gate_ctrl(struct dvb_frontend *fe, int enable) { @@ -2919,7 +2919,7 @@ struct dvb_frontend *stv0367cab_attach(const struct stv0367_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(stv0367cab_attach); +EXPORT_SYMBOL_GPL(stv0367cab_attach); /* * Functions for operation on Digital Devices hardware @@ -3340,7 +3340,7 @@ struct dvb_frontend *stv0367ddb_attach(const struct stv0367_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(stv0367ddb_attach); +EXPORT_SYMBOL_GPL(stv0367ddb_attach); MODULE_PARM_DESC(debug, "Set debug"); MODULE_PARM_DESC(i2c_debug, "Set i2c debug"); diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c index 212312d20ff6..e7b9b9b11d7d 100644 --- a/drivers/media/dvb-frontends/stv0900_core.c +++ b/drivers/media/dvb-frontends/stv0900_core.c @@ -1957,7 +1957,7 @@ struct dvb_frontend *stv0900_attach(const struct stv0900_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(stv0900_attach); +EXPORT_SYMBOL_GPL(stv0900_attach); MODULE_PARM_DESC(debug, "Set debug"); diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c index 0a600c1d7d1b..aba64162dac4 100644 --- a/drivers/media/dvb-frontends/stv090x.c +++ b/drivers/media/dvb-frontends/stv090x.c @@ -5072,7 +5072,7 @@ struct dvb_frontend *stv090x_attach(struct stv090x_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(stv090x_attach); +EXPORT_SYMBOL_GPL(stv090x_attach); static const struct i2c_device_id stv090x_id_table[] = { {"stv090x", 0}, diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c index 963f6a896102..1cf9c095dbff 100644 --- a/drivers/media/dvb-frontends/stv6110.c +++ b/drivers/media/dvb-frontends/stv6110.c @@ -427,7 +427,7 @@ struct dvb_frontend *stv6110_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(stv6110_attach); +EXPORT_SYMBOL_GPL(stv6110_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c index fbc4dbd62151..6ab200121591 100644 --- a/drivers/media/dvb-frontends/stv6110x.c +++ b/drivers/media/dvb-frontends/stv6110x.c @@ -468,7 +468,7 @@ const struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe, dev_info(&stv6110x->i2c->dev, "Attaching STV6110x\n"); return stv6110x->devctl; } -EXPORT_SYMBOL(stv6110x_attach); +EXPORT_SYMBOL_GPL(stv6110x_attach); static const struct i2c_device_id stv6110x_id_table[] = { {"stv6110x", 0}, diff --git a/drivers/media/dvb-frontends/tda10021.c b/drivers/media/dvb-frontends/tda10021.c index faa6e54b3372..462e12ab6bd1 100644 --- a/drivers/media/dvb-frontends/tda10021.c +++ b/drivers/media/dvb-frontends/tda10021.c @@ -523,4 +523,4 @@ MODULE_DESCRIPTION("Philips TDA10021 DVB-C demodulator driver"); MODULE_AUTHOR("Ralph Metzler, Holger Waechtler, Markus Schulz"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(tda10021_attach); +EXPORT_SYMBOL_GPL(tda10021_attach); diff --git a/drivers/media/dvb-frontends/tda10023.c b/drivers/media/dvb-frontends/tda10023.c index 8f32edf6b700..4c2541ecd743 100644 --- a/drivers/media/dvb-frontends/tda10023.c +++ b/drivers/media/dvb-frontends/tda10023.c @@ -594,4 +594,4 @@ MODULE_DESCRIPTION("Philips TDA10023 DVB-C demodulator driver"); MODULE_AUTHOR("Georg Acher, Hartmut Birr"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(tda10023_attach); +EXPORT_SYMBOL_GPL(tda10023_attach); diff --git a/drivers/media/dvb-frontends/tda10048.c b/drivers/media/dvb-frontends/tda10048.c index 0b3f6999515e..f6d8a64762b9 100644 --- a/drivers/media/dvb-frontends/tda10048.c +++ b/drivers/media/dvb-frontends/tda10048.c @@ -1138,7 +1138,7 @@ struct dvb_frontend *tda10048_attach(const struct tda10048_config *config, kfree(state); return NULL; } -EXPORT_SYMBOL(tda10048_attach); +EXPORT_SYMBOL_GPL(tda10048_attach); static const struct dvb_frontend_ops tda10048_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c index 83a798ca9b00..6f306db6c615 100644 --- a/drivers/media/dvb-frontends/tda1004x.c +++ b/drivers/media/dvb-frontends/tda1004x.c @@ -1378,5 +1378,5 @@ MODULE_DESCRIPTION("Philips TDA10045H & TDA10046H DVB-T Demodulator"); MODULE_AUTHOR("Andrew de Quincey & Robert Schlabbach"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(tda10045_attach); -EXPORT_SYMBOL(tda10046_attach); +EXPORT_SYMBOL_GPL(tda10045_attach); +EXPORT_SYMBOL_GPL(tda10046_attach); diff --git a/drivers/media/dvb-frontends/tda10086.c b/drivers/media/dvb-frontends/tda10086.c index cdcf97664bba..b449514ae585 100644 --- a/drivers/media/dvb-frontends/tda10086.c +++ b/drivers/media/dvb-frontends/tda10086.c @@ -764,4 +764,4 @@ MODULE_DESCRIPTION("Philips TDA10086 DVB-S Demodulator"); MODULE_AUTHOR("Andrew de Quincey"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(tda10086_attach); +EXPORT_SYMBOL_GPL(tda10086_attach); diff --git a/drivers/media/dvb-frontends/tda665x.c b/drivers/media/dvb-frontends/tda665x.c index 13e8969da7f8..346be5011fb7 100644 --- a/drivers/media/dvb-frontends/tda665x.c +++ b/drivers/media/dvb-frontends/tda665x.c @@ -227,7 +227,7 @@ struct dvb_frontend *tda665x_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(tda665x_attach); +EXPORT_SYMBOL_GPL(tda665x_attach); MODULE_DESCRIPTION("TDA665x driver"); MODULE_AUTHOR("Manu Abraham"); diff --git a/drivers/media/dvb-frontends/tda8083.c b/drivers/media/dvb-frontends/tda8083.c index e3e1c3db2c85..44f53624557b 100644 --- a/drivers/media/dvb-frontends/tda8083.c +++ b/drivers/media/dvb-frontends/tda8083.c @@ -481,4 +481,4 @@ MODULE_DESCRIPTION("Philips TDA8083 DVB-S Demodulator"); MODULE_AUTHOR("Ralph Metzler, Holger Waechtler"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(tda8083_attach); +EXPORT_SYMBOL_GPL(tda8083_attach); diff --git a/drivers/media/dvb-frontends/tda8261.c b/drivers/media/dvb-frontends/tda8261.c index 0d576d41c67d..8b06f92745dc 100644 --- a/drivers/media/dvb-frontends/tda8261.c +++ b/drivers/media/dvb-frontends/tda8261.c @@ -188,7 +188,7 @@ struct dvb_frontend *tda8261_attach(struct dvb_frontend *fe, return NULL; } -EXPORT_SYMBOL(tda8261_attach); +EXPORT_SYMBOL_GPL(tda8261_attach); MODULE_AUTHOR("Manu Abraham"); MODULE_DESCRIPTION("TDA8261 8PSK/QPSK Tuner"); diff --git a/drivers/media/dvb-frontends/tda826x.c b/drivers/media/dvb-frontends/tda826x.c index f9703a1dd758..eafcf5f7da3d 100644 --- a/drivers/media/dvb-frontends/tda826x.c +++ b/drivers/media/dvb-frontends/tda826x.c @@ -164,7 +164,7 @@ struct dvb_frontend *tda826x_attach(struct dvb_frontend *fe, int addr, struct i2 return fe; } -EXPORT_SYMBOL(tda826x_attach); +EXPORT_SYMBOL_GPL(tda826x_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c index 02338256b974..2f64f1a8bc23 100644 --- a/drivers/media/dvb-frontends/ts2020.c +++ b/drivers/media/dvb-frontends/ts2020.c @@ -525,7 +525,7 @@ struct dvb_frontend *ts2020_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(ts2020_attach); +EXPORT_SYMBOL_GPL(ts2020_attach); /* * We implement own regmap locking due to legacy DVB attach which uses frontend diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c index 2483f614d0e7..41dd9b6d3190 100644 --- a/drivers/media/dvb-frontends/tua6100.c +++ b/drivers/media/dvb-frontends/tua6100.c @@ -186,7 +186,7 @@ struct dvb_frontend *tua6100_attach(struct dvb_frontend *fe, int addr, struct i2 fe->tuner_priv = priv; return fe; } -EXPORT_SYMBOL(tua6100_attach); +EXPORT_SYMBOL_GPL(tua6100_attach); MODULE_DESCRIPTION("DVB tua6100 driver"); MODULE_AUTHOR("Andrew de Quincey"); diff --git a/drivers/media/dvb-frontends/ves1820.c b/drivers/media/dvb-frontends/ves1820.c index 9df14d0be1c1..ee5620e731e9 100644 --- a/drivers/media/dvb-frontends/ves1820.c +++ b/drivers/media/dvb-frontends/ves1820.c @@ -434,4 +434,4 @@ MODULE_DESCRIPTION("VLSI VES1820 DVB-C Demodulator driver"); MODULE_AUTHOR("Ralph Metzler, Holger Waechtler"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(ves1820_attach); +EXPORT_SYMBOL_GPL(ves1820_attach); diff --git a/drivers/media/dvb-frontends/ves1x93.c b/drivers/media/dvb-frontends/ves1x93.c index b74727286302..c60e21d26b88 100644 --- a/drivers/media/dvb-frontends/ves1x93.c +++ b/drivers/media/dvb-frontends/ves1x93.c @@ -540,4 +540,4 @@ MODULE_DESCRIPTION("VLSI VES1x93 DVB-S Demodulator driver"); MODULE_AUTHOR("Ralph Metzler"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(ves1x93_attach); +EXPORT_SYMBOL_GPL(ves1x93_attach); diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c index d392c7cce2ce..7ba575e9c55f 100644 --- a/drivers/media/dvb-frontends/zl10036.c +++ b/drivers/media/dvb-frontends/zl10036.c @@ -496,7 +496,7 @@ struct dvb_frontend *zl10036_attach(struct dvb_frontend *fe, kfree(state); return NULL; } -EXPORT_SYMBOL(zl10036_attach); +EXPORT_SYMBOL_GPL(zl10036_attach); module_param_named(debug, zl10036_debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/zl10039.c b/drivers/media/dvb-frontends/zl10039.c index 1335bf78d5b7..a3e4d219400c 100644 --- a/drivers/media/dvb-frontends/zl10039.c +++ b/drivers/media/dvb-frontends/zl10039.c @@ -295,7 +295,7 @@ struct dvb_frontend *zl10039_attach(struct dvb_frontend *fe, kfree(state); return NULL; } -EXPORT_SYMBOL(zl10039_attach); +EXPORT_SYMBOL_GPL(zl10039_attach); module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off)."); diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c index 2a2cf20a73d6..8849d05475c2 100644 --- a/drivers/media/dvb-frontends/zl10353.c +++ b/drivers/media/dvb-frontends/zl10353.c @@ -665,4 +665,4 @@ MODULE_DESCRIPTION("Zarlink ZL10353 DVB-T demodulator driver"); MODULE_AUTHOR("Chris Pascoe"); MODULE_LICENSE("GPL"); -EXPORT_SYMBOL(zl10353_attach); +EXPORT_SYMBOL_GPL(zl10353_attach); diff --git a/drivers/media/pci/bt8xx/dst.c b/drivers/media/pci/bt8xx/dst.c index 3e52a51982d7..110651e47831 100644 --- a/drivers/media/pci/bt8xx/dst.c +++ b/drivers/media/pci/bt8xx/dst.c @@ -1722,7 +1722,7 @@ struct dst_state *dst_attach(struct dst_state *state, struct dvb_adapter *dvb_ad return state; /* Manu (DST is a card not a frontend) */ } -EXPORT_SYMBOL(dst_attach); +EXPORT_SYMBOL_GPL(dst_attach); static const struct dvb_frontend_ops dst_dvbt_ops = { .delsys = { SYS_DVBT }, diff --git a/drivers/media/pci/bt8xx/dst_ca.c b/drivers/media/pci/bt8xx/dst_ca.c index 85fcdc59f0d1..571392d80ccc 100644 --- a/drivers/media/pci/bt8xx/dst_ca.c +++ b/drivers/media/pci/bt8xx/dst_ca.c @@ -668,7 +668,7 @@ struct dvb_device *dst_ca_attach(struct dst_state *dst, struct dvb_adapter *dvb_ return NULL; } -EXPORT_SYMBOL(dst_ca_attach); +EXPORT_SYMBOL_GPL(dst_ca_attach); MODULE_DESCRIPTION("DST DVB-S/T/C Combo CA driver"); MODULE_AUTHOR("Manu Abraham"); diff --git a/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c b/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c index 6868a0c4fc82..520ebd16b0c4 100644 --- a/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c +++ b/drivers/media/pci/ddbridge/ddbridge-dummy-fe.c @@ -112,7 +112,7 @@ struct dvb_frontend *ddbridge_dummy_fe_qam_attach(void) state->frontend.demodulator_priv = state; return &state->frontend; } -EXPORT_SYMBOL(ddbridge_dummy_fe_qam_attach); +EXPORT_SYMBOL_GPL(ddbridge_dummy_fe_qam_attach); static const struct dvb_frontend_ops ddbridge_dummy_fe_qam_ops = { .delsys = { SYS_DVBC_ANNEX_A }, diff --git a/drivers/media/tuners/fc0011.c b/drivers/media/tuners/fc0011.c index eaa3bbc903d7..3d3b54be2955 100644 --- a/drivers/media/tuners/fc0011.c +++ b/drivers/media/tuners/fc0011.c @@ -499,7 +499,7 @@ struct dvb_frontend *fc0011_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(fc0011_attach); +EXPORT_SYMBOL_GPL(fc0011_attach); MODULE_DESCRIPTION("Fitipower FC0011 silicon tuner driver"); MODULE_AUTHOR("Michael Buesch "); diff --git a/drivers/media/tuners/fc0012.c b/drivers/media/tuners/fc0012.c index 4429d5e8c579..81e65acbdb17 100644 --- a/drivers/media/tuners/fc0012.c +++ b/drivers/media/tuners/fc0012.c @@ -495,7 +495,7 @@ struct dvb_frontend *fc0012_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(fc0012_attach); +EXPORT_SYMBOL_GPL(fc0012_attach); MODULE_DESCRIPTION("Fitipower FC0012 silicon tuner driver"); MODULE_AUTHOR("Hans-Frieder Vogt "); diff --git a/drivers/media/tuners/fc0013.c b/drivers/media/tuners/fc0013.c index 29dd9b55ff33..1006a2798eef 100644 --- a/drivers/media/tuners/fc0013.c +++ b/drivers/media/tuners/fc0013.c @@ -608,7 +608,7 @@ struct dvb_frontend *fc0013_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(fc0013_attach); +EXPORT_SYMBOL_GPL(fc0013_attach); MODULE_DESCRIPTION("Fitipower FC0013 silicon tuner driver"); MODULE_AUTHOR("Hans-Frieder Vogt "); diff --git a/drivers/media/tuners/max2165.c b/drivers/media/tuners/max2165.c index 1c746bed51fe..1575ab94e1c8 100644 --- a/drivers/media/tuners/max2165.c +++ b/drivers/media/tuners/max2165.c @@ -410,7 +410,7 @@ struct dvb_frontend *max2165_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(max2165_attach); +EXPORT_SYMBOL_GPL(max2165_attach); MODULE_AUTHOR("David T. L. Wong "); MODULE_DESCRIPTION("Maxim MAX2165 silicon tuner driver"); diff --git a/drivers/media/tuners/mc44s803.c b/drivers/media/tuners/mc44s803.c index 0c9161516abd..ed8bdf7ebd99 100644 --- a/drivers/media/tuners/mc44s803.c +++ b/drivers/media/tuners/mc44s803.c @@ -356,7 +356,7 @@ struct dvb_frontend *mc44s803_attach(struct dvb_frontend *fe, kfree(priv); return NULL; } -EXPORT_SYMBOL(mc44s803_attach); +EXPORT_SYMBOL_GPL(mc44s803_attach); MODULE_AUTHOR("Jochen Friedrich"); MODULE_DESCRIPTION("Freescale MC44S803 silicon tuner driver"); diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c index 322c806228a5..da7e23c2689b 100644 --- a/drivers/media/tuners/mt2060.c +++ b/drivers/media/tuners/mt2060.c @@ -440,7 +440,7 @@ struct dvb_frontend * mt2060_attach(struct dvb_frontend *fe, struct i2c_adapter return fe; } -EXPORT_SYMBOL(mt2060_attach); +EXPORT_SYMBOL_GPL(mt2060_attach); static int mt2060_probe(struct i2c_client *client, const struct i2c_device_id *id) diff --git a/drivers/media/tuners/mt2131.c b/drivers/media/tuners/mt2131.c index 37f50ff6c0bd..eebc06088341 100644 --- a/drivers/media/tuners/mt2131.c +++ b/drivers/media/tuners/mt2131.c @@ -274,7 +274,7 @@ struct dvb_frontend * mt2131_attach(struct dvb_frontend *fe, fe->tuner_priv = priv; return fe; } -EXPORT_SYMBOL(mt2131_attach); +EXPORT_SYMBOL_GPL(mt2131_attach); MODULE_AUTHOR("Steven Toth"); MODULE_DESCRIPTION("Microtune MT2131 silicon tuner driver"); diff --git a/drivers/media/tuners/mt2266.c b/drivers/media/tuners/mt2266.c index 6136f20fa9b7..2e92885a6bcb 100644 --- a/drivers/media/tuners/mt2266.c +++ b/drivers/media/tuners/mt2266.c @@ -336,7 +336,7 @@ struct dvb_frontend * mt2266_attach(struct dvb_frontend *fe, struct i2c_adapter mt2266_calibrate(priv); return fe; } -EXPORT_SYMBOL(mt2266_attach); +EXPORT_SYMBOL_GPL(mt2266_attach); MODULE_AUTHOR("Olivier DANET"); MODULE_DESCRIPTION("Microtune MT2266 silicon tuner driver"); diff --git a/drivers/media/tuners/mxl5005s.c b/drivers/media/tuners/mxl5005s.c index ab4c43df9d18..2a8b0ea5d0cd 100644 --- a/drivers/media/tuners/mxl5005s.c +++ b/drivers/media/tuners/mxl5005s.c @@ -4116,7 +4116,7 @@ struct dvb_frontend *mxl5005s_attach(struct dvb_frontend *fe, fe->tuner_priv = state; return fe; } -EXPORT_SYMBOL(mxl5005s_attach); +EXPORT_SYMBOL_GPL(mxl5005s_attach); MODULE_DESCRIPTION("MaxLinear MXL5005S silicon tuner driver"); MODULE_AUTHOR("Steven Toth"); diff --git a/drivers/media/tuners/qt1010.c b/drivers/media/tuners/qt1010.c index 3853a3d43d4f..60931367b82c 100644 --- a/drivers/media/tuners/qt1010.c +++ b/drivers/media/tuners/qt1010.c @@ -440,7 +440,7 @@ struct dvb_frontend * qt1010_attach(struct dvb_frontend *fe, fe->tuner_priv = priv; return fe; } -EXPORT_SYMBOL(qt1010_attach); +EXPORT_SYMBOL_GPL(qt1010_attach); MODULE_DESCRIPTION("Quantek QT1010 silicon tuner driver"); MODULE_AUTHOR("Antti Palosaari "); diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c index 4ed94646116f..7d8d84dcb245 100644 --- a/drivers/media/tuners/tda18218.c +++ b/drivers/media/tuners/tda18218.c @@ -336,7 +336,7 @@ struct dvb_frontend *tda18218_attach(struct dvb_frontend *fe, return fe; } -EXPORT_SYMBOL(tda18218_attach); +EXPORT_SYMBOL_GPL(tda18218_attach); MODULE_DESCRIPTION("NXP TDA18218HN silicon tuner driver"); MODULE_AUTHOR("Antti Palosaari "); diff --git a/drivers/media/tuners/xc2028.c b/drivers/media/tuners/xc2028.c index 69c2e1b99bf1..5a967edceca9 100644 --- a/drivers/media/tuners/xc2028.c +++ b/drivers/media/tuners/xc2028.c @@ -1512,7 +1512,7 @@ struct dvb_frontend *xc2028_attach(struct dvb_frontend *fe, return NULL; } -EXPORT_SYMBOL(xc2028_attach); +EXPORT_SYMBOL_GPL(xc2028_attach); MODULE_DESCRIPTION("Xceive xc2028/xc3028 tuner driver"); MODULE_AUTHOR("Michel Ludwig "); diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index d59b4ab77430..57ded9ff3f04 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -1742,7 +1742,7 @@ struct dvb_frontend *xc4000_attach(struct dvb_frontend *fe, xc4000_release(fe); return NULL; } -EXPORT_SYMBOL(xc4000_attach); +EXPORT_SYMBOL_GPL(xc4000_attach); MODULE_AUTHOR("Steven Toth, Davide Ferri"); MODULE_DESCRIPTION("Xceive xc4000 silicon tuner driver"); diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c index 7b7d9fe4f945..2182e5b7b606 100644 --- a/drivers/media/tuners/xc5000.c +++ b/drivers/media/tuners/xc5000.c @@ -1460,7 +1460,7 @@ struct dvb_frontend *xc5000_attach(struct dvb_frontend *fe, xc5000_release(fe); return NULL; } -EXPORT_SYMBOL(xc5000_attach); +EXPORT_SYMBOL_GPL(xc5000_attach); MODULE_AUTHOR("Steven Toth"); MODULE_DESCRIPTION("Xceive xc5000 silicon tuner driver"); From ab8c52977fe0434de61737797d7922b97426592f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 30 May 2023 14:30:36 +0200 Subject: [PATCH 1226/2093] media: venus: hfi_venus: Write to VIDC_CTRL_INIT after unmasking interrupts commit d74e481609808330b4625b3691cf01e1f56e255e upstream. The startup procedure shouldn't be started with interrupts masked, as that may entail silent failures. Kick off initialization only after the interrupts are unmasked. Cc: stable@vger.kernel.org # v4.12+ Fixes: d96d3f30c0f2 ("[media] media: venus: hfi: add Venus HFI files") Signed-off-by: Konrad Dybcio Signed-off-by: Stanimir Varbanov Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/qcom/venus/hfi_venus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index bff435abd59b..8fc8f46dc390 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -453,7 +453,6 @@ static int venus_boot_core(struct venus_hfi_device *hdev) void __iomem *wrapper_base = hdev->core->wrapper_base; int ret = 0; - writel(BIT(VIDC_CTRL_INIT_CTRL_SHIFT), cpu_cs_base + VIDC_CTRL_INIT); if (IS_V6(hdev->core)) { mask_val = readl(wrapper_base + WRAPPER_INTR_MASK); mask_val &= ~(WRAPPER_INTR_MASK_A2HWD_BASK_V6 | @@ -464,6 +463,7 @@ static int venus_boot_core(struct venus_hfi_device *hdev) writel(mask_val, wrapper_base + WRAPPER_INTR_MASK); writel(1, cpu_cs_base + CPU_CS_SCIACMDARG3); + writel(BIT(VIDC_CTRL_INIT_CTRL_SHIFT), cpu_cs_base + VIDC_CTRL_INIT); while (!ctrl_status && count < max_tries) { ctrl_status = readl(cpu_cs_base + CPU_CS_SCIACMDARG0); if ((ctrl_status & CPU_CS_SCIACMDARG0_ERROR_STATUS_MASK) == 4) { From 6c4f87e52331a643d73d5c9bd6d1ea2798165096 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Mon, 21 Aug 2023 18:30:44 +0530 Subject: [PATCH 1227/2093] Revert "scsi: qla2xxx: Fix buffer overrun" commit 641671d97b9199f1ba35ccc2222d4b189a6a5de5 upstream. Revert due to Get PLOGI Template failed. This reverts commit b68710a8094fdffe8dd4f7a82c82649f479bb453. Cc: stable@vger.kernel.org Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230821130045.34850-9-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index b597c782b95e..30bbf33e3a6a 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -5571,7 +5571,7 @@ static void qla_get_login_template(scsi_qla_host_t *vha) __be32 *q; memset(ha->init_cb, 0, ha->init_cb_size); - sz = min_t(int, sizeof(struct fc_els_csp), ha->init_cb_size); + sz = min_t(int, sizeof(struct fc_els_flogi), ha->init_cb_size); rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma, ha->init_cb, sz); if (rval != QLA_SUCCESS) { From 316f3984298a66c783348d0937ddddea01987b35 Mon Sep 17 00:00:00 2001 From: Ranjan Kumar Date: Tue, 29 Aug 2023 14:30:19 +0530 Subject: [PATCH 1228/2093] scsi: mpt3sas: Perform additional retries if doorbell read returns 0 commit 4ca10f3e31745d35249a727ecd108eb58f0a8c5e upstream. The driver retries certain register reads 3 times if the returned value is 0. This was done because the controller could return 0 for certain registers if other registers were being accessed concurrently by the BMC. In certain systems with increased BMC interactions, the register values returned can be 0 for longer than 3 retries. Change the retry count from 3 to 30 for the affected registers to prevent problems with out-of-band management. Fixes: b899202901a8 ("scsi: mpt3sas: Add separate function for aero doorbell reads") Cc: stable@vger.kernel.org Signed-off-by: Ranjan Kumar Link: https://lore.kernel.org/r/20230829090020.5417-2-ranjan.kumar@broadcom.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/mpt3sas/mpt3sas_base.c | 46 +++++++++++++++++++++-------- drivers/scsi/mpt3sas/mpt3sas_base.h | 1 + 2 files changed, 34 insertions(+), 13 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 14ae0a9c5d3d..2093888f154e 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -139,6 +139,9 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc); static void _base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc); +static u32 +_base_readl_ext_retry(const volatile void __iomem *addr); + /** * mpt3sas_base_check_cmd_timeout - Function * to check timeout and command termination due @@ -214,6 +217,20 @@ _base_readl_aero(const volatile void __iomem *addr) return ret_val; } +static u32 +_base_readl_ext_retry(const volatile void __iomem *addr) +{ + u32 i, ret_val; + + for (i = 0 ; i < 30 ; i++) { + ret_val = readl(addr); + if (ret_val == 0) + continue; + } + + return ret_val; +} + static inline u32 _base_readl(const volatile void __iomem *addr) { @@ -941,7 +958,7 @@ mpt3sas_halt_firmware(struct MPT3SAS_ADAPTER *ioc) dump_stack(); - doorbell = ioc->base_readl(&ioc->chip->Doorbell); + doorbell = ioc->base_readl_ext_retry(&ioc->chip->Doorbell); if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) { mpt3sas_print_fault_code(ioc, doorbell & MPI2_DOORBELL_DATA_MASK); @@ -6697,7 +6714,7 @@ mpt3sas_base_get_iocstate(struct MPT3SAS_ADAPTER *ioc, int cooked) { u32 s, sc; - s = ioc->base_readl(&ioc->chip->Doorbell); + s = ioc->base_readl_ext_retry(&ioc->chip->Doorbell); sc = s & MPI2_IOC_STATE_MASK; return cooked ? sc : s; } @@ -6842,7 +6859,7 @@ _base_wait_for_doorbell_ack(struct MPT3SAS_ADAPTER *ioc, int timeout) __func__, count, timeout)); return 0; } else if (int_status & MPI2_HIS_IOC2SYS_DB_STATUS) { - doorbell = ioc->base_readl(&ioc->chip->Doorbell); + doorbell = ioc->base_readl_ext_retry(&ioc->chip->Doorbell); if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) { mpt3sas_print_fault_code(ioc, doorbell); @@ -6882,7 +6899,7 @@ _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout) count = 0; cntdn = 1000 * timeout; do { - doorbell_reg = ioc->base_readl(&ioc->chip->Doorbell); + doorbell_reg = ioc->base_readl_ext_retry(&ioc->chip->Doorbell); if (!(doorbell_reg & MPI2_DOORBELL_USED)) { dhsprintk(ioc, ioc_info(ioc, "%s: successful count(%d), timeout(%d)\n", @@ -7030,7 +7047,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, __le32 *mfp; /* make sure doorbell is not in use */ - if ((ioc->base_readl(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) { + if ((ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) { ioc_err(ioc, "doorbell is in use (line=%d)\n", __LINE__); return -EFAULT; } @@ -7079,7 +7096,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, } /* read the first two 16-bits, it gives the total length of the reply */ - reply[0] = le16_to_cpu(ioc->base_readl(&ioc->chip->Doorbell) + reply[0] = le16_to_cpu(ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); if ((_base_wait_for_doorbell_int(ioc, 5))) { @@ -7087,7 +7104,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, __LINE__); return -EFAULT; } - reply[1] = le16_to_cpu(ioc->base_readl(&ioc->chip->Doorbell) + reply[1] = le16_to_cpu(ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); @@ -7098,10 +7115,10 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, return -EFAULT; } if (i >= reply_bytes/2) /* overflow case */ - ioc->base_readl(&ioc->chip->Doorbell); + ioc->base_readl_ext_retry(&ioc->chip->Doorbell); else reply[i] = le16_to_cpu( - ioc->base_readl(&ioc->chip->Doorbell) + ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_DATA_MASK); writel(0, &ioc->chip->HostInterruptStatus); } @@ -7960,7 +7977,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc) goto out; } - host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic); + host_diagnostic = ioc->base_readl_ext_retry(&ioc->chip->HostDiagnostic); drsprintk(ioc, ioc_info(ioc, "wrote magic sequence: count(%d), host_diagnostic(0x%08x)\n", count, host_diagnostic)); @@ -7980,7 +7997,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc) for (count = 0; count < (300000000 / MPI2_HARD_RESET_PCIE_SECOND_READ_DELAY_MICRO_SEC); count++) { - host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic); + host_diagnostic = ioc->base_readl_ext_retry(&ioc->chip->HostDiagnostic); if (host_diagnostic == 0xFFFFFFFF) { ioc_info(ioc, @@ -8370,10 +8387,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->rdpq_array_enable_assigned = 0; ioc->use_32bit_dma = false; ioc->dma_mask = 64; - if (ioc->is_aero_ioc) + if (ioc->is_aero_ioc) { ioc->base_readl = &_base_readl_aero; - else + ioc->base_readl_ext_retry = &_base_readl_ext_retry; + } else { ioc->base_readl = &_base_readl; + ioc->base_readl_ext_retry = &_base_readl; + } r = mpt3sas_base_map_resources(ioc); if (r) goto out_free_resources; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 05364aa15ecd..10055c7e4a9f 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1618,6 +1618,7 @@ struct MPT3SAS_ADAPTER { u8 diag_trigger_active; u8 atomic_desc_capable; BASE_READ_REG base_readl; + BASE_READ_REG base_readl_ext_retry; struct SL_WH_MASTER_TRIGGER_T diag_trigger_master; struct SL_WH_EVENT_TRIGGERS_T diag_trigger_event; struct SL_WH_SCSI_TRIGGERS_T diag_trigger_scsi; From 4443f3695d581ad1a55f2ef59259dcd0c52402b3 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Wed, 6 Sep 2023 12:08:46 +0100 Subject: [PATCH 1229/2093] PCI: Free released resource after coalescing commit 8ec9c1d5d0a5a4744516adb483b97a238892f9d5 upstream. release_resource() doesn't actually free the resource or resource list entry so free the resource list entry to avoid a leak. Closes: https://lore.kernel.org/r/878r9sga1t.fsf@kernel.org/ Fixes: e54223275ba1 ("PCI: Release resource invalidated by coalescing") Link: https://lore.kernel.org/r/20230906110846.225369-1-ross.lagerwall@citrix.com Reported-by: Kalle Valo Tested-by: Kalle Valo Signed-off-by: Ross Lagerwall Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/probe.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 843e4a58788e..0945f50fe94f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -996,6 +996,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) res = window->res; if (!res->flags && !res->start && !res->end) { release_resource(res); + resource_list_destroy_entry(window); continue; } From 223fc5352054900f70b8b5e10cfc2f297e70c512 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 16 Aug 2023 10:59:39 -0700 Subject: [PATCH 1230/2093] PCI: hv: Fix a crash in hv_pci_restore_msi_msg() during hibernation commit 04bbe863241a9be7d57fb4cf217ee4a72f480e70 upstream. When a Linux VM with an assigned PCI device runs on Hyper-V, if the PCI device driver is not loaded yet (i.e. MSI-X/MSI is not enabled on the device yet), doing a VM hibernation triggers a panic in hv_pci_restore_msi_msg() -> msi_lock_descs(&pdev->dev), because pdev->dev.msi.data is still NULL. Avoid the panic by checking if MSI-X/MSI is enabled. Link: https://lore.kernel.org/r/20230816175939.21566-1-decui@microsoft.com Fixes: dc2b453290c4 ("PCI: hv: Rework MSI handling") Signed-off-by: Dexuan Cui Signed-off-by: Lorenzo Pieralisi Reviewed-by: sathyanarayanan.kuppuswamy@linux.intel.com Reviewed-by: Michael Kelley Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-hyperv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 3351863352d3..9693bab59bf7 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3930,6 +3930,9 @@ static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg) struct msi_desc *entry; int ret = 0; + if (!pdev->msi_enabled && !pdev->msix_enabled) + return 0; + msi_lock_descs(&pdev->dev); msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) { irq_data = irq_get_irq_data(entry->irq); From e95e31a8607d2672fb8c8bc1592602bfbed0f871 Mon Sep 17 00:00:00 2001 From: Feiyang Chen Date: Thu, 24 Aug 2023 09:37:38 +0800 Subject: [PATCH 1231/2093] PCI/PM: Only read PCI_PM_CTRL register when available commit 5694ba13b004eea683c6d4faeb6d6e7a9636bda0 upstream. For a device with no Power Management Capability, pci_power_up() previously returned 0 (success) if the platform was able to put the device in D0, which led to pci_set_full_power_state() trying to read PCI_PM_CTRL, even though it doesn't exist. Since dev->pm_cap == 0 in this case, pci_set_full_power_state() actually read the wrong register, interpreted it as PCI_PM_CTRL, and corrupted dev->current_state. This led to messages like this in some cases: pci 0000:01:00.0: Refused to change power state from D3hot to D0 To prevent this, make pci_power_up() always return a negative failure code if the device lacks a Power Management Capability, even if non-PCI platform power management has been able to put the device in D0. The failure will prevent pci_set_full_power_state() from trying to access PCI_PM_CTRL. Fixes: e200904b275c ("PCI/PM: Split pci_power_up()") Link: https://lore.kernel.org/r/20230824013738.1894965-1-chenfeiyang@loongson.cn Signed-off-by: Feiyang Chen Signed-off-by: Bjorn Helgaas Reviewed-by: "Rafael J. Wysocki" Cc: stable@vger.kernel.org # v5.19+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 88c437249982..835e9ea14b3a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1193,6 +1193,10 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) * * On success, return 0 or 1, depending on whether or not it is necessary to * restore the device's BARs subsequently (1 is returned in that case). + * + * On failure, return a negative error code. Always return failure if @dev + * lacks a Power Management Capability, even if the platform was able to + * put the device in D0 via non-PCI means. */ int pci_power_up(struct pci_dev *dev) { @@ -1209,9 +1213,6 @@ int pci_power_up(struct pci_dev *dev) else dev->current_state = state; - if (state == PCI_D0) - return 0; - return -EIO; } @@ -1269,8 +1270,12 @@ static int pci_set_full_power_state(struct pci_dev *dev) int ret; ret = pci_power_up(dev); - if (ret < 0) + if (ret < 0) { + if (dev->current_state == PCI_D0) + return 0; + return ret; + } pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); dev->current_state = pmcsr & PCI_PM_CTRL_STATE_MASK; From 4f4af6b8b7a23fa37decaf43b55403e6bfd8e219 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 22 Aug 2023 09:04:51 -0700 Subject: [PATCH 1232/2093] ntb: Drop packets when qp link is down commit f195a1a6fe416882984f8bd6c61afc1383171860 upstream. Currently when the transport receive packets after netdev has closed the transport returns error and triggers tx errors to be incremented and carrier to be stopped. There is no reason to return error if the device is already closed. Drop the packet and return 0. Fixes: e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers") Reported-by: Yuan Y Lu Tested-by: Yuan Y Lu Reviewed-by: Logan Gunthorpe Signed-off-by: Dave Jiang Signed-off-by: Jon Mason Signed-off-by: Greg Kroah-Hartman --- drivers/ntb/ntb_transport.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 2abd2235bbca..e58652b17b32 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -2276,9 +2276,13 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, struct ntb_queue_entry *entry; int rc; - if (!qp || !qp->link_is_up || !len) + if (!qp || !len) return -EINVAL; + /* If the qp link is down already, just ignore. */ + if (!qp->link_is_up) + return 0; + entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q); if (!entry) { qp->tx_err_no_buf++; From 88c7931f81d859713473bcdf99bf92b090ddab4d Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 22 Aug 2023 09:04:45 -0700 Subject: [PATCH 1233/2093] ntb: Clean up tx tail index on link down commit cc79bd2738c2d40aba58b2be6ce47dc0e471df0e upstream. The tx tail index is not reset when the link goes down. This causes the tail index to go out of sync when the link goes down and comes back up. Refactor the ntb_qp_link_down_reset() and reset the tail index as well. Fixes: 2849b5d70641 ("NTB: Reset transport QP link stats on down") Reported-by: Yuan Y Lu Tested-by: Yuan Y Lu Reviewed-by: Logan Gunthorpe Signed-off-by: Dave Jiang Signed-off-by: Jon Mason Signed-off-by: Greg Kroah-Hartman --- drivers/ntb/ntb_transport.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index e58652b17b32..7884ea9c7643 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -909,7 +909,7 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, return 0; } -static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp) +static void ntb_qp_link_context_reset(struct ntb_transport_qp *qp) { qp->link_is_up = false; qp->active = false; @@ -932,6 +932,13 @@ static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp) qp->tx_async = 0; } +static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp) +{ + ntb_qp_link_context_reset(qp); + if (qp->remote_rx_info) + qp->remote_rx_info->entry = qp->rx_max_entry - 1; +} + static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp) { struct ntb_transport_ctx *nt = qp->transport; @@ -1174,7 +1181,7 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt, qp->ndev = nt->ndev; qp->client_ready = false; qp->event_handler = NULL; - ntb_qp_link_down_reset(qp); + ntb_qp_link_context_reset(qp); if (mw_num < qp_count % mw_count) num_qps_mw = qp_count / mw_count + 1; From 5a3e327dc3fdf9586d3ed00f82e41b54f2c1e2af Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 22 Aug 2023 09:04:57 -0700 Subject: [PATCH 1234/2093] ntb: Fix calculation ntb_transport_tx_free_entry() commit 5a7693e6bbf19b22fd6c1d2c4b7beb0a03969e2c upstream. ntb_transport_tx_free_entry() never returns 0 with the current calculation. If head == tail, then it would return qp->tx_max_entry. Change compare to tail >= head and when they are equal, a 0 would be returned. Fixes: e74bfeedad08 ("NTB: Add flow control to the ntb_netdev") Reviewed-by: Logan Gunthorpe Signed-off-by: renlonglong Signed-off-by: Dave Jiang Signed-off-by: Jon Mason Signed-off-by: Greg Kroah-Hartman --- drivers/ntb/ntb_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 7884ea9c7643..9532108d2dce 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -2429,7 +2429,7 @@ unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp) unsigned int head = qp->tx_index; unsigned int tail = qp->remote_rx_info->entry; - return tail > head ? tail - head : qp->tx_max_entry + tail - head; + return tail >= head ? tail - head : qp->tx_max_entry + tail - head; } EXPORT_SYMBOL_GPL(ntb_transport_tx_free_entry); From 1654635bed834a5914b036a3657ba1a8bf8bf582 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 8 Sep 2023 14:55:30 -0500 Subject: [PATCH 1235/2093] Revert "PCI: Mark NVIDIA T4 GPUs to avoid bus reset" commit 5260bd6d36c83c5b269c33baaaf8c78e520908b0 upstream. This reverts commit d5af729dc2071273f14cbb94abbc60608142fd83. d5af729dc207 ("PCI: Mark NVIDIA T4 GPUs to avoid bus reset") avoided Secondary Bus Reset on the T4 because the reset seemed to not work when the T4 was directly attached to a Root Port. But NVIDIA thinks the issue is probably related to some issue with the Root Port, not with the T4. The T4 provides neither PM nor FLR reset, so masking bus reset compromises this device for assignment scenarios. Revert d5af729dc207 as requested by Wu Zongyong. This will leave SBR broken in the specific configuration Wu tested, as it was in v6.5, so Wu will debug that further. Link: https://lore.kernel.org/r/ZPqMCDWvITlOLHgJ@wuzongyong-alibaba Link: https://lore.kernel.org/r/20230908201104.GA305023@bhelgaas Signed-off-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- drivers/pci/quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index d6fe44a5270d..472fa2c8ebce 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3631,7 +3631,7 @@ static void quirk_no_bus_reset(struct pci_dev *dev) */ static void quirk_nvidia_no_bus_reset(struct pci_dev *dev) { - if ((dev->device & 0xffc0) == 0x2340 || dev->device == 0x1eb8) + if ((dev->device & 0xffc0) == 0x2340) quirk_no_bus_reset(dev); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, From 5e4e9900e6fa61302c26d028830b271997bf329f Mon Sep 17 00:00:00 2001 From: Li Lingfeng Date: Thu, 31 Aug 2023 15:59:00 +0800 Subject: [PATCH 1236/2093] block: don't add or resize partition on the disk with GENHD_FL_NO_PART commit 1a721de8489fa559ff4471f73c58bb74ac5580d3 upstream. Commit a33df75c6328 ("block: use an xarray for disk->part_tbl") remove disk_expand_part_tbl() in add_partition(), which means all kinds of devices will support extended dynamic `dev_t`. However, some devices with GENHD_FL_NO_PART are not expected to add or resize partition. Fix this by adding check of GENHD_FL_NO_PART before add or resize partition. Fixes: a33df75c6328 ("block: use an xarray for disk->part_tbl") Signed-off-by: Li Lingfeng Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230831075900.1725842-1-lilingfeng@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/ioctl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/ioctl.c b/block/ioctl.c index 9c5f637ff153..3c475e4166e9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -20,6 +20,8 @@ static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition p; long long start, length; + if (disk->flags & GENHD_FL_NO_PART) + return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) From 316a4a329a4d30eae930ec780a5c9483b65124ec Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Fri, 14 Jul 2023 00:09:58 +1000 Subject: [PATCH 1237/2093] procfs: block chmod on /proc/thread-self/comm commit ccf61486fe1e1a48e18c638d1813cda77b3c0737 upstream. Due to an oversight in commit 1b3044e39a89 ("procfs: fix pthread cross-thread naming if !PR_DUMPABLE") in switching from REG to NOD, chmod operations on /proc/thread-self/comm were no longer blocked as they are on almost all other procfs files. A very similar situation with /proc/self/environ was used to as a root exploit a long time ago, but procfs has SB_I_NOEXEC so this is simply a correctness issue. Ref: https://lwn.net/Articles/191954/ Ref: 6d76fa58b050 ("Don't allow chmod() on the /proc// files") Fixes: 1b3044e39a89 ("procfs: fix pthread cross-thread naming if !PR_DUMPABLE") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Aleksa Sarai Message-Id: <20230713141001.27046-1-cyphar@cyphar.com> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/proc/base.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 9e479d7d202b..74442e01793f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3581,7 +3581,8 @@ static int proc_tid_comm_permission(struct user_namespace *mnt_userns, } static const struct inode_operations proc_tid_comm_inode_operations = { - .permission = proc_tid_comm_permission, + .setattr = proc_setattr, + .permission = proc_tid_comm_permission, }; /* From 5ad3e534605ea9eba3c8376893fbf92127683dcc Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 18 Aug 2023 22:48:04 +0200 Subject: [PATCH 1238/2093] parisc: Fix /proc/cpuinfo output for lscpu commit 9f5ba4b3e1b3c123eeca5d2d09161e8720048b5c upstream. The lscpu command is broken since commit cab56b51ec0e ("parisc: Fix device names in /proc/iomem") added the PA pathname to all PA devices, includig the CPUs. lscpu parses /proc/cpuinfo and now believes it found different CPU types since every CPU is listed with an unique identifier (PA pathname). Fix this problem by simply dropping the PA pathname when listing the CPUs in /proc/cpuinfo. There is no need to show the pathname in this procfs file. Fixes: cab56b51ec0e ("parisc: Fix device names in /proc/iomem") Signed-off-by: Helge Deller Cc: # v4.9+ Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/processor.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index dddaaa6e7a82..1f6c776d8081 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -372,10 +372,18 @@ int show_cpuinfo (struct seq_file *m, void *v) { unsigned long cpu; + char cpu_name[60], *p; + + /* strip PA path from CPU name to not confuse lscpu */ + strlcpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name)); + p = strrchr(cpu_name, '['); + if (p) + *(--p) = 0; for_each_online_cpu(cpu) { - const struct cpuinfo_parisc *cpuinfo = &per_cpu(cpu_data, cpu); #ifdef CONFIG_SMP + const struct cpuinfo_parisc *cpuinfo = &per_cpu(cpu_data, cpu); + if (0 == cpuinfo->hpa) continue; #endif @@ -420,8 +428,7 @@ show_cpuinfo (struct seq_file *m, void *v) seq_printf(m, "model\t\t: %s - %s\n", boot_cpu_data.pdc.sys_model_name, - cpuinfo->dev ? - cpuinfo->dev->name : "Unknown"); + cpu_name); seq_printf(m, "hversion\t: 0x%08x\n" "sversion\t: 0x%08x\n", From b23c96589ff7f25ad2232524f6c74e0067be2369 Mon Sep 17 00:00:00 2001 From: Fudong Wang Date: Fri, 11 Aug 2023 08:24:59 +0800 Subject: [PATCH 1239/2093] drm/amd/display: Add smu write msg id fail retry process commit 72105dcfa3d12b5af49311f857e3490baa225135 upstream. A benchmark stress test (12-40 machines x 48hours) found that DCN315 has cases where DC writes to an indirect register to set the smu clock msg id, but when we go to read the same indirect register the returned msg id doesn't match with what we just set it to. So, to fix this retry the write until the register's value matches with the requested value. Cc: stable@vger.kernel.org # 6.1+ Fixes: f94903996140 ("drm/amd/display: Add DCN315 CLK_MGR") Reviewed-by: Charlene Liu Acked-by: Hamza Mahfooz Signed-off-by: Fudong Wang Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- .../display/dc/clk_mgr/dcn315/dcn315_smu.c | 20 +++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 925d6e13620e..1bbf85defd61 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -32,6 +32,7 @@ #define MAX_INSTANCE 6 #define MAX_SEGMENT 6 +#define SMU_REGISTER_WRITE_RETRY_COUNT 5 struct IP_BASE_INSTANCE { @@ -134,6 +135,8 @@ static int dcn315_smu_send_msg_with_param( unsigned int msg_id, unsigned int param) { uint32_t result; + uint32_t i = 0; + uint32_t read_back_data; result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000); @@ -150,10 +153,19 @@ static int dcn315_smu_send_msg_with_param( /* Set the parameter register for the SMU message, unit is Mhz */ REG_WRITE(MP1_SMN_C2PMSG_37, param); - /* Trigger the message transaction by writing the message ID */ - generic_write_indirect_reg(CTX, - REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA), - mmMP1_C2PMSG_3, msg_id); + for (i = 0; i < SMU_REGISTER_WRITE_RETRY_COUNT; i++) { + /* Trigger the message transaction by writing the message ID */ + generic_write_indirect_reg(CTX, + REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA), + mmMP1_C2PMSG_3, msg_id); + read_back_data = generic_read_indirect_reg(CTX, + REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA), + mmMP1_C2PMSG_3); + if (read_back_data == msg_id) + break; + udelay(2); + smu_print("SMU msg id write fail %x times. \n", i + 1); + } result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000); From c96c67991aac6401b4c6996093bccb704bb2ea4b Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 23 Aug 2023 02:07:02 +0000 Subject: [PATCH 1240/2093] bpf: Fix issue in verifying allow_ptr_leaks commit d75e30dddf73449bc2d10bb8e2f1a2c446bc67a2 upstream. After we converted the capabilities of our networking-bpf program from cap_sys_admin to cap_net_admin+cap_bpf, our networking-bpf program failed to start. Because it failed the bpf verifier, and the error log is "R3 pointer comparison prohibited". A simple reproducer as follows, SEC("cls-ingress") int ingress(struct __sk_buff *skb) { struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr); if ((long)(iph + 1) > (long)skb->data_end) return TC_ACT_STOLEN; return TC_ACT_OK; } Per discussion with Yonghong and Alexei [1], comparison of two packet pointers is not a pointer leak. This patch fixes it. Our local kernel is 6.1.y and we expect this fix to be backported to 6.1.y, so stable is CCed. [1]. https://lore.kernel.org/bpf/CAADnVQ+Nmspr7Si+pxWn8zkE7hX-7s93ugwC+94aXSy4uQ9vBg@mail.gmail.com/ Suggested-by: Yonghong Song Suggested-by: Alexei Starovoitov Signed-off-by: Yafang Shao Acked-by: Eduard Zingerman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230823020703.3790-2-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- kernel/bpf/verifier.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3c414e0ac819..3052680201e5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10401,6 +10401,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EINVAL; } + /* check src2 operand */ + err = check_reg_arg(env, insn->dst_reg, SRC_OP); + if (err) + return err; + + dst_reg = ®s[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); @@ -10412,12 +10418,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, if (err) return err; - if (is_pointer_value(env, insn->src_reg)) { + src_reg = ®s[insn->src_reg]; + if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) && + is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } - src_reg = ®s[insn->src_reg]; } else { if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); @@ -10425,12 +10432,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } } - /* check src2 operand */ - err = check_reg_arg(env, insn->dst_reg, SRC_OP); - if (err) - return err; - - dst_reg = ®s[insn->dst_reg]; is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; if (BPF_SRC(insn->code) == BPF_K) { From 9667854e69a7b42cd9ae0fa8a0e7bcf437644a02 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 24 Aug 2023 16:51:42 -0400 Subject: [PATCH 1241/2093] dlm: fix plock lookup when using multiple lockspaces commit 7c53e847ff5e97f033fdd31f71949807633d506b upstream. All posix lock ops, for all lockspaces (gfs2 file systems) are sent to userspace (dlm_controld) through a single misc device. The dlm_controld daemon reads the ops from the misc device and sends them to other cluster nodes using separate, per-lockspace cluster api communication channels. The ops for a single lockspace are ordered at this level, so that the results are received in the same sequence that the requests were sent. When the results are sent back to the kernel via the misc device, they are again funneled through the single misc device for all lockspaces. When the dlm code in the kernel processes the results from the misc device, these results will be returned in the same sequence that the requests were sent, on a per-lockspace basis. A recent change in this request/reply matching code missed the "per-lockspace" check (fsid comparison) when matching request and reply, so replies could be incorrectly matched to requests from other lockspaces. Cc: stable@vger.kernel.org Reported-by: Barry Marson Fixes: 57e2c2f2d94c ("fs: dlm: fix mismatch of plock results from userspace") Signed-off-by: Alexander Aring Signed-off-by: David Teigland Signed-off-by: Greg Kroah-Hartman --- fs/dlm/plock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 739e7d55c9e3..1bf5c51a4c23 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -455,7 +455,8 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, } } else { list_for_each_entry(iter, &recv_list, list) { - if (!iter->info.wait) { + if (!iter->info.wait && + iter->info.fsid == info.fsid) { op = iter; break; } @@ -467,8 +468,7 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, if (info.wait) WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); else - WARN_ON(op->info.fsid != info.fsid || - op->info.number != info.number || + WARN_ON(op->info.number != info.number || op->info.owner != info.owner || op->info.optype != info.optype); From f8a7f10a1dccf9868ff09342a73dce27501b86df Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 25 Aug 2023 15:32:41 +0200 Subject: [PATCH 1242/2093] dccp: Fix out of bounds access in DCCP error handler commit 977ad86c2a1bcaf58f01ab98df5cc145083c489c upstream. There was a previous attempt to fix an out-of-bounds access in the DCCP error handlers, but that fix assumed that the error handlers only want to access the first 8 bytes of the DCCP header. Actually, they also look at the DCCP sequence number, which is stored beyond 8 bytes, so an explicit pskb_may_pull() is required. Fixes: 6706a97fec96 ("dccp: fix out of bound access in dccp_v4_err()") Fixes: 1aa9d1a0e7ee ("ipv6: dccp: fix out of bound access in dccp_v6_err()") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/dccp/ipv4.c | 13 +++++++++---- net/dccp/ipv6.c | 15 ++++++++++----- 2 files changed, 19 insertions(+), 9 deletions(-) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index bfececa9e244..8f5d3c088111 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -255,12 +255,17 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - /* Only need dccph_dport & dccph_sport which are the first - * 4 bytes in dccp header. + /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, + * which is in byte 7 of the dccp header. * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. + * + * Later on, we want to access the sequence number fields, which are + * beyond 8 bytes, so we have to pskb_may_pull() ourselves. */ - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); + if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) + return -EINVAL; + iph = (struct iphdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet_lookup_established(net, &dccp_hashinfo, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b51ce6f8ceba..2b09e2644b13 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -74,7 +74,7 @@ static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; + const struct ipv6hdr *hdr; const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; @@ -83,12 +83,17 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - /* Only need dccph_dport & dccph_sport which are the first - * 4 bytes in dccp header. + /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, + * which is in byte 7 of the dccp header. * Our caller (icmpv6_notify()) already pulled 8 bytes for us. + * + * Later on, we want to access the sequence number fields, which are + * beyond 8 bytes, so we have to pskb_may_pull() ourselves. */ - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); + if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) + return -EINVAL; + hdr = (const struct ipv6hdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, From ba50e7773a99a109a1ea6f753b766a080d3b21cc Mon Sep 17 00:00:00 2001 From: Steve Rutherford Date: Thu, 24 Aug 2023 15:37:31 -0700 Subject: [PATCH 1243/2093] x86/sev: Make enc_dec_hypercall() accept a size instead of npages commit ac3f9c9f1b37edaa7d1a9b908bc79d843955a1a2 upstream. enc_dec_hypercall() accepted a page count instead of a size, which forced its callers to round up. As a result, non-page aligned vaddrs caused pages to be spuriously marked as decrypted via the encryption status hypercall, which in turn caused consistent corruption of pages during live migration. Live migration requires accurate encryption status information to avoid migrating pages from the wrong perspective. Fixes: 064ce6c550a0 ("mm: x86: Invoke hypercall when page encryption status is changed") Signed-off-by: Steve Rutherford Signed-off-by: Ingo Molnar Reviewed-by: Tom Lendacky Reviewed-by: Pankaj Gupta Tested-by: Ben Hillier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230824223731.2055016-1-srutherford@google.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mem_encrypt.h | 6 +++--- arch/x86/kernel/kvm.c | 4 +--- arch/x86/mm/mem_encrypt_amd.c | 13 ++++++------- 3 files changed, 10 insertions(+), 13 deletions(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 8f513372cd8d..c91326593e74 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -50,8 +50,8 @@ void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); -void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, - bool enc); +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, + unsigned long size, bool enc); void __init mem_encrypt_free_decrypted_mem(void); @@ -84,7 +84,7 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } static inline void __init -early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} +early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d4e48b4a438b..796e2f9e8761 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -972,10 +972,8 @@ static void __init kvm_init_platform(void) * Ensure that _bss_decrypted section is marked as decrypted in the * shared pages list. */ - nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted, - PAGE_SIZE); early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted, - nr_pages, 0); + __end_bss_decrypted - __start_bss_decrypted, 0); /* * If not booted using EFI, enable Live migration support. diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index ff6c0462beee..3ea0f763540a 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -288,11 +288,10 @@ static bool amd_enc_cache_flush_required(void) return !cpu_feature_enabled(X86_FEATURE_SME_COHERENT); } -static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) { #ifdef CONFIG_PARAVIRT - unsigned long sz = npages << PAGE_SHIFT; - unsigned long vaddr_end = vaddr + sz; + unsigned long vaddr_end = vaddr + size; while (vaddr < vaddr_end) { int psize, pmask, level; @@ -342,7 +341,7 @@ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool e snp_set_memory_private(vaddr, npages); if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) - enc_dec_hypercall(vaddr, npages, enc); + enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc); return true; } @@ -466,7 +465,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr, ret = 0; - early_set_mem_enc_dec_hypercall(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); + early_set_mem_enc_dec_hypercall(start, size, enc); out: __flush_tlb_all(); return ret; @@ -482,9 +481,9 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) return early_set_memory_enc_dec(vaddr, size, true); } -void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) { - enc_dec_hypercall(vaddr, npages, enc); + enc_dec_hypercall(vaddr, size, enc); } void __init sme_early_init(void) From 3d5fed8c79d9fa17671cb18e9a7b13f6a64b50fc Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 25 Aug 2023 21:44:01 +0200 Subject: [PATCH 1244/2093] r8169: fix ASPM-related issues on a number of systems with NIC version from RTL8168h commit 90ca51e8c654699b672ba61aeaa418dfb3252e5e upstream. This effectively reverts 4b5f82f6aaef. On a number of systems ASPM L1 causes tx timeouts with RTL8168h, see referenced bug report. Fixes: 4b5f82f6aaef ("r8169: enable ASPM L1/L1.1 from RTL8168h") Cc: stable@vger.kernel.org Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217814 Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/r8169_main.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index cabed1b7b45e..a9a0dca0c030 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5201,13 +5201,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Disable ASPM L1 as that cause random device stop working * problems as well as full system hangs for some PCIe devices users. - * Chips from RTL8168h partially have issues with L1.2, but seem - * to work fine with L1 and L1.1. */ if (rtl_aspm_is_safe(tp)) rc = 0; - else if (tp->mac_version >= RTL_GIGA_MAC_VER_46) - rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); else rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); tp->aspm_manageable = !rc; From 342d130205f15a3367d9ca33a846163c622ded33 Mon Sep 17 00:00:00 2001 From: Thore Sommer Date: Tue, 15 Aug 2023 14:29:42 +0300 Subject: [PATCH 1245/2093] X.509: if signature is unsupported skip validation commit ef5b52a631f8c18353e80ccab8408b963305510c upstream. When the hash algorithm for the signature is not available the digest size is 0 and the signature in the certificate is marked as unsupported. When validating a self-signed certificate, this needs to be checked, because otherwise trying to validate the signature will fail with an warning: Loading compiled-in X.509 certificates WARNING: CPU: 0 PID: 1 at crypto/rsa-pkcs1pad.c:537 \ pkcs1pad_verify+0x46/0x12c ... Problem loading in-kernel X.509 certificate (-22) Signed-off-by: Thore Sommer Cc: stable@vger.kernel.org # v4.7+ Fixes: 6c2dc5ae4ab7 ("X.509: Extract signature digest and make self-signed cert checks earlier") Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/asymmetric_keys/x509_public_key.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c index 0b4943a4592b..1815024bead3 100644 --- a/crypto/asymmetric_keys/x509_public_key.c +++ b/crypto/asymmetric_keys/x509_public_key.c @@ -117,6 +117,11 @@ int x509_check_for_self_signed(struct x509_certificate *cert) goto out; } + if (cert->unsupported_sig) { + ret = 0; + goto out; + } + ret = public_key_verify_signature(cert->pub, cert->sig); if (ret < 0) { if (ret == -ENOPKG) { From 40a1ef4bb092b2c8b7d9a6f98515331a1e2e87c9 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 23 Aug 2023 15:41:02 +0200 Subject: [PATCH 1246/2093] net: handle ARPHRD_PPP in dev_is_mac_header_xmit() commit a4f39c9f14a634e4cd35fcd338c239d11fcc73fc upstream. The goal is to support a bpf_redirect() from an ethernet device (ingress) to a ppp device (egress). The l2 header is added automatically by the ppp driver, thus the ethernet header should be removed. CC: stable@vger.kernel.org Fixes: 27b29f63058d ("bpf: add bpf_redirect() helper") Signed-off-by: Nicolas Dichtel Tested-by: Siwar Zitouni Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/if_arp.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 1ed52441972f..10a1e81434cb 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -53,6 +53,10 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: + /* PPP adds its l2 header automatically in ppp_start_xmit(). + * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). + */ + case ARPHRD_PPP: return false; default: return true; From d08b39bb3dffca258bf28900905b05e5ffdc255e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 1 Aug 2023 21:03:53 -0700 Subject: [PATCH 1247/2093] fsverity: skip PKCS#7 parser when keyring is empty commit 919dc320956ea353a7fb2d84265195ad5ef525ac upstream. If an fsverity builtin signature is given for a file but the ".fs-verity" keyring is empty, there's no real reason to run the PKCS#7 parser. Skip this to avoid the PKCS#7 attack surface when builtin signature support is configured into the kernel but is not being used. This is a hardening improvement, not a fix per se, but I've added Fixes and Cc stable to get it out to more users. Fixes: 432434c9f8e1 ("fs-verity: support builtin file signatures") Cc: stable@vger.kernel.org Reviewed-by: Jarkko Sakkinen Link: https://lore.kernel.org/r/20230820173237.2579-1-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- fs/verity/signature.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/verity/signature.c b/fs/verity/signature.c index 143a530a8008..b59de03055e1 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -54,6 +54,22 @@ int fsverity_verify_signature(const struct fsverity_info *vi, return 0; } + if (fsverity_keyring->keys.nr_leaves_on_tree == 0) { + /* + * The ".fs-verity" keyring is empty, due to builtin signatures + * being supported by the kernel but not actually being used. + * In this case, verify_pkcs7_signature() would always return an + * error, usually ENOKEY. It could also be EBADMSG if the + * PKCS#7 is malformed, but that isn't very important to + * distinguish. So, just skip to ENOKEY to avoid the attack + * surface of the PKCS#7 parser, which would otherwise be + * reachable by any task able to execute FS_IOC_ENABLE_VERITY. + */ + fsverity_err(inode, + "fs-verity keyring is empty, rejecting signed file!"); + return -ENOKEY; + } + d = kzalloc(sizeof(*d) + hash_alg->digest_size, GFP_KERNEL); if (!d) return -ENOMEM; From e6e6a5f50f58fadec397b23064b7e4830292863d Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 14 Aug 2023 15:08:53 -0500 Subject: [PATCH 1248/2093] x86/MCE: Always save CS register on AMD Zen IF Poison errors commit 4240e2ebe67941ce2c4f5c866c3af4b5ac7a0c67 upstream. The Instruction Fetch (IF) units on current AMD Zen-based systems do not guarantee a synchronous #MC is delivered for poison consumption errors. Therefore, MCG_STATUS[EIPV|RIPV] will not be set. However, the microarchitecture does guarantee that the exception is delivered within the same context. In other words, the exact rIP is not known, but the context is known to not have changed. There is no architecturally-defined method to determine this behavior. The Code Segment (CS) register is always valid on such IF unit poison errors regardless of the value of MCG_STATUS[EIPV|RIPV]. Add a quirk to save the CS register for poison consumption from the IF unit banks. This is needed to properly determine the context of the error. Otherwise, the severity grading function will assume the context is IN_KERNEL due to the m->cs value being 0 (the initialized value). This leads to unnecessary kernel panics on data poison errors due to the kernel believing the poison consumption occurred in kernel context. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230814200853.29258-1-yazen.ghannam@amd.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mce/core.c | 26 ++++++++++++++++++++++++++ arch/x86/kernel/cpu/mce/internal.h | 5 ++++- 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index e228d58ee264..f1a748da5fab 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -856,6 +856,26 @@ static noinstr bool quirk_skylake_repmov(void) return false; } +/* + * Some Zen-based Instruction Fetch Units set EIPV=RIPV=0 on poison consumption + * errors. This means mce_gather_info() will not save the "ip" and "cs" registers. + * + * However, the context is still valid, so save the "cs" register for later use. + * + * The "ip" register is truly unknown, so don't save it or fixup EIPV/RIPV. + * + * The Instruction Fetch Unit is at MCA bank 1 for all affected systems. + */ +static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 1) + return; + if (!(m->status & MCI_STATUS_POISON)) + return; + + m->cs = regs->cs; +} + /* * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. @@ -875,6 +895,9 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo if (mce_flags.snb_ifu_quirk) quirk_sandybridge_ifu(i, m, regs); + if (mce_flags.zen_ifu_quirk) + quirk_zen_ifu(i, m, regs); + m->bank = i; if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { mce_read_aux(m, i); @@ -1852,6 +1875,9 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; + if (c->x86 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; + } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 7e03f5b7f6bd..0bed57ac86c5 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -157,6 +157,9 @@ struct mce_vendor_flags { */ smca : 1, + /* Zen IFU quirk */ + zen_ifu_quirk : 1, + /* AMD-style error thresholding banks present. */ amd_threshold : 1, @@ -172,7 +175,7 @@ struct mce_vendor_flags { /* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */ skx_repmov_quirk : 1, - __reserved_0 : 56; + __reserved_0 : 55; }; extern struct mce_vendor_flags mce_flags; From a3f6c1447db81028dfa9d01efed5faa30c367547 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Thu, 3 Aug 2023 09:12:45 +0800 Subject: [PATCH 1249/2093] platform/chrome: chromeos_acpi: print hex string for ACPI_TYPE_BUFFER commit 0820debb7d489e9eb1f68b7bb69e6ae210699b3f upstream. `element->buffer.pointer` should be binary blob. `%s` doesn't work perfect for them. Print hex string for ACPI_TYPE_BUFFER. Also update the documentation to reflect this. Fixes: 0a4cad9c11ad ("platform/chrome: Add ChromeOS ACPI device driver") Cc: stable@vger.kernel.org Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230803011245.3773756-1-tzungbi@kernel.org Signed-off-by: Tzung-Bi Shih Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-driver-chromeos-acpi | 2 +- drivers/platform/chrome/chromeos_acpi.c | 31 ++++++++++++++++++- 2 files changed, 31 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-driver-chromeos-acpi b/Documentation/ABI/testing/sysfs-driver-chromeos-acpi index c308926e1568..7c8e129fc100 100644 --- a/Documentation/ABI/testing/sysfs-driver-chromeos-acpi +++ b/Documentation/ABI/testing/sysfs-driver-chromeos-acpi @@ -134,4 +134,4 @@ KernelVersion: 5.19 Description: Returns the verified boot data block shared between the firmware verification step and the kernel verification step - (binary). + (hex dump). diff --git a/drivers/platform/chrome/chromeos_acpi.c b/drivers/platform/chrome/chromeos_acpi.c index 50d8a4d4352d..1312aaaa8750 100644 --- a/drivers/platform/chrome/chromeos_acpi.c +++ b/drivers/platform/chrome/chromeos_acpi.c @@ -90,7 +90,36 @@ static int chromeos_acpi_handle_package(struct device *dev, union acpi_object *o case ACPI_TYPE_STRING: return sysfs_emit(buf, "%s\n", element->string.pointer); case ACPI_TYPE_BUFFER: - return sysfs_emit(buf, "%s\n", element->buffer.pointer); + { + int i, r, at, room_left; + const int byte_per_line = 16; + + at = 0; + room_left = PAGE_SIZE - 1; + for (i = 0; i < element->buffer.length && room_left; i += byte_per_line) { + r = hex_dump_to_buffer(element->buffer.pointer + i, + element->buffer.length - i, + byte_per_line, 1, buf + at, room_left, + false); + if (r > room_left) + goto truncating; + at += r; + room_left -= r; + + r = sysfs_emit_at(buf, at, "\n"); + if (!r) + goto truncating; + at += r; + room_left -= r; + } + + buf[at] = 0; + return at; +truncating: + dev_info_once(dev, "truncating sysfs content for %s\n", name); + sysfs_emit_at(buf, PAGE_SIZE - 4, "..\n"); + return PAGE_SIZE - 1; + } default: dev_err(dev, "element type %d not supported\n", element->type); return -EINVAL; From 351705a446214f83e63d9eb7b09ab3d123d42677 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 12 Jul 2023 16:00:11 +0200 Subject: [PATCH 1250/2093] mmc: renesas_sdhi: register irqs before registering controller commit 74f45de394d979cc7770271f92fafa53e1ed3119 upstream. IRQs should be ready to serve when we call mmc_add_host() via tmio_mmc_host_probe(). To achieve that, ensure that all irqs are masked before registering the handlers. Signed-off-by: Wolfram Sang Tested-by: Biju Das Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230712140011.18602-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/renesas_sdhi_core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index e38d0e8b8e0e..7572c5714b46 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -1006,6 +1006,8 @@ int renesas_sdhi_probe(struct platform_device *pdev, host->sdcard_irq_setbit_mask = TMIO_STAT_ALWAYS_SET_27; host->sdcard_irq_mask_all = TMIO_MASK_ALL_RCAR2; host->reset = renesas_sdhi_reset; + } else { + host->sdcard_irq_mask_all = TMIO_MASK_ALL; } /* Orginally registers were 16 bit apart, could be 32 or 64 nowadays */ @@ -1102,9 +1104,7 @@ int renesas_sdhi_probe(struct platform_device *pdev, host->ops.hs400_complete = renesas_sdhi_hs400_complete; } - ret = tmio_mmc_host_probe(host); - if (ret < 0) - goto edisclk; + sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask_all); num_irqs = platform_irq_count(pdev); if (num_irqs < 0) { @@ -1131,6 +1131,10 @@ int renesas_sdhi_probe(struct platform_device *pdev, goto eirq; } + ret = tmio_mmc_host_probe(host); + if (ret < 0) + goto edisclk; + dev_info(&pdev->dev, "%s base at %pa, max clock rate %u MHz\n", mmc_hostname(host->mmc), &res->start, host->mmc->f_max / 1000000); From e95d7a8a6edd14f8fab44c777dd7281db91f6ae2 Mon Sep 17 00:00:00 2001 From: Enlin Mu Date: Tue, 1 Aug 2023 14:04:32 +0800 Subject: [PATCH 1251/2093] pstore/ram: Check start of empty przs during init commit fe8c3623ab06603eb760444a032d426542212021 upstream. After commit 30696378f68a ("pstore/ram: Do not treat empty buffers as valid"), initialization would assume a prz was valid after seeing that the buffer_size is zero (regardless of the buffer start position). This unchecked start value means it could be outside the bounds of the buffer, leading to future access panics when written to: sysdump_panic_event+0x3b4/0x5b8 atomic_notifier_call_chain+0x54/0x90 panic+0x1c8/0x42c die+0x29c/0x2a8 die_kernel_fault+0x68/0x78 __do_kernel_fault+0x1c4/0x1e0 do_bad_area+0x40/0x100 do_translation_fault+0x68/0x80 do_mem_abort+0x68/0xf8 el1_da+0x1c/0xc0 __raw_writeb+0x38/0x174 __memcpy_toio+0x40/0xac persistent_ram_update+0x44/0x12c persistent_ram_write+0x1a8/0x1b8 ramoops_pstore_write+0x198/0x1e8 pstore_console_write+0x94/0xe0 ... To avoid this, also check if the prz start is 0 during the initialization phase. If not, the next prz sanity check case will discover it (start > size) and zap the buffer back to a sane state. Fixes: 30696378f68a ("pstore/ram: Do not treat empty buffers as valid") Cc: Yunlong Xing Cc: stable@vger.kernel.org Signed-off-by: Enlin Mu Link: https://lore.kernel.org/r/20230801060432.1307717-1-yunlong.xing@unisoc.com [kees: update commit log with backtrace and clarifications] Signed-off-by: Kees Cook Signed-off-by: Greg Kroah-Hartman --- fs/pstore/ram_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 2384de1c2d18..1e755d093d92 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -518,7 +518,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, sig ^= PERSISTENT_RAM_SIG; if (prz->buffer->sig == sig) { - if (buffer_size(prz) == 0) { + if (buffer_size(prz) == 0 && buffer_start(prz) == 0) { pr_debug("found existing empty buffer\n"); return 0; } From 8bf567b63c2afcc482041564d0ad0c4c2bf8cb09 Mon Sep 17 00:00:00 2001 From: D Scott Phillips Date: Mon, 26 Jun 2023 17:29:39 -0700 Subject: [PATCH 1252/2093] arm64: sdei: abort running SDEI handlers during crash commit 5cd474e57368f0957c343bb21e309cf82826b1ef upstream. Interrupts are blocked in SDEI context, per the SDEI spec: "The client interrupts cannot preempt the event handler." If we crashed in the SDEI handler-running context (as with ACPI's AGDI) then we need to clean up the SDEI state before proceeding to the crash kernel so that the crash kernel can have working interrupts. Track the active SDEI handler per-cpu so that we can COMPLETE_AND_RESUME the handler, discarding the interrupted context. Fixes: f5df26961853 ("arm64: kernel: Add arch-specific SDEI entry code and CPU masking") Signed-off-by: D Scott Phillips Cc: stable@vger.kernel.org Reviewed-by: James Morse Tested-by: Mihai Carabas Link: https://lore.kernel.org/r/20230627002939.2758-1-scott@os.amperecomputing.com Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/sdei.h | 6 ++++++ arch/arm64/kernel/entry.S | 27 +++++++++++++++++++++++++-- arch/arm64/kernel/sdei.c | 3 +++ arch/arm64/kernel/smp.c | 8 ++++---- drivers/firmware/arm_sdei.c | 19 +++++++++++++++++++ include/linux/arm_sdei.h | 2 ++ 6 files changed, 59 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h index 4292d9bafb9d..484cb6972e99 100644 --- a/arch/arm64/include/asm/sdei.h +++ b/arch/arm64/include/asm/sdei.h @@ -17,6 +17,9 @@ #include +DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event); +DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event); + extern unsigned long sdei_exit_mode; /* Software Delegated Exception entry point from firmware*/ @@ -29,6 +32,9 @@ asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num, unsigned long pc, unsigned long pstate); +/* Abort a running handler. Context is discarded. */ +void __sdei_handler_abort(void); + /* * The above entry point does the minimum to call C code. This function does * anything else, before calling the driver. diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 3671d9521d4f..beb4db21c89c 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -993,9 +993,13 @@ SYM_CODE_START(__sdei_asm_handler) mov x19, x1 -#if defined(CONFIG_VMAP_STACK) || defined(CONFIG_SHADOW_CALL_STACK) + /* Store the registered-event for crash_smp_send_stop() */ ldrb w4, [x19, #SDEI_EVENT_PRIORITY] -#endif + cbnz w4, 1f + adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6 + b 2f +1: adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6 +2: str x19, [x5] #ifdef CONFIG_VMAP_STACK /* @@ -1062,6 +1066,14 @@ SYM_CODE_START(__sdei_asm_handler) ldr_l x2, sdei_exit_mode + /* Clear the registered-event seen by crash_smp_send_stop() */ + ldrb w3, [x4, #SDEI_EVENT_PRIORITY] + cbnz w3, 1f + adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6 + b 2f +1: adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6 +2: str xzr, [x5] + alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 sdei_handler_exit exit_mode=x2 alternative_else_nop_endif @@ -1072,4 +1084,15 @@ alternative_else_nop_endif #endif SYM_CODE_END(__sdei_asm_handler) NOKPROBE(__sdei_asm_handler) + +SYM_CODE_START(__sdei_handler_abort) + mov_q x0, SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME + adr x1, 1f + ldr_l x2, sdei_exit_mode + sdei_handler_exit exit_mode=x2 + // exit the handler and jump to the next instruction. + // Exit will stomp x0-x17, PSTATE, ELR_ELx, and SPSR_ELx. +1: ret +SYM_CODE_END(__sdei_handler_abort) +NOKPROBE(__sdei_handler_abort) #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index d56e170e1ca7..48c6457b67db 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -47,6 +47,9 @@ DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr); DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr); #endif +DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event); +DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event); + static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu) { unsigned long *p; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index ffc5d76cf695..d323621d14a5 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -1047,10 +1047,8 @@ void crash_smp_send_stop(void) * If this cpu is the only one alive at this point in time, online or * not, there are no stop messages to be sent around, so just back out. */ - if (num_other_online_cpus() == 0) { - sdei_mask_local_cpu(); - return; - } + if (num_other_online_cpus() == 0) + goto skip_ipi; cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); @@ -1069,7 +1067,9 @@ void crash_smp_send_stop(void) pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", cpumask_pr_args(&mask)); +skip_ipi: sdei_mask_local_cpu(); + sdei_handler_abort(); } bool smp_crash_stop_failed(void) diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index f9040bd61081..285fe7ad490d 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -1095,3 +1095,22 @@ int sdei_event_handler(struct pt_regs *regs, return err; } NOKPROBE_SYMBOL(sdei_event_handler); + +void sdei_handler_abort(void) +{ + /* + * If the crash happened in an SDEI event handler then we need to + * finish the handler with the firmware so that we can have working + * interrupts in the crash kernel. + */ + if (__this_cpu_read(sdei_active_critical_event)) { + pr_warn("still in SDEI critical event context, attempting to finish handler.\n"); + __sdei_handler_abort(); + __this_cpu_write(sdei_active_critical_event, NULL); + } + if (__this_cpu_read(sdei_active_normal_event)) { + pr_warn("still in SDEI normal event context, attempting to finish handler.\n"); + __sdei_handler_abort(); + __this_cpu_write(sdei_active_normal_event, NULL); + } +} diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 14dc461b0e82..255701e1251b 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -47,10 +47,12 @@ int sdei_unregister_ghes(struct ghes *ghes); int sdei_mask_local_cpu(void); int sdei_unmask_local_cpu(void); void __init sdei_init(void); +void sdei_handler_abort(void); #else static inline int sdei_mask_local_cpu(void) { return 0; } static inline int sdei_unmask_local_cpu(void) { return 0; } static inline void sdei_init(void) { } +static inline void sdei_handler_abort(void) { } #endif /* CONFIG_ARM_SDE_INTERFACE */ From 6489ec0107860345bc57dcde39e63dfb05ac5c11 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 10 Aug 2023 10:22:36 +0200 Subject: [PATCH 1253/2093] s390/dcssblk: fix kernel crash with list_add corruption commit c8f40a0bccefd613748d080147469a4652d6e74c upstream. Commit fb08a1908cb1 ("dax: simplify the dax_device <-> gendisk association") introduced new logic for gendisk association, requiring drivers to explicitly call dax_add_host() and dax_remove_host(). For dcssblk driver, some dax_remove_host() calls were missing, e.g. in device remove path. The commit also broke error handling for out_dax case in device add path, resulting in an extra put_device() w/o the previous get_device() in that case. This lead to stale xarray entries after device add / remove cycles. In the case when a previously used struct gendisk pointer (xarray index) would be used again, because blk_alloc_disk() happened to return such a pointer, the xa_insert() in dax_add_host() would fail and go to out_dax, doing the extra put_device() in the error path. In combination with an already flawed error handling in dcssblk (device_register() cleanup), which needs to be addressed in a separate patch, this resulted in a missing device_del() / klist_del(), and eventually in the kernel crash with list_add corruption on a subsequent device_add() / klist_add(). Fix this by adding the missing dax_remove_host() calls, and also move the put_device() in the error path to restore the previous logic. Fixes: fb08a1908cb1 ("dax: simplify the dax_device <-> gendisk association") Cc: # 5.17+ Acked-by: Heiko Carstens Signed-off-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- drivers/s390/block/dcssblk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index c0f85ffb2b62..735ee0ca4a13 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -411,6 +411,7 @@ dcssblk_shared_store(struct device *dev, struct device_attribute *attr, const ch } list_del(&dev_info->lh); + dax_remove_host(dev_info->gd); kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); del_gendisk(dev_info->gd); @@ -706,9 +707,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char goto out; out_dax_host: + put_device(&dev_info->dev); dax_remove_host(dev_info->gd); out_dax: - put_device(&dev_info->dev); kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); put_dev: @@ -788,6 +789,7 @@ dcssblk_remove_store(struct device *dev, struct device_attribute *attr, const ch } list_del(&dev_info->lh); + dax_remove_host(dev_info->gd); kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); del_gendisk(dev_info->gd); From f9a3d6f037c96b7cded7d75b3a766f55b78829dc Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 15 Aug 2023 09:26:06 +0200 Subject: [PATCH 1254/2093] s390/ipl: add missing secure/has_secure file to ipl type 'unknown' commit ea5717cb13468323a7c3dd394748301802991f39 upstream. OS installers are relying on /sys/firmware/ipl/has_secure to be present on machines supporting secure boot. This file is present for all IPL types, but not the unknown type, which prevents a secure installation when an LPAR is booted in HMC via FTP(s), because this is an unknown IPL type in linux. While at it, also add the secure file. Fixes: c9896acc7851 ("s390/ipl: Provide has_secure sysfs attribute") Cc: stable@vger.kernel.org Signed-off-by: Sven Schnelle Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/ipl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 325cbf69ebbd..df5d2ec737d8 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -503,6 +503,8 @@ static struct attribute_group ipl_ccw_attr_group_lpar = { static struct attribute *ipl_unknown_attrs[] = { &sys_ipl_type_attr.attr, + &sys_ipl_secure_attr.attr, + &sys_ipl_has_secure_attr.attr, NULL, }; From 73e64c5eeddf441e761699eda32f6a4557c08ba9 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 28 Aug 2023 17:31:42 +0200 Subject: [PATCH 1255/2093] s390/dasd: fix string length handling commit f7cf22424665043787a96a66a048ff6b2cfd473c upstream. Building dasd_eckd.o with latest clang reveals this bug: CC drivers/s390/block/dasd_eckd.o drivers/s390/block/dasd_eckd.c:1082:3: warning: 'snprintf' will always be truncated; specified size is 1, but format string expands to at least 11 [-Wfortify-source] 1082 | snprintf(print_uid, sizeof(*print_uid), | ^ drivers/s390/block/dasd_eckd.c:1087:3: warning: 'snprintf' will always be truncated; specified size is 1, but format string expands to at least 10 [-Wfortify-source] 1087 | snprintf(print_uid, sizeof(*print_uid), | ^ Fix this by moving and using the existing UID_STRLEN for the arrays that are being written to. Also rename UID_STRLEN to DASD_UID_STRLEN to clarify its scope. Fixes: 23596961b437 ("s390/dasd: split up dasd_eckd_read_conf") Reviewed-by: Peter Oberparleiter Signed-off-by: Heiko Carstens Tested-by: Nick Desaulniers # build Reported-by: Nathan Chancellor Closes: https://github.com/ClangBuiltLinux/linux/issues/1923 Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20230828153142.2843753-2-hca@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/s390/block/dasd_devmap.c | 6 +----- drivers/s390/block/dasd_eckd.c | 10 +++++----- drivers/s390/block/dasd_int.h | 4 ++++ 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index df17f0f9cb0f..b2a4c3433057 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -1377,16 +1377,12 @@ static ssize_t dasd_vendor_show(struct device *dev, static DEVICE_ATTR(vendor, 0444, dasd_vendor_show, NULL); -#define UID_STRLEN ( /* vendor */ 3 + 1 + /* serial */ 14 + 1 +\ - /* SSID */ 4 + 1 + /* unit addr */ 2 + 1 +\ - /* vduit */ 32 + 1) - static ssize_t dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf) { + char uid_string[DASD_UID_STRLEN]; struct dasd_device *device; struct dasd_uid uid; - char uid_string[UID_STRLEN]; char ua_string[3]; device = dasd_device_from_cdev(to_ccwdev(dev)); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 792e5d245bc3..c5619751a065 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1079,12 +1079,12 @@ static void dasd_eckd_get_uid_string(struct dasd_conf *conf, create_uid(conf, &uid); if (strlen(uid.vduit) > 0) - snprintf(print_uid, sizeof(*print_uid), + snprintf(print_uid, DASD_UID_STRLEN, "%s.%s.%04x.%02x.%s", uid.vendor, uid.serial, uid.ssid, uid.real_unit_addr, uid.vduit); else - snprintf(print_uid, sizeof(*print_uid), + snprintf(print_uid, DASD_UID_STRLEN, "%s.%s.%04x.%02x", uid.vendor, uid.serial, uid.ssid, uid.real_unit_addr); @@ -1093,8 +1093,8 @@ static void dasd_eckd_get_uid_string(struct dasd_conf *conf, static int dasd_eckd_check_cabling(struct dasd_device *device, void *conf_data, __u8 lpm) { + char print_path_uid[DASD_UID_STRLEN], print_device_uid[DASD_UID_STRLEN]; struct dasd_eckd_private *private = device->private; - char print_path_uid[60], print_device_uid[60]; struct dasd_conf path_conf; path_conf.data = conf_data; @@ -1293,9 +1293,9 @@ static void dasd_eckd_path_available_action(struct dasd_device *device, __u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE]; __u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm; struct dasd_conf_data *conf_data; + char print_uid[DASD_UID_STRLEN]; struct dasd_conf path_conf; unsigned long flags; - char print_uid[60]; int rc, pos; opm = 0; @@ -5856,8 +5856,8 @@ static void dasd_eckd_dump_sense(struct dasd_device *device, static int dasd_eckd_reload_device(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + char print_uid[DASD_UID_STRLEN]; int rc, old_base; - char print_uid[60]; struct dasd_uid uid; unsigned long flags; diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 97adc8a7ae6b..f50932518f83 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -259,6 +259,10 @@ struct dasd_uid { char vduit[33]; }; +#define DASD_UID_STRLEN ( /* vendor */ 3 + 1 + /* serial */ 14 + 1 + \ + /* SSID */ 4 + 1 + /* unit addr */ 2 + 1 + \ + /* vduit */ 32 + 1) + /* * PPRC Status data */ From 08c86156361c97849a465746e78d57c00597c8e2 Mon Sep 17 00:00:00 2001 From: Thomas Bourgoin Date: Thu, 13 Jul 2023 17:15:15 +0200 Subject: [PATCH 1256/2093] crypto: stm32 - fix loop iterating through scatterlist for DMA commit d9c83f71eeceed2cb54bb78be84f2d4055fd9a1f upstream. We were reading the length of the scatterlist sg after copying value of tsg inside. So we are using the size of the previous scatterlist and for the first one we are using an unitialised value. Fix this by copying tsg in sg[0] before reading the size. Fixes : 8a1012d3f2ab ("crypto: stm32 - Support for STM32 HASH module") Cc: stable@vger.kernel.org Signed-off-by: Thomas Bourgoin Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/stm32/stm32-hash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c index e3f765434d64..4df5330afaa1 100644 --- a/drivers/crypto/stm32/stm32-hash.c +++ b/drivers/crypto/stm32/stm32-hash.c @@ -565,9 +565,9 @@ static int stm32_hash_dma_send(struct stm32_hash_dev *hdev) } for_each_sg(rctx->sg, tsg, rctx->nents, i) { + sg[0] = *tsg; len = sg->length; - sg[0] = *tsg; if (sg_is_last(sg)) { if (hdev->dma_mode == 1) { len = (ALIGN(sg->length, 16) - 16); From 7f3d84cfaec7bdbae4e2284de4cf1ddfeb5e3239 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 31 Jul 2023 21:15:48 -0600 Subject: [PATCH 1257/2093] cpufreq: brcmstb-avs-cpufreq: Fix -Warray-bounds bug commit e520d0b6be950ce3738cf4b9bd3b392be818f1dc upstream. Allocate extra space for terminating element at: drivers/cpufreq/brcmstb-avs-cpufreq.c: 449 table[i].frequency = CPUFREQ_TABLE_END; and add code comment to make this clear. This fixes the following -Warray-bounds warning seen after building ARM with multi_v7_defconfig (GCC 13): In function 'brcm_avs_get_freq_table', inlined from 'brcm_avs_cpufreq_init' at drivers/cpufreq/brcmstb-avs-cpufreq.c:623:15: drivers/cpufreq/brcmstb-avs-cpufreq.c:449:28: warning: array subscript 5 is outside array bounds of 'void[60]' [-Warray-bounds=] 449 | table[i].frequency = CPUFREQ_TABLE_END; In file included from include/linux/node.h:18, from include/linux/cpu.h:17, from include/linux/cpufreq.h:12, from drivers/cpufreq/brcmstb-avs-cpufreq.c:44: In function 'devm_kmalloc_array', inlined from 'devm_kcalloc' at include/linux/device.h:328:9, inlined from 'brcm_avs_get_freq_table' at drivers/cpufreq/brcmstb-avs-cpufreq.c:437:10, inlined from 'brcm_avs_cpufreq_init' at drivers/cpufreq/brcmstb-avs-cpufreq.c:623:15: include/linux/device.h:323:16: note: at offset 60 into object of size 60 allocated by 'devm_kmalloc' 323 | return devm_kmalloc(dev, bytes, flags); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help us make progress towards globally enabling -Warray-bounds. Link: https://github.com/KSPP/linux/issues/324 Fixes: de322e085995 ("cpufreq: brcmstb-avs-cpufreq: AVS CPUfreq driver for Broadcom STB SoCs") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Reviewed-by: Florian Fainelli Signed-off-by: Viresh Kumar Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/brcmstb-avs-cpufreq.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 4153150e20db..f644c5e325fb 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -434,7 +434,11 @@ brcm_avs_get_freq_table(struct device *dev, struct private_data *priv) if (ret) return ERR_PTR(ret); - table = devm_kcalloc(dev, AVS_PSTATE_MAX + 1, sizeof(*table), + /* + * We allocate space for the 5 different P-STATES AVS, + * plus extra space for a terminating element. + */ + table = devm_kcalloc(dev, AVS_PSTATE_MAX + 1 + 1, sizeof(*table), GFP_KERNEL); if (!table) return ERR_PTR(-ENOMEM); From 33a31064211cd7183700df7c1a7952884c8e7493 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 27 Jul 2023 10:16:31 -0700 Subject: [PATCH 1258/2093] of: property: fw_devlink: Add a devlink for panel followers commit fbf0ea2da3c7cd0b33ed7ae53a67ab1c24838cba upstream. Inform fw_devlink of the fact that a panel follower (like a touchscreen) is effectively a consumer of the panel from the purposes of fw_devlink. NOTE: this patch isn't required for correctness but instead optimizes probe order / helps avoid deferrals. Acked-by: Rob Herring Reviewed-by: Maxime Ripard Signed-off-by: Douglas Anderson Link: https://patchwork.freedesktop.org/patch/msgid/20230727101636.v4.4.Ibf8e1342b5b7906279db2365aca45e6253857bb3@changeid Cc: Adam Ford Signed-off-by: Greg Kroah-Hartman --- drivers/of/property.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/of/property.c b/drivers/of/property.c index c651aad6f34b..b636777e6f7c 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1266,6 +1266,7 @@ DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells") DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells") DEFINE_SIMPLE_PROP(leds, "leds", NULL) DEFINE_SIMPLE_PROP(backlight, "backlight", NULL) +DEFINE_SIMPLE_PROP(panel, "panel", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") @@ -1354,6 +1355,7 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_resets, }, { .parse_prop = parse_leds, }, { .parse_prop = parse_backlight, }, + { .parse_prop = parse_panel, }, { .parse_prop = parse_gpio_compat, }, { .parse_prop = parse_interrupts, }, { .parse_prop = parse_regulators, }, From 9b7cd3fe01f0d03cf5820b351a6be2a6e0a6da6f Mon Sep 17 00:00:00 2001 From: RD Babiera Date: Mon, 31 Jul 2023 16:59:23 +0000 Subject: [PATCH 1259/2093] usb: typec: tcpm: set initial svdm version based on pd revision commit c97cd0b4b54eb42aed7f6c3c295a2d137f6d2416 upstream. When sending Discover Identity messages to a Port Partner that uses Power Delivery v2 and SVDM v1, we currently send PD v2 messages with SVDM v2.0, expecting the port partner to respond with its highest supported SVDM version as stated in Section 6.4.4.2.3 in the Power Delivery v3 specification. However, sending SVDM v2 to some Power Delivery v2 port partners results in a NAK whereas sending SVDM v1 does not. NAK messages can be handled by the initiator (PD v3 section 6.4.4.2.5.1), and one solution could be to resend Discover Identity on a lower SVDM version if possible. But, Section 6.4.4.3 of PD v2 states that "A NAK response Should be taken as an indication not to retry that particular Command." Instead, we can set the SVDM version to the maximum one supported by the negotiated PD revision. When operating in PD v2, this obeys Section 6.4.4.2.3, which states the SVDM field "Shall be set to zero to indicate Version 1.0." In PD v3, the SVDM field "Shall be set to 01b to indicate Version 2.0." Fixes: c34e85fa69b9 ("usb: typec: tcpm: Send DISCOVER_IDENTITY from dedicated work") Cc: stable@vger.kernel.org Signed-off-by: RD Babiera Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230731165926.1815338-1-rdbabiera@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 5f45b82dd191..b2265fcd2197 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -3929,6 +3929,29 @@ static enum typec_cc_status tcpm_pwr_opmode_to_rp(enum typec_pwr_opmode opmode) } } +static void tcpm_set_initial_svdm_version(struct tcpm_port *port) +{ + switch (port->negotiated_rev) { + case PD_REV30: + break; + /* + * 6.4.4.2.3 Structured VDM Version + * 2.0 states "At this time, there is only one version (1.0) defined. + * This field Shall be set to zero to indicate Version 1.0." + * 3.0 states "This field Shall be set to 01b to indicate Version 2.0." + * To ensure that we follow the Power Delivery revision we are currently + * operating on, downgrade the SVDM version to the highest one supported + * by the Power Delivery revision. + */ + case PD_REV20: + typec_partner_set_svdm_version(port->partner, SVDM_VER_1_0); + break; + default: + typec_partner_set_svdm_version(port->partner, SVDM_VER_1_0); + break; + } +} + static void run_state_machine(struct tcpm_port *port) { int ret; @@ -4153,10 +4176,12 @@ static void run_state_machine(struct tcpm_port *port) * For now, this driver only supports SOP for DISCOVER_IDENTITY, thus using * port->explicit_contract to decide whether to send the command. */ - if (port->explicit_contract) + if (port->explicit_contract) { + tcpm_set_initial_svdm_version(port); mod_send_discover_delayed_work(port, 0); - else + } else { port->send_discover = false; + } /* * 6.3.5 @@ -4439,10 +4464,12 @@ static void run_state_machine(struct tcpm_port *port) * For now, this driver only supports SOP for DISCOVER_IDENTITY, thus using * port->explicit_contract. */ - if (port->explicit_contract) + if (port->explicit_contract) { + tcpm_set_initial_svdm_version(port); mod_send_discover_delayed_work(port, 0); - else + } else { port->send_discover = false; + } power_supply_changed(port->psy); break; From 0d3b5fe47938e9c451466845304a2bd74e967a80 Mon Sep 17 00:00:00 2001 From: RD Babiera Date: Mon, 14 Aug 2023 18:05:59 +0000 Subject: [PATCH 1260/2093] usb: typec: bus: verify partner exists in typec_altmode_attention commit f23643306430f86e2f413ee2b986e0773e79da31 upstream. Some usb hubs will negotiate DisplayPort Alt mode with the device but will then negotiate a data role swap after entering the alt mode. The data role swap causes the device to unregister all alt modes, however the usb hub will still send Attention messages even after failing to reregister the Alt Mode. type_altmode_attention currently does not verify whether or not a device's altmode partner exists, which results in a NULL pointer error when dereferencing the typec_altmode and typec_altmode_ops belonging to the altmode partner. Verify the presence of a device's altmode partner before sending the Attention message to the Alt Mode driver. Fixes: 8a37d87d72f0 ("usb: typec: Bus type for alternate modes") Cc: stable@vger.kernel.org Signed-off-by: RD Babiera Reviewed-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230814180559.923475-1-rdbabiera@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/bus.c | 12 ++++++++++-- drivers/usb/typec/tcpm/tcpm.c | 3 ++- include/linux/usb/typec_altmode.h | 2 +- 3 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 31c2a3130cad..69442a813585 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -154,12 +154,20 @@ EXPORT_SYMBOL_GPL(typec_altmode_exit); * * Notifies the partner of @adev about Attention command. */ -void typec_altmode_attention(struct typec_altmode *adev, u32 vdo) +int typec_altmode_attention(struct typec_altmode *adev, u32 vdo) { - struct typec_altmode *pdev = &to_altmode(adev)->partner->adev; + struct altmode *partner = to_altmode(adev)->partner; + struct typec_altmode *pdev; + + if (!partner) + return -ENODEV; + + pdev = &partner->adev; if (pdev->ops && pdev->ops->attention) pdev->ops->attention(pdev, vdo); + + return 0; } EXPORT_SYMBOL_GPL(typec_altmode_attention); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index b2265fcd2197..ad4d0314d27f 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1871,7 +1871,8 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port, } break; case ADEV_ATTENTION: - typec_altmode_attention(adev, p[1]); + if (typec_altmode_attention(adev, p[1])) + tcpm_log(port, "typec_altmode_attention no port partner altmode"); break; } } diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 350d49012659..28aeef8f9e7b 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -67,7 +67,7 @@ struct typec_altmode_ops { int typec_altmode_enter(struct typec_altmode *altmode, u32 *vdo); int typec_altmode_exit(struct typec_altmode *altmode); -void typec_altmode_attention(struct typec_altmode *altmode, u32 vdo); +int typec_altmode_attention(struct typec_altmode *altmode, u32 vdo); int typec_altmode_vdm(struct typec_altmode *altmode, const u32 header, const u32 *vdo, int count); int typec_altmode_notify(struct typec_altmode *altmode, unsigned long conf, From 90b01f8df56844cb4ac8f188eed92a5ee866020a Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 4 Aug 2023 15:10:59 -0400 Subject: [PATCH 1261/2093] USB: core: Unite old scheme and new scheme descriptor reads commit 85d07c55621676d47d873d2749b88f783cd4d5a1 upstream. In preparation for reworking the usb_get_device_descriptor() routine, it is desirable to unite the two different code paths responsible for initially determining endpoint 0's maximum packet size in a newly discovered USB device. Making this determination presents a chicken-and-egg sort of problem, in that the only way to learn the maxpacket value is to get it from the device descriptor retrieved from the device, but communicating with the device to retrieve a descriptor requires us to know beforehand the ep0 maxpacket size. In practice this problem is solved in two different ways, referred to in hub.c as the "old scheme" and the "new scheme". The old scheme (which is the approach recommended by the USB-2 spec) involves asking the device to send just the first eight bytes of its device descriptor. Such a transfer uses packets containing no more than eight bytes each, and every USB device must have an ep0 maxpacket size >= 8, so this should succeed. Since the bMaxPacketSize0 field of the device descriptor lies within the first eight bytes, this is all we need. The new scheme is an imitation of the technique used in an early Windows USB implementation, giving it the happy advantage of working with a wide variety of devices (some of them at the time would not work with the old scheme, although that's probably less true now). It involves making an initial guess of the ep0 maxpacket size, asking the device to send up to 64 bytes worth of its device descriptor (which is only 18 bytes long), and then resetting the device to clear any error condition that might have resulted from the guess being wrong. The initial guess is determined by the connection speed; it should be correct in all cases other than full speed, for which the allowed values are 8, 16, 32, and 64 (in this case the initial guess is 64). The reason for this patch is that the old- and new-scheme parts of hub_port_init() use different code paths, one involving usb_get_device_descriptor() and one not, for their initial reads of the device descriptor. Since these reads have essentially the same purpose and are made under essentially the same circumstances, this is illogical. It makes more sense to have both of them use a common subroutine. This subroutine does basically what the new scheme's code did, because that approach is more general than the one used by the old scheme. It only needs to know how many bytes to transfer and whether or not it is being called for the first iteration of a retry loop (in case of certain time-out errors). There are two main differences from the former code: We initialize the bDescriptorType field of the transfer buffer to 0 before performing the transfer, to avoid possibly accessing an uninitialized value afterward. We read the device descriptor into a temporary buffer rather than storing it directly into udev->descriptor, which the old scheme implementation used to do. Since the whole point of this first read of the device descriptor is to determine the bMaxPacketSize0 value, that is what the new routine returns (or an error code). The value is stored in a local variable rather than in udev->descriptor. As a side effect, this necessitates moving a section of code that checks the bcdUSB field for SuperSpeed devices until after the full device descriptor has been retrieved. Signed-off-by: Alan Stern Cc: Oliver Neukum Link: https://lore.kernel.org/r/495cb5d4-f956-4f4a-a875-1e67e9489510@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 173 ++++++++++++++++++++++------------------- 1 file changed, 94 insertions(+), 79 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 1abe43ddb75f..7266ca0da80a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4661,6 +4661,67 @@ static int hub_enable_device(struct usb_device *udev) return hcd->driver->enable_device(hcd, udev); } +/* + * Get the bMaxPacketSize0 value during initialization by reading the + * device's device descriptor. Since we don't already know this value, + * the transfer is unsafe and it ignores I/O errors, only testing for + * reasonable received values. + * + * For "old scheme" initialization, size will be 8 so we read just the + * start of the device descriptor, which should work okay regardless of + * the actual bMaxPacketSize0 value. For "new scheme" initialization, + * size will be 64 (and buf will point to a sufficiently large buffer), + * which might not be kosher according to the USB spec but it's what + * Windows does and what many devices expect. + * + * Returns: bMaxPacketSize0 or a negative error code. + */ +static int get_bMaxPacketSize0(struct usb_device *udev, + struct usb_device_descriptor *buf, int size, bool first_time) +{ + int i, rc; + + /* + * Retry on all errors; some devices are flakey. + * 255 is for WUSB devices, we actually need to use + * 512 (WUSB1.0[4.8.1]). + */ + for (i = 0; i < GET_MAXPACKET0_TRIES; ++i) { + /* Start with invalid values in case the transfer fails */ + buf->bDescriptorType = buf->bMaxPacketSize0 = 0; + rc = usb_control_msg(udev, usb_rcvaddr0pipe(), + USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, + USB_DT_DEVICE << 8, 0, + buf, size, + initial_descriptor_timeout); + switch (buf->bMaxPacketSize0) { + case 8: case 16: case 32: case 64: case 255: + if (buf->bDescriptorType == USB_DT_DEVICE) { + rc = buf->bMaxPacketSize0; + break; + } + fallthrough; + default: + if (rc >= 0) + rc = -EPROTO; + break; + } + + /* + * Some devices time out if they are powered on + * when already connected. They need a second + * reset, so return early. But only on the first + * attempt, lest we get into a time-out/reset loop. + */ + if (rc > 0 || (rc == -ETIMEDOUT && first_time && + udev->speed > USB_SPEED_FULL)) + break; + } + return rc; +} + +#define GET_DESCRIPTOR_BUFSIZE 64 + /* Reset device, (re)assign address, get device descriptor. * Device connection must be stable, no more debouncing needed. * Returns device in USB_STATE_ADDRESS, except on error. @@ -4685,6 +4746,12 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, int devnum = udev->devnum; const char *driver_name; bool do_new_scheme; + int maxp0; + struct usb_device_descriptor *buf; + + buf = kmalloc(GET_DESCRIPTOR_BUFSIZE, GFP_NOIO); + if (!buf) + return -ENOMEM; /* root hub ports have a slightly longer reset period * (from USB 2.0 spec, section 7.1.7.5) @@ -4799,9 +4866,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, for (retries = 0; retries < GET_DESCRIPTOR_TRIES; (++retries, msleep(100))) { if (do_new_scheme) { - struct usb_device_descriptor *buf; - int r = 0; - retval = hub_enable_device(udev); if (retval < 0) { dev_err(&udev->dev, @@ -4810,52 +4874,8 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, goto fail; } -#define GET_DESCRIPTOR_BUFSIZE 64 - buf = kmalloc(GET_DESCRIPTOR_BUFSIZE, GFP_NOIO); - if (!buf) { - retval = -ENOMEM; - continue; - } - - /* Retry on all errors; some devices are flakey. - * 255 is for WUSB devices, we actually need to use - * 512 (WUSB1.0[4.8.1]). - */ - for (operations = 0; operations < GET_MAXPACKET0_TRIES; - ++operations) { - buf->bMaxPacketSize0 = 0; - r = usb_control_msg(udev, usb_rcvaddr0pipe(), - USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, - USB_DT_DEVICE << 8, 0, - buf, GET_DESCRIPTOR_BUFSIZE, - initial_descriptor_timeout); - switch (buf->bMaxPacketSize0) { - case 8: case 16: case 32: case 64: case 255: - if (buf->bDescriptorType == - USB_DT_DEVICE) { - r = 0; - break; - } - fallthrough; - default: - if (r == 0) - r = -EPROTO; - break; - } - /* - * Some devices time out if they are powered on - * when already connected. They need a second - * reset. But only on the first attempt, - * lest we get into a time out/reset loop - */ - if (r == 0 || (r == -ETIMEDOUT && - retries == 0 && - udev->speed > USB_SPEED_FULL)) - break; - } - udev->descriptor.bMaxPacketSize0 = - buf->bMaxPacketSize0; - kfree(buf); + maxp0 = get_bMaxPacketSize0(udev, buf, + GET_DESCRIPTOR_BUFSIZE, retries == 0); retval = hub_port_reset(hub, port1, udev, delay, false); if (retval < 0) /* error or disconnect */ @@ -4866,14 +4886,13 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, retval = -ENODEV; goto fail; } - if (r) { - if (r != -ENODEV) + if (maxp0 < 0) { + if (maxp0 != -ENODEV) dev_err(&udev->dev, "device descriptor read/64, error %d\n", - r); - retval = -EMSGSIZE; + maxp0); + retval = maxp0; continue; } -#undef GET_DESCRIPTOR_BUFSIZE } /* @@ -4919,19 +4938,17 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, break; } - retval = usb_get_device_descriptor(udev, 8); - if (retval < 8) { + /* !do_new_scheme || wusb */ + maxp0 = get_bMaxPacketSize0(udev, buf, 8, retries == 0); + if (maxp0 < 0) { + retval = maxp0; if (retval != -ENODEV) dev_err(&udev->dev, "device descriptor read/8, error %d\n", retval); - if (retval >= 0) - retval = -EMSGSIZE; } else { u32 delay; - retval = 0; - delay = udev->parent->hub_delay; udev->hub_delay = min_t(u32, delay, USB_TP_TRANSMISSION_DELAY_MAX); @@ -4948,27 +4965,10 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, if (retval) goto fail; - /* - * Some superspeed devices have finished the link training process - * and attached to a superspeed hub port, but the device descriptor - * got from those devices show they aren't superspeed devices. Warm - * reset the port attached by the devices can fix them. - */ - if ((udev->speed >= USB_SPEED_SUPER) && - (le16_to_cpu(udev->descriptor.bcdUSB) < 0x0300)) { - dev_err(&udev->dev, "got a wrong device descriptor, " - "warm reset device\n"); - hub_port_reset(hub, port1, udev, - HUB_BH_RESET_TIME, true); - retval = -EINVAL; - goto fail; - } - - if (udev->descriptor.bMaxPacketSize0 == 0xff || - udev->speed >= USB_SPEED_SUPER) + if (maxp0 == 0xff || udev->speed >= USB_SPEED_SUPER) i = 512; else - i = udev->descriptor.bMaxPacketSize0; + i = maxp0; if (usb_endpoint_maxp(&udev->ep0.desc) != i) { if (udev->speed == USB_SPEED_LOW || !(i == 8 || i == 16 || i == 32 || i == 64)) { @@ -4994,6 +4994,20 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, goto fail; } + /* + * Some superspeed devices have finished the link training process + * and attached to a superspeed hub port, but the device descriptor + * got from those devices show they aren't superspeed devices. Warm + * reset the port attached by the devices can fix them. + */ + if ((udev->speed >= USB_SPEED_SUPER) && + (le16_to_cpu(udev->descriptor.bcdUSB) < 0x0300)) { + dev_err(&udev->dev, "got a wrong device descriptor, warm reset device\n"); + hub_port_reset(hub, port1, udev, HUB_BH_RESET_TIME, true); + retval = -EINVAL; + goto fail; + } + usb_detect_quirks(udev); if (udev->wusb == 0 && le16_to_cpu(udev->descriptor.bcdUSB) >= 0x0201) { @@ -5016,6 +5030,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, hub_port_disable(hub, port1, 0); update_devnum(udev, devnum); /* for disconnect processing */ } + kfree(buf); return retval; } From d309fa69c2e3c5e6134ac9386f833f683e66ad1a Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 4 Aug 2023 15:12:21 -0400 Subject: [PATCH 1262/2093] USB: core: Change usb_get_device_descriptor() API commit de28e469da75359a2bb8cd8778b78aa64b1be1f4 upstream. The usb_get_device_descriptor() routine reads the device descriptor from the udev device and stores it directly in udev->descriptor. This interface is error prone, because the USB subsystem expects in-memory copies of a device's descriptors to be immutable once the device has been initialized. The interface is changed so that the device descriptor is left in a kmalloc-ed buffer, not copied into the usb_device structure. A pointer to the buffer is returned to the caller, who is then responsible for kfree-ing it. The corresponding changes needed in the various callers are fairly small. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/d0111bb6-56c1-4f90-adf2-6cfe152f6561@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 10 ++++++--- drivers/usb/core/hub.c | 44 ++++++++++++++++++++------------------ drivers/usb/core/message.c | 29 +++++++++++-------------- drivers/usb/core/usb.h | 4 ++-- 4 files changed, 44 insertions(+), 43 deletions(-) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 8300baedafd2..6af0a31ff147 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -983,6 +983,7 @@ static int register_root_hub(struct usb_hcd *hcd) { struct device *parent_dev = hcd->self.controller; struct usb_device *usb_dev = hcd->self.root_hub; + struct usb_device_descriptor *descr; const int devnum = 1; int retval; @@ -994,13 +995,16 @@ static int register_root_hub(struct usb_hcd *hcd) mutex_lock(&usb_bus_idr_lock); usb_dev->ep0.desc.wMaxPacketSize = cpu_to_le16(64); - retval = usb_get_device_descriptor(usb_dev, USB_DT_DEVICE_SIZE); - if (retval != sizeof usb_dev->descriptor) { + descr = usb_get_device_descriptor(usb_dev); + if (IS_ERR(descr)) { + retval = PTR_ERR(descr); mutex_unlock(&usb_bus_idr_lock); dev_dbg (parent_dev, "can't read %s device descriptor %d\n", dev_name(&usb_dev->dev), retval); - return (retval < 0) ? retval : -EMSGSIZE; + return retval; } + usb_dev->descriptor = *descr; + kfree(descr); if (le16_to_cpu(usb_dev->descriptor.bcdUSB) >= 0x0201) { retval = usb_get_bos_descriptor(usb_dev); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 7266ca0da80a..ac58dcb409a3 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2656,12 +2656,17 @@ int usb_authorize_device(struct usb_device *usb_dev) } if (usb_dev->wusb) { - result = usb_get_device_descriptor(usb_dev, sizeof(usb_dev->descriptor)); - if (result < 0) { + struct usb_device_descriptor *descr; + + descr = usb_get_device_descriptor(usb_dev); + if (IS_ERR(descr)) { + result = PTR_ERR(descr); dev_err(&usb_dev->dev, "can't re-read device descriptor for " "authorization: %d\n", result); goto error_device_descriptor; } + usb_dev->descriptor = *descr; + kfree(descr); } usb_dev->authorized = 1; @@ -4747,7 +4752,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, const char *driver_name; bool do_new_scheme; int maxp0; - struct usb_device_descriptor *buf; + struct usb_device_descriptor *buf, *descr; buf = kmalloc(GET_DESCRIPTOR_BUFSIZE, GFP_NOIO); if (!buf) @@ -4984,15 +4989,16 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, usb_ep0_reinit(udev); } - retval = usb_get_device_descriptor(udev, USB_DT_DEVICE_SIZE); - if (retval < (signed)sizeof(udev->descriptor)) { + descr = usb_get_device_descriptor(udev); + if (IS_ERR(descr)) { + retval = PTR_ERR(descr); if (retval != -ENODEV) dev_err(&udev->dev, "device descriptor read/all, error %d\n", retval); - if (retval >= 0) - retval = -ENOMSG; goto fail; } + udev->descriptor = *descr; + kfree(descr); /* * Some superspeed devices have finished the link training process @@ -5111,7 +5117,7 @@ hub_power_remaining(struct usb_hub *hub) static int descriptors_changed(struct usb_device *udev, - struct usb_device_descriptor *old_device_descriptor, + struct usb_device_descriptor *new_device_descriptor, struct usb_host_bos *old_bos) { int changed = 0; @@ -5122,8 +5128,8 @@ static int descriptors_changed(struct usb_device *udev, int length; char *buf; - if (memcmp(&udev->descriptor, old_device_descriptor, - sizeof(*old_device_descriptor)) != 0) + if (memcmp(&udev->descriptor, new_device_descriptor, + sizeof(*new_device_descriptor)) != 0) return 1; if ((old_bos && !udev->bos) || (!old_bos && udev->bos)) @@ -5443,9 +5449,8 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1, { struct usb_port *port_dev = hub->ports[port1 - 1]; struct usb_device *udev = port_dev->child; - struct usb_device_descriptor descriptor; + struct usb_device_descriptor *descr; int status = -ENODEV; - int retval; dev_dbg(&port_dev->dev, "status %04x, change %04x, %s\n", portstatus, portchange, portspeed(hub, portstatus)); @@ -5472,23 +5477,20 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1, * changed device descriptors before resuscitating the * device. */ - descriptor = udev->descriptor; - retval = usb_get_device_descriptor(udev, - sizeof(udev->descriptor)); - if (retval < 0) { + descr = usb_get_device_descriptor(udev); + if (IS_ERR(descr)) { dev_dbg(&udev->dev, - "can't read device descriptor %d\n", - retval); + "can't read device descriptor %ld\n", + PTR_ERR(descr)); } else { - if (descriptors_changed(udev, &descriptor, + if (descriptors_changed(udev, descr, udev->bos)) { dev_dbg(&udev->dev, "device descriptor has changed\n"); - /* for disconnect() calls */ - udev->descriptor = descriptor; } else { status = 0; /* Nothing to do */ } + kfree(descr); } #ifdef CONFIG_PM } else if (udev->state == USB_STATE_SUSPENDED && diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 4d59d927ae3e..1673e5d08926 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1039,40 +1039,35 @@ char *usb_cache_string(struct usb_device *udev, int index) } /* - * usb_get_device_descriptor - (re)reads the device descriptor (usbcore) - * @dev: the device whose device descriptor is being updated - * @size: how much of the descriptor to read + * usb_get_device_descriptor - read the device descriptor + * @udev: the device whose device descriptor should be read * * Context: task context, might sleep. * - * Updates the copy of the device descriptor stored in the device structure, - * which dedicates space for this purpose. - * * Not exported, only for use by the core. If drivers really want to read * the device descriptor directly, they can call usb_get_descriptor() with * type = USB_DT_DEVICE and index = 0. * - * This call is synchronous, and may not be used in an interrupt context. - * - * Return: The number of bytes received on success, or else the status code - * returned by the underlying usb_control_msg() call. + * Returns: a pointer to a dynamically allocated usb_device_descriptor + * structure (which the caller must deallocate), or an ERR_PTR value. */ -int usb_get_device_descriptor(struct usb_device *dev, unsigned int size) +struct usb_device_descriptor *usb_get_device_descriptor(struct usb_device *udev) { struct usb_device_descriptor *desc; int ret; - if (size > sizeof(*desc)) - return -EINVAL; desc = kmalloc(sizeof(*desc), GFP_NOIO); if (!desc) - return -ENOMEM; + return ERR_PTR(-ENOMEM); + + ret = usb_get_descriptor(udev, USB_DT_DEVICE, 0, desc, sizeof(*desc)); + if (ret == sizeof(*desc)) + return desc; - ret = usb_get_descriptor(dev, USB_DT_DEVICE, 0, desc, size); if (ret >= 0) - memcpy(&dev->descriptor, desc, size); + ret = -EMSGSIZE; kfree(desc); - return ret; + return ERR_PTR(ret); } /* diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index 82538daac8b8..3bb2e1db42b5 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -42,8 +42,8 @@ extern bool usb_endpoint_is_ignored(struct usb_device *udev, struct usb_endpoint_descriptor *epd); extern int usb_remove_device(struct usb_device *udev); -extern int usb_get_device_descriptor(struct usb_device *dev, - unsigned int size); +extern struct usb_device_descriptor *usb_get_device_descriptor( + struct usb_device *udev); extern int usb_set_isoch_delay(struct usb_device *dev); extern int usb_get_bos_descriptor(struct usb_device *dev); extern void usb_release_bos_descriptor(struct usb_device *dev); From 8186596a663506b1124bede9fde6f243ef9f37ee Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 4 Aug 2023 15:14:14 -0400 Subject: [PATCH 1263/2093] USB: core: Fix race by not overwriting udev->descriptor in hub_port_init() commit ff33299ec8bb80cdcc073ad9c506bd79bb2ed20b upstream. Syzbot reported an out-of-bounds read in sysfs.c:read_descriptors(): BUG: KASAN: slab-out-of-bounds in read_descriptors+0x263/0x280 drivers/usb/core/sysfs.c:883 Read of size 8 at addr ffff88801e78b8c8 by task udevd/5011 CPU: 0 PID: 5011 Comm: udevd Not tainted 6.4.0-rc6-syzkaller-00195-g40f71e7cd3c6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:351 print_report mm/kasan/report.c:462 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:572 read_descriptors+0x263/0x280 drivers/usb/core/sysfs.c:883 ... Allocated by task 758: ... __do_kmalloc_node mm/slab_common.c:966 [inline] __kmalloc+0x5e/0x190 mm/slab_common.c:979 kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:680 [inline] usb_get_configuration+0x1f7/0x5170 drivers/usb/core/config.c:887 usb_enumerate_device drivers/usb/core/hub.c:2407 [inline] usb_new_device+0x12b0/0x19d0 drivers/usb/core/hub.c:2545 As analyzed by Khazhy Kumykov, the cause of this bug is a race between read_descriptors() and hub_port_init(): The first routine uses a field in udev->descriptor, not expecting it to change, while the second overwrites it. Prior to commit 45bf39f8df7f ("USB: core: Don't hold device lock while reading the "descriptors" sysfs file") this race couldn't occur, because the routines were mutually exclusive thanks to the device locking. Removing that locking from read_descriptors() exposed it to the race. The best way to fix the bug is to keep hub_port_init() from changing udev->descriptor once udev has been initialized and registered. Drivers expect the descriptors stored in the kernel to be immutable; we should not undermine this expectation. In fact, this change should have been made long ago. So now hub_port_init() will take an additional argument, specifying a buffer in which to store the device descriptor it reads. (If udev has not yet been initialized, the buffer pointer will be NULL and then hub_port_init() will store the device descriptor in udev as before.) This eliminates the data race responsible for the out-of-bounds read. The changes to hub_port_init() appear more extensive than they really are, because of indentation changes resulting from an attempt to avoid writing to other parts of the usb_device structure after it has been initialized. Similar changes should be made to the code that reads the BOS descriptor, but that can be handled in a separate patch later on. This patch is sufficient to fix the bug found by syzbot. Reported-and-tested-by: syzbot+18996170f8096c6174d0@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-usb/000000000000c0ffe505fe86c9ca@google.com/#r Signed-off-by: Alan Stern Cc: Khazhy Kumykov Fixes: 45bf39f8df7f ("USB: core: Don't hold device lock while reading the "descriptors" sysfs file") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/b958b47a-9a46-4c22-a9f9-e42e42c31251@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 114 +++++++++++++++++++++++++---------------- 1 file changed, 70 insertions(+), 44 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index ac58dcb409a3..cdfbbb5a2363 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4736,10 +4736,17 @@ static int get_bMaxPacketSize0(struct usb_device *udev, * the port lock. For a newly detected device that is not accessible * through any global pointers, it's not necessary to lock the device, * but it is still necessary to lock the port. + * + * For a newly detected device, @dev_descr must be NULL. The device + * descriptor retrieved from the device will then be stored in + * @udev->descriptor. For an already existing device, @dev_descr + * must be non-NULL. The device descriptor will be stored there, + * not in @udev->descriptor, because descriptors for registered + * devices are meant to be immutable. */ static int hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, - int retry_counter) + int retry_counter, struct usb_device_descriptor *dev_descr) { struct usb_device *hdev = hub->hdev; struct usb_hcd *hcd = bus_to_hcd(hdev->bus); @@ -4751,6 +4758,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, int devnum = udev->devnum; const char *driver_name; bool do_new_scheme; + const bool initial = !dev_descr; int maxp0; struct usb_device_descriptor *buf, *descr; @@ -4789,32 +4797,34 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, } oldspeed = udev->speed; - /* USB 2.0 section 5.5.3 talks about ep0 maxpacket ... - * it's fixed size except for full speed devices. - * For Wireless USB devices, ep0 max packet is always 512 (tho - * reported as 0xff in the device descriptor). WUSB1.0[4.8.1]. - */ - switch (udev->speed) { - case USB_SPEED_SUPER_PLUS: - case USB_SPEED_SUPER: - case USB_SPEED_WIRELESS: /* fixed at 512 */ - udev->ep0.desc.wMaxPacketSize = cpu_to_le16(512); - break; - case USB_SPEED_HIGH: /* fixed at 64 */ - udev->ep0.desc.wMaxPacketSize = cpu_to_le16(64); - break; - case USB_SPEED_FULL: /* 8, 16, 32, or 64 */ - /* to determine the ep0 maxpacket size, try to read - * the device descriptor to get bMaxPacketSize0 and - * then correct our initial guess. + if (initial) { + /* USB 2.0 section 5.5.3 talks about ep0 maxpacket ... + * it's fixed size except for full speed devices. + * For Wireless USB devices, ep0 max packet is always 512 (tho + * reported as 0xff in the device descriptor). WUSB1.0[4.8.1]. */ - udev->ep0.desc.wMaxPacketSize = cpu_to_le16(64); - break; - case USB_SPEED_LOW: /* fixed at 8 */ - udev->ep0.desc.wMaxPacketSize = cpu_to_le16(8); - break; - default: - goto fail; + switch (udev->speed) { + case USB_SPEED_SUPER_PLUS: + case USB_SPEED_SUPER: + case USB_SPEED_WIRELESS: /* fixed at 512 */ + udev->ep0.desc.wMaxPacketSize = cpu_to_le16(512); + break; + case USB_SPEED_HIGH: /* fixed at 64 */ + udev->ep0.desc.wMaxPacketSize = cpu_to_le16(64); + break; + case USB_SPEED_FULL: /* 8, 16, 32, or 64 */ + /* to determine the ep0 maxpacket size, try to read + * the device descriptor to get bMaxPacketSize0 and + * then correct our initial guess. + */ + udev->ep0.desc.wMaxPacketSize = cpu_to_le16(64); + break; + case USB_SPEED_LOW: /* fixed at 8 */ + udev->ep0.desc.wMaxPacketSize = cpu_to_le16(8); + break; + default: + goto fail; + } } if (udev->speed == USB_SPEED_WIRELESS) @@ -4837,22 +4847,24 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, if (udev->speed < USB_SPEED_SUPER) dev_info(&udev->dev, "%s %s USB device number %d using %s\n", - (udev->config) ? "reset" : "new", speed, + (initial ? "new" : "reset"), speed, devnum, driver_name); - /* Set up TT records, if needed */ - if (hdev->tt) { - udev->tt = hdev->tt; - udev->ttport = hdev->ttport; - } else if (udev->speed != USB_SPEED_HIGH - && hdev->speed == USB_SPEED_HIGH) { - if (!hub->tt.hub) { - dev_err(&udev->dev, "parent hub has no TT\n"); - retval = -EINVAL; - goto fail; + if (initial) { + /* Set up TT records, if needed */ + if (hdev->tt) { + udev->tt = hdev->tt; + udev->ttport = hdev->ttport; + } else if (udev->speed != USB_SPEED_HIGH + && hdev->speed == USB_SPEED_HIGH) { + if (!hub->tt.hub) { + dev_err(&udev->dev, "parent hub has no TT\n"); + retval = -EINVAL; + goto fail; + } + udev->tt = &hub->tt; + udev->ttport = port1; } - udev->tt = &hub->tt; - udev->ttport = port1; } /* Why interleave GET_DESCRIPTOR and SET_ADDRESS this way? @@ -4881,6 +4893,12 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, maxp0 = get_bMaxPacketSize0(udev, buf, GET_DESCRIPTOR_BUFSIZE, retries == 0); + if (maxp0 > 0 && !initial && + maxp0 != udev->descriptor.bMaxPacketSize0) { + dev_err(&udev->dev, "device reset changed ep0 maxpacket size!\n"); + retval = -ENODEV; + goto fail; + } retval = hub_port_reset(hub, port1, udev, delay, false); if (retval < 0) /* error or disconnect */ @@ -4954,6 +4972,12 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, } else { u32 delay; + if (!initial && maxp0 != udev->descriptor.bMaxPacketSize0) { + dev_err(&udev->dev, "device reset changed ep0 maxpacket size!\n"); + retval = -ENODEV; + goto fail; + } + delay = udev->parent->hub_delay; udev->hub_delay = min_t(u32, delay, USB_TP_TRANSMISSION_DELAY_MAX); @@ -4997,7 +5021,10 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, retval); goto fail; } - udev->descriptor = *descr; + if (initial) + udev->descriptor = *descr; + else + *dev_descr = *descr; kfree(descr); /* @@ -5302,7 +5329,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, } /* reset (non-USB 3.0 devices) and get descriptor */ - status = hub_port_init(hub, udev, port1, i); + status = hub_port_init(hub, udev, port1, i, NULL); if (status < 0) goto loop; @@ -5928,7 +5955,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) struct usb_device *parent_hdev = udev->parent; struct usb_hub *parent_hub; struct usb_hcd *hcd = bus_to_hcd(udev->bus); - struct usb_device_descriptor descriptor = udev->descriptor; + struct usb_device_descriptor descriptor; struct usb_host_bos *bos; int i, j, ret = 0; int port1 = udev->portnum; @@ -5960,7 +5987,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) /* ep0 maxpacket size may change; let the HCD know about it. * Other endpoints will be handled by re-enumeration. */ usb_ep0_reinit(udev); - ret = hub_port_init(parent_hub, udev, port1, i); + ret = hub_port_init(parent_hub, udev, port1, i, &descriptor); if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV) break; } @@ -5972,7 +5999,6 @@ static int usb_reset_and_verify_device(struct usb_device *udev) /* Device might have changed firmware (DFU or similar) */ if (descriptors_changed(udev, &descriptor, bos)) { dev_info(&udev->dev, "device firmware changed\n"); - udev->descriptor = descriptor; /* for disconnect() calls */ goto re_enumerate; } From f705617bab4766567874715eeed1b39dacb58671 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 11 Aug 2023 13:38:46 -0400 Subject: [PATCH 1264/2093] USB: core: Fix oversight in SuperSpeed initialization commit 59cf445754566984fd55af19ba7146c76e6627bc upstream. Commit 85d07c556216 ("USB: core: Unite old scheme and new scheme descriptor reads") altered the way USB devices are enumerated following detection, and in the process it messed up the initialization of SuperSpeed (or faster) devices: [ 31.650759] usb 2-1: new SuperSpeed Plus Gen 2x1 USB device number 2 using xhci_hcd [ 31.663107] usb 2-1: device descriptor read/8, error -71 [ 31.952697] usb 2-1: new SuperSpeed Plus Gen 2x1 USB device number 3 using xhci_hcd [ 31.965122] usb 2-1: device descriptor read/8, error -71 [ 32.080991] usb usb2-port1: attempt power cycle ... The problem was caused by the commit forgetting that in SuperSpeed or faster devices, the device descriptor uses a logarithmic encoding of the bMaxPacketSize0 value. (For some reason I thought the 255 case in the switch statement was meant for these devices, but it isn't -- it was meant for Wireless USB and is no longer needed.) We can fix the oversight by testing for buf->bMaxPacketSize0 = 9 (meaning 512, the actual maxpacket size for ep0 on all SuperSpeed devices) and straightening out the logic that checks and adjusts our initial guesses of the maxpacket value. Reported-and-tested-by: Thinh Nguyen Closes: https://lore.kernel.org/linux-usb/20230810002257.nadxmfmrobkaxgnz@synopsys.com/ Signed-off-by: Alan Stern Fixes: 85d07c556216 ("USB: core: Unite old scheme and new scheme descriptor reads") Link: https://lore.kernel.org/r/8809e6c5-59d5-4d2d-ac8f-6d106658ad73@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index cdfbbb5a2363..0069a24bd216 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4700,7 +4700,7 @@ static int get_bMaxPacketSize0(struct usb_device *udev, buf, size, initial_descriptor_timeout); switch (buf->bMaxPacketSize0) { - case 8: case 16: case 32: case 64: case 255: + case 8: case 16: case 32: case 64: case 9: if (buf->bDescriptorType == USB_DT_DEVICE) { rc = buf->bMaxPacketSize0; break; @@ -4994,23 +4994,35 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, if (retval) goto fail; - if (maxp0 == 0xff || udev->speed >= USB_SPEED_SUPER) - i = 512; - else - i = maxp0; - if (usb_endpoint_maxp(&udev->ep0.desc) != i) { - if (udev->speed == USB_SPEED_LOW || - !(i == 8 || i == 16 || i == 32 || i == 64)) { - dev_err(&udev->dev, "Invalid ep0 maxpacket: %d\n", i); - retval = -EMSGSIZE; - goto fail; - } + /* + * Check the ep0 maxpacket guess and correct it if necessary. + * maxp0 is the value stored in the device descriptor; + * i is the value it encodes (logarithmic for SuperSpeed or greater). + */ + i = maxp0; + if (udev->speed >= USB_SPEED_SUPER) { + if (maxp0 <= 16) + i = 1 << maxp0; + else + i = 0; /* Invalid */ + } + if (usb_endpoint_maxp(&udev->ep0.desc) == i) { + ; /* Initial ep0 maxpacket guess is right */ + } else if ((udev->speed == USB_SPEED_FULL || + udev->speed == USB_SPEED_HIGH) && + (i == 8 || i == 16 || i == 32 || i == 64)) { + /* Initial guess is wrong; use the descriptor's value */ if (udev->speed == USB_SPEED_FULL) dev_dbg(&udev->dev, "ep0 maxpacket = %d\n", i); else dev_warn(&udev->dev, "Using ep0 maxpacket: %d\n", i); udev->ep0.desc.wMaxPacketSize = cpu_to_le16(i); usb_ep0_reinit(udev); + } else { + /* Initial guess is wrong and descriptor's value is invalid */ + dev_err(&udev->dev, "Invalid ep0 maxpacket: %d\n", maxp0); + retval = -EMSGSIZE; + goto fail; } descr = usb_get_device_descriptor(udev); From e1eb0419126f0e0ac61d635739753fc16010db22 Mon Sep 17 00:00:00 2001 From: Jack Wang Date: Wed, 6 Sep 2023 15:17:12 +0200 Subject: [PATCH 1265/2093] x86/sgx: Break up long non-preemptible delays in sgx_vepc_release() commit 3d7d72a34e05b23e21bafc8bfb861e73c86b31f3 upstream. On large enclaves we hit the softlockup warning with following call trace: xa_erase() sgx_vepc_release() __fput() task_work_run() do_exit() The latency issue is similar to the one fixed in: 8795359e35bc ("x86/sgx: Silence softlockup detection when releasing large enclaves") The test system has 64GB of enclave memory, and all is assigned to a single VM. Release of 'vepc' takes a longer time and causes long latencies, which triggers the softlockup warning. Add cond_resched() to give other tasks a chance to run and reduce latencies, which also avoids the softlockup detector. [ mingo: Rewrote the changelog. ] Fixes: 540745ddbc70 ("x86/sgx: Introduce virtual EPC for use by KVM guests") Reported-by: Yu Zhang Signed-off-by: Jack Wang Signed-off-by: Ingo Molnar Tested-by: Yu Zhang Reviewed-by: Jarkko Sakkinen Reviewed-by: Kai Huang Acked-by: Haitao Huang Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/sgx/virt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c index 6a77a14eee38..f5549704ac4c 100644 --- a/arch/x86/kernel/cpu/sgx/virt.c +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -204,6 +204,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) continue; xa_erase(&vepc->page_array, index); + cond_resched(); } /* @@ -222,6 +223,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) list_add_tail(&epc_page->list, &secs_pages); xa_erase(&vepc->page_array, index); + cond_resched(); } /* @@ -243,6 +245,7 @@ static int sgx_vepc_release(struct inode *inode, struct file *file) if (sgx_vepc_free_page(epc_page)) list_add_tail(&epc_page->list, &secs_pages); + cond_resched(); } if (!list_empty(&secs_pages)) From cc8a853c2d5fe7e035c44fa18d3d9764fe220722 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 5 Sep 2023 06:42:48 -0700 Subject: [PATCH 1266/2093] perf/x86/uncore: Correct the number of CHAs on EMR commit 6f7f984fa85b305799076a1bcec941b9377587de upstream. Starting from SPR, the basic uncore PMON information is retrieved from the discovery table (resides in an MMIO space populated by BIOS). It is called the discovery method. The existing value of the type->num_boxes is from the discovery table. On some SPR variants, there is a firmware bug that makes the value from the discovery table incorrect. We use the value from the SPR_MSR_UNC_CBO_CONFIG MSR to replace the one from the discovery table: 38776cc45eb7 ("perf/x86/uncore: Correct the number of CHAs on SPR") Unfortunately, the SPR_MSR_UNC_CBO_CONFIG isn't available for the EMR XCC (Always returns 0), but the above firmware bug doesn't impact the EMR XCC. Don't let the value from the MSR replace the existing value from the discovery table. Fixes: 38776cc45eb7 ("perf/x86/uncore: Correct the number of CHAs on SPR") Reported-by: Stephane Eranian Reported-by: Yunying Sun Signed-off-by: Kan Liang Signed-off-by: Ingo Molnar Tested-by: Yunying Sun Link: https://lore.kernel.org/r/20230905134248.496114-1-kan.liang@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/intel/uncore_snbep.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 935081ddf60b..9b5859812f4f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6078,8 +6078,18 @@ void spr_uncore_cpu_init(void) type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA); if (type) { + /* + * The value from the discovery table (stored in the type->num_boxes + * of UNCORE_SPR_CHA) is incorrect on some SPR variants because of a + * firmware bug. Using the value from SPR_MSR_UNC_CBO_CONFIG to replace it. + */ rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo); - type->num_boxes = num_cbo; + /* + * The MSR doesn't work on the EMR XCC, but the firmware bug doesn't impact + * the EMR XCC. Don't let the value from the MSR replace the existing value. + */ + if (num_cbo) + type->num_boxes = num_cbo; } spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO); } From 8aaef0a3eb1b60f17595bd88a3e6ca59269312ee Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 7 Aug 2023 17:45:52 -0400 Subject: [PATCH 1267/2093] serial: sc16is7xx: remove obsolete out_thread label [ Upstream commit dabc54a45711fe77674a6c0348231e00e66bd567 ] Commit c8f71b49ee4d ("serial: sc16is7xx: setup GPIO controller later in probe") moved GPIO setup code later in probe function. Doing so also required to move ports cleanup code (out_ports label) after the GPIO cleanup code. After these moves, the out_thread label becomes misplaced and makes part of the cleanup code illogical. This patch remove the now obsolete out_thread label and make GPIO setup code jump to out_ports label if it fails. Signed-off-by: Hugo Villeneuve Reviewed-by: Lech Perczak Tested-by: Lech Perczak Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230807214556.540627-3-hugo@hugovil.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 049994292834 ("serial: sc16is7xx: fix regression with GPIO configuration") Signed-off-by: Sasha Levin --- drivers/tty/serial/sc16is7xx.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 8411a0f312db..c481c84019f4 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1532,7 +1532,7 @@ static int sc16is7xx_probe(struct device *dev, s->gpio.can_sleep = 1; ret = gpiochip_add_data(&s->gpio, s); if (ret) - goto out_thread; + goto out_ports; } #endif @@ -1558,8 +1558,6 @@ static int sc16is7xx_probe(struct device *dev, #ifdef CONFIG_GPIOLIB if (devtype->nr_gpio) gpiochip_remove(&s->gpio); - -out_thread: #endif out_ports: From e43a7ae58d003a93b1adcabfd7e0a1f81472c4cf Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 7 Aug 2023 17:45:54 -0400 Subject: [PATCH 1268/2093] serial: sc16is7xx: fix regression with GPIO configuration [ Upstream commit 0499942928341d572a42199580433c2b0725211e ] Commit 679875d1d880 ("sc16is7xx: Separate GPIOs from modem control lines") and commit 21144bab4f11 ("sc16is7xx: Handle modem status lines") changed the function of the GPIOs pins to act as modem control lines without any possibility of selecting GPIO function. As a consequence, applications that depends on GPIO lines configured by default as GPIO pins no longer work as expected. Also, the change to select modem control lines function was done only for channel A of dual UART variants (752/762). This was not documented in the log message. Allow to specify GPIO or modem control line function in the device tree, and for each of the ports (A or B). Do so by using the new device-tree property named "nxp,modem-control-line-ports" (property added in separate patch). When registering GPIO chip controller, mask-out GPIO pins declared as modem control lines according to this new DT property. Fixes: 679875d1d880 ("sc16is7xx: Separate GPIOs from modem control lines") Fixes: 21144bab4f11 ("sc16is7xx: Handle modem status lines") Cc: stable@vger.kernel.org Signed-off-by: Hugo Villeneuve Reviewed-by: Andy Shevchenko Reviewed-by: Lech Perczak Tested-by: Lech Perczak Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230807214556.540627-5-hugo@hugovil.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/sc16is7xx.c | 143 +++++++++++++++++++++++++-------- 1 file changed, 108 insertions(+), 35 deletions(-) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index c481c84019f4..21145eb8f2a9 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -236,7 +236,8 @@ /* IOControl register bits (Only 750/760) */ #define SC16IS7XX_IOCONTROL_LATCH_BIT (1 << 0) /* Enable input latching */ -#define SC16IS7XX_IOCONTROL_MODEM_BIT (1 << 1) /* Enable GPIO[7:4] as modem pins */ +#define SC16IS7XX_IOCONTROL_MODEM_A_BIT (1 << 1) /* Enable GPIO[7:4] as modem A pins */ +#define SC16IS7XX_IOCONTROL_MODEM_B_BIT (1 << 2) /* Enable GPIO[3:0] as modem B pins */ #define SC16IS7XX_IOCONTROL_SRESET_BIT (1 << 3) /* Software Reset */ /* EFCR register bits */ @@ -301,12 +302,12 @@ /* Misc definitions */ #define SC16IS7XX_FIFO_SIZE (64) #define SC16IS7XX_REG_SHIFT 2 +#define SC16IS7XX_GPIOS_PER_BANK 4 struct sc16is7xx_devtype { char name[10]; int nr_gpio; int nr_uart; - int has_mctrl; }; #define SC16IS7XX_RECONF_MD (1 << 0) @@ -336,7 +337,9 @@ struct sc16is7xx_port { struct clk *clk; #ifdef CONFIG_GPIOLIB struct gpio_chip gpio; + unsigned long gpio_valid_mask; #endif + u8 mctrl_mask; unsigned char buf[SC16IS7XX_FIFO_SIZE]; struct kthread_worker kworker; struct task_struct *kworker_task; @@ -447,35 +450,30 @@ static const struct sc16is7xx_devtype sc16is74x_devtype = { .name = "SC16IS74X", .nr_gpio = 0, .nr_uart = 1, - .has_mctrl = 0, }; static const struct sc16is7xx_devtype sc16is750_devtype = { .name = "SC16IS750", - .nr_gpio = 4, + .nr_gpio = 8, .nr_uart = 1, - .has_mctrl = 1, }; static const struct sc16is7xx_devtype sc16is752_devtype = { .name = "SC16IS752", - .nr_gpio = 0, + .nr_gpio = 8, .nr_uart = 2, - .has_mctrl = 1, }; static const struct sc16is7xx_devtype sc16is760_devtype = { .name = "SC16IS760", - .nr_gpio = 4, + .nr_gpio = 8, .nr_uart = 1, - .has_mctrl = 1, }; static const struct sc16is7xx_devtype sc16is762_devtype = { .name = "SC16IS762", - .nr_gpio = 0, + .nr_gpio = 8, .nr_uart = 2, - .has_mctrl = 1, }; static bool sc16is7xx_regmap_volatile(struct device *dev, unsigned int reg) @@ -1360,8 +1358,98 @@ static int sc16is7xx_gpio_direction_output(struct gpio_chip *chip, return 0; } + +static int sc16is7xx_gpio_init_valid_mask(struct gpio_chip *chip, + unsigned long *valid_mask, + unsigned int ngpios) +{ + struct sc16is7xx_port *s = gpiochip_get_data(chip); + + *valid_mask = s->gpio_valid_mask; + + return 0; +} + +static int sc16is7xx_setup_gpio_chip(struct sc16is7xx_port *s) +{ + struct device *dev = s->p[0].port.dev; + + if (!s->devtype->nr_gpio) + return 0; + + switch (s->mctrl_mask) { + case 0: + s->gpio_valid_mask = GENMASK(7, 0); + break; + case SC16IS7XX_IOCONTROL_MODEM_A_BIT: + s->gpio_valid_mask = GENMASK(3, 0); + break; + case SC16IS7XX_IOCONTROL_MODEM_B_BIT: + s->gpio_valid_mask = GENMASK(7, 4); + break; + default: + break; + } + + if (s->gpio_valid_mask == 0) + return 0; + + s->gpio.owner = THIS_MODULE; + s->gpio.parent = dev; + s->gpio.label = dev_name(dev); + s->gpio.init_valid_mask = sc16is7xx_gpio_init_valid_mask; + s->gpio.direction_input = sc16is7xx_gpio_direction_input; + s->gpio.get = sc16is7xx_gpio_get; + s->gpio.direction_output = sc16is7xx_gpio_direction_output; + s->gpio.set = sc16is7xx_gpio_set; + s->gpio.base = -1; + s->gpio.ngpio = s->devtype->nr_gpio; + s->gpio.can_sleep = 1; + + return gpiochip_add_data(&s->gpio, s); +} #endif +/* + * Configure ports designated to operate as modem control lines. + */ +static int sc16is7xx_setup_mctrl_ports(struct sc16is7xx_port *s) +{ + int i; + int ret; + int count; + u32 mctrl_port[2]; + struct device *dev = s->p[0].port.dev; + + count = device_property_count_u32(dev, "nxp,modem-control-line-ports"); + if (count < 0 || count > ARRAY_SIZE(mctrl_port)) + return 0; + + ret = device_property_read_u32_array(dev, "nxp,modem-control-line-ports", + mctrl_port, count); + if (ret) + return ret; + + s->mctrl_mask = 0; + + for (i = 0; i < count; i++) { + /* Use GPIO lines as modem control lines */ + if (mctrl_port[i] == 0) + s->mctrl_mask |= SC16IS7XX_IOCONTROL_MODEM_A_BIT; + else if (mctrl_port[i] == 1) + s->mctrl_mask |= SC16IS7XX_IOCONTROL_MODEM_B_BIT; + } + + if (s->mctrl_mask) + regmap_update_bits( + s->regmap, + SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT, + SC16IS7XX_IOCONTROL_MODEM_A_BIT | + SC16IS7XX_IOCONTROL_MODEM_B_BIT, s->mctrl_mask); + + return 0; +} + static const struct serial_rs485 sc16is7xx_rs485_supported = { .flags = SER_RS485_ENABLED | SER_RS485_RTS_AFTER_SEND, .delay_rts_before_send = 1, @@ -1474,12 +1562,6 @@ static int sc16is7xx_probe(struct device *dev, SC16IS7XX_EFCR_RXDISABLE_BIT | SC16IS7XX_EFCR_TXDISABLE_BIT); - /* Use GPIO lines as modem status registers */ - if (devtype->has_mctrl) - sc16is7xx_port_write(&s->p[i].port, - SC16IS7XX_IOCONTROL_REG, - SC16IS7XX_IOCONTROL_MODEM_BIT); - /* Initialize kthread work structs */ kthread_init_work(&s->p[i].tx_work, sc16is7xx_tx_proc); kthread_init_work(&s->p[i].reg_work, sc16is7xx_reg_proc); @@ -1517,23 +1599,14 @@ static int sc16is7xx_probe(struct device *dev, s->p[u].irda_mode = true; } + ret = sc16is7xx_setup_mctrl_ports(s); + if (ret) + goto out_ports; + #ifdef CONFIG_GPIOLIB - if (devtype->nr_gpio) { - /* Setup GPIO cotroller */ - s->gpio.owner = THIS_MODULE; - s->gpio.parent = dev; - s->gpio.label = dev_name(dev); - s->gpio.direction_input = sc16is7xx_gpio_direction_input; - s->gpio.get = sc16is7xx_gpio_get; - s->gpio.direction_output = sc16is7xx_gpio_direction_output; - s->gpio.set = sc16is7xx_gpio_set; - s->gpio.base = -1; - s->gpio.ngpio = devtype->nr_gpio; - s->gpio.can_sleep = 1; - ret = gpiochip_add_data(&s->gpio, s); - if (ret) - goto out_ports; - } + ret = sc16is7xx_setup_gpio_chip(s); + if (ret) + goto out_ports; #endif /* @@ -1556,7 +1629,7 @@ static int sc16is7xx_probe(struct device *dev, return 0; #ifdef CONFIG_GPIOLIB - if (devtype->nr_gpio) + if (s->gpio_valid_mask) gpiochip_remove(&s->gpio); #endif @@ -1580,7 +1653,7 @@ static void sc16is7xx_remove(struct device *dev) int i; #ifdef CONFIG_GPIOLIB - if (s->devtype->nr_gpio) + if (s->gpio_valid_mask) gpiochip_remove(&s->gpio); #endif From 1dd387668d5bd911df0b21716fff6f5180b11e42 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Thu, 31 Aug 2023 08:55:00 -0400 Subject: [PATCH 1269/2093] tracing: Zero the pipe cpumask on alloc to avoid spurious -EBUSY commit 3d07fa1dd19035eb0b13ae6697efd5caa9033e74 upstream. The pipe cpumask used to serialize opens between the main and percpu trace pipes is not zeroed or initialized. This can result in spurious -EBUSY returns if underlying memory is not fully zeroed. This has been observed by immediate failure to read the main trace_pipe file on an otherwise newly booted and idle system: # cat /sys/kernel/debug/tracing/trace_pipe cat: /sys/kernel/debug/tracing/trace_pipe: Device or resource busy Zero the allocation of pipe_cpumask to avoid the problem. Link: https://lore.kernel.org/linux-trace-kernel/20230831125500.986862-1-bfoster@redhat.com Cc: stable@vger.kernel.org Fixes: c2489bb7e6be ("tracing: Introduce pipe_cpumask to avoid race on trace_pipes") Reviewed-by: Zheng Yejian Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Brian Foster Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5d0465ae7be8..54ccdca39531 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9395,7 +9395,7 @@ static struct trace_array *trace_array_create(const char *name) if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; - if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) goto out_free_tr; tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; @@ -10267,7 +10267,7 @@ __init static int tracer_alloc_buffers(void) if (trace_create_savedcmd() < 0) goto out_free_temp_buffer; - if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) goto out_free_savedcmd; /* TODO: make the number of buffers hot pluggable with CPUS */ From ba6a70adb5573a4470ac510fa388696dbb8f0a0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Mon, 22 May 2023 15:08:23 +0200 Subject: [PATCH 1270/2093] Revert "drm/amd/display: Do not set drr on pipe commit" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 360930985ec9f394c82ba0b235403b4a366d1560 upstream. This reverts commit e101bf95ea87ccc03ac2f48dfc0757c6364ff3c7. Caused a regression: Samsung Odyssey Neo G9, running at 5120x1440@240/VRR, connected to Navi 21 via DisplayPort, blanks and the GPU hangs while starting the Steam game Assetto Corsa Competizione (via Proton 7.0). Example dmesg excerpt: amdgpu 0000:0c:00.0: [drm] ERROR [CRTC:82:crtc-0] flip_done timed out NMI watchdog: Watchdog detected hard LOCKUP on cpu 6 [...] RIP: 0010:amdgpu_device_rreg.part.0+0x2f/0xf0 [amdgpu] Code: 41 54 44 8d 24 b5 00 00 00 00 55 89 f5 53 48 89 fb 4c 3b a7 60 0b 00 00 73 6a 83 e2 02 74 29 4c 03 a3 68 0b 00 00 45 8b 24 24 <48> 8b 43 08 0f b7 70 3e 66 90 44 89 e0 5b 5d 41 5c 31 d2 31 c9 31 RSP: 0000:ffffb39a119dfb88 EFLAGS: 00000086 RAX: ffffffffc0eb96a0 RBX: ffff9e7963dc0000 RCX: 0000000000007fff RDX: 0000000000000000 RSI: 0000000000004ff6 RDI: ffff9e7963dc0000 RBP: 0000000000004ff6 R08: ffffb39a119dfc40 R09: 0000000000000010 R10: ffffb39a119dfc40 R11: ffffb39a119dfc44 R12: 00000000000e05ae R13: 0000000000000000 R14: ffff9e7963dc0010 R15: 0000000000000000 FS: 000000001012f6c0(0000) GS:ffff9e805eb80000(0000) knlGS:000000007fd40000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000461ca000 CR3: 00000002a8a20000 CR4: 0000000000350ee0 Call Trace: dm_read_reg_func+0x37/0xc0 [amdgpu] generic_reg_get2+0x22/0x60 [amdgpu] optc1_get_crtc_scanoutpos+0x6a/0xc0 [amdgpu] dc_stream_get_scanoutpos+0x74/0x90 [amdgpu] dm_crtc_get_scanoutpos+0x82/0xf0 [amdgpu] amdgpu_display_get_crtc_scanoutpos+0x91/0x190 [amdgpu] ? dm_read_reg_func+0x37/0xc0 [amdgpu] amdgpu_get_vblank_counter_kms+0xb4/0x1a0 [amdgpu] dm_pflip_high_irq+0x213/0x2f0 [amdgpu] amdgpu_dm_irq_handler+0x8a/0x200 [amdgpu] amdgpu_irq_dispatch+0xd4/0x220 [amdgpu] amdgpu_ih_process+0x7f/0x110 [amdgpu] amdgpu_irq_handler+0x1f/0x70 [amdgpu] __handle_irq_event_percpu+0x46/0x1b0 handle_irq_event+0x34/0x80 handle_edge_irq+0x9f/0x240 __common_interrupt+0x66/0x110 common_interrupt+0x5c/0xd0 asm_common_interrupt+0x22/0x40 Reviewed-by: Aurabindo Pillai Acked-by: Alex Deucher Signed-off-by: Michel Dänzer Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 6 ------ drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c | 7 ------- 2 files changed, 13 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 21fae818ca28..4ef632864948 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2032,12 +2032,6 @@ void dcn20_optimize_bandwidth( if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { - dc_dmub_srv_p_state_delegate(dc, - true, context); - context->bw_ctx.bw.dcn.clk.p_state_change_support = true; - } - dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index c97d3e81a83d..a1b312483d7f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -987,18 +987,11 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, void dcn30_prepare_bandwidth(struct dc *dc, struct dc_state *context) { - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { - dc->optimized_required = true; - context->bw_ctx.bw.dcn.clk.p_state_change_support = false; - } - if (dc->clk_mgr->dc_mode_softmax_enabled) if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 && context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); - - dc_dmub_srv_p_state_delegate(dc, false, context); } From d9ece8c0269f4efe391bfa1022266bdb78d8cbad Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Wed, 22 Feb 2023 11:59:16 +0800 Subject: [PATCH 1271/2093] md: Free resources in __md_stop commit 3e453522593d74a87cf68a38e14aa36ebca1dbcd upstream. If md_run() fails after ->active_io is initialized, then percpu_ref_exit is called in error path. However, later md_free_disk will call percpu_ref_exit again which leads to a panic because of null pointer dereference. It can also trigger this bug when resources are initialized but are freed in error path, then will be freed again in md_free_disk. BUG: kernel NULL pointer dereference, address: 0000000000000038 Oops: 0000 [#1] PREEMPT SMP Workqueue: md_misc mddev_delayed_delete RIP: 0010:free_percpu+0x110/0x630 Call Trace: __percpu_ref_exit+0x44/0x70 percpu_ref_exit+0x16/0x90 md_free_disk+0x2f/0x80 disk_release+0x101/0x180 device_release+0x84/0x110 kobject_put+0x12a/0x380 kobject_put+0x160/0x380 mddev_delayed_delete+0x19/0x30 process_one_work+0x269/0x680 worker_thread+0x266/0x640 kthread+0x151/0x1b0 ret_from_fork+0x1f/0x30 For creating raid device, md raid calls do_md_run->md_run, dm raid calls md_run. We alloc those memory in md_run. For stopping raid device, md raid calls do_md_stop->__md_stop, dm raid calls md_stop->__md_stop. So we can free those memory resources in __md_stop. Fixes: 72adae23a72c ("md: Change active_io to percpu") Reported-and-tested-by: Yu Kuai Signed-off-by: Xiao Ni Signed-off-by: Song Liu Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index b65d8bf54924..da718f6349dd 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6277,6 +6277,11 @@ static void __md_stop(struct mddev *mddev) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + + percpu_ref_exit(&mddev->writes_pending); + percpu_ref_exit(&mddev->active_io); + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); } void md_stop(struct mddev *mddev) @@ -6288,9 +6293,6 @@ void md_stop(struct mddev *mddev) */ __md_stop_writes(mddev); __md_stop(mddev); - percpu_ref_exit(&mddev->active_io); - bioset_exit(&mddev->bio_set); - bioset_exit(&mddev->sync_set); } EXPORT_SYMBOL_GPL(md_stop); @@ -7857,11 +7859,6 @@ static void md_free_disk(struct gendisk *disk) { struct mddev *mddev = disk->private_data; - percpu_ref_exit(&mddev->writes_pending); - percpu_ref_exit(&mddev->active_io); - bioset_exit(&mddev->bio_set); - bioset_exit(&mddev->sync_set); - mddev_free(mddev); } From 7795634751622709cab9ce4cad2bcd93f871fae3 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 16 May 2023 11:19:25 -0400 Subject: [PATCH 1272/2093] NFSv4.2: Fix a potential double free with READ_PLUS commit 43439d858bbae244a510de47f9a55f667ca4ed52 upstream. kfree()-ing the scratch page isn't enough, we also need to set the pointer back to NULL to avoid a double-free in the case of a resend. Fixes: fbd2a05f29a9 (NFSv4.2: Rework scratch handling for READ_PLUS) Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- fs/nfs/nfs4proc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3f96ccc386c3..b707a23c25e9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5444,10 +5444,18 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, return false; } +static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr) +{ + if (hdr->res.scratch) { + kfree(hdr->res.scratch); + hdr->res.scratch = NULL; + } +} + static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { - if (hdr->res.scratch) - kfree(hdr->res.scratch); + nfs4_read_plus_scratch_free(hdr); + if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) From adac9f0ddd2b291c7ce41f549fdb27a13616cff5 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 9 Jun 2023 15:26:25 -0400 Subject: [PATCH 1273/2093] NFSv4.2: Rework scratch handling for READ_PLUS (again) commit 303a78052091c81e9003915c521fdca1c7e117af upstream. I found that the read code might send multiple requests using the same nfs_pgio_header, but nfs4_proc_read_setup() is only called once. This is how we ended up occasionally double-freeing the scratch buffer, but also means we set a NULL pointer but non-zero length to the xdr scratch buffer. This results in an oops the first time decoding needs to copy something to scratch, which frequently happens when decoding READ_PLUS hole segments. I fix this by moving scratch handling into the pageio read code. I provide a function to allocate scratch space for decoding read replies, and free the scratch buffer when the nfs_pgio_header is freed. Fixes: fbd2a05f29a9 (NFSv4.2: Rework scratch handling for READ_PLUS) Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- fs/nfs/internal.h | 1 + fs/nfs/nfs42.h | 1 + fs/nfs/nfs42xdr.c | 2 +- fs/nfs/nfs4proc.c | 13 +------------ fs/nfs/read.c | 10 ++++++++++ 5 files changed, 14 insertions(+), 13 deletions(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ae7d4a8c728c..4b07a0508f9d 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -484,6 +484,7 @@ struct nfs_pgio_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); +extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 0fe5aacbcfdf..b59876b01a1e 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -13,6 +13,7 @@ * more? Need to consider not to pre-alloc too much for a compound. */ #define PNFS_LAYOUTSTATS_MAXDEV (4) +#define READ_PLUS_SCRATCH_SIZE (16) /* nfs4.2proc.c */ #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 75765382cc0e..20aa5e746497 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1351,7 +1351,7 @@ static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp, struct compound_hdr hdr; int status; - xdr_set_scratch_buffer(xdr, res->scratch, sizeof(res->scratch)); + xdr_set_scratch_buffer(xdr, res->scratch, READ_PLUS_SCRATCH_SIZE); status = decode_compound_hdr(xdr, &hdr); if (status) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b707a23c25e9..2dec0fed1ba1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5444,18 +5444,8 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, return false; } -static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr) -{ - if (hdr->res.scratch) { - kfree(hdr->res.scratch); - hdr->res.scratch = NULL; - } -} - static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { - nfs4_read_plus_scratch_free(hdr); - if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) @@ -5475,8 +5465,7 @@ static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr, /* Note: We don't use READ_PLUS with pNFS yet */ if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) { msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS]; - hdr->res.scratch = kmalloc(32, GFP_KERNEL); - return hdr->res.scratch != NULL; + return nfs_read_alloc_scratch(hdr, READ_PLUS_SCRATCH_SIZE); } return false; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index cd970ce62786..6aad42fbf797 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -47,6 +47,8 @@ static struct nfs_pgio_header *nfs_readhdr_alloc(void) static void nfs_readhdr_free(struct nfs_pgio_header *rhdr) { + if (rhdr->res.scratch != NULL) + kfree(rhdr->res.scratch); kmem_cache_free(nfs_rdata_cachep, rhdr); } @@ -109,6 +111,14 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); +bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size) +{ + WARN_ON(hdr->res.scratch != NULL); + hdr->res.scratch = kmalloc(size, GFP_KERNEL); + return hdr->res.scratch != NULL; +} +EXPORT_SYMBOL_GPL(nfs_read_alloc_scratch); + static void nfs_readpage_release(struct nfs_page *req, int error) { struct inode *inode = d_inode(nfs_req_openctx(req)->dentry); From b372816ad610ddebb221ab7b2f7d29cad6a26135 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 28 Mar 2023 17:44:00 +0800 Subject: [PATCH 1274/2093] md: fix regression for null-ptr-deference in __md_stop() commit 433279beba1d4872da10b7b60a539e0cb828b32b upstream. Commit 3e453522593d ("md: Free resources in __md_stop") tried to fix null-ptr-deference for 'active_io' by moving percpu_ref_exit() to __md_stop(), however, the commit also moving 'writes_pending' to __md_stop(), and this will cause mdadm tests broken: BUG: kernel NULL pointer dereference, address: 0000000000000038 Oops: 0000 [#1] PREEMPT SMP CPU: 15 PID: 17830 Comm: mdadm Not tainted 6.3.0-rc3-next-20230324-00009-g520d37 RIP: 0010:free_percpu+0x465/0x670 Call Trace: __percpu_ref_exit+0x48/0x70 percpu_ref_exit+0x1a/0x90 __md_stop+0xe9/0x170 do_md_stop+0x1e1/0x7b0 md_ioctl+0x90c/0x1aa0 blkdev_ioctl+0x19b/0x400 vfs_ioctl+0x20/0x50 __x64_sys_ioctl+0xba/0xe0 do_syscall_64+0x6c/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0xcd And the problem can be reporduced 100% by following test: mdadm -CR /dev/md0 -l1 -n1 /dev/sda --force echo inactive > /sys/block/md0/md/array_state echo read-auto > /sys/block/md0/md/array_state echo inactive > /sys/block/md0/md/array_state Root cause: // start raid raid1_run mddev_init_writes_pending percpu_ref_init // inactive raid array_state_store do_md_stop __md_stop percpu_ref_exit // start raid again array_state_store do_md_run raid1_run mddev_init_writes_pending if (mddev->writes_pending.percpu_count_ptr) // won't reinit // inactive raid again ... percpu_ref_exit -> null-ptr-deference Before the commit, 'writes_pending' is exited when mddev is freed, and it's safe to restart raid because mddev_init_writes_pending() already make sure that 'writes_pending' will only be initialized once. Fix the prblem by moving 'writes_pending' back, it's a litter hard to find the relationship between alloc memory and free memory, however, code changes is much less and we lived with this for a long time already. Fixes: 3e453522593d ("md: Free resources in __md_stop") Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230328094400.1448955-1-yukuai1@huaweicloud.com Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index da718f6349dd..86b2acfba1a7 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6278,7 +6278,6 @@ static void __md_stop(struct mddev *mddev) module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - percpu_ref_exit(&mddev->writes_pending); percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); @@ -6293,6 +6292,7 @@ void md_stop(struct mddev *mddev) */ __md_stop_writes(mddev); __md_stop(mddev); + percpu_ref_exit(&mddev->writes_pending); } EXPORT_SYMBOL_GPL(md_stop); @@ -7859,6 +7859,7 @@ static void md_free_disk(struct gendisk *disk) { struct mddev *mddev = disk->private_data; + percpu_ref_exit(&mddev->writes_pending); mddev_free(mddev); } From abb597c85acbe9001be625cda5a8fe7747b0d344 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Mar 2023 17:46:38 -0800 Subject: [PATCH 1275/2093] clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro commit c28cd1f3433c7e339315d1ddacaeacf0fdfbe252 upstream. We already mark fwnodes as initialized when they are registered as clock providers. We do this so that fw_devlink can tell when a clock driver doesn't use the driver core framework to probe/initialize its device. This ensures fw_devlink doesn't block the consumers of such a clock provider indefinitely. However, some users of CLK_OF_DECLARE() macros don't use the same node that matches the macro as the node for the clock provider, but they initialize the entire node. To cover these cases, also mark the nodes that match the macros as initialized when the init callback function is called. An example of this is "stericsson,u8500-clks" that's handled using CLK_OF_DECLARE() and looks something like this: clocks { compatible = "stericsson,u8500-clks"; prcmu_clk: prcmu-clock { #clock-cells = <1>; }; prcc_pclk: prcc-periph-clock { #clock-cells = <2>; }; prcc_kclk: prcc-kernel-clock { #clock-cells = <2>; }; prcc_reset: prcc-reset-controller { #reset-cells = <2>; }; ... }; This patch makes sure that "clocks" is marked as initialized so that fw_devlink knows that all nodes under it have been initialized. If the driver creates struct devices for some of the subnodes, fw_devlink is smart enough to know to wait for those devices to probe, so no special handling is required for those cases. Cc: Greg Kroah-Hartman Reported-by: Linus Walleij Link: https://lore.kernel.org/lkml/CACRpkdamxDX6EBVjKX5=D3rkHp17f5pwGdBVhzFU90-0MHY6dQ@mail.gmail.com/ Fixes: 4a032827daa8 ("of: property: Simplify of_link_to_phandle()") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20230302014639.297514-1-saravanak@google.com Reviewed-by: Linus Walleij Tested-by: Linus Walleij Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- include/linux/clk-provider.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 267cd06b54a0..a607dcb69ec1 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1361,7 +1361,13 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) +#define CLK_OF_DECLARE(name, compat, fn) \ + static void __init name##_of_clk_init_declare(struct device_node *np) \ + { \ + fn(np); \ + fwnode_dev_initialized(of_fwnode_handle(np), true); \ + } \ + OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization From 59e0dd5bef6cda8cbe4abcfab145c562026a86c0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Mar 2023 15:26:13 +0200 Subject: [PATCH 1276/2093] treewide: Fix probing of devices in DT overlays commit 1a50d9403fb90cbe4dea0ec9fd0351d2ecbd8924 upstream. When loading a DT overlay that creates a device, the device is not probed, unless the DT overlay is unloaded and reloaded again. After the recent refactoring to improve fw_devlink, it no longer depends on the "compatible" property to identify which device tree nodes will become struct devices. fw_devlink now picks up dangling consumers (consumers pointing to descendent device tree nodes of a device that aren't converted to child devices) when a device is successfully bound to a driver. See __fw_devlink_pickup_dangling_consumers(). However, during DT overlay, a device's device tree node can have sub-nodes added/removed without unbinding/rebinding the driver. This difference in behavior between the normal device instantiation and probing flow vs. the DT overlay flow has a bunch of implications that are pointed out elsewhere[1]. One of them is that the fw_devlink logic to pick up dangling consumers is never exercised. This patch solves the fw_devlink issue by marking all DT nodes added by DT overlays with FWNODE_FLAG_NOT_DEVICE (fwnode that won't become device), and by clearing the flag when a struct device is actually created for the DT node. This way, fw_devlink knows not to have consumers waiting on these newly added DT nodes, and to propagate the dependency to an ancestor DT node that has the corresponding struct device. Based on a patch by Saravana Kannan, which covered only platform and spi devices. [1] https://lore.kernel.org/r/CAGETcx_bkuFaLCiPrAWCPQz+w79ccDp6=9e881qmK=vx3hBMyg@mail.gmail.com Fixes: 4a032827daa89350 ("of: property: Simplify of_link_to_phandle()") Link: https://lore.kernel.org/r/CAGETcx_+rhHvaC_HJXGrr5_WAd2+k5f=rWYnkCZ6z5bGX-wj4w@mail.gmail.com Signed-off-by: Geert Uytterhoeven Acked-by: Mark Brown Acked-by: Wolfram Sang # for I2C Acked-by: Shawn Guo Acked-by: Saravana Kannan Tested-by: Ivan Bornyakov Link: https://lore.kernel.org/r/e1fa546682ea4c8474ff997ab6244c5e11b6f8bc.1680182615.git.geert+renesas@glider.be Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/bus/imx-weim.c | 6 ++++++ drivers/i2c/i2c-core-of.c | 5 +++++ drivers/of/dynamic.c | 1 + drivers/of/platform.c | 5 +++++ drivers/spi/spi.c | 5 +++++ 5 files changed, 22 insertions(+) diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 55d917bd1f3f..64f9eacd1b38 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -331,6 +331,12 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, "Failed to setup timing for '%pOF'\n", rd->dn); if (!of_node_check_flag(rd->dn, OF_POPULATED)) { + /* + * Clear the flag before adding the device so that + * fw_devlink doesn't skip adding consumers to this + * device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; if (!of_platform_device_create(rd->dn, NULL, &pdev->dev)) { dev_err(&pdev->dev, "Failed to create child device '%pOF'\n", diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index 3ed74aa4b44b..1073f82d5dd4 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -244,6 +244,11 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; client = of_i2c_register_device(adap, rd->dn); if (IS_ERR(client)) { dev_err(&adap->dev, "failed to create client for '%pOF'\n", diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 4e436f2d13ae..95501b77ef31 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -225,6 +225,7 @@ static void __of_attach_node(struct device_node *np) np->sibling = np->parent->child; np->parent->child = np; of_node_clear_flag(np, OF_DETACHED); + np->fwnode.flags |= FWNODE_FLAG_NOT_DEVICE; } /** diff --git a/drivers/of/platform.c b/drivers/of/platform.c index e181c3f50f1d..bf96862cb700 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -741,6 +741,11 @@ static int of_platform_notify(struct notifier_block *nb, if (of_node_check_flag(rd->dn, OF_POPULATED)) return NOTIFY_OK; + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; /* pdev_parent may be NULL when no bus platform device */ pdev_parent = of_find_device_by_node(rd->dn->parent); pdev = of_platform_device_create(rd->dn, NULL, diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 5f9aedd1f0b6..151fef199c38 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4370,6 +4370,11 @@ static int of_spi_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } + /* + * Clear the flag before adding the device so that fw_devlink + * doesn't skip adding consumers to this device. + */ + rd->dn->fwnode.flags &= ~FWNODE_FLAG_NOT_DEVICE; spi = of_register_spi_device(ctlr, rd->dn); put_device(&ctlr->dev); From c74b1cd93f260d9691a17fce33553bb87341c9e2 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 8 Mar 2023 13:47:11 -0700 Subject: [PATCH 1277/2093] clk: Avoid invalid function names in CLK_OF_DECLARE() commit 5cf9d015be160e2d90d29ae74ef1364390e8fce8 upstream. After commit c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro"), drivers/clk/mvebu/kirkwood.c fails to build: drivers/clk/mvebu/kirkwood.c:358:1: error: expected identifier or '(' CLK_OF_DECLARE(98dx1135_clk, "marvell,mv98dx1135-core-clock", ^ include/linux/clk-provider.h:1367:21: note: expanded from macro 'CLK_OF_DECLARE' static void __init name##_of_clk_init_declare(struct device_node *np) \ ^ :124:1: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ C function names must start with either an alphabetic letter or an underscore. To avoid generating invalid function names from clock names, add two underscores to the beginning of the identifier. Fixes: c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro") Suggested-by: Saravana Kannan Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230308-clk_of_declare-fix-v1-1-317b741e2532@kernel.org Reviewed-by: Saravana Kannan Reported-by: Naresh Kamboju Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- include/linux/clk-provider.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index a607dcb69ec1..aefb06373720 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1362,12 +1362,12 @@ struct clk_hw_onecell_data { }; #define CLK_OF_DECLARE(name, compat, fn) \ - static void __init name##_of_clk_init_declare(struct device_node *np) \ + static void __init __##name##_of_clk_init_declare(struct device_node *np) \ { \ fn(np); \ fwnode_dev_initialized(of_fwnode_handle(np), true); \ } \ - OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) + OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization From 41cb5369cb8042a8490f619340c5e98a512ddfd7 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 30 Dec 2022 12:53:41 -0500 Subject: [PATCH 1278/2093] udf: initialize newblock to 0 commit 23970a1c9475b305770fd37bebfec7a10f263787 upstream. The clang build reports this error fs/udf/inode.c:805:6: error: variable 'newblock' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized] if (*err < 0) ^~~~~~~~ newblock is never set before error handling jump. Initialize newblock to 0 and remove redundant settings. Fixes: d8b39db5fab8 ("udf: Handle error when adding extent to a file") Reported-by: Nathan Chancellor Signed-off-by: Tom Rix Signed-off-by: Jan Kara Message-Id: <20221230175341.1629734-1-trix@redhat.com> Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 1cdad5e9950b..b574c2a9ce7b 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -696,7 +696,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, struct kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; - udf_pblk_t newblocknum, newblock; + udf_pblk_t newblocknum, newblock = 0; sector_t offset = 0; int8_t etype; struct udf_inode_info *iinfo = UDF_I(inode); @@ -799,7 +799,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) { *err = ret; - newblock = 0; goto out_free; } c = 0; @@ -862,7 +861,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goal, err); if (!newblocknum) { *err = -ENOSPC; - newblock = 0; goto out_free; } if (isBeyondEOF) From 09045dae0d902f9f78901a26c7ff1714976a38f9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 13 Sep 2023 09:43:05 +0200 Subject: [PATCH 1279/2093] Linux 6.1.53 Link: https://lore.kernel.org/r/20230911134633.619970489@linuxfoundation.org Tested-by: Shuah Khan Tested-by: Bagas Sanjaya Tested-by: Sudip Mukherjee Tested-by: Linux Kernel Functional Testing Tested-by: Takeshi Ogasawara Tested-by: Conor Dooley Tested-by: Jon Hunter Tested-by: Florian Fainelli Tested-by: Guenter Roeck Tested-by: Salvatore Bonaccorso Tested-by: Ron Economos Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index c627e0bdb19f..35fc0d62898d 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 52 +SUBLEVEL = 53 EXTRAVERSION = NAME = Curry Ramen From 82a49ac6c80a5bce4d12088f4fa5379b233210cd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 18 Sep 2023 11:42:41 +0000 Subject: [PATCH 1280/2093] ANDROID: GKI: fix up merge issue in drivers/scsi/storvsc_drv.c In commit 22cf11e16270 ("FROMGIT: scsi: core: Change the return type of .eh_timed_out()") from upstream, the function signature changed which conflicted with other changes in LTS releases, where the merge ended up being incorrect. Fix this up by resolving the issue by hand. Fixes: 22cf11e16270 ("FROMGIT: scsi: core: Change the return type of .eh_timed_out()") Change-Id: I8256ae9d6d308f6674e1bc6e5e2a29a03f8b6f3b Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/storvsc_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 7a1dc5c7c49e..11aa9813b8d1 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1670,9 +1670,9 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) * be unbounded on Azure. Reset the timer unconditionally to give the host a * chance to perform EH. */ -static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) +static enum scsi_timeout_action storvsc_eh_timed_out(struct scsi_cmnd *scmnd) { - return BLK_EH_RESET_TIMER; + return SCSI_EH_RESET_TIMER; } static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd) From 7164d74aae1cd32540c7cd43208cb292a8339896 Mon Sep 17 00:00:00 2001 From: Quan Tian Date: Tue, 5 Sep 2023 10:36:10 +0000 Subject: [PATCH 1281/2093] net/ipv6: SKB symmetric hash should incorporate transport ports commit a5e2151ff9d5852d0ababbbcaeebd9646af9c8d9 upstream. __skb_get_hash_symmetric() was added to compute a symmetric hash over the protocol, addresses and transport ports, by commit eb70db875671 ("packet: Use symmetric hash for PACKET_FANOUT_HASH."). It uses flow_keys_dissector_symmetric_keys as the flow_dissector to incorporate IPv4 addresses, IPv6 addresses and ports. However, it should not specify the flag as FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, which stops further dissection when an IPv6 flow label is encountered, making transport ports not being incorporated in such case. As a consequence, the symmetric hash is based on 5-tuple for IPv4 but 3-tuple for IPv6 when flow label is present. It caused a few problems, e.g. when nft symhash and openvswitch l4_sym rely on the symmetric hash to perform load balancing as different L4 flows between two given IPv6 addresses would always get the same symmetric hash, leading to uneven traffic distribution. Removing the use of FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL makes sure the symmetric hash is based on 5-tuple for both IPv4 and IPv6 consistently. Fixes: eb70db875671 ("packet: Use symmetric hash for PACKET_FANOUT_HASH.") Reported-by: Lars Ekman Closes: https://github.com/antrea-io/antrea/issues/5457 Signed-off-by: Quan Tian Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/flow_dissector.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 007730412947..3288490590f2 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1738,8 +1738,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, - &keys, NULL, 0, 0, 0, - FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } From a73d04c460521e45f257d28d73df096e41ece324 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 21 Dec 2022 21:19:00 -0700 Subject: [PATCH 1282/2093] mm: multi-gen LRU: rename lrugen->lists[] to lrugen->folios[] commit 6df1b2212950aae2b2188c6645ea18e2a9e3fdd5 upstream. lru_gen_folio will be chained into per-node lists by the coming lrugen->list. Link: https://lkml.kernel.org/r/20221222041905.2431096-3-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Roman Gushchin Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- Documentation/mm/multigen_lru.rst | 8 ++++---- include/linux/mm_inline.h | 4 ++-- include/linux/mmzone.h | 8 ++++---- mm/vmscan.c | 20 ++++++++++---------- 4 files changed, 20 insertions(+), 20 deletions(-) diff --git a/Documentation/mm/multigen_lru.rst b/Documentation/mm/multigen_lru.rst index d7062c6a8946..d8f721f98868 100644 --- a/Documentation/mm/multigen_lru.rst +++ b/Documentation/mm/multigen_lru.rst @@ -89,15 +89,15 @@ variables are monotonically increasing. Generation numbers are truncated into ``order_base_2(MAX_NR_GENS+1)`` bits in order to fit into the gen counter in ``folio->flags``. Each -truncated generation number is an index to ``lrugen->lists[]``. The +truncated generation number is an index to ``lrugen->folios[]``. The sliding window technique is used to track at least ``MIN_NR_GENS`` and at most ``MAX_NR_GENS`` generations. The gen counter stores a value within ``[1, MAX_NR_GENS]`` while a page is on one of -``lrugen->lists[]``; otherwise it stores zero. +``lrugen->folios[]``; otherwise it stores zero. Each generation is divided into multiple tiers. A page accessed ``N`` times through file descriptors is in tier ``order_base_2(N)``. Unlike -generations, tiers do not have dedicated ``lrugen->lists[]``. In +generations, tiers do not have dedicated ``lrugen->folios[]``. In contrast to moving across generations, which requires the LRU lock, moving across tiers only involves atomic operations on ``folio->flags`` and therefore has a negligible cost. A feedback loop @@ -127,7 +127,7 @@ page mapped by this PTE to ``(max_seq%MAX_NR_GENS)+1``. Eviction -------- The eviction consumes old generations. Given an ``lruvec``, it -increments ``min_seq`` when ``lrugen->lists[]`` indexed by +increments ``min_seq`` when ``lrugen->folios[]`` indexed by ``min_seq%MAX_NR_GENS`` becomes empty. To select a type and a tier to evict from, it first compares ``min_seq[]`` to select the older type. If both types are equally old, it selects the one whose first tier has diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e8ed225d8f7c..4ef6c09cc2ee 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -256,9 +256,9 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) - list_add_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else - list_add(&folio->lru, &lrugen->lists[gen][type][zone]); + list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5f74891556f3..323ee36df683 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -312,7 +312,7 @@ enum lruvec_flags { * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while - * a page is on one of lrugen->lists[]. Otherwise it stores 0. + * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the @@ -324,8 +324,8 @@ enum lruvec_flags { * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * - * PG_active is always cleared while a page is on one of lrugen->lists[] so that - * the aging needs not to worry about it. And it's set again when a page + * PG_active is always cleared while a page is on one of lrugen->folios[] so + * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * @@ -412,7 +412,7 @@ struct lru_gen_struct { /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ - struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ diff --git a/mm/vmscan.c b/mm/vmscan.c index d18296109aa7..0400e3b45079 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4258,7 +4258,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) /* prevent cold/hot inversion if force_scan is true */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { - struct list_head *head = &lrugen->lists[old_gen][type][zone]; + struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); @@ -4269,7 +4269,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); - list_move_tail(&folio->lru, &lrugen->lists[new_gen][type][zone]); + list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); if (!--remaining) return false; @@ -4297,7 +4297,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { - if (!list_empty(&lrugen->lists[gen][type][zone])) + if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } @@ -4762,7 +4762,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { - list_move(&folio->lru, &lrugen->lists[gen][type][zone]); + list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } @@ -4771,7 +4771,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); - list_move_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); WRITE_ONCE(lrugen->protected[hist][type][tier - 1], lrugen->protected[hist][type][tier - 1] + delta); @@ -4783,7 +4783,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { gen = folio_inc_gen(lruvec, folio, true); - list_move(&folio->lru, &lrugen->lists[gen][type][zone]); + list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } @@ -4850,7 +4850,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, for (zone = sc->reclaim_idx; zone >= 0; zone--) { LIST_HEAD(moved); int skipped = 0; - struct list_head *head = &lrugen->lists[gen][type][zone]; + struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); @@ -5250,7 +5250,7 @@ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { - if (!list_empty(&lrugen->lists[gen][type][zone])) + if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } @@ -5295,7 +5295,7 @@ static bool drain_evictable(struct lruvec *lruvec) int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { - struct list_head *head = &lruvec->lrugen.lists[gen][type][zone]; + struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; @@ -5832,7 +5832,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) - INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]); + INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); lruvec->mm_state.seq = MIN_NR_GENS; init_waitqueue_head(&lruvec->mm_state.wait); From f36791596176c938b1197afead39c0bb2a98ea24 Mon Sep 17 00:00:00 2001 From: Kalesh Singh Date: Tue, 1 Aug 2023 19:56:02 -0700 Subject: [PATCH 1283/2093] Multi-gen LRU: fix per-zone reclaim commit 669281ee7ef731fb5204df9d948669bf32a5e68d upstream. MGLRU has a LRU list for each zone for each type (anon/file) in each generation: long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; The min_seq (oldest generation) can progress independently for each type but the max_seq (youngest generation) is shared for both anon and file. This is to maintain a common frame of reference. In order for eviction to advance the min_seq of a type, all the per-zone lists in the oldest generation of that type must be empty. The eviction logic only considers pages from eligible zones for eviction or promotion. scan_folios() { ... for (zone = sc->reclaim_idx; zone >= 0; zone--) { ... sort_folio(); // Promote ... isolate_folio(); // Evict } ... } Consider the system has the movable zone configured and default 4 generations. The current state of the system is as shown below (only illustrating one type for simplicity): Type: ANON Zone DMA32 Normal Movable Device Gen 0 0 0 4GB 0 Gen 1 0 1GB 1MB 0 Gen 2 1MB 4GB 1MB 0 Gen 3 1MB 1MB 1MB 0 Now consider there is a GFP_KERNEL allocation request (eligible zone index <= Normal), evict_folios() will return without doing any work since there are no pages to scan in the eligible zones of the oldest generation. Reclaim won't make progress until triggered from a ZONE_MOVABLE allocation request; which may not happen soon if there is a lot of free memory in the movable zone. This can lead to OOM kills, although there is 1GB pages in the Normal zone of Gen 1 that we have not yet tried to reclaim. This issue is not seen in the conventional active/inactive LRU since there are no per-zone lists. If there are no (not enough) folios to scan in the eligible zones, move folios from ineligible zone (zone_index > reclaim_index) to the next generation. This allows for the progression of min_seq and reclaiming from the next generation (Gen 1). Qualcomm, Mediatek and raspberrypi [1] discovered this issue independently. [1] https://github.com/raspberrypi/linux/issues/5395 Link: https://lkml.kernel.org/r/20230802025606.346758-1-kaleshsingh@google.com Fixes: ac35a4902374 ("mm: multi-gen LRU: minimal implementation") Signed-off-by: Kalesh Singh Reported-by: Charan Teja Kalla Reported-by: Lecopzer Chen Tested-by: AngeloGioacchino Del Regno [mediatek] Tested-by: Charan Teja Kalla Cc: Yu Zhao Cc: Barry Song Cc: Brian Geffon Cc: Jan Alexander Steffens (heftig) Cc: Matthias Brugger Cc: Oleksandr Natalenko Cc: Qi Zheng Cc: Steven Barrett Cc: Suleiman Souhlal Cc: Suren Baghdasaryan Cc: Aneesh Kumar K V Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmscan.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 0400e3b45079..78efee423f58 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4728,7 +4728,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) * the eviction ******************************************************************************/ -static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) +static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, + int tier_idx) { bool success; int gen = folio_lru_gen(folio); @@ -4779,6 +4780,13 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) return true; } + /* ineligible */ + if (zone > sc->reclaim_idx) { + gen = folio_inc_gen(lruvec, folio, false); + list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); + return true; + } + /* waiting for writeback */ if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { @@ -4831,7 +4839,8 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { - int gen, zone; + int i; + int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; @@ -4847,9 +4856,10 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, gen = lru_gen_from_seq(lrugen->min_seq[type]); - for (zone = sc->reclaim_idx; zone >= 0; zone--) { + for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped = 0; + int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { @@ -4863,7 +4873,7 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, scanned += delta; - if (sort_folio(lruvec, folio, tier)) + if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); From fd459200ff81161119fef6e036fba47a7141227d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Sep 2023 14:57:03 +0100 Subject: [PATCH 1284/2093] io_uring: always lock in io_apoll_task_func From: Dylan Yudaken [ upstream commit c06c6c5d276707e04cedbcc55625e984922118aa ] This is required for the failure case (io_req_complete_failed) and is missing. The alternative would be to only lock in the failure path, however all of the non-error paths in io_poll_check_events that do not do not return IOU_POLL_NO_ACTION end up locking anyway. The only extraneous lock would be for the multishot poll overflowing the CQE ring, however multishot poll would probably benefit from being locked as it will allow completions to be batched. So it seems reasonable to lock always. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20221124093559.3780686-3-dylany@meta.com Signed-off-by: Jens Axboe Signed-off-by: Pavel Begunkov Signed-off-by: Greg Kroah-Hartman --- io_uring/poll.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/io_uring/poll.c b/io_uring/poll.c index 869e1d2a4413..a4084acaff91 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -360,11 +360,12 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) if (ret == IOU_POLL_NO_ACTION) return; + io_tw_lock(req->ctx, locked); io_poll_remove_entries(req); io_poll_tw_hash_eject(req, locked); if (ret == IOU_POLL_REMOVE_POLL_USE_RES) - io_req_complete_post(req); + io_req_task_complete(req, locked); else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE) io_req_task_submit(req, locked); else From 5afbf7fdb730c4e2734a9f502ea9b9750a3c745b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Sep 2023 14:57:04 +0100 Subject: [PATCH 1285/2093] io_uring: revert "io_uring fix multishot accept ordering" From: Dylan Yudaken [ upstream commit 515e26961295bee9da5e26916c27739dca6c10e1 ] This is no longer needed after commit aa1df3a360a0 ("io_uring: fix CQE reordering"), since all reordering is now taken care of. This reverts commit cbd25748545c ("io_uring: fix multishot accept ordering"). Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20221107125236.260132-2-dylany@meta.com Signed-off-by: Jens Axboe Signed-off-by: Pavel Begunkov Signed-off-by: Greg Kroah-Hartman --- io_uring/net.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/io_uring/net.c b/io_uring/net.c index 2b44126a876e..00b4433b6cd8 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1337,12 +1337,12 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } - if (ret >= 0 && - io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, false)) + if (ret < 0) + return ret; + if (io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, true)) goto retry; - io_req_set_res(req, ret, 0); - return (issue_flags & IO_URING_F_MULTISHOT) ? IOU_STOP_MULTISHOT : IOU_OK; + return -ECANCELED; } int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) From b04f22b68643d35b3e0823ea92295b203ef83bf3 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Sep 2023 14:57:05 +0100 Subject: [PATCH 1286/2093] io_uring/net: don't overflow multishot accept [ upstream commit 1bfed23349716a7811645336a7ce42c4b8f250bc ] Don't allow overflowing multishot accept CQEs, we want to limit the grows of the overflow list. Cc: stable@vger.kernel.org Fixes: 4e86a2c980137 ("io_uring: implement multishot mode for accept") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/7d0d749649244873772623dd7747966f516fe6e2.1691757663.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/net.c b/io_uring/net.c index 00b4433b6cd8..7245218fdbe2 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1339,7 +1339,7 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags) if (ret < 0) return ret; - if (io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, true)) + if (io_post_aux_cqe(ctx, req->cqe.user_data, ret, IORING_CQE_F_MORE, false)) goto retry; return -ECANCELED; From 605d055452e7abed4aca012953aecc79c09baf12 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Sep 2023 14:57:06 +0100 Subject: [PATCH 1287/2093] io_uring: break out of iowq iopoll on teardown [ upstream commit 45500dc4e01c167ee063f3dcc22f51ced5b2b1e9 ] io-wq will retry iopoll even when it failed with -EAGAIN. If that races with task exit, which sets TIF_NOTIFY_SIGNAL for all its workers, such workers might potentially infinitely spin retrying iopoll again and again and each time failing on some allocation / waiting / etc. Don't keep spinning if io-wq is dying. Fixes: 561fb04a6a225 ("io_uring: replace workqueue usage with io-wq") Cc: stable@vger.kernel.org Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 10 ++++++++++ io_uring/io-wq.h | 1 + io_uring/io_uring.c | 2 ++ 3 files changed, 13 insertions(+) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 411bb2d1acd4..dc3d4b835622 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -181,6 +181,16 @@ static void io_worker_ref_put(struct io_wq *wq) complete(&wq->worker_done); } +bool io_wq_worker_stopped(void) +{ + struct io_worker *worker = current->worker_private; + + if (WARN_ON_ONCE(!io_wq_current_is_worker())) + return true; + + return test_bit(IO_WQ_BIT_EXIT, &worker->wqe->wq->state); +} + static void io_worker_cancel_cb(struct io_worker *worker) { struct io_wqe_acct *acct = io_wqe_get_acct(worker); diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index 31228426d192..31cc5cc9048c 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -52,6 +52,7 @@ void io_wq_hash_work(struct io_wq_work *work, void *val); int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); int io_wq_max_workers(struct io_wq *wq, int *new_count); +bool io_wq_worker_stopped(void); static inline bool io_wq_is_hashed(struct io_wq_work *work) { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 6d455e2428b9..7c8e81057eb1 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1823,6 +1823,8 @@ void io_wq_submit_work(struct io_wq_work *work) if (!needs_poll) { if (!(req->ctx->flags & IORING_SETUP_IOPOLL)) break; + if (io_wq_worker_stopped()) + break; cond_resched(); continue; } From 9704cfcf1fa9bd7b7a2e7d3adf892baa106d771d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Sep 2023 14:57:07 +0100 Subject: [PATCH 1288/2093] io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used From: Jens Axboe [ upstream commit ebdfefc09c6de7897962769bd3e63a2ff443ebf5 ] If we setup the ring with SQPOLL, then that polling thread has its own io-wq setup. This means that if the application uses IORING_REGISTER_IOWQ_AFF to set the io-wq affinity, we should not be setting it for the invoking task, but rather the sqpoll task. Add an sqpoll helper that parks the thread and updates the affinity, and use that one if we're using SQPOLL. Fixes: fe76421d1da1 ("io_uring: allow user configurable IO thread CPU affinity") Cc: stable@vger.kernel.org # 5.10+ Link: https://github.com/axboe/liburing/discussions/884 Signed-off-by: Jens Axboe Signed-off-by: Pavel Begunkov Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 7 +++++-- io_uring/io-wq.h | 2 +- io_uring/io_uring.c | 29 ++++++++++++++++++----------- io_uring/sqpoll.c | 15 +++++++++++++++ io_uring/sqpoll.h | 1 + 5 files changed, 40 insertions(+), 14 deletions(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index dc3d4b835622..98ac9dbcec2f 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1350,13 +1350,16 @@ static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node) return __io_wq_cpu_online(wq, cpu, false); } -int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask) +int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask) { int i; + if (!tctx || !tctx->io_wq) + return -EINVAL; + rcu_read_lock(); for_each_node(i) { - struct io_wqe *wqe = wq->wqes[i]; + struct io_wqe *wqe = tctx->io_wq->wqes[i]; if (mask) cpumask_copy(wqe->cpu_mask, mask); diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index 31cc5cc9048c..2b2a6406dd8e 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -50,7 +50,7 @@ void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); -int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); +int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask); int io_wq_max_workers(struct io_wq *wq, int *new_count); bool io_wq_worker_stopped(void); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7c8e81057eb1..f413ebed81ab 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3835,16 +3835,28 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx) return 0; } +static __cold int __io_register_iowq_aff(struct io_ring_ctx *ctx, + cpumask_var_t new_mask) +{ + int ret; + + if (!(ctx->flags & IORING_SETUP_SQPOLL)) { + ret = io_wq_cpu_affinity(current->io_uring, new_mask); + } else { + mutex_unlock(&ctx->uring_lock); + ret = io_sqpoll_wq_cpu_affinity(ctx, new_mask); + mutex_lock(&ctx->uring_lock); + } + + return ret; +} + static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, unsigned len) { - struct io_uring_task *tctx = current->io_uring; cpumask_var_t new_mask; int ret; - if (!tctx || !tctx->io_wq) - return -EINVAL; - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) return -ENOMEM; @@ -3865,19 +3877,14 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, return -EFAULT; } - ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); + ret = __io_register_iowq_aff(ctx, new_mask); free_cpumask_var(new_mask); return ret; } static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx) { - struct io_uring_task *tctx = current->io_uring; - - if (!tctx || !tctx->io_wq) - return -EINVAL; - - return io_wq_cpu_affinity(tctx->io_wq, NULL); + return __io_register_iowq_aff(ctx, NULL); } static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 6ffa5cf1bbb8..2949959cbe60 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -423,3 +423,18 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, io_sq_thread_finish(ctx); return ret; } + +__cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, + cpumask_var_t mask) +{ + struct io_sq_data *sqd = ctx->sq_data; + int ret = -EINVAL; + + if (sqd) { + io_sq_thread_park(sqd); + ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask); + io_sq_thread_unpark(sqd); + } + + return ret; +} diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h index 0c3fbcd1f583..36245f1afa5e 100644 --- a/io_uring/sqpoll.h +++ b/io_uring/sqpoll.h @@ -27,3 +27,4 @@ void io_sq_thread_park(struct io_sq_data *sqd); void io_sq_thread_unpark(struct io_sq_data *sqd); void io_put_sq_data(struct io_sq_data *sqd); int io_sqpoll_wait_sq(struct io_ring_ctx *ctx); +int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask); From 3e8b9b06de9d88e04f0a1daeab3ddf64af2e26a2 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 12 Sep 2023 14:57:08 +0100 Subject: [PATCH 1289/2093] io_uring: Don't set affinity on a dying sqpoll thread From: Gabriel Krisman Bertazi [ upstream commit bd6fc5da4c51107e1e0cec4a3a07963d1dae2c84 ] Syzbot reported a null-ptr-deref of sqd->thread inside io_sqpoll_wq_cpu_affinity. It turns out the sqd->thread can go away from under us during io_uring_register, in case the process gets a fatal signal during io_uring_register. It is not particularly hard to hit the race, and while I am not sure this is the exact case hit by syzbot, it solves it. Finally, checking ->thread is enough to close the race because we locked sqd while "parking" the thread, thus preventing it from going away. I reproduced it fairly consistently with a program that does: int main(void) { ... io_uring_queue_init(RING_LEN, &ring1, IORING_SETUP_SQPOLL); while (1) { io_uring_register_iowq_aff(ring, 1, &mask); } } Executed in a loop with timeout to trigger SIGTERM: while true; do timeout 1 /a.out ; done This will hit the following BUG() in very few attempts. BUG: kernel NULL pointer dereference, address: 00000000000007a8 PGD 800000010e949067 P4D 800000010e949067 PUD 10e46e067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 15715 Comm: dead-sqpoll Not tainted 6.5.0-rc7-next-20230825-g193296236fa0-dirty #23 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:io_sqpoll_wq_cpu_affinity+0x27/0x70 Code: 90 90 90 0f 1f 44 00 00 55 53 48 8b 9f 98 03 00 00 48 85 db 74 4f 48 89 df 48 89 f5 e8 e2 f8 ff ff 48 8b 43 38 48 85 c0 74 22 <48> 8b b8 a8 07 00 00 48 89 ee e8 ba b1 00 00 48 89 df 89 c5 e8 70 RSP: 0018:ffffb04040ea7e70 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff93c010749e40 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffffffa7653331 RDI: 00000000ffffffff RBP: ffffb04040ea7eb8 R08: 0000000000000000 R09: c0000000ffffdfff R10: ffff93c01141b600 R11: ffffb04040ea7d18 R12: ffff93c00ea74840 R13: 0000000000000011 R14: 0000000000000000 R15: ffff93c00ea74800 FS: 00007fb7c276ab80(0000) GS:ffff93c36f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000007a8 CR3: 0000000111634003 CR4: 0000000000370ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __die_body+0x1a/0x60 ? page_fault_oops+0x154/0x440 ? do_user_addr_fault+0x174/0x7b0 ? exc_page_fault+0x63/0x140 ? asm_exc_page_fault+0x22/0x30 ? io_sqpoll_wq_cpu_affinity+0x27/0x70 __io_register_iowq_aff+0x2b/0x60 __io_uring_register+0x614/0xa70 __x64_sys_io_uring_register+0xaa/0x1a0 do_syscall_64+0x3a/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 RIP: 0033:0x7fb7c226fec9 Code: 2e 00 b8 ca 00 00 00 0f 05 eb a5 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 97 7f 2d 00 f7 d8 64 89 01 48 RSP: 002b:00007ffe2c0674f8 EFLAGS: 00000246 ORIG_RAX: 00000000000001ab RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fb7c226fec9 RDX: 00007ffe2c067530 RSI: 0000000000000011 RDI: 0000000000000003 RBP: 00007ffe2c0675d0 R08: 00007ffe2c067550 R09: 00007ffe2c067550 R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe2c067750 R14: 0000000000000000 R15: 0000000000000000 Modules linked in: CR2: 00000000000007a8 ---[ end trace 0000000000000000 ]--- Reported-by: syzbot+c74fea926a78b8a91042@syzkaller.appspotmail.com Fixes: ebdfefc09c6d ("io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used") Signed-off-by: Gabriel Krisman Bertazi Link: https://lore.kernel.org/r/87v8cybuo6.fsf@suse.de Signed-off-by: Jens Axboe Signed-off-by: Pavel Begunkov Signed-off-by: Greg Kroah-Hartman --- io_uring/sqpoll.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 2949959cbe60..7b6facf529b8 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -432,7 +432,9 @@ __cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, if (sqd) { io_sq_thread_park(sqd); - ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask); + /* Don't set affinity for a dying thread */ + if (sqd->thread) + ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask); io_sq_thread_unpark(sqd); } From 98d3e7c5f757577394f036e0301db9e570342566 Mon Sep 17 00:00:00 2001 From: Gurchetan Singh Date: Fri, 7 Jul 2023 14:31:24 -0700 Subject: [PATCH 1290/2093] drm/virtio: Conditionally allocate virtio_gpu_fence commit 70d1ace56db6c79d39dbe9c0d5244452b67e2fde upstream. We don't want to create a fence for every command submission. It's only necessary when userspace provides a waitable token for submission. This could be: 1) bo_handles, to be used with VIRTGPU_WAIT 2) out_fence_fd, to be used with dma_fence apis 3) a ring_idx provided with VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK + DRM event API 4) syncobjs in the future The use case for just submitting a command to the host, and expecting no response. For example, gfxstream has GFXSTREAM_CONTEXT_PING that just wakes up the host side worker threads. There's also CROSS_DOMAIN_CMD_SEND which just sends data to the Wayland server. This prevents the need to signal the automatically created virtio_gpu_fence. In addition, VIRTGPU_EXECBUF_RING_IDX is checked when creating a DRM event object. VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is already defined in terms of per-context rings. It was theoretically possible to create a DRM event on the global timeline (ring_idx == 0), if the context enabled DRM event polling. However, that wouldn't work and userspace (Sommelier). Explicitly disallow it for clarity. Signed-off-by: Gurchetan Singh Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Dmitry Osipenko # edited coding style Link: https://patchwork.freedesktop.org/patch/msgid/20230707213124.494-1-gurchetansingh@chromium.org Signed-off-by: Alyssa Ross Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 30 +++++++++++++++----------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index da45215a933d..bc8c1e9a845f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -43,13 +43,9 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev, struct virtio_gpu_fence *fence, uint32_t ring_idx) { - struct virtio_gpu_fpriv *vfpriv = file->driver_priv; struct virtio_gpu_fence_event *e = NULL; int ret; - if (!(vfpriv->ring_idx_mask & BIT_ULL(ring_idx))) - return 0; - e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) return -ENOMEM; @@ -121,6 +117,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_fpriv *vfpriv = file->driver_priv; struct virtio_gpu_fence *out_fence; + bool drm_fence_event; int ret; uint32_t *bo_handles = NULL; void __user *user_bo_handles = NULL; @@ -216,15 +213,24 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, goto out_memdup; } - out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx); - if(!out_fence) { - ret = -ENOMEM; - goto out_unresv; - } + if ((exbuf->flags & VIRTGPU_EXECBUF_RING_IDX) && + (vfpriv->ring_idx_mask & BIT_ULL(ring_idx))) + drm_fence_event = true; + else + drm_fence_event = false; - ret = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx); - if (ret) - goto out_unresv; + if ((exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) || + exbuf->num_bo_handles || + drm_fence_event) + out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx); + else + out_fence = NULL; + + if (drm_fence_event) { + ret = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx); + if (ret) + goto out_unresv; + } if (out_fence_fd >= 0) { sync_file = sync_file_create(&out_fence->f); From faf7e224b4fab44dc1301ed439da1e3461f5a317 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:56 +0530 Subject: [PATCH 1291/2093] scsi: qla2xxx: Adjust IOCB resource on qpair create commit efa74a62aaa2429c04fe6cb277b3bf6739747d86 upstream. During NVMe queue creation, a new qpair is created. FW resource limit needs to be re-adjusted to take into account the new qpair. Otherwise, NVMe command can not go through. This issue was discovered while testing/forcing FW execution to fail at load time. Add call to readjust IOCB and exchange limit. In addition, get FW state command and require FW to be running. Otherwise, error is generated. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-3-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_gbl.h | 1 + drivers/scsi/qla2xxx/qla_init.c | 52 +++++++++++++++++++++------------ drivers/scsi/qla2xxx/qla_mbx.c | 3 ++ drivers/scsi/qla2xxx/qla_nvme.c | 1 + 4 files changed, 38 insertions(+), 19 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 316122709b0e..2e4537f9e5b5 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -143,6 +143,7 @@ void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess); void qla_edif_clear_appdata(struct scsi_qla_host *vha, struct fc_port *fcport); const char *sc_to_str(uint16_t cmd); +void qla_adjust_iocb_limit(scsi_qla_host_t *vha); /* * Global Data in qla_os.c source file. diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 30bbf33e3a6a..a45d54963a86 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4148,41 +4148,55 @@ qla24xx_detect_sfp(scsi_qla_host_t *vha) return ha->flags.lr_detected; } -void qla_init_iocb_limit(scsi_qla_host_t *vha) +static void __qla_adjust_iocb_limit(struct qla_qpair *qpair) { - u16 i, num_qps; - u32 limit; - struct qla_hw_data *ha = vha->hw; + u8 num_qps; + u16 limit; + struct qla_hw_data *ha = qpair->vha->hw; num_qps = ha->num_qpairs + 1; limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100; - ha->base_qpair->fwres.iocbs_total = ha->orig_fw_iocb_count; - ha->base_qpair->fwres.iocbs_limit = limit; - ha->base_qpair->fwres.iocbs_qp_limit = limit / num_qps; - ha->base_qpair->fwres.iocbs_used = 0; + qpair->fwres.iocbs_total = ha->orig_fw_iocb_count; + qpair->fwres.iocbs_limit = limit; + qpair->fwres.iocbs_qp_limit = limit / num_qps; - ha->base_qpair->fwres.exch_total = ha->orig_fw_xcb_count; - ha->base_qpair->fwres.exch_limit = (ha->orig_fw_xcb_count * - QLA_IOCB_PCT_LIMIT) / 100; + qpair->fwres.exch_total = ha->orig_fw_xcb_count; + qpair->fwres.exch_limit = (ha->orig_fw_xcb_count * + QLA_IOCB_PCT_LIMIT) / 100; +} + +void qla_init_iocb_limit(scsi_qla_host_t *vha) +{ + u8 i; + struct qla_hw_data *ha = vha->hw; + + __qla_adjust_iocb_limit(ha->base_qpair); + ha->base_qpair->fwres.iocbs_used = 0; ha->base_qpair->fwres.exch_used = 0; for (i = 0; i < ha->max_qpairs; i++) { if (ha->queue_pair_map[i]) { - ha->queue_pair_map[i]->fwres.iocbs_total = - ha->orig_fw_iocb_count; - ha->queue_pair_map[i]->fwres.iocbs_limit = limit; - ha->queue_pair_map[i]->fwres.iocbs_qp_limit = - limit / num_qps; + __qla_adjust_iocb_limit(ha->queue_pair_map[i]); ha->queue_pair_map[i]->fwres.iocbs_used = 0; - ha->queue_pair_map[i]->fwres.exch_total = ha->orig_fw_xcb_count; - ha->queue_pair_map[i]->fwres.exch_limit = - (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100; ha->queue_pair_map[i]->fwres.exch_used = 0; } } } +void qla_adjust_iocb_limit(scsi_qla_host_t *vha) +{ + u8 i; + struct qla_hw_data *ha = vha->hw; + + __qla_adjust_iocb_limit(ha->base_qpair); + + for (i = 0; i < ha->max_qpairs; i++) { + if (ha->queue_pair_map[i]) + __qla_adjust_iocb_limit(ha->queue_pair_map[i]); + } +} + /** * qla2x00_setup_chip() - Load and start RISC firmware. * @vha: HA context diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 359595a64664..3c2ee21195ed 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -2213,6 +2213,9 @@ qla2x00_get_firmware_state(scsi_qla_host_t *vha, uint16_t *states) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1054, "Entered %s.\n", __func__); + if (!ha->flags.fw_started) + return QLA_FUNCTION_FAILED; + mcp->mb[0] = MBC_GET_FIRMWARE_STATE; mcp->out_mb = MBX_0; if (IS_FWI2_CAPABLE(vha->hw)) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 57545d5e82b9..ebb8786c4c99 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -132,6 +132,7 @@ static int qla_nvme_alloc_queue(struct nvme_fc_local_port *lport, "Failed to allocate qpair\n"); return -EINVAL; } + qla_adjust_iocb_limit(vha); } *handle = qpair; From 820010cfe5f85ef084d5d694aaed3019a4ce87ec Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:57 +0530 Subject: [PATCH 1292/2093] scsi: qla2xxx: Limit TMF to 8 per function commit a8ec192427e0516436e61f9ca9eb49c54eadfe0a upstream. Per FW recommendation, 8 TMF's can be outstanding for each function. Previously, it allowed 8 per target. Limit TMF to 8 per function. Cc: stable@vger.kernel.org Fixes: 6a87679626b5 ("scsi: qla2xxx: Fix task management cmd fail due to unavailable resource") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-4-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_def.h | 9 +++--- drivers/scsi/qla2xxx/qla_init.c | 55 ++++++++++++++++++++------------- drivers/scsi/qla2xxx/qla_os.c | 2 ++ 3 files changed, 41 insertions(+), 25 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 5a2f629d18e6..84929c0e7eb6 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -458,6 +458,7 @@ static inline be_id_t port_id_to_be_id(port_id_t port_id) } struct tmf_arg { + struct list_head tmf_elem; struct qla_qpair *qpair; struct fc_port *fcport; struct scsi_qla_host *vha; @@ -2534,7 +2535,6 @@ enum rscn_addr_format { typedef struct fc_port { struct list_head list; struct scsi_qla_host *vha; - struct list_head tmf_pending; unsigned int conf_compl_supported:1; unsigned int deleted:2; @@ -2555,9 +2555,6 @@ typedef struct fc_port { unsigned int do_prli_nvme:1; uint8_t nvme_flag; - uint8_t active_tmf; -#define MAX_ACTIVE_TMF 8 - uint8_t node_name[WWN_SIZE]; uint8_t port_name[WWN_SIZE]; port_id_t d_id; @@ -4640,6 +4637,8 @@ struct qla_hw_data { uint32_t flt_region_aux_img_status_sec; }; uint8_t active_image; + uint8_t active_tmf; +#define MAX_ACTIVE_TMF 8 /* Needed for BEACON */ uint16_t beacon_blink_led; @@ -4654,6 +4653,8 @@ struct qla_hw_data { struct qla_msix_entry *msix_entries; + struct list_head tmf_pending; + struct list_head tmf_active; struct list_head vp_list; /* list of VP */ unsigned long vp_idx_map[(MAX_MULTI_ID_FABRIC / 8) / sizeof(unsigned long)]; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index a45d54963a86..02684892f5f6 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2187,30 +2187,42 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) return rval; } -static void qla_put_tmf(fc_port_t *fcport) +static void qla_put_tmf(struct tmf_arg *arg) { - struct scsi_qla_host *vha = fcport->vha; + struct scsi_qla_host *vha = arg->vha; struct qla_hw_data *ha = vha->hw; unsigned long flags; spin_lock_irqsave(&ha->tgt.sess_lock, flags); - fcport->active_tmf--; + ha->active_tmf--; + list_del(&arg->tmf_elem); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); } static -int qla_get_tmf(fc_port_t *fcport) +int qla_get_tmf(struct tmf_arg *arg) { - struct scsi_qla_host *vha = fcport->vha; + struct scsi_qla_host *vha = arg->vha; struct qla_hw_data *ha = vha->hw; unsigned long flags; + fc_port_t *fcport = arg->fcport; int rc = 0; - LIST_HEAD(tmf_elem); + struct tmf_arg *t; spin_lock_irqsave(&ha->tgt.sess_lock, flags); - list_add_tail(&tmf_elem, &fcport->tmf_pending); + list_for_each_entry(t, &ha->tmf_active, tmf_elem) { + if (t->fcport == arg->fcport && t->lun == arg->lun) { + /* reject duplicate TMF */ + ql_log(ql_log_warn, vha, 0x802c, + "found duplicate TMF. Nexus=%ld:%06x:%llu.\n", + vha->host_no, fcport->d_id.b24, arg->lun); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return -EINVAL; + } + } - while (fcport->active_tmf >= MAX_ACTIVE_TMF) { + list_add_tail(&arg->tmf_elem, &ha->tmf_pending); + while (ha->active_tmf >= MAX_ACTIVE_TMF) { spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); msleep(1); @@ -2222,15 +2234,17 @@ int qla_get_tmf(fc_port_t *fcport) rc = EIO; break; } - if (fcport->active_tmf < MAX_ACTIVE_TMF && - list_is_first(&tmf_elem, &fcport->tmf_pending)) + if (ha->active_tmf < MAX_ACTIVE_TMF && + list_is_first(&arg->tmf_elem, &ha->tmf_pending)) break; } - list_del(&tmf_elem); + list_del(&arg->tmf_elem); - if (!rc) - fcport->active_tmf++; + if (!rc) { + ha->active_tmf++; + list_add_tail(&arg->tmf_elem, &ha->tmf_active); + } spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); @@ -2252,15 +2266,18 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, a.vha = fcport->vha; a.fcport = fcport; a.lun = lun; + a.flags = flags; + INIT_LIST_HEAD(&a.tmf_elem); + if (flags & (TCF_LUN_RESET|TCF_ABORT_TASK_SET|TCF_CLEAR_TASK_SET|TCF_CLEAR_ACA)) { a.modifier = MK_SYNC_ID_LUN; - - if (qla_get_tmf(fcport)) - return QLA_FUNCTION_FAILED; } else { a.modifier = MK_SYNC_ID; } + if (qla_get_tmf(&a)) + return QLA_FUNCTION_FAILED; + if (vha->hw->mqenable) { for (i = 0; i < vha->hw->num_qpairs; i++) { qpair = vha->hw->queue_pair_map[i]; @@ -2286,13 +2303,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, goto bailout; a.qpair = vha->hw->base_qpair; - a.flags = flags; rval = __qla2x00_async_tm_cmd(&a); bailout: - if (a.modifier == MK_SYNC_ID_LUN) - qla_put_tmf(fcport); - + qla_put_tmf(&a); return rval; } @@ -5542,7 +5556,6 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) INIT_WORK(&fcport->reg_work, qla_register_fcport_fn); INIT_LIST_HEAD(&fcport->gnl_entry); INIT_LIST_HEAD(&fcport->list); - INIT_LIST_HEAD(&fcport->tmf_pending); INIT_LIST_HEAD(&fcport->sess_cmd_list); spin_lock_init(&fcport->sess_cmd_lock); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index ed70eb884786..bde536e3e752 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3002,6 +3002,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) atomic_set(&ha->num_pend_mbx_stage3, 0); atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD); ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD; + INIT_LIST_HEAD(&ha->tmf_pending); + INIT_LIST_HEAD(&ha->tmf_active); /* Assign ISP specific operations. */ if (IS_QLA2100(ha)) { From cd06c45b326e44f0d21dc1b3fa23e71f46847e28 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:55 +0530 Subject: [PATCH 1293/2093] scsi: qla2xxx: Fix deletion race condition commit 6dfe4344c168c6ca20fe7640649aacfcefcccb26 upstream. System crash when using debug kernel due to link list corruption. The cause of the link list corruption is due to session deletion was allowed to queue up twice. Here's the internal trace that show the same port was allowed to double queue for deletion on different cpu. 20808683956 015 qla2xxx [0000:13:00.1]-e801:4: Scheduling sess ffff93ebf9306800 for deletion 50:06:0e:80:12:48:ff:50 fc4_type 1 20808683957 027 qla2xxx [0000:13:00.1]-e801:4: Scheduling sess ffff93ebf9306800 for deletion 50:06:0e:80:12:48:ff:50 fc4_type 1 Move the clearing/setting of deleted flag lock. Cc: stable@vger.kernel.org Fixes: 726b85487067 ("qla2xxx: Add framework for async fabric discovery") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-2-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 16 ++++++++++++++-- drivers/scsi/qla2xxx/qla_target.c | 14 +++++++------- 2 files changed, 21 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 02684892f5f6..66527a2f5710 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -502,6 +502,7 @@ static void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea) { struct fc_port *fcport = ea->fcport; + unsigned long flags; ql_dbg(ql_dbg_disc, vha, 0x20d2, "%s %8phC DS %d LS %d rc %d login %d|%d rscn %d|%d lid %d\n", @@ -516,9 +517,15 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea) ql_dbg(ql_dbg_disc, vha, 0x2066, "%s %8phC: adisc fail: post delete\n", __func__, ea->fcport->port_name); + + spin_lock_irqsave(&vha->work_lock, flags); /* deleted = 0 & logout_on_delete = force fw cleanup */ - fcport->deleted = 0; + if (fcport->deleted == QLA_SESS_DELETED) + fcport->deleted = 0; + fcport->logout_on_delete = 1; + spin_unlock_irqrestore(&vha->work_lock, flags); + qlt_schedule_sess_for_deletion(ea->fcport); return; } @@ -1440,7 +1447,6 @@ void __qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); ea->fcport->login_gen++; - ea->fcport->deleted = 0; ea->fcport->logout_on_delete = 1; if (!ea->fcport->login_succ && !IS_SW_RESV_ADDR(ea->fcport->d_id)) { @@ -6143,6 +6149,8 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) void qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) { + unsigned long flags; + if (IS_SW_RESV_ADDR(fcport->d_id)) return; @@ -6152,7 +6160,11 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) qla2x00_set_fcport_disc_state(fcport, DSC_UPD_FCPORT); fcport->login_retry = vha->hw->login_retry_count; fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT); + + spin_lock_irqsave(&vha->work_lock, flags); fcport->deleted = 0; + spin_unlock_irqrestore(&vha->work_lock, flags); + if (vha->hw->current_topology == ISP_CFG_NL) fcport->logout_on_delete = 0; else diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index bb754a950802..545473a0ffc8 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1085,10 +1085,6 @@ void qlt_free_session_done(struct work_struct *work) (struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO); } - spin_lock_irqsave(&vha->work_lock, flags); - sess->flags &= ~FCF_ASYNC_SENT; - spin_unlock_irqrestore(&vha->work_lock, flags); - spin_lock_irqsave(&ha->tgt.sess_lock, flags); if (sess->se_sess) { sess->se_sess = NULL; @@ -1098,7 +1094,6 @@ void qlt_free_session_done(struct work_struct *work) qla2x00_set_fcport_disc_state(sess, DSC_DELETED); sess->fw_login_state = DSC_LS_PORT_UNAVAIL; - sess->deleted = QLA_SESS_DELETED; if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) { vha->fcport_count--; @@ -1150,10 +1145,15 @@ void qlt_free_session_done(struct work_struct *work) sess->explicit_logout = 0; spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - sess->free_pending = 0; qla2x00_dfs_remove_rport(vha, sess); + spin_lock_irqsave(&vha->work_lock, flags); + sess->flags &= ~FCF_ASYNC_SENT; + sess->deleted = QLA_SESS_DELETED; + sess->free_pending = 0; + spin_unlock_irqrestore(&vha->work_lock, flags); + ql_dbg(ql_dbg_disc, vha, 0xf001, "Unregistration of sess %p %8phC finished fcp_cnt %d\n", sess, sess->port_name, vha->fcport_count); @@ -1202,12 +1202,12 @@ void qlt_unreg_sess(struct fc_port *sess) * management from being sent. */ sess->flags |= FCF_ASYNC_SENT; + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; spin_unlock_irqrestore(&sess->vha->work_lock, flags); if (sess->se_sess) vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess); - sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; qla2x00_set_fcport_disc_state(sess, DSC_DELETE_PEND); sess->last_rscn_gen = sess->rscn_gen; sess->last_login_gen = sess->login_gen; From 6e44a7e2a0bc5f98419f0417b2ebdca75ca1bd12 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:03 +0530 Subject: [PATCH 1294/2093] scsi: qla2xxx: fix inconsistent TMF timeout commit 009e7fe4a1ed52276b332842a6b6e23b07200f2d upstream. Different behavior were experienced of session being torn down vs not when TMF is timed out. When FW detects the time out, the session is torn down. When driver detects the time out, the session is not torn down. Allow TMF error to return to upper layer without session tear down. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-10-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_isr.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index b41d604ca9bc..246e74cb929f 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2539,7 +2539,6 @@ qla24xx_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, void *tsk) case CS_PORT_BUSY: case CS_INCOMPLETE: case CS_PORT_UNAVAILABLE: - case CS_TIMEOUT: case CS_RESET: if (atomic_read(&fcport->state) == FCS_ONLINE) { ql_dbg(ql_dbg_disc, fcport->vha, 0x3021, From ddb8fa05981c266067faa9525853a55924a79c7f Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:58 +0530 Subject: [PATCH 1295/2093] scsi: qla2xxx: Fix command flush during TMF commit da7c21b72aa86e990af5f73bce6590b8d8d148d0 upstream. For each TMF request, driver iterates through each qpair and flushes commands associated to the TMF. At the end of the qpair flush, a Marker is used to complete the flush transaction. This process was repeated for each qpair. The multiple flush and marker for this TMF request seems to cause confusion for FW. Instead, 1 flush is sent to FW. Driver would wait for FW to go through all the I/Os on each qpair to be read then return. Driver then closes out the transaction with a Marker. Cc: stable@vger.kernel.org Fixes: d90171dd0da5 ("scsi: qla2xxx: Multi-que support for TMF") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-5-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 74 +++++++++++++++++---------------- drivers/scsi/qla2xxx/qla_iocb.c | 1 + drivers/scsi/qla2xxx/qla_os.c | 9 ++-- 3 files changed, 45 insertions(+), 39 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 66527a2f5710..8326b9474c3e 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2003,12 +2003,11 @@ qla2x00_tmf_iocb_timeout(void *data) int rc, h; unsigned long flags; - if (sp->type == SRB_MARKER) { - complete(&tmf->u.tmf.comp); - return; - } + if (sp->type == SRB_MARKER) + rc = QLA_FUNCTION_FAILED; + else + rc = qla24xx_async_abort_cmd(sp, false); - rc = qla24xx_async_abort_cmd(sp, false); if (rc) { spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags); for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) { @@ -2130,6 +2129,17 @@ static void qla2x00_tmf_sp_done(srb_t *sp, int res) complete(&tmf->u.tmf.comp); } +static int qla_tmf_wait(struct tmf_arg *arg) +{ + /* there are only 2 types of error handling that reaches here, lun or target reset */ + if (arg->flags & (TCF_LUN_RESET | TCF_ABORT_TASK_SET | TCF_CLEAR_TASK_SET)) + return qla2x00_eh_wait_for_pending_commands(arg->vha, + arg->fcport->d_id.b24, arg->lun, WAIT_LUN); + else + return qla2x00_eh_wait_for_pending_commands(arg->vha, + arg->fcport->d_id.b24, arg->lun, WAIT_TARGET); +} + static int __qla2x00_async_tm_cmd(struct tmf_arg *arg) { @@ -2137,8 +2147,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) struct srb_iocb *tm_iocb; srb_t *sp; int rval = QLA_FUNCTION_FAILED; - fc_port_t *fcport = arg->fcport; + u32 chip_gen, login_gen; + u64 jif; if (TMF_NOT_READY(arg->fcport)) { ql_dbg(ql_dbg_taskm, vha, 0x8032, @@ -2183,8 +2194,27 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) "TM IOCB failed (%x).\n", rval); } - if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) - rval = qla26xx_marker(arg); + if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) { + chip_gen = vha->hw->chip_reset; + login_gen = fcport->login_gen; + + jif = jiffies; + if (qla_tmf_wait(arg)) { + ql_log(ql_log_info, vha, 0x803e, + "Waited %u ms Nexus=%ld:%06x:%llu.\n", + jiffies_to_msecs(jiffies - jif), vha->host_no, + fcport->d_id.b24, arg->lun); + } + + if (chip_gen == vha->hw->chip_reset && login_gen == fcport->login_gen) { + rval = qla26xx_marker(arg); + } else { + ql_log(ql_log_info, vha, 0x803e, + "Skip Marker due to disruption. Nexus=%ld:%06x:%llu.\n", + vha->host_no, fcport->d_id.b24, arg->lun); + rval = QLA_FUNCTION_FAILED; + } + } done_free_sp: /* ref: INIT */ @@ -2262,9 +2292,8 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, uint32_t tag) { struct scsi_qla_host *vha = fcport->vha; - struct qla_qpair *qpair; struct tmf_arg a; - int i, rval = QLA_SUCCESS; + int rval = QLA_SUCCESS; if (TMF_NOT_READY(fcport)) return QLA_SUSPENDED; @@ -2284,34 +2313,9 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun, if (qla_get_tmf(&a)) return QLA_FUNCTION_FAILED; - if (vha->hw->mqenable) { - for (i = 0; i < vha->hw->num_qpairs; i++) { - qpair = vha->hw->queue_pair_map[i]; - if (!qpair) - continue; - - if (TMF_NOT_READY(fcport)) { - ql_log(ql_log_warn, vha, 0x8026, - "Unable to send TM due to disruption.\n"); - rval = QLA_SUSPENDED; - break; - } - - a.qpair = qpair; - a.flags = flags|TCF_NOTMCMD_TO_TARGET; - rval = __qla2x00_async_tm_cmd(&a); - if (rval) - break; - } - } - - if (rval) - goto bailout; - a.qpair = vha->hw->base_qpair; rval = __qla2x00_async_tm_cmd(&a); -bailout: qla_put_tmf(&a); return rval; } diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index c9a686f06d29..9e524d52dc86 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3887,6 +3887,7 @@ qla_marker_iocb(srb_t *sp, struct mrk_entry_24xx *mrk) { mrk->entry_type = MARKER_TYPE; mrk->modifier = sp->u.iocb_cmd.u.tmf.modifier; + mrk->handle = make_handle(sp->qpair->req->id, sp->handle); if (sp->u.iocb_cmd.u.tmf.modifier != MK_SYNC_ALL) { mrk->nport_handle = cpu_to_le16(sp->u.iocb_cmd.u.tmf.loop_id); int_to_scsilun(sp->u.iocb_cmd.u.tmf.lun, (struct scsi_lun *)&mrk->lun); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bde536e3e752..aadf38b44581 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1478,8 +1478,9 @@ qla2xxx_eh_device_reset(struct scsi_cmnd *cmd) goto eh_reset_failed; } err = 3; - if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id, - sdev->lun, WAIT_LUN) != QLA_SUCCESS) { + if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24, + cmd->device->lun, + WAIT_LUN) != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x800d, "wait for pending cmds failed for cmd=%p.\n", cmd); goto eh_reset_failed; @@ -1545,8 +1546,8 @@ qla2xxx_eh_target_reset(struct scsi_cmnd *cmd) goto eh_reset_failed; } err = 3; - if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id, - 0, WAIT_TARGET) != QLA_SUCCESS) { + if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24, 0, + WAIT_TARGET) != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x800d, "wait for pending cmds failed for cmd=%p.\n", cmd); goto eh_reset_failed; From 01e3440ce0218112d53d026270fd6b51a0124190 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:30:59 +0530 Subject: [PATCH 1296/2093] scsi: qla2xxx: Fix erroneous link up failure commit 5b51f35d127e7bef55fa869d2465e2bca4636454 upstream. Link up failure occurred where driver failed to see certain events from FW indicating link up (AEN 8011) and fabric login completion (AEN 8014). Without these 2 events, driver would not proceed forward to scan the fabric. The cause of this is due to delay in the receive of interrupt for Mailbox 60 that causes qla to set the fw_started flag late. The late setting of this flag causes other interrupts to be dropped. These dropped interrupts happen to be the link up (AEN 8011) and fabric login completion (AEN 8014). Set fw_started flag early to prevent interrupts being dropped. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-6-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 3 ++- drivers/scsi/qla2xxx/qla_isr.c | 6 +++++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 8326b9474c3e..03ef225cfd2f 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4816,15 +4816,16 @@ qla2x00_init_rings(scsi_qla_host_t *vha) if (ha->flags.edif_enabled) mid_init_cb->init_cb.frame_payload_size = cpu_to_le16(ELS_MAX_PAYLOAD); + QLA_FW_STARTED(ha); rval = qla2x00_init_firmware(vha, ha->init_cb_size); next_check: if (rval) { + QLA_FW_STOPPED(ha); ql_log(ql_log_fatal, vha, 0x00d2, "Init Firmware **** FAILED ****.\n"); } else { ql_dbg(ql_dbg_init, vha, 0x00d3, "Init Firmware -- success.\n"); - QLA_FW_STARTED(ha); vha->u_ql2xexchoffld = vha->u_ql2xiniexchg = 0; } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 246e74cb929f..0111249cc877 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1121,8 +1121,12 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) unsigned long flags; fc_port_t *fcport = NULL; - if (!vha->hw->flags.fw_started) + if (!vha->hw->flags.fw_started) { + ql_log(ql_log_warn, vha, 0x50ff, + "Dropping AEN - %04x %04x %04x %04x.\n", + mb[0], mb[1], mb[2], mb[3]); return; + } /* Setup to process RIO completion. */ handle_cnt = 0; From addaa136f10bdef7367c2cce8611ff928ddad82f Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:01 +0530 Subject: [PATCH 1297/2093] scsi: qla2xxx: Turn off noisy message log commit 8ebaa45163a3fedc885c1dc7d43ea987a2f00a06 upstream. Some consider noisy log as test failure. Turn off noisy message log. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-8-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index ebb8786c4c99..c9a6fc882a80 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -664,7 +664,7 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, rval = qla2x00_start_nvme_mq(sp); if (rval != QLA_SUCCESS) { - ql_log(ql_log_warn, vha, 0x212d, + ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x212d, "qla2x00_start_nvme_mq failed = %d\n", rval); sp->priv = NULL; priv->sp = NULL; From e6aabf0654cce4cea540b4655824a3e2da452cc4 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:00 +0530 Subject: [PATCH 1298/2093] scsi: qla2xxx: Fix session hang in gnl commit 39d22740712c7563a2e18c08f033deeacdaf66e7 upstream. Connection does not resume after a host reset / chip reset. The cause of the blockage is due to the FCF_ASYNC_ACTIVE left on. The gnl command was interrupted by the chip reset. On exiting the command, this flag should be turn off to allow relogin to reoccur. Clear this flag to prevent blockage. Cc: stable@vger.kernel.org Fixes: 17e64648aa47 ("scsi: qla2xxx: Correct fcport flags handling") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-7-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 03ef225cfd2f..e122fe8423e2 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1135,7 +1135,7 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) u16 *mb; if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT)) - return rval; + goto done; ql_dbg(ql_dbg_disc, vha, 0x20d9, "Async-gnlist WWPN %8phC \n", fcport->port_name); @@ -1189,8 +1189,9 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) done_free_sp: /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + fcport->flags &= ~(FCF_ASYNC_SENT); done: - fcport->flags &= ~(FCF_ASYNC_ACTIVE | FCF_ASYNC_SENT); + fcport->flags &= ~(FCF_ASYNC_ACTIVE); return rval; } From 1f0e3814adc72885063242b39e8780ed934dafb6 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 14 Jul 2023 12:31:02 +0530 Subject: [PATCH 1299/2093] scsi: qla2xxx: Fix TMF leak through commit 5d3148d8e8b05f084e607ac3bd55a4c317a9f934 upstream. Task management can retry up to 5 times when FW resource becomes bottle neck. Between the retries, there is a short sleep. Current code assumes the chip has not reset or session has not changed. Check for chip reset or session change before sending Task management. Cc: stable@vger.kernel.org Fixes: 9803fb5d2759 ("scsi: qla2xxx: Fix task management cmd failure") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230714070104.40052-9-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index e122fe8423e2..5d2eef8ce0ae 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2039,10 +2039,14 @@ static void qla_marker_sp_done(srb_t *sp, int res) complete(&tmf->u.tmf.comp); } -#define START_SP_W_RETRIES(_sp, _rval) \ +#define START_SP_W_RETRIES(_sp, _rval, _chip_gen, _login_gen) \ {\ int cnt = 5; \ do { \ + if (_chip_gen != sp->vha->hw->chip_reset || _login_gen != sp->fcport->login_gen) {\ + _rval = EINVAL; \ + break; \ + } \ _rval = qla2x00_start_sp(_sp); \ if (_rval == EAGAIN) \ msleep(1); \ @@ -2065,6 +2069,7 @@ qla26xx_marker(struct tmf_arg *arg) srb_t *sp; int rval = QLA_FUNCTION_FAILED; fc_port_t *fcport = arg->fcport; + u32 chip_gen, login_gen; if (TMF_NOT_READY(arg->fcport)) { ql_dbg(ql_dbg_taskm, vha, 0x8039, @@ -2074,6 +2079,9 @@ qla26xx_marker(struct tmf_arg *arg) return QLA_SUSPENDED; } + chip_gen = vha->hw->chip_reset; + login_gen = fcport->login_gen; + /* ref: INIT */ sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL); if (!sp) @@ -2091,7 +2099,7 @@ qla26xx_marker(struct tmf_arg *arg) tm_iocb->u.tmf.loop_id = fcport->loop_id; tm_iocb->u.tmf.vp_index = vha->vp_idx; - START_SP_W_RETRIES(sp, rval); + START_SP_W_RETRIES(sp, rval, chip_gen, login_gen); ql_dbg(ql_dbg_taskm, vha, 0x8006, "Async-marker hdl=%x loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d rval %d.\n", @@ -2160,6 +2168,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) return QLA_SUSPENDED; } + chip_gen = vha->hw->chip_reset; + login_gen = fcport->login_gen; + /* ref: INIT */ sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL); if (!sp) @@ -2177,7 +2188,7 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) tm_iocb->u.tmf.flags = arg->flags; tm_iocb->u.tmf.lun = arg->lun; - START_SP_W_RETRIES(sp, rval); + START_SP_W_RETRIES(sp, rval, chip_gen, login_gen); ql_dbg(ql_dbg_taskm, vha, 0x802f, "Async-tmf hdl=%x loop-id=%x portid=%06x ctrl=%x lun=%lld qp=%d rval=%x.\n", @@ -2196,9 +2207,6 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) } if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) { - chip_gen = vha->hw->chip_reset; - login_gen = fcport->login_gen; - jif = jiffies; if (qla_tmf_wait(arg)) { ql_log(ql_log_info, vha, 0x803e, From 98643561d853e313a522ed764aff58440a914e9c Mon Sep 17 00:00:00 2001 From: Manish Rangankar Date: Mon, 21 Aug 2023 18:30:42 +0530 Subject: [PATCH 1300/2093] scsi: qla2xxx: Remove unsupported ql2xenabledif option commit e9105c4b7a9208a21a9bda133707624f12ddabc2 upstream. User accidently passed module parameter ql2xenabledif=1 which is unsupported. However, driver still initialized which lead to guard tag errors during device discovery. Remove unsupported ql2xenabledif=1 option and validate the user input. Cc: stable@vger.kernel.org Signed-off-by: Manish Rangankar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230821130045.34850-7-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_attr.c | 2 -- drivers/scsi/qla2xxx/qla_dbg.c | 2 +- drivers/scsi/qla2xxx/qla_os.c | 9 +++++++-- 3 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 64734d6e8ccb..07fbaa452d8a 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3093,8 +3093,6 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable) vha->flags.difdix_supported = 1; ql_dbg(ql_dbg_user, vha, 0x7082, "Registered for DIF/DIX type 1 and 3 protection.\n"); - if (ql2xenabledif == 1) - prot = SHOST_DIX_TYPE0_PROTECTION; scsi_host_set_prot(vha->host, prot | SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index d7e8454304ce..ab637324262f 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -18,7 +18,7 @@ * | Queue Command and IO tracing | 0x3074 | 0x300b | * | | | 0x3027-0x3028 | * | | | 0x303d-0x3041 | - * | | | 0x302d,0x3033 | + * | | | 0x302e,0x3033 | * | | | 0x3036,0x3038 | * | | | 0x303a | * | DPC Thread | 0x4023 | 0x4002,0x4013 | diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index aadf38b44581..e75e5eddfe1c 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3281,6 +3281,13 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) host->max_id = ha->max_fibre_devices; host->cmd_per_lun = 3; host->unique_id = host->host_no; + + if (ql2xenabledif && ql2xenabledif != 2) { + ql_log(ql_log_warn, base_vha, 0x302d, + "Invalid value for ql2xenabledif, resetting it to default (2)\n"); + ql2xenabledif = 2; + } + if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif) host->max_cmd_len = 32; else @@ -3518,8 +3525,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) base_vha->flags.difdix_supported = 1; ql_dbg(ql_dbg_init, base_vha, 0x00f1, "Registering for DIF/DIX type 1 and 3 protection.\n"); - if (ql2xenabledif == 1) - prot = SHOST_DIX_TYPE0_PROTECTION; if (ql2xprotmask) scsi_host_set_prot(host, ql2xprotmask); else From 974887e1d6890a77965233aabb597b085cfbc02e Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Mon, 21 Aug 2023 18:30:38 +0530 Subject: [PATCH 1301/2093] scsi: qla2xxx: Flush mailbox commands on chip reset commit 6d0b65569c0a10b27c49bacd8d25bcd406003533 upstream. Fix race condition between Interrupt thread and Chip reset thread in trying to flush the same mailbox. With the race condition, the "ha->mbx_intr_comp" will get an extra complete() call. The extra complete call create erroneous mailbox timeout condition when the next mailbox is sent where the mailbox call does not wait for interrupt to arrive. Instead, it advances without waiting. Add lock protection around the check for mailbox completion. Cc: stable@vger.kernel.org Fixes: b2000805a975 ("scsi: qla2xxx: Flush mailbox commands on chip reset") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230821130045.34850-3-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_def.h | 1 - drivers/scsi/qla2xxx/qla_init.c | 7 ++++--- drivers/scsi/qla2xxx/qla_mbx.c | 4 ---- drivers/scsi/qla2xxx/qla_os.c | 1 - 4 files changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 84929c0e7eb6..eb67059b6737 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -4367,7 +4367,6 @@ struct qla_hw_data { uint8_t aen_mbx_count; atomic_t num_pend_mbx_stage1; atomic_t num_pend_mbx_stage2; - atomic_t num_pend_mbx_stage3; uint16_t frame_payload_size; uint32_t login_retry_count; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 5d2eef8ce0ae..db5484ef656c 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -7444,14 +7444,15 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) } /* purge MBox commands */ - if (atomic_read(&ha->num_pend_mbx_stage3)) { + spin_lock_irqsave(&ha->hardware_lock, flags); + if (test_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags)) { clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags); complete(&ha->mbx_intr_comp); } + spin_unlock_irqrestore(&ha->hardware_lock, flags); i = 0; - while (atomic_read(&ha->num_pend_mbx_stage3) || - atomic_read(&ha->num_pend_mbx_stage2) || + while (atomic_read(&ha->num_pend_mbx_stage2) || atomic_read(&ha->num_pend_mbx_stage1)) { msleep(20); i++; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 3c2ee21195ed..f794f4363a38 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -273,7 +273,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) spin_unlock_irqrestore(&ha->hardware_lock, flags); wait_time = jiffies; - atomic_inc(&ha->num_pend_mbx_stage3); if (!wait_for_completion_timeout(&ha->mbx_intr_comp, mcp->tov * HZ)) { ql_dbg(ql_dbg_mbx, vha, 0x117a, @@ -290,7 +289,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) spin_unlock_irqrestore(&ha->hardware_lock, flags); atomic_dec(&ha->num_pend_mbx_stage2); - atomic_dec(&ha->num_pend_mbx_stage3); rval = QLA_ABORTED; goto premature_exit; } @@ -302,11 +300,9 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) ha->flags.mbox_busy = 0; spin_unlock_irqrestore(&ha->hardware_lock, flags); atomic_dec(&ha->num_pend_mbx_stage2); - atomic_dec(&ha->num_pend_mbx_stage3); rval = QLA_ABORTED; goto premature_exit; } - atomic_dec(&ha->num_pend_mbx_stage3); if (time_after(jiffies, wait_time + 5 * HZ)) ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n", diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index e75e5eddfe1c..a1b31382c19d 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3000,7 +3000,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) ha->max_exchg = FW_MAX_EXCHANGES_CNT; atomic_set(&ha->num_pend_mbx_stage1, 0); atomic_set(&ha->num_pend_mbx_stage2, 0); - atomic_set(&ha->num_pend_mbx_stage3, 0); atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD); ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD; INIT_LIST_HEAD(&ha->tmf_pending); From c7355cbb9c1b30d1934e054ba9953974cf0065a0 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Mon, 21 Aug 2023 18:30:43 +0530 Subject: [PATCH 1302/2093] scsi: qla2xxx: Fix smatch warn for qla_init_iocb_limit() commit b496953dd0444001b12f425ea07d78c1f47e3193 upstream. Fix indentation for warning reported by smatch: drivers/scsi/qla2xxx/qla_init.c:4199 qla_init_iocb_limit() warn: inconsistent indenting Fixes: efa74a62aaa2 ("scsi: qla2xxx: Adjust IOCB resource on qpair create") Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230821130045.34850-8-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index db5484ef656c..688bf0a24c83 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4204,7 +4204,7 @@ void qla_init_iocb_limit(scsi_qla_host_t *vha) u8 i; struct qla_hw_data *ha = vha->hw; - __qla_adjust_iocb_limit(ha->base_qpair); + __qla_adjust_iocb_limit(ha->base_qpair); ha->base_qpair->fwres.iocbs_used = 0; ha->base_qpair->fwres.exch_used = 0; From 3a9d4db2d2e00812dabbe7ea2f34c5fdf975d2cd Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Mon, 21 Aug 2023 18:30:41 +0530 Subject: [PATCH 1303/2093] scsi: qla2xxx: Error code did not return to upper layer commit 0ba0b018f94525a6b32f5930f980ce9b62b72e6f upstream. TMF was returned with an error code. The error code was not preserved to be returned to upper layer. Instead, the error code from the Marker was returned. Preserve error code from TMF and return it to upper layer. Cc: stable@vger.kernel.org Fixes: da7c21b72aa8 ("scsi: qla2xxx: Fix command flush during TMF") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230821130045.34850-6-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 688bf0a24c83..56351698253a 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2224,6 +2224,8 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg) rval = QLA_FUNCTION_FAILED; } } + if (tm_iocb->u.tmf.data) + rval = tm_iocb->u.tmf.data; done_free_sp: /* ref: INIT */ From f55797084931eef73708259afc7003dda4cfb4d1 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Mon, 21 Aug 2023 18:30:39 +0530 Subject: [PATCH 1304/2093] scsi: qla2xxx: Fix firmware resource tracking commit e370b64c7db96384a0886a09a9d80406e4c663d7 upstream. The storage was not draining I/Os and the work load was not spread out across different CPUs evenly. This led to firmware resource counters getting overrun on the busy CPU. This overrun prevented error recovery from happening in a timely manner. By switching the counter to atomic, it allows the count to be little more accurate to prevent the overrun. Cc: stable@vger.kernel.org Fixes: da7c21b72aa8 ("scsi: qla2xxx: Fix command flush during TMF") Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230821130045.34850-4-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_def.h | 11 ++++++ drivers/scsi/qla2xxx/qla_dfs.c | 10 ++++++ drivers/scsi/qla2xxx/qla_init.c | 8 +++++ drivers/scsi/qla2xxx/qla_inline.h | 57 ++++++++++++++++++++++++++++++- drivers/scsi/qla2xxx/qla_os.c | 5 +-- 5 files changed, 88 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index eb67059b6737..7d282906598f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3740,6 +3740,16 @@ struct qla_fw_resources { u16 pad; }; +struct qla_fw_res { + u16 iocb_total; + u16 iocb_limit; + atomic_t iocb_used; + + u16 exch_total; + u16 exch_limit; + atomic_t exch_used; +}; + #define QLA_IOCB_PCT_LIMIT 95 /*Queue pair data structure */ @@ -4782,6 +4792,7 @@ struct qla_hw_data { spinlock_t sadb_lock; /* protects list */ struct els_reject elsrej; u8 edif_post_stop_cnt_down; + struct qla_fw_res fwres ____cacheline_aligned; }; #define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES)) diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c index 1925cc6897b6..f060e593685d 100644 --- a/drivers/scsi/qla2xxx/qla_dfs.c +++ b/drivers/scsi/qla2xxx/qla_dfs.c @@ -276,6 +276,16 @@ qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused) seq_printf(s, "estimate exchange used[%d] high water limit [%d] n", exch_used, ha->base_qpair->fwres.exch_limit); + + if (ql2xenforce_iocb_limit == 2) { + iocbs_used = atomic_read(&ha->fwres.iocb_used); + exch_used = atomic_read(&ha->fwres.exch_used); + seq_printf(s, " estimate iocb2 used [%d] high water limit [%d]\n", + iocbs_used, ha->fwres.iocb_limit); + + seq_printf(s, " estimate exchange2 used[%d] high water limit [%d] \n", + exch_used, ha->fwres.exch_limit); + } } return 0; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 56351698253a..36abdb0de169 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4217,6 +4217,14 @@ void qla_init_iocb_limit(scsi_qla_host_t *vha) ha->queue_pair_map[i]->fwres.exch_used = 0; } } + + ha->fwres.iocb_total = ha->orig_fw_iocb_count; + ha->fwres.iocb_limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100; + ha->fwres.exch_total = ha->orig_fw_xcb_count; + ha->fwres.exch_limit = (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100; + + atomic_set(&ha->fwres.iocb_used, 0); + atomic_set(&ha->fwres.exch_used, 0); } void qla_adjust_iocb_limit(scsi_qla_host_t *vha) diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index a034699e58ae..a7b5d1114682 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -386,6 +386,7 @@ enum { RESOURCE_IOCB = BIT_0, RESOURCE_EXCH = BIT_1, /* exchange */ RESOURCE_FORCE = BIT_2, + RESOURCE_HA = BIT_3, }; static inline int @@ -393,7 +394,7 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores) { u16 iocbs_used, i; u16 exch_used; - struct qla_hw_data *ha = qp->vha->hw; + struct qla_hw_data *ha = qp->hw; if (!ql2xenforce_iocb_limit) { iores->res_type = RESOURCE_NONE; @@ -428,15 +429,69 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores) return -ENOSPC; } } + + if (ql2xenforce_iocb_limit == 2) { + if ((iores->iocb_cnt + atomic_read(&ha->fwres.iocb_used)) >= + ha->fwres.iocb_limit) { + iores->res_type = RESOURCE_NONE; + return -ENOSPC; + } + + if (iores->res_type & RESOURCE_EXCH) { + if ((iores->exch_cnt + atomic_read(&ha->fwres.exch_used)) >= + ha->fwres.exch_limit) { + iores->res_type = RESOURCE_NONE; + return -ENOSPC; + } + } + } + force: qp->fwres.iocbs_used += iores->iocb_cnt; qp->fwres.exch_used += iores->exch_cnt; + if (ql2xenforce_iocb_limit == 2) { + atomic_add(iores->iocb_cnt, &ha->fwres.iocb_used); + atomic_add(iores->exch_cnt, &ha->fwres.exch_used); + iores->res_type |= RESOURCE_HA; + } return 0; } +/* + * decrement to zero. This routine will not decrement below zero + * @v: pointer of type atomic_t + * @amount: amount to decrement from v + */ +static void qla_atomic_dtz(atomic_t *v, int amount) +{ + int c, old, dec; + + c = atomic_read(v); + for (;;) { + dec = c - amount; + if (unlikely(dec < 0)) + dec = 0; + + old = atomic_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } +} + static inline void qla_put_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores) { + struct qla_hw_data *ha = qp->hw; + + if (iores->res_type & RESOURCE_HA) { + if (iores->res_type & RESOURCE_IOCB) + qla_atomic_dtz(&ha->fwres.iocb_used, iores->iocb_cnt); + + if (iores->res_type & RESOURCE_EXCH) + qla_atomic_dtz(&ha->fwres.exch_used, iores->exch_cnt); + } + if (iores->res_type & RESOURCE_IOCB) { if (qp->fwres.iocbs_used >= iores->iocb_cnt) { qp->fwres.iocbs_used -= iores->iocb_cnt; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index a1b31382c19d..78f7cd16967f 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -44,10 +44,11 @@ module_param(ql2xfulldump_on_mpifail, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ql2xfulldump_on_mpifail, "Set this to take full dump on MPI hang."); -int ql2xenforce_iocb_limit = 1; +int ql2xenforce_iocb_limit = 2; module_param(ql2xenforce_iocb_limit, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ql2xenforce_iocb_limit, - "Enforce IOCB throttling, to avoid FW congestion. (default: 1)"); + "Enforce IOCB throttling, to avoid FW congestion. (default: 2) " + "1: track usage per queue, 2: track usage per adapter"); /* * CT6 CTX allocation cache From a0b4a0666beacfe8add9c71d8922475541dbae73 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 1 Sep 2023 20:03:06 +0800 Subject: [PATCH 1305/2093] null_blk: fix poll request timeout handling commit 5a26e45edb4690d58406178b5a9ea4c6dcf2c105 upstream. When doing io_uring benchmark on /dev/nullb0, it's easy to crash the kernel if poll requests timeout triggered, as reported by David. [1] BUG: kernel NULL pointer dereference, address: 0000000000000008 Workqueue: kblockd blk_mq_timeout_work RIP: 0010:null_timeout_rq+0x4e/0x91 Call Trace: ? null_timeout_rq+0x4e/0x91 blk_mq_handle_expired+0x31/0x4b bt_iter+0x68/0x84 ? bt_tags_iter+0x81/0x81 __sbitmap_for_each_set.constprop.0+0xb0/0xf2 ? __blk_mq_complete_request_remote+0xf/0xf bt_for_each+0x46/0x64 ? __blk_mq_complete_request_remote+0xf/0xf ? percpu_ref_get_many+0xc/0x2a blk_mq_queue_tag_busy_iter+0x14d/0x18e blk_mq_timeout_work+0x95/0x127 process_one_work+0x185/0x263 worker_thread+0x1b5/0x227 This is indeed a race problem between null_timeout_rq() and null_poll(). null_poll() null_timeout_rq() spin_lock(&nq->poll_lock) list_splice_init(&nq->poll_list, &list) spin_unlock(&nq->poll_lock) while (!list_empty(&list)) req = list_first_entry() list_del_init() ... blk_mq_add_to_batch() // req->rq_next = NULL spin_lock(&nq->poll_lock) // rq->queuelist->next == NULL list_del_init(&rq->queuelist) spin_unlock(&nq->poll_lock) Fix these problems by setting requests state to MQ_RQ_COMPLETE under nq->poll_lock protection, in which null_timeout_rq() can safely detect this race and early return. Note this patch just fix the kernel panic when request timeout happen. [1] https://lore.kernel.org/all/3893581.1691785261@warthog.procyon.org.uk/ Fixes: 0a593fbbc245 ("null_blk: poll queue support") Reported-by: David Howells Tested-by: David Howells Reviewed-by: Ming Lei Signed-off-by: Chengming Zhou Link: https://lore.kernel.org/r/20230901120306.170520-2-chengming.zhou@linux.dev Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/null_blk/main.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index e8cb914223cd..e9f38eba2f13 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1585,9 +1585,12 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) struct nullb_queue *nq = hctx->driver_data; LIST_HEAD(list); int nr = 0; + struct request *rq; spin_lock(&nq->poll_lock); list_splice_init(&nq->poll_list, &list); + list_for_each_entry(rq, &list, queuelist) + blk_mq_set_request_complete(rq); spin_unlock(&nq->poll_lock); while (!list_empty(&list)) { @@ -1613,16 +1616,21 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq) struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); - pr_info("rq %p timed out\n", rq); - if (hctx->type == HCTX_TYPE_POLL) { struct nullb_queue *nq = hctx->driver_data; spin_lock(&nq->poll_lock); + /* The request may have completed meanwhile. */ + if (blk_mq_request_completed(rq)) { + spin_unlock(&nq->poll_lock); + return BLK_EH_DONE; + } list_del_init(&rq->queuelist); spin_unlock(&nq->poll_lock); } + pr_info("rq %p timed out\n", rq); + /* * If the device is marked as blocking (i.e. memory backed or zoned * device), the submission path may be blocked waiting for resources From f83c1b13f8154e0284448912756d0a351a1a602a Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 13 Jun 2023 13:06:49 +0200 Subject: [PATCH 1306/2093] fbdev/ep93xx-fb: Do not assign to struct fb_info.dev commit f90a0e5265b60cdd3c77990e8105f79aa2fac994 upstream. Do not assing the Linux device to struct fb_info.dev. The call to register_framebuffer() initializes the field to the fbdev device. Drivers should not override its value. Fixes a bug where the driver incorrectly decreases the hardware device's reference counter and leaks the fbdev device. v2: * add Fixes tag (Dan) Signed-off-by: Thomas Zimmermann Fixes: 88017bda96a5 ("ep93xx video driver") Cc: # v2.6.32+ Reviewed-by: Javier Martinez Canillas Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20230613110953.24176-15-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/ep93xx-fb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c index 305f1587bd89..8b2bc4adc50f 100644 --- a/drivers/video/fbdev/ep93xx-fb.c +++ b/drivers/video/fbdev/ep93xx-fb.c @@ -474,7 +474,6 @@ static int ep93xxfb_probe(struct platform_device *pdev) if (!info) return -ENOMEM; - info->dev = &pdev->dev; platform_set_drvdata(pdev, info); fbi = info->par; fbi->mach_info = mach_info; From c0341bddd6cca99834b6fd211ffff9fb5320cebb Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 18 Jul 2023 15:28:55 +0200 Subject: [PATCH 1307/2093] clk: qcom: camcc-sc7180: fix async resume during probe commit c948ff727e25297f3a703eb5349dd66aabf004e4 upstream. To make sure that the controller is runtime resumed and its power domain is enabled before accessing its registers during probe, the synchronous runtime PM interface must be used. Fixes: 8d4025943e13 ("clk: qcom: camcc-sc7180: Use runtime PM ops instead of clk ones") Cc: stable@vger.kernel.org # 5.11 Cc: Stephen Boyd Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230718132902.21430-2-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/camcc-sc7180.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/camcc-sc7180.c b/drivers/clk/qcom/camcc-sc7180.c index 8a4ba7a19ed1..6f56bdbf0204 100644 --- a/drivers/clk/qcom/camcc-sc7180.c +++ b/drivers/clk/qcom/camcc-sc7180.c @@ -1664,7 +1664,7 @@ static int cam_cc_sc7180_probe(struct platform_device *pdev) return ret; } - ret = pm_runtime_get(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret) return ret; From 3c9881fd220ab8a7b4dc7599151f0470e5b27d57 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 21 Jun 2023 14:53:35 +0200 Subject: [PATCH 1308/2093] drm/ast: Fix DRAM init on AST2200 commit 4cfe75f0f14f044dae66ad0e6eea812d038465d9 upstream. Fix the test for the AST2200 in the DRAM initialization. The value in ast->chip has to be compared against an enum constant instead of a numerical value. This bug got introduced when the driver was first imported into the kernel. Signed-off-by: Thomas Zimmermann Fixes: 312fec1405dd ("drm: Initial KMS driver for AST (ASpeed Technologies) 2000 series (v2)") Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: # v3.5+ Reviewed-by: Sui Jingfeng Reviewed-by: Jocelyn Falempe Tested-by: Jocelyn Falempe # AST2600 Link: https://patchwork.freedesktop.org/patch/msgid/20230621130032.3568-2-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ast/ast_post.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 82fd3c8adee1..5b2c2b7745bf 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -291,7 +291,7 @@ static void ast_init_dram_reg(struct drm_device *dev) ; } while (ast_read32(ast, 0x10100) != 0xa8); } else {/* AST2100/1100 */ - if (ast->chip == AST2100 || ast->chip == 2200) + if (ast->chip == AST2100 || ast->chip == AST2200) dram_reg_info = ast2100_dram_table_data; else dram_reg_info = ast1100_dram_table_data; From b83ae66d82657e47f4b8b14d63e82f6eb7b22918 Mon Sep 17 00:00:00 2001 From: Sheetal Date: Thu, 22 Jun 2023 17:04:09 +0530 Subject: [PATCH 1309/2093] ASoC: tegra: Fix SFC conversion for few rates commit d900d9a435ca95a386f49424f3689cd17ec201da upstream. Sample rate conversions for rates greater than 48kHz are found to be failing. It means x->y conversions fail when either x or y is greater than 48kHz. This happens because, tegra210_sfc_rate_to_idx() returns incorrect index for rates greater than 48kHz. This actually depends on the tegra210_sfc_rates[] array and it is not in sync with frequency values of SFC TX/RX register. To be precise, 64kHz entry is missing in above array defined in the driver. Due to this wrong index is returned and this results in incorrect programming of coefficients. To fix this, align the tegra210_sfc_rates[] array with SFC register specification and thus add 64kHz entry to it. Also, the coefficient table is updated to reflect that none of the conversions are supported for 64kHz. Fixes: b2f74ec53a6c ("ASoC: tegra: Add Tegra210 based SFC driver") Cc: stable@vger.kernel.org Signed-off-by: Sheetal Reviewed-by: Mohan Kumar D Reviewed-by: Sameer Pujar Link: https://lore.kernel.org/r/Message-Id: <1687433656-7892-2-git-send-email-spujar@nvidia.com> Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/tegra/tegra210_sfc.c | 31 ++++++++++++++++++++++++++++++- sound/soc/tegra/tegra210_sfc.h | 4 ++-- 2 files changed, 32 insertions(+), 3 deletions(-) diff --git a/sound/soc/tegra/tegra210_sfc.c b/sound/soc/tegra/tegra210_sfc.c index 368f077e7bee..5d2125aa6122 100644 --- a/sound/soc/tegra/tegra210_sfc.c +++ b/sound/soc/tegra/tegra210_sfc.c @@ -2,7 +2,7 @@ // // tegra210_sfc.c - Tegra210 SFC driver // -// Copyright (c) 2021 NVIDIA CORPORATION. All rights reserved. +// Copyright (c) 2021-2023 NVIDIA CORPORATION. All rights reserved. #include #include @@ -42,6 +42,7 @@ static const int tegra210_sfc_rates[TEGRA210_SFC_NUM_RATES] = { 32000, 44100, 48000, + 64000, 88200, 96000, 176400, @@ -2857,6 +2858,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_8to32, coef_8to44, coef_8to48, + UNSUPP_CONV, coef_8to88, coef_8to96, UNSUPP_CONV, @@ -2872,6 +2874,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_11to32, coef_11to44, coef_11to48, + UNSUPP_CONV, coef_11to88, coef_11to96, UNSUPP_CONV, @@ -2887,6 +2890,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_16to32, coef_16to44, coef_16to48, + UNSUPP_CONV, coef_16to88, coef_16to96, coef_16to176, @@ -2902,6 +2906,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_22to32, coef_22to44, coef_22to48, + UNSUPP_CONV, coef_22to88, coef_22to96, coef_22to176, @@ -2917,6 +2922,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_24to32, coef_24to44, coef_24to48, + UNSUPP_CONV, coef_24to88, coef_24to96, coef_24to176, @@ -2932,6 +2938,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { BYPASS_CONV, coef_32to44, coef_32to48, + UNSUPP_CONV, coef_32to88, coef_32to96, coef_32to176, @@ -2947,6 +2954,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_44to32, BYPASS_CONV, coef_44to48, + UNSUPP_CONV, coef_44to88, coef_44to96, coef_44to176, @@ -2962,11 +2970,28 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_48to32, coef_48to44, BYPASS_CONV, + UNSUPP_CONV, coef_48to88, coef_48to96, coef_48to176, coef_48to192, }, + /* Convertions from 64 kHz */ + { + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + UNSUPP_CONV, + }, /* Convertions from 88.2 kHz */ { coef_88to8, @@ -2977,6 +3002,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_88to32, coef_88to44, coef_88to48, + UNSUPP_CONV, BYPASS_CONV, coef_88to96, coef_88to176, @@ -2991,6 +3017,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_96to32, coef_96to44, coef_96to48, + UNSUPP_CONV, coef_96to88, BYPASS_CONV, coef_96to176, @@ -3006,6 +3033,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_176to32, coef_176to44, coef_176to48, + UNSUPP_CONV, coef_176to88, coef_176to96, BYPASS_CONV, @@ -3021,6 +3049,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = { coef_192to32, coef_192to44, coef_192to48, + UNSUPP_CONV, coef_192to88, coef_192to96, coef_192to176, diff --git a/sound/soc/tegra/tegra210_sfc.h b/sound/soc/tegra/tegra210_sfc.h index 5a6b66e297d8..a4c993d79403 100644 --- a/sound/soc/tegra/tegra210_sfc.h +++ b/sound/soc/tegra/tegra210_sfc.h @@ -2,7 +2,7 @@ /* * tegra210_sfc.h - Definitions for Tegra210 SFC driver * - * Copyright (c) 2021 NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2021-2023 NVIDIA CORPORATION. All rights reserved. * */ @@ -47,7 +47,7 @@ #define TEGRA210_SFC_EN_SHIFT 0 #define TEGRA210_SFC_EN (1 << TEGRA210_SFC_EN_SHIFT) -#define TEGRA210_SFC_NUM_RATES 12 +#define TEGRA210_SFC_NUM_RATES 13 /* Fields in TEGRA210_SFC_COEF_RAM */ #define TEGRA210_SFC_COEF_RAM_EN BIT(0) From df2d596e7e9cf8c5a2b0d46e6452c9e0041cd494 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 18 Jul 2023 15:29:02 +0200 Subject: [PATCH 1310/2093] clk: qcom: turingcc-qcs404: fix missing resume during probe commit a9f71a033587c9074059132d34c74eabbe95ef26 upstream. Drivers that enable runtime PM must make sure that the controller is runtime resumed before accessing its registers to prevent the power domain from being disabled. Fixes: 892df0191b29 ("clk: qcom: Add QCS404 TuringCC") Cc: stable@vger.kernel.org # 5.2 Cc: Bjorn Andersson Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230718132902.21430-9-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/turingcc-qcs404.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/turingcc-qcs404.c b/drivers/clk/qcom/turingcc-qcs404.c index 43184459228f..2cd288d6c3e4 100644 --- a/drivers/clk/qcom/turingcc-qcs404.c +++ b/drivers/clk/qcom/turingcc-qcs404.c @@ -125,11 +125,22 @@ static int turingcc_probe(struct platform_device *pdev) return ret; } - ret = qcom_cc_probe(pdev, &turingcc_desc); - if (ret < 0) + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) return ret; + ret = qcom_cc_probe(pdev, &turingcc_desc); + if (ret < 0) + goto err_put_rpm; + + pm_runtime_put(&pdev->dev); + return 0; + +err_put_rpm: + pm_runtime_put_sync(&pdev->dev); + + return ret; } static const struct dev_pm_ops turingcc_pm_ops = { From 22ec50d7b524183513721fdf05a5c20fa6656639 Mon Sep 17 00:00:00 2001 From: Chris Paterson Date: Fri, 9 Jun 2023 23:11:36 +0100 Subject: [PATCH 1311/2093] arm64: dts: renesas: rzg2l: Fix txdv-skew-psec typos commit db67345716a52abb750ec8f76d6a5675218715f9 upstream. It looks like txdv-skew-psec is a typo from a copy+paste. txdv-skew-psec is not present in the PHY bindings nor is it in the driver. Correct to txen-skew-psec which is clearly what it was meant to be. Given that the default for txen-skew-psec is 0, and the device tree is only trying to set it to 0 anyway, there should not be any functional change from this fix. Fixes: 361b0dcbd7f9 ("arm64: dts: renesas: rzg2l-smarc-som: Enable Ethernet") Fixes: 6494e4f90503 ("arm64: dts: renesas: rzg2ul-smarc-som: Enable Ethernet on SMARC platform") Fixes: ce0c63b6a5ef ("arm64: dts: renesas: Add initial device tree for RZ/G2LC SMARC EVK") Cc: stable@vger.kernel.org # 6.1.y Reported-by: Tomohiro Komagata Signed-off-by: Chris Paterson Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230609221136.7431-1-chris.paterson2@renesas.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi | 4 ++-- arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi | 2 +- arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi index c4faff092380..fee53c25fc80 100644 --- a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi @@ -100,7 +100,7 @@ phy0: ethernet-phy@7 { rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; - txdv-skew-psec = <0>; + txen-skew-psec = <0>; rxd0-skew-psec = <0>; rxd1-skew-psec = <0>; rxd2-skew-psec = <0>; @@ -128,7 +128,7 @@ phy1: ethernet-phy@7 { rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; - txdv-skew-psec = <0>; + txen-skew-psec = <0>; rxd0-skew-psec = <0>; rxd1-skew-psec = <0>; rxd2-skew-psec = <0>; diff --git a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi index 78e6e2376b01..5ff66aa6f8ba 100644 --- a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi @@ -77,7 +77,7 @@ phy0: ethernet-phy@7 { rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; - txdv-skew-psec = <0>; + txen-skew-psec = <0>; rxd0-skew-psec = <0>; rxd1-skew-psec = <0>; rxd2-skew-psec = <0>; diff --git a/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi index 2a0feb53f0dc..b62973bc2f0d 100644 --- a/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi @@ -80,7 +80,7 @@ phy0: ethernet-phy@7 { rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; - txdv-skew-psec = <0>; + txen-skew-psec = <0>; rxd0-skew-psec = <0>; rxd1-skew-psec = <0>; rxd2-skew-psec = <0>; @@ -107,7 +107,7 @@ phy1: ethernet-phy@7 { rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; - txdv-skew-psec = <0>; + txen-skew-psec = <0>; rxd0-skew-psec = <0>; rxd1-skew-psec = <0>; rxd2-skew-psec = <0>; From 0f7339056893f270e391c23d2438871a79deec86 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 24 Aug 2023 23:29:18 -0500 Subject: [PATCH 1312/2093] send channel sequence number in SMB3 requests after reconnects commit 09ee7a3bf866c0fa5ee1914d2c65958559eb5b4c upstream. The ChannelSequence field in the SMB3 header is supposed to be increased after reconnect to allow the server to distinguish requests from before and after the reconnect. We had always been setting it to zero. There are cases where incrementing ChannelSequence on requests after network reconnects can reduce the chance of data corruptions. See MS-SMB2 3.2.4.1 and 3.2.7.1 Signed-off-by: Steve French Cc: stable@vger.kernel.org # 5.16+ Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/cifsglob.h | 1 + fs/smb/client/connect.c | 1 + fs/smb/client/smb2ops.c | 11 ++++++++++- fs/smb/client/smb2pdu.c | 11 +++++++++++ fs/smb/common/smb2pdu.h | 22 ++++++++++++++++++++++ 5 files changed, 45 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 4a092cc5a393..03f34ec63e10 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -734,6 +734,7 @@ struct TCP_Server_Info { */ #define CIFS_SERVER_IS_CHAN(server) (!!(server)->primary_server) struct TCP_Server_Info *primary_server; + __u16 channel_sequence_num; /* incremented on primary channel on each chan reconnect */ #ifdef CONFIG_CIFS_SWN_UPCALL bool use_swn_dstaddr; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 9cd282960c0b..57da4f23c1e4 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1725,6 +1725,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, ctx->target_rfc1001_name, RFC1001_NAME_LEN_WITH_NULL); tcp_ses->session_estab = false; tcp_ses->sequence_number = 0; + tcp_ses->channel_sequence_num = 0; /* only tracked for primary channel */ tcp_ses->reconnect_instance = 1; tcp_ses->lstrp = jiffies; tcp_ses->compress_algorithm = cpu_to_le16(ctx->compression); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 6b020d80bb94..1387d5126f53 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -167,8 +167,17 @@ smb2_set_credits(struct TCP_Server_Info *server, const int val) spin_lock(&server->req_lock); server->credits = val; - if (val == 1) + if (val == 1) { server->reconnect_instance++; + /* + * ChannelSequence updated for all channels in primary channel so that consistent + * across SMB3 requests sent on any channel. See MS-SMB2 3.2.4.1 and 3.2.7.1 + */ + if (CIFS_SERVER_IS_CHAN(server)) + server->primary_server->channel_sequence_num++; + else + server->channel_sequence_num++; + } scredits = server->credits; in_flight = server->in_flight; spin_unlock(&server->req_lock); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index ae17d78f6ba1..847d69d327c2 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -88,9 +88,20 @@ smb2_hdr_assemble(struct smb2_hdr *shdr, __le16 smb2_cmd, const struct cifs_tcon *tcon, struct TCP_Server_Info *server) { + struct smb3_hdr_req *smb3_hdr; shdr->ProtocolId = SMB2_PROTO_NUMBER; shdr->StructureSize = cpu_to_le16(64); shdr->Command = smb2_cmd; + if (server->dialect >= SMB30_PROT_ID) { + /* After reconnect SMB3 must set ChannelSequence on subsequent reqs */ + smb3_hdr = (struct smb3_hdr_req *)shdr; + /* if primary channel is not set yet, use default channel for chan sequence num */ + if (CIFS_SERVER_IS_CHAN(server)) + smb3_hdr->ChannelSequence = + cpu_to_le16(server->primary_server->channel_sequence_num); + else + smb3_hdr->ChannelSequence = cpu_to_le16(server->channel_sequence_num); + } if (server) { spin_lock(&server->req_lock); /* Request up to 10 credits but don't go over the limit. */ diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 7d605db3bb3b..9619015d78f2 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -153,6 +153,28 @@ struct smb2_hdr { __u8 Signature[16]; } __packed; +struct smb3_hdr_req { + __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */ + __le16 StructureSize; /* 64 */ + __le16 CreditCharge; /* MBZ */ + __le16 ChannelSequence; /* See MS-SMB2 3.2.4.1 and 3.2.7.1 */ + __le16 Reserved; + __le16 Command; + __le16 CreditRequest; /* CreditResponse */ + __le32 Flags; + __le32 NextCommand; + __le64 MessageId; + union { + struct { + __le32 ProcessId; + __le32 TreeId; + } __packed SyncId; + __le64 AsyncId; + } __packed Id; + __le64 SessionId; + __u8 Signature[16]; +} __packed; + struct smb2_pdu { struct smb2_hdr hdr; __le16 StructureSize2; /* size of wct area (varies, request specific) */ From 21ef9e11205fca43785eecf7d4a99528d4de5701 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 4 Jul 2023 13:52:40 +0200 Subject: [PATCH 1313/2093] memcg: drop kmem.limit_in_bytes commit 86327e8eb94c52eca4f93cfece2e29d1bf52acbf upstream. kmem.limit_in_bytes (v1 way to limit kernel memory usage) has been deprecated since 58056f77502f ("memcg, kmem: further deprecate kmem.limit_in_bytes") merged in 5.16. We haven't heard about any serious users since then but it seems that the mere presence of the file is causing more harm thatn good. We (SUSE) have had several bug reports from customers where Docker based containers started to fail because a write to kmem.limit_in_bytes has failed. This was unexpected because runc code only expects ENOENT (kmem disabled) or EBUSY (tasks already running within cgroup). So a new error code was unexpected and the whole container startup failed. This has been later addressed by https://github.com/opencontainers/runc/commit/52390d68040637dfc77f9fda6bbe70952423d380 so current Docker runtimes do not suffer from the problem anymore. There are still older version of Docker in use and likely hard to get rid of completely. Address this by wiping out the file completely and effectively get back to pre 4.5 era and CONFIG_MEMCG_KMEM=n configuration. I would recommend backporting to stable trees which have picked up 58056f77502f ("memcg, kmem: further deprecate kmem.limit_in_bytes"). [mhocko@suse.com: restore _KMEM switch case] Link: https://lkml.kernel.org/r/ZKe5wxdbvPi5Cwd7@dhcp22.suse.cz Link: https://lkml.kernel.org/r/20230704115240.14672-1-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Roman Gushchin Cc: Muchun Song Cc: Tejun Heo Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cgroup-v1/memory.rst | 2 -- mm/memcontrol.c | 10 ---------- 2 files changed, 12 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 2524061836ac..34911ce5e4b5 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -91,8 +91,6 @@ Brief summary of control files. memory.oom_control set/show oom controls. memory.numa_stat show the number of memory usage per numa node - memory.kmem.limit_in_bytes This knob is deprecated and writing to - it will return -ENOTSUPP. memory.kmem.usage_in_bytes show current kernel memory allocation memory.kmem.failcnt show the number of kernel memory usage hits limits diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 67b6d8238b3e..0a403b241718 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3841,10 +3841,6 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, case _MEMSWAP: ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; - case _KMEM: - /* kmem.limit_in_bytes is deprecated. */ - ret = -EOPNOTSUPP; - break; case _TCP: ret = memcg_update_tcp_max(memcg, nr_pages); break; @@ -5055,12 +5051,6 @@ static struct cftype mem_cgroup_legacy_files[] = { .seq_show = memcg_numa_stat_show, }, #endif - { - .name = "kmem.limit_in_bytes", - .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), From 84a212a72c84906f75ed7ea926b2e584a9ce9234 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 7 Jul 2023 11:38:59 +0800 Subject: [PATCH 1314/2093] mm: hugetlb_vmemmap: fix a race between vmemmap pmd split commit 3ce2c24cb68f228590a053d6058a5901cd31af61 upstream. The local variable @page in __split_vmemmap_huge_pmd() to obtain a pmd page without holding page_table_lock may possiblely get the page table page instead of a huge pmd page. The effect may be in set_pte_at() since we may pass an invalid page struct, if set_pte_at() wants to access the page struct (e.g. CONFIG_PAGE_TABLE_CHECK is enabled), it may crash the kernel. So fix it. And inline __split_vmemmap_huge_pmd() since it only has one user. Link: https://lkml.kernel.org/r/20230707033859.16148-1-songmuchun@bytedance.com Fixes: d8d55f5616cf ("mm: sparsemem: use page table lock to protect kernel pmd operations") Signed-off-by: Muchun Song Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb_vmemmap.c | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-) diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4962dd1ba4a6..c04214055229 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -36,14 +36,22 @@ struct vmemmap_remap_walk { struct list_head *vmemmap_pages; }; -static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) { pmd_t __pmd; int i; unsigned long addr = start; - struct page *page = pmd_page(*pmd); - pte_t *pgtable = pte_alloc_one_kernel(&init_mm); + struct page *head; + pte_t *pgtable; + spin_lock(&init_mm.page_table_lock); + head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL; + spin_unlock(&init_mm.page_table_lock); + + if (!head) + return 0; + + pgtable = pte_alloc_one_kernel(&init_mm); if (!pgtable) return -ENOMEM; @@ -53,7 +61,7 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) pte_t entry, *pte; pgprot_t pgprot = PAGE_KERNEL; - entry = mk_pte(page + i, pgprot); + entry = mk_pte(head + i, pgprot); pte = pte_offset_kernel(&__pmd, addr); set_pte_at(&init_mm, addr, pte, entry); } @@ -65,8 +73,8 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) * be treated as indepdenent small pages (as they can be freed * individually). */ - if (!PageReserved(page)) - split_page(page, get_order(PMD_SIZE)); + if (!PageReserved(head)) + split_page(head, get_order(PMD_SIZE)); /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); @@ -80,20 +88,6 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) return 0; } -static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) -{ - int leaf; - - spin_lock(&init_mm.page_table_lock); - leaf = pmd_leaf(*pmd); - spin_unlock(&init_mm.page_table_lock); - - if (!leaf) - return 0; - - return __split_vmemmap_huge_pmd(pmd, start); -} - static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct vmemmap_remap_walk *walk) From 421855d0d24db9678fb438a3d9f3993ed82fbbc4 Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Fri, 14 Jul 2023 11:52:38 +1000 Subject: [PATCH 1315/2093] lib/test_meminit: allocate pages up to order MAX_ORDER commit efb78fa86e95832b78ca0ba60f3706788a818938 upstream. test_pages() tests the page allocator by calling alloc_pages() with different orders up to order 10. However, different architectures and platforms support different maximum contiguous allocation sizes. The default maximum allocation order (MAX_ORDER) is 10, but architectures can use CONFIG_ARCH_FORCE_MAX_ORDER to override this. On platforms where this is less than 10, test_meminit() will blow up with a WARN(). This is expected, so let's not do that. Replace the hardcoded "10" with the MAX_ORDER macro so that we test allocations up to the expected platform limit. Link: https://lkml.kernel.org/r/20230714015238.47931-1-ajd@linux.ibm.com Fixes: 5015a300a522 ("lib: introduce test_meminit module") Signed-off-by: Andrew Donnellan Reviewed-by: Alexander Potapenko Cc: Xiaoke Wang Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- lib/test_meminit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 60e1984c060f..0ae35223d773 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -93,7 +93,7 @@ static int __init test_pages(int *total_failures) int failures = 0, num_tests = 0; int i; - for (i = 0; i < 10; i++) + for (i = 0; i <= MAX_ORDER; i++) num_tests += do_alloc_pages_order(i, &failures); REPORT_FAILURES_IN_FN(); From ff2c44f0118d0ab4b563a6fd52359cbe78a3c9cd Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 27 Aug 2023 13:46:11 +0200 Subject: [PATCH 1316/2093] parisc: led: Fix LAN receive and transmit LEDs commit 4db89524b084f712a887256391fc19d9f66c8e55 upstream. Fix the LAN receive and LAN transmit LEDs, which where swapped up to now. Signed-off-by: Helge Deller Cc: Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/asm/led.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/parisc/include/asm/led.h b/arch/parisc/include/asm/led.h index 6de13d08a388..b70b9094fb7c 100644 --- a/arch/parisc/include/asm/led.h +++ b/arch/parisc/include/asm/led.h @@ -11,8 +11,8 @@ #define LED1 0x02 #define LED0 0x01 /* bottom (or furthest left) LED */ -#define LED_LAN_TX LED0 /* for LAN transmit activity */ -#define LED_LAN_RCV LED1 /* for LAN receive activity */ +#define LED_LAN_RCV LED0 /* for LAN receive activity */ +#define LED_LAN_TX LED1 /* for LAN transmit activity */ #define LED_DISK_IO LED2 /* for disk activity */ #define LED_HEARTBEAT LED3 /* heartbeat */ From db5d5673ab7ec45e0463d23e41465a31d0288846 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 25 Aug 2023 17:46:39 +0200 Subject: [PATCH 1317/2093] parisc: led: Reduce CPU overhead for disk & lan LED computation commit 358ad816e52d4253b38c2f312e6b1cbd89e0dbf7 upstream. Older PA-RISC machines have LEDs which show the disk- and LAN-activity. The computation is done in software and takes quite some time, e.g. on a J6500 this may take up to 60% time of one CPU if the machine is loaded via network traffic. Since most people don't care about the LEDs, start with LEDs disabled and just show a CPU heartbeat LED. The disk and LAN LEDs can be turned on manually via /proc/pdc/led. Signed-off-by: Helge Deller Cc: Signed-off-by: Greg Kroah-Hartman --- drivers/parisc/led.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index 8bdc5e043831..3737c1021f88 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -56,8 +56,8 @@ static int led_type __read_mostly = -1; static unsigned char lastleds; /* LED state from most recent update */ static unsigned int led_heartbeat __read_mostly = 1; -static unsigned int led_diskio __read_mostly = 1; -static unsigned int led_lanrxtx __read_mostly = 1; +static unsigned int led_diskio __read_mostly; +static unsigned int led_lanrxtx __read_mostly; static char lcd_text[32] __read_mostly; static char lcd_text_default[32] __read_mostly; static int lcd_no_led_support __read_mostly = 0; /* KittyHawk doesn't support LED on its LCD */ From 9c8fc05bd4d0796514a09950ad6dd368d5cefa90 Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Wed, 16 Aug 2023 19:38:45 +0000 Subject: [PATCH 1318/2093] cifs: update desired access while requesting for directory lease commit b6d44d42313baa45a81ce9b299aeee2ccf3d0ee1 upstream. We read and cache directory contents when we get directory lease, so we should ask for read permission to read contents of directory. Signed-off-by: Bharath SM Reviewed-by: Shyam Prasad N Cc: stable@vger.kernel.org Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/cached_dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index bfc964b36c72..5a132c1e6f6c 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -218,7 +218,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, .tcon = tcon, .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), - .desired_access = FILE_READ_ATTRIBUTES, + .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES, .disposition = FILE_OPEN, .fid = pfid, }; From 54e5ff4af78bf203c7e037b199d2dc46a620a53b Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Tue, 22 Aug 2023 12:53:40 +0530 Subject: [PATCH 1319/2093] pinctrl: cherryview: fix address_space_handler() argument commit d5301c90716a8e20bc961a348182daca00c8e8f0 upstream. First argument of acpi_*_address_space_handler() APIs is acpi_handle of the device, which is incorrectly passed in driver ->remove() path here. Fix it by passing the appropriate argument and while at it, make both API calls consistent using ACPI_HANDLE(). Fixes: a0b028597d59 ("pinctrl: cherryview: Add support for GMMR GPIO opregion") Cc: stable@vger.kernel.org Signed-off-by: Raag Jadav Acked-by: Mika Westerberg Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/intel/pinctrl-cherryview.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 0d6b5fab2f7e..de07b0837a04 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1698,7 +1698,6 @@ static int chv_pinctrl_probe(struct platform_device *pdev) struct intel_community_context *cctx; struct intel_community *community; struct device *dev = &pdev->dev; - struct acpi_device *adev = ACPI_COMPANION(dev); struct intel_pinctrl *pctrl; acpi_status status; unsigned int i; @@ -1766,7 +1765,7 @@ static int chv_pinctrl_probe(struct platform_device *pdev) if (ret) return ret; - status = acpi_install_address_space_handler(adev->handle, + status = acpi_install_address_space_handler(ACPI_HANDLE(dev), community->acpi_space_id, chv_pinctrl_mmio_access_handler, NULL, pctrl); @@ -1783,7 +1782,7 @@ static int chv_pinctrl_remove(struct platform_device *pdev) struct intel_pinctrl *pctrl = platform_get_drvdata(pdev); const struct intel_community *community = &pctrl->communities[0]; - acpi_remove_address_space_handler(ACPI_COMPANION(&pdev->dev), + acpi_remove_address_space_handler(ACPI_HANDLE(&pdev->dev), community->acpi_space_id, chv_pinctrl_mmio_access_handler); From 311db21d4a1fef2f5a0eefef40411faf31ceadce Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 28 Jul 2023 18:59:23 +0200 Subject: [PATCH 1320/2093] dt-bindings: clock: xlnx,versal-clk: drop select:false commit 172044e30b00977784269e8ab72132a48293c654 upstream. select:false makes the schema basically ignored and not effective, which is clearly not what we want for a device binding. Fixes: 352546805a44 ("dt-bindings: clock: Add bindings for versal clock driver") Cc: Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230728165923.108589-1-krzysztof.kozlowski@linaro.org Reviewed-by: Conor Dooley Reviewed-by: Shubhrajyoti Datta Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml b/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml index 229af98b1d30..7cd88bc3a67d 100644 --- a/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml +++ b/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml @@ -16,8 +16,6 @@ description: | reads required input clock frequencies from the devicetree and acts as clock provider for all clock consumers of PS clocks. -select: false - properties: compatible: const: xlnx,versal-clk From 871244f8efe8692e0de5f1545b4f159ebc2561a7 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Mon, 7 Aug 2023 10:47:44 +0200 Subject: [PATCH 1321/2093] clk: imx: pll14xx: dynamically configure PLL for 393216000/361267200Hz commit 72d00e560d10665e6139c9431956a87ded6e9880 upstream. Since commit b09c68dc57c9 ("clk: imx: pll14xx: Support dynamic rates"), the driver has the ability to dynamically compute PLL parameters to approximate the requested rates. This is not always used, because the logic is as follows: - Check if the target rate is hardcoded in the frequency table - Check if varying only kdiv is possible, so switch over is glitch free - Compute rate dynamically by iterating over pdiv range If we skip the frequency table for the 1443x PLL, we find that the computed values differ to the hardcoded ones. This can be valid if the hardcoded values guarantee for example an earlier lock-in or if the divisors are chosen, so that other important rates are more likely to be reached glitch-free. For rates (393216000 and 361267200, this doesn't seem to be the case: They are only approximated by existing parameters (393215995 and 361267196 Hz, respectively) and they aren't reachable glitch-free from other hardcoded frequencies. Dropping them from the table allows us to lock-in to these frequencies exactly. This is immediately noticeable because they are the assigned-clock-rates for IMX8MN_AUDIO_PLL1 and IMX8MN_AUDIO_PLL2, respectively and a look into clk_summary so far showed that they were a few Hz short of the target: imx8mn-board:~# grep audio_pll[12]_out /sys/kernel/debug/clk/clk_summary audio_pll2_out 0 0 0 361267196 0 0 50000 N audio_pll1_out 1 1 0 393215995 0 0 50000 Y and afterwards: imx8mn-board:~# grep audio_pll[12]_out /sys/kernel/debug/clk/clk_summary audio_pll2_out 0 0 0 361267200 0 0 50000 N audio_pll1_out 1 1 0 393216000 0 0 50000 Y This change is equivalent to adding following hardcoded values: /* rate mdiv pdiv sdiv kdiv */ PLL_1443X_RATE(393216000, 655, 5, 3, 23593), PLL_1443X_RATE(361267200, 497, 33, 0, -16882), Fixes: 053a4ffe2988 ("clk: imx: imx8mm: fix audio pll setting") Cc: stable@vger.kernel.org # v5.18+ Signed-off-by: Ahmad Fatoum Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20230807084744.1184791-2-m.felsch@pengutronix.de Signed-off-by: Abel Vesa Signed-off-by: Greg Kroah-Hartman --- drivers/clk/imx/clk-pll14xx.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c index 1d0f79e9c346..f3856df92307 100644 --- a/drivers/clk/imx/clk-pll14xx.c +++ b/drivers/clk/imx/clk-pll14xx.c @@ -62,8 +62,6 @@ static const struct imx_pll14xx_rate_table imx_pll1443x_tbl[] = { PLL_1443X_RATE(650000000U, 325, 3, 2, 0), PLL_1443X_RATE(594000000U, 198, 2, 2, 0), PLL_1443X_RATE(519750000U, 173, 2, 2, 16384), - PLL_1443X_RATE(393216000U, 262, 2, 3, 9437), - PLL_1443X_RATE(361267200U, 361, 3, 3, 17511), }; struct imx_pll14xx_clk imx_1443x_pll = { From 5b3b0f7f73639e16d08aeb437ba173981b686fb5 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Mon, 7 Aug 2023 10:47:43 +0200 Subject: [PATCH 1322/2093] clk: imx: pll14xx: align pdiv with reference manual commit 37cfd5e457cbdcd030f378127ff2d62776f641e7 upstream. The PLL14xx hardware can be found on i.MX8M{M,N,P} SoCs and always come with a 6-bit pre-divider. Neither the reference manuals nor the datasheets of these SoCs do mention any restrictions. Furthermore the current code doesn't respect the restrictions from the comment too. Therefore drop the restriction and align the max pre-divider (pdiv) value to 63 to get more accurate frequencies. Fixes: b09c68dc57c9 ("clk: imx: pll14xx: Support dynamic rates") Cc: stable@vger.kernel.org Signed-off-by: Marco Felsch Reviewed-by: Abel Vesa Reviewed-by: Adam Ford Signed-off-by: Philipp Zabel Acked-by: Sascha Hauer Tested-by: Ahmad Fatoum Link: https://lore.kernel.org/r/20230807084744.1184791-1-m.felsch@pengutronix.de Signed-off-by: Abel Vesa Signed-off-by: Greg Kroah-Hartman --- drivers/clk/imx/clk-pll14xx.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c index f3856df92307..416d582a9e8e 100644 --- a/drivers/clk/imx/clk-pll14xx.c +++ b/drivers/clk/imx/clk-pll14xx.c @@ -135,11 +135,10 @@ static void imx_pll14xx_calc_settings(struct clk_pll14xx *pll, unsigned long rat /* * Fractional PLL constrains: * - * a) 6MHz <= prate <= 25MHz - * b) 1 <= p <= 63 (1 <= p <= 4 prate = 24MHz) - * c) 64 <= m <= 1023 - * d) 0 <= s <= 6 - * e) -32768 <= k <= 32767 + * a) 1 <= p <= 63 + * b) 64 <= m <= 1023 + * c) 0 <= s <= 6 + * d) -32768 <= k <= 32767 * * fvco = (m * 65536 + k) * prate / (p * 65536) */ @@ -182,7 +181,7 @@ static void imx_pll14xx_calc_settings(struct clk_pll14xx *pll, unsigned long rat } /* Finally calculate best values */ - for (pdiv = 1; pdiv <= 7; pdiv++) { + for (pdiv = 1; pdiv <= 63; pdiv++) { for (sdiv = 0; sdiv <= 6; sdiv++) { /* calc mdiv = round(rate * pdiv * 2^sdiv) / prate) */ mdiv = DIV_ROUND_CLOSEST(rate * (pdiv << sdiv), prate); From c4e1204bd71437a4e2f885370936fa493fa17c8e Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sat, 13 May 2023 00:17:23 +0300 Subject: [PATCH 1323/2093] clk: qcom: gcc-mdm9615: use proper parent for pll0_vote clock commit 1583694bb4eaf186f17131dbc1b83d6057d2749b upstream. The pll0_vote clock definitely should have pll0 as a parent (instead of pll8). Fixes: 7792a8d6713c ("clk: mdm9615: Add support for MDM9615 Clock Controllers") Cc: stable@kernel.org Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230512211727.3445575-7-dmitry.baryshkov@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/gcc-mdm9615.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-mdm9615.c b/drivers/clk/qcom/gcc-mdm9615.c index 8bed02a748ab..470a277603a9 100644 --- a/drivers/clk/qcom/gcc-mdm9615.c +++ b/drivers/clk/qcom/gcc-mdm9615.c @@ -58,7 +58,7 @@ static struct clk_regmap pll0_vote = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "pll0_vote", - .parent_names = (const char *[]){ "pll8" }, + .parent_names = (const char *[]){ "pll0" }, .num_parents = 1, .ops = &clk_pll_vote_ops, }, From f6250ecb7fbb934b89539e7e2ba6c1d8555c0975 Mon Sep 17 00:00:00 2001 From: Chris Lew Date: Tue, 1 Aug 2023 12:17:12 +0530 Subject: [PATCH 1324/2093] soc: qcom: qmi_encdec: Restrict string length in decode commit 8d207400fd6b79c92aeb2f33bb79f62dff904ea2 upstream. The QMI TLV value for strings in a lot of qmi element info structures account for null terminated strings with MAX_LEN + 1. If a string is actually MAX_LEN + 1 length, this will cause an out of bounds access when the NULL character is appended in decoding. Fixes: 9b8a11e82615 ("soc: qcom: Introduce QMI encoder/decoder") Cc: stable@vger.kernel.org Signed-off-by: Chris Lew Signed-off-by: Praveenkumar I Link: https://lore.kernel.org/r/20230801064712.3590128-1-quic_ipkumar@quicinc.com Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/soc/qcom/qmi_encdec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soc/qcom/qmi_encdec.c b/drivers/soc/qcom/qmi_encdec.c index b7158e3c3a0b..5c7161b18b72 100644 --- a/drivers/soc/qcom/qmi_encdec.c +++ b/drivers/soc/qcom/qmi_encdec.c @@ -534,8 +534,8 @@ static int qmi_decode_string_elem(const struct qmi_elem_info *ei_array, decoded_bytes += rc; } - if (string_len > temp_ei->elem_len) { - pr_err("%s: String len %d > Max Len %d\n", + if (string_len >= temp_ei->elem_len) { + pr_err("%s: String len %d >= Max Len %d\n", __func__, string_len, temp_ei->elem_len); return -ETOOSMALL; } else if (string_len > tlv_len) { From 5310f712157a4129636ae3ffa6d4847e1bcd7e5a Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 18 Jul 2023 15:28:56 +0200 Subject: [PATCH 1325/2093] clk: qcom: dispcc-sm8450: fix runtime PM imbalance on probe errors commit b0f3d01bda6c3f6f811e70f76d2040ae81f64565 upstream. Make sure to decrement the runtime PM usage count before returning in case regmap initialisation fails. Fixes: 16fb89f92ec4 ("clk: qcom: Add support for Display Clock Controller on SM8450") Cc: stable@vger.kernel.org # 6.1 Cc: Dmitry Baryshkov Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230718132902.21430-3-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/dispcc-sm8450.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/dispcc-sm8450.c b/drivers/clk/qcom/dispcc-sm8450.c index 0cd7ebe90301..64626f620a01 100644 --- a/drivers/clk/qcom/dispcc-sm8450.c +++ b/drivers/clk/qcom/dispcc-sm8450.c @@ -1783,8 +1783,10 @@ static int disp_cc_sm8450_probe(struct platform_device *pdev) return ret; regmap = qcom_cc_map(pdev, &disp_cc_sm8450_desc); - if (IS_ERR(regmap)) - return PTR_ERR(regmap); + if (IS_ERR(regmap)) { + ret = PTR_ERR(regmap); + goto err_put_rpm; + } clk_lucid_evo_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); clk_lucid_evo_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); @@ -1799,9 +1801,16 @@ static int disp_cc_sm8450_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0xe05c, BIT(0), BIT(0)); ret = qcom_cc_really_probe(pdev, &disp_cc_sm8450_desc, regmap); + if (ret) + goto err_put_rpm; pm_runtime_put(&pdev->dev); + return 0; + +err_put_rpm: + pm_runtime_put_sync(&pdev->dev); + return ret; } From eab2ece5e4b5099aaf7982e528375ce1c0aff432 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 18 Jul 2023 15:28:59 +0200 Subject: [PATCH 1326/2093] clk: qcom: lpasscc-sc7280: fix missing resume during probe commit 66af5339d4f8e20c6d89a490570bd94d40f1a7f6 upstream. Drivers that enable runtime PM must make sure that the controller is runtime resumed before accessing its registers to prevent the power domain from being disabled. Fixes: 4ab43d171181 ("clk: qcom: Add lpass clock controller driver for SC7280") Cc: stable@vger.kernel.org # 5.16 Cc: Taniya Das Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230718132902.21430-6-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/lpasscc-sc7280.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/clk/qcom/lpasscc-sc7280.c b/drivers/clk/qcom/lpasscc-sc7280.c index 8486d7135ab1..113146835902 100644 --- a/drivers/clk/qcom/lpasscc-sc7280.c +++ b/drivers/clk/qcom/lpasscc-sc7280.c @@ -115,9 +115,13 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev) ret = pm_clk_add(&pdev->dev, "iface"); if (ret < 0) { dev_err(&pdev->dev, "failed to acquire iface clock\n"); - goto destroy_pm_clk; + goto err_destroy_pm_clk; } + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + goto err_destroy_pm_clk; + if (!of_property_read_bool(pdev->dev.of_node, "qcom,adsp-pil-mode")) { lpass_regmap_config.name = "qdsp6ss"; lpass_regmap_config.max_register = 0x3f; @@ -125,7 +129,7 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev) ret = qcom_cc_probe_by_index(pdev, 0, desc); if (ret) - goto destroy_pm_clk; + goto err_put_rpm; } lpass_regmap_config.name = "top_cc"; @@ -134,11 +138,15 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev) ret = qcom_cc_probe_by_index(pdev, 1, desc); if (ret) - goto destroy_pm_clk; + goto err_put_rpm; + + pm_runtime_put(&pdev->dev); return 0; -destroy_pm_clk: +err_put_rpm: + pm_runtime_put_sync(&pdev->dev); +err_destroy_pm_clk: pm_clk_destroy(&pdev->dev); disable_pm_runtime: From 017e60a215d85b82171821fe608ae286c3161ead Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 18 Jul 2023 15:29:00 +0200 Subject: [PATCH 1327/2093] clk: qcom: q6sstop-qcs404: fix missing resume during probe commit 97112c83f4671a4a722f99a53be4e91fac4091bc upstream. Drivers that enable runtime PM must make sure that the controller is runtime resumed before accessing its registers to prevent the power domain from being disabled. Fixes: 6cdef2738db0 ("clk: qcom: Add Q6SSTOP clock controller for QCS404") Cc: stable@vger.kernel.org # 5.5 Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230718132902.21430-7-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/q6sstop-qcs404.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/q6sstop-qcs404.c b/drivers/clk/qcom/q6sstop-qcs404.c index 780074e05841..26e2d63614ac 100644 --- a/drivers/clk/qcom/q6sstop-qcs404.c +++ b/drivers/clk/qcom/q6sstop-qcs404.c @@ -174,21 +174,32 @@ static int q6sstopcc_qcs404_probe(struct platform_device *pdev) return ret; } + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + return ret; + q6sstop_regmap_config.name = "q6sstop_tcsr"; desc = &tcsr_qcs404_desc; ret = qcom_cc_probe_by_index(pdev, 1, desc); if (ret) - return ret; + goto err_put_rpm; q6sstop_regmap_config.name = "q6sstop_cc"; desc = &q6sstop_qcs404_desc; ret = qcom_cc_probe_by_index(pdev, 0, desc); if (ret) - return ret; + goto err_put_rpm; + + pm_runtime_put(&pdev->dev); return 0; + +err_put_rpm: + pm_runtime_put_sync(&pdev->dev); + + return ret; } static const struct dev_pm_ops q6sstopcc_pm_ops = { From 1bb9546c7aedad78d07374d066f4a9eb02c3ded3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 18 Jul 2023 15:29:01 +0200 Subject: [PATCH 1328/2093] clk: qcom: mss-sc7180: fix missing resume during probe commit e2349da0fa7ca822cda72f427345b95795358fe7 upstream. Drivers that enable runtime PM must make sure that the controller is runtime resumed before accessing its registers to prevent the power domain from being disabled. Fixes: 8def929c4097 ("clk: qcom: Add modem clock controller driver for SC7180") Cc: stable@vger.kernel.org # 5.7 Cc: Taniya Das Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230718132902.21430-8-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/clk/qcom/mss-sc7180.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/mss-sc7180.c b/drivers/clk/qcom/mss-sc7180.c index 5a1407440662..d106bc65470e 100644 --- a/drivers/clk/qcom/mss-sc7180.c +++ b/drivers/clk/qcom/mss-sc7180.c @@ -87,11 +87,22 @@ static int mss_sc7180_probe(struct platform_device *pdev) return ret; } - ret = qcom_cc_probe(pdev, &mss_sc7180_desc); - if (ret < 0) + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) return ret; + ret = qcom_cc_probe(pdev, &mss_sc7180_desc); + if (ret < 0) + goto err_put_rpm; + + pm_runtime_put(&pdev->dev); + return 0; + +err_put_rpm: + pm_runtime_put_sync(&pdev->dev); + + return ret; } static const struct dev_pm_ops mss_sc7180_pm_ops = { From dac14a1dbe20e003215dacb8a3a1a7e4ca4e0ad0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 19 Aug 2023 17:22:14 -0400 Subject: [PATCH 1329/2093] NFS: Fix a potential data corruption commit 88975a55969e11f26fe3846bf4fbf8e7dc8cbbd4 upstream. We must ensure that the subrequests are joined back into the head before we can retransmit a request. If the head was not on the commit lists, because the server wrote it synchronously, we still need to add it back to the retransmission list. Add a call that mirrors the effect of nfs_cancel_remove_inode() for O_DIRECT. Fixes: ed5d588fe47f ("NFS: Try to join page groups before an O_DIRECT retransmission") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- fs/nfs/direct.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index cf34d0c30945..3bb530d4bb5c 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -474,13 +474,31 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, return result; } +static void nfs_direct_add_page_head(struct list_head *list, + struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + if (!list_empty(&head->wb_list) || !nfs_lock_request(head)) + return; + if (!list_empty(&head->wb_list)) { + nfs_unlock_request(head); + return; + } + list_add(&head->wb_list, list); + kref_get(&head->wb_kref); + kref_get(&head->wb_kref); +} + static void nfs_direct_join_group(struct list_head *list, struct inode *inode) { struct nfs_page *req, *subreq; list_for_each_entry(req, list, wb_list) { - if (req->wb_head != req) + if (req->wb_head != req) { + nfs_direct_add_page_head(&req->wb_list, req); continue; + } subreq = req->wb_this_page; if (subreq == req) continue; From fd9a8ad2cfa74c648b3ecb547ea931027770978b Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 20 Jul 2023 18:37:51 +0300 Subject: [PATCH 1330/2093] NFSv4/pnfs: minor fix for cleanup path in nfs4_get_device_info commit 96562c45af5c31b89a197af28f79bfa838fb8391 upstream. It is an almost improbable error case but when page allocating loop in nfs4_get_device_info() fails then we should only free the already allocated pages, as __free_page() can't deal with NULL arguments. Found by Linux Verification Center (linuxtesting.org). Cc: stable@vger.kernel.org Signed-off-by: Fedor Pchelkin Reviewed-by: Benjamin Coddington Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- fs/nfs/pnfs_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index ddbbf4fcda86..178001c90156 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -154,7 +154,7 @@ nfs4_get_device_info(struct nfs_server *server, set_bit(NFS_DEVICEID_NOCACHE, &d->flags); out_free_pages: - for (i = 0; i < max_pages; i++) + while (--i >= 0) __free_page(pages[i]); kfree(pages); out_free_pdev: From 8b4d0f3890c89d7c7b670c83e6b40308122e7c56 Mon Sep 17 00:00:00 2001 From: Qiang Yu Date: Thu, 18 May 2023 14:22:39 +0800 Subject: [PATCH 1331/2093] bus: mhi: host: Skip MHI reset if device is in RDDM commit cabce92dd805945a090dc6fc73b001bb35ed083a upstream. In RDDM EE, device can not process MHI reset issued by host. In case of MHI power off, host is issuing MHI reset and polls for it to get cleared until it times out. Since this timeout can not be avoided in case of RDDM, skip the MHI reset in this scenarios. Cc: Fixes: a6e2e3522f29 ("bus: mhi: core: Add support for PM state transitions") Signed-off-by: Qiang Yu Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1684390959-17836-1-git-send-email-quic_qianyu@quicinc.com Signed-off-by: Manivannan Sadhasivam Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/host/pm.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c index 083459028a4b..8a4362d75fc4 100644 --- a/drivers/bus/mhi/host/pm.c +++ b/drivers/bus/mhi/host/pm.c @@ -470,6 +470,10 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl) /* Trigger MHI RESET so that the device will not access host memory */ if (!MHI_PM_IN_FATAL_STATE(mhi_cntrl->pm_state)) { + /* Skip MHI RESET if in RDDM state */ + if (mhi_cntrl->rddm_image && mhi_get_exec_env(mhi_cntrl) == MHI_EE_RDDM) + goto skip_mhi_reset; + dev_dbg(dev, "Triggering MHI Reset in device\n"); mhi_set_mhi_state(mhi_cntrl, MHI_STATE_RESET); @@ -495,6 +499,7 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl) } } +skip_mhi_reset: dev_dbg(dev, "Waiting for all pending event ring processing to complete\n"); mhi_event = mhi_cntrl->mhi_event; From 5f7676fdaf4242607160cff87576bfb5c505a042 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 23:51:02 +0530 Subject: [PATCH 1332/2093] net: add SKB_HEAD_ALIGN() helper commit 115f1a5c42bdad9a9ea356fc0b4a39ec7537947f upstream. We have many places using this expression: SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) Use of SKB_HEAD_ALIGN() will allow to clean them. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Paolo Abeni Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski [Ajay: Regenerated the patch for v6.1.y] Signed-off-by: Ajay Kaher Signed-off-by: Greg Kroah-Hartman --- include/linux/skbuff.h | 8 ++++++++ net/core/skbuff.c | 18 ++++++------------ 2 files changed, 14 insertions(+), 12 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cc5ed2cf25f6..2feee144fc0e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -261,6 +261,14 @@ #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + +/* For X bytes available in skb->head, what is the minimal + * allocation needed, knowing struct skb_shared_info needs + * to be aligned. + */ +#define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 24bf4aa222d2..4aea8f546b3f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -504,8 +504,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = SKB_HEAD_ALIGN(size); osize = kmalloc_size_roundup(size); data = kmalloc_reserve(osize, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) @@ -578,8 +577,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, goto skb_success; } - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; @@ -678,8 +676,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, data = page_frag_alloc_1k(&nc->page_small, gfp_mask); pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); } else { - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; @@ -1837,8 +1834,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = SKB_HEAD_ALIGN(size); size = kmalloc_size_roundup(size); data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) @@ -6204,8 +6200,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = SKB_HEAD_ALIGN(size); size = kmalloc_size_roundup(size); data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) @@ -6323,8 +6318,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = SKB_HEAD_ALIGN(size); size = kmalloc_size_roundup(size); data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) From 36974c3a5438f6ddeb2f0037aebacde46c662014 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 23:51:03 +0530 Subject: [PATCH 1333/2093] net: remove osize variable in __alloc_skb() commit 65998d2bf857b9ae5acc1f3b70892bd1b429ccab upstream. This is a cleanup patch, to prepare following change. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Paolo Abeni Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski [Ajay: Regenerated the patch for v6.1.y] Signed-off-by: Ajay Kaher Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4aea8f546b3f..1c059b695f4e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -479,7 +479,6 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, { struct kmem_cache *cache; struct sk_buff *skb; - unsigned int osize; bool pfmemalloc; u8 *data; @@ -505,16 +504,15 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * Both skb->head and skb_shared_info are cache line aligned. */ size = SKB_HEAD_ALIGN(size); - osize = kmalloc_size_roundup(size); - data = kmalloc_reserve(osize, gfp_mask, node, &pfmemalloc); + size = kmalloc_size_roundup(size); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - size = SKB_WITH_OVERHEAD(osize); - prefetchw(data + size); + prefetchw(data + SKB_WITH_OVERHEAD(size)); /* * Only clear those fields we need to clear, not those that we will @@ -522,7 +520,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - __build_skb_around(skb, data, osize); + __build_skb_around(skb, data, size); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { From 2b39866f0a38fa6d2f8d054addbe90b8fed04632 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 23:51:04 +0530 Subject: [PATCH 1334/2093] net: factorize code in kmalloc_reserve() commit 5c0e820cbbbe2d1c4cea5cd2bfc1302c123436df upstream. All kmalloc_reserve() callers have to make the same computation, we can factorize them, to prepare following patch in the series. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Acked-by: Paolo Abeni Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski [Ajay: Regenerated the patch for v6.1.y] Signed-off-by: Ajay Kaher Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1c059b695f4e..fb8d100b0c7d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -424,17 +424,20 @@ EXPORT_SYMBOL(napi_build_skb); * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ -static void *kmalloc_reserve(size_t size, gfp_t flags, int node, +static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { - void *obj; bool ret_pfmemalloc = false; + unsigned int obj_size; + void *obj; + obj_size = SKB_HEAD_ALIGN(*size); + *size = obj_size = kmalloc_size_roundup(obj_size); /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ - obj = kmalloc_node_track_caller(size, + obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) @@ -442,7 +445,7 @@ static void *kmalloc_reserve(size_t size, gfp_t flags, int node, /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmalloc_node_track_caller(size, flags, node); + obj = kmalloc_node_track_caller(obj_size, flags, node); out: if (pfmemalloc) @@ -503,9 +506,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ - size = SKB_HEAD_ALIGN(size); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); + data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. @@ -1832,9 +1833,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_HEAD_ALIGN(size); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); @@ -6198,9 +6197,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_HEAD_ALIGN(size); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6316,9 +6313,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_HEAD_ALIGN(size); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); From 31cf7853a940181593e4472fc56f46574123f9f6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 23:51:05 +0530 Subject: [PATCH 1335/2093] net: deal with integer overflows in kmalloc_reserve() commit 915d975b2ffa58a14bfcf16fafe00c41315949ff upstream. Blamed commit changed: ptr = kmalloc(size); if (ptr) size = ksize(ptr); to: size = kmalloc_size_roundup(size); ptr = kmalloc(size); This allowed various crash as reported by syzbot [1] and Kyle Zeng. Problem is that if @size is bigger than 0x80000001, kmalloc_size_roundup(size) returns 2^32. kmalloc_reserve() uses a 32bit variable (obj_size), so 2^32 is truncated to 0. kmalloc(0) returns ZERO_SIZE_PTR which is not handled by skb allocations. Following trace can be triggered if a netdev->mtu is set close to 0x7fffffff We might in the future limit netdev->mtu to more sensible limit (like KMALLOC_MAX_SIZE). This patch is based on a syzbot report, and also a report and tentative fix from Kyle Zeng. [1] BUG: KASAN: user-memory-access in __build_skb_around net/core/skbuff.c:294 [inline] BUG: KASAN: user-memory-access in __alloc_skb+0x3c4/0x6e8 net/core/skbuff.c:527 Write of size 32 at addr 00000000fffffd10 by task syz-executor.4/22554 CPU: 1 PID: 22554 Comm: syz-executor.4 Not tainted 6.1.39-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/03/2023 Call trace: dump_backtrace+0x1c8/0x1f4 arch/arm64/kernel/stacktrace.c:279 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:286 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x120/0x1a0 lib/dump_stack.c:106 print_report+0xe4/0x4b4 mm/kasan/report.c:398 kasan_report+0x150/0x1ac mm/kasan/report.c:495 kasan_check_range+0x264/0x2a4 mm/kasan/generic.c:189 memset+0x40/0x70 mm/kasan/shadow.c:44 __build_skb_around net/core/skbuff.c:294 [inline] __alloc_skb+0x3c4/0x6e8 net/core/skbuff.c:527 alloc_skb include/linux/skbuff.h:1316 [inline] igmpv3_newpack+0x104/0x1088 net/ipv4/igmp.c:359 add_grec+0x81c/0x1124 net/ipv4/igmp.c:534 igmpv3_send_cr net/ipv4/igmp.c:667 [inline] igmp_ifc_timer_expire+0x1b0/0x1008 net/ipv4/igmp.c:810 call_timer_fn+0x1c0/0x9f0 kernel/time/timer.c:1474 expire_timers kernel/time/timer.c:1519 [inline] __run_timers+0x54c/0x710 kernel/time/timer.c:1790 run_timer_softirq+0x28/0x4c kernel/time/timer.c:1803 _stext+0x380/0xfbc ____do_softirq+0x14/0x20 arch/arm64/kernel/irq.c:79 call_on_irq_stack+0x24/0x4c arch/arm64/kernel/entry.S:891 do_softirq_own_stack+0x20/0x2c arch/arm64/kernel/irq.c:84 invoke_softirq kernel/softirq.c:437 [inline] __irq_exit_rcu+0x1c0/0x4cc kernel/softirq.c:683 irq_exit_rcu+0x14/0x78 kernel/softirq.c:695 el0_interrupt+0x7c/0x2e0 arch/arm64/kernel/entry-common.c:717 __el0_irq_handler_common+0x18/0x24 arch/arm64/kernel/entry-common.c:724 el0t_64_irq_handler+0x10/0x1c arch/arm64/kernel/entry-common.c:729 el0t_64_irq+0x1a0/0x1a4 arch/arm64/kernel/entry.S:584 Fixes: 12d6c1d3a2ad ("skbuff: Proactively round up to kmalloc bucket size") Reported-by: syzbot Reported-by: Kyle Zeng Signed-off-by: Eric Dumazet Cc: Kees Cook Cc: Vlastimil Babka Signed-off-by: David S. Miller [Ajay: Regenerated the patch for v6.1.y] Signed-off-by: Ajay Kaher Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fb8d100b0c7d..8dca4a7ca4a1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -428,11 +428,17 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { bool ret_pfmemalloc = false; - unsigned int obj_size; + size_t obj_size; void *obj; obj_size = SKB_HEAD_ALIGN(*size); - *size = obj_size = kmalloc_size_roundup(obj_size); + + obj_size = kmalloc_size_roundup(obj_size); + /* The following cast might truncate high-order bits of obj_size, this + * is harmless because kmalloc(obj_size >= 2^32) will fail anyway. + */ + *size = (unsigned int)obj_size; + /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. From 390275d7a86314334d14851944b65608e5b42356 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 22 Jul 2023 13:47:48 +0900 Subject: [PATCH 1336/2093] kbuild: rpm-pkg: define _arch conditionally [ Upstream commit 233046a2afd12a4f699305b92ee634eebf1e4f31 ] Commit 3089b2be0cce ("kbuild: rpm-pkg: fix build error when _arch is undefined") does not work as intended; _arch is always defined as $UTS_MACHINE. The intention was to define _arch to $UTS_MACHINE only when it is not defined. Fixes: 3089b2be0cce ("kbuild: rpm-pkg: fix build error when _arch is undefined") Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/package/mkspec | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/package/mkspec b/scripts/package/mkspec index 70392fd2fd29..f892cf8e37f0 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -51,7 +51,7 @@ $S Source: kernel-$__KERNELRELEASE.tar.gz Provides: $PROVIDES # $UTS_MACHINE as a fallback of _arch in case # /usr/lib/rpm/platform/*/macros was not included. - %define _arch %{?_arch:$UTS_MACHINE} + %{!?_arch: %define _arch $UTS_MACHINE} %define __spec_install_post /usr/lib/rpm/brp-compress || : %define debug_package %{nil} From 46d3bc902b038d4e761d27a069afe5bc686b42eb Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 23 Aug 2023 20:50:41 +0900 Subject: [PATCH 1337/2093] kbuild: do not run depmod for 'make modules_sign' [ Upstream commit 2429742e506a2b5939a62c629c4a46d91df0ada8 ] Commit 961ab4a3cd66 ("kbuild: merge scripts/Makefile.modsign to scripts/Makefile.modinst") started to run depmod at the end of 'make modules_sign'. Move the depmod rule to scripts/Makefile.modinst and run it only when $(modules_sign_only) is empty. Fixes: 961ab4a3cd66 ("kbuild: merge scripts/Makefile.modsign to scripts/Makefile.modinst") Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier Signed-off-by: Sasha Levin --- Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Makefile b/Makefile index 35fc0d62898d..f23edaa0e813 100644 --- a/Makefile +++ b/Makefile @@ -1939,7 +1939,9 @@ quiet_cmd_depmod = DEPMOD $(MODLIB) modules_install: $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst +ifndef modules_sign_only $(call cmd,depmod) +endif else # CONFIG_MODULES From c4807163e2d4cec9ca4a95eb8952a716f9c5ea1c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 25 Feb 2023 11:58:48 +0100 Subject: [PATCH 1338/2093] tpm_crb: Fix an error handling path in crb_acpi_add() [ Upstream commit 9c377852ddfdc557b1370f196b0cfdf28d233460 ] Some error paths don't call acpi_put_table() before returning. Branch to the correct place instead of doing some direct return. Fixes: 4d2732882703 ("tpm_crb: Add support for CRB devices based on Pluton") Signed-off-by: Christophe JAILLET Acked-by: Matthew Garrett Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_crb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index db0b774207d3..f45239e73c4c 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -775,12 +775,13 @@ static int crb_acpi_add(struct acpi_device *device) FW_BUG "TPM2 ACPI table has wrong size %u for start method type %d\n", buf->header.length, ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON); - return -EINVAL; + rc = -EINVAL; + goto out; } crb_pluton = ACPI_ADD_PTR(struct tpm2_crb_pluton, buf, sizeof(*buf)); rc = crb_map_pluton(dev, priv, buf, crb_pluton); if (rc) - return rc; + goto out; } priv->sm = sm; From 694e43f22c5b4b52be73b6a2b26dddab382660b6 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Aug 2023 15:46:16 +0200 Subject: [PATCH 1339/2093] gfs2: Switch to wait_event in gfs2_logd [ Upstream commit 6df373b09b1dcf2f7d579f515f653f89a896d417 ] In gfs2_logd(), switch from an open-coded wait loop to wait_event_interruptible_timeout(). Signed-off-by: Andreas Gruenbacher Stable-dep-of: b74cd55aa9a9 ("gfs2: low-memory forced flush fixes") Signed-off-by: Sasha Levin --- fs/gfs2/log.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 61323deb80bc..69c3facfcbef 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1304,7 +1304,6 @@ int gfs2_logd(void *data) { struct gfs2_sbd *sdp = data; unsigned long t = 1; - DEFINE_WAIT(wait); while (!kthread_should_stop()) { @@ -1341,17 +1340,11 @@ int gfs2_logd(void *data) try_to_freeze(); - do { - prepare_to_wait(&sdp->sd_logd_waitq, &wait, - TASK_INTERRUPTIBLE); - if (!gfs2_ail_flush_reqd(sdp) && - !gfs2_jrnl_flush_reqd(sdp) && - !kthread_should_stop()) - t = schedule_timeout(t); - } while(t && !gfs2_ail_flush_reqd(sdp) && - !gfs2_jrnl_flush_reqd(sdp) && - !kthread_should_stop()); - finish_wait(&sdp->sd_logd_waitq, &wait); + t = wait_event_interruptible_timeout(sdp->sd_logd_waitq, + gfs2_ail_flush_reqd(sdp) || + gfs2_jrnl_flush_reqd(sdp) || + kthread_should_stop(), + t); } return 0; From 36201d559b47ec95b6689b16d8b6b6e12fa02d9b Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 10 Aug 2023 17:15:46 +0200 Subject: [PATCH 1340/2093] gfs2: low-memory forced flush fixes [ Upstream commit b74cd55aa9a9d0aca760028a51343ec79812e410 ] First, function gfs2_ail_flush_reqd checks the SDF_FORCE_AIL_FLUSH flag to determine if an AIL flush should be forced in low-memory situations. However, it also immediately clears the flag, and when called repeatedly as in function gfs2_logd, the flag will be lost. Fix that by pulling the SDF_FORCE_AIL_FLUSH flag check out of gfs2_ail_flush_reqd. Second, function gfs2_writepages sets the SDF_FORCE_AIL_FLUSH flag whether or not enough pages were written. If enough pages could be written, flushing the AIL is unnecessary, though. Third, gfs2_writepages doesn't wake up logd after setting the SDF_FORCE_AIL_FLUSH flag, so it can take a long time for logd to react. It would be preferable to wake up logd, but that hurts the performance of some workloads and we don't quite understand why so far, so don't wake up logd so far. Fixes: b066a4eebd4f ("gfs2: forcibly flush ail to relieve memory pressure") Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/aops.c | 4 ++-- fs/gfs2/log.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 2f04c0ff7470..1e9fa26f04fe 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -182,13 +182,13 @@ static int gfs2_writepages(struct address_space *mapping, int ret; /* - * Even if we didn't write any pages here, we might still be holding + * Even if we didn't write enough pages here, we might still be holding * dirty pages in the ail. We forcibly flush the ail because we don't * want balance_dirty_pages() to loop indefinitely trying to write out * pages held in the ail that it can't find. */ ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops); - if (ret == 0) + if (ret == 0 && wbc->nr_to_write > 0) set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags); return ret; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 69c3facfcbef..e021d5f50c23 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1285,9 +1285,6 @@ static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp) { unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free); - if (test_and_clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags)) - return 1; - return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >= atomic_read(&sdp->sd_log_thresh2); } @@ -1328,7 +1325,9 @@ int gfs2_logd(void *data) GFS2_LFC_LOGD_JFLUSH_REQD); } - if (gfs2_ail_flush_reqd(sdp)) { + if (test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) || + gfs2_ail_flush_reqd(sdp)) { + clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags); gfs2_ail1_start(sdp); gfs2_ail1_wait(sdp); gfs2_ail1_empty(sdp, 0); @@ -1341,6 +1340,7 @@ int gfs2_logd(void *data) try_to_freeze(); t = wait_event_interruptible_timeout(sdp->sd_logd_waitq, + test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) || gfs2_ail_flush_reqd(sdp) || gfs2_jrnl_flush_reqd(sdp) || kthread_should_stop(), From 39c29d075352a642bc3ea5fe5969fbd77b1db299 Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Wed, 2 Aug 2023 09:52:22 -0400 Subject: [PATCH 1341/2093] mailbox: qcom-ipcc: fix incorrect num_chans counting [ Upstream commit a493208079e299aefdc15169dc80e3da3ebb718a ] Breaking out early when a match is found leads to an incorrect num_chans value when more than one ipcc mailbox channel is used by the same device. Fixes: e9d50e4b4d04 ("mailbox: qcom-ipcc: Dynamic alloc for channel arrangement") Signed-off-by: Jonathan Marek Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/qcom-ipcc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c index 7e27acf6c0cc..f597a1bd5684 100644 --- a/drivers/mailbox/qcom-ipcc.c +++ b/drivers/mailbox/qcom-ipcc.c @@ -227,10 +227,8 @@ static int qcom_ipcc_setup_mbox(struct qcom_ipcc *ipcc, ret = of_parse_phandle_with_args(client_dn, "mboxes", "#mbox-cells", j, &curr_ph); of_node_put(curr_ph.np); - if (!ret && curr_ph.np == controller_dn) { + if (!ret && curr_ph.np == controller_dn) ipcc->num_chans++; - break; - } } } From 8ab59422395027abab0b1acc05e3edcc5c942643 Mon Sep 17 00:00:00 2001 From: Konstantin Meskhidze Date: Tue, 5 Sep 2023 17:59:14 +0800 Subject: [PATCH 1342/2093] kconfig: fix possible buffer overflow [ Upstream commit a3b7039bb2b22fcd2ad20d59c00ed4e606ce3754 ] Buffer 'new_argv' is accessed without bound check after accessing with bound check via 'new_argc' index. Fixes: e298f3b49def ("kconfig: add built-in function support") Co-developed-by: Ivanov Mikhail Signed-off-by: Konstantin Meskhidze Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/kconfig/preprocess.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/scripts/kconfig/preprocess.c b/scripts/kconfig/preprocess.c index 748da578b418..d1f5bcff4b62 100644 --- a/scripts/kconfig/preprocess.c +++ b/scripts/kconfig/preprocess.c @@ -396,6 +396,9 @@ static char *eval_clause(const char *str, size_t len, int argc, char *argv[]) p++; } + + if (new_argc >= FUNCTION_MAX_ARGS) + pperror("too many function arguments"); new_argv[new_argc++] = prev; /* From eb17c3d0055b0be441c845ff4ee29c3a842ea5a4 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Sun, 9 Jul 2023 12:06:37 -0500 Subject: [PATCH 1343/2093] Input: iqs7222 - configure power mode before triggering ATI [ Upstream commit 2e00b8bf5624767f6be7427b6eb532524793463e ] If the device drops into ultra-low-power mode before being placed into normal-power mode as part of ATI being triggered, the device does not assert any interrupts until the ATI routine is restarted two seconds later. Solve this problem by adopting the vendor's recommendation, which calls for the device to be placed into normal-power mode prior to being configured and ATI being triggered. The original implementation followed this sequence, but the order was inadvertently changed as part of the resolution of a separate erratum. Fixes: 1e4189d8af27 ("Input: iqs7222 - protect volatile registers") Signed-off-by: Jeff LaBundy Link: https://lore.kernel.org/r/ZKrpHc2Ji9qR25r2@nixie71 Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/iqs7222.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c index e47ab6c1177f..f24b174c7266 100644 --- a/drivers/input/misc/iqs7222.c +++ b/drivers/input/misc/iqs7222.c @@ -1381,9 +1381,6 @@ static int iqs7222_ati_trigger(struct iqs7222_private *iqs7222) if (error) return error; - sys_setup &= ~IQS7222_SYS_SETUP_INTF_MODE_MASK; - sys_setup &= ~IQS7222_SYS_SETUP_PWR_MODE_MASK; - for (i = 0; i < IQS7222_NUM_RETRIES; i++) { /* * Trigger ATI from streaming and normal-power modes so that @@ -1561,8 +1558,11 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir) return error; } - if (dir == READ) + if (dir == READ) { + iqs7222->sys_setup[0] &= ~IQS7222_SYS_SETUP_INTF_MODE_MASK; + iqs7222->sys_setup[0] &= ~IQS7222_SYS_SETUP_PWR_MODE_MASK; return 0; + } return iqs7222_ati_trigger(iqs7222); } From e5dee8222d7ccd1e1676229618e2f77e80b432df Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 1344/2093] perf trace: Use zfree() to reduce chances of use after free [ Upstream commit 9997d5dd177c52017fa0541bf236a4232c8148e6 ] Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: 7962ef13651a ("perf trace: Really free the evsel->priv area") Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 97b17f8941dc..6392fcf2610c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2293,7 +2293,7 @@ static void syscall__exit(struct syscall *sc) if (!sc) return; - free(sc->arg_fmt); + zfree(&sc->arg_fmt); } static int trace__sys_enter(struct trace *trace, struct evsel *evsel, @@ -3129,7 +3129,7 @@ static void evlist__free_syscall_tp_fields(struct evlist *evlist) if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls")) continue; - free(et->fmt); + zfree(&et->fmt); free(et); } } @@ -4765,11 +4765,11 @@ static void trace__exit(struct trace *trace) int i; strlist__delete(trace->ev_qualifier); - free(trace->ev_qualifier_ids.entries); + zfree(&trace->ev_qualifier_ids.entries); if (trace->syscalls.table) { for (i = 0; i <= trace->sctbl->syscalls.max_id; i++) syscall__exit(&trace->syscalls.table[i]); - free(trace->syscalls.table); + zfree(&trace->syscalls.table); } syscalltbl__delete(trace->sctbl); zfree(&trace->perfconfig_events); From 62dd514c34be63d3d5cae1f52a7e8b96c6dd6630 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 19 Jul 2023 15:37:14 -0300 Subject: [PATCH 1345/2093] perf trace: Really free the evsel->priv area [ Upstream commit 7962ef13651a9163f07b530607392ea123482e8a ] In 3cb4d5e00e037c70 ("perf trace: Free syscall tp fields in evsel->priv") it only was freeing if strcmp(evsel->tp_format->system, "syscalls") returned zero, while the corresponding initialization of evsel->priv was being performed if it was _not_ zero, i.e. if the tp system wasn't 'syscalls'. Just stop looking for that and free it if evsel->priv was set, which should be equivalent. Also use the pre-existing evsel_trace__delete() function. This resolves these leaks, detected with: $ make EXTRA_CFLAGS="-fsanitize=address" BUILD_BPF_SKEL=1 CORESIGHT=1 O=/tmp/build/perf-tools-next -C tools/perf install-bin ================================================================= ==481565==ERROR: LeakSanitizer: detected memory leaks Direct leak of 40 byte(s) in 1 object(s) allocated from: #0 0x7f7343cba097 in calloc (/lib64/libasan.so.8+0xba097) #1 0x987966 in zalloc (/home/acme/bin/perf+0x987966) #2 0x52f9b9 in evsel_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:307 #3 0x52f9b9 in evsel__syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:333 #4 0x52f9b9 in evsel__init_raw_syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:458 #5 0x52f9b9 in perf_evsel__raw_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:480 #6 0x540e8b in trace__add_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3212 #7 0x540e8b in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3891 #8 0x540e8b in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5156 #9 0x5ef262 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323 #10 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377 #11 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421 #12 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537 #13 0x7f7342c4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f) Direct leak of 40 byte(s) in 1 object(s) allocated from: #0 0x7f7343cba097 in calloc (/lib64/libasan.so.8+0xba097) #1 0x987966 in zalloc (/home/acme/bin/perf+0x987966) #2 0x52f9b9 in evsel_trace__new /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:307 #3 0x52f9b9 in evsel__syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:333 #4 0x52f9b9 in evsel__init_raw_syscall_tp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:458 #5 0x52f9b9 in perf_evsel__raw_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:480 #6 0x540dd1 in trace__add_syscall_newtp /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3205 #7 0x540dd1 in trace__run /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:3891 #8 0x540dd1 in cmd_trace /home/acme/git/perf-tools-next/tools/perf/builtin-trace.c:5156 #9 0x5ef262 in run_builtin /home/acme/git/perf-tools-next/tools/perf/perf.c:323 #10 0x4196da in handle_internal_command /home/acme/git/perf-tools-next/tools/perf/perf.c:377 #11 0x4196da in run_argv /home/acme/git/perf-tools-next/tools/perf/perf.c:421 #12 0x4196da in main /home/acme/git/perf-tools-next/tools/perf/perf.c:537 #13 0x7f7342c4a50f in __libc_start_call_main (/lib64/libc.so.6+0x2750f) SUMMARY: AddressSanitizer: 80 byte(s) leaked in 2 allocation(s). [root@quaco ~]# With this we plug all leaks with "perf trace sleep 1". Fixes: 3cb4d5e00e037c70 ("perf trace: Free syscall tp fields in evsel->priv") Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Link: https://lore.kernel.org/lkml/20230719202951.534582-5-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6392fcf2610c..93dab6423a04 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3124,13 +3124,8 @@ static void evlist__free_syscall_tp_fields(struct evlist *evlist) struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - struct evsel_trace *et = evsel->priv; - - if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls")) - continue; - - zfree(&et->fmt); - free(et); + evsel_trace__delete(evsel->priv); + evsel->priv = NULL; } } From b9734e8505bd8094e028ad43add9aa0188f82142 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:17 +0100 Subject: [PATCH 1346/2093] pwm: atmel-tcb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9609284a76978daf53a54e05cff36873a75e4d13 ] The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Claudiu Beznea Signed-off-by: Thierry Reding Stable-dep-of: c11622324c02 ("pwm: atmel-tcb: Fix resource freeing in error path and remove") Signed-off-by: Sasha Levin --- drivers/pwm/pwm-atmel-tcb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c index 2837b4ce8053..4a116dc44f6e 100644 --- a/drivers/pwm/pwm-atmel-tcb.c +++ b/drivers/pwm/pwm-atmel-tcb.c @@ -500,7 +500,7 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) return err; } -static int atmel_tcb_pwm_remove(struct platform_device *pdev) +static void atmel_tcb_pwm_remove(struct platform_device *pdev) { struct atmel_tcb_pwm_chip *tcbpwm = platform_get_drvdata(pdev); @@ -509,8 +509,6 @@ static int atmel_tcb_pwm_remove(struct platform_device *pdev) clk_disable_unprepare(tcbpwm->slow_clk); clk_put(tcbpwm->slow_clk); clk_put(tcbpwm->clk); - - return 0; } static const struct of_device_id atmel_tcb_pwm_dt_ids[] = { @@ -564,7 +562,7 @@ static struct platform_driver atmel_tcb_pwm_driver = { .pm = &atmel_tcb_pwm_pm_ops, }, .probe = atmel_tcb_pwm_probe, - .remove = atmel_tcb_pwm_remove, + .remove_new = atmel_tcb_pwm_remove, }; module_platform_driver(atmel_tcb_pwm_driver); From c42256a283d607a95be6906412279a7ff3edcaba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 19 Jul 2023 21:20:09 +0200 Subject: [PATCH 1347/2093] pwm: atmel-tcb: Harmonize resource allocation order MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0323e8fedd1ef25342cf7abf3a2024f5670362b8 ] Allocate driver data as first resource in the probe function. This way it can be used during allocation of the other resources (instead of assigning these to local variables first and update driver data only when it's allocated). Also as driver data is allocated using a devm function this should happen first to have the order of freeing resources in the error path and the remove function in reverse. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Stable-dep-of: c11622324c02 ("pwm: atmel-tcb: Fix resource freeing in error path and remove") Signed-off-by: Sasha Levin --- drivers/pwm/pwm-atmel-tcb.c | 49 +++++++++++++++---------------------- 1 file changed, 20 insertions(+), 29 deletions(-) diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c index 4a116dc44f6e..613dd1810fb5 100644 --- a/drivers/pwm/pwm-atmel-tcb.c +++ b/drivers/pwm/pwm-atmel-tcb.c @@ -422,13 +422,14 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) struct atmel_tcb_pwm_chip *tcbpwm; const struct atmel_tcb_config *config; struct device_node *np = pdev->dev.of_node; - struct regmap *regmap; - struct clk *clk, *gclk = NULL; - struct clk *slow_clk; char clk_name[] = "t0_clk"; int err; int channel; + tcbpwm = devm_kzalloc(&pdev->dev, sizeof(*tcbpwm), GFP_KERNEL); + if (tcbpwm == NULL) + return -ENOMEM; + err = of_property_read_u32(np, "reg", &channel); if (err < 0) { dev_err(&pdev->dev, @@ -437,47 +438,37 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) return err; } - regmap = syscon_node_to_regmap(np->parent); - if (IS_ERR(regmap)) - return PTR_ERR(regmap); + tcbpwm->regmap = syscon_node_to_regmap(np->parent); + if (IS_ERR(tcbpwm->regmap)) + return PTR_ERR(tcbpwm->regmap); - slow_clk = of_clk_get_by_name(np->parent, "slow_clk"); - if (IS_ERR(slow_clk)) - return PTR_ERR(slow_clk); + tcbpwm->slow_clk = of_clk_get_by_name(np->parent, "slow_clk"); + if (IS_ERR(tcbpwm->slow_clk)) + return PTR_ERR(tcbpwm->slow_clk); clk_name[1] += channel; - clk = of_clk_get_by_name(np->parent, clk_name); - if (IS_ERR(clk)) - clk = of_clk_get_by_name(np->parent, "t0_clk"); - if (IS_ERR(clk)) - return PTR_ERR(clk); + tcbpwm->clk = of_clk_get_by_name(np->parent, clk_name); + if (IS_ERR(tcbpwm->clk)) + tcbpwm->clk = of_clk_get_by_name(np->parent, "t0_clk"); + if (IS_ERR(tcbpwm->clk)) + return PTR_ERR(tcbpwm->clk); match = of_match_node(atmel_tcb_of_match, np->parent); config = match->data; if (config->has_gclk) { - gclk = of_clk_get_by_name(np->parent, "gclk"); - if (IS_ERR(gclk)) - return PTR_ERR(gclk); - } - - tcbpwm = devm_kzalloc(&pdev->dev, sizeof(*tcbpwm), GFP_KERNEL); - if (tcbpwm == NULL) { - err = -ENOMEM; - goto err_slow_clk; + tcbpwm->gclk = of_clk_get_by_name(np->parent, "gclk"); + if (IS_ERR(tcbpwm->gclk)) + return PTR_ERR(tcbpwm->gclk); } tcbpwm->chip.dev = &pdev->dev; tcbpwm->chip.ops = &atmel_tcb_pwm_ops; tcbpwm->chip.npwm = NPWM; tcbpwm->channel = channel; - tcbpwm->regmap = regmap; - tcbpwm->clk = clk; - tcbpwm->gclk = gclk; - tcbpwm->slow_clk = slow_clk; tcbpwm->width = config->counter_width; - err = clk_prepare_enable(slow_clk); + err = clk_prepare_enable(tcbpwm->slow_clk); if (err) goto err_slow_clk; @@ -495,7 +486,7 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) clk_disable_unprepare(tcbpwm->slow_clk); err_slow_clk: - clk_put(slow_clk); + clk_put(tcbpwm->slow_clk); return err; } From 9de7eb95bbe82ab36213790cf93849f023e0e492 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 19 Jul 2023 21:20:10 +0200 Subject: [PATCH 1348/2093] pwm: atmel-tcb: Fix resource freeing in error path and remove MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c11622324c023415fb69196c5fc3782d2b8cced0 ] Several resources were not freed in the error path and the remove function. Add the forgotten items. Fixes: 34cbcd72588f ("pwm: atmel-tcb: Add sama5d2 support") Fixes: 061f8572a31c ("pwm: atmel-tcb: Switch to new binding") Signed-off-by: Uwe Kleine-König Reviewed-by: Claudiu Beznea Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-atmel-tcb.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c index 613dd1810fb5..2826fc216d29 100644 --- a/drivers/pwm/pwm-atmel-tcb.c +++ b/drivers/pwm/pwm-atmel-tcb.c @@ -450,16 +450,20 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) tcbpwm->clk = of_clk_get_by_name(np->parent, clk_name); if (IS_ERR(tcbpwm->clk)) tcbpwm->clk = of_clk_get_by_name(np->parent, "t0_clk"); - if (IS_ERR(tcbpwm->clk)) - return PTR_ERR(tcbpwm->clk); + if (IS_ERR(tcbpwm->clk)) { + err = PTR_ERR(tcbpwm->clk); + goto err_slow_clk; + } match = of_match_node(atmel_tcb_of_match, np->parent); config = match->data; if (config->has_gclk) { tcbpwm->gclk = of_clk_get_by_name(np->parent, "gclk"); - if (IS_ERR(tcbpwm->gclk)) - return PTR_ERR(tcbpwm->gclk); + if (IS_ERR(tcbpwm->gclk)) { + err = PTR_ERR(tcbpwm->gclk); + goto err_clk; + } } tcbpwm->chip.dev = &pdev->dev; @@ -470,7 +474,7 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) err = clk_prepare_enable(tcbpwm->slow_clk); if (err) - goto err_slow_clk; + goto err_gclk; spin_lock_init(&tcbpwm->lock); @@ -485,6 +489,12 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) err_disable_clk: clk_disable_unprepare(tcbpwm->slow_clk); +err_gclk: + clk_put(tcbpwm->gclk); + +err_clk: + clk_put(tcbpwm->clk); + err_slow_clk: clk_put(tcbpwm->slow_clk); @@ -498,8 +508,9 @@ static void atmel_tcb_pwm_remove(struct platform_device *pdev) pwmchip_remove(&tcbpwm->chip); clk_disable_unprepare(tcbpwm->slow_clk); - clk_put(tcbpwm->slow_clk); + clk_put(tcbpwm->gclk); clk_put(tcbpwm->clk); + clk_put(tcbpwm->slow_clk); } static const struct of_device_id atmel_tcb_pwm_dt_ids[] = { From d7add200199168109a2de4d71878b8a937ff094d Mon Sep 17 00:00:00 2001 From: Ying Liu Date: Fri, 21 Jul 2023 09:29:03 +0000 Subject: [PATCH 1349/2093] backlight: gpio_backlight: Drop output GPIO direction check for initial power state [ Upstream commit fe1328b5b2a087221e31da77e617f4c2b70f3b7f ] So, let's drop output GPIO direction check and only check GPIO value to set the initial power state. Fixes: 706dc68102bc ("backlight: gpio: Explicitly set the direction of the GPIO") Signed-off-by: Liu Ying Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20230721093342.1532531-1-victor.liu@nxp.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/video/backlight/gpio_backlight.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c index 5c5c99f7979e..30ec5b684533 100644 --- a/drivers/video/backlight/gpio_backlight.c +++ b/drivers/video/backlight/gpio_backlight.c @@ -87,8 +87,7 @@ static int gpio_backlight_probe(struct platform_device *pdev) /* Not booted with device tree or no phandle link to the node */ bl->props.power = def_value ? FB_BLANK_UNBLANK : FB_BLANK_POWERDOWN; - else if (gpiod_get_direction(gbl->gpiod) == 0 && - gpiod_get_value_cansleep(gbl->gpiod) == 0) + else if (gpiod_get_value_cansleep(gbl->gpiod) == 0) bl->props.power = FB_BLANK_POWERDOWN; else bl->props.power = FB_BLANK_UNBLANK; From a7345501a3bd4589c94ad6734a6bab2de194a070 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 23 Jul 2023 22:30:18 -0700 Subject: [PATCH 1350/2093] Input: tca6416-keypad - always expect proper IRQ number in i2c client [ Upstream commit 687fe7dfb736b03ab820d172ea5dbfc1ec447135 ] Remove option having i2c client contain raw gpio number instead of proper IRQ number. There are no users of this facility in mainline and it will allow cleaning up the driver code with regard to wakeup handling, etc. Link: https://lore.kernel.org/r/20230724053024.352054-1-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov Stable-dep-of: cc141c35af87 ("Input: tca6416-keypad - fix interrupt enable disbalance") Signed-off-by: Sasha Levin --- drivers/input/keyboard/tca6416-keypad.c | 27 +++++++++---------------- include/linux/tca6416_keypad.h | 1 - 2 files changed, 10 insertions(+), 18 deletions(-) diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c index afcdfbb002ff..b48adec8fe2e 100644 --- a/drivers/input/keyboard/tca6416-keypad.c +++ b/drivers/input/keyboard/tca6416-keypad.c @@ -148,7 +148,7 @@ static int tca6416_keys_open(struct input_dev *dev) if (chip->use_polling) schedule_delayed_work(&chip->dwork, msecs_to_jiffies(100)); else - enable_irq(chip->irqnum); + enable_irq(chip->client->irq); return 0; } @@ -160,7 +160,7 @@ static void tca6416_keys_close(struct input_dev *dev) if (chip->use_polling) cancel_delayed_work_sync(&chip->dwork); else - disable_irq(chip->irqnum); + disable_irq(chip->client->irq); } static int tca6416_setup_registers(struct tca6416_keypad_chip *chip) @@ -266,12 +266,7 @@ static int tca6416_keypad_probe(struct i2c_client *client, goto fail1; if (!chip->use_polling) { - if (pdata->irq_is_gpio) - chip->irqnum = gpio_to_irq(client->irq); - else - chip->irqnum = client->irq; - - error = request_threaded_irq(chip->irqnum, NULL, + error = request_threaded_irq(client->irq, NULL, tca6416_keys_isr, IRQF_TRIGGER_FALLING | IRQF_ONESHOT | IRQF_NO_AUTOEN, @@ -279,7 +274,7 @@ static int tca6416_keypad_probe(struct i2c_client *client, if (error) { dev_dbg(&client->dev, "Unable to claim irq %d; error %d\n", - chip->irqnum, error); + client->irq, error); goto fail1; } } @@ -298,8 +293,8 @@ static int tca6416_keypad_probe(struct i2c_client *client, fail2: if (!chip->use_polling) { - free_irq(chip->irqnum, chip); - enable_irq(chip->irqnum); + free_irq(client->irq, chip); + enable_irq(client->irq); } fail1: input_free_device(input); @@ -312,8 +307,8 @@ static void tca6416_keypad_remove(struct i2c_client *client) struct tca6416_keypad_chip *chip = i2c_get_clientdata(client); if (!chip->use_polling) { - free_irq(chip->irqnum, chip); - enable_irq(chip->irqnum); + free_irq(client->irq, chip); + enable_irq(client->irq); } input_unregister_device(chip->input); @@ -324,10 +319,9 @@ static void tca6416_keypad_remove(struct i2c_client *client) static int tca6416_keypad_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); - struct tca6416_keypad_chip *chip = i2c_get_clientdata(client); if (device_may_wakeup(dev)) - enable_irq_wake(chip->irqnum); + enable_irq_wake(client->irq); return 0; } @@ -335,10 +329,9 @@ static int tca6416_keypad_suspend(struct device *dev) static int tca6416_keypad_resume(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); - struct tca6416_keypad_chip *chip = i2c_get_clientdata(client); if (device_may_wakeup(dev)) - disable_irq_wake(chip->irqnum); + disable_irq_wake(client->irq); return 0; } diff --git a/include/linux/tca6416_keypad.h b/include/linux/tca6416_keypad.h index b0d36a9934cc..5cf6f6f82aa7 100644 --- a/include/linux/tca6416_keypad.h +++ b/include/linux/tca6416_keypad.h @@ -25,7 +25,6 @@ struct tca6416_keys_platform_data { unsigned int rep:1; /* enable input subsystem auto repeat */ uint16_t pinmask; uint16_t invert; - int irq_is_gpio; int use_polling; /* use polling if Interrupt is not connected*/ }; #endif From e62e740009ccc753f8b7c3aa8a8873a443c05185 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sun, 23 Jul 2023 22:30:20 -0700 Subject: [PATCH 1351/2093] Input: tca6416-keypad - fix interrupt enable disbalance [ Upstream commit cc141c35af873c6796e043adcb820833bd8ef8c5 ] The driver has been switched to use IRQF_NO_AUTOEN, but in the error unwinding and remove paths calls to enable_irq() were left in place, which will lead to an incorrect enable counter value. Fixes: bcd9730a04a1 ("Input: move to use request_irq by IRQF_NO_AUTOEN flag") Link: https://lore.kernel.org/r/20230724053024.352054-3-dmitry.torokhov@gmail.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/keyboard/tca6416-keypad.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c index b48adec8fe2e..9c1489c0dae1 100644 --- a/drivers/input/keyboard/tca6416-keypad.c +++ b/drivers/input/keyboard/tca6416-keypad.c @@ -292,10 +292,8 @@ static int tca6416_keypad_probe(struct i2c_client *client, return 0; fail2: - if (!chip->use_polling) { + if (!chip->use_polling) free_irq(client->irq, chip); - enable_irq(client->irq); - } fail1: input_free_device(input); kfree(chip); @@ -306,10 +304,8 @@ static void tca6416_keypad_remove(struct i2c_client *client) { struct tca6416_keypad_chip *chip = i2c_get_clientdata(client); - if (!chip->use_polling) { + if (!chip->use_polling) free_irq(client->irq, chip); - enable_irq(client->irq); - } input_unregister_device(chip->input); kfree(chip); From 6522397e7502f92f48048bca61ac82f51970404b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 2 Aug 2023 18:22:14 -0300 Subject: [PATCH 1352/2093] perf annotate bpf: Don't enclose non-debug code with an assert() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 979e9c9fc9c2a761303585e07fe2699bdd88182f ] In 616b14b47a86d880 ("perf build: Conditionally define NDEBUG") we started using NDEBUG=1 when DEBUG=1 isn't present, so code that is enclosed with assert() is not called. In dd317df072071903 ("perf build: Make binutil libraries opt in") we stopped linking against binutils-devel, for licensing reasons. Recently people asked me why annotation of BPF programs wasn't working, i.e. this: $ perf annotate bpf_prog_5280546344e3f45c_kfree_skb was returning: case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF: scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation"); This was on a fedora rpm, so its new enough that I had to try to test by rebuilding using BUILD_NONDISTRO=1, only to get it segfaulting on me. This combination made this libopcode function not to be called: assert(bfd_check_format(bfdf, bfd_object)); Changing it to: if (!bfd_check_format(bfdf, bfd_object)) abort(); Made it work, looking at this "check" function made me realize it changes the 'bfdf' internal state, i.e. we better call it. So stop using assert() on it, just call it and abort if it fails. Probably it is better to propagate the error, etc, but it seems it is unlikely to fail from the usage done so far and we really need to stop using libopcodes, so do the quick fix above and move on. With it we have BPF annotation back working when built with BUILD_NONDISTRO=1: ⬢[acme@toolbox perf-tools-next]$ perf annotate --stdio2 bpf_prog_5280546344e3f45c_kfree_skb | head No kallsyms or vmlinux with build-id 939bc71a1a51cdc434e60af93c7e734f7d5c0e7e was found Samples: 12 of event 'cpu-clock:ppp', 4000 Hz, Event count (approx.): 3000000, [percent: local period] bpf_prog_5280546344e3f45c_kfree_skb() bpf_prog_5280546344e3f45c_kfree_skb Percent int kfree_skb(struct trace_event_raw_kfree_skb *args) { nop 33.33 xchg %ax,%ax push %rbp mov %rsp,%rbp sub $0x180,%rsp push %rbx push %r13 ⬢[acme@toolbox perf-tools-next]$ Fixes: 6987561c9e86eace ("perf annotate: Enable annotation of BPF programs") Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Mohamed Mahmoud Cc: Namhyung Kim Cc: Dave Tucker Cc: Derek Barbosa Cc: Song Liu Link: https://lore.kernel.org/lkml/ZMrMzoQBe0yqMek1@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/annotate.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index db475e44f42f..a9122ea3b44c 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1756,8 +1756,11 @@ static int symbol__disassemble_bpf(struct symbol *sym, perf_exe(tpath, sizeof(tpath)); bfdf = bfd_openr(tpath, NULL); - assert(bfdf); - assert(bfd_check_format(bfdf, bfd_object)); + if (bfdf == NULL) + abort(); + + if (!bfd_check_format(bfdf, bfd_object)) + abort(); s = open_memstream(&buf, &buf_size); if (!s) { @@ -1805,7 +1808,8 @@ static int symbol__disassemble_bpf(struct symbol *sym, #else disassemble = disassembler(bfdf); #endif - assert(disassemble); + if (disassemble == NULL) + abort(); fflush(s); do { From 6a43e0d623115949becf0bdcb22f8c097af855e9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 21 Jul 2023 13:18:52 -0700 Subject: [PATCH 1353/2093] x86/virt: Drop unnecessary check on extended CPUID level in cpu_has_svm() [ Upstream commit 5df8ecfe3632d5879d1f154f7aa8de441b5d1c89 ] Drop the explicit check on the extended CPUID level in cpu_has_svm(), the kernel's cached CPUID info will leave the entire SVM leaf unset if said leaf is not supported by hardware. Prior to using cached information, the check was needed to avoid false positives due to Intel's rather crazy CPUID behavior of returning the values of the maximum supported leaf if the specified leaf is unsupported. Fixes: 682a8108872f ("x86/kvm/svm: Simplify cpu_has_svm()") Link: https://lore.kernel.org/r/20230721201859.2307736-13-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Sasha Levin --- arch/x86/include/asm/virtext.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 3b12e6b99412..6c2e3ff3cb28 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -101,12 +101,6 @@ static inline int cpu_has_svm(const char **msg) return 0; } - if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) { - if (msg) - *msg = "can't execute cpuid_8000000a"; - return 0; - } - if (!boot_cpu_has(X86_FEATURE_SVM)) { if (msg) *msg = "svm not available"; From b7cbcafb6d04b95291d1b9e615879b5ae7c37ebf Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Mon, 14 Aug 2023 16:57:57 +0530 Subject: [PATCH 1354/2093] perf vendor events: Update the JSON/events descriptions for power10 platform [ Upstream commit 3286f88f31da060ac2789cee247153961ba57e49 ] Update the description for some of the JSON/events for power10 platform. Fixes: 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform") Signed-off-by: Kajol Jain Cc: Athira Rajeev Cc: Disha Goel Cc: Ian Rogers Cc: Kajol Jain Cc: Madhavan Srinivasan Cc: Namhyung Kim Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230814112803.1508296-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- .../arch/powerpc/power10/cache.json | 4 +- .../arch/powerpc/power10/frontend.json | 30 ++++++------ .../arch/powerpc/power10/marked.json | 20 ++++---- .../arch/powerpc/power10/memory.json | 6 +-- .../arch/powerpc/power10/others.json | 48 +++++++++---------- .../arch/powerpc/power10/pipeline.json | 20 ++++---- .../pmu-events/arch/powerpc/power10/pmc.json | 4 +- .../arch/powerpc/power10/translation.json | 6 +-- 8 files changed, 69 insertions(+), 69 deletions(-) diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json index 605be14f441c..9cb929bb64af 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json @@ -17,7 +17,7 @@ { "EventCode": "0x34056", "EventName": "PM_EXEC_STALL_LOAD_FINISH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction." }, { "EventCode": "0x3006C", @@ -27,7 +27,7 @@ { "EventCode": "0x300F4", "EventName": "PM_RUN_INST_CMPL_CONC", - "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set." + "BriefDescription": "PowerPC instruction completed by this thread when all threads in the core had the run-latch set." }, { "EventCode": "0x4C016", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json index 558f9530f54e..61e9e0222c87 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json @@ -7,7 +7,7 @@ { "EventCode": "0x10006", "EventName": "PM_DISP_STALL_HELD_OTHER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason." }, { "EventCode": "0x10010", @@ -32,12 +32,12 @@ { "EventCode": "0x1D05E", "EventName": "PM_DISP_STALL_HELD_HALT_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management." }, { "EventCode": "0x1E050", "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR." }, { "EventCode": "0x1F054", @@ -67,7 +67,7 @@ { "EventCode": "0x100F6", "EventName": "PM_IERAT_MISS", - "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event." + "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event. This event only counts instruction demand access." }, { "EventCode": "0x100F8", @@ -77,7 +77,7 @@ { "EventCode": "0x20006", "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue." }, { "EventCode": "0x20114", @@ -102,7 +102,7 @@ { "EventCode": "0x2D01A", "EventName": "PM_DISP_STALL_IC_MISS", - "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss." + "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss." }, { "EventCode": "0x2E018", @@ -112,7 +112,7 @@ { "EventCode": "0x2E01A", "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full." }, { "EventCode": "0x2C142", @@ -137,7 +137,7 @@ { "EventCode": "0x30004", "EventName": "PM_DISP_STALL_FLUSH", - "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." + "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC." }, { "EventCode": "0x3000A", @@ -157,7 +157,7 @@ { "EventCode": "0x30018", "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together." }, { "EventCode": "0x30026", @@ -182,7 +182,7 @@ { "EventCode": "0x3D05C", "EventName": "PM_DISP_STALL_HELD_RENAME_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC." }, { "EventCode": "0x3E052", @@ -192,7 +192,7 @@ { "EventCode": "0x3E054", "EventName": "PM_LD_MISS_L1", - "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." + "BriefDescription": "Load missed L1, counted at finish time. LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." }, { "EventCode": "0x301EA", @@ -202,7 +202,7 @@ { "EventCode": "0x300FA", "EventName": "PM_INST_FROM_L3MISS", - "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss." }, { "EventCode": "0x40006", @@ -232,16 +232,16 @@ { "EventCode": "0x4E01A", "EventName": "PM_DISP_STALL_HELD_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason." }, { "EventCode": "0x4003C", "EventName": "PM_DISP_STALL_HELD_SYNC_CYC", - "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." + "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch." }, { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL", - "BriefDescription": "Vector store instructions completed." + "BriefDescription": "Vector store instruction completed." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json index 58b5dfe3a273..131f8d0e8831 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json @@ -62,7 +62,7 @@ { "EventCode": "0x200FD", "EventName": "PM_L1_ICACHE_MISS", - "BriefDescription": "Demand iCache Miss." + "BriefDescription": "Demand instruction cache miss." }, { "EventCode": "0x30130", @@ -72,7 +72,7 @@ { "EventCode": "0x34146", "EventName": "PM_MRK_LD_CMPL", - "BriefDescription": "Marked loads completed." + "BriefDescription": "Marked load instruction completed." }, { "EventCode": "0x3E158", @@ -82,12 +82,12 @@ { "EventCode": "0x3E15A", "EventName": "PM_MRK_ST_FIN", - "BriefDescription": "The marked instruction was a store of any kind." + "BriefDescription": "Marked store instruction finished." }, { "EventCode": "0x30068", "EventName": "PM_L1_ICACHE_RELOADED_PREF", - "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)." + "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)." }, { "EventCode": "0x301E4", @@ -102,12 +102,12 @@ { "EventCode": "0x300FE", "EventName": "PM_DATA_FROM_L3MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss." }, { "EventCode": "0x40012", "EventName": "PM_L1_ICACHE_RELOADED_ALL", - "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." + "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, { "EventCode": "0x40134", @@ -117,22 +117,22 @@ { "EventCode": "0x4505A", "EventName": "PM_SP_FLOP_CMPL", - "BriefDescription": "Single Precision floating point instructions completed." + "BriefDescription": "Single Precision floating point instruction completed." }, { "EventCode": "0x4D058", "EventName": "PM_VECTOR_FLOP_CMPL", - "BriefDescription": "Vector floating point instructions completed." + "BriefDescription": "Vector floating point instruction completed." }, { "EventCode": "0x4D05A", "EventName": "PM_NON_MATH_FLOP_CMPL", - "BriefDescription": "Non Math instructions completed." + "BriefDescription": "Non Math instruction completed." }, { "EventCode": "0x401E0", "EventName": "PM_MRK_INST_CMPL", - "BriefDescription": "marked instruction completed." + "BriefDescription": "Marked instruction completed." }, { "EventCode": "0x400FE", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json index 843b51f531e9..c4c10ca98cad 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json @@ -47,7 +47,7 @@ { "EventCode": "0x10062", "EventName": "PM_LD_L3MISS_PEND_CYC", - "BriefDescription": "Cycles L3 miss was pending for this thread." + "BriefDescription": "Cycles in which an L3 miss was pending for this thread." }, { "EventCode": "0x20010", @@ -132,7 +132,7 @@ { "EventCode": "0x300FC", "EventName": "PM_DTLB_MISS", - "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity." + "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. This event only counts for demand misses." }, { "EventCode": "0x4D02C", @@ -142,7 +142,7 @@ { "EventCode": "0x4003E", "EventName": "PM_LD_CMPL", - "BriefDescription": "Loads completed." + "BriefDescription": "Load instruction completed." }, { "EventCode": "0x4C040", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index 7d0de1a2860b..e691041ee867 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -2,12 +2,12 @@ { "EventCode": "0x10016", "EventName": "PM_VSU0_ISSUE", - "BriefDescription": "VSU instructions issued to VSU pipe 0." + "BriefDescription": "VSU instruction issued to VSU pipe 0." }, { "EventCode": "0x1001C", "EventName": "PM_ULTRAVISOR_INST_CMPL", - "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state." + "BriefDescription": "PowerPC instruction completed while the thread was in ultravisor state." }, { "EventCode": "0x100F0", @@ -17,12 +17,12 @@ { "EventCode": "0x10134", "EventName": "PM_MRK_ST_DONE_L2", - "BriefDescription": "Marked stores completed in L2 (RC machine done)." + "BriefDescription": "Marked store completed in L2." }, { "EventCode": "0x1505E", "EventName": "PM_LD_HIT_L1", - "BriefDescription": "Loads that finished without experiencing an L1 miss." + "BriefDescription": "Load finished without experiencing an L1 miss." }, { "EventCode": "0x1F056", @@ -42,7 +42,7 @@ { "EventCode": "0x101E4", "EventName": "PM_MRK_L1_ICACHE_MISS", - "BriefDescription": "Marked Instruction suffered an icache Miss." + "BriefDescription": "Marked instruction suffered an instruction cache miss." }, { "EventCode": "0x101EA", @@ -72,7 +72,7 @@ { "EventCode": "0x2E010", "EventName": "PM_ADJUNCT_INST_CMPL", - "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state." + "BriefDescription": "PowerPC instruction completed while the thread was in Adjunct state." }, { "EventCode": "0x2E014", @@ -122,7 +122,7 @@ { "EventCode": "0x201E4", "EventName": "PM_MRK_DATA_FROM_L3MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load." + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." }, { "EventCode": "0x201E8", @@ -132,17 +132,17 @@ { "EventCode": "0x200F2", "EventName": "PM_INST_DISP", - "BriefDescription": "PowerPC instructions dispatched." + "BriefDescription": "PowerPC instruction dispatched." }, { "EventCode": "0x30132", "EventName": "PM_MRK_VSU_FIN", - "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit." + "BriefDescription": "VSU marked instruction finished. Excludes simple FX instructions issued to the Store Unit." }, { "EventCode": "0x30038", "EventName": "PM_EXEC_STALL_DMISS_LMEM", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCAPI cache, or local OpenCAPI memory." }, { "EventCode": "0x3F04A", @@ -152,12 +152,12 @@ { "EventCode": "0x3405A", "EventName": "PM_PRIVILEGED_INST_CMPL", - "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state." + "BriefDescription": "PowerPC instruction completed while the thread was in Privileged state." }, { "EventCode": "0x3F150", "EventName": "PM_MRK_ST_DRAIN_CYC", - "BriefDescription": "cycles to drain st from core to L2." + "BriefDescription": "Cycles in which the marked store drained from the core to the L2." }, { "EventCode": "0x3F054", @@ -182,7 +182,7 @@ { "EventCode": "0x4001C", "EventName": "PM_VSU_FIN", - "BriefDescription": "VSU instructions finished." + "BriefDescription": "VSU instruction finished." }, { "EventCode": "0x4C01A", @@ -197,7 +197,7 @@ { "EventCode": "0x4D022", "EventName": "PM_HYPERVISOR_INST_CMPL", - "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state." + "BriefDescription": "PowerPC instruction completed while the thread was in hypervisor state." }, { "EventCode": "0x4D026", @@ -212,32 +212,32 @@ { "EventCode": "0x40030", "EventName": "PM_INST_FIN", - "BriefDescription": "Instructions finished." + "BriefDescription": "Instruction finished." }, { "EventCode": "0x44146", "EventName": "PM_MRK_STCX_CORE_CYC", - "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." + "BriefDescription": "Cycles spent in the core portion of a marked STCX instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2." }, { "EventCode": "0x44054", "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instructions completed." + "BriefDescription": "Vector load instruction completed." }, { "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", - "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." + "BriefDescription": "Two floating point instruction completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only." }, { "EventCode": "0x45056", "EventName": "PM_SCALAR_FLOP_CMPL", - "BriefDescription": "Scalar floating point instructions completed." + "BriefDescription": "Scalar floating point instruction completed." }, { "EventCode": "0x4505C", "EventName": "PM_MATH_FLOP_CMPL", - "BriefDescription": "Math floating point instructions completed." + "BriefDescription": "Math floating point instruction completed." }, { "EventCode": "0x4D05E", @@ -252,21 +252,21 @@ { "EventCode": "0x401E6", "EventName": "PM_MRK_INST_FROM_L3MISS", - "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction." + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." }, { "EventCode": "0x401E8", "EventName": "PM_MRK_DATA_FROM_L2MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load." + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction." }, { "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", - "BriefDescription": "Load Missed L1, counted at finish time." + "BriefDescription": "Load missed L1, counted at finish time." }, { "EventCode": "0x400FA", "EventName": "PM_RUN_INST_CMPL", - "BriefDescription": "Completed PowerPC instructions gated by the run latch." + "BriefDescription": "PowerPC instruction completed while the run latch is set." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json index b8aded6045fa..449f57e8ba6a 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json @@ -2,7 +2,7 @@ { "EventCode": "0x100FE", "EventName": "PM_INST_CMPL", - "BriefDescription": "PowerPC instructions completed." + "BriefDescription": "PowerPC instruction completed." }, { "EventCode": "0x1000C", @@ -12,7 +12,7 @@ { "EventCode": "0x1000E", "EventName": "PM_MMA_ISSUED", - "BriefDescription": "MMA instructions issued." + "BriefDescription": "MMA instruction issued." }, { "EventCode": "0x10012", @@ -107,7 +107,7 @@ { "EventCode": "0x2D012", "EventName": "PM_VSU1_ISSUE", - "BriefDescription": "VSU instructions issued to VSU pipe 1." + "BriefDescription": "VSU instruction issued to VSU pipe 1." }, { "EventCode": "0x2D018", @@ -122,7 +122,7 @@ { "EventCode": "0x2E01E", "EventName": "PM_EXEC_STALL_NTC_FLUSH", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous next-to-finish (NTF) instruction is still completing and the new NTF instruction is stalled at dispatch." }, { "EventCode": "0x2013C", @@ -137,7 +137,7 @@ { "EventCode": "0x201E2", "EventName": "PM_MRK_LD_MISS_L1", - "BriefDescription": "Marked DL1 Demand Miss counted at finish time." + "BriefDescription": "Marked demand data load miss counted at finish time." }, { "EventCode": "0x200F4", @@ -172,7 +172,7 @@ { "EventCode": "0x30028", "EventName": "PM_CMPL_STALL_MEM_ECC", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a STCX waiting for its result or a load waiting for non-critical sectors of data and ECC." }, { "EventCode": "0x30036", @@ -187,12 +187,12 @@ { "EventCode": "0x3F044", "EventName": "PM_VSU2_ISSUE", - "BriefDescription": "VSU instructions issued to VSU pipe 2." + "BriefDescription": "VSU instruction issued to VSU pipe 2." }, { "EventCode": "0x30058", "EventName": "PM_TLBIE_FIN", - "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." + "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." }, { "EventCode": "0x3D058", @@ -252,7 +252,7 @@ { "EventCode": "0x4E012", "EventName": "PM_EXEC_STALL_UNKNOWN", - "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together." + "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the next-to-finish (NTF) instruction finishes and completions came too close together." }, { "EventCode": "0x4D020", @@ -267,7 +267,7 @@ { "EventCode": "0x45058", "EventName": "PM_IC_MISS_CMPL", - "BriefDescription": "Non-speculative icache miss, counted at completion." + "BriefDescription": "Non-speculative instruction cache miss, counted at completion." }, { "EventCode": "0x4D050", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json index b5d1bd39cfb2..364fedbfb490 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json @@ -12,11 +12,11 @@ { "EventCode": "0x45052", "EventName": "PM_4FLOP_CMPL", - "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." + "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)." }, { "EventCode": "0x4D054", "EventName": "PM_8FLOP_CMPL", - "BriefDescription": "Four Double Precision vector instructions completed." + "BriefDescription": "Four Double Precision vector instruction completed." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index db3766dca07c..3e47b804a0a8 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -17,7 +17,7 @@ { "EventCode": "0x2011C", "EventName": "PM_MRK_NTF_CYC", - "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)." + "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)." }, { "EventCode": "0x2E01C", @@ -37,7 +37,7 @@ { "EventCode": "0x200FE", "EventName": "PM_DATA_FROM_L2MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss." + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss." }, { "EventCode": "0x30010", @@ -52,6 +52,6 @@ { "EventCode": "0x4D05C", "EventName": "PM_DPP_FLOP_CMPL", - "BriefDescription": "Double-Precision or Quad-Precision instructions completed." + "BriefDescription": "Double-Precision or Quad-Precision instruction completed." } ] From 6ade9094b477e40ef3f7fb072b6fe6f766bc6636 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Mon, 14 Aug 2023 16:57:58 +0530 Subject: [PATCH 1355/2093] perf vendor events: Drop some of the JSON/events for power10 platform [ Upstream commit e104df97b8dcfbab2e42de634b99bf03f0805d85 ] Drop some of the JSON/events for power10 platform due to counter data mismatch. Fixes: 32daa5d7899e0343 ("perf vendor events: Initial JSON/events list for power10 platform") Signed-off-by: Kajol Jain Cc: Athira Rajeev Cc: Disha Goel Cc: Ian Rogers Cc: Kajol Jain Cc: Madhavan Srinivasan Cc: Namhyung Kim Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230814112803.1508296-2-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- .../arch/powerpc/power10/floating_point.json | 7 ------- tools/perf/pmu-events/arch/powerpc/power10/marked.json | 10 ---------- tools/perf/pmu-events/arch/powerpc/power10/others.json | 5 ----- .../perf/pmu-events/arch/powerpc/power10/pipeline.json | 10 ---------- .../pmu-events/arch/powerpc/power10/translation.json | 5 ----- 5 files changed, 37 deletions(-) delete mode 100644 tools/perf/pmu-events/arch/powerpc/power10/floating_point.json diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json deleted file mode 100644 index 54acb55e2c8c..000000000000 --- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json +++ /dev/null @@ -1,7 +0,0 @@ -[ - { - "EventCode": "0x4016E", - "EventName": "PM_THRESH_NOT_MET", - "BriefDescription": "Threshold counter did not meet threshold." - } -] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json index 131f8d0e8831..f2436fc5537c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json @@ -19,11 +19,6 @@ "EventName": "PM_MRK_BR_TAKEN_CMPL", "BriefDescription": "Marked Branch Taken instruction completed." }, - { - "EventCode": "0x20112", - "EventName": "PM_MRK_NTF_FIN", - "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch." - }, { "EventCode": "0x2C01C", "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP", @@ -64,11 +59,6 @@ "EventName": "PM_L1_ICACHE_MISS", "BriefDescription": "Demand instruction cache miss." }, - { - "EventCode": "0x30130", - "EventName": "PM_MRK_INST_FIN", - "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU." - }, { "EventCode": "0x34146", "EventName": "PM_MRK_LD_CMPL", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index e691041ee867..36c5bbc64c3b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -29,11 +29,6 @@ "EventName": "PM_DISP_SS0_2_INSTR_CYC", "BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions." }, - { - "EventCode": "0x1F15C", - "EventName": "PM_MRK_STCX_L2_CYC", - "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)." - }, { "EventCode": "0x10066", "EventName": "PM_ADJUNCT_CYC", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json index 449f57e8ba6a..799893c56f32 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json @@ -194,11 +194,6 @@ "EventName": "PM_TLBIE_FIN", "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted." }, - { - "EventCode": "0x3D058", - "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE", - "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)." - }, { "EventCode": "0x30066", "EventName": "PM_LSU_FIN", @@ -269,11 +264,6 @@ "EventName": "PM_IC_MISS_CMPL", "BriefDescription": "Non-speculative instruction cache miss, counted at completion." }, - { - "EventCode": "0x4D050", - "EventName": "PM_VSU_NON_FLOP_CMPL", - "BriefDescription": "Non-floating point VSU instructions completed." - }, { "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index 3e47b804a0a8..961e2491e73f 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -4,11 +4,6 @@ "EventName": "PM_MRK_START_PROBE_NOP_CMPL", "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed." }, - { - "EventCode": "0x20016", - "EventName": "PM_ST_FIN", - "BriefDescription": "Store finish count. Includes speculative activity." - }, { "EventCode": "0x20018", "EventName": "PM_ST_FWD", From adeb9f392d07f5dc0fa57aed661cb00f57cd93e2 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Mon, 14 Aug 2023 16:57:59 +0530 Subject: [PATCH 1356/2093] perf vendor events: Drop STORES_PER_INST metric event for power10 platform [ Upstream commit 4836b9a85ef148c7c9779b66fab3f7279e488d90 ] Drop STORES_PER_INST metric event for the power10 platform, as the metric expression of STORES_PER_INST metric event using dropped event PM_ST_FIN. Fixes: 3ca3af7d1f230d1f ("perf vendor events power10: Add metric events JSON file for power10 platform") Signed-off-by: Kajol Jain Cc: Athira Rajeev Cc: Disha Goel Cc: Ian Rogers Cc: Kajol Jain Cc: Madhavan Srinivasan Cc: Namhyung Kim Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230814112803.1508296-3-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/pmu-events/arch/powerpc/power10/metrics.json | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json index b57526fa44f2..6e76f65c314c 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json @@ -453,12 +453,6 @@ "MetricGroup": "General", "MetricName": "LOADS_PER_INST" }, - { - "BriefDescription": "Average number of finished stores per completed instruction", - "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL", - "MetricGroup": "General", - "MetricName": "STORES_PER_INST" - }, { "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction", "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", From 032cd8ce89a450bf4a11dc3ffaae7668aebf17d9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 17 Aug 2023 09:11:21 -0300 Subject: [PATCH 1357/2093] perf top: Don't pass an ERR_PTR() directly to perf_session__delete() [ Upstream commit ef23cb593304bde0cc046fd4cc83ae7ea2e24f16 ] While debugging a segfault on 'perf lock contention' without an available perf.data file I noticed that it was basically calling: perf_session__delete(ERR_PTR(-1)) Resulting in: (gdb) run lock contention Starting program: /root/bin/perf lock contention [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib64/libthread_db.so.1". failed to open perf.data: No such file or directory (try 'perf record' first) Initializing perf session failed Program received signal SIGSEGV, Segmentation fault. 0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858 2858 if (!session->auxtrace) (gdb) p session $1 = (struct perf_session *) 0xffffffffffffffff (gdb) bt #0 0x00000000005e7515 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2858 #1 0x000000000057bb4d in perf_session__delete (session=0xffffffffffffffff) at util/session.c:300 #2 0x000000000047c421 in __cmd_contention (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2161 #3 0x000000000047dc95 in cmd_lock (argc=0, argv=0x7fffffffe200) at builtin-lock.c:2604 #4 0x0000000000501466 in run_builtin (p=0xe597a8 , argc=2, argv=0x7fffffffe200) at perf.c:322 #5 0x00000000005016d5 in handle_internal_command (argc=2, argv=0x7fffffffe200) at perf.c:375 #6 0x0000000000501824 in run_argv (argcp=0x7fffffffe02c, argv=0x7fffffffe020) at perf.c:419 #7 0x0000000000501b11 in main (argc=2, argv=0x7fffffffe200) at perf.c:535 (gdb) So just set it to NULL after using PTR_ERR(session) to decode the error as perf_session__delete(NULL) is supported. The same problem was found in 'perf top' after an audit of all perf_session__new() failure handling. Fixes: 6ef81c55a2b6584c ("perf session: Return error code for perf_session__new() function on failure") Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Greg Kroah-Hartman Cc: Jeremie Galarneau Cc: Jiri Olsa Cc: Kate Stewart Cc: Mamatha Inamdar Cc: Mukesh Ojha Cc: Nageswara R Sastry Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Shawn Landden Cc: Song Liu Cc: Thomas Gleixner Cc: Tzvetomir Stoyanov Link: https://lore.kernel.org/lkml/ZN4Q2rxxsL08A8rd@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-top.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 4b3ff7687236..f9917848cdad 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1751,6 +1751,7 @@ int cmd_top(int argc, const char **argv) top.session = perf_session__new(NULL, NULL); if (IS_ERR(top.session)) { status = PTR_ERR(top.session); + top.session = NULL; goto out_delete_evlist; } From fa5392873639ecfdd0cd737e021c4784e952b1eb Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Fri, 11 Aug 2023 17:32:20 +0530 Subject: [PATCH 1358/2093] watchdog: intel-mid_wdt: add MODULE_ALIAS() to allow auto-load [ Upstream commit cf38e7691c85f1b09973b22a0b89bf1e1228d2f9 ] When built with CONFIG_INTEL_MID_WATCHDOG=m, currently the driver needs to be loaded manually, for the lack of module alias. This causes unintended resets in cases where watchdog timer is set-up by bootloader and the driver is not explicitly loaded. Add MODULE_ALIAS() to load the driver automatically at boot and avoid this issue. Fixes: 87a1ef8058d9 ("watchdog: add Intel MID watchdog driver support") Signed-off-by: Raag Jadav Reviewed-by: Andy Shevchenko Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230811120220.31578-1-raag.jadav@intel.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/intel-mid_wdt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c index 9b2173f765c8..fb7fae750181 100644 --- a/drivers/watchdog/intel-mid_wdt.c +++ b/drivers/watchdog/intel-mid_wdt.c @@ -203,3 +203,4 @@ module_platform_driver(mid_wdt_driver); MODULE_AUTHOR("David Cohen "); MODULE_DESCRIPTION("Watchdog Driver for Intel MID platform"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:intel_mid_wdt"); From 523f6268e86552a048975749251184c4e9a4b38f Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Mon, 17 Jul 2023 17:52:57 +0200 Subject: [PATCH 1359/2093] pwm: lpc32xx: Remove handling of PWM channels MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4aae44f65827f0213a7361cf9c32cfe06114473f ] Because LPC32xx PWM controllers have only a single output which is registered as the only PWM device/channel per controller, it is known in advance that pwm->hwpwm value is always 0. On basis of this fact simplify the code by removing operations with pwm->hwpwm, there is no controls which require channel number as input. Even though I wasn't aware at the time when I forward ported that patch, this fixes a null pointer dereference as lpc32xx->chip.pwms is NULL before devm_pwmchip_add() is called. Reported-by: Dan Carpenter Signed-off-by: Vladimir Zapolskiy Signed-off-by: Uwe Kleine-König Fixes: 3d2813fb17e5 ("pwm: lpc32xx: Don't modify HW state in .probe() after the PWM chip was registered") Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-lpc32xx.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c index 86a0ea0f6955..806f0bb3ad6d 100644 --- a/drivers/pwm/pwm-lpc32xx.c +++ b/drivers/pwm/pwm-lpc32xx.c @@ -51,10 +51,10 @@ static int lpc32xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, if (duty_cycles > 255) duty_cycles = 255; - val = readl(lpc32xx->base + (pwm->hwpwm << 2)); + val = readl(lpc32xx->base); val &= ~0xFFFF; val |= (period_cycles << 8) | duty_cycles; - writel(val, lpc32xx->base + (pwm->hwpwm << 2)); + writel(val, lpc32xx->base); return 0; } @@ -69,9 +69,9 @@ static int lpc32xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) if (ret) return ret; - val = readl(lpc32xx->base + (pwm->hwpwm << 2)); + val = readl(lpc32xx->base); val |= PWM_ENABLE; - writel(val, lpc32xx->base + (pwm->hwpwm << 2)); + writel(val, lpc32xx->base); return 0; } @@ -81,9 +81,9 @@ static void lpc32xx_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) struct lpc32xx_pwm_chip *lpc32xx = to_lpc32xx_pwm_chip(chip); u32 val; - val = readl(lpc32xx->base + (pwm->hwpwm << 2)); + val = readl(lpc32xx->base); val &= ~PWM_ENABLE; - writel(val, lpc32xx->base + (pwm->hwpwm << 2)); + writel(val, lpc32xx->base); clk_disable_unprepare(lpc32xx->clk); } @@ -141,9 +141,9 @@ static int lpc32xx_pwm_probe(struct platform_device *pdev) lpc32xx->chip.npwm = 1; /* If PWM is disabled, configure the output to the default value */ - val = readl(lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2)); + val = readl(lpc32xx->base); val &= ~PWM_PIN_LEVEL; - writel(val, lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2)); + writel(val, lpc32xx->base); ret = devm_pwmchip_add(&pdev->dev, &lpc32xx->chip); if (ret < 0) { From 66b23e7b0822e48b2ff5a099491f59557fb8bdd1 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sun, 9 Jul 2023 23:57:39 +0530 Subject: [PATCH 1360/2093] perf test stat_bpf_counters_cgrp: Fix shellcheck issue about logical operators [ Upstream commit 0dd1f815545d7210150642741c364521cc5cf116 ] Running shellcheck on lock_contention.sh generates below warning: In stat_bpf_counters_cgrp.sh line 28: if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then ^-- SC2166 (warning): Prefer [ p ] && [ q ] as [ p -a q ] is not well defined. In stat_bpf_counters_cgrp.sh line 34: local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) ^-------------^ SC3043 (warning): In POSIX sh, 'local' is undefined. ^-------^ SC2155 (warning): Declare and assign separately to avoid masking return values. ^-- SC2046 (warning): Quote this to prevent word splitting. In stat_bpf_counters_cgrp.sh line 51: local output ^----------^ SC3043 (warning): In POSIX sh, 'local' is undefined. In stat_bpf_counters_cgrp.sh line 65: local output ^----------^ SC3043 (warning): In POSIX sh, 'local' is undefined. Fixed above warnings by: - Changing the expression [p -a q] to [p] && [q]. - Fixing shellcheck warnings for local usage, by prefixing function name to the variable. Signed-off-by: Kajol Jain Acked-by: Ian Rogers Cc: Disha Goel Cc: Jiri Olsa Cc: Madhavan Srinivasan Cc: Namhyung Kim Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230709182800.53002-6-atrajeev@linux.vnet.ibm.com Signed-off-by: Athira Rajeev Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: a84260e31402 ("perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test") Signed-off-by: Sasha Levin --- .../tests/shell/stat_bpf_counters_cgrp.sh | 28 ++++++++----------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh index d724855d097c..a74440a00b6b 100755 --- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh +++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh @@ -25,22 +25,22 @@ check_bpf_counter() find_cgroups() { # try usual systemd slices first - if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then + if [ -d /sys/fs/cgroup/system.slice ] && [ -d /sys/fs/cgroup/user.slice ]; then test_cgroups="system.slice,user.slice" return fi # try root and self cgroups - local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) - if [ -z ${self_cgrp} ]; then + find_cgroups_self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) + if [ -z ${find_cgroups_self_cgrp} ]; then # cgroup v2 doesn't specify perf_event - self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3) + find_cgroups_self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3) fi - if [ -z ${self_cgrp} ]; then + if [ -z ${find_cgroups_self_cgrp} ]; then test_cgroups="/" else - test_cgroups="/,${self_cgrp}" + test_cgroups="/,${find_cgroups_self_cgrp}" fi } @@ -48,13 +48,11 @@ find_cgroups() # Just check if it runs without failure and has non-zero results. check_system_wide_counted() { - local output - - output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1) - if echo ${output} | grep -q -F "&1) + if echo ${check_system_wide_counted_output} | grep -q -F "&1) - if echo ${output} | grep -q -F "&1) + if echo ${check_cpu_list_counted_output} | grep -q -F " Date: Fri, 25 Aug 2023 09:41:52 -0700 Subject: [PATCH 1361/2093] perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test [ Upstream commit a84260e314029e6dc9904fd6eabf8d9fd7965351 ] It has system-wide test and cpu-list test but the cpu-list test fails sometimes. It runs sleep command on CPU1 and measure both user.slice and system.slice cgroups by default (on systemd-based systems). But if the system was idle enough, sometime the system.slice gets no count and it makes the test failing. Maybe that's because it only looks at the CPU1, let's add CPU0 to increase the chance it finds some tasks. Fixes: 7901086014bbaa3a ("perf test: Add a new test for perf stat cgroup BPF counter") Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230825164152.165610-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/tests/shell/stat_bpf_counters_cgrp.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh index a74440a00b6b..e75d0780dc78 100755 --- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh +++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh @@ -60,7 +60,7 @@ check_system_wide_counted() check_cpu_list_counted() { - check_cpu_list_counted_output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1) + check_cpu_list_counted_output=$(perf stat -C 0,1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1) if echo ${check_cpu_list_counted_output} | grep -q -F " Date: Mon, 21 Aug 2023 17:30:35 +0200 Subject: [PATCH 1362/2093] drm/i915: mark requests for GuC virtual engines to avoid use-after-free [ Upstream commit 5eefc5307c983b59344a4cb89009819f580c84fa ] References to i915_requests may be trapped by userspace inside a sync_file or dmabuf (dma-resv) and held indefinitely across different proceses. To counter-act the memory leaks, we try to not to keep references from the request past their completion. On the other side on fence release we need to know if rq->engine is valid and points to hw engine (true for non-virtual requests). To make it possible extra bit has been added to rq->execution_mask, for marking virtual engines. Fixes: bcb9aa45d5a0 ("Revert "drm/i915: Hold reference to intel_context over life of i915_request"") Signed-off-by: Chris Wilson Signed-off-by: Andrzej Hajda Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20230821153035.3903006-1-andrzej.hajda@intel.com (cherry picked from commit 280410677af763f3871b93e794a199cfcf6fb580) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/intel_engine_types.h | 1 + drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 3 +++ drivers/gpu/drm/i915/i915_request.c | 7 ++----- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 6b5d4ea22b67..107f465a27b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -56,6 +56,7 @@ struct intel_breadcrumbs; typedef u32 intel_engine_mask_t; #define ALL_ENGINES ((intel_engine_mask_t)~0ul) +#define VIRTUAL_ENGINES BIT(BITS_PER_TYPE(intel_engine_mask_t) - 1) struct intel_hw_status_page { struct list_head timelines; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 0ec07dad1dcf..fecdc7ea78eb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -5111,6 +5111,9 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, ve->base.flags = I915_ENGINE_IS_VIRTUAL; + BUILD_BUG_ON(ilog2(VIRTUAL_ENGINES) < I915_NUM_ENGINES); + ve->base.mask = VIRTUAL_ENGINES; + intel_context_init(&ve->context, &ve->base); for (n = 0; n < count; n++) { diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 803cd2ad4deb..7ce126a01cbf 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -134,9 +134,7 @@ static void i915_fence_release(struct dma_fence *fence) i915_sw_fence_fini(&rq->semaphore); /* - * Keep one request on each engine for reserved use under mempressure - * do not use with virtual engines as this really is only needed for - * kernel contexts. + * Keep one request on each engine for reserved use under mempressure. * * We do not hold a reference to the engine here and so have to be * very careful in what rq->engine we poke. The virtual engine is @@ -166,8 +164,7 @@ static void i915_fence_release(struct dma_fence *fence) * know that if the rq->execution_mask is a single bit, rq->engine * can be a physical engine with the exact corresponding mask. */ - if (!intel_engine_is_virtual(rq->engine) && - is_power_of_2(rq->execution_mask) && + if (is_power_of_2(rq->execution_mask) && !cmpxchg(&rq->engine->request_pool, NULL, rq)) return; From fd2420905c8ede1967bca335adde6af4a8d4a49e Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Wed, 16 Aug 2023 09:27:07 +0800 Subject: [PATCH 1363/2093] blk-throttle: use calculate_io/bytes_allowed() for throtl_trim_slice() [ Upstream commit e8368b57c006dc0e02dcd8a9dc9f2060ff5476fe ] There are no functional changes, just make the code cleaner. Signed-off-by: Yu Kuai Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230816012708.1193747-4-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Stable-dep-of: eead0056648c ("blk-throttle: consider 'carryover_ios/bytes' in throtl_trim_slice()") Signed-off-by: Sasha Levin --- block/blk-throttle.c | 116 +++++++++++++++++++++---------------------- 1 file changed, 56 insertions(+), 60 deletions(-) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index f1bc600c4ded..931795da4d65 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -697,66 +697,6 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw) return true; } -/* Trim the used slices and adjust slice start accordingly */ -static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) -{ - unsigned long nr_slices, time_elapsed, io_trim; - u64 bytes_trim, tmp; - - BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); - - /* - * If bps are unlimited (-1), then time slice don't get - * renewed. Don't try to trim the slice if slice is used. A new - * slice will start when appropriate. - */ - if (throtl_slice_used(tg, rw)) - return; - - /* - * A bio has been dispatched. Also adjust slice_end. It might happen - * that initially cgroup limit was very low resulting in high - * slice_end, but later limit was bumped up and bio was dispatched - * sooner, then we need to reduce slice_end. A high bogus slice_end - * is bad because it does not allow new slice to start. - */ - - throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice); - - time_elapsed = jiffies - tg->slice_start[rw]; - - nr_slices = time_elapsed / tg->td->throtl_slice; - - if (!nr_slices) - return; - tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices; - do_div(tmp, HZ); - bytes_trim = tmp; - - io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) / - HZ; - - if (!bytes_trim && !io_trim) - return; - - if (tg->bytes_disp[rw] >= bytes_trim) - tg->bytes_disp[rw] -= bytes_trim; - else - tg->bytes_disp[rw] = 0; - - if (tg->io_disp[rw] >= io_trim) - tg->io_disp[rw] -= io_trim; - else - tg->io_disp[rw] = 0; - - tg->slice_start[rw] += nr_slices * tg->td->throtl_slice; - - throtl_log(&tg->service_queue, - "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu", - rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim, - tg->slice_start[rw], tg->slice_end[rw], jiffies); -} - static unsigned int calculate_io_allowed(u32 iops_limit, unsigned long jiffy_elapsed) { @@ -786,6 +726,62 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ); } +/* Trim the used slices and adjust slice start accordingly */ +static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) +{ + unsigned long time_elapsed, io_trim; + u64 bytes_trim; + + BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); + + /* + * If bps are unlimited (-1), then time slice don't get + * renewed. Don't try to trim the slice if slice is used. A new + * slice will start when appropriate. + */ + if (throtl_slice_used(tg, rw)) + return; + + /* + * A bio has been dispatched. Also adjust slice_end. It might happen + * that initially cgroup limit was very low resulting in high + * slice_end, but later limit was bumped up and bio was dispatched + * sooner, then we need to reduce slice_end. A high bogus slice_end + * is bad because it does not allow new slice to start. + */ + + throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice); + + time_elapsed = rounddown(jiffies - tg->slice_start[rw], + tg->td->throtl_slice); + if (!time_elapsed) + return; + + bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), + time_elapsed); + io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed); + if (!bytes_trim && !io_trim) + return; + + if (tg->bytes_disp[rw] >= bytes_trim) + tg->bytes_disp[rw] -= bytes_trim; + else + tg->bytes_disp[rw] = 0; + + if (tg->io_disp[rw] >= io_trim) + tg->io_disp[rw] -= io_trim; + else + tg->io_disp[rw] = 0; + + tg->slice_start[rw] += time_elapsed; + + throtl_log(&tg->service_queue, + "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice, + bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw], + jiffies); +} + static void __tg_update_carryover(struct throtl_grp *tg, bool rw) { unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw]; From 84d577923450827997ef19015591bc1bfd0aef0f Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Wed, 16 Aug 2023 09:27:08 +0800 Subject: [PATCH 1364/2093] blk-throttle: consider 'carryover_ios/bytes' in throtl_trim_slice() [ Upstream commit eead0056648cef49d7b15c07ae612fa217083165 ] Currently, 'carryover_ios/bytes' is not handled in throtl_trim_slice(), for consequence, 'carryover_ios/bytes' will be used to throttle bio multiple times, for example: 1) set iops limit to 100, and slice start is 0, slice end is 100ms; 2) current time is 0, and 10 ios are dispatched, those io won't be throttled and io_disp is 10; 3) still at current time 0, update iops limit to 1000, carryover_ios is updated to (0 - 10) = -10; 4) in this slice(0 - 100ms), io_allowed = 100 + (-10) = 90, which means only 90 ios can be dispatched without waiting; 5) assume that io is throttled in slice(0 - 100ms), and throtl_trim_slice() update silce to (100ms - 200ms). In this case, 'carryover_ios/bytes' is not cleared and still only 90 ios can be dispatched between 100ms - 200ms. Fix this problem by updating 'carryover_ios/bytes' in throtl_trim_slice(). Fixes: a880ae93e5b5 ("blk-throttle: fix io hung due to configuration updates") Reported-by: zhuxiaohui Link: https://lore.kernel.org/all/20230812072116.42321-1-zhuxiaohui.400@bytedance.com/ Signed-off-by: Yu Kuai Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230816012708.1193747-5-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-throttle.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 931795da4d65..1007f8027857 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -729,8 +729,9 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) /* Trim the used slices and adjust slice start accordingly */ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) { - unsigned long time_elapsed, io_trim; - u64 bytes_trim; + unsigned long time_elapsed; + long long bytes_trim; + int io_trim; BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); @@ -758,17 +759,21 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) return; bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), - time_elapsed); - io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed); - if (!bytes_trim && !io_trim) + time_elapsed) + + tg->carryover_bytes[rw]; + io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) + + tg->carryover_ios[rw]; + if (bytes_trim <= 0 && io_trim <= 0) return; - if (tg->bytes_disp[rw] >= bytes_trim) + tg->carryover_bytes[rw] = 0; + if ((long long)tg->bytes_disp[rw] >= bytes_trim) tg->bytes_disp[rw] -= bytes_trim; else tg->bytes_disp[rw] = 0; - if (tg->io_disp[rw] >= io_trim) + tg->carryover_ios[rw] = 0; + if ((int)tg->io_disp[rw] >= io_trim) tg->io_disp[rw] -= io_trim; else tg->io_disp[rw] = 0; @@ -776,7 +781,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) tg->slice_start[rw] += time_elapsed; throtl_log(&tg->service_queue, - "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu", + "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice, bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw], jiffies); From 60e3318e3e900ba1ddfead937012b3432dfccc92 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 4 Oct 2022 18:41:20 -0300 Subject: [PATCH 1365/2093] cifs: use fs_context for automounts [ Upstream commit 9fd29a5bae6e8f94b410374099a6fddb253d2d5f ] Use filesystem context support to handle dfs links. Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Stable-dep-of: efc0b0bcffcb ("smb: propagate error code of extract_sharename()") Signed-off-by: Sasha Levin --- fs/smb/client/cifs_dfs_ref.c | 100 ++++++++++++++--------------------- 1 file changed, 40 insertions(+), 60 deletions(-) diff --git a/fs/smb/client/cifs_dfs_ref.c b/fs/smb/client/cifs_dfs_ref.c index b0864da9ef43..020e71fe1454 100644 --- a/fs/smb/client/cifs_dfs_ref.c +++ b/fs/smb/client/cifs_dfs_ref.c @@ -258,61 +258,23 @@ char *cifs_compose_mount_options(const char *sb_mountdata, goto compose_mount_options_out; } -/** - * cifs_dfs_do_mount - mounts specified path using DFS full path - * - * Always pass down @fullpath to smb3_do_mount() so we can use the root server - * to perform failover in case we failed to connect to the first target in the - * referral. - * - * @mntpt: directory entry for the path we are trying to automount - * @cifs_sb: parent/root superblock - * @fullpath: full path in UNC format - */ -static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt, - struct cifs_sb_info *cifs_sb, - const char *fullpath) -{ - struct vfsmount *mnt; - char *mountdata; - char *devname; - - devname = kstrdup(fullpath, GFP_KERNEL); - if (!devname) - return ERR_PTR(-ENOMEM); - - convert_delimiter(devname, '/'); - - /* TODO: change to call fs_context_for_mount(), fill in context directly, call fc_mount */ - - /* See afs_mntpt_do_automount in fs/afs/mntpt.c for an example */ - - /* strip first '\' from fullpath */ - mountdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - fullpath + 1, NULL, NULL); - if (IS_ERR(mountdata)) { - kfree(devname); - return (struct vfsmount *)mountdata; - } - - mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata); - kfree(mountdata); - kfree(devname); - return mnt; -} - /* * Create a vfsmount that we can automount */ -static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) +static struct vfsmount *cifs_dfs_do_automount(struct path *path) { + int rc; + struct dentry *mntpt = path->dentry; + struct fs_context *fc; struct cifs_sb_info *cifs_sb; - void *page; + void *page = NULL; + struct smb3_fs_context *ctx, *cur_ctx; + struct smb3_fs_context tmp; char *full_path; struct vfsmount *mnt; - cifs_dbg(FYI, "in %s\n", __func__); - BUG_ON(IS_ROOT(mntpt)); + if (IS_ROOT(mntpt)) + return ERR_PTR(-ESTALE); /* * The MSDFS spec states that paths in DFS referral requests and @@ -321,29 +283,47 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) * gives us the latter, so we must adjust the result. */ cifs_sb = CIFS_SB(mntpt->d_sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) { - mnt = ERR_PTR(-EREMOTE); - goto cdda_exit; - } + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) + return ERR_PTR(-EREMOTE); + + cur_ctx = cifs_sb->ctx; + + fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, mntpt); + if (IS_ERR(fc)) + return ERR_CAST(fc); + + ctx = smb3_fc2context(fc); page = alloc_dentry_path(); /* always use tree name prefix */ full_path = build_path_from_dentry_optional_prefix(mntpt, page, true); if (IS_ERR(full_path)) { mnt = ERR_CAST(full_path); - goto free_full_path; + goto out; } - convert_delimiter(full_path, '\\'); + convert_delimiter(full_path, '/'); cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); - mnt = cifs_dfs_do_mount(mntpt, cifs_sb, full_path); - cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__, full_path + 1, mnt); + tmp = *cur_ctx; + tmp.source = full_path; + tmp.UNC = tmp.prepath = NULL; -free_full_path: + rc = smb3_fs_context_dup(ctx, &tmp); + if (rc) { + mnt = ERR_PTR(rc); + goto out; + } + + rc = smb3_parse_devname(full_path, ctx); + if (!rc) + mnt = fc_mount(fc); + else + mnt = ERR_PTR(rc); + +out: + put_fs_context(fc); free_dentry_path(page); -cdda_exit: - cifs_dbg(FYI, "leaving %s\n" , __func__); return mnt; } @@ -354,9 +334,9 @@ struct vfsmount *cifs_dfs_d_automount(struct path *path) { struct vfsmount *newmnt; - cifs_dbg(FYI, "in %s\n", __func__); + cifs_dbg(FYI, "%s: %pd\n", __func__, path->dentry); - newmnt = cifs_dfs_do_automount(path->dentry); + newmnt = cifs_dfs_do_automount(path); if (IS_ERR(newmnt)) { cifs_dbg(FYI, "leaving %s [automount failed]\n" , __func__); return newmnt; From 47f72ee50226ec0da35a608ae781db16a7cbdb31 Mon Sep 17 00:00:00 2001 From: Katya Orlova Date: Tue, 15 Aug 2023 16:38:31 +0300 Subject: [PATCH 1366/2093] smb: propagate error code of extract_sharename() [ Upstream commit efc0b0bcffcba60d9c6301063d25a22a4744b499 ] In addition to the EINVAL, there may be an ENOMEM. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 70431bfd825d ("cifs: Support fscache indexing rewrite") Signed-off-by: Katya Orlova Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/fscache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index f6f3a6b75601..e73625b5d0cc 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -48,7 +48,7 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) sharename = extract_sharename(tcon->tree_name); if (IS_ERR(sharename)) { cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__); - return -EINVAL; + return PTR_ERR(sharename); } slen = strlen(sharename); From f39b49077abec4c9c3a4c2966532004851c51006 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Aug 2023 12:35:41 +0000 Subject: [PATCH 1367/2093] net/sched: fq_pie: avoid stalls in fq_pie_timer() [ Upstream commit 8c21ab1bae945686c602c5bfa4e3f3352c2452c5 ] When setting a high number of flows (limit being 65536), fq_pie_timer() is currently using too much time as syzbot reported. Add logic to yield the cpu every 2048 flows (less than 150 usec on debug kernels). It should also help by not blocking qdisc fast paths for too long. Worst case (65536 flows) would need 31 jiffies for a complete scan. Relevant extract from syzbot report: rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { 0-.... } 2663 jiffies s: 873 root: 0x1/. rcu: blocking rcu_node structures (internal RCU debug): Sending NMI from CPU 1 to CPUs 0: NMI backtrace for cpu 0 CPU: 0 PID: 5177 Comm: syz-executor273 Not tainted 6.5.0-syzkaller-00453-g727dbda16b83 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 RIP: 0010:check_kcov_mode kernel/kcov.c:173 [inline] RIP: 0010:write_comp_data+0x21/0x90 kernel/kcov.c:236 Code: 2e 0f 1f 84 00 00 00 00 00 65 8b 05 01 b2 7d 7e 49 89 f1 89 c6 49 89 d2 81 e6 00 01 00 00 49 89 f8 65 48 8b 14 25 80 b9 03 00 00 01 ff 00 74 0e 85 f6 74 59 8b 82 04 16 00 00 85 c0 74 4f 8b RSP: 0018:ffffc90000007bb8 EFLAGS: 00000206 RAX: 0000000000000101 RBX: ffffc9000dc0d140 RCX: ffffffff885893b0 RDX: ffff88807c075940 RSI: 0000000000000100 RDI: 0000000000000001 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffc9000dc0d178 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000555555d54380(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f6b442f6130 CR3: 000000006fe1c000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: pie_calculate_probability+0x480/0x850 net/sched/sch_pie.c:415 fq_pie_timer+0x1da/0x4f0 net/sched/sch_fq_pie.c:387 call_timer_fn+0x1a0/0x580 kernel/time/timer.c:1700 Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Link: https://lore.kernel.org/lkml/00000000000017ad3f06040bf394@google.com/ Reported-by: syzbot+e46fbd5289363464bc13@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet Reviewed-by: Michal Kubiak Reviewed-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230829123541.3745013-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_fq_pie.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 591d87d5e5c0..68e6acd0f130 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -61,6 +61,7 @@ struct fq_pie_sched_data { struct pie_params p_params; u32 ecn_prob; u32 flows_cnt; + u32 flows_cursor; u32 quantum; u32 memory_limit; u32 new_flow_count; @@ -375,22 +376,32 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, static void fq_pie_timer(struct timer_list *t) { struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer); + unsigned long next, tupdate; struct Qdisc *sch = q->sch; spinlock_t *root_lock; /* to lock qdisc for probability calculations */ - u32 idx; + int max_cnt, i; rcu_read_lock(); root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - for (idx = 0; idx < q->flows_cnt; idx++) - pie_calculate_probability(&q->p_params, &q->flows[idx].vars, - q->flows[idx].backlog); - - /* reset the timer to fire after 'tupdate' jiffies. */ - if (q->p_params.tupdate) - mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate); + /* Limit this expensive loop to 2048 flows per round. */ + max_cnt = min_t(int, q->flows_cnt - q->flows_cursor, 2048); + for (i = 0; i < max_cnt; i++) { + pie_calculate_probability(&q->p_params, + &q->flows[q->flows_cursor].vars, + q->flows[q->flows_cursor].backlog); + q->flows_cursor++; + } + tupdate = q->p_params.tupdate; + next = 0; + if (q->flows_cursor >= q->flows_cnt) { + q->flows_cursor = 0; + next = tupdate; + } + if (tupdate) + mod_timer(&q->adapt_timer, jiffies + next); spin_unlock(root_lock); rcu_read_unlock(); } From 471f534971d90c31975c46bb20550e5b95d055b0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Aug 2023 09:45:19 +0000 Subject: [PATCH 1368/2093] sctp: annotate data-races around sk->sk_wmem_queued [ Upstream commit dc9511dd6f37fe803f6b15b61b030728d7057417 ] sk->sk_wmem_queued can be read locklessly from sctp_poll() Use sk_wmem_queued_add() when the field is changed, and add READ_ONCE() annotations in sctp_writeable() and sctp_assocs_seq_show() syzbot reported: BUG: KCSAN: data-race in sctp_poll / sctp_wfree read-write to 0xffff888149d77810 of 4 bytes by interrupt on cpu 0: sctp_wfree+0x170/0x4a0 net/sctp/socket.c:9147 skb_release_head_state+0xb7/0x1a0 net/core/skbuff.c:988 skb_release_all net/core/skbuff.c:1000 [inline] __kfree_skb+0x16/0x140 net/core/skbuff.c:1016 consume_skb+0x57/0x180 net/core/skbuff.c:1232 sctp_chunk_destroy net/sctp/sm_make_chunk.c:1503 [inline] sctp_chunk_put+0xcd/0x130 net/sctp/sm_make_chunk.c:1530 sctp_datamsg_put+0x29a/0x300 net/sctp/chunk.c:128 sctp_chunk_free+0x34/0x50 net/sctp/sm_make_chunk.c:1515 sctp_outq_sack+0xafa/0xd70 net/sctp/outqueue.c:1381 sctp_cmd_process_sack net/sctp/sm_sideeffect.c:834 [inline] sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1366 [inline] sctp_side_effects net/sctp/sm_sideeffect.c:1198 [inline] sctp_do_sm+0x12c7/0x31b0 net/sctp/sm_sideeffect.c:1169 sctp_assoc_bh_rcv+0x2b2/0x430 net/sctp/associola.c:1051 sctp_inq_push+0x108/0x120 net/sctp/inqueue.c:80 sctp_rcv+0x116e/0x1340 net/sctp/input.c:243 sctp6_rcv+0x25/0x40 net/sctp/ipv6.c:1120 ip6_protocol_deliver_rcu+0x92f/0xf30 net/ipv6/ip6_input.c:437 ip6_input_finish net/ipv6/ip6_input.c:482 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip6_input+0xbd/0x1b0 net/ipv6/ip6_input.c:491 dst_input include/net/dst.h:468 [inline] ip6_rcv_finish+0x1e2/0x2e0 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:303 [inline] ipv6_rcv+0x74/0x150 net/ipv6/ip6_input.c:309 __netif_receive_skb_one_core net/core/dev.c:5452 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5566 process_backlog+0x21f/0x380 net/core/dev.c:5894 __napi_poll+0x60/0x3b0 net/core/dev.c:6460 napi_poll net/core/dev.c:6527 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6660 __do_softirq+0xc1/0x265 kernel/softirq.c:553 run_ksoftirqd+0x17/0x20 kernel/softirq.c:921 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:389 ret_from_fork+0x2e/0x40 arch/x86/kernel/process.c:145 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 read to 0xffff888149d77810 of 4 bytes by task 17828 on cpu 1: sctp_writeable net/sctp/socket.c:9304 [inline] sctp_poll+0x265/0x410 net/sctp/socket.c:8671 sock_poll+0x253/0x270 net/socket.c:1374 vfs_poll include/linux/poll.h:88 [inline] do_pollfd fs/select.c:873 [inline] do_poll fs/select.c:921 [inline] do_sys_poll+0x636/0xc00 fs/select.c:1015 __do_sys_ppoll fs/select.c:1121 [inline] __se_sys_ppoll+0x1af/0x1f0 fs/select.c:1101 __x64_sys_ppoll+0x67/0x80 fs/select.c:1101 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00019e80 -> 0x0000cc80 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 17828 Comm: syz-executor.1 Not tainted 6.5.0-rc7-syzkaller-00185-g28f20a19294d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Marcelo Ricardo Leitner Acked-by: Xin Long Link: https://lore.kernel.org/r/20230830094519.950007-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sctp/proc.c | 2 +- net/sctp/socket.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/sctp/proc.c b/net/sctp/proc.c index f13d6a34f32f..ec00ee75d59a 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -282,7 +282,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, refcount_read(&sk->sk_wmem_alloc), - sk->sk_wmem_queued, + READ_ONCE(sk->sk_wmem_queued), sk->sk_sndbuf, sk->sk_rcvbuf); seq_printf(seq, "\n"); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a11b0d903514..32e3669adf14 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -68,7 +68,7 @@ #include /* Forward declarations for internal helper functions. */ -static bool sctp_writeable(struct sock *sk); +static bool sctp_writeable(const struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, size_t msg_len); @@ -139,7 +139,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk); - sk->sk_wmem_queued += chunk->skb->truesize + sizeof(struct sctp_chunk); + sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk)); sk_mem_charge(sk, chunk->skb->truesize); } @@ -9139,7 +9139,7 @@ static void sctp_wfree(struct sk_buff *skb) struct sock *sk = asoc->base.sk; sk_mem_uncharge(sk, skb->truesize); - sk->sk_wmem_queued -= skb->truesize + sizeof(struct sctp_chunk); + sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk))); asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk); WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc)); @@ -9292,9 +9292,9 @@ void sctp_write_space(struct sock *sk) * UDP-style sockets or TCP-style sockets, this code should work. * - Daisy */ -static bool sctp_writeable(struct sock *sk) +static bool sctp_writeable(const struct sock *sk) { - return sk->sk_sndbuf > sk->sk_wmem_queued; + return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued); } /* Wait for an association to go into ESTABLISHED state. If timeout is 0, From 5aaa7ee232034e82d86e51d8305199a44d518234 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Aug 2023 09:55:20 +0000 Subject: [PATCH 1369/2093] ipv4: annotate data-races around fi->fib_dead [ Upstream commit fce92af1c29d90184dfec638b5738831097d66e9 ] syzbot complained about a data-race in fib_table_lookup() [1] Add appropriate annotations to document it. [1] BUG: KCSAN: data-race in fib_release_info / fib_table_lookup write to 0xffff888150f31744 of 1 bytes by task 1189 on cpu 0: fib_release_info+0x3a0/0x460 net/ipv4/fib_semantics.c:281 fib_table_delete+0x8d2/0x900 net/ipv4/fib_trie.c:1777 fib_magic+0x1c1/0x1f0 net/ipv4/fib_frontend.c:1106 fib_del_ifaddr+0x8cf/0xa60 net/ipv4/fib_frontend.c:1317 fib_inetaddr_event+0x77/0x200 net/ipv4/fib_frontend.c:1448 notifier_call_chain kernel/notifier.c:93 [inline] blocking_notifier_call_chain+0x90/0x200 kernel/notifier.c:388 __inet_del_ifa+0x4df/0x800 net/ipv4/devinet.c:432 inet_del_ifa net/ipv4/devinet.c:469 [inline] inetdev_destroy net/ipv4/devinet.c:322 [inline] inetdev_event+0x553/0xaf0 net/ipv4/devinet.c:1606 notifier_call_chain kernel/notifier.c:93 [inline] raw_notifier_call_chain+0x6b/0x1c0 kernel/notifier.c:461 call_netdevice_notifiers_info net/core/dev.c:1962 [inline] call_netdevice_notifiers_mtu+0xd2/0x130 net/core/dev.c:2037 dev_set_mtu_ext+0x30b/0x3e0 net/core/dev.c:8673 do_setlink+0x5be/0x2430 net/core/rtnetlink.c:2837 rtnl_setlink+0x255/0x300 net/core/rtnetlink.c:3177 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6445 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2549 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6463 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1914 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg net/socket.c:748 [inline] sock_write_iter+0x1aa/0x230 net/socket.c:1129 do_iter_write+0x4b4/0x7b0 fs/read_write.c:860 vfs_writev+0x1a8/0x320 fs/read_write.c:933 do_writev+0xf8/0x220 fs/read_write.c:976 __do_sys_writev fs/read_write.c:1049 [inline] __se_sys_writev fs/read_write.c:1046 [inline] __x64_sys_writev+0x45/0x50 fs/read_write.c:1046 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888150f31744 of 1 bytes by task 21839 on cpu 1: fib_table_lookup+0x2bf/0xd50 net/ipv4/fib_trie.c:1585 fib_lookup include/net/ip_fib.h:383 [inline] ip_route_output_key_hash_rcu+0x38c/0x12c0 net/ipv4/route.c:2751 ip_route_output_key_hash net/ipv4/route.c:2641 [inline] __ip_route_output_key include/net/route.h:134 [inline] ip_route_output_flow+0xa6/0x150 net/ipv4/route.c:2869 send4+0x1e7/0x500 drivers/net/wireguard/socket.c:61 wg_socket_send_skb_to_peer+0x94/0x130 drivers/net/wireguard/socket.c:175 wg_socket_send_buffer_to_peer+0xd6/0x100 drivers/net/wireguard/socket.c:200 wg_packet_send_handshake_initiation drivers/net/wireguard/send.c:40 [inline] wg_packet_handshake_send_worker+0x10c/0x150 drivers/net/wireguard/send.c:51 process_one_work+0x434/0x860 kernel/workqueue.c:2600 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2751 kthread+0x1d7/0x210 kernel/kthread.c:389 ret_from_fork+0x2e/0x40 arch/x86/kernel/process.c:145 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 value changed: 0x00 -> 0x01 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 21839 Comm: kworker/u4:18 Tainted: G W 6.5.0-syzkaller #0 Fixes: dccd9ecc3744 ("ipv4: Do not use dead fib_info entries.") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230830095520.1046984-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv4/fib_semantics.c | 5 ++++- net/ipv4/fib_trie.c | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3bb890a40ed7..3b6e6bc80dc1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -278,7 +278,8 @@ void fib_release_info(struct fib_info *fi) hlist_del(&nexthop_nh->nh_hash); } endfor_nexthops(fi) } - fi->fib_dead = 1; + /* Paired with READ_ONCE() from fib_table_lookup() */ + WRITE_ONCE(fi->fib_dead, 1); fib_info_put(fi); } spin_unlock_bh(&fib_info_lock); @@ -1581,6 +1582,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, link_it: ofi = fib_find_info(fi); if (ofi) { + /* fib_table_lookup() should not see @fi yet. */ fi->fib_dead = 1; free_fib_info(fi); refcount_inc(&ofi->fib_treeref); @@ -1619,6 +1621,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, failure: if (fi) { + /* fib_table_lookup() should not see @fi yet. */ fi->fib_dead = 1; free_fib_info(fi); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 74d403dbd2b4..d13fb9e76b97 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1582,7 +1582,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, if (fa->fa_dscp && inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) continue; - if (fi->fib_dead) + /* Paired with WRITE_ONCE() in fib_release_info() */ + if (READ_ONCE(fi->fib_dead)) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; From 9036b6342fcdab190d6edce3dd447859c1de90fc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Aug 2023 10:12:44 +0000 Subject: [PATCH 1370/2093] net: read sk->sk_family once in sk_mc_loop() [ Upstream commit a3e0fdf71bbe031de845e8e08ed7fba49f9c702c ] syzbot is playing with IPV6_ADDRFORM quite a lot these days, and managed to hit the WARN_ON_ONCE(1) in sk_mc_loop() We have many more similar issues to fix. WARNING: CPU: 1 PID: 1593 at net/core/sock.c:782 sk_mc_loop+0x165/0x260 Modules linked in: CPU: 1 PID: 1593 Comm: kworker/1:3 Not tainted 6.1.40-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Workqueue: events_power_efficient gc_worker RIP: 0010:sk_mc_loop+0x165/0x260 net/core/sock.c:782 Code: 34 1b fd 49 81 c7 18 05 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 20 00 74 08 4c 89 ff e8 25 36 6d fd 4d 8b 37 eb 13 e8 db 33 1b fd <0f> 0b b3 01 eb 34 e8 d0 33 1b fd 45 31 f6 49 83 c6 38 4c 89 f0 48 RSP: 0018:ffffc90000388530 EFLAGS: 00010246 RAX: ffffffff846d9b55 RBX: 0000000000000011 RCX: ffff88814f884980 RDX: 0000000000000102 RSI: ffffffff87ae5160 RDI: 0000000000000011 RBP: ffffc90000388550 R08: 0000000000000003 R09: ffffffff846d9a65 R10: 0000000000000002 R11: ffff88814f884980 R12: dffffc0000000000 R13: ffff88810dbee000 R14: 0000000000000010 R15: ffff888150084000 FS: 0000000000000000(0000) GS:ffff8881f6b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000180 CR3: 000000014ee5b000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [] ip6_finish_output2+0x33f/0x1ae0 net/ipv6/ip6_output.c:83 [] __ip6_finish_output net/ipv6/ip6_output.c:200 [inline] [] ip6_finish_output+0x6c6/0xb10 net/ipv6/ip6_output.c:211 [] NF_HOOK_COND include/linux/netfilter.h:298 [inline] [] ip6_output+0x2bc/0x3d0 net/ipv6/ip6_output.c:232 [] dst_output include/net/dst.h:444 [inline] [] ip6_local_out+0x10f/0x140 net/ipv6/output_core.c:161 [] ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:483 [inline] [] ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:529 [inline] [] ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:602 [inline] [] ipvlan_queue_xmit+0x1174/0x1be0 drivers/net/ipvlan/ipvlan_core.c:677 [] ipvlan_start_xmit+0x49/0x100 drivers/net/ipvlan/ipvlan_main.c:229 [] netdev_start_xmit include/linux/netdevice.h:4925 [inline] [] xmit_one net/core/dev.c:3644 [inline] [] dev_hard_start_xmit+0x320/0x980 net/core/dev.c:3660 [] sch_direct_xmit+0x2a0/0x9c0 net/sched/sch_generic.c:342 [] qdisc_restart net/sched/sch_generic.c:407 [inline] [] __qdisc_run+0xb13/0x1e70 net/sched/sch_generic.c:415 [] qdisc_run+0xd6/0x260 include/net/pkt_sched.h:125 [] net_tx_action+0x7ac/0x940 net/core/dev.c:5247 [] __do_softirq+0x2bd/0x9bd kernel/softirq.c:599 [] invoke_softirq kernel/softirq.c:430 [inline] [] __irq_exit_rcu+0xc8/0x170 kernel/softirq.c:683 [] irq_exit_rcu+0x9/0x20 kernel/softirq.c:695 Fixes: 7ad6848c7e81 ("ip: fix mc_loop checks for tunnels with multicast outer addresses") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230830101244.1146934-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/core/sock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index fc475845c94d..fa988063630d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -761,7 +761,8 @@ bool sk_mc_loop(struct sock *sk) return false; if (!sk) return true; - switch (sk->sk_family) { + /* IPV6_ADDRFORM can change sk->sk_family under us. */ + switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_sk(sk)->mc_loop; #if IS_ENABLED(CONFIG_IPV6) From d92c34348b37d21c80636205f863ab0b8117010f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 30 Aug 2023 13:00:37 +0200 Subject: [PATCH 1371/2093] net: fib: avoid warn splat in flow dissector [ Upstream commit 8aae7625ff3f0bd5484d01f1b8d5af82e44bec2d ] New skbs allocated via nf_send_reset() have skb->dev == NULL. fib*_rules_early_flow_dissect helpers already have a 'struct net' argument but its not passed down to the flow dissector core, which will then WARN as it can't derive a net namespace to use: WARNING: CPU: 0 PID: 0 at net/core/flow_dissector.c:1016 __skb_flow_dissect+0xa91/0x1cd0 [..] ip_route_me_harder+0x143/0x330 nf_send_reset+0x17c/0x2d0 [nf_reject_ipv4] nft_reject_inet_eval+0xa9/0xf2 [nft_reject_inet] nft_do_chain+0x198/0x5d0 [nf_tables] nft_do_chain_inet+0xa4/0x110 [nf_tables] nf_hook_slow+0x41/0xc0 ip_local_deliver+0xce/0x110 .. Cc: Stanislav Fomichev Cc: David Ahern Cc: Ido Schimmel Fixes: 812fa71f0d96 ("netfilter: Dissect flow after packet mangling") Link: https://bugzilla.kernel.org/show_bug.cgi?id=217826 Signed-off-by: Florian Westphal Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230830110043.30497-1-fw@strlen.de Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- include/net/ip6_fib.h | 5 ++++- include/net/ip_fib.h | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6268963d9599..a92f6eb85306 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -610,7 +610,10 @@ static inline bool fib6_rules_early_flow_dissect(struct net *net, if (!net->ipv6.fib6_rules_require_fldissect) return false; - skb_flow_dissect_flow_keys(skb, flkeys, flag); + memset(flkeys, 0, sizeof(*flkeys)); + __skb_flow_dissect(net, skb, &flow_keys_dissector, + flkeys, NULL, 0, 0, 0, flag); + fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; fl6->flowi6_proto = flkeys->basic.ip_proto; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index a378eff827c7..f0c13864180e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -418,7 +418,10 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, if (!net->ipv4.fib_rules_require_fldissect) return false; - skb_flow_dissect_flow_keys(skb, flkeys, flag); + memset(flkeys, 0, sizeof(*flkeys)); + __skb_flow_dissect(net, skb, &flow_keys_dissector, + flkeys, NULL, 0, 0, 0, flag); + fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; From 6436973164ea5506a495f39e56be5aea375e7832 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Thu, 31 Aug 2023 12:01:17 +0200 Subject: [PATCH 1372/2093] xsk: Fix xsk_diag use-after-free error during socket cleanup [ Upstream commit 3e019d8a05a38abb5c85d4f1e85fda964610aa14 ] Fix a use-after-free error that is possible if the xsk_diag interface is used after the socket has been unbound from the device. This can happen either due to the socket being closed or the device disappearing. In the early days of AF_XDP, the way we tested that a socket was not bound to a device was to simply check if the netdevice pointer in the xsk socket structure was NULL. Later, a better system was introduced by having an explicit state variable in the xsk socket struct. For example, the state of a socket that is on the way to being closed and has been unbound from the device is XSK_UNBOUND. The commit in the Fixes tag below deleted the old way of signalling that a socket is unbound, setting dev to NULL. This in the belief that all code using the old way had been exterminated. That was unfortunately not true as the xsk diagnostics code was still using the old way and thus does not work as intended when a socket is going down. Fix this by introducing a test against the state variable. If the socket is in the state XSK_UNBOUND, simply abort the diagnostic's netlink operation. Fixes: 18b1ab7aa76b ("xsk: Fix race at socket teardown") Reported-by: syzbot+822d1359297e2694f873@syzkaller.appspotmail.com Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Tested-by: syzbot+822d1359297e2694f873@syzkaller.appspotmail.com Tested-by: Maciej Fijalkowski Reviewed-by: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20230831100119.17408-1-magnus.karlsson@gmail.com Signed-off-by: Sasha Levin --- net/xdp/xsk_diag.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index c014217f5fa7..22b36c8143cf 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -111,6 +111,9 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, sock_diag_save_cookie(sk, msg->xdiag_cookie); mutex_lock(&xs->mutex); + if (READ_ONCE(xs->state) == XSK_UNBOUND) + goto out_nlmsg_trim; + if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) goto out_nlmsg_trim; From f5738399ed965be3ba734bd039bf96a455bb5ac0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 28 Jul 2023 18:35:07 -0700 Subject: [PATCH 1373/2093] drm/i915/gvt: Verify pfn is "valid" before dereferencing "struct page" [ Upstream commit f046923af79158361295ed4f0a588c80b9fdcc1d ] Check that the pfn found by gfn_to_pfn() is actually backed by "struct page" memory prior to retrieving and dereferencing the page. KVM supports backing guest memory with VM_PFNMAP, VM_IO, etc., and so there is no guarantee the pfn returned by gfn_to_pfn() has an associated "struct page". Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Reviewed-by: Yan Zhao Tested-by: Yongwei Ma Reviewed-by: Zhi Wang Link: https://lore.kernel.org/r/20230729013535.1070024-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gvt/gtt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 80c60754a5c1..92462cd4bf7c 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1188,6 +1188,10 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry)); if (is_error_noslot_pfn(pfn)) return -EINVAL; + + if (!pfn_valid(pfn)) + return -EINVAL; + return PageTransHuge(pfn_to_page(pfn)); } From 2b7510bb92c1fc19292801778e971cbb46e2499f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 28 Jul 2023 18:35:11 -0700 Subject: [PATCH 1374/2093] drm/i915/gvt: Put the page reference obtained by KVM's gfn_to_pfn() [ Upstream commit 708e49583d7da863898b25dafe4bcd799c414278 ] Put the struct page reference acquired by gfn_to_pfn(), KVM's API is that the caller is ultimately responsible for dropping any reference. Note, kvm_release_pfn_clean() ensures the pfn is actually a refcounted struct page before trying to put any references. Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Reviewed-by: Yan Zhao Tested-by: Yongwei Ma Reviewed-by: Zhi Wang Link: https://lore.kernel.org/r/20230729013535.1070024-6-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gvt/gtt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 92462cd4bf7c..980d671ac359 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1179,6 +1179,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, { const struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops; kvm_pfn_t pfn; + int ret; if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M)) return 0; @@ -1192,7 +1193,9 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu, if (!pfn_valid(pfn)) return -EINVAL; - return PageTransHuge(pfn_to_page(pfn)); + ret = PageTransHuge(pfn_to_page(pfn)); + kvm_release_pfn_clean(pfn); + return ret; } static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, From bd9bd085c6816885dedcd690de22d088975e6df2 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 28 Jul 2023 18:35:16 -0700 Subject: [PATCH 1375/2093] drm/i915/gvt: Drop unused helper intel_vgpu_reset_gtt() [ Upstream commit a90c367e5af63880008e21dd199dac839e0e9e0f ] Drop intel_vgpu_reset_gtt() as it no longer has any callers. In addition to eliminating dead code, this eliminates the last possible scenario where __kvmgt_protect_table_find() can be reached without holding vgpu_lock. Requiring vgpu_lock to be held when calling __kvmgt_protect_table_find() will allow a protecting the gfn hash with vgpu_lock without too much fuss. No functional change intended. Fixes: ba25d977571e ("drm/i915/gvt: Do not destroy ppgtt_mm during vGPU D3->D0.") Reviewed-by: Yan Zhao Tested-by: Yongwei Ma Reviewed-by: Zhi Wang Link: https://lore.kernel.org/r/20230729013535.1070024-11-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gvt/gtt.c | 18 ------------------ drivers/gpu/drm/i915/gvt/gtt.h | 1 - 2 files changed, 19 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 980d671ac359..79bf1be68d8c 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2887,24 +2887,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old) ggtt_invalidate(gvt->gt); } -/** - * intel_vgpu_reset_gtt - reset the all GTT related status - * @vgpu: a vGPU - * - * This function is called from vfio core to reset reset all - * GTT related status, including GGTT, PPGTT, scratch page. - * - */ -void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu) -{ - /* Shadow pages are only created when there is no page - * table tracking data, so remove page tracking data after - * removing the shadow pages. - */ - intel_vgpu_destroy_all_ppgtt_mm(vgpu); - intel_vgpu_reset_ggtt(vgpu, true); -} - /** * intel_gvt_restore_ggtt - restore all vGPU's ggtt entries * @gvt: intel gvt device diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index a3b0f59ec8bd..4cb183e06e95 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -224,7 +224,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old); void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu); int intel_gvt_init_gtt(struct intel_gvt *gvt); -void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu); void intel_gvt_clean_gtt(struct intel_gvt *gvt); struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu, From f1175881ddd91db46648c28eec05628e30e14c65 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 31 Aug 2023 13:52:08 +0000 Subject: [PATCH 1376/2093] net: use sk_forward_alloc_get() in sk_get_meminfo() [ Upstream commit 66d58f046c9d3a8f996b7138d02e965fd0617de0 ] inet_sk_diag_fill() has been changed to use sk_forward_alloc_get(), but sk_get_meminfo() was forgotten. Fixes: 292e6077b040 ("net: introduce sk_forward_alloc_get()") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index fa988063630d..6ff58fa5f41e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3715,7 +3715,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); - mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; + mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk); mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); From 787c5829681b14903ae507853994860caed00718 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 31 Aug 2023 13:52:09 +0000 Subject: [PATCH 1377/2093] net: annotate data-races around sk->sk_forward_alloc [ Upstream commit 5e6300e7b3a4ab5b72a82079753868e91fbf9efc ] Every time sk->sk_forward_alloc is read locklessly, add a READ_ONCE(). Add sk_forward_alloc_add() helper to centralize updates, to reduce number of WRITE_ONCE(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/sock.h | 12 +++++++++--- net/core/sock.c | 8 ++++---- net/ipv4/tcp_output.c | 2 +- net/ipv4/udp.c | 6 +++--- net/mptcp/protocol.c | 6 +++--- 5 files changed, 20 insertions(+), 14 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index d1f936ed9755..fe695e8bfe28 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1049,6 +1049,12 @@ static inline void sk_wmem_queued_add(struct sock *sk, int val) WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } +static inline void sk_forward_alloc_add(struct sock *sk, int val) +{ + /* Paired with lockless reads of sk->sk_forward_alloc */ + WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val); +} + void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ @@ -1401,7 +1407,7 @@ static inline int sk_forward_alloc_get(const struct sock *sk) if (sk->sk_prot->forward_alloc_get) return sk->sk_prot->forward_alloc_get(sk); #endif - return sk->sk_forward_alloc; + return READ_ONCE(sk->sk_forward_alloc); } static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) @@ -1697,14 +1703,14 @@ static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; - sk->sk_forward_alloc -= size; + sk_forward_alloc_add(sk, -size); } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; - sk->sk_forward_alloc += size; + sk_forward_alloc_add(sk, size); sk_mem_reclaim(sk); } diff --git a/net/core/sock.c b/net/core/sock.c index 6ff58fa5f41e..aa628c6314f6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1034,7 +1034,7 @@ static int sock_reserve_memory(struct sock *sk, int bytes) mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); return -ENOMEM; } - sk->sk_forward_alloc += pages << PAGE_SHIFT; + sk_forward_alloc_add(sk, pages << PAGE_SHIFT); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem + (pages << PAGE_SHIFT)); @@ -3082,10 +3082,10 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); - sk->sk_forward_alloc += amt << PAGE_SHIFT; + sk_forward_alloc_add(sk, amt << PAGE_SHIFT); ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) - sk->sk_forward_alloc -= amt << PAGE_SHIFT; + sk_forward_alloc_add(sk, -(amt << PAGE_SHIFT)); return ret; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -3117,7 +3117,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; - sk->sk_forward_alloc -= amount << PAGE_SHIFT; + sk_forward_alloc_add(sk, -(amount << PAGE_SHIFT)); __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 26bd039f9296..dc3166e56169 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3380,7 +3380,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) if (delta <= 0) return; amt = sk_mem_pages(delta); - sk->sk_forward_alloc += amt << PAGE_SHIFT; + sk_forward_alloc_add(sk, amt << PAGE_SHIFT); sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 42c1f7d9a980..b2aa7777521f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1474,9 +1474,9 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, spin_lock(&sk_queue->lock); - sk->sk_forward_alloc += size; + sk_forward_alloc_add(sk, size); amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); - sk->sk_forward_alloc -= amt; + sk_forward_alloc_add(sk, -amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); @@ -1582,7 +1582,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) sk->sk_forward_alloc += delta; } - sk->sk_forward_alloc -= size; + sk_forward_alloc_add(sk, -size); /* no need to setup a destructor, we will explicitly release the * forward allocated memory on dequeue diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 61fefa1a82db..573db9c2bc1c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1802,7 +1802,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } /* data successfully copied into the write queue */ - sk->sk_forward_alloc -= total_ts; + sk_forward_alloc_add(sk, -total_ts); copied += psize; dfrag->data_len += psize; frag_truesize += psize; @@ -3278,7 +3278,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) /* move all the rx fwd alloc into the sk_mem_reclaim_final in * inet_sock_destruct() will dispose it */ - sk->sk_forward_alloc += msk->rmem_fwd_alloc; + sk_forward_alloc_add(sk, msk->rmem_fwd_alloc); msk->rmem_fwd_alloc = 0; mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); @@ -3562,7 +3562,7 @@ static void mptcp_shutdown(struct sock *sk, int how) static int mptcp_forward_alloc_get(const struct sock *sk) { - return sk->sk_forward_alloc + mptcp_sk(sk)->rmem_fwd_alloc; + return READ_ONCE(sk->sk_forward_alloc) + mptcp_sk(sk)->rmem_fwd_alloc; } static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) From b7d25ac3627a0ed3569cc5cb15305e172ca58385 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 31 Aug 2023 13:52:10 +0000 Subject: [PATCH 1378/2093] mptcp: annotate data-races around msk->rmem_fwd_alloc [ Upstream commit 9531e4a83febc3fb47ac77e24cfb5ea97e50034d ] msk->rmem_fwd_alloc can be read locklessly. Add mptcp_rmem_fwd_alloc_add(), similar to sk_forward_alloc_add(), and appropriate READ_ONCE()/WRITE_ONCE() annotations. Fixes: 6511882cdd82 ("mptcp: allocate fwd memory separately on the rx and tx path") Signed-off-by: Eric Dumazet Cc: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/mptcp/protocol.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 573db9c2bc1c..6dd880d6b051 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -131,9 +131,15 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } +static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size) +{ + WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc, + mptcp_sk(sk)->rmem_fwd_alloc + size); +} + static void mptcp_rmem_charge(struct sock *sk, int size) { - mptcp_sk(sk)->rmem_fwd_alloc -= size; + mptcp_rmem_fwd_alloc_add(sk, -size); } static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, @@ -174,7 +180,7 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, static void __mptcp_rmem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; - mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT; + mptcp_rmem_charge(sk, amount << PAGE_SHIFT); __sk_mem_reduce_allocated(sk, amount); } @@ -183,7 +189,7 @@ static void mptcp_rmem_uncharge(struct sock *sk, int size) struct mptcp_sock *msk = mptcp_sk(sk); int reclaimable; - msk->rmem_fwd_alloc += size; + mptcp_rmem_fwd_alloc_add(sk, size); reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk); /* see sk_mem_uncharge() for the rationale behind the following schema */ @@ -338,7 +344,7 @@ static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size) if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) return false; - msk->rmem_fwd_alloc += amount; + mptcp_rmem_fwd_alloc_add(sk, amount); return true; } @@ -3279,7 +3285,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) * inet_sock_destruct() will dispose it */ sk_forward_alloc_add(sk, msk->rmem_fwd_alloc); - msk->rmem_fwd_alloc = 0; + WRITE_ONCE(msk->rmem_fwd_alloc, 0); mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); mptcp_free_local_addr_list(msk); @@ -3562,7 +3568,8 @@ static void mptcp_shutdown(struct sock *sk, int how) static int mptcp_forward_alloc_get(const struct sock *sk) { - return READ_ONCE(sk->sk_forward_alloc) + mptcp_sk(sk)->rmem_fwd_alloc; + return READ_ONCE(sk->sk_forward_alloc) + + READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc); } static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) From 0b2ee66411fe09584501140e6fa3578bc5063900 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Thu, 31 Aug 2023 10:03:30 +0200 Subject: [PATCH 1379/2093] ipv4: ignore dst hint for multipath routes [ Upstream commit 6ac66cb03ae306c2e288a9be18226310529f5b25 ] Route hints when the nexthop is part of a multipath group causes packets in the same receive batch to be sent to the same nexthop irrespective of the multipath hash of the packet. So, do not extract route hint for packets whose destination is part of a multipath group. A new SKB flag IPSKB_MULTIPATH is introduced for this purpose, set the flag when route is looked up in ip_mkroute_input() and use it in ip_extract_route_hint() to check for the existence of the flag. Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive") Signed-off-by: Sriram Yagnaraman Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/ip.h | 1 + net/ipv4/ip_input.c | 3 ++- net/ipv4/route.c | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/include/net/ip.h b/include/net/ip.h index 1872f570abed..c286344628db 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -57,6 +57,7 @@ struct inet_skb_parm { #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) #define IPSKB_NOPOLICY BIT(8) +#define IPSKB_MULTIPATH BIT(9) u16 frag_max_size; }; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index e880ce77322a..e7196ecffafc 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -584,7 +584,8 @@ static void ip_sublist_rcv_finish(struct list_head *head) static struct sk_buff *ip_extract_route_hint(const struct net *net, struct sk_buff *skb, int rt_type) { - if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST) + if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST || + IPCB(skb)->flags & IPSKB_MULTIPATH) return NULL; return skb; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 51bd9a50a1d1..a04ffc128e22 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2146,6 +2146,7 @@ static int ip_mkroute_input(struct sk_buff *skb, int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); + IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif From 7ddfe350e2554a28551333f4f50f95f5290dcf72 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Thu, 31 Aug 2023 10:03:31 +0200 Subject: [PATCH 1380/2093] ipv6: ignore dst hint for multipath routes [ Upstream commit 8423be8926aa82cd2e28bba5cc96ccb72c7ce6be ] Route hints when the nexthop is part of a multipath group causes packets in the same receive batch to be sent to the same nexthop irrespective of the multipath hash of the packet. So, do not extract route hint for packets whose destination is part of a multipath group. A new SKB flag IP6SKB_MULTIPATH is introduced for this purpose, set the flag when route is looked up in fib6_select_path() and use it in ip6_can_use_hint() to check for the existence of the flag. Fixes: 197dbf24e360 ("ipv6: introduce and uses route look hints for list input.") Signed-off-by: Sriram Yagnaraman Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/ipv6.h | 1 + net/ipv6/ip6_input.c | 3 ++- net/ipv6/route.c | 3 +++ 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 37dfdcfcdd54..15d7529ac953 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -146,6 +146,7 @@ struct inet6_skb_parm { #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 #define IP6SKB_FAKEJUMBO 512 +#define IP6SKB_MULTIPATH 1024 }; #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index d94041bb4287..b8378814532c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -99,7 +99,8 @@ static bool ip6_can_use_hint(const struct sk_buff *skb, static struct sk_buff *ip6_extract_route_hint(const struct net *net, struct sk_buff *skb) { - if (fib6_routes_require_src(net) || fib6_has_custom_rules(net)) + if (fib6_routes_require_src(net) || fib6_has_custom_rules(net) || + IP6CB(skb)->flags & IP6SKB_MULTIPATH) return NULL; return skb; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 960ab43a49c4..93957b20fccc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -425,6 +425,9 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (match->nh && have_oif_match && res->nh) return; + if (skb) + IP6CB(skb)->flags |= IP6SKB_MULTIPATH; + /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ From 24b1e835db343cc410c1270cdb95f723b282825d Mon Sep 17 00:00:00 2001 From: Corinna Vinschen Date: Thu, 31 Aug 2023 14:19:13 +0200 Subject: [PATCH 1381/2093] igb: disable virtualization features on 82580 [ Upstream commit fa09bc40b21a33937872c4c4cf0f266ec9fa4869 ] Disable virtualization features on 82580 just as on i210/i211. This avoids that virt functions are acidentally called on 82850. Fixes: 55cac248caa4 ("igb: Add full support for 82580 devices") Signed-off-by: Corinna Vinschen Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index d0ead18ec026..45ce4ed16146 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3877,8 +3877,9 @@ static void igb_probe_vfs(struct igb_adapter *adapter) struct pci_dev *pdev = adapter->pdev; struct e1000_hw *hw = &adapter->hw; - /* Virtualization features not supported on i210 family. */ - if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) + /* Virtualization features not supported on i210 and 82580 family. */ + if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211) || + (hw->mac.type == e1000_82580)) return; /* Of the below we really only want the effect of getting From a47ad6d226dca9e18cab6e046c62881db427976b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 31 Aug 2023 21:38:12 +0000 Subject: [PATCH 1382/2093] gve: fix frag_list chaining [ Upstream commit 817c7cd2043a83a3d8147f40eea1505ac7300b62 ] gve_rx_append_frags() is able to build skbs chained with frag_list, like GRO engine. Problem is that shinfo->frag_list should only be used for the head of the chain. All other links should use skb->next pointer. Otherwise, built skbs are not valid and can cause crashes. Equivalent code in GRO (skb_gro_receive()) is: if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; NAPI_GRO_CB(p)->last = skb; Fixes: 9b8dd5e5ea48 ("gve: DQO: Add RX path") Signed-off-by: Eric Dumazet Cc: Bailey Forrest Cc: Willem de Bruijn Cc: Catherine Sullivan Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 2e6461b0ea8b..a9409e3721ad 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -492,7 +492,10 @@ static int gve_rx_append_frags(struct napi_struct *napi, if (!skb) return -1; - skb_shinfo(rx->ctx.skb_tail)->frag_list = skb; + if (rx->ctx.skb_tail == rx->ctx.skb_head) + skb_shinfo(rx->ctx.skb_head)->frag_list = skb; + else + rx->ctx.skb_tail->next = skb; rx->ctx.skb_tail = skb; num_frags = 0; } From e752860bbc3ca9ded2df9fe47c7149327e0e9778 Mon Sep 17 00:00:00 2001 From: Liang Chen Date: Fri, 1 Sep 2023 12:09:21 +0800 Subject: [PATCH 1383/2093] veth: Fixing transmit return status for dropped packets [ Upstream commit 151e887d8ff97e2e42110ffa1fb1e6a2128fb364 ] The veth_xmit function returns NETDEV_TX_OK even when packets are dropped. This behavior leads to incorrect calculations of statistics counts, as well as things like txq->trans_start updates. Fixes: e314dbdc1c0d ("[NET]: Virtual ethernet device driver.") Signed-off-by: Liang Chen Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/veth.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 727b9278b9fe..36c5a41f84e4 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -313,6 +313,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct veth_rq *rq = NULL; + int ret = NETDEV_TX_OK; struct net_device *rcv; int length = skb->len; bool use_napi = false; @@ -345,6 +346,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) } else { drop: atomic64_inc(&priv->dropped); + ret = NET_XMIT_DROP; } if (use_napi) @@ -352,7 +354,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); - return NETDEV_TX_OK; + return ret; } static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes) From aa8fd3a636918390b8040cb1d646dbf8214b8ed7 Mon Sep 17 00:00:00 2001 From: Alex Henrie Date: Thu, 31 Aug 2023 22:41:27 -0600 Subject: [PATCH 1384/2093] net: ipv6/addrconf: avoid integer underflow in ipv6_create_tempaddr [ Upstream commit f31867d0d9d82af757c1e0178b659438f4c1ea3c ] The existing code incorrectly casted a negative value (the result of a subtraction) to an unsigned value without checking. For example, if /proc/sys/net/ipv6/conf/*/temp_prefered_lft was set to 1, the preferred lifetime would jump to 4 billion seconds. On my machine and network the shortest lifetime that avoided underflow was 3 seconds. Fixes: 76506a986dc3 ("IPv6: fix DESYNC_FACTOR") Signed-off-by: Alex Henrie Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/addrconf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 48a6486951cd..83be84219824 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1368,7 +1368,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) * idev->desync_factor if it's larger */ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft); - max_desync_factor = min_t(__u32, + max_desync_factor = min_t(long, idev->cnf.max_desync_factor, cnf_temp_preferred_lft - regen_advance); From 71fb38b222cff65f282b068f9ef83d5ce5e9c87d Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 1 Sep 2023 06:53:23 +0200 Subject: [PATCH 1385/2093] net: phy: micrel: Correct bit assignments for phy_device flags [ Upstream commit 719c5e37e99d2fd588d1c994284d17650a66354c ] Previously, the defines for phy_device flags in the Micrel driver were ambiguous in their representation. They were intended to be bit masks but were mistakenly defined as bit positions. This led to the following issues: - MICREL_KSZ8_P1_ERRATA, designated for KSZ88xx switches, overlapped with MICREL_PHY_FXEN and MICREL_PHY_50MHZ_CLK. - Due to this overlap, the code path for MICREL_PHY_FXEN, tailored for the KSZ8041 PHY, was not executed for KSZ88xx PHYs. - Similarly, the code associated with MICREL_PHY_50MHZ_CLK wasn't triggered for KSZ88xx. To rectify this, all three flags have now been explicitly converted to use the `BIT()` macro, ensuring they are defined as bit masks and preventing potential overlaps in the future. Fixes: 49011e0c1555 ("net: phy: micrel: ksz886x/ksz8081: add cabletest support") Signed-off-by: Oleksij Rempel Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/micrel_phy.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 1f7c33b2f5a3..e164facb0f36 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -38,9 +38,9 @@ #define PHY_ID_KSZ9477 0x00221631 /* struct phy_device dev_flags definitions */ -#define MICREL_PHY_50MHZ_CLK 0x00000001 -#define MICREL_PHY_FXEN 0x00000002 -#define MICREL_KSZ8_P1_ERRATA 0x00000003 +#define MICREL_PHY_50MHZ_CLK BIT(0) +#define MICREL_PHY_FXEN BIT(1) +#define MICREL_KSZ8_P1_ERRATA BIT(2) #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC From 923877254f002ae87d441382bb1096d9e773d56d Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 1 Sep 2023 13:21:37 -0700 Subject: [PATCH 1386/2093] bpf, sockmap: Fix skb refcnt race after locking changes [ Upstream commit a454d84ee20baf7bd7be90721b9821f73c7d23d9 ] There is a race where skb's from the sk_psock_backlog can be referenced after userspace side has already skb_consumed() the sk_buff and its refcnt dropped to zer0 causing use after free. The flow is the following: while ((skb = skb_peek(&psock->ingress_skb)) sk_psock_handle_Skb(psock, skb, ..., ingress) if (!ingress) ... sk_psock_skb_ingress sk_psock_skb_ingress_enqueue(skb) msg->skb = skb sk_psock_queue_msg(psock, msg) skb_dequeue(&psock->ingress_skb) The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is what the application reads when recvmsg() is called. An application can read this anytime after the msg is placed on the queue. The recvmsg hook will also read msg->skb and then after user space reads the msg will call consume_skb(skb) on it effectively free'ing it. But, the race is in above where backlog queue still has a reference to the skb and calls skb_dequeue(). If the skb_dequeue happens after the user reads and free's the skb we have a use after free. The !ingress case does not suffer from this problem because it uses sendmsg_*(sk, msg) which does not pass the sk_buff further down the stack. The following splat was observed with 'test_progs -t sockmap_listen': [ 1022.710250][ T2556] general protection fault, ... [...] [ 1022.712830][ T2556] Workqueue: events sk_psock_backlog [ 1022.713262][ T2556] RIP: 0010:skb_dequeue+0x4c/0x80 [ 1022.713653][ T2556] Code: ... [...] [ 1022.720699][ T2556] Call Trace: [ 1022.720984][ T2556] [ 1022.721254][ T2556] ? die_addr+0x32/0x80^M [ 1022.721589][ T2556] ? exc_general_protection+0x25a/0x4b0 [ 1022.722026][ T2556] ? asm_exc_general_protection+0x22/0x30 [ 1022.722489][ T2556] ? skb_dequeue+0x4c/0x80 [ 1022.722854][ T2556] sk_psock_backlog+0x27a/0x300 [ 1022.723243][ T2556] process_one_work+0x2a7/0x5b0 [ 1022.723633][ T2556] worker_thread+0x4f/0x3a0 [ 1022.723998][ T2556] ? __pfx_worker_thread+0x10/0x10 [ 1022.724386][ T2556] kthread+0xfd/0x130 [ 1022.724709][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725066][ T2556] ret_from_fork+0x2d/0x50 [ 1022.725409][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725799][ T2556] ret_from_fork_asm+0x1b/0x30 [ 1022.726201][ T2556] To fix we add an skb_get() before passing the skb to be enqueued in the engress queue. This bumps the skb->users refcnt so that consume_skb() and kfree_skb will not immediately free the sk_buff. With this we can be sure the skb is still around when we do the dequeue. Then we just need to decrement the refcnt or free the skb in the backlog case which we do by calling kfree_skb() on the ingress case as well as the sendmsg case. Before locking change from fixes tag we had the sock locked so we couldn't race with user and there was no issue here. Fixes: 799aa7f98d53e ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Jiri Olsa Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Tested-by: Xu Kuohai Tested-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230901202137.214666-1-john.fastabend@gmail.com Signed-off-by: Sasha Levin --- net/core/skmsg.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 296e45b6c3c0..a5c1f67dc96e 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -611,12 +611,18 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { + int err = 0; + if (!ingress) { if (!sock_writeable(psock->sk)) return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - return sk_psock_skb_ingress(psock, skb, off, len); + skb_get(skb); + err = sk_psock_skb_ingress(psock, skb, off, len); + if (err < 0) + kfree_skb(skb); + return err; } static void sk_psock_skb_state(struct sk_psock *psock, @@ -684,9 +690,7 @@ static void sk_psock_backlog(struct work_struct *work) } while (len); skb = skb_dequeue(&psock->ingress_skb); - if (!ingress) { - kfree_skb(skb); - } + kfree_skb(skb); } end: mutex_unlock(&psock->work_mutex); From b9cdbb38e030fc2fe97fe27b54cbb6b4fbff250f Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 1 Sep 2023 17:27:05 -0700 Subject: [PATCH 1387/2093] af_unix: Fix data-races around user->unix_inflight. [ Upstream commit 0bc36c0650b21df36fbec8136add83936eaf0607 ] user->unix_inflight is changed under spin_lock(unix_gc_lock), but too_many_unix_fds() reads it locklessly. Let's annotate the write/read accesses to user->unix_inflight. BUG: KCSAN: data-race in unix_attach_fds / unix_inflight write to 0xffffffff8546f2d0 of 8 bytes by task 44798 on cpu 1: unix_inflight+0x157/0x180 net/unix/scm.c:66 unix_attach_fds+0x147/0x1e0 net/unix/scm.c:123 unix_scm_to_skb net/unix/af_unix.c:1827 [inline] unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1950 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline] unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg+0x148/0x160 net/socket.c:748 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548 __sys_sendmsg+0x94/0x140 net/socket.c:2577 __do_sys_sendmsg net/socket.c:2586 [inline] __se_sys_sendmsg net/socket.c:2584 [inline] __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 read to 0xffffffff8546f2d0 of 8 bytes by task 44814 on cpu 0: too_many_unix_fds net/unix/scm.c:101 [inline] unix_attach_fds+0x54/0x1e0 net/unix/scm.c:110 unix_scm_to_skb net/unix/af_unix.c:1827 [inline] unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1950 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline] unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg+0x148/0x160 net/socket.c:748 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548 __sys_sendmsg+0x94/0x140 net/socket.c:2577 __do_sys_sendmsg net/socket.c:2586 [inline] __se_sys_sendmsg net/socket.c:2584 [inline] __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 value changed: 0x000000000000000c -> 0x000000000000000d Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 44814 Comm: systemd-coredum Not tainted 6.4.0-11989-g6843306689af #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 712f4aad406b ("unix: properly account for FDs passed over unix sockets") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Acked-by: Willy Tarreau Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/unix/scm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/unix/scm.c b/net/unix/scm.c index aa27a02478dc..e8e2a00bb0f5 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -63,7 +63,7 @@ void unix_inflight(struct user_struct *user, struct file *fp) /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); } - user->unix_inflight++; + WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); spin_unlock(&unix_gc_lock); } @@ -84,7 +84,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp) /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); } - user->unix_inflight--; + WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); spin_unlock(&unix_gc_lock); } @@ -98,7 +98,7 @@ static inline bool too_many_unix_fds(struct task_struct *p) { struct user_struct *user = current_user(); - if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); return false; } From 2d8933ca863e252fb09ad0be483255e3dfeb1f54 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 1 Sep 2023 17:27:06 -0700 Subject: [PATCH 1388/2093] af_unix: Fix data-race around unix_tot_inflight. [ Upstream commit ade32bd8a738d7497ffe9743c46728db26740f78 ] unix_tot_inflight is changed under spin_lock(unix_gc_lock), but unix_release_sock() reads it locklessly. Let's use READ_ONCE() for unix_tot_inflight. Note that the writer side was marked by commit 9d6d7f1cb67c ("af_unix: annote lockless accesses to unix_tot_inflight & gc_in_progress") BUG: KCSAN: data-race in unix_inflight / unix_release_sock write (marked) to 0xffffffff871852b8 of 4 bytes by task 123 on cpu 1: unix_inflight+0x130/0x180 net/unix/scm.c:64 unix_attach_fds+0x137/0x1b0 net/unix/scm.c:123 unix_scm_to_skb net/unix/af_unix.c:1832 [inline] unix_dgram_sendmsg+0x46a/0x14f0 net/unix/af_unix.c:1955 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x148/0x160 net/socket.c:747 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2493 ___sys_sendmsg+0xc6/0x140 net/socket.c:2547 __sys_sendmsg+0x94/0x140 net/socket.c:2576 __do_sys_sendmsg net/socket.c:2585 [inline] __se_sys_sendmsg net/socket.c:2583 [inline] __x64_sys_sendmsg+0x45/0x50 net/socket.c:2583 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffffffff871852b8 of 4 bytes by task 4891 on cpu 0: unix_release_sock+0x608/0x910 net/unix/af_unix.c:671 unix_release+0x59/0x80 net/unix/af_unix.c:1058 __sock_release+0x7d/0x170 net/socket.c:653 sock_close+0x19/0x30 net/socket.c:1385 __fput+0x179/0x5e0 fs/file_table.c:321 ____fput+0x15/0x20 fs/file_table.c:349 task_work_run+0x116/0x1a0 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0x00000000 -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 4891 Comm: systemd-coredum Not tainted 6.4.0-rc5-01219-gfa0e21fa4443 #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 9305cfa4443d ("[AF_UNIX]: Make unix_tot_inflight counter non-atomic") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ca31847a6c70..310952f4c68f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -667,7 +667,7 @@ static void unix_release_sock(struct sock *sk, int embrion) * What the above comment does talk about? --ANK(980817) */ - if (unix_tot_inflight) + if (READ_ONCE(unix_tot_inflight)) unix_gc(); /* Garbage collect fds */ } From ce3aa88ceccdafd4286aef2cc9834b1e342218ab Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 1 Sep 2023 17:27:07 -0700 Subject: [PATCH 1389/2093] af_unix: Fix data-races around sk->sk_shutdown. [ Upstream commit afe8764f76346ba838d4f162883e23d2fcfaa90e ] sk->sk_shutdown is changed under unix_state_lock(sk), but unix_dgram_sendmsg() calls two functions to read sk_shutdown locklessly. sock_alloc_send_pskb `- sock_wait_for_wmem Let's use READ_ONCE() there. Note that the writer side was marked by commit e1d09c2c2f57 ("af_unix: Fix data races around sk->sk_shutdown."). BUG: KCSAN: data-race in sock_alloc_send_pskb / unix_release_sock write (marked) to 0xffff8880069af12c of 1 bytes by task 1 on cpu 1: unix_release_sock+0x75c/0x910 net/unix/af_unix.c:631 unix_release+0x59/0x80 net/unix/af_unix.c:1053 __sock_release+0x7d/0x170 net/socket.c:654 sock_close+0x19/0x30 net/socket.c:1386 __fput+0x2a3/0x680 fs/file_table.c:384 ____fput+0x15/0x20 fs/file_table.c:412 task_work_run+0x116/0x1a0 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 read to 0xffff8880069af12c of 1 bytes by task 28650 on cpu 0: sock_alloc_send_pskb+0xd2/0x620 net/core/sock.c:2767 unix_dgram_sendmsg+0x2f8/0x14f0 net/unix/af_unix.c:1944 unix_seqpacket_sendmsg net/unix/af_unix.c:2308 [inline] unix_seqpacket_sendmsg+0xba/0x130 net/unix/af_unix.c:2292 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg+0x148/0x160 net/socket.c:748 ____sys_sendmsg+0x4e4/0x610 net/socket.c:2494 ___sys_sendmsg+0xc6/0x140 net/socket.c:2548 __sys_sendmsg+0x94/0x140 net/socket.c:2577 __do_sys_sendmsg net/socket.c:2586 [inline] __se_sys_sendmsg net/socket.c:2584 [inline] __x64_sys_sendmsg+0x45/0x50 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 value changed: 0x00 -> 0x03 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 28650 Comm: systemd-coredum Not tainted 6.4.0-11989-g6843306689af #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index aa628c6314f6..71990525d37e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2690,7 +2690,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; - if (sk->sk_shutdown & SEND_SHUTDOWN) + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; if (sk->sk_err) break; @@ -2720,7 +2720,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, goto failure; err = -EPIPE; - if (sk->sk_shutdown & SEND_SHUTDOWN) + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) From 2100bbf55e565c9005e4d5d2f7c333d35741073f Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 1 Sep 2023 17:27:08 -0700 Subject: [PATCH 1390/2093] af_unix: Fix data race around sk->sk_err. [ Upstream commit b192812905e4b134f7b7994b079eb647e9d2d37e ] As with sk->sk_shutdown shown in the previous patch, sk->sk_err can be read locklessly by unix_dgram_sendmsg(). Let's use READ_ONCE() for sk_err as well. Note that the writer side is marked by commit cc04410af7de ("af_unix: annotate lockless accesses to sk->sk_err"). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index 71990525d37e..e5858fa5d6d5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2692,7 +2692,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } From a18349dc8d916a64d7c93f05da98953e3386d8e9 Mon Sep 17 00:00:00 2001 From: valis Date: Fri, 1 Sep 2023 12:22:37 -0400 Subject: [PATCH 1391/2093] net: sched: sch_qfq: Fix UAF in qfq_dequeue() [ Upstream commit 8fc134fee27f2263988ae38920bc03da416b03d8 ] When the plug qdisc is used as a class of the qfq qdisc it could trigger a UAF. This issue can be reproduced with following commands: tc qdisc add dev lo root handle 1: qfq tc class add dev lo parent 1: classid 1:1 qfq weight 1 maxpkt 512 tc qdisc add dev lo parent 1:1 handle 2: plug tc filter add dev lo parent 1: basic classid 1:1 ping -c1 127.0.0.1 and boom: [ 285.353793] BUG: KASAN: slab-use-after-free in qfq_dequeue+0xa7/0x7f0 [ 285.354910] Read of size 4 at addr ffff8880bad312a8 by task ping/144 [ 285.355903] [ 285.356165] CPU: 1 PID: 144 Comm: ping Not tainted 6.5.0-rc3+ #4 [ 285.357112] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [ 285.358376] Call Trace: [ 285.358773] [ 285.359109] dump_stack_lvl+0x44/0x60 [ 285.359708] print_address_description.constprop.0+0x2c/0x3c0 [ 285.360611] kasan_report+0x10c/0x120 [ 285.361195] ? qfq_dequeue+0xa7/0x7f0 [ 285.361780] qfq_dequeue+0xa7/0x7f0 [ 285.362342] __qdisc_run+0xf1/0x970 [ 285.362903] net_tx_action+0x28e/0x460 [ 285.363502] __do_softirq+0x11b/0x3de [ 285.364097] do_softirq.part.0+0x72/0x90 [ 285.364721] [ 285.365072] [ 285.365422] __local_bh_enable_ip+0x77/0x90 [ 285.366079] __dev_queue_xmit+0x95f/0x1550 [ 285.366732] ? __pfx_csum_and_copy_from_iter+0x10/0x10 [ 285.367526] ? __pfx___dev_queue_xmit+0x10/0x10 [ 285.368259] ? __build_skb_around+0x129/0x190 [ 285.368960] ? ip_generic_getfrag+0x12c/0x170 [ 285.369653] ? __pfx_ip_generic_getfrag+0x10/0x10 [ 285.370390] ? csum_partial+0x8/0x20 [ 285.370961] ? raw_getfrag+0xe5/0x140 [ 285.371559] ip_finish_output2+0x539/0xa40 [ 285.372222] ? __pfx_ip_finish_output2+0x10/0x10 [ 285.372954] ip_output+0x113/0x1e0 [ 285.373512] ? __pfx_ip_output+0x10/0x10 [ 285.374130] ? icmp_out_count+0x49/0x60 [ 285.374739] ? __pfx_ip_finish_output+0x10/0x10 [ 285.375457] ip_push_pending_frames+0xf3/0x100 [ 285.376173] raw_sendmsg+0xef5/0x12d0 [ 285.376760] ? do_syscall_64+0x40/0x90 [ 285.377359] ? __static_call_text_end+0x136578/0x136578 [ 285.378173] ? do_syscall_64+0x40/0x90 [ 285.378772] ? kasan_enable_current+0x11/0x20 [ 285.379469] ? __pfx_raw_sendmsg+0x10/0x10 [ 285.380137] ? __sock_create+0x13e/0x270 [ 285.380673] ? __sys_socket+0xf3/0x180 [ 285.381174] ? __x64_sys_socket+0x3d/0x50 [ 285.381725] ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.382425] ? __rcu_read_unlock+0x48/0x70 [ 285.382975] ? ip4_datagram_release_cb+0xd8/0x380 [ 285.383608] ? __pfx_ip4_datagram_release_cb+0x10/0x10 [ 285.384295] ? preempt_count_sub+0x14/0xc0 [ 285.384844] ? __list_del_entry_valid+0x76/0x140 [ 285.385467] ? _raw_spin_lock_bh+0x87/0xe0 [ 285.386014] ? __pfx__raw_spin_lock_bh+0x10/0x10 [ 285.386645] ? release_sock+0xa0/0xd0 [ 285.387148] ? preempt_count_sub+0x14/0xc0 [ 285.387712] ? freeze_secondary_cpus+0x348/0x3c0 [ 285.388341] ? aa_sk_perm+0x177/0x390 [ 285.388856] ? __pfx_aa_sk_perm+0x10/0x10 [ 285.389441] ? check_stack_object+0x22/0x70 [ 285.390032] ? inet_send_prepare+0x2f/0x120 [ 285.390603] ? __pfx_inet_sendmsg+0x10/0x10 [ 285.391172] sock_sendmsg+0xcc/0xe0 [ 285.391667] __sys_sendto+0x190/0x230 [ 285.392168] ? __pfx___sys_sendto+0x10/0x10 [ 285.392727] ? kvm_clock_get_cycles+0x14/0x30 [ 285.393328] ? set_normalized_timespec64+0x57/0x70 [ 285.393980] ? _raw_spin_unlock_irq+0x1b/0x40 [ 285.394578] ? __x64_sys_clock_gettime+0x11c/0x160 [ 285.395225] ? __pfx___x64_sys_clock_gettime+0x10/0x10 [ 285.395908] ? _copy_to_user+0x3e/0x60 [ 285.396432] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.397086] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.397734] ? do_syscall_64+0x71/0x90 [ 285.398258] __x64_sys_sendto+0x74/0x90 [ 285.398786] do_syscall_64+0x64/0x90 [ 285.399273] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.399949] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.400605] ? do_syscall_64+0x71/0x90 [ 285.401124] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.401807] RIP: 0033:0x495726 [ 285.402233] Code: ff ff ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 11 b8 2c 00 00 00 0f 09 [ 285.404683] RSP: 002b:00007ffcc25fb618 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 285.405677] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 0000000000495726 [ 285.406628] RDX: 0000000000000040 RSI: 0000000002518750 RDI: 0000000000000000 [ 285.407565] RBP: 00000000005205ef R08: 00000000005f8838 R09: 000000000000001c [ 285.408523] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000002517634 [ 285.409460] R13: 00007ffcc25fb6f0 R14: 0000000000000003 R15: 0000000000000000 [ 285.410403] [ 285.410704] [ 285.410929] Allocated by task 144: [ 285.411402] kasan_save_stack+0x1e/0x40 [ 285.411926] kasan_set_track+0x21/0x30 [ 285.412442] __kasan_slab_alloc+0x55/0x70 [ 285.412973] kmem_cache_alloc_node+0x187/0x3d0 [ 285.413567] __alloc_skb+0x1b4/0x230 [ 285.414060] __ip_append_data+0x17f7/0x1b60 [ 285.414633] ip_append_data+0x97/0xf0 [ 285.415144] raw_sendmsg+0x5a8/0x12d0 [ 285.415640] sock_sendmsg+0xcc/0xe0 [ 285.416117] __sys_sendto+0x190/0x230 [ 285.416626] __x64_sys_sendto+0x74/0x90 [ 285.417145] do_syscall_64+0x64/0x90 [ 285.417624] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.418306] [ 285.418531] Freed by task 144: [ 285.418960] kasan_save_stack+0x1e/0x40 [ 285.419469] kasan_set_track+0x21/0x30 [ 285.419988] kasan_save_free_info+0x27/0x40 [ 285.420556] ____kasan_slab_free+0x109/0x1a0 [ 285.421146] kmem_cache_free+0x1c2/0x450 [ 285.421680] __netif_receive_skb_core+0x2ce/0x1870 [ 285.422333] __netif_receive_skb_one_core+0x97/0x140 [ 285.423003] process_backlog+0x100/0x2f0 [ 285.423537] __napi_poll+0x5c/0x2d0 [ 285.424023] net_rx_action+0x2be/0x560 [ 285.424510] __do_softirq+0x11b/0x3de [ 285.425034] [ 285.425254] The buggy address belongs to the object at ffff8880bad31280 [ 285.425254] which belongs to the cache skbuff_head_cache of size 224 [ 285.426993] The buggy address is located 40 bytes inside of [ 285.426993] freed 224-byte region [ffff8880bad31280, ffff8880bad31360) [ 285.428572] [ 285.428798] The buggy address belongs to the physical page: [ 285.429540] page:00000000f4b77674 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbad31 [ 285.430758] flags: 0x100000000000200(slab|node=0|zone=1) [ 285.431447] page_type: 0xffffffff() [ 285.431934] raw: 0100000000000200 ffff88810094a8c0 dead000000000122 0000000000000000 [ 285.432757] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 [ 285.433562] page dumped because: kasan: bad access detected [ 285.434144] [ 285.434320] Memory state around the buggy address: [ 285.434828] ffff8880bad31180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.435580] ffff8880bad31200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.436264] >ffff8880bad31280: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 285.436777] ^ [ 285.437106] ffff8880bad31300: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 285.437616] ffff8880bad31380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.438126] ================================================================== [ 285.438662] Disabling lock debugging due to kernel taint Fix this by: 1. Changing sch_plug's .peek handler to qdisc_peek_dequeued(), a function compatible with non-work-conserving qdiscs 2. Checking the return value of qdisc_dequeue_peeked() in sch_qfq. Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Reported-by: valis Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230901162237.11525-1-jhs@mojatatu.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_plug.c | 2 +- net/sched/sch_qfq.c | 22 +++++++++++++++++----- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index ea8c4a7174bb..35f49edf63db 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -207,7 +207,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .priv_size = sizeof(struct plug_sched_data), .enqueue = plug_enqueue, .dequeue = plug_dequeue, - .peek = qdisc_peek_head, + .peek = qdisc_peek_dequeued, .init = plug_init, .change = plug_change, .reset = qdisc_reset_queue, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index e150d08f182d..ed01634af82c 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -973,10 +973,13 @@ static void qfq_update_eligible(struct qfq_sched *q) } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ -static void agg_dequeue(struct qfq_aggregate *agg, - struct qfq_class *cl, unsigned int len) +static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - qdisc_dequeue_peeked(cl->qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); + + if (!skb) + return NULL; cl->deficit -= (int) len; @@ -986,6 +989,8 @@ static void agg_dequeue(struct qfq_aggregate *agg, cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } + + return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, @@ -1131,11 +1136,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) if (!skb) return NULL; - qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + + skb = agg_dequeue(in_serv_agg, cl, len); + + if (!skb) { + sch->q.qlen++; + return NULL; + } + + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - agg_dequeue(in_serv_agg, cl, len); /* If lmax is lowered, through qfq_change_class, for a class * owning pending packets with larger size than the new value * of lmax, then the following condition may hold. From e30388b80d2356dc42a748aa33903b84ecd84ad7 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Sun, 3 Sep 2023 02:07:08 +0900 Subject: [PATCH 1392/2093] kcm: Destroy mutex in kcm_exit_net() [ Upstream commit 6ad40b36cd3b04209e2d6c89d252c873d8082a59 ] kcm_exit_net() should call mutex_destroy() on knet->mutex. This is especially needed if CONFIG_DEBUG_MUTEXES is enabled. Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Signed-off-by: Shigeru Yoshida Link: https://lore.kernel.org/r/20230902170708.1727999-1-syoshida@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/kcm/kcmsock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 890a2423f559..6a97662d7548 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1981,6 +1981,8 @@ static __net_exit void kcm_exit_net(struct net *net) * that all multiplexors and psocks have been destroyed. */ WARN_ON(!list_empty(&knet->mux_list)); + + mutex_destroy(&knet->mutex); } static struct pernet_operations kcm_net_ops = { From e2e2c839d827d80b9b55c6b44cc24ce846e5c490 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Tue, 5 Sep 2023 12:18:16 +0530 Subject: [PATCH 1393/2093] octeontx2-af: Fix truncation of smq in CN10K NIX AQ enqueue mbox handler [ Upstream commit 29fe7a1b62717d58f033009874554d99d71f7d37 ] The smq value used in the CN10K NIX AQ instruction enqueue mailbox handler was truncated to 9-bit value from 10-bit value because of typecasting the CN10K mbox request structure to the CN9K structure. Though this hasn't caused any problems when programming the NIX SQ context to the HW because the context structure is the same size. However, this causes a problem when accessing the structure parameters. This patch reads the right smq value for each platform. Fixes: 30077d210c83 ("octeontx2-af: cn10k: Update NIX/NPA context structure") Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../ethernet/marvell/octeontx2/af/rvu_nix.c | 21 +++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index c85e0180d96d..1f3a8cf42765 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -834,6 +834,21 @@ static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block, return 0; } +static void nix_get_aq_req_smq(struct rvu *rvu, struct nix_aq_enq_req *req, + u16 *smq, u16 *smq_mask) +{ + struct nix_cn10k_aq_enq_req *aq_req; + + if (!is_rvu_otx2(rvu)) { + aq_req = (struct nix_cn10k_aq_enq_req *)req; + *smq = aq_req->sq.smq; + *smq_mask = aq_req->sq_mask.smq; + } else { + *smq = req->sq.smq; + *smq_mask = req->sq_mask.smq; + } +} + static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, struct nix_aq_enq_req *req, struct nix_aq_enq_rsp *rsp) @@ -845,6 +860,7 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, struct rvu_block *block; struct admin_queue *aq; struct rvu_pfvf *pfvf; + u16 smq, smq_mask; void *ctx, *mask; bool ena; u64 cfg; @@ -916,13 +932,14 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, if (rc) return rc; + nix_get_aq_req_smq(rvu, req, &smq, &smq_mask); /* Check if SQ pointed SMQ belongs to this PF/VF or not */ if (req->ctype == NIX_AQ_CTYPE_SQ && ((req->op == NIX_AQ_INSTOP_INIT && req->sq.ena) || (req->op == NIX_AQ_INSTOP_WRITE && - req->sq_mask.ena && req->sq_mask.smq && req->sq.ena))) { + req->sq_mask.ena && req->sq.ena && smq_mask))) { if (!is_valid_txschq(rvu, blkaddr, NIX_TXSCH_LVL_SMQ, - pcifunc, req->sq.smq)) + pcifunc, smq)) return NIX_AF_ERR_AQ_ENQUEUE; } From 30acc4f954a0c838e2c02d939c1feda2fabf8cbd Mon Sep 17 00:00:00 2001 From: Olga Zaborska Date: Tue, 25 Jul 2023 10:10:56 +0200 Subject: [PATCH 1394/2093] igc: Change IGC_MIN to allow set rx/tx value between 64 and 80 [ Upstream commit 5aa48279712e1f134aac908acde4df798955a955 ] Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx value between 64 and 80. All igc devices can use as low as 64 descriptors. This change will unify igc with other drivers. Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64") Fixes: 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers") Signed-off-by: Olga Zaborska Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index f83cbc4a1afa..d3b17aa1d1a8 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -354,11 +354,11 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc) /* TX/RX descriptor defines */ #define IGC_DEFAULT_TXD 256 #define IGC_DEFAULT_TX_WORK 128 -#define IGC_MIN_TXD 80 +#define IGC_MIN_TXD 64 #define IGC_MAX_TXD 4096 #define IGC_DEFAULT_RXD 256 -#define IGC_MIN_RXD 80 +#define IGC_MIN_RXD 64 #define IGC_MAX_RXD 4096 /* Supported Rx Buffer Sizes */ From 74b98c61c9c687f9c7dc2157a8c56f2c3d0f9df0 Mon Sep 17 00:00:00 2001 From: Olga Zaborska Date: Tue, 25 Jul 2023 10:10:57 +0200 Subject: [PATCH 1395/2093] igbvf: Change IGBVF_MIN to allow set rx/tx value between 64 and 80 [ Upstream commit 8360717524a24a421c36ef8eb512406dbd42160a ] Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx value between 64 and 80. All igbvf devices can use as low as 64 descriptors. This change will unify igbvf with other drivers. Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64") Fixes: d4e0fe01a38a ("igbvf: add new driver to support 82576 virtual functions") Signed-off-by: Olga Zaborska Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igbvf/igbvf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index 57d39ee00b58..7b83678ba83a 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -39,11 +39,11 @@ enum latency_range { /* Tx/Rx descriptor defines */ #define IGBVF_DEFAULT_TXD 256 #define IGBVF_MAX_TXD 4096 -#define IGBVF_MIN_TXD 80 +#define IGBVF_MIN_TXD 64 #define IGBVF_DEFAULT_RXD 256 #define IGBVF_MAX_RXD 4096 -#define IGBVF_MIN_RXD 80 +#define IGBVF_MIN_RXD 64 #define IGBVF_MIN_ITR_USECS 10 /* 100000 irq/sec */ #define IGBVF_MAX_ITR_USECS 10000 /* 100 irq/sec */ From ccb048dae8ffc207d1992caec996dc987bf9fe47 Mon Sep 17 00:00:00 2001 From: Olga Zaborska Date: Tue, 25 Jul 2023 10:10:58 +0200 Subject: [PATCH 1396/2093] igb: Change IGB_MIN to allow set rx/tx value between 64 and 80 [ Upstream commit 6319685bdc8ad5310890add907b7c42f89302886 ] Change the minimum value of RX/TX descriptors to 64 to enable setting the rx/tx value between 64 and 80. All igb devices can use as low as 64 descriptors. This change will unify igb with other drivers. Based on commit 7b1be1987c1e ("e1000e: lower ring minimum size to 64") Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver") Signed-off-by: Olga Zaborska Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 015b78144114..a2b759531cb7 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -34,11 +34,11 @@ struct igb_adapter; /* TX/RX descriptor defines */ #define IGB_DEFAULT_TXD 256 #define IGB_DEFAULT_TX_WORK 128 -#define IGB_MIN_TXD 80 +#define IGB_MIN_TXD 64 #define IGB_MAX_TXD 4096 #define IGB_DEFAULT_RXD 256 -#define IGB_MIN_RXD 80 +#define IGB_MIN_RXD 64 #define IGB_MAX_RXD 4096 #define IGB_DEFAULT_ITR 3 /* dynamic */ From 147d8da33a2c2195ec63acd56cd7d80a3458c253 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 31 Aug 2023 13:59:59 +0300 Subject: [PATCH 1397/2093] s390/zcrypt: don't leak memory if dev_set_name() fails [ Upstream commit 6252f47b78031979ad919f971dc8468b893488bd ] When dev_set_name() fails, zcdn_create() doesn't free the newly allocated resources. Do it. Fixes: 00fab2350e6b ("s390/zcrypt: multiple zcrypt device nodes support") Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230831110000.24279-1-andriy.shevchenko@linux.intel.com Signed-off-by: Harald Freudenberger Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- drivers/s390/crypto/zcrypt_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index f94b43ce9a65..28e34d155334 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -441,6 +441,7 @@ static int zcdn_create(const char *name) ZCRYPT_NAME "_%d", (int)MINOR(devt)); nodename[sizeof(nodename) - 1] = '\0'; if (dev_set_name(&zcdndev->device, nodename)) { + kfree(zcdndev); rc = -EINVAL; goto unlockout; } From 175f290dc937052553d442d7983fcd50f9817fa3 Mon Sep 17 00:00:00 2001 From: Ariel Marcovitch Date: Sat, 26 Aug 2023 20:33:17 +0300 Subject: [PATCH 1398/2093] idr: fix param name in idr_alloc_cyclic() doc [ Upstream commit 2a15de80dd0f7e04a823291aa9eb49c5294f56af ] The relevant parameter is 'start' and not 'nextid' Fixes: 460488c58ca8 ("idr: Remove idr_alloc_ext") Signed-off-by: Ariel Marcovitch Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Sasha Levin --- lib/idr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/idr.c b/lib/idr.c index 7ecdfdb5309e..13f2758c2377 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(idr_alloc); * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * - * Allocates an unused ID in the range specified by @nextid and @end. If + * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * The search for an unused ID will start at the last ID allocated and will From 54b59bc18d195e560934ff183d4cc48b2deb019b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Sep 2023 13:40:46 +0000 Subject: [PATCH 1399/2093] ip_tunnels: use DEV_STATS_INC() [ Upstream commit 9b271ebaf9a2c5c566a54bc6cd915962e8241130 ] syzbot/KCSAN reported data-races in iptunnel_xmit_stats() [1] This can run from multiple cpus without mutual exclusion. Adopt SMP safe DEV_STATS_INC() to update dev->stats fields. [1] BUG: KCSAN: data-race in iptunnel_xmit / iptunnel_xmit read-write to 0xffff8881353df170 of 8 bytes by task 30263 on cpu 1: iptunnel_xmit_stats include/net/ip_tunnels.h:493 [inline] iptunnel_xmit+0x432/0x4a0 net/ipv4/ip_tunnel_core.c:87 ip_tunnel_xmit+0x1477/0x1750 net/ipv4/ip_tunnel.c:831 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:662 __netdev_start_xmit include/linux/netdevice.h:4889 [inline] netdev_start_xmit include/linux/netdevice.h:4903 [inline] xmit_one net/core/dev.c:3544 [inline] dev_hard_start_xmit+0x11b/0x3f0 net/core/dev.c:3560 __dev_queue_xmit+0xeee/0x1de0 net/core/dev.c:4340 dev_queue_xmit include/linux/netdevice.h:3082 [inline] __bpf_tx_skb net/core/filter.c:2129 [inline] __bpf_redirect_no_mac net/core/filter.c:2159 [inline] __bpf_redirect+0x723/0x9c0 net/core/filter.c:2182 ____bpf_clone_redirect net/core/filter.c:2453 [inline] bpf_clone_redirect+0x16c/0x1d0 net/core/filter.c:2425 ___bpf_prog_run+0xd7d/0x41e0 kernel/bpf/core.c:1954 __bpf_prog_run512+0x74/0xa0 kernel/bpf/core.c:2195 bpf_dispatcher_nop_func include/linux/bpf.h:1181 [inline] __bpf_prog_run include/linux/filter.h:609 [inline] bpf_prog_run include/linux/filter.h:616 [inline] bpf_test_run+0x15d/0x3d0 net/bpf/test_run.c:423 bpf_prog_test_run_skb+0x77b/0xa00 net/bpf/test_run.c:1045 bpf_prog_test_run+0x265/0x3d0 kernel/bpf/syscall.c:3996 __sys_bpf+0x3af/0x780 kernel/bpf/syscall.c:5353 __do_sys_bpf kernel/bpf/syscall.c:5439 [inline] __se_sys_bpf kernel/bpf/syscall.c:5437 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5437 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read-write to 0xffff8881353df170 of 8 bytes by task 30249 on cpu 0: iptunnel_xmit_stats include/net/ip_tunnels.h:493 [inline] iptunnel_xmit+0x432/0x4a0 net/ipv4/ip_tunnel_core.c:87 ip_tunnel_xmit+0x1477/0x1750 net/ipv4/ip_tunnel.c:831 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:662 __netdev_start_xmit include/linux/netdevice.h:4889 [inline] netdev_start_xmit include/linux/netdevice.h:4903 [inline] xmit_one net/core/dev.c:3544 [inline] dev_hard_start_xmit+0x11b/0x3f0 net/core/dev.c:3560 __dev_queue_xmit+0xeee/0x1de0 net/core/dev.c:4340 dev_queue_xmit include/linux/netdevice.h:3082 [inline] __bpf_tx_skb net/core/filter.c:2129 [inline] __bpf_redirect_no_mac net/core/filter.c:2159 [inline] __bpf_redirect+0x723/0x9c0 net/core/filter.c:2182 ____bpf_clone_redirect net/core/filter.c:2453 [inline] bpf_clone_redirect+0x16c/0x1d0 net/core/filter.c:2425 ___bpf_prog_run+0xd7d/0x41e0 kernel/bpf/core.c:1954 __bpf_prog_run512+0x74/0xa0 kernel/bpf/core.c:2195 bpf_dispatcher_nop_func include/linux/bpf.h:1181 [inline] __bpf_prog_run include/linux/filter.h:609 [inline] bpf_prog_run include/linux/filter.h:616 [inline] bpf_test_run+0x15d/0x3d0 net/bpf/test_run.c:423 bpf_prog_test_run_skb+0x77b/0xa00 net/bpf/test_run.c:1045 bpf_prog_test_run+0x265/0x3d0 kernel/bpf/syscall.c:3996 __sys_bpf+0x3af/0x780 kernel/bpf/syscall.c:5353 __do_sys_bpf kernel/bpf/syscall.c:5439 [inline] __se_sys_bpf kernel/bpf/syscall.c:5437 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5437 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x0000000000018830 -> 0x0000000000018831 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 30249 Comm: syz-executor.4 Not tainted 6.5.0-syzkaller-11704-g3f86ed6ec0b3 #0 Fixes: 039f50629b7f ("ip_tunnel: Move stats update to iptunnel_xmit()") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/ip_tunnels.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index fca357679816..bca80522f95c 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -473,15 +473,14 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) u64_stats_inc(&tstats->tx_packets); u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); - } else { - struct net_device_stats *err_stats = &dev->stats; + return; + } - if (pkt_len < 0) { - err_stats->tx_errors++; - err_stats->tx_aborted_errors++; - } else { - err_stats->tx_dropped++; - } + if (pkt_len < 0) { + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_aborted_errors); + } else { + DEV_STATS_INC(dev, tx_dropped); } } From 483f0e3975df282899b20bf71b1041f0982416eb Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 6 Sep 2023 00:53:36 +0300 Subject: [PATCH 1400/2093] net: dsa: sja1105: fix bandwidth discrepancy between tc-cbs software and offload [ Upstream commit 954ad9bf13c4f95a4958b5f8433301f2ab99e1f5 ] More careful measurement of the tc-cbs bandwidth shows that the stream bandwidth (effectively idleslope) increases, there is a larger and larger discrepancy between the rate limit obtained by the software Qdisc, and the rate limit obtained by its offloaded counterpart. The discrepancy becomes so large, that e.g. at an idleslope of 40000 (40Mbps), the offloaded cbs does not actually rate limit anything, and traffic will pass at line rate through a 100 Mbps port. The reason for the discrepancy is that the hardware documentation I've been following is incorrect. UM11040.pdf (for SJA1105P/Q/R/S) states about IDLE_SLOPE that it is "the rate (in unit of bytes/sec) at which the credit counter is increased". Cross-checking with UM10944.pdf (for SJA1105E/T) and UM11107.pdf (for SJA1110), the wording is different: "This field specifies the value, in bytes per second times link speed, by which the credit counter is increased". So there's an extra scaling for link speed that the driver is currently not accounting for, and apparently (empirically), that link speed is expressed in Kbps. I've pondered whether to pollute the sja1105_mac_link_up() implementation with CBS shaper reprogramming, but I don't think it is worth it. IMO, the UAPI exposed by tc-cbs requires user space to recalculate the sendslope anyway, since the formula for that depends on port_transmit_rate (see man tc-cbs), which is not an invariant from tc's perspective. So we use the offload->sendslope and offload->idleslope to deduce the original port_transmit_rate from the CBS formula, and use that value to scale the offload->sendslope and offload->idleslope to values that the hardware understands. Some numerical data points: 40Mbps stream, max interfering frame size 1500, port speed 100M --------------------------------------------------------------- tc-cbs parameters: idleslope 40000 sendslope -60000 locredit -900 hicredit 600 which result in hardware values: Before (doesn't work) After (works) credit_hi 600 600 credit_lo 900 900 send_slope 7500000 75 idle_slope 5000000 50 40Mbps stream, max interfering frame size 1500, port speed 1G ------------------------------------------------------------- tc-cbs parameters: idleslope 40000 sendslope -960000 locredit -1440 hicredit 60 which result in hardware values: Before (doesn't work) After (works) credit_hi 60 60 credit_lo 1440 1440 send_slope 120000000 120 idle_slope 5000000 5 5.12Mbps stream, max interfering frame size 1522, port speed 100M ----------------------------------------------------------------- tc-cbs parameters: idleslope 5120 sendslope -94880 locredit -1444 hicredit 77 which result in hardware values: Before (doesn't work) After (works) credit_hi 77 77 credit_lo 1444 1444 send_slope 11860000 118 idle_slope 640000 6 Tested on SJA1105T, SJA1105S and SJA1110A, at 1Gbps and 100Mbps. Fixes: 4d7525085a9b ("net: dsa: sja1105: offload the Credit-Based Shaper qdisc") Reported-by: Yanan Yang Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105_main.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 947e8f7c0988..377f17750200 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2157,6 +2157,7 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port, { struct sja1105_private *priv = ds->priv; struct sja1105_cbs_entry *cbs; + s64 port_transmit_rate_kbps; int index; if (!offload->enable) @@ -2174,9 +2175,17 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port, */ cbs->credit_hi = offload->hicredit; cbs->credit_lo = abs(offload->locredit); - /* User space is in kbits/sec, hardware in bytes/sec */ - cbs->idle_slope = offload->idleslope * BYTES_PER_KBIT; - cbs->send_slope = abs(offload->sendslope * BYTES_PER_KBIT); + /* User space is in kbits/sec, while the hardware in bytes/sec times + * link speed. Since the given offload->sendslope is good only for the + * current link speed anyway, and user space is likely to reprogram it + * when that changes, don't even bother to track the port's link speed, + * but deduce the port transmit rate from idleslope - sendslope. + */ + port_transmit_rate_kbps = offload->idleslope - offload->sendslope; + cbs->idle_slope = div_s64(offload->idleslope * BYTES_PER_KBIT, + port_transmit_rate_kbps); + cbs->send_slope = div_s64(abs(offload->sendslope * BYTES_PER_KBIT), + port_transmit_rate_kbps); /* Convert the negative values from 64-bit 2's complement * to 32-bit 2's complement (for the case of 0x80000000 whose * negative is still negative). From ec9f203ad7f3c7f20f3a662f39a58fdf5c8ef74b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 6 Sep 2023 00:53:37 +0300 Subject: [PATCH 1401/2093] net: dsa: sja1105: fix -ENOSPC when replacing the same tc-cbs too many times [ Upstream commit 894cafc5c62ccced758077bd4e970dc714c42637 ] After running command [2] too many times in a row: [1] $ tc qdisc add dev sw2p0 root handle 1: mqprio num_tc 8 \ map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 hw 0 [2] $ tc qdisc replace dev sw2p0 parent 1:1 cbs offload 1 \ idleslope 120000 sendslope -880000 locredit -1320 hicredit 180 (aka more than priv->info->num_cbs_shapers times) we start seeing the following error message: Error: Specified device failed to setup cbs hardware offload. This comes from the fact that ndo_setup_tc(TC_SETUP_QDISC_CBS) presents the same API for the qdisc create and replace cases, and the sja1105 driver fails to distinguish between the 2. Thus, it always thinks that it must allocate the same shaper for a {port, queue} pair, when it may instead have to replace an existing one. Fixes: 4d7525085a9b ("net: dsa: sja1105: offload the Credit-Based Shaper qdisc") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105_main.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 377f17750200..9dd5cdcda284 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2123,6 +2123,18 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port, #define BYTES_PER_KBIT (1000LL / 8) +static int sja1105_find_cbs_shaper(struct sja1105_private *priv, + int port, int prio) +{ + int i; + + for (i = 0; i < priv->info->num_cbs_shapers; i++) + if (priv->cbs[i].port == port && priv->cbs[i].prio == prio) + return i; + + return -1; +} + static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv) { int i; @@ -2163,9 +2175,14 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port, if (!offload->enable) return sja1105_delete_cbs_shaper(priv, port, offload->queue); - index = sja1105_find_unused_cbs_shaper(priv); - if (index < 0) - return -ENOSPC; + /* The user may be replacing an existing shaper */ + index = sja1105_find_cbs_shaper(priv, port, offload->queue); + if (index < 0) { + /* That isn't the case - see if we can allocate a new one */ + index = sja1105_find_unused_cbs_shaper(priv); + if (index < 0) + return -ENOSPC; + } cbs = &priv->cbs[index]; cbs->port = port; From 5f09b79e99adba6eae268d58baefffbc6d6e317c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 6 Sep 2023 00:53:38 +0300 Subject: [PATCH 1402/2093] net: dsa: sja1105: complete tc-cbs offload support on SJA1110 [ Upstream commit 180a7419fe4adc8d9c8e0ef0fd17bcdd0cf78acd ] The blamed commit left this delta behind: struct sja1105_cbs_entry { - u64 port; - u64 prio; + u64 port; /* Not used for SJA1110 */ + u64 prio; /* Not used for SJA1110 */ u64 credit_hi; u64 credit_lo; u64 send_slope; u64 idle_slope; }; but did not actually implement tc-cbs offload fully for the new switch. The offload is accepted, but it doesn't work. The difference compared to earlier switch generations is that now, the table of CBS shapers is sparse, because there are many more shapers, so the mapping between a {port, prio} and a table index is static, rather than requiring us to store the port and prio into the sja1105_cbs_entry. So, the problem is that the code programs the CBS shaper parameters at a dynamic table index which is incorrect. All that needs to be done for SJA1110 CBS shapers to work is to bypass the logic which allocates shapers in a dense manner, as for SJA1105, and use the fixed mapping instead. Fixes: 3e77e59bf8cf ("net: dsa: sja1105: add support for the SJA1110 switch family") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105.h | 2 ++ drivers/net/dsa/sja1105/sja1105_main.c | 13 +++++++++++++ drivers/net/dsa/sja1105/sja1105_spi.c | 4 ++++ 3 files changed, 19 insertions(+) diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index fb3cd4c78faa..a831bb0a5207 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -132,6 +132,8 @@ struct sja1105_info { int max_frame_mem; int num_ports; bool multiple_cascade_ports; + /* Every {port, TXQ} has its own CBS shaper */ + bool fixed_cbs_mapping; enum dsa_tag_protocol tag_proto; const struct sja1105_dynamic_table_ops *dyn_ops; const struct sja1105_table_ops *static_ops; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 9dd5cdcda284..ff94c5996faf 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2122,12 +2122,22 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port, } #define BYTES_PER_KBIT (1000LL / 8) +/* Port 0 (the uC port) does not have CBS shapers */ +#define SJA1110_FIXED_CBS(port, prio) ((((port) - 1) * SJA1105_NUM_TC) + (prio)) static int sja1105_find_cbs_shaper(struct sja1105_private *priv, int port, int prio) { int i; + if (priv->info->fixed_cbs_mapping) { + i = SJA1110_FIXED_CBS(port, prio); + if (i >= 0 && i < priv->info->num_cbs_shapers) + return i; + + return -1; + } + for (i = 0; i < priv->info->num_cbs_shapers; i++) if (priv->cbs[i].port == port && priv->cbs[i].prio == prio) return i; @@ -2139,6 +2149,9 @@ static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv) { int i; + if (priv->info->fixed_cbs_mapping) + return -1; + for (i = 0; i < priv->info->num_cbs_shapers; i++) if (!priv->cbs[i].idle_slope && !priv->cbs[i].send_slope) return i; diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index d3c9ad6d39d4..e6b61aef4127 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -781,6 +781,7 @@ const struct sja1105_info sja1110a_info = { .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, + .fixed_cbs_mapping = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -831,6 +832,7 @@ const struct sja1105_info sja1110b_info = { .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, + .fixed_cbs_mapping = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -881,6 +883,7 @@ const struct sja1105_info sja1110c_info = { .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, + .fixed_cbs_mapping = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -931,6 +934,7 @@ const struct sja1105_info sja1110d_info = { .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, + .fixed_cbs_mapping = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, From a12f15d1f863c8231c03d6922e182341e6768cfc Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 25 Oct 2022 11:45:16 -0700 Subject: [PATCH 1403/2093] bpf: Remove prog->active check for bpf_lsm and bpf_iter [ Upstream commit 271de525e1d7f564e88a9d212c50998b49a54476 ] The commit 64696c40d03c ("bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline") removed prog->active check for struct_ops prog. The bpf_lsm and bpf_iter is also using trampoline. Like struct_ops, the bpf_lsm and bpf_iter have fixed hooks for the prog to attach. The kernel does not call the same hook in a recursive way. This patch also removes the prog->active check for bpf_lsm and bpf_iter. A later patch has a test to reproduce the recursion issue for a sleepable bpf_lsm program. This patch appends the '_recur' naming to the existing enter and exit functions that track the prog->active counter. New __bpf_prog_{enter,exit}[_sleepable] function are added to skip the prog->active tracking. The '_struct_ops' version is also removed. It also moves the decision on picking the enter and exit function to the new bpf_trampoline_{enter,exit}(). It returns the '_recur' ones for all tracing progs to use. For bpf_lsm, bpf_iter, struct_ops (no prog->active tracking after 64696c40d03c), and bpf_lsm_cgroup (no prog->active tracking after 69fd337a975c7), it will return the functions that don't track the prog->active. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20221025184524.3526117-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov Stable-dep-of: 7645629f7dc8 ("bpf: Invoke __bpf_prog_exit_sleepable_recur() on recursion in kern_sys_bpf().") Signed-off-by: Sasha Levin --- arch/arm64/net/bpf_jit_comp.c | 9 +--- arch/x86/net/bpf_jit_comp.c | 19 +-------- include/linux/bpf.h | 24 +++++------ include/linux/bpf_verifier.h | 13 ++++++ kernel/bpf/syscall.c | 5 ++- kernel/bpf/trampoline.c | 80 +++++++++++++++++++++++++++++------ 6 files changed, 97 insertions(+), 53 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 14134fd34ff7..0ce5f13eabb1 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1655,13 +1655,8 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, struct bpf_prog *p = l->link.prog; int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); - if (p->aux->sleepable) { - enter_prog = (u64)__bpf_prog_enter_sleepable; - exit_prog = (u64)__bpf_prog_exit_sleepable; - } else { - enter_prog = (u64)__bpf_prog_enter; - exit_prog = (u64)__bpf_prog_exit; - } + enter_prog = (u64)bpf_trampoline_enter(p); + exit_prog = (u64)bpf_trampoline_exit(p); if (l->cookie == 0) { /* if cookie is zero, one instruction is enough to store it */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index db6053a22e86..5e680e039d0e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1813,10 +1813,6 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, int run_ctx_off, bool save_ret) { - void (*exit)(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit; - u64 (*enter)(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter; u8 *prog = *pprog; u8 *jmp_insn; int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); @@ -1835,23 +1831,12 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off); - if (p->aux->sleepable) { - enter = __bpf_prog_enter_sleepable; - exit = __bpf_prog_exit_sleepable; - } else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) { - enter = __bpf_prog_enter_struct_ops; - exit = __bpf_prog_exit_struct_ops; - } else if (p->expected_attach_type == BPF_LSM_CGROUP) { - enter = __bpf_prog_enter_lsm_cgroup; - exit = __bpf_prog_exit_lsm_cgroup; - } - /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: lea rsi, [rbp - ctx_cookie_off] */ EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_call(&prog, enter, prog)) + if (emit_call(&prog, bpf_trampoline_enter(p), prog)) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -1896,7 +1881,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); /* arg3: lea rdx, [rbp - run_ctx_off] */ EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_call(&prog, exit, prog)) + if (emit_call(&prog, bpf_trampoline_exit(p), prog)) return -EINVAL; *pprog = prog; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8cef9ec3a89c..b3d3aa8437dc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -862,22 +862,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *orig_call); -/* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx); -u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx); -u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); +typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); +bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog); +bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog); struct bpf_ksym { unsigned long start; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 0eb8f035b3d9..1a32baa78ce2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -648,4 +648,17 @@ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) prog->aux->dst_prog->type : prog->type; } +static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) +{ + switch (resolve_prog_type(prog)) { + case BPF_PROG_TYPE_TRACING: + return prog->expected_attach_type != BPF_TRACE_ITER; + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_LSM: + return false; + default: + return true; + } +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0c44a716f0a2..7afec961c572 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5136,13 +5136,14 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) run_ctx.bpf_cookie = 0; run_ctx.saved_run_ctx = NULL; - if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) { + if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); - __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); + __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, + &run_ctx); bpf_prog_put(prog); return 0; #endif diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 30af8f66e17b..88841e352dcd 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -874,7 +874,7 @@ static __always_inline u64 notrace bpf_prog_start_time(void) * [2..MAX_U64] - execute bpf prog and record execution time. * This is start time. */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) +static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { rcu_read_lock(); @@ -911,7 +911,8 @@ static void notrace update_prog_stats(struct bpf_prog *prog, } } -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx) +static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -922,8 +923,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_ rcu_read_unlock(); } -u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) +static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { /* Runtime stats are exported via actual BPF_LSM_CGROUP @@ -937,8 +938,8 @@ u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, return NO_START_TIME; } -void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) +static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -947,7 +948,8 @@ void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, rcu_read_unlock(); } -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) +u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) { rcu_read_lock_trace(); migrate_disable(); @@ -963,8 +965,8 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_r return bpf_prog_start_time(); } -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) +void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -974,8 +976,30 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, rcu_read_unlock_trace(); } -u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) +static u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) +{ + rcu_read_lock_trace(); + migrate_disable(); + might_fault(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + + return bpf_prog_start_time(); +} + +static void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + update_prog_stats(prog, start); + migrate_enable(); + rcu_read_unlock_trace(); +} + +static u64 notrace __bpf_prog_enter(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { rcu_read_lock(); @@ -986,8 +1010,8 @@ u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, return bpf_prog_start_time(); } -void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) +static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -1007,6 +1031,36 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) percpu_ref_put(&tr->pcref); } +bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) +{ + bool sleepable = prog->aux->sleepable; + + if (bpf_prog_check_recur(prog)) + return sleepable ? __bpf_prog_enter_sleepable_recur : + __bpf_prog_enter_recur; + + if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_CGROUP) + return __bpf_prog_enter_lsm_cgroup; + + return sleepable ? __bpf_prog_enter_sleepable : __bpf_prog_enter; +} + +bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) +{ + bool sleepable = prog->aux->sleepable; + + if (bpf_prog_check_recur(prog)) + return sleepable ? __bpf_prog_exit_sleepable_recur : + __bpf_prog_exit_recur; + + if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_CGROUP) + return __bpf_prog_exit_lsm_cgroup; + + return sleepable ? __bpf_prog_exit_sleepable : __bpf_prog_exit; +} + int __weak arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, From 04f92e67b35d3c5c0f6e1bf5cd883a04dbadac56 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 30 Aug 2023 10:04:04 +0200 Subject: [PATCH 1404/2093] bpf: Invoke __bpf_prog_exit_sleepable_recur() on recursion in kern_sys_bpf(). [ Upstream commit 7645629f7dc88cd777f98970134bf1a54c8d77e3 ] If __bpf_prog_enter_sleepable_recur() detects recursion then it returns 0 without undoing rcu_read_lock_trace(), migrate_disable() or decrementing the recursion counter. This is fine in the JIT case because the JIT code will jump in the 0 case to the end and invoke the matching exit trampoline (__bpf_prog_exit_sleepable_recur()). This is not the case in kern_sys_bpf() which returns directly to the caller with an error code. Add __bpf_prog_exit_sleepable_recur() as clean up in the recursion case. Fixes: b1d18a7574d0d ("bpf: Extend sys_bpf commands for bpf_syscall programs.") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230830080405.251926-2-bigeasy@linutronix.de Signed-off-by: Sasha Levin --- kernel/bpf/syscall.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7afec961c572..76484137233a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5138,6 +5138,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) run_ctx.saved_run_ctx = NULL; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ + __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); bpf_prog_put(prog); return -EBUSY; } From 6cf0d1d5a50b635a59f252f168e7aa50c1ffe636 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 30 Aug 2023 10:04:05 +0200 Subject: [PATCH 1405/2093] bpf: Assign bpf_tramp_run_ctx::saved_run_ctx before recursion check. [ Upstream commit 6764e767f4af1e35f87f3497e1182d945de37f93 ] __bpf_prog_enter_recur() assigns bpf_tramp_run_ctx::saved_run_ctx before performing the recursion check which means in case of a recursion __bpf_prog_exit_recur() uses the previously set bpf_tramp_run_ctx::saved_run_ctx value. __bpf_prog_enter_sleepable_recur() assigns bpf_tramp_run_ctx::saved_run_ctx after the recursion check which means in case of a recursion __bpf_prog_exit_sleepable_recur() uses an uninitialized value. This does not look right. If I read the entry trampoline code right, then bpf_tramp_run_ctx isn't initialized upfront. Align __bpf_prog_enter_sleepable_recur() with __bpf_prog_enter_recur() and set bpf_tramp_run_ctx::saved_run_ctx before the recursion check is made. Remove the assignment of saved_run_ctx in kern_sys_bpf() since it happens a few cycles later. Fixes: e384c7b7b46d0 ("bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20230830080405.251926-3-bigeasy@linutronix.de Signed-off-by: Sasha Levin --- kernel/bpf/syscall.c | 1 - kernel/bpf/trampoline.c | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 76484137233a..0c8b7733573e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5135,7 +5135,6 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) } run_ctx.bpf_cookie = 0; - run_ctx.saved_run_ctx = NULL; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 88841e352dcd..c4381dfcd6b0 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -955,13 +955,12 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, migrate_disable(); might_fault(); + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); return 0; } - - run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); - return bpf_prog_start_time(); } From d9ebfc0f21377690837ebbd119e679243e0099cc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 5 Sep 2023 23:13:56 +0200 Subject: [PATCH 1406/2093] netfilter: nftables: exthdr: fix 4-byte stack OOB write [ Upstream commit fd94d9dadee58e09b49075240fe83423eb1dcd36 ] If priv->len is a multiple of 4, then dst[len / 4] can write past the destination array which leads to stack corruption. This construct is necessary to clean the remainder of the register in case ->len is NOT a multiple of the register size, so make it conditional just like nft_payload.c does. The bug was added in 4.1 cycle and then copied/inherited when tcp/sctp and ip option support was added. Bug reported by Zero Day Initiative project (ZDI-CAN-21950, ZDI-CAN-21951, ZDI-CAN-21961). Fixes: 49499c3e6e18 ("netfilter: nf_tables: switch registers to 32 bit addressing") Fixes: 935b7f643018 ("netfilter: nft_exthdr: add TCP option matching") Fixes: 133dc203d77d ("netfilter: nft_exthdr: Support SCTP chunks") Fixes: dbb5281a1f84 ("netfilter: nf_tables: add support for matching IPv4 options") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_exthdr.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index c307c57a93e5..efb50c2b41f3 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -35,6 +35,14 @@ static unsigned int optlen(const u8 *opt, unsigned int offset) return opt[offset + 1]; } +static int nft_skb_copy_to_reg(const struct sk_buff *skb, int offset, u32 *dest, unsigned int len) +{ + if (len % NFT_REG32_SIZE) + dest[len / NFT_REG32_SIZE] = 0; + + return skb_copy_bits(skb, offset, dest, len); +} + static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -56,8 +64,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, } offset += priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; - if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0) + if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0) goto err; return; err: @@ -153,8 +160,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, } offset += priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; - if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0) + if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0) goto err; return; err: @@ -210,7 +216,8 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, if (priv->flags & NFT_EXTHDR_F_PRESENT) { *dest = 1; } else { - dest[priv->len / NFT_REG32_SIZE] = 0; + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; memcpy(dest, opt + offset, priv->len); } @@ -388,9 +395,8 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr, offset + ntohs(sch->length) > pkt->skb->len) break; - dest[priv->len / NFT_REG32_SIZE] = 0; - if (skb_copy_bits(pkt->skb, offset + priv->offset, - dest, priv->len) < 0) + if (nft_skb_copy_to_reg(pkt->skb, offset + priv->offset, + dest, priv->len) < 0) break; return; } From 7bb8d52b4271be7527b6e3120ae6ce4c6cdf6e34 Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Fri, 1 Sep 2023 10:50:20 -0300 Subject: [PATCH 1407/2093] netfilter: nfnetlink_osf: avoid OOB read [ Upstream commit f4f8a7803119005e87b716874bec07c751efafec ] The opt_num field is controlled by user mode and is not currently validated inside the kernel. An attacker can take advantage of this to trigger an OOB read and potentially leak information. BUG: KASAN: slab-out-of-bounds in nf_osf_match_one+0xbed/0xd10 net/netfilter/nfnetlink_osf.c:88 Read of size 2 at addr ffff88804bc64272 by task poc/6431 CPU: 1 PID: 6431 Comm: poc Not tainted 6.0.0-rc4 #1 Call Trace: nf_osf_match_one+0xbed/0xd10 net/netfilter/nfnetlink_osf.c:88 nf_osf_find+0x186/0x2f0 net/netfilter/nfnetlink_osf.c:281 nft_osf_eval+0x37f/0x590 net/netfilter/nft_osf.c:47 expr_call_ops_eval net/netfilter/nf_tables_core.c:214 nft_do_chain+0x2b0/0x1490 net/netfilter/nf_tables_core.c:264 nft_do_chain_ipv4+0x17c/0x1f0 net/netfilter/nft_chain_filter.c:23 [..] Also add validation to genre, subtype and version fields. Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match") Reported-by: Lucas Leong Signed-off-by: Wander Lairson Costa Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nfnetlink_osf.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 8f1bfa6ccc2d..50723ba08289 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -315,6 +315,14 @@ static int nfnl_osf_add_callback(struct sk_buff *skb, f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + if (f->opt_num > ARRAY_SIZE(f->opt)) + return -EINVAL; + + if (!memchr(f->genre, 0, MAXGENRELEN) || + !memchr(f->subtype, 0, MAXGENRELEN) || + !memchr(f->version, 0, MAXGENRELEN)) + return -EINVAL; + kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL); if (!kf) return -ENOMEM; From 5c28780f4232626409eaccde4b48f2f99294261b Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 6 Sep 2023 15:20:12 +0800 Subject: [PATCH 1408/2093] net: hns3: fix tx timeout issue [ Upstream commit 61a1deacc3d4fd3d57d7fda4d935f7f7503e8440 ] Currently, the driver knocks the ring doorbell before updating the ring->last_to_use in tx flow. if the hardware transmiting packet and napi poll scheduling are fast enough, it may get the old ring->last_to_use in drivers' napi poll. In this case, the driver will think the tx is not completed, and return directly without clear the flag __QUEUE_STATE_STACK_XOFF, which may cause tx timeout. Fixes: 20d06ca2679c ("net: hns3: optimize the tx clean process") Signed-off-by: Jian Shen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 61f833d61f58..9942b21cd619 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2102,8 +2102,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, */ if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num && !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) { + /* This smp_store_release() pairs with smp_load_aquire() in + * hns3_nic_reclaim_desc(). Ensure that the BD valid bit + * is updated. + */ + smp_store_release(&ring->last_to_use, ring->next_to_use); hns3_tx_push_bd(ring, num); - WRITE_ONCE(ring->last_to_use, ring->next_to_use); return; } @@ -2114,6 +2118,11 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, return; } + /* This smp_store_release() pairs with smp_load_aquire() in + * hns3_nic_reclaim_desc(). Ensure that the BD valid bit is updated. + */ + smp_store_release(&ring->last_to_use, ring->next_to_use); + if (ring->tqp->mem_base) hns3_tx_mem_doorbell(ring); else @@ -2121,7 +2130,6 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG); ring->pending_buf = 0; - WRITE_ONCE(ring->last_to_use, ring->next_to_use); } static void hns3_tsyn(struct net_device *netdev, struct sk_buff *skb, @@ -3562,9 +3570,8 @@ static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i) static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring, int *bytes, int *pkts, int budget) { - /* pair with ring->last_to_use update in hns3_tx_doorbell(), - * smp_store_release() is not used in hns3_tx_doorbell() because - * the doorbell operation already have the needed barrier operation. + /* This smp_load_acquire() pairs with smp_store_release() in + * hns3_tx_doorbell(). */ int ltu = smp_load_acquire(&ring->last_to_use); int ntc = ring->next_to_clean; From b5087697130aff8b25b7b237586f96e65a306272 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Wed, 6 Sep 2023 15:20:14 +0800 Subject: [PATCH 1409/2093] net: hns3: fix byte order conversion issue in hclge_dbg_fd_tcam_read() [ Upstream commit efccf655e99b6907ca07a466924e91805892e7d3 ] req1->tcam_data is defined as "u8 tcam_data[8]", and we convert it as (u32 *) without considerring byte order conversion, it may result in printing wrong data for tcam_data. Convert tcam_data to (__le32 *) first to fix it. Fixes: b5a0b70d77b9 ("net: hns3: refactor dump fd tcam of debugfs") Signed-off-by: Hao Chen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- .../ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 5cb8f1818e51..a1c59f4aae98 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -1517,7 +1517,7 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x, struct hclge_desc desc[3]; int pos = 0; int ret, i; - u32 *req; + __le32 *req; hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, true); desc[0].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT); @@ -1542,22 +1542,22 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x, tcam_msg.loc); /* tcam_data0 ~ tcam_data1 */ - req = (u32 *)req1->tcam_data; + req = (__le32 *)req1->tcam_data; for (i = 0; i < 2; i++) pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, - "%08x\n", *req++); + "%08x\n", le32_to_cpu(*req++)); /* tcam_data2 ~ tcam_data7 */ - req = (u32 *)req2->tcam_data; + req = (__le32 *)req2->tcam_data; for (i = 0; i < 6; i++) pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, - "%08x\n", *req++); + "%08x\n", le32_to_cpu(*req++)); /* tcam_data8 ~ tcam_data12 */ - req = (u32 *)req3->tcam_data; + req = (__le32 *)req3->tcam_data; for (i = 0; i < 5; i++) pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, - "%08x\n", *req++); + "%08x\n", le32_to_cpu(*req++)); return ret; } From d76436e26943c632062555925c4de3bfcdeff97c Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Wed, 6 Sep 2023 15:20:15 +0800 Subject: [PATCH 1410/2093] net: hns3: fix debugfs concurrency issue between kfree buffer and read [ Upstream commit c295160b1d95e885f1af4586a221cb221d232d10 ] Now in hns3_dbg_uninit(), there may be concurrency between kfree buffer and read, it may result in memory error. Moving debugfs_remove_recursive() in front of kfree buffer to ensure they don't happen at the same time. Fixes: 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process") Signed-off-by: Hao Chen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 69d1549e63a9..00eed9835cb5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1406,9 +1406,9 @@ int hns3_dbg_init(struct hnae3_handle *handle) return 0; out: - mutex_destroy(&handle->dbgfs_lock); debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; + mutex_destroy(&handle->dbgfs_lock); return ret; } @@ -1416,6 +1416,9 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) { u32 i; + debugfs_remove_recursive(handle->hnae3_dbgfs); + handle->hnae3_dbgfs = NULL; + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) if (handle->dbgfs_buf[i]) { kvfree(handle->dbgfs_buf[i]); @@ -1423,8 +1426,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) } mutex_destroy(&handle->dbgfs_lock); - debugfs_remove_recursive(handle->hnae3_dbgfs); - handle->hnae3_dbgfs = NULL; } void hns3_dbg_register_debugfs(const char *debugfs_dir_name) From 9bd9afd55c523670fac649b393288d0430419c26 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Wed, 6 Sep 2023 15:20:16 +0800 Subject: [PATCH 1411/2093] net: hns3: fix invalid mutex between tc qdisc and dcb ets command issue [ Upstream commit fa5564945f7d15ae2390b00c08b6abaef0165cda ] We hope that tc qdisc and dcb ets commands can not be used crosswise. If we want to use any of the commands to configure tc, We must use the other command to clear the existing configuration. However, when we configure a single tc with tc qdisc, we can still configure it with dcb ets. Because we use mqprio_active as the tag of tc qdisc configuration, but with dcb ets, we do not check mqprio_active. This patch fix this issue by check mqprio_active before executing the dcb ets command. and add dcb_ets_active to replace HCLGE_FLAG_DCB_ENABLE and HCLGE_FLAG_MQPRIO_ENABLE at the hclge layer, Fixes: cacde272dd00 ("net: hns3: Add hclge_dcb module for the support of DCB feature") Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 + .../hisilicon/hns3/hns3pf/hclge_dcb.c | 20 +++++-------------- .../hisilicon/hns3/hns3pf/hclge_main.c | 5 +++-- .../hisilicon/hns3/hns3pf/hclge_main.h | 2 -- 4 files changed, 9 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index fcb8b6dc5ab9..c693bb701ba3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -797,6 +797,7 @@ struct hnae3_tc_info { u8 max_tc; /* Total number of TCs */ u8 num_tc; /* Total number of enabled TCs */ bool mqprio_active; + bool dcb_ets_active; }; #define HNAE3_MAX_DSCP 64 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 09362823140d..2740f0d703e4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -251,7 +251,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) int ret; if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || - hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) + h->kinfo.tc_info.mqprio_active) return -EINVAL; ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed); @@ -267,10 +267,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) } hclge_tm_schd_info_update(hdev, num_tc); - if (num_tc > 1) - hdev->flag |= HCLGE_FLAG_DCB_ENABLE; - else - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; + h->kinfo.tc_info.dcb_ets_active = num_tc > 1; ret = hclge_ieee_ets_to_tm_info(hdev, ets); if (ret) @@ -463,7 +460,7 @@ static u8 hclge_getdcbx(struct hnae3_handle *h) struct hclge_vport *vport = hclge_get_vport(h); struct hclge_dev *hdev = vport->back; - if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) + if (h->kinfo.tc_info.mqprio_active) return 0; return hdev->dcbx_cap; @@ -587,7 +584,8 @@ static int hclge_setup_tc(struct hnae3_handle *h, if (!test_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state)) return -EBUSY; - if (hdev->flag & HCLGE_FLAG_DCB_ENABLE) + kinfo = &vport->nic.kinfo; + if (kinfo->tc_info.dcb_ets_active) return -EINVAL; ret = hclge_mqprio_qopt_check(hdev, mqprio_qopt); @@ -601,7 +599,6 @@ static int hclge_setup_tc(struct hnae3_handle *h, if (ret) return ret; - kinfo = &vport->nic.kinfo; memcpy(&old_tc_info, &kinfo->tc_info, sizeof(old_tc_info)); hclge_sync_mqprio_qopt(&kinfo->tc_info, mqprio_qopt); kinfo->tc_info.mqprio_active = tc > 0; @@ -610,13 +607,6 @@ static int hclge_setup_tc(struct hnae3_handle *h, if (ret) goto err_out; - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; - - if (tc > 1) - hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE; - else - hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE; - return hclge_notify_init_up(hdev); err_out: diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 84ecd8b9be48..884e45fb6b72 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -11132,6 +11132,7 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle, static void hclge_info_show(struct hclge_dev *hdev) { + struct hnae3_handle *handle = &hdev->vport->nic; struct device *dev = &hdev->pdev->dev; dev_info(dev, "PF info begin:\n"); @@ -11148,9 +11149,9 @@ static void hclge_info_show(struct hclge_dev *hdev) dev_info(dev, "This is %s PF\n", hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main"); dev_info(dev, "DCB %s\n", - hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable"); + handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable"); dev_info(dev, "MQPRIO %s\n", - hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable"); + handle->kinfo.tc_info.mqprio_active ? "enable" : "disable"); dev_info(dev, "Default tx spare buffer size: %u\n", hdev->tx_spare_buf_size); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 13f23d606e77..f6fef790e16c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -916,8 +916,6 @@ struct hclge_dev { #define HCLGE_FLAG_MAIN BIT(0) #define HCLGE_FLAG_DCB_CAPABLE BIT(1) -#define HCLGE_FLAG_DCB_ENABLE BIT(2) -#define HCLGE_FLAG_MQPRIO_ENABLE BIT(3) u32 flag; u32 pkt_buf_size; /* Total pf buf size for tx/rx */ From 1368067718648431f2b66abc13eabb4a92da1e1b Mon Sep 17 00:00:00 2001 From: Yisen Zhuang Date: Wed, 6 Sep 2023 15:20:17 +0800 Subject: [PATCH 1412/2093] net: hns3: fix the port information display when sfp is absent [ Upstream commit 674d9591a32d01df75d6b5fffed4ef942a294376 ] When sfp is absent or unidentified, the port type should be displayed as PORT_OTHERS, rather than PORT_FIBRE. Fixes: 88d10bd6f730 ("net: hns3: add support for multiple media type") Signed-off-by: Yisen Zhuang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index cdf76fb58d45..e22835ae8a94 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -776,7 +776,9 @@ static int hns3_get_link_ksettings(struct net_device *netdev, hns3_get_ksettings(h, cmd); break; case HNAE3_MEDIA_TYPE_FIBER: - if (module_type == HNAE3_MODULE_TYPE_CR) + if (module_type == HNAE3_MODULE_TYPE_UNKNOWN) + cmd->base.port = PORT_OTHER; + else if (module_type == HNAE3_MODULE_TYPE_CR) cmd->base.port = PORT_DA; else cmd->base.port = PORT_FIBRE; From 9cd5cf0bfeafe7ca5002ce09659b5319f2442cdd Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Wed, 6 Sep 2023 15:20:18 +0800 Subject: [PATCH 1413/2093] net: hns3: remove GSO partial feature bit [ Upstream commit 60326634f6c54528778de18bfef1e8a7a93b3771 ] HNS3 NIC does not support GSO partial packets segmentation. Actually tunnel packets for example NvGRE packets segment offload and checksum offload is already supported. There is no need to keep gso partial feature bit. So this patch removes it. Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9942b21cd619..8aae179554a8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3315,8 +3315,6 @@ static void hns3_set_default_feature(struct net_device *netdev) netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; - netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | From 69561478400cc7a76ab1f8f0c26a0368a949a6c0 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Mon, 24 Jul 2023 14:07:42 +0200 Subject: [PATCH 1414/2093] sh: boards: Fix CEU buffer size passed to dma_declare_coherent_memory() [ Upstream commit fb60211f377b69acffead3147578f86d0092a7a5 ] In all these cases, the last argument to dma_declare_coherent_memory() is the buffer end address, but the expected value should be the size of the reserved region. Fixes: 39fb993038e1 ("media: arch: sh: ap325rxa: Use new renesas-ceu camera driver") Fixes: c2f9b05fd5c1 ("media: arch: sh: ecovec: Use new renesas-ceu camera driver") Fixes: f3590dc32974 ("media: arch: sh: kfr2r09: Use new renesas-ceu camera driver") Fixes: 186c446f4b84 ("media: arch: sh: migor: Use new renesas-ceu camera driver") Fixes: 1a3c230b4151 ("media: arch: sh: ms7724se: Use new renesas-ceu camera driver") Signed-off-by: Petr Tesarik Reviewed-by: Geert Uytterhoeven Reviewed-by: Jacopo Mondi Reviewed-by: John Paul Adrian Glaubitz Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20230724120742.2187-1-petrtesarik@huaweicloud.com Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Sasha Levin --- arch/sh/boards/mach-ap325rxa/setup.c | 2 +- arch/sh/boards/mach-ecovec24/setup.c | 6 ++---- arch/sh/boards/mach-kfr2r09/setup.c | 2 +- arch/sh/boards/mach-migor/setup.c | 2 +- arch/sh/boards/mach-se/7724/setup.c | 6 ++---- 5 files changed, 7 insertions(+), 11 deletions(-) diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c index c77b5f00a66a..d8f8dca4d796 100644 --- a/arch/sh/boards/mach-ap325rxa/setup.c +++ b/arch/sh/boards/mach-ap325rxa/setup.c @@ -530,7 +530,7 @@ static int __init ap325rxa_devices_setup(void) device_initialize(&ap325rxa_ceu_device.dev); dma_declare_coherent_memory(&ap325rxa_ceu_device.dev, ceu_dma_membase, ceu_dma_membase, - ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(&ap325rxa_ceu_device); diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 674da7ebd8b7..7ec03d4a4edf 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -1454,15 +1454,13 @@ static int __init arch_setup(void) device_initialize(&ecovec_ceu_devices[0]->dev); dma_declare_coherent_memory(&ecovec_ceu_devices[0]->dev, ceu0_dma_membase, ceu0_dma_membase, - ceu0_dma_membase + - CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(ecovec_ceu_devices[0]); device_initialize(&ecovec_ceu_devices[1]->dev); dma_declare_coherent_memory(&ecovec_ceu_devices[1]->dev, ceu1_dma_membase, ceu1_dma_membase, - ceu1_dma_membase + - CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(ecovec_ceu_devices[1]); gpiod_add_lookup_table(&cn12_power_gpiod_table); diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c index 20f4db778ed6..c6d556dfbbbe 100644 --- a/arch/sh/boards/mach-kfr2r09/setup.c +++ b/arch/sh/boards/mach-kfr2r09/setup.c @@ -603,7 +603,7 @@ static int __init kfr2r09_devices_setup(void) device_initialize(&kfr2r09_ceu_device.dev); dma_declare_coherent_memory(&kfr2r09_ceu_device.dev, ceu_dma_membase, ceu_dma_membase, - ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(&kfr2r09_ceu_device); diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index f60061283c48..773ee767d0c4 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -604,7 +604,7 @@ static int __init migor_devices_setup(void) device_initialize(&migor_ceu_device.dev); dma_declare_coherent_memory(&migor_ceu_device.dev, ceu_dma_membase, ceu_dma_membase, - ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(&migor_ceu_device); diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index b60a2626e18b..6495f9354065 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -940,15 +940,13 @@ static int __init devices_setup(void) device_initialize(&ms7724se_ceu_devices[0]->dev); dma_declare_coherent_memory(&ms7724se_ceu_devices[0]->dev, ceu0_dma_membase, ceu0_dma_membase, - ceu0_dma_membase + - CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(ms7724se_ceu_devices[0]); device_initialize(&ms7724se_ceu_devices[1]->dev); dma_declare_coherent_memory(&ms7724se_ceu_devices[1]->dev, ceu1_dma_membase, ceu1_dma_membase, - ceu1_dma_membase + - CEU_BUFFER_MEMORY_SIZE - 1); + CEU_BUFFER_MEMORY_SIZE); platform_device_add(ms7724se_ceu_devices[1]); return platform_add_devices(ms7724se_devices, From 017a058053685d172046cd81e5d384ba60a5fbd6 Mon Sep 17 00:00:00 2001 From: Kalesh Singh Date: Tue, 1 Aug 2023 19:56:03 -0700 Subject: [PATCH 1415/2093] Multi-gen LRU: avoid race in inc_min_seq() commit bb5e7f234eacf34b65be67ebb3613e3b8cf11b87 upstream. inc_max_seq() will try to inc_min_seq() if nr_gens == MAX_NR_GENS. This is because the generations are reused (the last oldest now empty generation will become the next youngest generation). inc_min_seq() is retried until successful, dropping the lru_lock and yielding the CPU on each failure, and retaking the lock before trying again: while (!inc_min_seq(lruvec, type, can_swap)) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } However, the initial condition that required incrementing the min_seq (nr_gens == MAX_NR_GENS) is not retested. This can change by another call to inc_max_seq() from run_aging() with force_scan=true from the debugfs interface. Since the eviction stalls when the nr_gens == MIN_NR_GENS, avoid unnecessarily incrementing the min_seq by rechecking the number of generations before each attempt. This issue was uncovered in previous discussion on the list by Yu Zhao and Aneesh Kumar [1]. [1] https://lore.kernel.org/linux-mm/CAOUHufbO7CaVm=xjEb1avDhHVvnC8pJmGyKcFf2iY_dpf+zR3w@mail.gmail.com/ Link: https://lkml.kernel.org/r/20230802025606.346758-2-kaleshsingh@google.com Fixes: d6c3af7d8a2b ("mm: multi-gen LRU: debugfs interface") Signed-off-by: Kalesh Singh Tested-by: AngeloGioacchino Del Regno [mediatek] Tested-by: Charan Teja Kalla Cc: Yu Zhao Cc: Aneesh Kumar K V Cc: Barry Song Cc: Brian Geffon Cc: Jan Alexander Steffens (heftig) Cc: Lecopzer Chen Cc: Matthias Brugger Cc: Oleksandr Natalenko Cc: Qi Zheng Cc: Steven Barrett Cc: Suleiman Souhlal Cc: Suren Baghdasaryan Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmscan.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 78efee423f58..93d6f27dd40b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4331,6 +4331,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan) int type, zone; struct lru_gen_struct *lrugen = &lruvec->lrugen; +restart: spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); @@ -4341,11 +4342,12 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan) VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); - while (!inc_min_seq(lruvec, type, can_swap)) { - spin_unlock_irq(&lruvec->lru_lock); - cond_resched(); - spin_lock_irq(&lruvec->lru_lock); - } + if (inc_min_seq(lruvec, type, can_swap)) + continue; + + spin_unlock_irq(&lruvec->lru_lock); + cond_resched(); + goto restart; } /* From 8eea0afbcc9d99a0be99d278c8c2291d2cb8cc7a Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 8 Jun 2023 12:00:54 -0700 Subject: [PATCH 1416/2093] net/mlx5: Free IRQ rmap and notifier on kernel shutdown commit 314ded538e5f22e7610b1bf621402024a180ec80 upstream. The kernel IRQ system needs the irq affinity notifier to be clear before attempting to free the irq, see WARN_ON log below. On a normal driver unload we don't have this issue since we do the complete cleanup of the irq resources. To fix this, put the important resources cleanup in a helper function and use it in both normal driver unload and shutdown flows. [ 4497.498434] ------------[ cut here ]------------ [ 4497.498726] WARNING: CPU: 0 PID: 9 at kernel/irq/manage.c:2034 free_irq+0x295/0x340 [ 4497.499193] Modules linked in: [ 4497.499386] CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G W 6.4.0-rc4+ #10 [ 4497.499876] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc38 04/01/2014 [ 4497.500518] Workqueue: events do_poweroff [ 4497.500849] RIP: 0010:free_irq+0x295/0x340 [ 4497.501132] Code: 85 c0 0f 84 1d ff ff ff 48 89 ef ff d0 0f 1f 00 e9 10 ff ff ff 0f 0b e9 72 ff ff ff 49 8d 7f 28 ff d0 0f 1f 00 e9 df fd ff ff <0f> 0b 48 c7 80 c0 008 [ 4497.502269] RSP: 0018:ffffc90000053da0 EFLAGS: 00010282 [ 4497.502589] RAX: ffff888100949600 RBX: ffff88810330b948 RCX: 0000000000000000 [ 4497.503035] RDX: ffff888100949600 RSI: ffff888100400490 RDI: 0000000000000023 [ 4497.503472] RBP: ffff88810330c7e0 R08: ffff8881004005d0 R09: ffffffff8273a260 [ 4497.503923] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8881009ae000 [ 4497.504359] R13: ffff8881009ae148 R14: 0000000000000000 R15: ffff888100949600 [ 4497.504804] FS: 0000000000000000(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 [ 4497.505302] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4497.505671] CR2: 00007fce98806298 CR3: 000000000262e005 CR4: 0000000000370ef0 [ 4497.506104] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4497.506540] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4497.507002] Call Trace: [ 4497.507158] [ 4497.507299] ? free_irq+0x295/0x340 [ 4497.507522] ? __warn+0x7c/0x130 [ 4497.507740] ? free_irq+0x295/0x340 [ 4497.507963] ? report_bug+0x171/0x1a0 [ 4497.508197] ? handle_bug+0x3c/0x70 [ 4497.508417] ? exc_invalid_op+0x17/0x70 [ 4497.508662] ? asm_exc_invalid_op+0x1a/0x20 [ 4497.508926] ? free_irq+0x295/0x340 [ 4497.509146] mlx5_irq_pool_free_irqs+0x48/0x90 [ 4497.509421] mlx5_irq_table_free_irqs+0x38/0x50 [ 4497.509714] mlx5_core_eq_free_irqs+0x27/0x40 [ 4497.509984] shutdown+0x7b/0x100 [ 4497.510184] pci_device_shutdown+0x30/0x60 [ 4497.510440] device_shutdown+0x14d/0x240 [ 4497.510698] kernel_power_off+0x30/0x70 [ 4497.510938] process_one_work+0x1e6/0x3e0 [ 4497.511183] worker_thread+0x49/0x3b0 [ 4497.511407] ? __pfx_worker_thread+0x10/0x10 [ 4497.511679] kthread+0xe0/0x110 [ 4497.511879] ? __pfx_kthread+0x10/0x10 [ 4497.512114] ret_from_fork+0x29/0x50 [ 4497.512342] Fixes: 9c2d08010963 ("net/mlx5: Free irqs only on shutdown callback") Signed-off-by: Saeed Mahameed Reviewed-by: Shay Drory Signed-off-by: Mathieu Tortuyaux Signed-off-by: Greg Kroah-Hartman --- .../net/ethernet/mellanox/mlx5/core/pci_irq.c | 26 ++++++++++++++----- 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 5e0f7d96aac5..d136360ac6a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -123,18 +123,32 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, return ret; } -static void irq_release(struct mlx5_irq *irq) +/* mlx5_system_free_irq - Free an IRQ + * @irq: IRQ to free + * + * Free the IRQ and other resources such as rmap from the system. + * BUT doesn't free or remove reference from mlx5. + * This function is very important for the shutdown flow, where we need to + * cleanup system resoruces but keep mlx5 objects alive, + * see mlx5_irq_table_free_irqs(). + */ +static void mlx5_system_free_irq(struct mlx5_irq *irq) { - struct mlx5_irq_pool *pool = irq->pool; - - xa_erase(&pool->irqs, irq->index); /* free_irq requires that affinity_hint and rmap will be cleared * before calling it. This is why there is asymmetry with set_rmap * which should be called after alloc_irq but before request_irq. */ irq_update_affinity_hint(irq->irqn, NULL); - free_cpumask_var(irq->mask); free_irq(irq->irqn, &irq->nh); +} + +static void irq_release(struct mlx5_irq *irq) +{ + struct mlx5_irq_pool *pool = irq->pool; + + xa_erase(&pool->irqs, irq->index); + mlx5_system_free_irq(irq); + free_cpumask_var(irq->mask); kfree(irq); } @@ -597,7 +611,7 @@ static void mlx5_irq_pool_free_irqs(struct mlx5_irq_pool *pool) unsigned long index; xa_for_each(&pool->irqs, index, irq) - free_irq(irq->irqn, &irq->nh); + mlx5_system_free_irq(irq); } static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table) From f2953184bf1960ff0f1268c613d58f5d74db1ea4 Mon Sep 17 00:00:00 2001 From: Pavel Kozlov Date: Tue, 15 Aug 2023 19:11:36 +0400 Subject: [PATCH 1417/2093] ARC: atomics: Add compiler barrier to atomic operations... commit 42f51fb24fd39cc547c086ab3d8a314cc603a91c upstream. ... to avoid unwanted gcc optimizations SMP kernels fail to boot with commit 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations"). | | percpu: BUG: failure at mm/percpu.c:2981/pcpu_build_alloc_info()! | The write operation performed by the SCOND instruction in the atomic inline asm code is not properly passed to the compiler. The compiler cannot correctly optimize a nested loop that runs through the cpumask in the pcpu_build_alloc_info() function. Fix this by add a compiler barrier (memory clobber in inline asm). Apparently atomic ops used to have memory clobber implicitly via surrounding smp_mb(). However commit b64be6836993c431e ("ARC: atomics: implement relaxed variants") removed the smp_mb() for the relaxed variants, but failed to add the explicit compiler barrier. Link: https://github.com/foss-for-synopsys-dwc-arc-processors/linux/issues/135 Cc: # v6.3+ Fixes: b64be6836993c43 ("ARC: atomics: implement relaxed variants") Signed-off-by: Pavel Kozlov Signed-off-by: Vineet Gupta [vgupta: tweaked the changelog and added Fixes tag] Signed-off-by: Greg Kroah-Hartman --- arch/arc/include/asm/atomic-llsc.h | 6 +++--- arch/arc/include/asm/atomic64-arcv2.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h index 1b0ffaeee16d..5258cb81a16b 100644 --- a/arch/arc/include/asm/atomic-llsc.h +++ b/arch/arc/include/asm/atomic-llsc.h @@ -18,7 +18,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \ : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \ : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \ [i] "ir" (i) \ - : "cc"); \ + : "cc", "memory"); \ } \ #define ATOMIC_OP_RETURN(op, asm_op) \ @@ -34,7 +34,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ : [val] "=&r" (val) \ : [ctr] "r" (&v->counter), \ [i] "ir" (i) \ - : "cc"); \ + : "cc", "memory"); \ \ return val; \ } @@ -56,7 +56,7 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ [orig] "=&r" (orig) \ : [ctr] "r" (&v->counter), \ [i] "ir" (i) \ - : "cc"); \ + : "cc", "memory"); \ \ return orig; \ } diff --git a/arch/arc/include/asm/atomic64-arcv2.h b/arch/arc/include/asm/atomic64-arcv2.h index c5a8010fdc97..9089f34baac3 100644 --- a/arch/arc/include/asm/atomic64-arcv2.h +++ b/arch/arc/include/asm/atomic64-arcv2.h @@ -60,7 +60,7 @@ static inline void arch_atomic64_##op(s64 a, atomic64_t *v) \ " bnz 1b \n" \ : "=&r"(val) \ : "r"(&v->counter), "ir"(a) \ - : "cc"); \ + : "cc", "memory"); \ } \ #define ATOMIC64_OP_RETURN(op, op1, op2) \ @@ -77,7 +77,7 @@ static inline s64 arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \ " bnz 1b \n" \ : [val] "=&r"(val) \ : "r"(&v->counter), "ir"(a) \ - : "cc"); /* memory clobber comes from smp_mb() */ \ + : "cc", "memory"); \ \ return val; \ } @@ -99,7 +99,7 @@ static inline s64 arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \ " bnz 1b \n" \ : "=&r"(orig), "=&r"(val) \ : "r"(&v->counter), "ir"(a) \ - : "cc"); /* memory clobber comes from smp_mb() */ \ + : "cc", "memory"); \ \ return orig; \ } From de43bc17987d12060426e640017793c638243c27 Mon Sep 17 00:00:00 2001 From: Walter Chang Date: Mon, 17 Jul 2023 17:07:34 +0800 Subject: [PATCH 1418/2093] clocksource/drivers/arm_arch_timer: Disable timer before programming CVAL commit e7d65e40ab5a5940785c5922f317602d0268caaf upstream. Due to the fact that the use of `writeq_relaxed()` to program CVAL is not guaranteed to be atomic, it is necessary to disable the timer before programming CVAL. However, if the MMIO timer is already enabled and has not yet expired, there is a possibility of unexpected behavior occurring: when the CPU enters the idle state during this period, and if the CPU's local event is earlier than the broadcast event, the following process occurs: tick_broadcast_enter() tick_broadcast_oneshot_control(TICK_BROADCAST_ENTER) __tick_broadcast_oneshot_control() ___tick_broadcast_oneshot_control() tick_broadcast_set_event() clockevents_program_event() set_next_event_mem() During this process, the MMIO timer remains enabled while programming CVAL. To prevent such behavior, disable timer explicitly prior to programming CVAL. Fixes: 8b82c4f883a7 ("clocksource/drivers/arm_arch_timer: Move MMIO timer programming over to CVAL") Cc: stable@vger.kernel.org Signed-off-by: Walter Chang Acked-by: Marc Zyngier Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230717090735.19370-1-walter.chang@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/clocksource/arm_arch_timer.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 933bb960490d..239c70ac120e 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -773,6 +773,13 @@ static __always_inline void set_next_event_mem(const int access, unsigned long e u64 cnt; ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk); + + /* Timer must be disabled before programming CVAL */ + if (ctrl & ARCH_TIMER_CTRL_ENABLE) { + ctrl &= ~ARCH_TIMER_CTRL_ENABLE; + arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk); + } + ctrl |= ARCH_TIMER_CTRL_ENABLE; ctrl &= ~ARCH_TIMER_CTRL_IT_MASK; From 6ea18981bb8af9b3b0c0497b11f334f136dc1b3a Mon Sep 17 00:00:00 2001 From: Hien Huynh Date: Thu, 6 Jul 2023 12:21:50 +0100 Subject: [PATCH 1419/2093] dmaengine: sh: rz-dmac: Fix destination and source data size setting commit c6ec8c83a29fb3aec3efa6fabbf5344498f57c7f upstream. Before setting DDS and SDS values, we need to clear its value first otherwise, we get incorrect results when we change/update the DMA bus width several times due to the 'OR' expression. Fixes: 5000d37042a6 ("dmaengine: sh: Add DMAC driver for RZ/G2L SoC") Cc: stable@kernel.org Signed-off-by: Hien Huynh Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230706112150.198941-3-biju.das.jz@bp.renesas.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/dma/sh/rz-dmac.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 476847a4916b..2967141f4e7b 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -9,6 +9,7 @@ * Copyright 2012 Javier Martin, Vista Silicon */ +#include #include #include #include @@ -145,8 +146,8 @@ struct rz_dmac { #define CHCFG_REQD BIT(3) #define CHCFG_SEL(bits) ((bits) & 0x07) #define CHCFG_MEM_COPY (0x80400008) -#define CHCFG_FILL_DDS(a) (((a) << 16) & GENMASK(19, 16)) -#define CHCFG_FILL_SDS(a) (((a) << 12) & GENMASK(15, 12)) +#define CHCFG_FILL_DDS_MASK GENMASK(19, 16) +#define CHCFG_FILL_SDS_MASK GENMASK(15, 12) #define CHCFG_FILL_TM(a) (((a) & BIT(5)) << 22) #define CHCFG_FILL_AM(a) (((a) & GENMASK(4, 2)) << 6) #define CHCFG_FILL_LVL(a) (((a) & BIT(1)) << 5) @@ -609,13 +610,15 @@ static int rz_dmac_config(struct dma_chan *chan, if (val == CHCFG_DS_INVALID) return -EINVAL; - channel->chcfg |= CHCFG_FILL_DDS(val); + channel->chcfg &= ~CHCFG_FILL_DDS_MASK; + channel->chcfg |= FIELD_PREP(CHCFG_FILL_DDS_MASK, val); val = rz_dmac_ds_to_val_mapping(config->src_addr_width); if (val == CHCFG_DS_INVALID) return -EINVAL; - channel->chcfg |= CHCFG_FILL_SDS(val); + channel->chcfg &= ~CHCFG_FILL_SDS_MASK; + channel->chcfg |= FIELD_PREP(CHCFG_FILL_SDS_MASK, val); return 0; } From c5f23305f8b1bce5d2c618626318604870c368ef Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 14 Jul 2023 10:55:26 +0800 Subject: [PATCH 1420/2093] jbd2: fix checkpoint cleanup performance regression commit 373ac521799d9e97061515aca6ec6621789036bb upstream. journal_clean_one_cp_list() has been merged into journal_shrink_one_cp_list(), but do chekpoint buffer cleanup from the committing process is just a best effort, it should stop scan once it meet a busy buffer, or else it will cause a lot of invalid buffer scan and checks. We catch a performance regression when doing fs_mark tests below. Test cmd: ./fs_mark -d scratch -s 1024 -n 10000 -t 1 -D 100 -N 100 Before merging checkpoint buffer cleanup: FSUse% Count Size Files/sec App Overhead 95 10000 1024 8304.9 49033 After merging checkpoint buffer cleanup: FSUse% Count Size Files/sec App Overhead 95 10000 1024 7649.0 50012 FSUse% Count Size Files/sec App Overhead 95 10000 1024 2107.1 50871 After merging checkpoint buffer cleanup, the total loop count in journal_shrink_one_cp_list() could be up to 6,261,600+ (50,000+ ~ 100,000+ in general), most of them are invalid. This patch fix it through passing 'shrink_type' into journal_shrink_one_cp_list() and add a new 'SHRINK_BUSY_STOP' to indicate it should stop once meet a busy buffer. After fix, the loop count descending back to 10,000+. After this fix: FSUse% Count Size Files/sec App Overhead 95 10000 1024 8558.4 49109 Cc: stable@kernel.org Fixes: b98dba273a0e ("jbd2: remove journal_clean_one_cp_list()") Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230714025528.564988-2-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/jbd2/checkpoint.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 9ec91017a7f3..936c6d758a65 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -349,6 +349,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* Checkpoint list management */ +enum shrink_type {SHRINK_DESTROY, SHRINK_BUSY_STOP, SHRINK_BUSY_SKIP}; + /* * journal_shrink_one_cp_list * @@ -360,7 +362,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * Called with j_list_lock held. */ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, - bool destroy, bool *released) + enum shrink_type type, + bool *released) { struct journal_head *last_jh; struct journal_head *next_jh = jh; @@ -376,12 +379,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, jh = next_jh; next_jh = jh->b_cpnext; - if (destroy) { + if (type == SHRINK_DESTROY) { ret = __jbd2_journal_remove_checkpoint(jh); } else { ret = jbd2_journal_try_remove_checkpoint(jh); - if (ret < 0) - continue; + if (ret < 0) { + if (type == SHRINK_BUSY_SKIP) + continue; + break; + } } nr_freed++; @@ -445,7 +451,7 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, tid = transaction->t_tid; freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, - false, &released); + SHRINK_BUSY_SKIP, &released); nr_freed += freed; (*nr_to_scan) -= min(*nr_to_scan, freed); if (*nr_to_scan == 0) @@ -485,19 +491,21 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) { transaction_t *transaction, *last_transaction, *next_transaction; + enum shrink_type type; bool released; transaction = journal->j_checkpoint_transactions; if (!transaction) return; + type = destroy ? SHRINK_DESTROY : SHRINK_BUSY_STOP; last_transaction = transaction->t_cpprev; next_transaction = transaction; do { transaction = next_transaction; next_transaction = transaction->t_cpnext; journal_shrink_one_cp_list(transaction->t_checkpoint_list, - destroy, &released); + type, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if From dbafe636db415299e54d9dfefc1003bda9e71c9d Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 14 Jul 2023 10:55:27 +0800 Subject: [PATCH 1421/2093] jbd2: check 'jh->b_transaction' before removing it from checkpoint MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 590a809ff743e7bd890ba5fb36bc38e20a36de53 upstream. Following process will corrupt ext4 image: Step 1: jbd2_journal_commit_transaction __jbd2_journal_insert_checkpoint(jh, commit_transaction) // Put jh into trans1->t_checkpoint_list journal->j_checkpoint_transactions = commit_transaction // Put trans1 into journal->j_checkpoint_transactions Step 2: do_get_write_access test_clear_buffer_dirty(bh) // clear buffer dirty，set jbd dirty __jbd2_journal_file_buffer(jh, transaction) // jh belongs to trans2 Step 3: drop_cache journal_shrink_one_cp_list jbd2_journal_try_remove_checkpoint if (!trylock_buffer(bh)) // lock bh, true if (buffer_dirty(bh)) // buffer is not dirty __jbd2_journal_remove_checkpoint(jh) // remove jh from trans1->t_checkpoint_list Step 4: jbd2_log_do_checkpoint trans1 = journal->j_checkpoint_transactions // jh is not in trans1->t_checkpoint_list jbd2_cleanup_journal_tail(journal) // trans1 is done Step 5: Power cut, trans2 is not committed, jh is lost in next mounting. Fix it by checking 'jh->b_transaction' before remove it from checkpoint. Cc: stable@kernel.org Fixes: 46f881b5b175 ("jbd2: fix a race when checking checkpoint buffer busy") Signed-off-by: Zhihao Cheng Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230714025528.564988-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/jbd2/checkpoint.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 936c6d758a65..f033ac807013 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -639,6 +639,8 @@ int jbd2_journal_try_remove_checkpoint(struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); + if (jh->b_transaction) + return -EBUSY; if (!trylock_buffer(bh)) return -EBUSY; if (buffer_dirty(bh)) { From 20108975ec51988228b02e46f21967530f3e7108 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Mon, 26 Jun 2023 15:33:22 +0800 Subject: [PATCH 1422/2093] jbd2: correct the end of the journal recovery scan range commit 2dfba3bb40ad8536b9fa802364f2d40da31aa88e upstream. We got a filesystem inconsistency issue below while running generic/475 I/O failure pressure test with fast_commit feature enabled. Symlink /p3/d3/d1c/d6c/dd6/dce/l101 (inode #132605) is invalid. If fast_commit feature is enabled, a special fast_commit journal area is appended to the end of the normal journal area. The journal->j_last point to the first unused block behind the normal journal area instead of the whole log area, and the journal->j_fc_last point to the first unused block behind the fast_commit journal area. While doing journal recovery, do_one_pass(PASS_SCAN) should first scan the normal journal area and turn around to the first block once it meet journal->j_last, but the wrap() macro misuse the journal->j_fc_last, so the recovering could not read the next magic block (commit block perhaps) and would end early mistakenly and missing tN and every transaction after it in the following example. Finally, it could lead to filesystem inconsistency. | normal journal area | fast commit area | +-------------------------------------------------+------------------+ | tN(rere) | tN+1 |~| tN-x |...| tN-1 | tN(front) | .... | +-------------------------------------------------+------------------+ / / / start journal->j_last journal->j_fc_last This patch fix it by use the correct ending journal->j_last. Fixes: 5b849b5f96b4 ("jbd2: fast commit recovery path") Cc: stable@kernel.org Reported-by: Theodore Ts'o Link: https://lore.kernel.org/linux-ext4/20230613043120.GB1584772@mit.edu/ Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230626073322.3956567-1-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/jbd2/recovery.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 8286a9ec122f..357a3f7632e3 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -229,12 +229,8 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) /* Make sure we wrap around the log correctly! */ #define wrap(journal, var) \ do { \ - unsigned long _wrap_last = \ - jbd2_has_feature_fast_commit(journal) ? \ - (journal)->j_fc_last : (journal)->j_last; \ - \ - if (var >= _wrap_last) \ - var -= (_wrap_last - (journal)->j_first); \ + if (var >= (journal)->j_last) \ + var -= ((journal)->j_last - (journal)->j_first); \ } while (0) static int fc_do_one_pass(journal_t *journal, @@ -517,9 +513,7 @@ static int do_one_pass(journal_t *journal, break; jbd2_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", - next_commit_ID, next_log_block, - jbd2_has_feature_fast_commit(journal) ? - journal->j_fc_last : journal->j_last); + next_commit_ID, next_log_block, journal->j_last); /* Skip over each chunk of the transaction looking * either the next descriptor block or the final commit From 03393857a95b59d5dfa9fd06e597d289d7e060d1 Mon Sep 17 00:00:00 2001 From: Wang Jianjian Date: Thu, 3 Aug 2023 00:28:39 +0800 Subject: [PATCH 1423/2093] ext4: add correct group descriptors and reserved GDT blocks to system zone commit 68228da51c9a436872a4ef4b5a7692e29f7e5bc7 upstream. When setup_system_zone, flex_bg is not initialized so it is always 1. Use a new helper function, ext4_num_base_meta_blocks() which does not depend on sbi->s_log_groups_per_flex being initialized. [ Squashed two patches in the Link URL's below together into a single commit, which is simpler to review/understand. Also fix checkpatch warnings. --TYT ] Cc: stable@kernel.org Signed-off-by: Wang Jianjian Link: https://lore.kernel.org/r/tencent_21AF0D446A9916ED5C51492CC6C9A0A77B05@qq.com Link: https://lore.kernel.org/r/tencent_D744D1450CC169AEA77FCF0A64719909ED05@qq.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/balloc.c | 15 +++++++++++---- fs/ext4/block_validity.c | 8 ++++---- fs/ext4/ext4.h | 2 ++ 3 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 8e83b51e3c68..fbd0329cf254 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -910,11 +910,11 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) } /* - * This function returns the number of file system metadata clusters at + * This function returns the number of file system metadata blocks at * the beginning of a block group, including the reserved gdt blocks. */ -static unsigned ext4_num_base_meta_clusters(struct super_block *sb, - ext4_group_t block_group) +unsigned int ext4_num_base_meta_blocks(struct super_block *sb, + ext4_group_t block_group) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned num; @@ -932,8 +932,15 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb, } else { /* For META_BG_BLOCK_GROUPS */ num += ext4_bg_num_gdb(sb, block_group); } - return EXT4_NUM_B2C(sbi, num); + return num; } + +static unsigned int ext4_num_base_meta_clusters(struct super_block *sb, + ext4_group_t block_group) +{ + return EXT4_NUM_B2C(EXT4_SB(sb), ext4_num_base_meta_blocks(sb, block_group)); +} + /** * ext4_inode_to_goal_block - return a hint for block allocation * @inode: inode for block allocation diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 5504f72bbbbe..6fe3c941b565 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -215,7 +215,6 @@ int ext4_setup_system_zone(struct super_block *sb) struct ext4_system_blocks *system_blks; struct ext4_group_desc *gdp; ext4_group_t i; - int flex_size = ext4_flex_bg_size(sbi); int ret; system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); @@ -223,12 +222,13 @@ int ext4_setup_system_zone(struct super_block *sb) return -ENOMEM; for (i=0; i < ngroups; i++) { + unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i); + cond_resched(); - if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) { + if (meta_blks != 0) { ret = add_system_zone(system_blks, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1, 0); + meta_blks, 0); if (ret) goto err; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0ea3960cb83e..72abb8d6caf7 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3096,6 +3096,8 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno, extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); +extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb, + ext4_group_t block_group); extern __printf(7, 8) void __ext4_error(struct super_block *, const char *, unsigned int, bool, From 1fb3f1bbfdb511034b0360dbeb0f6a8424ed2a5c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= Date: Thu, 3 Aug 2023 10:17:13 +0100 Subject: [PATCH 1424/2093] ext4: fix memory leaks in ext4_fname_{setup_filename,prepare_lookup} MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 7ca4b085f430f3774c3838b3da569ceccd6a0177 upstream. If the filename casefolding fails, we'll be leaking memory from the fscrypt_name struct, namely from the 'crypto_buf.name' member. Make sure we free it in the error path on both ext4_fname_setup_filename() and ext4_fname_prepare_lookup() functions. Cc: stable@kernel.org Fixes: 1ae98e295fa2 ("ext4: optimize match for casefolded encrypted dirs") Signed-off-by: Luís Henriques Reviewed-by: Eric Biggers Link: https://lore.kernel.org/r/20230803091713.13239-1-lhenriques@suse.de Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/crypto.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index e20ac0654b3f..453d4da5de52 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -33,6 +33,8 @@ int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); + if (err) + ext4_fname_free_filename(fname); #endif return err; } @@ -51,6 +53,8 @@ int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); + if (err) + ext4_fname_free_filename(fname); #endif return err; } From 1c64dbe8fa3552a340bca6d7fa09468c16ed2a85 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 7 Jul 2023 07:03:13 -0700 Subject: [PATCH 1425/2093] f2fs: flush inode if atomic file is aborted commit a3ab55746612247ce3dcaac6de66f5ffc055b9df upstream. Let's flush the inode being aborted atomic operation to avoid stale dirty inode during eviction in this call stack: f2fs_mark_inode_dirty_sync+0x22/0x40 [f2fs] f2fs_abort_atomic_write+0xc4/0xf0 [f2fs] f2fs_evict_inode+0x3f/0x690 [f2fs] ? sugov_start+0x140/0x140 evict+0xc3/0x1c0 evict_inodes+0x17b/0x210 generic_shutdown_super+0x32/0x120 kill_block_super+0x21/0x50 deactivate_locked_super+0x31/0x90 cleanup_mnt+0x100/0x160 task_work_run+0x59/0x90 do_exit+0x33b/0xa50 do_group_exit+0x2d/0x80 __x64_sys_exit_group+0x14/0x20 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd This triggers f2fs_bug_on() in f2fs_evict_inode: f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); This fixes the syzbot report: loop0: detected capacity change from 0 to 131072 F2FS-fs (loop0): invalid crc value F2FS-fs (loop0): Found nat_bits in checkpoint F2FS-fs (loop0): Mounted with checkpoint version = 48b305e4 ------------[ cut here ]------------ kernel BUG at fs/f2fs/inode.c:869! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 5014 Comm: syz-executor220 Not tainted 6.4.0-syzkaller-11479-g6cd06ab12d1a #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 RIP: 0010:f2fs_evict_inode+0x172d/0x1e00 fs/f2fs/inode.c:869 Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 6a 06 00 00 8b 75 40 ba 01 00 00 00 4c 89 e7 e8 6d ce 06 00 e9 aa fc ff ff e8 63 22 e2 fd <0f> 0b e8 5c 22 e2 fd 48 c7 c0 a8 3a 18 8d 48 ba 00 00 00 00 00 fc RSP: 0018:ffffc90003a6fa00 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff8880273b8000 RSI: ffffffff83a2bd0d RDI: 0000000000000007 RBP: ffff888077db91b0 R08: 0000000000000007 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff888029a3c000 R13: ffff888077db9660 R14: ffff888029a3c0b8 R15: ffff888077db9c50 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1909bb9000 CR3: 00000000276a9000 CR4: 0000000000350ef0 Call Trace: evict+0x2ed/0x6b0 fs/inode.c:665 dispose_list+0x117/0x1e0 fs/inode.c:698 evict_inodes+0x345/0x440 fs/inode.c:748 generic_shutdown_super+0xaf/0x480 fs/super.c:478 kill_block_super+0x64/0xb0 fs/super.c:1417 kill_f2fs_super+0x2af/0x3c0 fs/f2fs/super.c:4704 deactivate_locked_super+0x98/0x160 fs/super.c:330 deactivate_super+0xb1/0xd0 fs/super.c:361 cleanup_mnt+0x2ae/0x3d0 fs/namespace.c:1254 task_work_run+0x16f/0x270 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xa9a/0x29a0 kernel/exit.c:874 do_group_exit+0xd4/0x2a0 kernel/exit.c:1024 __do_sys_exit_group kernel/exit.c:1035 [inline] __se_sys_exit_group kernel/exit.c:1033 [inline] __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1033 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f309be71a09 Code: Unable to access opcode bytes at 0x7f309be719df. RSP: 002b:00007fff171df518 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 00007f309bef7330 RCX: 00007f309be71a09 RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000001 RBP: 0000000000000001 R08: ffffffffffffffc0 R09: 00007f309bef1e40 R10: 0000000000010600 R11: 0000000000000246 R12: 00007f309bef7330 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000001 Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:f2fs_evict_inode+0x172d/0x1e00 fs/f2fs/inode.c:869 Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 6a 06 00 00 8b 75 40 ba 01 00 00 00 4c 89 e7 e8 6d ce 06 00 e9 aa fc ff ff e8 63 22 e2 fd <0f> 0b e8 5c 22 e2 fd 48 c7 c0 a8 3a 18 8d 48 ba 00 00 00 00 00 fc RSP: 0018:ffffc90003a6fa00 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff8880273b8000 RSI: ffffffff83a2bd0d RDI: 0000000000000007 RBP: ffff888077db91b0 R08: 0000000000000007 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff888029a3c000 R13: ffff888077db9660 R14: ffff888029a3c0b8 R15: ffff888077db9c50 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1909bb9000 CR3: 00000000276a9000 CR4: 0000000000350ef0 Cc: Reported-and-tested-by: syzbot+e1246909d526a9d470fa@syzkaller.appspotmail.com Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/segment.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index cbbf95b99541..16bf9d5c8d4f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -204,6 +204,8 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) f2fs_i_size_write(inode, fi->original_i_size); fi->original_i_size = 0; } + /* avoid stale dirty inode during eviction */ + sync_inode_metadata(inode, 0); } static int __replace_atomic_write_block(struct inode *inode, pgoff_t index, From 980b592c60874d9b8bca5663549edc73acd42946 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 18 Aug 2023 11:34:32 -0700 Subject: [PATCH 1426/2093] f2fs: avoid false alarm of circular locking commit 5c13e2388bf3426fd69a89eb46e50469e9624e56 upstream. ====================================================== WARNING: possible circular locking dependency detected 6.5.0-rc5-syzkaller-00353-gae545c3283dc #0 Not tainted ------------------------------------------------------ syz-executor273/5027 is trying to acquire lock: ffff888077fe1fb0 (&fi->i_sem){+.+.}-{3:3}, at: f2fs_down_write fs/f2fs/f2fs.h:2133 [inline] ffff888077fe1fb0 (&fi->i_sem){+.+.}-{3:3}, at: f2fs_add_inline_entry+0x300/0x6f0 fs/f2fs/inline.c:644 but task is already holding lock: ffff888077fe07c8 (&fi->i_xattr_sem){.+.+}-{3:3}, at: f2fs_down_read fs/f2fs/f2fs.h:2108 [inline] ffff888077fe07c8 (&fi->i_xattr_sem){.+.+}-{3:3}, at: f2fs_add_dentry+0x92/0x230 fs/f2fs/dir.c:783 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&fi->i_xattr_sem){.+.+}-{3:3}: down_read+0x9c/0x470 kernel/locking/rwsem.c:1520 f2fs_down_read fs/f2fs/f2fs.h:2108 [inline] f2fs_getxattr+0xb1e/0x12c0 fs/f2fs/xattr.c:532 __f2fs_get_acl+0x5a/0x900 fs/f2fs/acl.c:179 f2fs_acl_create fs/f2fs/acl.c:377 [inline] f2fs_init_acl+0x15c/0xb30 fs/f2fs/acl.c:420 f2fs_init_inode_metadata+0x159/0x1290 fs/f2fs/dir.c:558 f2fs_add_regular_entry+0x79e/0xb90 fs/f2fs/dir.c:740 f2fs_add_dentry+0x1de/0x230 fs/f2fs/dir.c:788 f2fs_do_add_link+0x190/0x280 fs/f2fs/dir.c:827 f2fs_add_link fs/f2fs/f2fs.h:3554 [inline] f2fs_mkdir+0x377/0x620 fs/f2fs/namei.c:781 vfs_mkdir+0x532/0x7e0 fs/namei.c:4117 do_mkdirat+0x2a9/0x330 fs/namei.c:4140 __do_sys_mkdir fs/namei.c:4160 [inline] __se_sys_mkdir fs/namei.c:4158 [inline] __x64_sys_mkdir+0xf2/0x140 fs/namei.c:4158 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #0 (&fi->i_sem){+.+.}-{3:3}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x2e3d/0x5de0 kernel/locking/lockdep.c:5144 lock_acquire kernel/locking/lockdep.c:5761 [inline] lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5726 down_write+0x93/0x200 kernel/locking/rwsem.c:1573 f2fs_down_write fs/f2fs/f2fs.h:2133 [inline] f2fs_add_inline_entry+0x300/0x6f0 fs/f2fs/inline.c:644 f2fs_add_dentry+0xa6/0x230 fs/f2fs/dir.c:784 f2fs_do_add_link+0x190/0x280 fs/f2fs/dir.c:827 f2fs_add_link fs/f2fs/f2fs.h:3554 [inline] f2fs_mkdir+0x377/0x620 fs/f2fs/namei.c:781 vfs_mkdir+0x532/0x7e0 fs/namei.c:4117 ovl_do_mkdir fs/overlayfs/overlayfs.h:196 [inline] ovl_mkdir_real+0xb5/0x370 fs/overlayfs/dir.c:146 ovl_workdir_create+0x3de/0x820 fs/overlayfs/super.c:309 ovl_make_workdir fs/overlayfs/super.c:711 [inline] ovl_get_workdir fs/overlayfs/super.c:864 [inline] ovl_fill_super+0xdab/0x6180 fs/overlayfs/super.c:1400 vfs_get_super+0xf9/0x290 fs/super.c:1152 vfs_get_tree+0x88/0x350 fs/super.c:1519 do_new_mount fs/namespace.c:3335 [inline] path_mount+0x1492/0x1ed0 fs/namespace.c:3662 do_mount fs/namespace.c:3675 [inline] __do_sys_mount fs/namespace.c:3884 [inline] __se_sys_mount fs/namespace.c:3861 [inline] __x64_sys_mount+0x293/0x310 fs/namespace.c:3861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- rlock(&fi->i_xattr_sem); lock(&fi->i_sem); lock(&fi->i_xattr_sem); lock(&fi->i_sem); Cc: Reported-and-tested-by: syzbot+e5600587fa9cbf8e3826@syzkaller.appspotmail.com Fixes: 5eda1ad1aaff "f2fs: fix deadlock in i_xattr_sem and inode page lock" Tested-by: Guenter Roeck Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/f2fs.h | 24 +++++++++++++++--------- fs/f2fs/inline.c | 3 ++- 2 files changed, 17 insertions(+), 10 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index c2b7d0923894..37dca728ff96 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2160,15 +2160,6 @@ static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem) return down_read_trylock(&sem->internal_rwsem); } -#ifdef CONFIG_DEBUG_LOCK_ALLOC -static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass) -{ - down_read_nested(&sem->internal_rwsem, subclass); -} -#else -#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem) -#endif - static inline void f2fs_up_read(struct f2fs_rwsem *sem) { up_read(&sem->internal_rwsem); @@ -2179,6 +2170,21 @@ static inline void f2fs_down_write(struct f2fs_rwsem *sem) down_write(&sem->internal_rwsem); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass) +{ + down_read_nested(&sem->internal_rwsem, subclass); +} + +static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass) +{ + down_write_nested(&sem->internal_rwsem, subclass); +} +#else +#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem) +#define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem) +#endif + static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem) { return down_write_trylock(&sem->internal_rwsem); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 7e867dff681d..8747eec3d0a3 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -642,7 +642,8 @@ int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname, } if (inode) { - f2fs_down_write(&F2FS_I(inode)->i_sem); + f2fs_down_write_nested(&F2FS_I(inode)->i_sem, + SINGLE_DEPTH_NESTING); page = f2fs_init_inode_metadata(inode, dir, fname, ipage); if (IS_ERR(page)) { err = PTR_ERR(page); From 0649dc0af93acac75eaf03ac898f28bd65479984 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 7 Aug 2023 08:36:28 -0700 Subject: [PATCH 1427/2093] lib: test_scanf: Add explicit type cast to result initialization in test_number_prefix() commit 92382d744176f230101d54f5c017bccd62770f01 upstream. A recent change in clang allows it to consider more expressions as compile time constants, which causes it to point out an implicit conversion in the scanf tests: lib/test_scanf.c:661:2: warning: implicit conversion from 'int' to 'unsigned char' changes value from -168 to 88 [-Wconstant-conversion] 661 | test_number_prefix(unsigned char, "0xA7", "%2hhx%hhx", 0, 0xa7, 2, check_uchar); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ lib/test_scanf.c:609:29: note: expanded from macro 'test_number_prefix' 609 | T result[2] = {~expect[0], ~expect[1]}; \ | ~ ^~~~~~~~~~ 1 warning generated. The result of the bitwise negation is the type of the operand after going through the integer promotion rules, so this truncation is expected but harmless, as the initial values in the result array get overwritten by _test() anyways. Add an explicit cast to the expected type in test_number_prefix() to silence the warning. There is no functional change, as all the tests still pass with GCC 13.1.0 and clang 18.0.0. Cc: stable@vger.kernel.org Link: https://github.com/ClangBuiltLinux/linuxq/issues/1899 Link: https://github.com/llvm/llvm-project/commit/610ec954e1f81c0e8fcadedcd25afe643f5a094e Suggested-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230807-test_scanf-wconstant-conversion-v2-1-839ca39083e1@kernel.org Signed-off-by: Greg Kroah-Hartman --- lib/test_scanf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_scanf.c b/lib/test_scanf.c index b620cf7de503..a2707af2951a 100644 --- a/lib/test_scanf.c +++ b/lib/test_scanf.c @@ -606,7 +606,7 @@ static void __init numbers_slice(void) #define test_number_prefix(T, str, scan_fmt, expect0, expect1, n_args, fn) \ do { \ const T expect[2] = { expect0, expect1 }; \ - T result[2] = {~expect[0], ~expect[1]}; \ + T result[2] = { (T)~expect[0], (T)~expect[1] }; \ \ _test(fn, &expect, str, scan_fmt, n_args, &result[0], &result[1]); \ } while (0) From e93bc372dbc0bde133c854c03502a95617041972 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Sun, 16 Jul 2023 04:28:04 +0200 Subject: [PATCH 1428/2093] hwspinlock: qcom: add missing regmap config for SFPB MMIO implementation commit 23316be8a9d450f33a21f1efe7d89570becbec58 upstream. Commit 5d4753f741d8 ("hwspinlock: qcom: add support for MMIO on older SoCs") introduced and made regmap_config mandatory in the of_data struct but didn't add the regmap_config for sfpb based devices. SFPB based devices can both use the legacy syscon way to probe or the new MMIO way and currently device that use the MMIO way are broken as they lack the definition of the now required regmap_config and always return -EINVAL (and indirectly makes fail probing everything that depends on it, smem, nandc with smem-parser...) Fix this by correctly adding the missing regmap_config and restore function of hwspinlock on SFPB based devices with MMIO implementation. Cc: stable@vger.kernel.org Fixes: 5d4753f741d8 ("hwspinlock: qcom: add support for MMIO on older SoCs") Signed-off-by: Christian Marangi Link: https://lore.kernel.org/r/20230716022804.21239-1-ansuelsmth@gmail.com Signed-off-by: Bjorn Andersson Signed-off-by: Greg Kroah-Hartman --- drivers/hwspinlock/qcom_hwspinlock.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c index 9cf186362ae2..3f08cd4a5c28 100644 --- a/drivers/hwspinlock/qcom_hwspinlock.c +++ b/drivers/hwspinlock/qcom_hwspinlock.c @@ -69,9 +69,18 @@ static const struct hwspinlock_ops qcom_hwspinlock_ops = { .unlock = qcom_hwspinlock_unlock, }; +static const struct regmap_config sfpb_mutex_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x100, + .fast_io = true, +}; + static const struct qcom_hwspinlock_of_data of_sfpb_mutex = { .offset = 0x4, .stride = 0x4, + .regmap_config = &sfpb_mutex_config, }; static const struct regmap_config tcsr_msm8226_mutex_config = { From cdd0d707357c1924258599fd2b2f758ce8f7522a Mon Sep 17 00:00:00 2001 From: Werner Fischer Date: Tue, 29 Aug 2023 13:33:58 +0200 Subject: [PATCH 1429/2093] ata: ahci: Add Elkhart Lake AHCI controller MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2a2df98ec592667927b5c1351afa6493ea125c9f upstream. Elkhart Lake is the successor of Apollo Lake and Gemini Lake. These CPUs and their PCHs are used in mobile and embedded environments. With this patch I suggest that Elkhart Lake SATA controllers [1] should use the default LPM policy for mobile chipsets. The disadvantage of missing hot-plug support with this setting should not be an issue, as those CPUs are used in embedded environments and not in servers with hot-plug backplanes. We discovered that the Elkhart Lake SATA controllers have been missing in ahci.c after a customer reported the throttling of his SATA SSD after a short period of higher I/O. We determined the high temperature of the SSD controller in idle mode as the root cause for that. Depending on the used SSD, we have seen up to 1.8 Watt lower system idle power usage and up to 30°C lower SSD controller temperatures in our tests, when we set med_power_with_dipm manually. I have provided a table showing seven different SATA SSDs from ATP, Intel/Solidigm and Samsung [2]. Intel lists a total of 3 SATA controller IDs (4B60, 4B62, 4B63) in [1] for those mobile PCHs. This commit just adds 0x4b63 as I do not have test systems with 0x4b60 and 0x4b62 SATA controllers. I have tested this patch with a system which uses 0x4b63 as SATA controller. [1] https://sata-io.org/product/8803 [2] https://www.thomas-krenn.com/en/wiki/SATA_Link_Power_Management#Example_LES_v4 Signed-off-by: Werner Fischer Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman --- drivers/ata/ahci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 53ab2306da00..1645335b8d2d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -422,6 +422,8 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_low_power }, /* Ice Lake LP AHCI */ { PCI_VDEVICE(INTEL, 0x02d3), board_ahci_low_power }, /* Comet Lake PCH-U AHCI */ { PCI_VDEVICE(INTEL, 0x02d7), board_ahci_low_power }, /* Comet Lake PCH RAID */ + /* Elkhart Lake IDs 0x4b60 & 0x4b62 https://sata-io.org/product/8803 not tested yet */ + { PCI_VDEVICE(INTEL, 0x4b63), board_ahci_low_power }, /* Elkhart Lake AHCI */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, From 1605f27090170ecf40ffdc36b6a4490fe0fe5d5e Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Sun, 27 Aug 2023 16:13:47 +1200 Subject: [PATCH 1430/2093] ata: pata_falcon: fix IO base selection for Q40 commit 8a1f00b753ecfdb117dc1a07e68c46d80e7923ea upstream. With commit 44b1fbc0f5f3 ("m68k/q40: Replace q40ide driver with pata_falcon and falconide"), the Q40 IDE driver was replaced by pata_falcon.c. Both IO and memory resources were defined for the Q40 IDE platform device, but definition of the IDE register addresses was modeled after the Falcon case, both in use of the memory resources and in including register shift and byte vs. word offset in the address. This was correct for the Falcon case, which does not apply any address translation to the register addresses. In the Q40 case, all of device base address, byte access offset and register shift is included in the platform specific ISA access translation (in asm/mm_io.h). As a consequence, such address translation gets applied twice, and register addresses are mangled. Use the device base address from the platform IO resource for Q40 (the IO address translation will then add the correct ISA window base address and byte access offset), with register shift 1. Use MMIO base address and register shift 2 as before for Falcon. Encode PIO_OFFSET into IO port addresses for all registers for Q40 except the data transfer register. Encode the MMIO offset there (pata_falcon_data_xfer() directly uses raw IO with no address translation). Reported-by: William R Sowerbutts Closes: https://lore.kernel.org/r/CAMuHMdUU62jjunJh9cqSqHT87B0H0A4udOOPs=WN7WZKpcagVA@mail.gmail.com Link: https://lore.kernel.org/r/CAMuHMdUU62jjunJh9cqSqHT87B0H0A4udOOPs=WN7WZKpcagVA@mail.gmail.com Fixes: 44b1fbc0f5f3 ("m68k/q40: Replace q40ide driver with pata_falcon and falconide") Cc: stable@vger.kernel.org Cc: Finn Thain Cc: Geert Uytterhoeven Tested-by: William R Sowerbutts Signed-off-by: Michael Schmitz Reviewed-by: Sergey Shtylyov Reviewed-by: Geert Uytterhoeven Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman --- drivers/ata/pata_falcon.c | 46 +++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 19 deletions(-) diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c index 823c88622e34..ffdd12e722c9 100644 --- a/drivers/ata/pata_falcon.c +++ b/drivers/ata/pata_falcon.c @@ -123,8 +123,8 @@ static int __init pata_falcon_init_one(struct platform_device *pdev) struct resource *base_res, *ctl_res, *irq_res; struct ata_host *host; struct ata_port *ap; - void __iomem *base; - int irq = 0; + void __iomem *base, *ctl_base; + int irq = 0, io_offset = 1, reg_shift = 2; /* Falcon defaults */ dev_info(&pdev->dev, "Atari Falcon and Q40/Q60 PATA controller\n"); @@ -165,26 +165,34 @@ static int __init pata_falcon_init_one(struct platform_device *pdev) ap->pio_mask = ATA_PIO4; ap->flags |= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_IORDY; - base = (void __iomem *)base_mem_res->start; /* N.B. this assumes data_addr will be used for word-sized I/O only */ - ap->ioaddr.data_addr = base + 0 + 0 * 4; - ap->ioaddr.error_addr = base + 1 + 1 * 4; - ap->ioaddr.feature_addr = base + 1 + 1 * 4; - ap->ioaddr.nsect_addr = base + 1 + 2 * 4; - ap->ioaddr.lbal_addr = base + 1 + 3 * 4; - ap->ioaddr.lbam_addr = base + 1 + 4 * 4; - ap->ioaddr.lbah_addr = base + 1 + 5 * 4; - ap->ioaddr.device_addr = base + 1 + 6 * 4; - ap->ioaddr.status_addr = base + 1 + 7 * 4; - ap->ioaddr.command_addr = base + 1 + 7 * 4; + ap->ioaddr.data_addr = (void __iomem *)base_mem_res->start; - base = (void __iomem *)ctl_mem_res->start; - ap->ioaddr.altstatus_addr = base + 1; - ap->ioaddr.ctl_addr = base + 1; + if (base_res) { /* only Q40 has IO resources */ + io_offset = 0x10000; + reg_shift = 0; + base = (void __iomem *)base_res->start; + ctl_base = (void __iomem *)ctl_res->start; + } else { + base = (void __iomem *)base_mem_res->start; + ctl_base = (void __iomem *)ctl_mem_res->start; + } - ata_port_desc(ap, "cmd 0x%lx ctl 0x%lx", - (unsigned long)base_mem_res->start, - (unsigned long)ctl_mem_res->start); + ap->ioaddr.error_addr = base + io_offset + (1 << reg_shift); + ap->ioaddr.feature_addr = base + io_offset + (1 << reg_shift); + ap->ioaddr.nsect_addr = base + io_offset + (2 << reg_shift); + ap->ioaddr.lbal_addr = base + io_offset + (3 << reg_shift); + ap->ioaddr.lbam_addr = base + io_offset + (4 << reg_shift); + ap->ioaddr.lbah_addr = base + io_offset + (5 << reg_shift); + ap->ioaddr.device_addr = base + io_offset + (6 << reg_shift); + ap->ioaddr.status_addr = base + io_offset + (7 << reg_shift); + ap->ioaddr.command_addr = base + io_offset + (7 << reg_shift); + + ap->ioaddr.altstatus_addr = ctl_base + io_offset; + ap->ioaddr.ctl_addr = ctl_base + io_offset; + + ata_port_desc(ap, "cmd %px ctl %px data %px", + base, ctl_base, ap->ioaddr.data_addr); irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (irq_res && irq_res->start > 0) { From ae73b94ad7710e8d810bc0b4fbda07f68faca246 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Aug 2023 07:43:18 +0900 Subject: [PATCH 1431/2093] ata: sata_gemini: Add missing MODULE_DESCRIPTION commit 8566572bf3b4d6e416a4bf2110dbb4817d11ba59 upstream. Add the missing MODULE_DESCRIPTION() to avoid warnings such as: WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/ata/sata_gemini.o when compiling with W=1. Fixes: be4e456ed3a5 ("ata: Add driver for Faraday Technology FTIDE010") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/ata/sata_gemini.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index b729e9919bb0..c96fcf9ee3c0 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -428,6 +428,7 @@ static struct platform_driver gemini_sata_driver = { }; module_platform_driver(gemini_sata_driver); +MODULE_DESCRIPTION("low level driver for Cortina Systems Gemini SATA bridge"); MODULE_AUTHOR("Linus Walleij "); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:" DRV_NAME); From 6694be119f632fe57aa1a4b36008e5ed460e27e8 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Aug 2023 07:41:59 +0900 Subject: [PATCH 1432/2093] ata: pata_ftide010: Add missing MODULE_DESCRIPTION commit 7274eef5729037300f29d14edeb334a47a098f65 upstream. Add the missing MODULE_DESCRIPTION() to avoid warnings such as: WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/ata/pata_ftide010.o when compiling with W=1. Fixes: be4e456ed3a5 ("ata: Add driver for Faraday Technology FTIDE010") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/ata/pata_ftide010.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/pata_ftide010.c b/drivers/ata/pata_ftide010.c index 0117df0fe3c5..092ba6f87aa3 100644 --- a/drivers/ata/pata_ftide010.c +++ b/drivers/ata/pata_ftide010.c @@ -567,6 +567,7 @@ static struct platform_driver pata_ftide010_driver = { }; module_platform_driver(pata_ftide010_driver); +MODULE_DESCRIPTION("low level driver for Faraday Technology FTIDE010"); MODULE_AUTHOR("Linus Walleij "); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:" DRV_NAME); From ef819c2f8e8a0da58d765ab1960cb976565ce0af Mon Sep 17 00:00:00 2001 From: ruanmeisi Date: Tue, 25 Apr 2023 19:13:54 +0800 Subject: [PATCH 1433/2093] fuse: nlookup missing decrement in fuse_direntplus_link commit b8bd342d50cbf606666488488f9fea374aceb2d5 upstream. During our debugging of glusterfs, we found an Assertion failed error: inode_lookup >= nlookup, which was caused by the nlookup value in the kernel being greater than that in the FUSE file system. The issue was introduced by fuse_direntplus_link, where in the function, fuse_iget increments nlookup, and if d_splice_alias returns failure, fuse_direntplus_link returns failure without decrementing nlookup https://github.com/gluster/glusterfs/pull/4081 Signed-off-by: ruanmeisi Fixes: 0b05b18381ee ("fuse: implement NFS-like readdirplus support") Cc: # v3.9 Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/fuse/readdir.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index e8deaacf1832..f40bc51fa531 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -243,8 +243,16 @@ static int fuse_direntplus_link(struct file *file, dput(dentry); dentry = alias; } - if (IS_ERR(dentry)) + if (IS_ERR(dentry)) { + if (!IS_ERR(inode)) { + struct fuse_inode *fi = get_fuse_inode(inode); + + spin_lock(&fi->lock); + fi->nlookup--; + spin_unlock(&fi->lock); + } return PTR_ERR(dentry); + } } if (fc->readdirplus_auto) set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); From 59c38f050d9bace5dab5b187efdbab864ce85ab4 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 21 Jul 2023 16:42:14 +0900 Subject: [PATCH 1434/2093] btrfs: zoned: do not zone finish data relocation block group commit 332581bde2a419d5f12a93a1cdc2856af649a3cc upstream. When multiple writes happen at once, we may need to sacrifice a currently active block group to be zone finished for a new allocation. We choose a block group with the least free space left, and zone finish it. To do the finishing, we need to send IOs for already allocated region and wait for them and on-going IOs. Otherwise, these IOs fail because the zone is already finished at the time the IO reach a device. However, if a block group dedicated to the data relocation is zone finished, there is a chance that finishing it before an ongoing write IO reaches the device. That is because there is timing gap between an allocation is done (block_group->reservations == 0, as pre-allocation is done) and an ordered extent is created when the relocation IO starts. Thus, if we finish the zone between them, we can fail the IOs. We cannot simply use "fs_info->data_reloc_bg == block_group->start" to avoid the zone finishing. Because, the data_reloc_bg may already switch to a new block group, while there are still ongoing write IOs to the old data_reloc_bg. So, this patch reworks the BLOCK_GROUP_FLAG_ZONED_DATA_RELOC bit to indicate there is a data relocation allocation and/or ongoing write to the block group. The bit is set on allocation and cleared in end_io function of the last IO for the currently allocated region. To change the timing of the bit setting also solves the issue that the bit being left even after there is no IO going on. With the current code, if the data_reloc_bg switches after the last IO to the current data_reloc_bg, the bit is set at this timing and there is no one clearing that bit. As a result, that block group is kept unallocatable for anything. Fixes: 343d8a30851c ("btrfs: zoned: prevent allocation from previous data relocation BG") Fixes: 74e91b12b115 ("btrfs: zoned: zone finish unused block group") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/extent-tree.c | 43 ++++++++++++++++++++++-------------------- fs/btrfs/zoned.c | 16 +++++++++++++--- 2 files changed, 36 insertions(+), 23 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f2ee70c03f0d..0640ef59fe66 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3810,7 +3810,8 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group, fs_info->data_reloc_bg == 0); if (block_group->ro || - test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { + (!ffe_ctl->for_data_reloc && + test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags))) { ret = 1; goto out; } @@ -3853,8 +3854,26 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group, if (ffe_ctl->for_treelog && !fs_info->treelog_bg) fs_info->treelog_bg = block_group->start; - if (ffe_ctl->for_data_reloc && !fs_info->data_reloc_bg) - fs_info->data_reloc_bg = block_group->start; + if (ffe_ctl->for_data_reloc) { + if (!fs_info->data_reloc_bg) + fs_info->data_reloc_bg = block_group->start; + /* + * Do not allow allocations from this block group, unless it is + * for data relocation. Compared to increasing the ->ro, setting + * the ->zoned_data_reloc_ongoing flag still allows nocow + * writers to come in. See btrfs_inc_nocow_writers(). + * + * We need to disable an allocation to avoid an allocation of + * regular (non-relocation data) extent. With mix of relocation + * extents and regular extents, we can dispatch WRITE commands + * (for relocation extents) and ZONE APPEND commands (for + * regular extents) at the same time to the same zone, which + * easily break the write pointer. + * + * Also, this flag avoids this block group to be zone finished. + */ + set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags); + } ffe_ctl->found_offset = start + block_group->alloc_offset; block_group->alloc_offset += num_bytes; @@ -3872,24 +3891,8 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group, out: if (ret && ffe_ctl->for_treelog) fs_info->treelog_bg = 0; - if (ret && ffe_ctl->for_data_reloc && - fs_info->data_reloc_bg == block_group->start) { - /* - * Do not allow further allocations from this block group. - * Compared to increasing the ->ro, setting the - * ->zoned_data_reloc_ongoing flag still allows nocow - * writers to come in. See btrfs_inc_nocow_writers(). - * - * We need to disable an allocation to avoid an allocation of - * regular (non-relocation data) extent. With mix of relocation - * extents and regular extents, we can dispatch WRITE commands - * (for relocation extents) and ZONE APPEND commands (for - * regular extents) at the same time to the same zone, which - * easily break the write pointer. - */ - set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags); + if (ret && ffe_ctl->for_data_reloc) fs_info->data_reloc_bg = 0; - } spin_unlock(&fs_info->relocation_bg_lock); spin_unlock(&fs_info->treelog_bg_lock); spin_unlock(&block_group->lock); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 9bc7ac06c517..675dbed075d8 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2009,6 +2009,10 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ * and block_group->meta_write_pointer for metadata. */ if (!fully_written) { + if (test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { + spin_unlock(&block_group->lock); + return -EAGAIN; + } spin_unlock(&block_group->lock); ret = btrfs_inc_block_group_ro(block_group, false); @@ -2037,7 +2041,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ return 0; } - if (block_group->reserved) { + if (block_group->reserved || + test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, + &block_group->runtime_flags)) { spin_unlock(&block_group->lock); btrfs_dec_block_group_ro(block_group); return -EAGAIN; @@ -2268,7 +2274,10 @@ void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logica /* All relocation extents are written. */ if (block_group->start + block_group->alloc_offset == logical + length) { - /* Now, release this block group for further allocations. */ + /* + * Now, release this block group for further allocations and + * zone finish. + */ clear_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags); } @@ -2292,7 +2301,8 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) spin_lock(&block_group->lock); if (block_group->reserved || block_group->alloc_offset == 0 || - (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM)) { + (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) || + test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); continue; } From cdc3ba292df88a4561f97b2cc25ff6b30f5d6962 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Fri, 21 Jul 2023 09:02:07 -0700 Subject: [PATCH 1435/2093] btrfs: fix start transaction qgroup rsv double free commit a6496849671a5bc9218ecec25a983253b34351b1 upstream. btrfs_start_transaction reserves metadata space of the PERTRANS type before it identifies a transaction to start/join. This allows flushing when reserving that space without a deadlock. However, it results in a race which temporarily breaks qgroup rsv accounting. T1 T2 start_transaction do_stuff start_transaction qgroup_reserve_meta_pertrans commit_transaction qgroup_free_meta_all_pertrans hit an error starting txn goto reserve_fail qgroup_free_meta_pertrans (already freed!) The basic issue is that there is nothing preventing another commit from committing before start_transaction finishes (in fact sometimes we intentionally wait for it) so any error path that frees the reserve is at risk of this race. While this exact space was getting freed anyway, and it's not a huge deal to double free it (just a warning, the free code catches this), it can result in incorrectly freeing some other pertrans reservation in this same reservation, which could then lead to spuriously granting reservations we might not have the space for. Therefore, I do believe it is worth fixing. To fix it, use the existing prealloc->pertrans conversion mechanism. When we first reserve the space, we reserve prealloc space and only when we are sure we have a transaction do we convert it to pertrans. This way any racing commits do not blow away our reservation, but we still get a pertrans reservation that is freed when _this_ transaction gets committed. This issue can be reproduced by running generic/269 with either qgroups or squotas enabled via mkfs on the scratch device. Reviewed-by: Josef Bacik CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Boris Burkov Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/transaction.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 2b776fce1c0f..7353f33c082c 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -580,8 +580,13 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, u64 delayed_refs_bytes = 0; qgroup_reserved = num_items * fs_info->nodesize; - ret = btrfs_qgroup_reserve_meta_pertrans(root, qgroup_reserved, - enforce_qgroups); + /* + * Use prealloc for now, as there might be a currently running + * transaction that could free this reserved space prematurely + * by committing. + */ + ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserved, + enforce_qgroups, false); if (ret) return ERR_PTR(ret); @@ -693,6 +698,14 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, h->reloc_reserved = reloc_reserved; } + /* + * Now that we have found a transaction to be a part of, convert the + * qgroup reservation from prealloc to pertrans. A different transaction + * can't race in and free our pertrans out from under us. + */ + if (qgroup_reserved) + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + got_it: if (!current->journal_info) current->journal_info = h; @@ -740,7 +753,7 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, btrfs_block_rsv_release(fs_info, &fs_info->trans_block_rsv, num_bytes, NULL); reserve_fail: - btrfs_qgroup_free_meta_pertrans(root, qgroup_reserved); + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); return ERR_PTR(ret); } From f933a1c43b68103c4deaf2e4289fc1e65428d8b4 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Fri, 21 Jul 2023 09:02:06 -0700 Subject: [PATCH 1436/2093] btrfs: free qgroup rsv on io failure commit e28b02118b94e42be3355458a2406c6861e2dd32 upstream. If we do a write whose bio suffers an error, we will never reclaim the qgroup reserved space for it. We allocate the space in the write_iter codepath, then release the reservation as we allocate the ordered extent, but we only create a delayed ref if the ordered extent finishes. If it has an error, we simply leak the rsv. This is apparent in running any error injecting (dmerror) fstests like btrfs/146 or btrfs/160. Such tests fail due to dmesg on umount complaining about the leaked qgroup data space. When we clean up other aspects of space on failed ordered_extents, also free the qgroup rsv. Reviewed-by: Josef Bacik CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Boris Burkov Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/inode.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 28bcba2e0590..222068bf8003 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3393,6 +3393,13 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) btrfs_free_reserved_extent(fs_info, ordered_extent->disk_bytenr, ordered_extent->disk_num_bytes, 1); + /* + * Actually free the qgroup rsv which was released when + * the ordered extent was created. + */ + btrfs_qgroup_free_refroot(fs_info, inode->root->root_key.objectid, + ordered_extent->qgroup_rsv, + BTRFS_QGROUP_RSV_DATA); } } From 91f6a538d625d360400eb03ce4d65297c695302c Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 26 Jul 2023 16:56:57 +0100 Subject: [PATCH 1437/2093] btrfs: don't start transaction when joining with TRANS_JOIN_NOSTART commit 4490e803e1fe9fab8db5025e44e23b55df54078b upstream. When joining a transaction with TRANS_JOIN_NOSTART, if we don't find a running transaction we end up creating one. This goes against the purpose of TRANS_JOIN_NOSTART which is to join a running transaction if its state is at or below the state TRANS_STATE_COMMIT_START, otherwise return an -ENOENT error and don't start a new transaction. So fix this to not create a new transaction if there's no running transaction at or below that state. CC: stable@vger.kernel.org # 4.14+ Fixes: a6d155d2e363 ("Btrfs: fix deadlock between fiemap and transaction commits") Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/transaction.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 7353f33c082c..a55556759441 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -279,10 +279,11 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info, spin_unlock(&fs_info->trans_lock); /* - * If we are ATTACH, we just want to catch the current transaction, - * and commit it. If there is no transaction, just return ENOENT. + * If we are ATTACH or TRANS_JOIN_NOSTART, we just want to catch the + * current transaction, and commit it. If there is no transaction, just + * return ENOENT. */ - if (type == TRANS_ATTACH) + if (type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART) return -ENOENT; /* From 08daa38ca212d87f77beae839bc9be71079c7abf Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 31 Jul 2023 11:13:00 -0400 Subject: [PATCH 1438/2093] btrfs: set page extent mapped after read_folio in relocate_one_page commit e7f1326cc24e22b38afc3acd328480a1183f9e79 upstream. One of the CI runs triggered the following panic assertion failed: PagePrivate(page) && page->private, in fs/btrfs/subpage.c:229 ------------[ cut here ]------------ kernel BUG at fs/btrfs/subpage.c:229! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 0 PID: 923660 Comm: btrfs Not tainted 6.5.0-rc3+ #1 pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) pc : btrfs_subpage_assert+0xbc/0xf0 lr : btrfs_subpage_assert+0xbc/0xf0 sp : ffff800093213720 x29: ffff800093213720 x28: ffff8000932138b4 x27: 000000000c280000 x26: 00000001b5d00000 x25: 000000000c281000 x24: 000000000c281fff x23: 0000000000001000 x22: 0000000000000000 x21: ffffff42b95bf880 x20: ffff42b9528e0000 x19: 0000000000001000 x18: ffffffffffffffff x17: 667274622f736620 x16: 6e69202c65746176 x15: 0000000000000028 x14: 0000000000000003 x13: 00000000002672d7 x12: 0000000000000000 x11: ffffcd3f0ccd9204 x10: ffffcd3f0554ae50 x9 : ffffcd3f0379528c x8 : ffff800093213428 x7 : 0000000000000000 x6 : ffffcd3f091771e8 x5 : ffff42b97f333948 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : ffff42b9556cde80 x0 : 000000000000004f Call trace: btrfs_subpage_assert+0xbc/0xf0 btrfs_subpage_set_dirty+0x38/0xa0 btrfs_page_set_dirty+0x58/0x88 relocate_one_page+0x204/0x5f0 relocate_file_extent_cluster+0x11c/0x180 relocate_data_extent+0xd0/0xf8 relocate_block_group+0x3d0/0x4e8 btrfs_relocate_block_group+0x2d8/0x490 btrfs_relocate_chunk+0x54/0x1a8 btrfs_balance+0x7f4/0x1150 btrfs_ioctl+0x10f0/0x20b8 __arm64_sys_ioctl+0x120/0x11d8 invoke_syscall.constprop.0+0x80/0xd8 do_el0_svc+0x6c/0x158 el0_svc+0x50/0x1b0 el0t_64_sync_handler+0x120/0x130 el0t_64_sync+0x194/0x198 Code: 91098021 b0007fa0 91346000 97e9c6d2 (d4210000) This is the same problem outlined in 17b17fcd6d44 ("btrfs: set_page_extent_mapped after read_folio in btrfs_cont_expand") , and the fix is the same. I originally looked for the same pattern elsewhere in our code, but mistakenly skipped over this code because I saw the page cache readahead before we set_page_extent_mapped, not realizing that this was only in the !page case, that we can still end up with a !uptodate page and then do the btrfs_read_folio further down. The fix here is the same as the above mentioned patch, move the set_page_extent_mapped call to after the btrfs_read_folio() block to make sure that we have the subpage blocksize stuff setup properly before using the page. CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/relocation.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d3591c7f166a..d2bdcc2cce49 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2985,9 +2985,6 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, if (!page) return -ENOMEM; } - ret = set_page_extent_mapped(page); - if (ret < 0) - goto release_page; if (PageReadahead(page)) page_cache_async_readahead(inode->i_mapping, ra, NULL, @@ -3003,6 +3000,15 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, } } + /* + * We could have lost page private when we dropped the lock to read the + * page above, make sure we set_page_extent_mapped here so we have any + * of the subpage blocksize stuff we need in place. + */ + ret = set_page_extent_mapped(page); + if (ret < 0) + goto release_page; + page_start = page_offset(page); page_end = page_start + PAGE_SIZE - 1; From b692f7d1576baf961fa02f681658640ac4edca92 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 8 Aug 2023 01:12:40 +0900 Subject: [PATCH 1439/2093] btrfs: zoned: re-enable metadata over-commit for zoned mode commit 5b135b382a360f4c87cf8896d1465b0b07f10cb0 upstream. Now that, we can re-enable metadata over-commit. As we moved the activation from the reservation time to the write time, we no longer need to ensure all the reserved bytes is properly activated. Without the metadata over-commit, it suffers from lower performance because it needs to flush the delalloc items more often and allocate more block groups. Re-enabling metadata over-commit will solve the issue. Fixes: 79417d040f4f ("btrfs: zoned: disable metadata overcommit for zoned") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/space-info.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index c7642c00a65d..2635fb4bffa0 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -404,11 +404,7 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, return 0; used = btrfs_space_info_used(space_info, true); - if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags) && - (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) - avail = 0; - else - avail = calc_available_free_space(fs_info, space_info, flush); + avail = calc_available_free_space(fs_info, space_info, flush); if (used + bytes < writable_total_bytes(fs_info, space_info) + avail) return 1; From 09974a1352d3479748cfb08dbfc39a3c019e4486 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Mon, 31 Jul 2023 19:16:34 +0800 Subject: [PATCH 1440/2093] btrfs: use the correct superblock to compare fsid in btrfs_validate_super commit d167aa76dc0683828588c25767da07fb549e4f48 upstream. The function btrfs_validate_super() should verify the fsid in the provided superblock argument. Because, all its callers expect it to do that. Such as in the following stack: write_all_supers() sb = fs_info->super_for_commit; btrfs_validate_write_super(.., sb) btrfs_validate_super(.., sb, ..) scrub_one_super() btrfs_validate_super(.., sb, ..) And check_dev_super() btrfs_validate_super(.., sb, ..) However, it currently verifies the fs_info::super_copy::fsid instead, which is not correct. Fix this using the correct fsid in the superblock argument. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Johannes Thumshirn Tested-by: Guilherme G. Piccoli Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 96369c44863a..64daae693afd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2721,11 +2721,10 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } - if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid, - BTRFS_FSID_SIZE)) { + if (memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, "superblock fsid doesn't match fsid of fs_devices: %pU != %pU", - fs_info->super_copy->fsid, fs_info->fs_devices->fsid); + sb->fsid, fs_info->fs_devices->fsid); ret = -EINVAL; } From 8bf2d4ca521d3acb57fc1607386e749b3cc92aaf Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Mon, 12 Jun 2023 17:23:59 +0800 Subject: [PATCH 1441/2093] drm/mxsfb: Disable overlay plane in mxsfb_plane_overlay_atomic_disable() commit aa656d48e871a1b062e1bbf9474d8b831c35074c upstream. When disabling overlay plane in mxsfb_plane_overlay_atomic_update(), overlay plane's framebuffer pointer is NULL. So, dereferencing it would cause a kernel Oops(NULL pointer dereferencing). Fix the issue by disabling overlay plane in mxsfb_plane_overlay_atomic_disable() instead. Fixes: cb285a5348e7 ("drm: mxsfb: Replace mxsfb_get_fb_paddr() with drm_fb_cma_get_gem_addr()") Cc: stable@vger.kernel.org # 5.19+ Signed-off-by: Liu Ying Reviewed-by: Marek Vasut Signed-off-by: Marek Vasut Link: https://patchwork.freedesktop.org/patch/msgid/20230612092359.784115-1-victor.liu@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/mxsfb/mxsfb_kms.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index 3bcc9c0f2019..7ed2516b6de0 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -611,6 +611,14 @@ static void mxsfb_plane_overlay_atomic_update(struct drm_plane *plane, writel(ctrl, mxsfb->base + LCDC_AS_CTRL); } +static void mxsfb_plane_overlay_atomic_disable(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct mxsfb_drm_private *mxsfb = to_mxsfb_drm_private(plane->dev); + + writel(0, mxsfb->base + LCDC_AS_CTRL); +} + static bool mxsfb_format_mod_supported(struct drm_plane *plane, uint32_t format, uint64_t modifier) @@ -626,6 +634,7 @@ static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = { static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = { .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_overlay_atomic_update, + .atomic_disable = mxsfb_plane_overlay_atomic_disable, }; static const struct drm_plane_funcs mxsfb_plane_funcs = { From a7e118fcc8b4431fb0d70cc4b45bad158c7c32a1 Mon Sep 17 00:00:00 2001 From: William Zhang Date: Thu, 6 Jul 2023 11:29:07 -0700 Subject: [PATCH 1442/2093] mtd: rawnand: brcmnand: Fix crash during the panic_write commit e66dd317194daae0475fe9e5577c80aa97f16cb9 upstream. When executing a NAND command within the panic write path, wait for any pending command instead of calling BUG_ON to avoid crashing while already crashing. Fixes: 27c5b17cd1b1 ("mtd: nand: add NAND driver "library" for Broadcom STB NAND controller") Signed-off-by: William Zhang Reviewed-by: Florian Fainelli Reviewed-by: Kursad Oney Reviewed-by: Kamal Dasu Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230706182909.79151-4-william.zhang@broadcom.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index d8418d7fcc37..218782c0f8c0 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -1592,7 +1592,17 @@ static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd) dev_dbg(ctrl->dev, "send native cmd %d addr 0x%llx\n", cmd, cmd_addr); - BUG_ON(ctrl->cmd_pending != 0); + /* + * If we came here through _panic_write and there is a pending + * command, try to wait for it. If it times out, rather than + * hitting BUG_ON, just return so we don't crash while crashing. + */ + if (oops_in_progress) { + if (ctrl->cmd_pending && + bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0)) + return; + } else + BUG_ON(ctrl->cmd_pending != 0); ctrl->cmd_pending = cmd; ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0); From 45fe4ad7f439799ee1b7b5f80bf82e8b34a98d25 Mon Sep 17 00:00:00 2001 From: William Zhang Date: Thu, 6 Jul 2023 11:29:08 -0700 Subject: [PATCH 1443/2093] mtd: rawnand: brcmnand: Fix potential out-of-bounds access in oob write commit 5d53244186c9ac58cb88d76a0958ca55b83a15cd upstream. When the oob buffer length is not in multiple of words, the oob write function does out-of-bounds read on the oob source buffer at the last iteration. Fix that by always checking length limit on the oob buffer read and fill with 0xff when reaching the end of the buffer to the oob registers. Fixes: 27c5b17cd1b1 ("mtd: nand: add NAND driver "library" for Broadcom STB NAND controller") Signed-off-by: William Zhang Reviewed-by: Florian Fainelli Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230706182909.79151-5-william.zhang@broadcom.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 218782c0f8c0..974201d310a8 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -1461,19 +1461,33 @@ static int write_oob_to_regs(struct brcmnand_controller *ctrl, int i, const u8 *oob, int sas, int sector_1k) { int tbytes = sas << sector_1k; - int j; + int j, k = 0; + u32 last = 0xffffffff; + u8 *plast = (u8 *)&last; /* Adjust OOB values for 1K sector size */ if (sector_1k && (i & 0x01)) tbytes = max(0, tbytes - (int)ctrl->max_oob); tbytes = min_t(int, tbytes, ctrl->max_oob); - for (j = 0; j < tbytes; j += 4) + /* + * tbytes may not be multiple of words. Make sure we don't read out of + * the boundary and stop at last word. + */ + for (j = 0; (j + 3) < tbytes; j += 4) oob_reg_write(ctrl, j, (oob[j + 0] << 24) | (oob[j + 1] << 16) | (oob[j + 2] << 8) | (oob[j + 3] << 0)); + + /* handle the remaing bytes */ + while (j < tbytes) + plast[k++] = oob[j++]; + + if (tbytes & 0x3) + oob_reg_write(ctrl, (tbytes & ~0x3), (__force u32)cpu_to_be32(last)); + return tbytes; } From 7c6ba20a0b9aeb82a6c097c74ccbecdda8e9fc25 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 18 Jul 2023 13:56:11 +0200 Subject: [PATCH 1444/2093] mtd: spi-nor: Correct flags for Winbond w25q128 commit 83e824a4a595132f9bd7ac4f5afff857bfc5991e upstream. The Winbond "w25q128" (actual vendor name W25Q128JV) has exactly the same flags as the sibling device "w25q128jv". The devices both require unlocking to enable write access. The actual product naming between devices vs the Linux strings in winbond.c: 0xef4018: "w25q128" W25Q128JV-IN/IQ/JQ 0xef7018: "w25q128jv" W25Q128JV-IM/JM The latter device, "w25q128jv" supports features named DTQ and QPI, otherwise it is the same. Not having the right flags has the annoying side effect that write access does not work. After this patch I can write to the flash on the Inteno XG6846 router. The flash memory also supports dual and quad SPI modes. This does not currently manifest, but by turning on SFDP parsing, the right SPI modes are emitted in /sys/kernel/debug/spi-nor/spi1.0/capabilities for this chip, so we also turn on this. Since we now have determined that SFDP parsing works on the device, we also detect the geometry using SFDP. After this dmesg and sysfs says: [ 1.062401] spi-nor spi1.0: w25q128 (16384 Kbytes) cat erasesize 65536 (16384*1024)/65536 = 256 sectors spi-nor sysfs: cat jedec_id ef4018 cat manufacturer winbond cat partname w25q128 hexdump -v -C sfdp 00000000 53 46 44 50 05 01 00 ff 00 05 01 10 80 00 00 ff 00000010 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000020 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000030 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000040 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000050 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000060 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000070 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff 00000080 e5 20 f9 ff ff ff ff 07 44 eb 08 6b 08 3b 42 bb 00000090 fe ff ff ff ff ff 00 00 ff ff 40 eb 0c 20 0f 52 000000a0 10 d8 00 00 36 02 a6 00 82 ea 14 c9 e9 63 76 33 000000b0 7a 75 7a 75 f7 a2 d5 5c 19 f7 4d ff e9 30 f8 80 Cc: stable@vger.kernel.org Suggested-by: Michael Walle Reviewed-by: Michael Walle Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230718-spi-nor-winbond-w25q128-v5-1-a73653ee46c3@linaro.org Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/spi-nor/winbond.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/winbond.c b/drivers/mtd/spi-nor/winbond.c index ffaa24055259..b7c775b615e8 100644 --- a/drivers/mtd/spi-nor/winbond.c +++ b/drivers/mtd/spi-nor/winbond.c @@ -120,8 +120,9 @@ static const struct flash_info winbond_nor_parts[] = { NO_SFDP_FLAGS(SECT_4K) }, { "w25q80bl", INFO(0xef4014, 0, 64 * 1024, 16) NO_SFDP_FLAGS(SECT_4K) }, - { "w25q128", INFO(0xef4018, 0, 64 * 1024, 256) - NO_SFDP_FLAGS(SECT_4K) }, + { "w25q128", INFO(0xef4018, 0, 0, 0) + PARSE_SFDP + FLAGS(SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB) }, { "w25q256", INFO(0xef4019, 0, 64 * 1024, 512) NO_SFDP_FLAGS(SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) .fixups = &w25q256_fixups }, From 31d42146fa6f65ca3dd90761e1e5ef14156f780f Mon Sep 17 00:00:00 2001 From: William Zhang Date: Thu, 6 Jul 2023 11:29:06 -0700 Subject: [PATCH 1445/2093] mtd: rawnand: brcmnand: Fix potential false time out warning commit 9cc0a598b944816f2968baf2631757f22721b996 upstream. If system is busy during the command status polling function, the driver may not get the chance to poll the status register till the end of time out and return the premature status. Do a final check after time out happens to ensure reading the correct status. Fixes: 9d2ee0a60b8b ("mtd: nand: brcmnand: Check flash #WP pin status before nand erase/program") Signed-off-by: William Zhang Reviewed-by: Florian Fainelli Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230706182909.79151-3-william.zhang@broadcom.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 974201d310a8..befbbd3544c5 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -1072,6 +1072,14 @@ static int bcmnand_ctrl_poll_status(struct brcmnand_controller *ctrl, cpu_relax(); } while (time_after(limit, jiffies)); + /* + * do a final check after time out in case the CPU was busy and the driver + * did not get enough time to perform the polling to avoid false alarms + */ + val = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS); + if ((val & mask) == expected_val) + return 0; + dev_warn(ctrl->dev, "timeout on status poll (expected %x got %x)\n", expected_val, val & mask); From 3388ca3a38a5356d97236738013df4337b84e1ed Mon Sep 17 00:00:00 2001 From: William Zhang Date: Thu, 6 Jul 2023 11:29:05 -0700 Subject: [PATCH 1446/2093] mtd: rawnand: brcmnand: Fix ECC level field setting for v7.2 controller commit 2ec2839a9062db8a592525a3fdabd42dcd9a3a9b upstream. v7.2 controller has different ECC level field size and shift in the acc control register than its predecessor and successor controller. It needs to be set specifically. Fixes: decba6d47869 ("mtd: brcmnand: Add v7.2 controller support") Signed-off-by: William Zhang Reviewed-by: Florian Fainelli Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230706182909.79151-2-william.zhang@broadcom.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/brcmnand/brcmnand.c | 74 +++++++++++++----------- 1 file changed, 41 insertions(+), 33 deletions(-) diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index befbbd3544c5..39661e23d7d4 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -272,6 +272,7 @@ struct brcmnand_controller { const unsigned int *page_sizes; unsigned int page_size_shift; unsigned int max_oob; + u32 ecc_level_shift; u32 features; /* for low-power standby/resume only */ @@ -596,6 +597,34 @@ enum { INTFC_CTLR_READY = BIT(31), }; +/*********************************************************************** + * NAND ACC CONTROL bitfield + * + * Some bits have remained constant throughout hardware revision, while + * others have shifted around. + ***********************************************************************/ + +/* Constant for all versions (where supported) */ +enum { + /* See BRCMNAND_HAS_CACHE_MODE */ + ACC_CONTROL_CACHE_MODE = BIT(22), + + /* See BRCMNAND_HAS_PREFETCH */ + ACC_CONTROL_PREFETCH = BIT(23), + + ACC_CONTROL_PAGE_HIT = BIT(24), + ACC_CONTROL_WR_PREEMPT = BIT(25), + ACC_CONTROL_PARTIAL_PAGE = BIT(26), + ACC_CONTROL_RD_ERASED = BIT(27), + ACC_CONTROL_FAST_PGM_RDIN = BIT(28), + ACC_CONTROL_WR_ECC = BIT(30), + ACC_CONTROL_RD_ECC = BIT(31), +}; + +#define ACC_CONTROL_ECC_SHIFT 16 +/* Only for v7.2 */ +#define ACC_CONTROL_ECC_EXT_SHIFT 13 + static inline bool brcmnand_non_mmio_ops(struct brcmnand_controller *ctrl) { #if IS_ENABLED(CONFIG_MTD_NAND_BRCMNAND_BCMA) @@ -737,6 +766,12 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl) else if (of_property_read_bool(ctrl->dev->of_node, "brcm,nand-has-wp")) ctrl->features |= BRCMNAND_HAS_WP; + /* v7.2 has different ecc level shift in the acc register */ + if (ctrl->nand_version == 0x0702) + ctrl->ecc_level_shift = ACC_CONTROL_ECC_EXT_SHIFT; + else + ctrl->ecc_level_shift = ACC_CONTROL_ECC_SHIFT; + return 0; } @@ -931,30 +966,6 @@ static inline int brcmnand_cmd_shift(struct brcmnand_controller *ctrl) return 0; } -/*********************************************************************** - * NAND ACC CONTROL bitfield - * - * Some bits have remained constant throughout hardware revision, while - * others have shifted around. - ***********************************************************************/ - -/* Constant for all versions (where supported) */ -enum { - /* See BRCMNAND_HAS_CACHE_MODE */ - ACC_CONTROL_CACHE_MODE = BIT(22), - - /* See BRCMNAND_HAS_PREFETCH */ - ACC_CONTROL_PREFETCH = BIT(23), - - ACC_CONTROL_PAGE_HIT = BIT(24), - ACC_CONTROL_WR_PREEMPT = BIT(25), - ACC_CONTROL_PARTIAL_PAGE = BIT(26), - ACC_CONTROL_RD_ERASED = BIT(27), - ACC_CONTROL_FAST_PGM_RDIN = BIT(28), - ACC_CONTROL_WR_ECC = BIT(30), - ACC_CONTROL_RD_ECC = BIT(31), -}; - static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl) { if (ctrl->nand_version == 0x0702) @@ -967,18 +978,15 @@ static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl) return GENMASK(4, 0); } -#define NAND_ACC_CONTROL_ECC_SHIFT 16 -#define NAND_ACC_CONTROL_ECC_EXT_SHIFT 13 - static inline u32 brcmnand_ecc_level_mask(struct brcmnand_controller *ctrl) { u32 mask = (ctrl->nand_version >= 0x0600) ? 0x1f : 0x0f; - mask <<= NAND_ACC_CONTROL_ECC_SHIFT; + mask <<= ACC_CONTROL_ECC_SHIFT; /* v7.2 includes additional ECC levels */ - if (ctrl->nand_version >= 0x0702) - mask |= 0x7 << NAND_ACC_CONTROL_ECC_EXT_SHIFT; + if (ctrl->nand_version == 0x0702) + mask |= 0x7 << ACC_CONTROL_ECC_EXT_SHIFT; return mask; } @@ -992,8 +1000,8 @@ static void brcmnand_set_ecc_enabled(struct brcmnand_host *host, int en) if (en) { acc_control |= ecc_flags; /* enable RD/WR ECC */ - acc_control |= host->hwcfg.ecc_level - << NAND_ACC_CONTROL_ECC_SHIFT; + acc_control &= ~brcmnand_ecc_level_mask(ctrl); + acc_control |= host->hwcfg.ecc_level << ctrl->ecc_level_shift; } else { acc_control &= ~ecc_flags; /* disable RD/WR ECC */ acc_control &= ~brcmnand_ecc_level_mask(ctrl); @@ -2593,7 +2601,7 @@ static int brcmnand_set_cfg(struct brcmnand_host *host, tmp &= ~brcmnand_ecc_level_mask(ctrl); tmp &= ~brcmnand_spare_area_mask(ctrl); if (ctrl->nand_version >= 0x0302) { - tmp |= cfg->ecc_level << NAND_ACC_CONTROL_ECC_SHIFT; + tmp |= cfg->ecc_level << ctrl->ecc_level_shift; tmp |= cfg->spare_area_size; } nand_writereg(ctrl, acc_control_offs, tmp); From e1769b1dfcaebb7e4272528fa2f198c6549f619b Mon Sep 17 00:00:00 2001 From: Melissa Wen Date: Thu, 31 Aug 2023 15:12:28 -0100 Subject: [PATCH 1447/2093] drm/amd/display: enable cursor degamma for DCN3+ DRM legacy gamma commit 57a943ebfcdb4a97fbb409640234bdb44bfa1953 upstream. For DRM legacy gamma, AMD display manager applies implicit sRGB degamma using a pre-defined sRGB transfer function. It works fine for DCN2 family where degamma ROM and custom curves go to the same color block. But, on DCN3+, degamma is split into two blocks: degamma ROM for pre-defined TFs and `gamma correction` for user/custom curves and degamma ROM settings doesn't apply to cursor plane. To get DRM legacy gamma working as expected, enable cursor degamma ROM for implict sRGB degamma on HW with this configuration. Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2803 Fixes: 96b020e2163f ("drm/amd/display: check attr flag before set cursor degamma on DCN3+") Signed-off-by: Melissa Wen Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 3c50b3ff7954..cd6e99cf74a0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1269,6 +1269,13 @@ void handle_cursor_update(struct drm_plane *plane, attributes.rotation_angle = 0; attributes.attribute_flags.value = 0; + /* Enable cursor degamma ROM on DCN3+ for implicit sRGB degamma in DRM + * legacy gamma setup. + */ + if (crtc_state->cm_is_degamma_srgb && + adev->dm.dc->caps.color.dpp.gamma_corr) + attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1; + attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0]; if (crtc_state->stream) { From ff536a96687cf976d89bed08d40fcaae6bf50304 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Tue, 5 Sep 2023 13:27:22 -0400 Subject: [PATCH 1448/2093] drm/amd/display: prevent potential division by zero errors commit 07e388aab042774f284a2ad75a70a194517cdad4 upstream. There are two places in apply_below_the_range() where it's possible for a divide by zero error to occur. So, to fix this make sure the divisor is non-zero before attempting the computation in both cases. Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2637 Fixes: a463b263032f ("drm/amd/display: Fix frames_to_insert math") Fixes: ded6119e825a ("drm/amd/display: Reinstate LFC optimization") Reviewed-by: Aurabindo Pillai Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/modules/freesync/freesync.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 0f39ab9dc5b4..9e74b6e8b573 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -338,7 +338,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync, * - Delta for CEIL: delta_from_mid_point_in_us_1 * - Delta for FLOOR: delta_from_mid_point_in_us_2 */ - if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) { + if (mid_point_frames_ceil && + (last_render_time_in_us / mid_point_frames_ceil) < + in_out_vrr->min_duration_in_us) { /* Check for out of range. * If using CEIL produces a value that is out of range, * then we are forced to use FLOOR. @@ -385,8 +387,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Either we've calculated the number of frames to insert, * or we need to insert min duration frames */ - if (last_render_time_in_us / frames_to_insert < - in_out_vrr->min_duration_in_us){ + if (frames_to_insert && + (last_render_time_in_us / frames_to_insert) < + in_out_vrr->min_duration_in_us){ frames_to_insert -= (frames_to_insert > 1) ? 1 : 0; } From 3988692acc92df172570bbd271647ffa1581ff34 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 8 Aug 2023 16:31:31 -0700 Subject: [PATCH 1449/2093] KVM: SVM: Take and hold ir_list_lock when updating vCPU's Physical ID entry commit 4c08e737f056fec930b416a2bd37ed266d724f95 upstream. Hoist the acquisition of ir_list_lock from avic_update_iommu_vcpu_affinity() to its two callers, avic_vcpu_load() and avic_vcpu_put(), specifically to encapsulate the write to the vCPU's entry in the AVIC Physical ID table. This will allow a future fix to pull information from the Physical ID entry when updating the IRTE, without potentially consuming stale information, i.e. without racing with the vCPU being (un)loaded. Add a comment to call out that ir_list_lock does NOT protect against multiple writers, specifically that reading the Physical ID entry in avic_vcpu_put() outside of the lock is safe. To preserve some semblance of independence from ir_list_lock, keep the READ_ONCE() in avic_vcpu_load() even though acuiring the spinlock effectively ensures the load(s) will be generated after acquiring the lock. Cc: stable@vger.kernel.org Tested-by: Alejandro Jimenez Reviewed-by: Joao Martins Link: https://lore.kernel.org/r/20230808233132.2499764-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/avic.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index e910ec5a0cc0..60d60552ce0e 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1022,10 +1022,11 @@ static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { int ret = 0; - unsigned long flags; struct amd_svm_iommu_ir *ir; struct vcpu_svm *svm = to_svm(vcpu); + lockdep_assert_held(&svm->ir_list_lock); + if (!kvm_arch_has_assigned_device(vcpu->kvm)) return 0; @@ -1033,19 +1034,15 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) * Here, we go through the per-vcpu ir_list to update all existing * interrupt remapping table entry targeting this vcpu. */ - spin_lock_irqsave(&svm->ir_list_lock, flags); - if (list_empty(&svm->ir_list)) - goto out; + return 0; list_for_each_entry(ir, &svm->ir_list, node) { ret = amd_iommu_update_ga(cpu, r, ir->data); if (ret) - break; + return ret; } -out: - spin_unlock_irqrestore(&svm->ir_list_lock, flags); - return ret; + return 0; } void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -1053,6 +1050,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) u64 entry; int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); + unsigned long flags; lockdep_assert_preemption_disabled(); @@ -1069,6 +1067,8 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (kvm_vcpu_is_blocking(vcpu)) return; + spin_lock_irqsave(&svm->ir_list_lock, flags); + entry = READ_ONCE(*(svm->avic_physical_id_cache)); entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; @@ -1077,25 +1077,40 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); + + spin_unlock_irqrestore(&svm->ir_list_lock, flags); } void avic_vcpu_put(struct kvm_vcpu *vcpu) { u64 entry; struct vcpu_svm *svm = to_svm(vcpu); + unsigned long flags; lockdep_assert_preemption_disabled(); + /* + * Note, reading the Physical ID entry outside of ir_list_lock is safe + * as only the pCPU that has loaded (or is loading) the vCPU is allowed + * to modify the entry, and preemption is disabled. I.e. the vCPU + * can't be scheduled out and thus avic_vcpu_{put,load}() can't run + * recursively. + */ entry = READ_ONCE(*(svm->avic_physical_id_cache)); /* Nothing to do if IsRunning == '0' due to vCPU blocking. */ if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) return; + spin_lock_irqsave(&svm->ir_list_lock, flags); + avic_update_iommu_vcpu_affinity(vcpu, -1, 0); entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + } void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) From ba82001e4118d1381d73e5109cefb9888b1f845b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Aug 2023 18:36:18 -0700 Subject: [PATCH 1450/2093] KVM: SVM: Don't inject #UD if KVM attempts to skip SEV guest insn commit cb49631ad111570f1bad37702c11c2ae07fa2e3c upstream. Don't inject a #UD if KVM attempts to "emulate" to skip an instruction for an SEV guest, and instead resume the guest and hope that it can make forward progress. When commit 04c40f344def ("KVM: SVM: Inject #UD on attempted emulation for SEV guest w/o insn buffer") added the completely arbitrary #UD behavior, there were no known scenarios where a well-behaved guest would induce a VM-Exit that triggered emulation, i.e. it was thought that injecting #UD would be helpful. However, now that KVM (correctly) attempts to re-inject INT3/INTO, e.g. if a #NPF is encountered when attempting to deliver the INT3/INTO, an SEV guest can trigger emulation without a buffer, through no fault of its own. Resuming the guest and retrying the INT3/INTO is architecturally wrong, e.g. the vCPU will incorrectly re-hit code #DBs, but for SEV guests there is literally no other option that has a chance of making forward progress. Drop the #UD injection for all "skip" emulation, not just those related to INT3/INTO, even though that means that the guest will likely end up in an infinite loop instead of getting a #UD (the vCPU may also crash, e.g. if KVM emulated everything about an instruction except for advancing RIP). There's no evidence that suggests that an unexpected #UD is actually better than hanging the vCPU, e.g. a soft-hung vCPU can still respond to IRQs and NMIs to generate a backtrace. Reported-by: Wu Zongyo Closes: https://lore.kernel.org/all/8eb933fd-2cf3-d7a9-32fe-2a1d82eac42a@mail.ustc.edu.cn Fixes: 6ef88d6e36c2 ("KVM: SVM: Re-inject INT3/INTO instead of retrying the instruction") Cc: stable@vger.kernel.org Cc: Tom Lendacky Link: https://lore.kernel.org/r/20230825013621.2845700-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/svm.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a96f9a17e8b5..7e4d66be18ef 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -366,6 +366,8 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK; } +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, bool commit_side_effects) @@ -386,6 +388,14 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, } if (!svm->next_rip) { + /* + * FIXME: Drop this when kvm_emulate_instruction() does the + * right thing and treats "can't emulate" as outright failure + * for EMULTYPE_SKIP. + */ + if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0)) + return 0; + if (unlikely(!commit_side_effects)) old_rflags = svm->vmcb->save.rflags; @@ -4592,16 +4602,25 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and * decode garbage. * - * Inject #UD if KVM reached this point without an instruction buffer. - * In practice, this path should never be hit by a well-behaved guest, - * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path - * is still theoretically reachable, e.g. via unaccelerated fault-like - * AVIC access, and needs to be handled by KVM to avoid putting the - * guest into an infinite loop. Injecting #UD is somewhat arbitrary, - * but its the least awful option given lack of insight into the guest. + * If KVM is NOT trying to simply skip an instruction, inject #UD if + * KVM reached this point without an instruction buffer. In practice, + * this path should never be hit by a well-behaved guest, e.g. KVM + * doesn't intercept #UD or #GP for SEV guests, but this path is still + * theoretically reachable, e.g. via unaccelerated fault-like AVIC + * access, and needs to be handled by KVM to avoid putting the guest + * into an infinite loop. Injecting #UD is somewhat arbitrary, but + * its the least awful option given lack of insight into the guest. + * + * If KVM is trying to skip an instruction, simply resume the guest. + * If a #NPF occurs while the guest is vectoring an INT3/INTO, then KVM + * will attempt to re-inject the INT3/INTO and skip the instruction. + * In that scenario, retrying the INT3/INTO and hoping the guest will + * make forward progress is the only option that has a chance of + * success (and in practice it will work the vast majority of the time). */ if (unlikely(!insn)) { - kvm_queue_exception(vcpu, UD_VECTOR); + if (!(emul_type & EMULTYPE_SKIP)) + kvm_queue_exception(vcpu, UD_VECTOR); return false; } From 5c18ace750e4d4d58d7da02d1c669bf21c824158 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Aug 2023 19:23:56 -0700 Subject: [PATCH 1451/2093] KVM: SVM: Get source vCPUs from source VM for SEV-ES intrahost migration commit f1187ef24eb8f36e8ad8106d22615ceddeea6097 upstream. Fix a goof where KVM tries to grab source vCPUs from the destination VM when doing intrahost migration. Grabbing the wrong vCPU not only hoses the guest, it also crashes the host due to the VMSA pointer being left NULL. BUG: unable to handle page fault for address: ffffe38687000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 39 PID: 17143 Comm: sev_migrate_tes Tainted: GO 6.5.0-smp--fff2e47e6c3b-next #151 Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 34.28.0 07/10/2023 RIP: 0010:__free_pages+0x15/0xd0 RSP: 0018:ffff923fcf6e3c78 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffe38687000000 RCX: 0000000000000100 RDX: 0000000000000100 RSI: 0000000000000000 RDI: ffffe38687000000 RBP: ffff923fcf6e3c88 R08: ffff923fcafb0000 R09: 0000000000000000 R10: 0000000000000000 R11: ffffffff83619b90 R12: ffff923fa9540000 R13: 0000000000080007 R14: ffff923f6d35d000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff929d0d7c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffe38687000000 CR3: 0000005224c34005 CR4: 0000000000770ee0 PKRU: 55555554 Call Trace: sev_free_vcpu+0xcb/0x110 [kvm_amd] svm_vcpu_free+0x75/0xf0 [kvm_amd] kvm_arch_vcpu_destroy+0x36/0x140 [kvm] kvm_destroy_vcpus+0x67/0x100 [kvm] kvm_arch_destroy_vm+0x161/0x1d0 [kvm] kvm_put_kvm+0x276/0x560 [kvm] kvm_vm_release+0x25/0x30 [kvm] __fput+0x106/0x280 ____fput+0x12/0x20 task_work_run+0x86/0xb0 do_exit+0x2e3/0x9c0 do_group_exit+0xb1/0xc0 __x64_sys_exit_group+0x1b/0x20 do_syscall_64+0x41/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd CR2: ffffe38687000000 Fixes: 6defa24d3b12 ("KVM: SEV: Init target VMCBs in sev_migrate_from") Cc: stable@vger.kernel.org Cc: Peter Gonda Reviewed-by: Peter Gonda Reviewed-by: Pankaj Gupta Link: https://lore.kernel.org/r/20230825022357.2852133-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index e0437acb5cf7..9a1fa28443ae 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1723,7 +1723,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) * Note, the source is not required to have the same number of * vCPUs as the destination when migrating a vanilla SEV VM. */ - src_vcpu = kvm_get_vcpu(dst_kvm, i); + src_vcpu = kvm_get_vcpu(src_kvm, i); src_svm = to_svm(src_vcpu); /* From 6c1ecfea1daf6e75c46e295aad99dfbafd878897 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 28 Jul 2023 18:15:48 -0700 Subject: [PATCH 1452/2093] KVM: nSVM: Check instead of asserting on nested TSC scaling support commit 7cafe9b8e22bb3d77f130c461aedf6868c4aaf58 upstream. Check for nested TSC scaling support on nested SVM VMRUN instead of asserting that TSC scaling is exposed to L1 if L1's MSR_AMD64_TSC_RATIO has diverged from KVM's default. Userspace can trigger the WARN at will by writing the MSR and then updating guest CPUID to hide the feature (modifying guest CPUID is allowed anytime before KVM_RUN). E.g. hacking KVM's state_test selftest to do vcpu_set_msr(vcpu, MSR_AMD64_TSC_RATIO, 0); vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_TSCRATEMSR); after restoring state in a new VM+vCPU yields an endless supply of: ------------[ cut here ]------------ WARNING: CPU: 164 PID: 62565 at arch/x86/kvm/svm/nested.c:699 nested_vmcb02_prepare_control+0x3d6/0x3f0 [kvm_amd] Call Trace: enter_svm_guest_mode+0x114/0x560 [kvm_amd] nested_svm_vmrun+0x260/0x330 [kvm_amd] vmrun_interception+0x29/0x30 [kvm_amd] svm_invoke_exit_handler+0x35/0x100 [kvm_amd] svm_handle_exit+0xe7/0x180 [kvm_amd] kvm_arch_vcpu_ioctl_run+0x1eab/0x2570 [kvm] kvm_vcpu_ioctl+0x4c9/0x5b0 [kvm] __se_sys_ioctl+0x7a/0xc0 __x64_sys_ioctl+0x21/0x30 do_syscall_64+0x41/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x45ca1b Note, the nested #VMEXIT path has the same flaw, but needs a different fix and will be handled separately. Fixes: 5228eb96a487 ("KVM: x86: nSVM: implement nested TSC scaling") Cc: Maxim Levitsky Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230729011608.1065019-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/nested.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 92268645a5fe..798845699a58 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -660,10 +660,9 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) { - WARN_ON(!svm->tsc_scaling_enabled); + if (svm->tsc_scaling_enabled && + svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) nested_svm_update_tsc_ratio_msr(vcpu); - } vmcb02->control.int_ctl = (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | From 5b2b0535fa7adee7e295fed0a3095082131a8d05 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 28 Jul 2023 18:15:49 -0700 Subject: [PATCH 1453/2093] KVM: nSVM: Load L1's TSC multiplier based on L1 state, not L2 state commit 0c94e2468491cbf0754f49a5136ab51294a96b69 upstream. When emulating nested VM-Exit, load L1's TSC multiplier if L1's desired ratio doesn't match the current ratio, not if the ratio L1 is using for L2 diverges from the default. Functionally, the end result is the same as KVM will run L2 with L1's multiplier if L2's multiplier is the default, i.e. checking that L1's multiplier is loaded is equivalent to checking if L2 has a non-default multiplier. However, the assertion that TSC scaling is exposed to L1 is flawed, as userspace can trigger the WARN at will by writing the MSR and then updating guest CPUID to hide the feature (modifying guest CPUID is allowed anytime before KVM_RUN). E.g. hacking KVM's state_test selftest to do vcpu_set_msr(vcpu, MSR_AMD64_TSC_RATIO, 0); vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_TSCRATEMSR); after restoring state in a new VM+vCPU yields an endless supply of: ------------[ cut here ]------------ WARNING: CPU: 10 PID: 206939 at arch/x86/kvm/svm/nested.c:1105 nested_svm_vmexit+0x6af/0x720 [kvm_amd] Call Trace: nested_svm_exit_handled+0x102/0x1f0 [kvm_amd] svm_handle_exit+0xb9/0x180 [kvm_amd] kvm_arch_vcpu_ioctl_run+0x1eab/0x2570 [kvm] kvm_vcpu_ioctl+0x4c9/0x5b0 [kvm] ? trace_hardirqs_off+0x4d/0xa0 __se_sys_ioctl+0x7a/0xc0 __x64_sys_ioctl+0x21/0x30 do_syscall_64+0x41/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Unlike the nested VMRUN path, hoisting the svm->tsc_scaling_enabled check into the if-statement is wrong as KVM needs to ensure L1's multiplier is loaded in the above scenario. Alternatively, the WARN_ON() could simply be deleted, but that would make KVM's behavior even more subtle, e.g. it's not immediately obvious why it's safe to write MSR_AMD64_TSC_RATIO when checking only tsc_ratio_msr. Fixes: 5228eb96a487 ("KVM: x86: nSVM: implement nested TSC scaling") Cc: Maxim Levitsky Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230729011608.1065019-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/nested.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 798845699a58..8053974af326 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1021,8 +1021,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); } - if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) { - WARN_ON(!svm->tsc_scaling_enabled); + if (kvm_caps.has_tsc_control && + vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) { vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); } From 12645e623f287f60b72bca09941b10f5c2adf2fc Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 8 Aug 2023 16:31:32 -0700 Subject: [PATCH 1454/2093] KVM: SVM: Set target pCPU during IRTE update if target vCPU is running commit f3cebc75e7425d6949d726bb8e937095b0aef025 upstream. Update the target pCPU for IOMMU doorbells when updating IRTE routing if KVM is actively running the associated vCPU. KVM currently only updates the pCPU when loading the vCPU (via avic_vcpu_load()), and so doorbell events will be delayed until the vCPU goes through a put+load cycle (which might very well "never" happen for the lifetime of the VM). To avoid inserting a stale pCPU, e.g. due to racing between updating IRTE routing and vCPU load/put, get the pCPU information from the vCPU's Physical APIC ID table entry (a.k.a. avic_physical_id_cache in KVM) and update the IRTE while holding ir_list_lock. Add comments with --verbose enabled to explain exactly what is and isn't protected by ir_list_lock. Fixes: 411b44ba80ab ("svm: Implements update_pi_irte hook to setup posted interrupt") Reported-by: dengqiao.joey Cc: stable@vger.kernel.org Cc: Alejandro Jimenez Cc: Joao Martins Cc: Maxim Levitsky Cc: Suravee Suthikulpanit Tested-by: Alejandro Jimenez Reviewed-by: Joao Martins Link: https://lore.kernel.org/r/20230808233132.2499764-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/avic.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 60d60552ce0e..d3e66740c7c6 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -810,6 +810,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) int ret = 0; unsigned long flags; struct amd_svm_iommu_ir *ir; + u64 entry; /** * In some cases, the existing irte is updated and re-set, @@ -843,6 +844,18 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) ir->data = pi->ir_data; spin_lock_irqsave(&svm->ir_list_lock, flags); + + /* + * Update the target pCPU for IOMMU doorbells if the vCPU is running. + * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM + * will update the pCPU info when the vCPU awkened and/or scheduled in. + * See also avic_vcpu_load(). + */ + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) + amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK, + true, pi->ir_data); + list_add(&ir->node, &svm->ir_list); spin_unlock_irqrestore(&svm->ir_list_lock, flags); out: @@ -1067,6 +1080,13 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (kvm_vcpu_is_blocking(vcpu)) return; + /* + * Grab the per-vCPU interrupt remapping lock even if the VM doesn't + * _currently_ have assigned devices, as that can change. Holding + * ir_list_lock ensures that either svm_ir_list_add() will consume + * up-to-date entry information, or that this task will wait until + * svm_ir_list_add() completes to set the new target pCPU. + */ spin_lock_irqsave(&svm->ir_list_lock, flags); entry = READ_ONCE(*(svm->avic_physical_id_cache)); @@ -1102,6 +1122,14 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) return; + /* + * Take and hold the per-vCPU interrupt remapping lock while updating + * the Physical ID entry even though the lock doesn't protect against + * multiple writers (see above). Holding ir_list_lock ensures that + * either svm_ir_list_add() will consume up-to-date entry information, + * or that this task will wait until svm_ir_list_add() completes to + * mark the vCPU as not running. + */ spin_lock_irqsave(&svm->ir_list_lock, flags); avic_update_iommu_vcpu_affinity(vcpu, -1, 0); From 60b5ef4cf82c866816564ef9d9294f5051352ef0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 24 Aug 2023 19:23:57 -0700 Subject: [PATCH 1455/2093] KVM: SVM: Skip VMSA init in sev_es_init_vmcb() if pointer is NULL commit 1952e74da96fb3e48b72a2d0ece78c688a5848c1 upstream. Skip initializing the VMSA physical address in the VMCB if the VMSA is NULL, which occurs during intrahost migration as KVM initializes the VMCB before copying over state from the source to the destination (including the VMSA and its physical address). In normal builds, __pa() is just math, so the bug isn't fatal, but with CONFIG_DEBUG_VIRTUAL=y, the validity of the virtual address is verified and passing in NULL will make the kernel unhappy. Fixes: 6defa24d3b12 ("KVM: SEV: Init target VMCBs in sev_migrate_from") Cc: stable@vger.kernel.org Cc: Peter Gonda Reviewed-by: Peter Gonda Reviewed-by: Pankaj Gupta Link: https://lore.kernel.org/r/20230825022357.2852133-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/sev.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 9a1fa28443ae..d08d5e085649 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2951,9 +2951,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* * An SEV-ES guest requires a VMSA area that is a separate from the * VMCB page. Do not include the encryption mask on the VMSA physical - * address since hardware will access it using the guest key. + * address since hardware will access it using the guest key. Note, + * the VMSA will be NULL if this vCPU is the destination for intrahost + * migration, and will be copied later. */ - svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); + if (svm->sev_es.vmsa) + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); From ec5409612255e1a73b388d9b4f070905e7a98ee7 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 18 Jul 2023 15:37:18 +0100 Subject: [PATCH 1456/2093] MIPS: Fix CONFIG_CPU_DADDI_WORKAROUNDS `modules_install' regression MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a79a404e6c2241ebc528b9ebf4c0832457b498c3 upstream. Remove a build-time check for the presence of the GCC `-msym32' option. This option has been there since GCC 4.1.0, which is below the minimum required as at commit 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed"), when an error message: arch/mips/Makefile:306: *** CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32. Stop. started to trigger for the `modules_install' target with configurations such as `decstation_64_defconfig' that set CONFIG_CPU_DADDI_WORKAROUNDS, because said commit has made `cc-option-yn' an undefined function for non-build targets. Reported-by: Jan-Benedict Glaw Signed-off-by: Maciej W. Rozycki Fixes: 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed") Cc: stable@vger.kernel.org # v5.13+ Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index fe64ad43ba88..75cf36450b62 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -308,8 +308,8 @@ ifdef CONFIG_64BIT endif endif - ifeq ($(KBUILD_SYM32)$(call cc-option-yn,-msym32), yy) - cflags-y += -msym32 -DKBUILD_64BIT_SYM32 + ifeq ($(KBUILD_SYM32), y) + cflags-$(KBUILD_SYM32) += -msym32 -DKBUILD_64BIT_SYM32 else ifeq ($(CONFIG_CPU_DADDI_WORKAROUNDS), y) $(error CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32) From cb0940640d51bc68315b94cc858a3a995b381a87 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 31 Jul 2023 02:49:32 -0700 Subject: [PATCH 1457/2093] perf hists browser: Fix hierarchy mode header commit e2cabf2a44791f01c21f8d5189b946926e34142e upstream. The commit ef9ff6017e3c4593 ("perf ui browser: Move the extra title lines from the hists browser") introduced ui_browser__gotorc_title() to help moving non-title lines easily. But it missed to update the title for the hierarchy mode so it won't print the header line on TUI at all. $ perf report --hierarchy Fixes: ef9ff6017e3c4593 ("perf ui browser: Move the extra title lines from the hists browser") Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230731094934.1616495-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/ui/browsers/hists.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index b72ee6822222..962371ea8bcd 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1779,7 +1779,7 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser) hists_browser__scnprintf_hierarchy_headers(browser, headers, sizeof(headers)); - ui_browser__gotorc(&browser->b, 0, 0); + ui_browser__gotorc_title(&browser->b, 0, 0); ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1); } From be69e8c8f5c2fa3a11690205fb7a1be7063a582a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 25 Aug 2023 09:41:51 -0700 Subject: [PATCH 1458/2093] perf test shell stat_bpf_counters: Fix test on Intel commit 68ca249c964f520af7f8763e22f12bd26b57b870 upstream. As of now, bpf counters (bperf) don't support event groups. But the default perf stat includes topdown metrics if supported (on recent Intel machines) which require groups. That makes perf stat exiting. $ sudo perf stat --bpf-counter true bpf managed perf events do not yet support groups. Actually the test explicitly uses cycles event only, but it missed to pass the option when it checks the availability of the command. Fixes: 2c0cb9f56020d2ea ("perf test: Add a shell test for 'perf stat --bpf-counters' new option") Reviewed-by: Song Liu Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230825164152.165610-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/tests/shell/stat_bpf_counters.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 13473aeba489..6bf24b85294c 100755 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -22,10 +22,10 @@ compare_number() } # skip if --bpf-counters is not supported -if ! perf stat --bpf-counters true > /dev/null 2>&1; then +if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then if [ "$1" = "-v" ]; then echo "Skipping: --bpf-counters not supported" - perf --no-pager stat --bpf-counters true || true + perf --no-pager stat -e cycles --bpf-counters true || true fi exit 2 fi From f4618f1316294abf5088d3a32f38a6ba19ce08f9 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 25 Aug 2023 08:25:49 -0700 Subject: [PATCH 1459/2093] perf tools: Handle old data in PERF_RECORD_ATTR commit 9bf63282ea77a531ea58acb42fb3f40d2d1e4497 upstream. The PERF_RECORD_ATTR is used for a pipe mode to describe an event with attribute and IDs. The ID table comes after the attr and it calculate size of the table using the total record size and the attr size. n_ids = (total_record_size - end_of_the_attr_field) / sizeof(u64) This is fine for most use cases, but sometimes it saves the pipe output in a file and then process it later. And it becomes a problem if there is a change in attr size between the record and report. $ perf record -o- > perf-pipe.data # old version $ perf report -i- < perf-pipe.data # new version For example, if the attr size is 128 and it has 4 IDs, then it would save them in 168 byte like below: 8 byte: perf event header { .type = PERF_RECORD_ATTR, .size = 168 }, 128 byte: perf event attr { .size = 128, ... }, 32 byte: event IDs [] = { 1234, 1235, 1236, 1237 }, But when report later, it thinks the attr size is 136 then it only read the last 3 entries as ID. 8 byte: perf event header { .type = PERF_RECORD_ATTR, .size = 168 }, 136 byte: perf event attr { .size = 136, ... }, 24 byte: event IDs [] = { 1235, 1236, 1237 }, // 1234 is missing So it should use the recorded version of the attr. The attr has the size field already then it should honor the size when reading data. Fixes: 2c46dbb517a10b18 ("perf: Convert perf header attrs into attr events") Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Tom Zanussi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230825152552.112913-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/header.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 98dfaf84bd13..9e2dce70b130 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -4331,7 +4331,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, union perf_event *event, struct evlist **pevlist) { - u32 i, ids, n_ids; + u32 i, n_ids; + u64 *ids; struct evsel *evsel; struct evlist *evlist = *pevlist; @@ -4347,9 +4348,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, evlist__add(evlist, evsel); - ids = event->header.size; - ids -= (void *)&event->attr.id - (void *)event; - n_ids = ids / sizeof(u64); + n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size; + n_ids = n_ids / sizeof(u64); /* * We don't have the cpu and thread maps on the header, so * for allocating the perf_sample_id table we fake 1 cpu and @@ -4358,8 +4358,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, if (perf_evsel__alloc_id(&evsel->core, 1, n_ids)) return -ENOMEM; + ids = (void *)&event->attr.attr + event->attr.attr.size; for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]); } return 0; From c29bfda64b44bc20b99a2d86fc7db9c1e4cb8931 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 31 Jul 2023 02:49:33 -0700 Subject: [PATCH 1460/2093] perf hists browser: Fix the number of entries for 'e' key commit f6b8436bede3e80226e8b2100279c4450c73806a upstream. The 'e' key is to toggle expand/collapse the selected entry only. But the current code has a bug that it only increases the number of entries by 1 in the hierarchy mode so users cannot move under the current entry after the key stroke. This is due to a wrong assumption in the hist_entry__set_folding(). The commit b33f922651011eff ("perf hists browser: Put hist_entry folding logic into single function") factored out the code, but actually it should be handled separately. The hist_browser__set_folding() is to update fold state for each entry so it needs to traverse all (child) entries regardless of the current fold state. So it increases the number of entries by 1. But the hist_entry__set_folding() only cares the currently selected entry and its all children. So it should count all unfolded child entries. This code is implemented in hist_browser__toggle_fold() already so we can just call it. Fixes: b33f922651011eff ("perf hists browser: Put hist_entry folding logic into single function") Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230731094934.1616495-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/ui/browsers/hists.c | 58 ++++++++++++++-------------------- 1 file changed, 24 insertions(+), 34 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 962371ea8bcd..fd3e67d2c6bd 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -407,11 +407,6 @@ static bool hist_browser__selection_has_children(struct hist_browser *browser) return container_of(ms, struct callchain_list, ms)->has_children; } -static bool hist_browser__he_selection_unfolded(struct hist_browser *browser) -{ - return browser->he_selection ? browser->he_selection->unfolded : false; -} - static bool hist_browser__selection_unfolded(struct hist_browser *browser) { struct hist_entry *he = browser->he_selection; @@ -584,8 +579,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, return n; } -static void __hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *hb, bool unfold) +static void hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *hb, bool unfold) { hist_entry__init_have_children(he); he->unfolded = unfold ? he->has_children : false; @@ -603,34 +598,12 @@ static void __hist_entry__set_folding(struct hist_entry *he, he->nr_rows = 0; } -static void hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *browser, bool unfold) -{ - double percent; - - percent = hist_entry__get_percent_limit(he); - if (he->filtered || percent < browser->min_pcnt) - return; - - __hist_entry__set_folding(he, browser, unfold); - - if (!he->depth || unfold) - browser->nr_hierarchy_entries++; - if (he->leaf) - browser->nr_callchain_rows += he->nr_rows; - else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { - browser->nr_hierarchy_entries++; - he->has_no_entry = true; - he->nr_rows = 1; - } else - he->has_no_entry = false; -} - static void __hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; struct hist_entry *he; + double percent; nd = rb_first_cached(&browser->hists->entries); while (nd) { @@ -640,6 +613,21 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold) nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); hist_entry__set_folding(he, browser, unfold); + + percent = hist_entry__get_percent_limit(he); + if (he->filtered || percent < browser->min_pcnt) + continue; + + if (!he->depth || unfold) + browser->nr_hierarchy_entries++; + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { + browser->nr_hierarchy_entries++; + he->has_no_entry = true; + he->nr_rows = 1; + } else + he->has_no_entry = false; } } @@ -659,8 +647,10 @@ static void hist_browser__set_folding_selected(struct hist_browser *browser, boo if (!browser->he_selection) return; - hist_entry__set_folding(browser->he_selection, browser, unfold); - browser->b.nr_entries = hist_browser__nr_entries(browser); + if (unfold == browser->he_selection->unfolded) + return; + + hist_browser__toggle_fold(browser); } static void ui_browser__warn_lost_events(struct ui_browser *browser) @@ -732,8 +722,8 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l hist_browser__set_folding(browser, true); break; case 'e': - /* Expand the selected entry. */ - hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser)); + /* Toggle expand/collapse the selected entry. */ + hist_browser__toggle_fold(browser); break; case 'H': browser->show_headers = !browser->show_headers; From 2d7a6fcb1f232c91fe405161d2ba5731ccb97a34 Mon Sep 17 00:00:00 2001 From: Wenjing Liu Date: Tue, 15 Aug 2023 10:47:52 -0400 Subject: [PATCH 1461/2093] drm/amd/display: always switch off ODM before committing more streams commit 49a30c3d1a2258fc93cfe6eea8e4951dabadc824 upstream. ODM power optimization is only supported with single stream. When ODM power optimization is enabled, we might not have enough free pipes for enabling other stream. So when we are committing more than 1 stream we should first switch off ODM power optimization to make room for new stream and then allocating pipe resource for the new stream. Cc: stable@vger.kernel.org Fixes: 59de751e3845 ("drm/amd/display: add ODM case when looking for first split pipe") Reviewed-by: Dillon Varone Acked-by: Hamza Mahfooz Signed-off-by: Wenjing Liu Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 674ab6d9b31e..0a7c083afe3c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1977,12 +1977,12 @@ enum dc_status dc_commit_streams(struct dc *dc, } } - /* Check for case where we are going from odm 2:1 to max - * pipe scenario. For these cases, we will call - * commit_minimal_transition_state() to exit out of odm 2:1 - * first before processing new streams + /* ODM Combine 2:1 power optimization is only applied for single stream + * scenario, it uses extra pipes than needed to reduce power consumption + * We need to switch off this feature to make room for new streams. */ - if (stream_count == dc->res_pool->pipe_count) { + if (stream_count > dc->current_state->stream_count && + dc->current_state->stream_count == 1) { for (i = 0; i < dc->res_pool->pipe_count; i++) { pipe = &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->next_odm_pipe) From b53fee19ec5e07e5553f362cad8a3e00cf6d16ab Mon Sep 17 00:00:00 2001 From: Gabe Teeger Date: Mon, 14 Aug 2023 16:06:18 -0400 Subject: [PATCH 1462/2093] drm/amd/display: Remove wait while locked commit 5a3ccb1400339268c5e3dc1fa044a7f6c7f59a02 upstream. [Why] We wait for mpc idle while in a locked state, leading to potential deadlock. [What] Move the wait_for_idle call to outside of HW lock. This and a call to wait_drr_doublebuffer_pending_clear are moved added to a new static helper function called wait_for_outstanding_hw_updates, to make the interface clearer. Cc: stable@vger.kernel.org Fixes: 8f0d304d21b3 ("drm/amd/display: Do not commit pipe when updating DRR") Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Gabe Teeger Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/Makefile | 1 + drivers/gpu/drm/amd/display/dc/core/dc.c | 58 +++++++++++++------ .../drm/amd/display/dc/dcn20/dcn20_hwseq.c | 11 ---- 3 files changed, 42 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile index b9effadfc4bb..89da06033332 100644 --- a/drivers/gpu/drm/amd/display/dc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/Makefile @@ -82,3 +82,4 @@ DC_EDID += dc_edid_parser.o AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB)) AMD_DISPLAY_EDID = $(addprefix $(AMDDALPATH)/dc/,$(DC_EDID)) AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB) $(AMD_DISPLAY_EDID) + diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 0a7c083afe3c..16c05a24ac7a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3361,6 +3361,45 @@ void dc_dmub_update_dirty_rect(struct dc *dc, } } +static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context) +{ +/* + * This function calls HWSS to wait for any potentially double buffered + * operations to complete. It should be invoked as a pre-amble prior + * to full update programming before asserting any HW locks. + */ + int pipe_idx; + int opp_inst; + int opp_count = dc->res_pool->pipe_count; + struct hubp *hubp; + int mpcc_inst; + const struct pipe_ctx *pipe_ctx; + + for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) { + pipe_ctx = &dc_context->res_ctx.pipe_ctx[pipe_idx]; + + if (!pipe_ctx->stream) + continue; + + if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear) + pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg); + + hubp = pipe_ctx->plane_res.hubp; + if (!hubp) + continue; + + mpcc_inst = hubp->inst; + // MPCC inst is equal to pipe index in practice + for (opp_inst = 0; opp_inst < opp_count; opp_inst++) { + if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) { + dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst); + dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false; + break; + } + } + } +} + static void commit_planes_for_stream(struct dc *dc, struct dc_surface_update *srf_updates, int surface_count, @@ -3378,24 +3417,9 @@ static void commit_planes_for_stream(struct dc *dc, // dc->current_state anymore, so we have to cache it before we apply // the new SubVP context subvp_prev_use = false; - - dc_z10_restore(dc); - - if (update_type == UPDATE_TYPE_FULL) { - /* wait for all double-buffer activity to clear on all pipes */ - int pipe_idx; - - for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx]; - - if (!pipe_ctx->stream) - continue; - - if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear) - pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg); - } - } + if (update_type == UPDATE_TYPE_FULL) + wait_for_outstanding_hw_updates(dc, context); if (get_seamless_boot_stream_count(context) > 0 && surface_count > 0) { /* Optimize seamless boot flag keeps clocks and watermarks high until diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 4ef632864948..fbc188812ccc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1515,17 +1515,6 @@ static void dcn20_update_dchubp_dpp( || plane_state->update_flags.bits.global_alpha_change || plane_state->update_flags.bits.per_pixel_alpha_change) { // MPCC inst is equal to pipe index in practice - int mpcc_inst = hubp->inst; - int opp_inst; - int opp_count = dc->res_pool->pipe_count; - - for (opp_inst = 0; opp_inst < opp_count; opp_inst++) { - if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) { - dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst); - dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false; - break; - } - } hws->funcs.update_mpcc(dc, pipe_ctx); } From cb30ff2adb10a660ded094b088aca763aaf74dea Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Tue, 15 Aug 2023 09:13:37 -0400 Subject: [PATCH 1463/2093] drm/amdgpu: register a dirty framebuffer callback for fbcon commit 0a611560f53bfd489e33f4a718c915f1a6123d03 upstream. fbcon requires that we implement &drm_framebuffer_funcs.dirty. Otherwise, the framebuffer might take a while to flush (which would manifest as noticeable lag). However, we can't enable this callback for non-fbcon cases since it may cause too many atomic commits to be made at once. So, implement amdgpu_dirtyfb() and only enable it for fbcon framebuffers (we can use the "struct drm_file file" parameter in the callback to check for this since it is only NULL when called by fbcon, at least in the mainline kernel) on devices that support atomic KMS. Cc: Aurabindo Pillai Cc: Mario Limonciello Cc: stable@vger.kernel.org # 6.1+ Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2519 Reviewed-by: Mario Limonciello Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 26 ++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index dd6f9ae6fbe9..2fced451f0ae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -38,6 +38,8 @@ #include #include #include +#include +#include #include #include #include @@ -493,11 +495,29 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector, return true; } +static int amdgpu_dirtyfb(struct drm_framebuffer *fb, struct drm_file *file, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, unsigned int num_clips) +{ + + if (file) + return -ENOSYS; + + return drm_atomic_helper_dirtyfb(fb, file, flags, color, clips, + num_clips); +} + static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, }; +static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = { + .destroy = drm_gem_fb_destroy, + .create_handle = drm_gem_fb_create_handle, + .dirty = amdgpu_dirtyfb +}; + uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, uint64_t bo_flags) { @@ -1100,7 +1120,11 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev, if (ret) goto err; - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (drm_drv_uses_atomic_modeset(dev)) + ret = drm_framebuffer_init(dev, &rfb->base, + &amdgpu_fb_funcs_atomic); + else + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); if (ret) goto err; From 9acb294ebdfef8a619f0132259458de029c69330 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Sun, 3 Sep 2023 15:10:25 +0800 Subject: [PATCH 1464/2093] kunit: Fix wild-memory-access bug in kunit_free_suite_set() [ Upstream commit 2810c1e99867a811e631dd24e63e6c1e3b78a59d ] Inject fault while probing kunit-example-test.ko, if kstrdup() fails in mod_sysfs_setup() in load_module(), the mod->state will switch from MODULE_STATE_COMING to MODULE_STATE_GOING instead of from MODULE_STATE_LIVE to MODULE_STATE_GOING, so only kunit_module_exit() will be called without kunit_module_init(), and the mod->kunit_suites is no set correctly and the free in kunit_free_suite_set() will cause below wild-memory-access bug. The mod->state state machine when load_module() succeeds: MODULE_STATE_UNFORMED ---> MODULE_STATE_COMING ---> MODULE_STATE_LIVE ^ | | | delete_module +---------------- MODULE_STATE_GOING <---------+ The mod->state state machine when load_module() fails at mod_sysfs_setup(): MODULE_STATE_UNFORMED ---> MODULE_STATE_COMING ---> MODULE_STATE_GOING ^ | | | +-----------------------------------------------+ Call kunit_module_init() at MODULE_STATE_COMING state to fix the issue because MODULE_STATE_LIVE is transformed from it. Unable to handle kernel paging request at virtual address ffffff341e942a88 KASAN: maybe wild-memory-access in range [0x0003f9a0f4a15440-0x0003f9a0f4a15447] Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 swapper pgtable: 4k pages, 48-bit VAs, pgdp=00000000441ea000 [ffffff341e942a88] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP Modules linked in: kunit_example_test(-) cfg80211 rfkill 8021q garp mrp stp llc ipv6 [last unloaded: kunit_example_test] CPU: 3 PID: 2035 Comm: modprobe Tainted: G W N 6.5.0-next-20230828+ #136 Hardware name: linux,dummy-virt (DT) pstate: a0000005 (NzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : kfree+0x2c/0x70 lr : kunit_free_suite_set+0xcc/0x13c sp : ffff8000829b75b0 x29: ffff8000829b75b0 x28: ffff8000829b7b90 x27: 0000000000000000 x26: dfff800000000000 x25: ffffcd07c82a7280 x24: ffffcd07a50ab300 x23: ffffcd07a50ab2e8 x22: 1ffff00010536ec0 x21: dfff800000000000 x20: ffffcd07a50ab2f0 x19: ffffcd07a50ab2f0 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: ffffcd07c24b6764 x14: ffffcd07c24b63c0 x13: ffffcd07c4cebb94 x12: ffff700010536ec7 x11: 1ffff00010536ec6 x10: ffff700010536ec6 x9 : dfff800000000000 x8 : 00008fffefac913a x7 : 0000000041b58ab3 x6 : 0000000000000000 x5 : 1ffff00010536ec5 x4 : ffff8000829b7628 x3 : dfff800000000000 x2 : ffffff341e942a80 x1 : ffffcd07a50aa000 x0 : fffffc0000000000 Call trace: kfree+0x2c/0x70 kunit_free_suite_set+0xcc/0x13c kunit_module_notify+0xd8/0x360 blocking_notifier_call_chain+0xc4/0x128 load_module+0x382c/0x44a4 init_module_from_file+0xd4/0x128 idempotent_init_module+0x2c8/0x524 __arm64_sys_finit_module+0xac/0x100 invoke_syscall+0x6c/0x258 el0_svc_common.constprop.0+0x160/0x22c do_el0_svc+0x44/0x5c el0_svc+0x38/0x78 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194 Code: aa0003e1 b25657e0 d34cfc42 8b021802 (f9400440) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs Kernel Offset: 0x4d0742200000 from 0xffff800080000000 PHYS_OFFSET: 0xffffee43c0000000 CPU features: 0x88000203,3c020000,1000421b Memory Limit: none Rebooting in 1 seconds.. Fixes: 3d6e44623841 ("kunit: unify module and builtin suite definitions") Signed-off-by: Jinjie Ruan Reviewed-by: Rae Moar Reviewed-by: David Gow Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- lib/kunit/test.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 184df6f701b4..a90bd265d73d 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -667,12 +667,13 @@ static int kunit_module_notify(struct notifier_block *nb, unsigned long val, switch (val) { case MODULE_STATE_LIVE: - kunit_module_init(mod); break; case MODULE_STATE_GOING: kunit_module_exit(mod); break; case MODULE_STATE_COMING: + kunit_module_init(mod); + break; case MODULE_STATE_UNFORMED: break; } From 980f8445479814509a3cd55a8eabaae1c9030a4c Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Thu, 7 Sep 2023 10:57:09 +0800 Subject: [PATCH 1465/2093] net: ipv4: fix one memleak in __inet_del_ifa() [ Upstream commit ac28b1ec6135649b5d78b028e47264cb3ebca5ea ] I got the below warning when do fuzzing test: unregister_netdevice: waiting for bond0 to become free. Usage count = 2 It can be repoduced via: ip link add bond0 type bond sysctl -w net.ipv4.conf.bond0.promote_secondaries=1 ip addr add 4.117.174.103/0 scope 0x40 dev bond0 ip addr add 192.168.100.111/255.255.255.254 scope 0 dev bond0 ip addr add 0.0.0.4/0 scope 0x40 secondary dev bond0 ip addr del 4.117.174.103/0 scope 0x40 dev bond0 ip link delete bond0 type bond In this reproduction test case, an incorrect 'last_prim' is found in __inet_del_ifa(), as a result, the secondary address(0.0.0.4/0 scope 0x40) is lost. The memory of the secondary address is leaked and the reference of in_device and net_device is leaked. Fix this problem: Look for 'last_prim' starting at location of the deleted IP and inserting the promoted IP into the location of 'last_prim'. Fixes: 0ff60a45678e ("[IPV4]: Fix secondary IP addresses after promotion") Signed-off-by: Liu Jian Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/devinet.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e8b9a9202fec..35d6e74be840 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -354,14 +354,14 @@ static void __inet_del_ifa(struct in_device *in_dev, { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; - struct in_ifaddr *last_prim; + struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); - last_prim = rtnl_dereference(in_dev->ifa_list); + last_prim = ifap; if (in_dev->dead) goto no_promotions; @@ -375,7 +375,7 @@ static void __inet_del_ifa(struct in_device *in_dev, while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) - last_prim = ifa; + last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || @@ -439,9 +439,9 @@ static void __inet_del_ifa(struct in_device *in_dev, rcu_assign_pointer(prev_prom->ifa_next, next_sec); - last_sec = rtnl_dereference(last_prim->ifa_next); + last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); - rcu_assign_pointer(last_prim->ifa_next, promote); + rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; From cdd61a27fb0af51c84312547165afc94feaee040 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Wed, 5 Jul 2023 13:53:17 +0200 Subject: [PATCH 1466/2093] kselftest/runner.sh: Propagate SIGTERM to runner child MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9616cb34b08ec86642b162eae75c5a7ca8debe3c ] Timeouts in kselftest are done using the "timeout" command with the "--foreground" option. Without the "foreground" option, it is not possible for a user to cancel the runner using SIGINT, because the signal is not propagated to timeout which is running in a different process group. The "forground" options places the timeout in the same process group as its parent, but only sends the SIGTERM (on timeout) signal to the forked process. Unfortunately, this does not play nice with all kselftests, e.g. "net:fcnal-test.sh", where the child processes will linger because timeout does not send SIGTERM to the group. Some users have noted these hangs [1]. Fix this by nesting the timeout with an additional timeout without the foreground option. Link: https://lore.kernel.org/all/7650b2eb-0aee-a2b0-2e64-c9bc63210f67@alu.unizg.hr/ # [1] Fixes: 651e0d881461 ("kselftest/runner: allow to properly deliver signals to tests") Signed-off-by: Björn Töpel Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/kselftest/runner.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 294619ade49f..1333ab1eda70 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -35,7 +35,8 @@ tap_timeout() { # Make sure tests will time out if utility is available. if [ -x /usr/bin/timeout ] ; then - /usr/bin/timeout --foreground "$kselftest_timeout" $1 + /usr/bin/timeout --foreground "$kselftest_timeout" \ + /usr/bin/timeout "$kselftest_timeout" $1 else $1 fi From ef5d546b9d4fa7c8cbd1fb787bbff5691f348531 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Tue, 22 Aug 2023 15:58:37 +0200 Subject: [PATCH 1467/2093] selftests: Keep symlinks, when possible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3f3f384139ed147c71e1d770accf610133d5309b ] When kselftest is built/installed with the 'gen_tar' target, rsync is used for the installation step to copy files. Extra care is needed for tests that have symlinks. Commit ae108c48b5d2 ("selftests: net: Fix cross-tree inclusion of scripts") added '-L' (transform symlink into referent file/dir) to rsync, to fix dangling links. However, that broke some tests where the symlink (being a symlink) is part of the test (e.g. exec:execveat). Use rsync's '--copy-unsafe-links' that does right thing. Fixes: ae108c48b5d2 ("selftests: net: Fix cross-tree inclusion of scripts") Signed-off-by: Björn Töpel Reviewed-by: Benjamin Poirier Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/lib.mk | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 05400462c779..aa646e0661f3 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -72,7 +72,7 @@ endef run_tests: all ifdef building_out_of_srctree @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - rsync -aLq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ + rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi @if [ "X$(TEST_PROGS)" != "X" ]; then \ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \ @@ -86,7 +86,7 @@ endif define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) - $(if $(INSTALL_LIST),rsync -aL $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST) $(INSTALL_PATH)/) endef define INSTALL_RULE From 70c8d17007dc4a07156b7da44509527990e569b3 Mon Sep 17 00:00:00 2001 From: Guangguan Wang Date: Fri, 8 Sep 2023 11:31:43 +0800 Subject: [PATCH 1468/2093] net/smc: use smc_lgr_list.lock to protect smc_lgr_list.list iterate in smcr_port_add [ Upstream commit f5146e3ef0a9eea405874b36178c19a4863b8989 ] While doing smcr_port_add, there maybe linkgroup add into or delete from smc_lgr_list.list at the same time, which may result kernel crash. So, use smc_lgr_list.lock to protect smc_lgr_list.list iterate in smcr_port_add. The crash calltrace show below: BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 0 PID: 559726 Comm: kworker/0:92 Kdump: loaded Tainted: G Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 449e491 04/01/2014 Workqueue: events smc_ib_port_event_work [smc] RIP: 0010:smcr_port_add+0xa6/0xf0 [smc] RSP: 0000:ffffa5a2c8f67de0 EFLAGS: 00010297 RAX: 0000000000000001 RBX: ffff9935e0650000 RCX: 0000000000000000 RDX: 0000000000000010 RSI: ffff9935e0654290 RDI: ffff9935c8560000 RBP: 0000000000000000 R08: 0000000000000000 R09: ffff9934c0401918 R10: 0000000000000000 R11: ffffffffb4a5c278 R12: ffff99364029aae4 R13: ffff99364029aa00 R14: 00000000ffffffed R15: ffff99364029ab08 FS: 0000000000000000(0000) GS:ffff994380600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000f06a10003 CR4: 0000000002770ef0 PKRU: 55555554 Call Trace: smc_ib_port_event_work+0x18f/0x380 [smc] process_one_work+0x19b/0x340 worker_thread+0x30/0x370 ? process_one_work+0x340/0x340 kthread+0x114/0x130 ? __kthread_cancel_work+0x50/0x50 ret_from_fork+0x1f/0x30 Fixes: 1f90a05d9ff9 ("net/smc: add smcr_port_add() and smcr_link_up() processing") Signed-off-by: Guangguan Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/smc_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index c676d92af7b7..64b6dd439938 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1650,6 +1650,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; + spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { struct smc_link *link; @@ -1665,6 +1666,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) if (link) smc_llc_add_link_local(link); } + spin_unlock_bh(&smc_lgr_list.lock); } /* link is down - switch connections to alternate link, From 9dbbc87d5b61606fbf9e84e921006174693865a2 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Thu, 7 Sep 2023 12:46:31 +0200 Subject: [PATCH 1469/2093] net: stmmac: fix handling of zero coalescing tx-usecs [ Upstream commit fa60b8163816f194786f3ee334c9a458da7699c6 ] Setting ethtool -C eth0 tx-usecs 0 is supposed to disable the use of the coalescing timer but currently it gets programmed with zero delay instead. Disable the use of the coalescing timer if tx-usecs is zero by preventing it from being restarted. Note that to keep things simple we don't start/stop the timer when the coalescing settings are changed, but just let that happen on the next transmit or timer expiry. Fixes: 8fce33317023 ("net: stmmac: Rework coalesce timer and fix multi-queue races") Signed-off-by: Vincent Whitchurch Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a07bcb2f5d2e..1559a4dafd41 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2692,9 +2692,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) /* We still have pending packets, let's call for a new scheduling */ if (tx_q->dirty_tx != tx_q->cur_tx) - hrtimer_start(&tx_q->txtimer, - STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]), - HRTIMER_MODE_REL); + stmmac_tx_timer_arm(priv, queue); __netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue)); @@ -2975,9 +2973,13 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; + u32 tx_coal_timer = priv->tx_coal_timer[queue]; + + if (!tx_coal_timer) + return; hrtimer_start(&tx_q->txtimer, - STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]), + STMMAC_COAL_TIMER(tx_coal_timer), HRTIMER_MODE_REL); } From 349638f7e5d3c7d328565587bb7b0454bbee02e2 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Fri, 8 Sep 2023 14:19:49 +0800 Subject: [PATCH 1470/2093] net: ethernet: mvpp2_main: fix possible OOB write in mvpp2_ethtool_get_rxnfc() [ Upstream commit 51fe0a470543f345e3c62b6798929de3ddcedc1d ] rules is allocated in ethtool_get_rxnfc and the size is determined by rule_cnt from user space. So rule_cnt needs to be check before using rules to avoid OOB writing or NULL pointer dereference. Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support") Signed-off-by: Hangyu Hua Reviewed-by: Marcin Wojtas Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index b399bdb1ca36..f936640cca4e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5578,6 +5578,11 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev, break; case ETHTOOL_GRXCLSRLALL: for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) { + if (loc == info->rule_cnt) { + ret = -EMSGSIZE; + break; + } + if (port->rfs_rules[i]) rules[loc++] = i; } From ff5faed5f5487b0fd2b640ba1304f82a5ebaab42 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Fri, 8 Sep 2023 14:19:50 +0800 Subject: [PATCH 1471/2093] net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in mtk_hwlro_get_fdir_all() [ Upstream commit e4c79810755f66c9a933ca810da2724133b1165a ] rule_locs is allocated in ethtool_get_rxnfc and the size is determined by rule_cnt from user space. So rule_cnt needs to be check before using rule_locs to avoid NULL pointer dereference. Fixes: 7aab747e5563 ("net: ethernet: mediatek: add ethtool functions to configure RX flows of HW LRO") Signed-off-by: Hangyu Hua Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 7e318133423a..0ac5ae16308f 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2698,6 +2698,9 @@ static int mtk_hwlro_get_fdir_all(struct net_device *dev, int i; for (i = 0; i < MTK_MAX_LRO_IP_CNT; i++) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + if (mac->hwlro_ip[i]) { rule_locs[cnt] = i; cnt++; From 61866f7d814e5792bf47410d7d3ff32e49bd292a Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Fri, 8 Sep 2023 18:17:52 +0800 Subject: [PATCH 1472/2093] hsr: Fix uninit-value access in fill_frame_info() [ Upstream commit 484b4833c604c0adcf19eac1ca14b60b757355b5 ] Syzbot reports the following uninit-value access problem. ===================================================== BUG: KMSAN: uninit-value in fill_frame_info net/hsr/hsr_forward.c:601 [inline] BUG: KMSAN: uninit-value in hsr_forward_skb+0x9bd/0x30f0 net/hsr/hsr_forward.c:616 fill_frame_info net/hsr/hsr_forward.c:601 [inline] hsr_forward_skb+0x9bd/0x30f0 net/hsr/hsr_forward.c:616 hsr_dev_xmit+0x192/0x330 net/hsr/hsr_device.c:223 __netdev_start_xmit include/linux/netdevice.h:4889 [inline] netdev_start_xmit include/linux/netdevice.h:4903 [inline] xmit_one net/core/dev.c:3544 [inline] dev_hard_start_xmit+0x247/0xa10 net/core/dev.c:3560 __dev_queue_xmit+0x34d0/0x52a0 net/core/dev.c:4340 dev_queue_xmit include/linux/netdevice.h:3082 [inline] packet_xmit+0x9c/0x6b0 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3087 [inline] packet_sendmsg+0x8b1d/0x9f30 net/packet/af_packet.c:3119 sock_sendmsg_nosec net/socket.c:730 [inline] sock_sendmsg net/socket.c:753 [inline] __sys_sendto+0x781/0xa30 net/socket.c:2176 __do_sys_sendto net/socket.c:2188 [inline] __se_sys_sendto net/socket.c:2184 [inline] __ia32_sys_sendto+0x11f/0x1c0 net/socket.c:2184 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Uninit was created at: slab_post_alloc_hook+0x12f/0xb70 mm/slab.h:767 slab_alloc_node mm/slub.c:3478 [inline] kmem_cache_alloc_node+0x577/0xa80 mm/slub.c:3523 kmalloc_reserve+0x148/0x470 net/core/skbuff.c:559 __alloc_skb+0x318/0x740 net/core/skbuff.c:644 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6299 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2794 packet_alloc_skb net/packet/af_packet.c:2936 [inline] packet_snd net/packet/af_packet.c:3030 [inline] packet_sendmsg+0x70e8/0x9f30 net/packet/af_packet.c:3119 sock_sendmsg_nosec net/socket.c:730 [inline] sock_sendmsg net/socket.c:753 [inline] __sys_sendto+0x781/0xa30 net/socket.c:2176 __do_sys_sendto net/socket.c:2188 [inline] __se_sys_sendto net/socket.c:2184 [inline] __ia32_sys_sendto+0x11f/0x1c0 net/socket.c:2184 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 It is because VLAN not yet supported in hsr driver. Return error when protocol is ETH_P_8021Q in fill_frame_info() now to fix it. Fixes: 451d8123f897 ("net: prp: add packet handling support") Reported-by: syzbot+bf7e6250c7ce248f3ec9@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=bf7e6250c7ce248f3ec9 Signed-off-by: Ziyang Xuan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/hsr/hsr_forward.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 629daacc9607..b71dab630a87 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -594,6 +594,7 @@ static int fill_frame_info(struct hsr_frame_info *frame, proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto; /* FIXME: */ netdev_warn_once(skb->dev, "VLAN not yet supported"); + return -EINVAL; } frame->is_from_san = false; From c281948cebcccf275afbec7cb03adb68d39288e7 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 4 Aug 2023 17:35:31 +0800 Subject: [PATCH 1473/2093] net: ethernet: adi: adin1110: use eth_broadcast_addr() to assign broadcast address [ Upstream commit 54024dbec95585243391caeb9f04a2620e630765 ] Use eth_broadcast_addr() to assign broadcast address instead of memset(). Signed-off-by: Yang Yingliang Reviewed-by: Simon Horman Signed-off-by: David S. Miller Stable-dep-of: 32530dba1bd4 ("net:ethernet:adi:adin1110: Fix forwarding offload") Signed-off-by: Sasha Levin --- drivers/net/ethernet/adi/adin1110.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index ecce5f7a549f..cc026780ee0e 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -740,7 +740,7 @@ static int adin1110_broadcasts_filter(struct adin1110_port_priv *port_priv, u32 port_rules = 0; u8 mask[ETH_ALEN]; - memset(mask, 0xFF, ETH_ALEN); + eth_broadcast_addr(mask); if (accept_broadcast && port_priv->state == BR_STATE_FORWARDING) port_rules = adin1110_port_rules(port_priv, true, true); @@ -761,7 +761,7 @@ static int adin1110_set_mac_address(struct net_device *netdev, return -EADDRNOTAVAIL; eth_hw_addr_set(netdev, dev_addr); - memset(mask, 0xFF, ETH_ALEN); + eth_broadcast_addr(mask); mac_slot = (!port_priv->nr) ? ADIN_MAC_P1_ADDR_SLOT : ADIN_MAC_P2_ADDR_SLOT; port_rules = adin1110_port_rules(port_priv, true, false); @@ -1251,7 +1251,7 @@ static int adin1110_port_set_blocking_state(struct adin1110_port_priv *port_priv goto out; /* Allow only BPDUs to be passed to the CPU */ - memset(mask, 0xFF, ETH_ALEN); + eth_broadcast_addr(mask); port_rules = adin1110_port_rules(port_priv, true, false); ret = adin1110_write_mac_address(port_priv, mac_slot, mac, mask, port_rules); @@ -1366,7 +1366,7 @@ static int adin1110_fdb_add(struct adin1110_port_priv *port_priv, other_port = priv->ports[!port_priv->nr]; port_rules = adin1110_port_rules(port_priv, false, true); - memset(mask, 0xFF, ETH_ALEN); + eth_broadcast_addr(mask); return adin1110_write_mac_address(other_port, mac_nr, (u8 *)fdb->addr, mask, port_rules); From 66e79c2f3a9358b9191d14683f5296fcc6e26f28 Mon Sep 17 00:00:00 2001 From: Ciprian Regus Date: Fri, 8 Sep 2023 15:58:08 +0300 Subject: [PATCH 1474/2093] net:ethernet:adi:adin1110: Fix forwarding offload [ Upstream commit 32530dba1bd48da4437d18d9a8dbc9d2826938a6 ] Currently, when a new fdb entry is added (with both ports of the ADIN2111 bridged), the driver configures the MAC filters for the wrong port, which results in the forwarding being done by the host, and not actually hardware offloaded. The ADIN2111 offloads the forwarding by setting filters on the destination MAC address of incoming frames. Based on these, they may be routed to the other port. Thus, if a frame has to be forwarded from port 1 to port 2, the required configuration for the ADDR_FILT_UPRn register should set the APPLY2PORT1 bit (instead of APPLY2PORT2, as it's currently the case). Fixes: bc93e19d088b ("net: ethernet: adi: Add ADIN1110 support") Signed-off-by: Ciprian Regus Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/adi/adin1110.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index cc026780ee0e..ed2863ed6a5b 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -1365,7 +1365,7 @@ static int adin1110_fdb_add(struct adin1110_port_priv *port_priv, return -ENOMEM; other_port = priv->ports[!port_priv->nr]; - port_rules = adin1110_port_rules(port_priv, false, true); + port_rules = adin1110_port_rules(other_port, false, true); eth_broadcast_addr(mask); return adin1110_write_mac_address(other_port, mac_nr, (u8 *)fdb->addr, From 9a3e7eca2b5b80095d8313ec1a5343bec34df267 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 8 Sep 2023 16:33:48 +0300 Subject: [PATCH 1475/2093] net: dsa: sja1105: hide all multicast addresses from "bridge fdb show" [ Upstream commit 02c652f5465011126152bbd93b6a582a1d0c32f1 ] Commit 4d9423549501 ("net: dsa: sja1105: offload bridge port flags to device") has partially hidden some multicast entries from showing up in the "bridge fdb show" output, but it wasn't enough. Addresses which are added through "bridge mdb add" still show up. Hide them all. Fixes: 291d1e72b756 ("net: dsa: sja1105: Add support for FDB and MDB management") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105_main.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index ff94c5996faf..f8228a81234f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1875,13 +1875,14 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, if (!(l2_lookup.destports & BIT(port))) continue; - /* We need to hide the FDB entry for unknown multicast */ - if (l2_lookup.macaddr == SJA1105_UNKNOWN_MULTICAST && - l2_lookup.mask_macaddr == SJA1105_UNKNOWN_MULTICAST) - continue; - u64_to_ether_addr(l2_lookup.macaddr, macaddr); + /* Hardware FDB is shared for fdb and mdb, "bridge fdb show" + * only wants to see unicast + */ + if (is_multicast_ether_addr(macaddr)) + continue; + /* We need to hide the dsa_8021q VLANs from the user. */ if (vid_is_dsa_8021q(l2_lookup.vlanid)) l2_lookup.vlanid = 0; From 538e7fe66c46bbae124cbfb3dce355eb25efcd88 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 8 Sep 2023 16:33:49 +0300 Subject: [PATCH 1476/2093] net: dsa: sja1105: propagate exact error code from sja1105_dynamic_config_poll_valid() [ Upstream commit c956798062b5a308db96e75157747291197f0378 ] Currently, sja1105_dynamic_config_wait_complete() returns either 0 or -ETIMEDOUT, because it just looks at the read_poll_timeout() return code. There will be future changes which move some more checks to sja1105_dynamic_config_poll_valid(). It is important that we propagate their exact return code (-ENOENT, -EINVAL), because callers of sja1105_dynamic_config_read() depend on them. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Stable-dep-of: 7cef293b9a63 ("net: dsa: sja1105: fix multicast forwarding working only for last added mdb entry") Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105_dynamic_config.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index 7729d3f8b7f5..93d47dab8d3e 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -1211,13 +1211,14 @@ sja1105_dynamic_config_wait_complete(struct sja1105_private *priv, struct sja1105_dyn_cmd *cmd, const struct sja1105_dynamic_table_ops *ops) { - int rc; + int err, rc; - return read_poll_timeout(sja1105_dynamic_config_poll_valid, - rc, rc != -EAGAIN, - SJA1105_DYNAMIC_CONFIG_SLEEP_US, - SJA1105_DYNAMIC_CONFIG_TIMEOUT_US, - false, priv, cmd, ops); + err = read_poll_timeout(sja1105_dynamic_config_poll_valid, + rc, rc != -EAGAIN, + SJA1105_DYNAMIC_CONFIG_SLEEP_US, + SJA1105_DYNAMIC_CONFIG_TIMEOUT_US, + false, priv, cmd, ops); + return err < 0 ? err : rc; } /* Provides read access to the settings through the dynamic interface From d766cf9ddb9714b373fcb86e437e54dcf232c3cc Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 8 Sep 2023 16:33:50 +0300 Subject: [PATCH 1477/2093] net: dsa: sja1105: fix multicast forwarding working only for last added mdb entry [ Upstream commit 7cef293b9a634a05fcce9e1df4aee3aeed023345 ] The commit cited in Fixes: did 2 things: it refactored the read-back polling from sja1105_dynamic_config_read() into a new function, sja1105_dynamic_config_wait_complete(), and it called that from sja1105_dynamic_config_write() too. What is problematic is the refactoring. The refactored code from sja1105_dynamic_config_poll_valid() works like the previous one, but the problem is that it uses another packed_buf[] SPI buffer, and there was code at the end of sja1105_dynamic_config_read() which was relying on the read-back packed_buf[]: /* Don't dereference possibly NULL pointer - maybe caller * only wanted to see whether the entry existed or not. */ if (entry) ops->entry_packing(packed_buf, entry, UNPACK); After the change, the packed_buf[] that this code sees is no longer the entry read back from hardware, but the original entry that the caller passed to the sja1105_dynamic_config_read(), packed into this buffer. This difference is the most notable with the SJA1105_SEARCH uses from sja1105pqrs_fdb_add() - used for both fdb and mdb. There, we have logic added by commit 728db843df88 ("net: dsa: sja1105: ignore the FDB entry for unknown multicast when adding a new address") to figure out whether the address we're trying to add matches on any existing hardware entry, with the exception of the catch-all multicast address. That logic was broken, because with sja1105_dynamic_config_read() not working properly, it doesn't return us the entry read back from hardware, but the entry that we passed to it. And, since for multicast, a match will always exist, it will tell us that any mdb entry already exists at index=0 L2 Address Lookup table. It is index=0 because the caller doesn't know the index - it wants to find it out, and sja1105_dynamic_config_read() does: if (index < 0) { // SJA1105_SEARCH /* Avoid copying a signed negative number to an u64 */ cmd.index = 0; // <- this cmd.search = true; } else { cmd.index = index; cmd.search = false; } So, to the caller of sja1105_dynamic_config_read(), the returned info looks entirely legit, and it will add all mdb entries to FDB index 0. There, they will always overwrite each other (not to mention, potentially they can also overwrite a pre-existing bridge fdb entry), and the user-visible impact will be that only the last mdb entry will be forwarded as it should. The others won't (will be flooded or dropped, depending on the egress flood settings). Fixing is a bit more complicated, and involves either passing the same packed_buf[] to sja1105_dynamic_config_wait_complete(), or moving all the extra processing on the packed_buf[] to sja1105_dynamic_config_wait_complete(). I've opted for the latter, because it makes sja1105_dynamic_config_wait_complete() a bit more self-contained. Fixes: df405910ab9f ("net: dsa: sja1105: wait for dynamic config command completion on writes too") Reported-by: Yanan Yang Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../net/dsa/sja1105/sja1105_dynamic_config.c | 80 +++++++++---------- 1 file changed, 37 insertions(+), 43 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index 93d47dab8d3e..984c0e604e8d 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -1175,18 +1175,15 @@ const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN] = { static int sja1105_dynamic_config_poll_valid(struct sja1105_private *priv, - struct sja1105_dyn_cmd *cmd, - const struct sja1105_dynamic_table_ops *ops) + const struct sja1105_dynamic_table_ops *ops, + void *entry, bool check_valident, + bool check_errors) { u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {}; + struct sja1105_dyn_cmd cmd = {}; int rc; - /* We don't _need_ to read the full entry, just the command area which - * is a fixed SJA1105_SIZE_DYN_CMD. But our cmd_packing() API expects a - * buffer that contains the full entry too. Additionally, our API - * doesn't really know how many bytes into the buffer does the command - * area really begin. So just read back the whole entry. - */ + /* Read back the whole entry + command structure. */ rc = sja1105_xfer_buf(priv, SPI_READ, ops->addr, packed_buf, ops->packed_size); if (rc) @@ -1195,11 +1192,25 @@ sja1105_dynamic_config_poll_valid(struct sja1105_private *priv, /* Unpack the command structure, and return it to the caller in case it * needs to perform further checks on it (VALIDENT). */ - memset(cmd, 0, sizeof(*cmd)); - ops->cmd_packing(packed_buf, cmd, UNPACK); + ops->cmd_packing(packed_buf, &cmd, UNPACK); /* Hardware hasn't cleared VALID => still working on it */ - return cmd->valid ? -EAGAIN : 0; + if (cmd.valid) + return -EAGAIN; + + if (check_valident && !cmd.valident && !(ops->access & OP_VALID_ANYWAY)) + return -ENOENT; + + if (check_errors && cmd.errors) + return -EINVAL; + + /* Don't dereference possibly NULL pointer - maybe caller + * only wanted to see whether the entry existed or not. + */ + if (entry) + ops->entry_packing(packed_buf, entry, UNPACK); + + return 0; } /* Poll the dynamic config entry's control area until the hardware has @@ -1208,8 +1219,9 @@ sja1105_dynamic_config_poll_valid(struct sja1105_private *priv, */ static int sja1105_dynamic_config_wait_complete(struct sja1105_private *priv, - struct sja1105_dyn_cmd *cmd, - const struct sja1105_dynamic_table_ops *ops) + const struct sja1105_dynamic_table_ops *ops, + void *entry, bool check_valident, + bool check_errors) { int err, rc; @@ -1217,7 +1229,8 @@ sja1105_dynamic_config_wait_complete(struct sja1105_private *priv, rc, rc != -EAGAIN, SJA1105_DYNAMIC_CONFIG_SLEEP_US, SJA1105_DYNAMIC_CONFIG_TIMEOUT_US, - false, priv, cmd, ops); + false, priv, ops, entry, check_valident, + check_errors); return err < 0 ? err : rc; } @@ -1287,25 +1300,14 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv, mutex_lock(&priv->dynamic_config_lock); rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf, ops->packed_size); - if (rc < 0) { - mutex_unlock(&priv->dynamic_config_lock); - return rc; - } - - rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops); - mutex_unlock(&priv->dynamic_config_lock); if (rc < 0) - return rc; + goto out; - if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY)) - return -ENOENT; + rc = sja1105_dynamic_config_wait_complete(priv, ops, entry, true, false); +out: + mutex_unlock(&priv->dynamic_config_lock); - /* Don't dereference possibly NULL pointer - maybe caller - * only wanted to see whether the entry existed or not. - */ - if (entry) - ops->entry_packing(packed_buf, entry, UNPACK); - return 0; + return rc; } int sja1105_dynamic_config_write(struct sja1105_private *priv, @@ -1357,22 +1359,14 @@ int sja1105_dynamic_config_write(struct sja1105_private *priv, mutex_lock(&priv->dynamic_config_lock); rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf, ops->packed_size); - if (rc < 0) { - mutex_unlock(&priv->dynamic_config_lock); - return rc; - } - - rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops); - mutex_unlock(&priv->dynamic_config_lock); if (rc < 0) - return rc; + goto out; - cmd = (struct sja1105_dyn_cmd) {0}; - ops->cmd_packing(packed_buf, &cmd, UNPACK); - if (cmd.errors) - return -EINVAL; + rc = sja1105_dynamic_config_wait_complete(priv, ops, NULL, false, true); +out: + mutex_unlock(&priv->dynamic_config_lock); - return 0; + return rc; } static u8 sja1105_crc8_add(u8 crc, u8 byte, u8 poly) From e74bd1b229cb16ce078fc36177c6d6dcdf28d160 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 8 Sep 2023 16:33:51 +0300 Subject: [PATCH 1478/2093] net: dsa: sja1105: serialize sja1105_port_mcast_flood() with other FDB accesses [ Upstream commit ea32690daf4fa525dc5a4d164bd00ed8c756e1c6 ] sja1105_fdb_add() runs from the dsa_owq, and sja1105_port_mcast_flood() runs from switchdev_deferred_process_work(). Prior to the blamed commit, they used to be indirectly serialized through the rtnl_lock(), which no longer holds true because dsa_owq dropped that. So, it is now possible that we traverse the static config BLK_IDX_L2_LOOKUP elements concurrently compared to when we change them, in sja1105_static_fdb_change(). That is not ideal, since it might result in data corruption. Introduce a mutex which serializes accesses to the hardware FDB and to the static config elements for the L2 Address Lookup table. I can't find a good reason to add locking around sja1105_fdb_dump(). I'll add it later if needed. Fixes: 0faf890fc519 ("net: dsa: drop rtnl_lock from dsa_slave_switchdev_event_work") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105.h | 2 + drivers/net/dsa/sja1105/sja1105_main.c | 56 ++++++++++++++++++++------ 2 files changed, 45 insertions(+), 13 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index a831bb0a5207..06e0ebfe652a 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -264,6 +264,8 @@ struct sja1105_private { * the switch doesn't confuse them with one another. */ struct mutex mgmt_lock; + /* Serializes accesses to the FDB */ + struct mutex fdb_lock; /* PTP two-step TX timestamp ID, and its serialization lock */ spinlock_t ts_id_lock; u8 ts_id; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index f8228a81234f..c6c74e302e4d 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1805,6 +1805,7 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port, struct dsa_db db) { struct sja1105_private *priv = ds->priv; + int rc; if (!vid) { switch (db.type) { @@ -1819,12 +1820,16 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port, } } - return priv->info->fdb_add_cmd(ds, port, addr, vid); + mutex_lock(&priv->fdb_lock); + rc = priv->info->fdb_add_cmd(ds, port, addr, vid); + mutex_unlock(&priv->fdb_lock); + + return rc; } -static int sja1105_fdb_del(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, - struct dsa_db db) +static int __sja1105_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db) { struct sja1105_private *priv = ds->priv; @@ -1844,6 +1849,20 @@ static int sja1105_fdb_del(struct dsa_switch *ds, int port, return priv->info->fdb_del_cmd(ds, port, addr, vid); } +static int sja1105_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + struct sja1105_private *priv = ds->priv; + int rc; + + mutex_lock(&priv->fdb_lock); + rc = __sja1105_fdb_del(ds, port, addr, vid, db); + mutex_unlock(&priv->fdb_lock); + + return rc; +} + static int sja1105_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data) { @@ -1906,6 +1925,8 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port) }; int i; + mutex_lock(&priv->fdb_lock); + for (i = 0; i < SJA1105_MAX_L2_LOOKUP_COUNT; i++) { struct sja1105_l2_lookup_entry l2_lookup = {0}; u8 macaddr[ETH_ALEN]; @@ -1919,7 +1940,7 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port) if (rc) { dev_err(ds->dev, "Failed to read FDB: %pe\n", ERR_PTR(rc)); - return; + break; } if (!(l2_lookup.destports & BIT(port))) @@ -1931,14 +1952,16 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port) u64_to_ether_addr(l2_lookup.macaddr, macaddr); - rc = sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid, db); + rc = __sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid, db); if (rc) { dev_err(ds->dev, "Failed to delete FDB entry %pM vid %lld: %pe\n", macaddr, l2_lookup.vlanid, ERR_PTR(rc)); - return; + break; } } + + mutex_unlock(&priv->fdb_lock); } static int sja1105_mdb_add(struct dsa_switch *ds, int port, @@ -2964,7 +2987,9 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to, { struct sja1105_l2_lookup_entry *l2_lookup; struct sja1105_table *table; - int match; + int match, rc; + + mutex_lock(&priv->fdb_lock); table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP]; l2_lookup = table->entries; @@ -2977,7 +3002,8 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to, if (match == table->entry_count) { NL_SET_ERR_MSG_MOD(extack, "Could not find FDB entry for unknown multicast"); - return -ENOSPC; + rc = -ENOSPC; + goto out; } if (flags.val & BR_MCAST_FLOOD) @@ -2985,10 +3011,13 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to, else l2_lookup[match].destports &= ~BIT(to); - return sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP, - l2_lookup[match].index, - &l2_lookup[match], - true); + rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP, + l2_lookup[match].index, + &l2_lookup[match], true); +out: + mutex_unlock(&priv->fdb_lock); + + return rc; } static int sja1105_port_pre_bridge_flags(struct dsa_switch *ds, int port, @@ -3358,6 +3387,7 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->dynamic_config_lock); mutex_init(&priv->mgmt_lock); + mutex_init(&priv->fdb_lock); spin_lock_init(&priv->ts_id_lock); rc = sja1105_parse_dt(priv); From 44c8ffd482cc8376ec3f7c4db3380c640733f412 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 8 Sep 2023 16:33:52 +0300 Subject: [PATCH 1479/2093] net: dsa: sja1105: block FDB accesses that are concurrent with a switch reset [ Upstream commit 86899e9e1e29e854b5f6dcc24ba4f75f792c89aa ] Currently, when we add the first sja1105 port to a bridge with vlan_filtering 1, then we sometimes see this output: sja1105 spi2.2: port 4 failed to read back entry for be:79:b4:9e:9e:96 vid 3088: -ENOENT sja1105 spi2.2: Reset switch and programmed static config. Reason: VLAN filtering sja1105 spi2.2: port 0 failed to add be:79:b4:9e:9e:96 vid 0 to fdb: -2 It is because sja1105_fdb_add() runs from the dsa_owq which is no longer serialized with switch resets since it dropped the rtnl_lock() in the blamed commit. Either performing the FDB accesses before the reset, or after the reset, is equally fine, because sja1105_static_fdb_change() backs up those changes in the static config, but FDB access during reset isn't ok. Make sja1105_static_config_reload() take the fdb_lock to fix that. Fixes: 0faf890fc519 ("net: dsa: drop rtnl_lock from dsa_slave_switchdev_event_work") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/sja1105/sja1105_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c6c74e302e4d..f1f1368e8146 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2304,6 +2304,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv, int rc, i; s64 now; + mutex_lock(&priv->fdb_lock); mutex_lock(&priv->mgmt_lock); mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; @@ -2418,6 +2419,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv, goto out; out: mutex_unlock(&priv->mgmt_lock); + mutex_unlock(&priv->fdb_lock); return rc; } From 2323397e5877c50699f81aec4a86222fc8c0f141 Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Fri, 8 Sep 2023 15:01:52 +0800 Subject: [PATCH 1480/2093] r8152: check budget for r8152_poll() [ Upstream commit a7b8d60b37237680009dd0b025fe8c067aba0ee3 ] According to the document of napi, there is no rx process when the budget is 0. Therefore, r8152_poll() has to return 0 directly when the budget is equal to 0. Fixes: d2187f8e4454 ("r8152: divide the tx and rx bottom functions") Signed-off-by: Hayes Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/usb/r8152.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 059d610901d8..fc1458f96e17 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2628,6 +2628,9 @@ static int r8152_poll(struct napi_struct *napi, int budget) struct r8152 *tp = container_of(napi, struct r8152, napi); int work_done; + if (!budget) + return 0; + work_done = rx_bottom(tp, budget); if (work_done < budget) { From 16989de75497574b5fafd174c0c233d5a86858b7 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Sun, 10 Sep 2023 02:03:10 +0900 Subject: [PATCH 1481/2093] kcm: Fix memory leak in error path of kcm_sendmsg() [ Upstream commit c821a88bd720b0046433173185fd841a100d44ad ] syzbot reported a memory leak like below: BUG: memory leak unreferenced object 0xffff88810b088c00 (size 240): comm "syz-executor186", pid 5012, jiffies 4294943306 (age 13.680s) hex dump (first 32 bytes): 00 89 08 0b 81 88 ff ff 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] __alloc_skb+0x1ef/0x230 net/core/skbuff.c:634 [] alloc_skb include/linux/skbuff.h:1289 [inline] [] kcm_sendmsg+0x269/0x1050 net/kcm/kcmsock.c:815 [] sock_sendmsg_nosec net/socket.c:725 [inline] [] sock_sendmsg+0x56/0xb0 net/socket.c:748 [] ____sys_sendmsg+0x365/0x470 net/socket.c:2494 [] ___sys_sendmsg+0xc9/0x130 net/socket.c:2548 [] __sys_sendmsg+0xa6/0x120 net/socket.c:2577 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd In kcm_sendmsg(), kcm_tx_msg(head)->last_skb is used as a cursor to append newly allocated skbs to 'head'. If some bytes are copied, an error occurred, and jumped to out_error label, 'last_skb' is left unmodified. A later kcm_sendmsg() will use an obsoleted 'last_skb' reference, corrupting the 'head' frag_list and causing the leak. This patch fixes this issue by properly updating the last allocated skb in 'last_skb'. Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-and-tested-by: syzbot+6f98de741f7dbbfc4ccb@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6f98de741f7dbbfc4ccb Signed-off-by: Shigeru Yoshida Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/kcm/kcmsock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 6a97662d7548..dd929a835074 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1074,6 +1074,8 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (head != kcm->seq_skb) kfree_skb(head); + else if (copied) + kcm_tx_msg(head)->last_skb = skb; err = sk_stream_error(sk, msg->msg_flags, err); From 30c8bbe1edba060dde76bcbc147ec7ca0b7e2a9a Mon Sep 17 00:00:00 2001 From: Liming Sun Date: Tue, 29 Aug 2023 13:42:59 -0400 Subject: [PATCH 1482/2093] platform/mellanox: mlxbf-tmfifo: Drop the Rx packet if no more descriptors [ Upstream commit 78034cbece79c2d730ad0770b3b7f23eedbbecf5 ] This commit fixes tmfifo console stuck issue when the virtual networking interface is in down state. In such case, the network Rx descriptors runs out and causes the Rx network packet staying in the head of the tmfifo thus blocking the console packets. The fix is to drop the Rx network packet when no more Rx descriptors. Function name mlxbf_tmfifo_release_pending_pkt() is also renamed to mlxbf_tmfifo_release_pkt() to be more approperiate. Fixes: 1357dfd7261f ("platform/mellanox: Add TmFifo driver for Mellanox BlueField Soc") Signed-off-by: Liming Sun Reviewed-by: Vadim Pasternak Reviewed-by: David Thompson Link: https://lore.kernel.org/r/8c0177dc938ae03f52ff7e0b62dbeee74b7bec09.1693322547.git.limings@nvidia.com Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/mlxbf-tmfifo.c | 66 ++++++++++++++++++------ 1 file changed, 49 insertions(+), 17 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index d31fe7eed38d..ee8648a271fd 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -56,6 +56,7 @@ struct mlxbf_tmfifo; * @vq: pointer to the virtio virtqueue * @desc: current descriptor of the pending packet * @desc_head: head descriptor of the pending packet + * @drop_desc: dummy desc for packet dropping * @cur_len: processed length of the current descriptor * @rem_len: remaining length of the pending packet * @pkt_len: total length of the pending packet @@ -72,6 +73,7 @@ struct mlxbf_tmfifo_vring { struct virtqueue *vq; struct vring_desc *desc; struct vring_desc *desc_head; + struct vring_desc drop_desc; int cur_len; int rem_len; u32 pkt_len; @@ -83,6 +85,14 @@ struct mlxbf_tmfifo_vring { struct mlxbf_tmfifo *fifo; }; +/* Check whether vring is in drop mode. */ +#define IS_VRING_DROP(_r) ({ \ + typeof(_r) (r) = (_r); \ + (r->desc_head == &r->drop_desc ? true : false); }) + +/* A stub length to drop maximum length packet. */ +#define VRING_DROP_DESC_MAX_LEN GENMASK(15, 0) + /* Interrupt types. */ enum { MLXBF_TM_RX_LWM_IRQ, @@ -243,6 +253,7 @@ static int mlxbf_tmfifo_alloc_vrings(struct mlxbf_tmfifo *fifo, vring->align = SMP_CACHE_BYTES; vring->index = i; vring->vdev_id = tm_vdev->vdev.id.device; + vring->drop_desc.len = VRING_DROP_DESC_MAX_LEN; dev = &tm_vdev->vdev.dev; size = vring_size(vring->num, vring->align); @@ -348,7 +359,7 @@ static u32 mlxbf_tmfifo_get_pkt_len(struct mlxbf_tmfifo_vring *vring, return len; } -static void mlxbf_tmfifo_release_pending_pkt(struct mlxbf_tmfifo_vring *vring) +static void mlxbf_tmfifo_release_pkt(struct mlxbf_tmfifo_vring *vring) { struct vring_desc *desc_head; u32 len = 0; @@ -577,19 +588,25 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring, if (vring->cur_len + sizeof(u64) <= len) { /* The whole word. */ - if (is_rx) - memcpy(addr + vring->cur_len, &data, sizeof(u64)); - else - memcpy(&data, addr + vring->cur_len, sizeof(u64)); + if (!IS_VRING_DROP(vring)) { + if (is_rx) + memcpy(addr + vring->cur_len, &data, + sizeof(u64)); + else + memcpy(&data, addr + vring->cur_len, + sizeof(u64)); + } vring->cur_len += sizeof(u64); } else { /* Leftover bytes. */ - if (is_rx) - memcpy(addr + vring->cur_len, &data, - len - vring->cur_len); - else - memcpy(&data, addr + vring->cur_len, - len - vring->cur_len); + if (!IS_VRING_DROP(vring)) { + if (is_rx) + memcpy(addr + vring->cur_len, &data, + len - vring->cur_len); + else + memcpy(&data, addr + vring->cur_len, + len - vring->cur_len); + } vring->cur_len = len; } @@ -690,8 +707,16 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring, /* Get the descriptor of the next packet. */ if (!vring->desc) { desc = mlxbf_tmfifo_get_next_pkt(vring, is_rx); - if (!desc) - return false; + if (!desc) { + /* Drop next Rx packet to avoid stuck. */ + if (is_rx) { + desc = &vring->drop_desc; + vring->desc_head = desc; + vring->desc = desc; + } else { + return false; + } + } } else { desc = vring->desc; } @@ -724,17 +749,24 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring, vring->rem_len -= len; /* Get the next desc on the chain. */ - if (vring->rem_len > 0 && + if (!IS_VRING_DROP(vring) && vring->rem_len > 0 && (virtio16_to_cpu(vdev, desc->flags) & VRING_DESC_F_NEXT)) { idx = virtio16_to_cpu(vdev, desc->next); desc = &vr->desc[idx]; goto mlxbf_tmfifo_desc_done; } - /* Done and release the pending packet. */ - mlxbf_tmfifo_release_pending_pkt(vring); + /* Done and release the packet. */ desc = NULL; fifo->vring[is_rx] = NULL; + if (!IS_VRING_DROP(vring)) { + mlxbf_tmfifo_release_pkt(vring); + } else { + vring->pkt_len = 0; + vring->desc_head = NULL; + vring->desc = NULL; + return false; + } /* * Make sure the load/store are in order before @@ -914,7 +946,7 @@ static void mlxbf_tmfifo_virtio_del_vqs(struct virtio_device *vdev) /* Release the pending packet. */ if (vring->desc) - mlxbf_tmfifo_release_pending_pkt(vring); + mlxbf_tmfifo_release_pkt(vring); vq = vring->vq; if (vq) { vring->vq = NULL; From 3a45dcfb4d3cbe683b082ccde6a724534b73e4f9 Mon Sep 17 00:00:00 2001 From: Liming Sun Date: Tue, 29 Aug 2023 13:43:00 -0400 Subject: [PATCH 1483/2093] platform/mellanox: mlxbf-tmfifo: Drop jumbo frames [ Upstream commit fc4c655821546239abb3cf4274d66b9747aa87dd ] This commit drops over-sized network packets to avoid tmfifo queue stuck. Fixes: 1357dfd7261f ("platform/mellanox: Add TmFifo driver for Mellanox BlueField Soc") Signed-off-by: Liming Sun Reviewed-by: Vadim Pasternak Reviewed-by: David Thompson Link: https://lore.kernel.org/r/9318936c2447f76db475c985ca6d91f057efcd41.1693322547.git.limings@nvidia.com Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/mlxbf-tmfifo.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index ee8648a271fd..a04ff89a7ec4 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -205,7 +205,7 @@ static u8 mlxbf_tmfifo_net_default_mac[ETH_ALEN] = { static efi_char16_t mlxbf_tmfifo_efi_name[] = L"RshimMacAddr"; /* Maximum L2 header length. */ -#define MLXBF_TMFIFO_NET_L2_OVERHEAD 36 +#define MLXBF_TMFIFO_NET_L2_OVERHEAD (ETH_HLEN + VLAN_HLEN) /* Supported virtio-net features. */ #define MLXBF_TMFIFO_NET_FEATURES \ @@ -623,13 +623,14 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring, * flag is set. */ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring, - struct vring_desc *desc, + struct vring_desc **desc, bool is_rx, bool *vring_change) { struct mlxbf_tmfifo *fifo = vring->fifo; struct virtio_net_config *config; struct mlxbf_tmfifo_msg_hdr hdr; int vdev_id, hdr_len; + bool drop_rx = false; /* Read/Write packet header. */ if (is_rx) { @@ -649,8 +650,8 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring, if (ntohs(hdr.len) > __virtio16_to_cpu(virtio_legacy_is_little_endian(), config->mtu) + - MLXBF_TMFIFO_NET_L2_OVERHEAD) - return; + MLXBF_TMFIFO_NET_L2_OVERHEAD) + drop_rx = true; } else { vdev_id = VIRTIO_ID_CONSOLE; hdr_len = 0; @@ -665,16 +666,25 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring, if (!tm_dev2) return; - vring->desc = desc; + vring->desc = *desc; vring = &tm_dev2->vrings[MLXBF_TMFIFO_VRING_RX]; *vring_change = true; } + + if (drop_rx && !IS_VRING_DROP(vring)) { + if (vring->desc_head) + mlxbf_tmfifo_release_pkt(vring); + *desc = &vring->drop_desc; + vring->desc_head = *desc; + vring->desc = *desc; + } + vring->pkt_len = ntohs(hdr.len) + hdr_len; } else { /* Network virtio has an extra header. */ hdr_len = (vring->vdev_id == VIRTIO_ID_NET) ? sizeof(struct virtio_net_hdr) : 0; - vring->pkt_len = mlxbf_tmfifo_get_pkt_len(vring, desc); + vring->pkt_len = mlxbf_tmfifo_get_pkt_len(vring, *desc); hdr.type = (vring->vdev_id == VIRTIO_ID_NET) ? VIRTIO_ID_NET : VIRTIO_ID_CONSOLE; hdr.len = htons(vring->pkt_len - hdr_len); @@ -723,7 +733,7 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring, /* Beginning of a packet. Start to Rx/Tx packet header. */ if (vring->pkt_len == 0) { - mlxbf_tmfifo_rxtx_header(vring, desc, is_rx, &vring_change); + mlxbf_tmfifo_rxtx_header(vring, &desc, is_rx, &vring_change); (*avail)--; /* Return if new packet is for another ring. */ From 3f16330a4869e08d646d91b2637e49c20c5ffd65 Mon Sep 17 00:00:00 2001 From: Shravan Kumar Ramani Date: Tue, 5 Sep 2023 08:49:32 -0400 Subject: [PATCH 1484/2093] platform/mellanox: mlxbf-pmc: Fix potential buffer overflows [ Upstream commit 80ccd40568bcd3655b0fd0be1e9b3379fd6e1056 ] Replace sprintf with sysfs_emit where possible. Size check in mlxbf_pmc_event_list_show should account for "\0". Fixes: 1a218d312e65 ("platform/mellanox: mlxbf-pmc: Add Mellanox BlueField PMC driver") Signed-off-by: Shravan Kumar Ramani Reviewed-by: Vadim Pasternak Reviewed-by: David Thompson Link: https://lore.kernel.org/r/bef39ef32319a31b32f999065911f61b0d3b17c3.1693917738.git.shravankr@nvidia.com Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/mlxbf-pmc.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index be967d797c28..95afcae7b9fa 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -1008,7 +1008,7 @@ static ssize_t mlxbf_pmc_counter_show(struct device *dev, } else return -EINVAL; - return sprintf(buf, "0x%llx\n", value); + return sysfs_emit(buf, "0x%llx\n", value); } /* Store function for "counter" sysfs files */ @@ -1078,13 +1078,13 @@ static ssize_t mlxbf_pmc_event_show(struct device *dev, err = mlxbf_pmc_read_event(blk_num, cnt_num, is_l3, &evt_num); if (err) - return sprintf(buf, "No event being monitored\n"); + return sysfs_emit(buf, "No event being monitored\n"); evt_name = mlxbf_pmc_get_event_name(pmc->block_name[blk_num], evt_num); if (!evt_name) return -EINVAL; - return sprintf(buf, "0x%llx: %s\n", evt_num, evt_name); + return sysfs_emit(buf, "0x%llx: %s\n", evt_num, evt_name); } /* Store function for "event" sysfs files */ @@ -1139,9 +1139,9 @@ static ssize_t mlxbf_pmc_event_list_show(struct device *dev, return -EINVAL; for (i = 0, buf[0] = '\0'; i < size; ++i) { - len += sprintf(e_info, "0x%x: %s\n", events[i].evt_num, - events[i].evt_name); - if (len > PAGE_SIZE) + len += snprintf(e_info, sizeof(e_info), "0x%x: %s\n", + events[i].evt_num, events[i].evt_name); + if (len >= PAGE_SIZE) break; strcat(buf, e_info); ret = len; @@ -1168,7 +1168,7 @@ static ssize_t mlxbf_pmc_enable_show(struct device *dev, value = FIELD_GET(MLXBF_PMC_L3C_PERF_CNT_CFG_EN, perfcnt_cfg); - return sprintf(buf, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } /* Store function for "enable" sysfs files - only for l3cache */ From 9d392695f323d564f84b03ef3991c0a507c4646e Mon Sep 17 00:00:00 2001 From: Shravan Kumar Ramani Date: Tue, 5 Sep 2023 08:49:33 -0400 Subject: [PATCH 1485/2093] platform/mellanox: mlxbf-pmc: Fix reading of unprogrammed events [ Upstream commit 0f5969452e162efc50bdc98968fb62b424a9874b ] This fix involves 2 changes: - All event regs have a reset value of 0, which is not a valid event_number as per the event_list for most blocks and hence seen as an error. Add a "disable" event with event_number 0 for all blocks. - The enable bit for each counter need not be checked before reading the event info, and hence removed. Fixes: 1a218d312e65 ("platform/mellanox: mlxbf-pmc: Add Mellanox BlueField PMC driver") Signed-off-by: Shravan Kumar Ramani Reviewed-by: Vadim Pasternak Reviewed-by: David Thompson Link: https://lore.kernel.org/r/04d0213932d32681de1c716b54320ed894e52425.1693917738.git.shravankr@nvidia.com Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/mlxbf-pmc.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 95afcae7b9fa..2d4bbe99959e 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -191,6 +191,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_smgen_events[] = { }; static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_1[] = { + { 0x0, "DISABLE" }, { 0xa0, "TPIO_DATA_BEAT" }, { 0xa1, "TDMA_DATA_BEAT" }, { 0xa2, "MAP_DATA_BEAT" }, @@ -214,6 +215,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_1[] = { }; static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_2[] = { + { 0x0, "DISABLE" }, { 0xa0, "TPIO_DATA_BEAT" }, { 0xa1, "TDMA_DATA_BEAT" }, { 0xa2, "MAP_DATA_BEAT" }, @@ -246,6 +248,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_2[] = { }; static const struct mlxbf_pmc_events mlxbf_pmc_ecc_events[] = { + { 0x0, "DISABLE" }, { 0x100, "ECC_SINGLE_ERROR_CNT" }, { 0x104, "ECC_DOUBLE_ERROR_CNT" }, { 0x114, "SERR_INJ" }, @@ -258,6 +261,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_ecc_events[] = { }; static const struct mlxbf_pmc_events mlxbf_pmc_mss_events[] = { + { 0x0, "DISABLE" }, { 0xc0, "RXREQ_MSS" }, { 0xc1, "RXDAT_MSS" }, { 0xc2, "TXRSP_MSS" }, @@ -265,6 +269,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_mss_events[] = { }; static const struct mlxbf_pmc_events mlxbf_pmc_hnf_events[] = { + { 0x0, "DISABLE" }, { 0x45, "HNF_REQUESTS" }, { 0x46, "HNF_REJECTS" }, { 0x47, "ALL_BUSY" }, @@ -323,6 +328,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_hnf_events[] = { }; static const struct mlxbf_pmc_events mlxbf_pmc_hnfnet_events[] = { + { 0x0, "DISABLE" }, { 0x12, "CDN_REQ" }, { 0x13, "DDN_REQ" }, { 0x14, "NDN_REQ" }, @@ -892,7 +898,7 @@ static int mlxbf_pmc_read_event(int blk_num, uint32_t cnt_num, bool is_l3, uint64_t *result) { uint32_t perfcfg_offset, perfval_offset; - uint64_t perfmon_cfg, perfevt, perfctl; + uint64_t perfmon_cfg, perfevt; if (cnt_num >= pmc->block[blk_num].counters) return -EINVAL; @@ -904,25 +910,6 @@ static int mlxbf_pmc_read_event(int blk_num, uint32_t cnt_num, bool is_l3, perfval_offset = perfcfg_offset + pmc->block[blk_num].counters * MLXBF_PMC_REG_SIZE; - /* Set counter in "read" mode */ - perfmon_cfg = FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_ADDR, - MLXBF_PMC_PERFCTL); - perfmon_cfg |= FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_STROBE, 1); - perfmon_cfg |= FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_WR_R_B, 0); - - if (mlxbf_pmc_write(pmc->block[blk_num].mmio_base + perfcfg_offset, - MLXBF_PMC_WRITE_REG_64, perfmon_cfg)) - return -EFAULT; - - /* Check if the counter is enabled */ - - if (mlxbf_pmc_read(pmc->block[blk_num].mmio_base + perfval_offset, - MLXBF_PMC_READ_REG_64, &perfctl)) - return -EFAULT; - - if (!FIELD_GET(MLXBF_PMC_PERFCTL_EN0, perfctl)) - return -EINVAL; - /* Set counter in "read" mode */ perfmon_cfg = FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_ADDR, MLXBF_PMC_PERFEVT); From f72497c521c98f2112b4649b43b90659533d7e43 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 4 Sep 2023 14:00:35 +0200 Subject: [PATCH 1486/2093] platform/mellanox: NVSW_SN2201 should depend on ACPI [ Upstream commit 0a138f1670bd1af13ba6949c48ea86ddd4bf557e ] The only probing method supported by the Nvidia SN2201 platform driver is probing through an ACPI match table. Hence add a dependency on ACPI, to prevent asking the user about this driver when configuring a kernel without ACPI support. Fixes: 662f24826f95 ("platform/mellanox: Add support for new SN2201 system") Signed-off-by: Geert Uytterhoeven Acked-by: Vadim Pasternak Acked-by: Andi Shyti Link: https://lore.kernel.org/r/ec5a4071691ab08d58771b7732a9988e89779268.1693828363.git.geert+renesas@glider.be Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/platform/mellanox/Kconfig b/drivers/platform/mellanox/Kconfig index 382793e73a60..30b50920b278 100644 --- a/drivers/platform/mellanox/Kconfig +++ b/drivers/platform/mellanox/Kconfig @@ -80,8 +80,8 @@ config MLXBF_PMC config NVSW_SN2201 tristate "Nvidia SN2201 platform driver support" - depends on HWMON - depends on I2C + depends on HWMON && I2C + depends on ACPI || COMPILE_TEST select REGMAP_I2C help This driver provides support for the Nvidia SN2201 platform. From 7f4116c6f98412a6e29ace6d6a7b41ebb4e8a392 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Sat, 9 Sep 2023 16:14:34 +0800 Subject: [PATCH 1487/2093] net/tls: do not free tls_rec on async operation in bpf_exec_tx_verdict() [ Upstream commit cfaa80c91f6f99b9342b6557f0f0e1143e434066 ] I got the below warning when do fuzzing test: BUG: KASAN: null-ptr-deref in scatterwalk_copychunks+0x320/0x470 Read of size 4 at addr 0000000000000008 by task kworker/u8:1/9 CPU: 0 PID: 9 Comm: kworker/u8:1 Tainted: G OE Hardware name: linux,dummy-virt (DT) Workqueue: pencrypt_parallel padata_parallel_worker Call trace: dump_backtrace+0x0/0x420 show_stack+0x34/0x44 dump_stack+0x1d0/0x248 __kasan_report+0x138/0x140 kasan_report+0x44/0x6c __asan_load4+0x94/0xd0 scatterwalk_copychunks+0x320/0x470 skcipher_next_slow+0x14c/0x290 skcipher_walk_next+0x2fc/0x480 skcipher_walk_first+0x9c/0x110 skcipher_walk_aead_common+0x380/0x440 skcipher_walk_aead_encrypt+0x54/0x70 ccm_encrypt+0x13c/0x4d0 crypto_aead_encrypt+0x7c/0xfc pcrypt_aead_enc+0x28/0x84 padata_parallel_worker+0xd0/0x2dc process_one_work+0x49c/0xbdc worker_thread+0x124/0x880 kthread+0x210/0x260 ret_from_fork+0x10/0x18 This is because the value of rec_seq of tls_crypto_info configured by the user program is too large, for example, 0xffffffffffffff. In addition, TLS is asynchronously accelerated. When tls_do_encryption() returns -EINPROGRESS and sk->sk_err is set to EBADMSG due to rec_seq overflow, skmsg is released before the asynchronous encryption process ends. As a result, the UAF problem occurs during the asynchronous processing of the encryption module. If the operation is asynchronous and the encryption module returns EINPROGRESS, do not free the record information. Fixes: 635d93981786 ("net/tls: free record only on encryption error") Signed-off-by: Liu Jian Reviewed-by: Sabrina Dubroca Link: https://lore.kernel.org/r/20230909081434.2324940-1-liujian56@huawei.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/tls/tls_sw.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 96b4545ea700..9be00ebbb234 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -802,7 +802,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, psock = sk_psock_get(sk); if (!psock || !policy) { err = tls_push_record(sk, flags, record_type); - if (err && sk->sk_err == EBADMSG) { + if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); err = -sk->sk_err; @@ -831,7 +831,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, switch (psock->eval) { case __SK_PASS: err = tls_push_record(sk, flags, record_type); - if (err && sk->sk_err == EBADMSG) { + if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); err = -sk->sk_err; From 7aa720c350c7108179a37c3cec0b80087ab7479c Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Tue, 11 Apr 2023 18:07:11 +0530 Subject: [PATCH 1488/2093] net: macb: Enable PTP unicast [ Upstream commit ee4e92c26c60b7344b7261035683a37da5a6119b ] Enable transmission and reception of PTP unicast packets by updating PTP unicast config bit and setting current HW mac address as allowed address in PTP unicast filter registers. Signed-off-by: Harini Katakam Signed-off-by: Michal Simek Signed-off-by: Radhey Shyam Pandey Signed-off-by: Jakub Kicinski Stable-dep-of: 403f0e771457 ("net: macb: fix sleep inside spinlock") Signed-off-by: Sasha Levin --- drivers/net/ethernet/cadence/macb.h | 4 ++++ drivers/net/ethernet/cadence/macb_main.c | 13 +++++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 9c410f93a103..1aa578c1ca4a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -95,6 +95,8 @@ #define GEM_SA4B 0x00A0 /* Specific4 Bottom */ #define GEM_SA4T 0x00A4 /* Specific4 Top */ #define GEM_WOL 0x00b8 /* Wake on LAN */ +#define GEM_RXPTPUNI 0x00D4 /* PTP RX Unicast address */ +#define GEM_TXPTPUNI 0x00D8 /* PTP TX Unicast address */ #define GEM_EFTSH 0x00e8 /* PTP Event Frame Transmitted Seconds Register 47:32 */ #define GEM_EFRSH 0x00ec /* PTP Event Frame Received Seconds Register 47:32 */ #define GEM_PEFTSH 0x00f0 /* PTP Peer Event Frame Transmitted Seconds Register 47:32 */ @@ -245,6 +247,8 @@ #define MACB_TZQ_OFFSET 12 /* Transmit zero quantum pause frame */ #define MACB_TZQ_SIZE 1 #define MACB_SRTSM_OFFSET 15 /* Store Receive Timestamp to Memory */ +#define MACB_PTPUNI_OFFSET 20 /* PTP Unicast packet enable */ +#define MACB_PTPUNI_SIZE 1 #define MACB_OSSMODE_OFFSET 24 /* Enable One Step Synchro Mode */ #define MACB_OSSMODE_SIZE 1 #define MACB_MIIONRGMII_OFFSET 28 /* MII Usage on RGMII Interface */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 5fb991835078..9470e895591e 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -288,6 +288,11 @@ static void macb_set_hwaddr(struct macb *bp) top = cpu_to_le16(*((u16 *)(bp->dev->dev_addr + 4))); macb_or_gem_writel(bp, SA1T, top); + if (gem_has_ptp(bp)) { + gem_writel(bp, RXPTPUNI, bottom); + gem_writel(bp, TXPTPUNI, bottom); + } + /* Clear unused address register sets */ macb_or_gem_writel(bp, SA2B, 0); macb_or_gem_writel(bp, SA2T, 0); @@ -721,8 +726,12 @@ static void macb_mac_link_up(struct phylink_config *config, spin_unlock_irqrestore(&bp->lock, flags); - /* Enable Rx and Tx */ - macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); + /* Enable Rx and Tx; Enable PTP unicast */ + ctrl = macb_readl(bp, NCR); + if (gem_has_ptp(bp)) + ctrl |= MACB_BIT(PTPUNI); + + macb_writel(bp, NCR, ctrl | MACB_BIT(RE) | MACB_BIT(TE)); netif_tx_wake_all_queues(ndev); } From d5d315cf7687dd9b8dcf9da09d9145f86b30fe2a Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Fri, 8 Sep 2023 13:29:13 +0200 Subject: [PATCH 1489/2093] net: macb: fix sleep inside spinlock [ Upstream commit 403f0e771457e2b8811dc280719d11b9bacf10f4 ] macb_set_tx_clk() is called under a spinlock but itself calls clk_set_rate() which can sleep. This results in: | BUG: sleeping function called from invalid context at kernel/locking/mutex.c:580 | pps pps1: new PPS source ptp1 | in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 40, name: kworker/u4:3 | preempt_count: 1, expected: 0 | RCU nest depth: 0, expected: 0 | 4 locks held by kworker/u4:3/40: | #0: ffff000003409148 | macb ff0c0000.ethernet: gem-ptp-timer ptp clock registered. | ((wq_completion)events_power_efficient){+.+.}-{0:0}, at: process_one_work+0x14c/0x51c | #1: ffff8000833cbdd8 ((work_completion)(&pl->resolve)){+.+.}-{0:0}, at: process_one_work+0x14c/0x51c | #2: ffff000004f01578 (&pl->state_mutex){+.+.}-{4:4}, at: phylink_resolve+0x44/0x4e8 | #3: ffff000004f06f50 (&bp->lock){....}-{3:3}, at: macb_mac_link_up+0x40/0x2ac | irq event stamp: 113998 | hardirqs last enabled at (113997): [] _raw_spin_unlock_irq+0x30/0x64 | hardirqs last disabled at (113998): [] _raw_spin_lock_irqsave+0xac/0xc8 | softirqs last enabled at (113608): [] __do_softirq+0x430/0x4e4 | softirqs last disabled at (113597): [] ____do_softirq+0x10/0x1c | CPU: 0 PID: 40 Comm: kworker/u4:3 Not tainted 6.5.0-11717-g9355ce8b2f50-dirty #368 | Hardware name: ... ZynqMP ... (DT) | Workqueue: events_power_efficient phylink_resolve | Call trace: | dump_backtrace+0x98/0xf0 | show_stack+0x18/0x24 | dump_stack_lvl+0x60/0xac | dump_stack+0x18/0x24 | __might_resched+0x144/0x24c | __might_sleep+0x48/0x98 | __mutex_lock+0x58/0x7b0 | mutex_lock_nested+0x24/0x30 | clk_prepare_lock+0x4c/0xa8 | clk_set_rate+0x24/0x8c | macb_mac_link_up+0x25c/0x2ac | phylink_resolve+0x178/0x4e8 | process_one_work+0x1ec/0x51c | worker_thread+0x1ec/0x3e4 | kthread+0x120/0x124 | ret_from_fork+0x10/0x20 The obvious fix is to move the call to macb_set_tx_clk() out of the protected area. This seems safe as rx and tx are both disabled anyway at this point. It is however not entirely clear what the spinlock shall protect. It could be the read-modify-write access to the NCFGR register, but this is accessed in macb_set_rx_mode() and macb_set_rxcsum_feature() as well without holding the spinlock. It could also be the register accesses done in mog_init_rings() or macb_init_buffers(), but again these functions are called without holding the spinlock in macb_hresp_error_task(). The locking seems fishy in this driver and it might deserve another look before this patch is applied. Fixes: 633e98a711ac0 ("net: macb: use resolved link config in mac_link_up()") Signed-off-by: Sascha Hauer Link: https://lore.kernel.org/r/20230908112913.1701766-1-s.hauer@pengutronix.de Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/cadence/macb_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 9470e895591e..54b032a46b48 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -705,8 +705,6 @@ static void macb_mac_link_up(struct phylink_config *config, if (rx_pause) ctrl |= MACB_BIT(PAE); - macb_set_tx_clk(bp, speed); - /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down * cleared the pipeline and control registers. */ @@ -726,6 +724,9 @@ static void macb_mac_link_up(struct phylink_config *config, spin_unlock_irqrestore(&bp->lock, flags); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + macb_set_tx_clk(bp, speed); + /* Enable Rx and Tx; Enable PTP unicast */ ctrl = macb_readl(bp, NCR); if (gem_has_ptp(bp)) From 8b6556c4c4e35707c0e102a861e94a3ecb223342 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Sep 2023 15:42:13 +0000 Subject: [PATCH 1490/2093] ipv6: fix ip6_sock_set_addr_preferences() typo [ Upstream commit 8cdd9f1aaedf823006449faa4e540026c692ac43 ] ip6_sock_set_addr_preferences() second argument should be an integer. SUNRPC attempts to set IPV6_PREFER_SRC_PUBLIC were translated to IPV6_PREFER_SRC_TMP Fixes: 18d5ad623275 ("ipv6: add ip6_sock_set_addr_preferences") Signed-off-by: Eric Dumazet Cc: Christoph Hellwig Cc: Chuck Lever Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230911154213.713941-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e4ceef687c1c..8ced11216759 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1322,7 +1322,7 @@ static inline int __ip6_sock_set_addr_preferences(struct sock *sk, int val) return 0; } -static inline int ip6_sock_set_addr_preferences(struct sock *sk, bool val) +static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val) { int ret; From 82f9af464e01f314f228523ef4cb8f46406c587a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 27 Mar 2023 16:54:54 -0700 Subject: [PATCH 1491/2093] ipv6: Remove in6addr_any alternatives. [ Upstream commit 8cdc3223e78c43e1b60ea1c536a103e32fdca3c5 ] Some code defines the IPv6 wildcard address as a local variable and use it with memcmp() or ipv6_addr_equal(). Let's use in6addr_any and ipv6_addr_any() instead. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Mark Bloch Reviewed-by: David Ahern Signed-off-by: David S. Miller Stable-dep-of: aa99e5f87bd5 ("tcp: Fix bind() regression for v4-mapped-v6 wildcard address.") Signed-off-by: Sasha Levin --- .../net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 5 ++--- include/net/ip6_fib.h | 9 +++------ include/trace/events/fib.h | 5 ++--- include/trace/events/fib6.h | 5 +---- net/ethtool/ioctl.c | 10 +++++----- net/ipv4/inet_hashtables.c | 11 ++++------- 6 files changed, 17 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 72b61f66df37..cd15d36b1507 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -97,7 +97,6 @@ int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) else if (ip_version == 6) { int ipv6_size = MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6); - struct in6_addr zerov6 = {}; daddr = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6); @@ -105,8 +104,8 @@ int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6); memcpy(&tun_attr->dst_ip.v6, daddr, ipv6_size); memcpy(&tun_attr->src_ip.v6, saddr, ipv6_size); - if (!memcmp(&tun_attr->dst_ip.v6, &zerov6, sizeof(zerov6)) || - !memcmp(&tun_attr->src_ip.v6, &zerov6, sizeof(zerov6))) + if (ipv6_addr_any(&tun_attr->dst_ip.v6) || + ipv6_addr_any(&tun_attr->src_ip.v6)) return 0; } #endif diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index a92f6eb85306..fa4e6af382e2 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -472,13 +472,10 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) rcu_read_lock(); from = rcu_dereference(rt->from); - if (from) { + if (from) *addr = from->fib6_prefsrc.addr; - } else { - struct in6_addr in6_zero = {}; - - *addr = in6_zero; - } + else + *addr = in6addr_any; rcu_read_unlock(); } diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h index c2300c407f58..76297ecd4935 100644 --- a/include/trace/events/fib.h +++ b/include/trace/events/fib.h @@ -36,7 +36,6 @@ TRACE_EVENT(fib_table_lookup, ), TP_fast_assign( - struct in6_addr in6_zero = {}; struct net_device *dev; struct in6_addr *in6; __be32 *p32; @@ -74,7 +73,7 @@ TRACE_EVENT(fib_table_lookup, *p32 = nhc->nhc_gw.ipv4; in6 = (struct in6_addr *)__entry->gw6; - *in6 = in6_zero; + *in6 = in6addr_any; } else if (nhc->nhc_gw_family == AF_INET6) { p32 = (__be32 *) __entry->gw4; *p32 = 0; @@ -87,7 +86,7 @@ TRACE_EVENT(fib_table_lookup, *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; - *in6 = in6_zero; + *in6 = in6addr_any; } ), diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h index 6e821eb79450..4d3e607b3cde 100644 --- a/include/trace/events/fib6.h +++ b/include/trace/events/fib6.h @@ -68,11 +68,8 @@ TRACE_EVENT(fib6_table_lookup, strcpy(__entry->name, "-"); } if (res->f6i == net->ipv6.fib6_null_entry) { - struct in6_addr in6_zero = {}; - in6 = (struct in6_addr *)__entry->gw; - *in6 = in6_zero; - + *in6 = in6addr_any; } else if (res->nh) { in6 = (struct in6_addr *)__entry->gw; *in6 = res->nh->fib_nh_gw6; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 940c0e27be73..e31d1247b9f0 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -3090,7 +3091,6 @@ struct ethtool_rx_flow_rule * ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) { const struct ethtool_rx_flow_spec *fs = input->fs; - static struct in6_addr zero_addr = {}; struct ethtool_rx_flow_match *match; struct ethtool_rx_flow_rule *flow; struct flow_action_entry *act; @@ -3196,20 +3196,20 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) v6_spec = &fs->h_u.tcp_ip6_spec; v6_m_spec = &fs->m_u.tcp_ip6_spec; - if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + if (!ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6src)) { memcpy(&match->key.ipv6.src, v6_spec->ip6src, sizeof(match->key.ipv6.src)); memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src, sizeof(match->mask.ipv6.src)); } - if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { + if (!ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6dst)) { memcpy(&match->key.ipv6.dst, v6_spec->ip6dst, sizeof(match->key.ipv6.dst)); memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst, sizeof(match->mask.ipv6.dst)); } - if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || - memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { + if (!ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6src) || + !ipv6_addr_any((struct in6_addr *)v6_m_spec->ip6dst)) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c19b462662ad..38a92c8c6686 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -813,13 +813,11 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const unsigned short port, int l3mdev, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - struct in6_addr addr_any = {}; - if (sk->sk_family != tb->family) { if (sk->sk_family == AF_INET) return net_eq(ib2_net(tb), net) && tb->port == port && tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &addr_any); + ipv6_addr_any(&tb->v6_rcv_saddr); return false; } @@ -827,7 +825,7 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const if (sk->sk_family == AF_INET6) return net_eq(ib2_net(tb), net) && tb->port == port && tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &addr_any); + ipv6_addr_any(&tb->v6_rcv_saddr); else #endif return net_eq(ib2_net(tb), net) && tb->port == port && @@ -853,11 +851,10 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); u32 hash; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr addr_any = {}; +#if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) - hash = ipv6_portaddr_hash(net, &addr_any, port); + hash = ipv6_portaddr_hash(net, &in6addr_any, port); else #endif hash = ipv4_portaddr_hash(net, 0, port); From 489ced24c7cac38db8af63f79f118fe78c3c709d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Sep 2023 11:36:55 -0700 Subject: [PATCH 1492/2093] tcp: Factorise sk_family-independent comparison in inet_bind2_bucket_match(_addr_any). [ Upstream commit c6d277064b1da7f9015b575a562734de87a7e463 ] This is a prep patch to make the following patches cleaner that touch inet_bind2_bucket_match() and inet_bind2_bucket_match_addr_any(). Both functions have duplicated comparison for netns, port, and l3mdev. Let's factorise them. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: aa99e5f87bd5 ("tcp: Fix bind() regression for v4-mapped-v6 wildcard address.") Signed-off-by: Sasha Levin --- net/ipv4/inet_hashtables.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 38a92c8c6686..71d77b3b6536 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -795,41 +795,39 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { + if (!net_eq(ib2_net(tb), net) || tb->port != port || + tb->l3mdev != l3mdev) + return false; + #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family != tb->family) return false; if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); - else + return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); #endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr; + return tb->rcv_saddr == sk->sk_rcv_saddr; } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { + if (!net_eq(ib2_net(tb), net) || tb->port != port || + tb->l3mdev != l3mdev) + return false; + #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family != tb->family) { if (sk->sk_family == AF_INET) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_any(&tb->v6_rcv_saddr); + return ipv6_addr_any(&tb->v6_rcv_saddr); return false; } if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_any(&tb->v6_rcv_saddr); - else + return ipv6_addr_any(&tb->v6_rcv_saddr); #endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == 0; + return tb->rcv_saddr == 0; } /* The socket's bhash2 hashbucket spinlock must be held when this is called */ From 63830afece934aa94cdbc9610598829d05d81a00 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Sep 2023 11:36:56 -0700 Subject: [PATCH 1493/2093] tcp: Fix bind() regression for v4-mapped-v6 wildcard address. [ Upstream commit aa99e5f87bd54db55dd37cb130bd5eb55933027f ] Andrei Vagin reported bind() regression with strace logs. If we bind() a TCPv6 socket to ::FFFF:0.0.0.0 and then bind() a TCPv4 socket to 127.0.0.1, the 2nd bind() should fail but now succeeds. from socket import * s1 = socket(AF_INET6, SOCK_STREAM) s1.bind(('::ffff:0.0.0.0', 0)) s2 = socket(AF_INET, SOCK_STREAM) s2.bind(('127.0.0.1', s1.getsockname()[1])) During the 2nd bind(), if tb->family is AF_INET6 and sk->sk_family is AF_INET in inet_bind2_bucket_match_addr_any(), we still need to check if tb has the v4-mapped-v6 wildcard address. The example above does not work after commit 5456262d2baa ("net: Fix incorrect address comparison when searching for a bind2 bucket"), but the blamed change is not the commit. Before the commit, the leading zeros of ::FFFF:0.0.0.0 were treated as 0.0.0.0, and the sequence above worked by chance. Technically, this case has been broken since bhash2 was introduced. Note that if we bind() two sockets to 127.0.0.1 and then ::FFFF:0.0.0.0, the 2nd bind() fails properly because we fall back to using bhash to detect conflicts for the v4-mapped-v6 address. Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: Andrei Vagin Closes: https://lore.kernel.org/netdev/ZPuYBOFC8zsK6r9T@google.com/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/ipv6.h | 5 +++++ net/ipv4/inet_hashtables.c | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8ced11216759..517bdae78614 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -750,6 +750,11 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) cpu_to_be32(0x0000ffff))) == 0UL; } +static inline bool ipv6_addr_v4mapped_any(const struct in6_addr *a) +{ + return ipv6_addr_v4mapped(a) && ipv4_is_zeronet(a->s6_addr32[3]); +} + static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 71d77b3b6536..eb522c0374d5 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -819,7 +819,8 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family != tb->family) { if (sk->sk_family == AF_INET) - return ipv6_addr_any(&tb->v6_rcv_saddr); + return ipv6_addr_any(&tb->v6_rcv_saddr) || + ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr); return false; } From 6f0d85d501ab51f1b6bf6aeb37347499762d11fa Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Sep 2023 11:36:57 -0700 Subject: [PATCH 1494/2093] tcp: Fix bind() regression for v4-mapped-v6 non-wildcard address. [ Upstream commit c48ef9c4aed3632566b57ba66cec6ec78624d4cb ] Since bhash2 was introduced, the example below does not work as expected. These two bind() should conflict, but the 2nd bind() now succeeds. from socket import * s1 = socket(AF_INET6, SOCK_STREAM) s1.bind(('::ffff:127.0.0.1', 0)) s2 = socket(AF_INET, SOCK_STREAM) s2.bind(('127.0.0.1', s1.getsockname()[1])) During the 2nd bind() in inet_csk_get_port(), inet_bind2_bucket_find() fails to find the 1st socket's tb2, so inet_bind2_bucket_create() allocates a new tb2 for the 2nd socket. Then, we call inet_csk_bind_conflict() that checks conflicts in the new tb2 by inet_bhash2_conflict(). However, the new tb2 does not include the 1st socket, thus the bind() finally succeeds. In this case, inet_bind2_bucket_match() must check if AF_INET6 tb2 has the conflicting v4-mapped-v6 address so that inet_bind2_bucket_find() returns the 1st socket's tb2. Note that if we bind two sockets to 127.0.0.1 and then ::FFFF:127.0.0.1, the 2nd bind() fails properly for the same reason mentinoed in the previous commit. Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Acked-by: Andrei Vagin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/inet_hashtables.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index eb522c0374d5..d79de4b95186 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -800,8 +800,13 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, return false; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) + if (sk->sk_family != tb->family) { + if (sk->sk_family == AF_INET) + return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) && + tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; + return false; + } if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); From a47db2caae27a2e1d991a4853216fa7f448a94d9 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Mon, 11 Sep 2023 13:28:14 -0700 Subject: [PATCH 1495/2093] ixgbe: fix timestamp configuration code [ Upstream commit 3c44191dd76cf9c0cc49adaf34384cbd42ef8ad2 ] The commit in fixes introduced flags to control the status of hardware configuration while processing packets. At the same time another structure is used to provide configuration of timestamper to user-space applications. The way it was coded makes this structures go out of sync easily. The repro is easy for 82599 chips: [root@hostname ~]# hwstamp_ctl -i eth0 -r 12 -t 1 current settings: tx_type 0 rx_filter 0 new settings: tx_type 1 rx_filter 12 The eth0 device is properly configured to timestamp any PTPv2 events. [root@hostname ~]# hwstamp_ctl -i eth0 -r 1 -t 1 current settings: tx_type 1 rx_filter 12 SIOCSHWTSTAMP failed: Numerical result out of range The requested time stamping mode is not supported by the hardware. The error is properly returned because HW doesn't support all packets timestamping. But the adapter->flags is cleared of timestamp flags even though no HW configuration was done. From that point no RX timestamps are received by user-space application. But configuration shows good values: [root@hostname ~]# hwstamp_ctl -i eth0 current settings: tx_type 1 rx_filter 12 Fix the issue by applying new flags only when the HW was actually configured. Fixes: a9763f3cb54c ("ixgbe: Update PTP to support X550EM_x devices") Signed-off-by: Vadim Fedorenko Reviewed-by: Simon Horman Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 28 +++++++++++--------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index f8605f57bd06..75e1383263c1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -995,6 +995,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED; u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED; u32 tsync_rx_mtrl = PTP_EV_PORT << 16; + u32 aflags = adapter->flags; bool is_l2 = false; u32 regval; @@ -1012,20 +1013,20 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, case HWTSTAMP_FILTER_NONE: tsync_rx_ctl = 0; tsync_rx_mtrl = 0; - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG; - adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG; - adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: @@ -1039,8 +1040,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2; is_l2 = true; config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; - adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_NTP_ALL: @@ -1051,7 +1052,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, if (hw->mac.type >= ixgbe_mac_X550) { tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_ALL; config->rx_filter = HWTSTAMP_FILTER_ALL; - adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; + aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; break; } fallthrough; @@ -1062,8 +1063,6 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, * Delay_Req messages and hardware does not support * timestamping all packets => return error */ - adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | - IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); config->rx_filter = HWTSTAMP_FILTER_NONE; return -ERANGE; } @@ -1095,8 +1094,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, IXGBE_TSYNCRXCTL_TYPE_ALL | IXGBE_TSYNCRXCTL_TSIP_UT_EN; config->rx_filter = HWTSTAMP_FILTER_ALL; - adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; - adapter->flags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER; + aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; + aflags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER; is_l2 = true; break; default: @@ -1129,6 +1128,9 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, IXGBE_WRITE_FLUSH(hw); + /* configure adapter flags only when HW is actually configured */ + adapter->flags = aflags; + /* clear TX/RX time stamp registers, just to be sure */ ixgbe_ptp_clear_tx_timestamp(adapter); IXGBE_READ_REG(hw, IXGBE_RXSTMPH); From e5b28ce127a690f3acc49a6a342e6c9442c9edd6 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Sep 2023 19:27:53 -0700 Subject: [PATCH 1496/2093] kcm: Fix error handling for SOCK_DGRAM in kcm_sendmsg(). [ Upstream commit a22730b1b4bf437c6bbfdeff5feddf54be4aeada ] syzkaller found a memory leak in kcm_sendmsg(), and commit c821a88bd720 ("kcm: Fix memory leak in error path of kcm_sendmsg()") suppressed it by updating kcm_tx_msg(head)->last_skb if partial data is copied so that the following sendmsg() will resume from the skb. However, we cannot know how many bytes were copied when we get the error. Thus, we could mess up the MSG_MORE queue. When kcm_sendmsg() fails for SOCK_DGRAM, we should purge the queue as we do so for UDP by udp_flush_pending_frames(). Even without this change, when the error occurred, the following sendmsg() resumed from a wrong skb and the queue was messed up. However, we have yet to get such a report, and only syzkaller stumbled on it. So, this can be changed safely. Note this does not change SOCK_SEQPACKET behaviour. Fixes: c821a88bd720 ("kcm: Fix memory leak in error path of kcm_sendmsg()") Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230912022753.33327-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/kcm/kcmsock.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index dd929a835074..65845c59c065 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1065,17 +1065,18 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) out_error: kcm_push(kcm); - if (copied && sock->type == SOCK_SEQPACKET) { + if (sock->type == SOCK_SEQPACKET) { /* Wrote some bytes before encountering an * error, return partial success. */ - goto partial_message; - } - - if (head != kcm->seq_skb) + if (copied) + goto partial_message; + if (head != kcm->seq_skb) + kfree_skb(head); + } else { kfree_skb(head); - else if (copied) - kcm_tx_msg(head)->last_skb = skb; + kcm->seq_skb = NULL; + } err = sk_stream_error(sk, msg->msg_flags, err); From 3ce9925584c66c2f5944d581533eec564adc377a Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 18 Jul 2023 15:37:23 +0100 Subject: [PATCH 1497/2093] MIPS: Only fiddle with CHECKFLAGS if `need-compiler' commit 4fe4a6374c4db9ae2b849b61e84b58685dca565a upstream. We have originally guarded fiddling with CHECKFLAGS in our arch Makefile by checking for the CONFIG_MIPS variable, not set for targets such as `distclean', etc. that neither include `.config' nor use the compiler. Starting from commit 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed") we have had a generic `need-compiler' variable explicitly telling us if the compiler will be used and thus its capabilities need to be checked and expressed in the form of compilation flags. If this variable is not set, then `make' functions such as `cc-option' are undefined, causing all kinds of weirdness to happen if we expect specific results to be returned, most recently: cc1: error: '-mloongson-mmi' must be used with '-mhard-float' messages with configurations such as `fuloong2e_defconfig' and the `modules_install' target, which does include `.config' and yet does not use the compiler. Replace the check for CONFIG_MIPS with one for `need-compiler' instead, so as to prevent the compiler from being ever called for CHECKFLAGS when not needed. Reported-by: Guillaume Tucker Closes: https://lore.kernel.org/r/85031c0c-d981-031e-8a50-bc4fad2ddcd8@collabora.com/ Signed-off-by: Maciej W. Rozycki Fixes: 805b2e1d427a ("kbuild: include Makefile.compiler only when compiler is needed") Cc: stable@vger.kernel.org # v5.13+ Reported-by: "kernelci.org bot" Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 75cf36450b62..ee8f47aef98b 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -350,7 +350,7 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_LDFLAGS += -m $(ld-emul) -ifdef CONFIG_MIPS +ifdef need-compiler CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \ egrep -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \ sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g') From 77b49370a261c9c79587d4a83960d5db39ee6cfa Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Wed, 21 Jun 2023 19:13:26 -0400 Subject: [PATCH 1498/2093] drm/amd/display: Fix a bug when searching for insert_above_mpcc commit 3d028d5d60d516c536de1ddd3ebf3d55f3f8983b upstream. [WHY] Currently, when insert_plane is called with insert_above_mpcc parameter that is equal to tree->opp_list, the function returns NULL. [HOW] Instead, the function should insert the plane at the top of the tree. Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Reviewed-by: Jun Lei Acked-by: Tom Chung Signed-off-by: Wesley Chalmers Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c index 8e9384094f6d..f2f55565e98a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c @@ -212,8 +212,9 @@ struct mpcc *mpc1_insert_plane( /* check insert_above_mpcc exist in tree->opp_list */ struct mpcc *temp_mpcc = tree->opp_list; - while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc) - temp_mpcc = temp_mpcc->mpcc_bot; + if (temp_mpcc != insert_above_mpcc) + while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc) + temp_mpcc = temp_mpcc->mpcc_bot; if (temp_mpcc == NULL) return NULL; } From a356197db198ad9825ce225f19f2c7448ef9eea0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 19 Sep 2023 12:28:10 +0200 Subject: [PATCH 1499/2093] Linux 6.1.54 Link: https://lore.kernel.org/r/20230917191040.964416434@linuxfoundation.org Tested-by: SeongJae Park Tested-by: Takeshi Ogasawara Tested-by: Bagas Sanjaya Tested-by: Conor Dooley Tested-by: Ron Economos Tested-by: Jon Hunter Tested-by: Salvatore Bonaccorso Tested-by: Florian Fainelli Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Tested-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index f23edaa0e813..844afa653fdd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 53 +SUBLEVEL = 54 EXTRAVERSION = NAME = Curry Ramen From 726deae613bc1b6096ad3b61cc1e63e33330fbc2 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 4 Aug 2023 13:33:12 +0800 Subject: [PATCH 1500/2093] autofs: fix memory leak of waitqueues in autofs_catatonic_mode [ Upstream commit ccbe77f7e45dfb4420f7f531b650c00c6e9c7507 ] Syzkaller reports a memory leak: BUG: memory leak unreferenced object 0xffff88810b279e00 (size 96): comm "syz-executor399", pid 3631, jiffies 4294964921 (age 23.870s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 08 9e 27 0b 81 88 ff ff ..........'..... 08 9e 27 0b 81 88 ff ff 00 00 00 00 00 00 00 00 ..'............. backtrace: [] kmalloc_trace+0x20/0x90 mm/slab_common.c:1046 [] kmalloc include/linux/slab.h:576 [inline] [] autofs_wait+0x3fa/0x9a0 fs/autofs/waitq.c:378 [] autofs_do_expire_multi+0xa7/0x3e0 fs/autofs/expire.c:593 [] autofs_expire_multi+0x53/0x80 fs/autofs/expire.c:619 [] autofs_root_ioctl_unlocked+0x322/0x3b0 fs/autofs/root.c:897 [] autofs_root_ioctl+0x25/0x30 fs/autofs/root.c:910 [] vfs_ioctl fs/ioctl.c:51 [inline] [] __do_sys_ioctl fs/ioctl.c:870 [inline] [] __se_sys_ioctl fs/ioctl.c:856 [inline] [] __x64_sys_ioctl+0xfc/0x140 fs/ioctl.c:856 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd autofs_wait_queue structs should be freed if their wait_ctr becomes zero. Otherwise they will be lost. In this case an AUTOFS_IOC_EXPIRE_MULTI ioctl is done, then a new waitqueue struct is allocated in autofs_wait(), its initial wait_ctr equals 2. After that wait_event_killable() is interrupted (it returns -ERESTARTSYS), so that 'wq->name.name == NULL' condition may be not satisfied. Actually, this condition can be satisfied when autofs_wait_release() or autofs_catatonic_mode() is called and, what is also important, wait_ctr is decremented in those places. Upon the exit of autofs_wait(), wait_ctr is decremented to 1. Then the unmounting process begins: kill_sb calls autofs_catatonic_mode(), which should have freed the waitqueues, but it only decrements its usage counter to zero which is not a correct behaviour. edit:imk This description is of course not correct. The umount performed as a result of an expire is a umount of a mount that has been automounted, it's not the autofs mount itself. They happen independently, usually after everything mounted within the autofs file system has been expired away. If everything hasn't been expired away the automount daemon can still exit leaving mounts in place. But expires done in both cases will result in a notification that calls autofs_wait_release() with a result status. The problem case is the summary execution of of the automount daemon. In this case any waiting processes won't be woken up until either they are terminated or the mount is umounted. end edit: imk So in catatonic mode we should free waitqueues which counter becomes zero. edit: imk Initially I was concerned that the calling of autofs_wait_release() and autofs_catatonic_mode() was not mutually exclusive but that can't be the case (obviously) because the queue entry (or entries) is removed from the list when either of these two functions are called. Consequently the wait entry will be freed by only one of these functions or by the woken process in autofs_wait() depending on the order of the calls. end edit: imk Reported-by: syzbot+5e53f70e69ff0c0a1c0c@syzkaller.appspotmail.com Suggested-by: Takeshi Misawa Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Signed-off-by: Ian Kent Cc: Matthew Wilcox Cc: Andrei Vagin Cc: autofs@vger.kernel.org Cc: linux-kernel@vger.kernel.org Message-Id: <169112719161.7590.6700123246297365841.stgit@donald.themaw.net> Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/autofs/waitq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index 54c1f8b8b075..efdc76732fae 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -32,8 +32,9 @@ void autofs_catatonic_mode(struct autofs_sb_info *sbi) wq->status = -ENOENT; /* Magic is gone - report failure */ kfree(wq->name.name - wq->offset); wq->name.name = NULL; - wq->wait_ctr--; wake_up_interruptible(&wq->queue); + if (!--wq->wait_ctr) + kfree(wq); wq = nwq; } fput(sbi->pipe); /* Close the pipe */ From 28062cd6eda04035d8f6ded2001292ac8b496149 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 1 Aug 2023 19:02:28 +0800 Subject: [PATCH 1501/2093] btrfs: output extra debug info if we failed to find an inline backref [ Upstream commit 7f72f50547b7af4ddf985b07fc56600a4deba281 ] [BUG] Syzbot reported several warning triggered inside lookup_inline_extent_backref(). [CAUSE] As usual, the reproducer doesn't reliably trigger locally here, but at least we know the WARN_ON() is triggered when an inline backref can not be found, and it can only be triggered when @insert is true. (I.e. inserting a new inline backref, which means the backref should already exist) [ENHANCEMENT] After the WARN_ON(), dump all the parameters and the extent tree leaf to help debug. Link: https://syzkaller.appspot.com/bug?extid=d6f9ff86c1d804ba2bc6 Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/extent-tree.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0640ef59fe66..08ff10a81cb9 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -863,6 +863,11 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, err = -ENOENT; goto out; } else if (WARN_ON(ret)) { + btrfs_print_leaf(path->nodes[0]); + btrfs_err(fs_info, +"extent item not found for insert, bytenr %llu num_bytes %llu parent %llu root_objectid %llu owner %llu offset %llu", + bytenr, num_bytes, parent, root_objectid, owner, + offset); err = -EIO; goto out; } From 34bff6d850019e00001129d6de3aa4874c2cf471 Mon Sep 17 00:00:00 2001 From: Will Shiu Date: Fri, 21 Jul 2023 13:19:04 +0800 Subject: [PATCH 1502/2093] locks: fix KASAN: use-after-free in trace_event_raw_event_filelock_lock [ Upstream commit 74f6f5912693ce454384eaeec48705646a21c74f ] As following backtrace, the struct file_lock request , in posix_lock_inode is free before ftrace function using. Replace the ftrace function ahead free flow could fix the use-after-free issue. [name:report&]=============================================== BUG:KASAN: use-after-free in trace_event_raw_event_filelock_lock+0x80/0x12c [name:report&]Read at addr f6ffff8025622620 by task NativeThread/16753 [name:report_hw_tags&]Pointer tag: [f6], memory tag: [fe] [name:report&] BT: Hardware name: MT6897 (DT) Call trace: dump_backtrace+0xf8/0x148 show_stack+0x18/0x24 dump_stack_lvl+0x60/0x7c print_report+0x2c8/0xa08 kasan_report+0xb0/0x120 __do_kernel_fault+0xc8/0x248 do_bad_area+0x30/0xdc do_tag_check_fault+0x1c/0x30 do_mem_abort+0x58/0xbc el1_abort+0x3c/0x5c el1h_64_sync_handler+0x54/0x90 el1h_64_sync+0x68/0x6c trace_event_raw_event_filelock_lock+0x80/0x12c posix_lock_inode+0xd0c/0xd60 do_lock_file_wait+0xb8/0x190 fcntl_setlk+0x2d8/0x440 ... [name:report&] [name:report&]Allocated by task 16752: ... slab_post_alloc_hook+0x74/0x340 kmem_cache_alloc+0x1b0/0x2f0 posix_lock_inode+0xb0/0xd60 ... [name:report&] [name:report&]Freed by task 16752: ... kmem_cache_free+0x274/0x5b0 locks_dispose_list+0x3c/0x148 posix_lock_inode+0xc40/0xd60 do_lock_file_wait+0xb8/0x190 fcntl_setlk+0x2d8/0x440 do_fcntl+0x150/0xc18 ... Signed-off-by: Will Shiu Signed-off-by: Jeff Layton Signed-off-by: Sasha Levin --- fs/locks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/locks.c b/fs/locks.c index 240b9309ed6d..1047ab2b15e9 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1300,6 +1300,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); + trace_posix_lock_inode(inode, request, error); /* * Free any unused locks. */ @@ -1308,7 +1309,6 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); - trace_posix_lock_inode(inode, request, error); return error; } From e1f686930ee4b059c7baa3c3904b2401829f2589 Mon Sep 17 00:00:00 2001 From: Abhishek Mainkar Date: Mon, 26 Jun 2023 22:26:06 +0000 Subject: [PATCH 1503/2093] ACPICA: Add AML_NO_OPERAND_RESOLVE flag to Timer [ Upstream commit 3a21ffdbc825e0919db9da0e27ee5ff2cc8a863e ] ACPICA commit 90310989a0790032f5a0140741ff09b545af4bc5 According to the ACPI specification 19.6.134, no argument is required to be passed for ASL Timer instruction. For taking care of no argument, AML_NO_OPERAND_RESOLVE flag is added to ASL Timer instruction opcode. When ASL timer instruction interpreted by ACPI interpreter, getting error. After adding AML_NO_OPERAND_RESOLVE flag to ASL Timer instruction opcode, issue is not observed. ============================================================= UBSAN: array-index-out-of-bounds in acpica/dswexec.c:401:12 index -1 is out of range for type 'union acpi_operand_object *[9]' CPU: 37 PID: 1678 Comm: cat Not tainted 6.0.0-dev-th500-6.0.y-1+bcf8c46459e407-generic-64k HW name: NVIDIA BIOS v1.1.1-d7acbfc-dirty 12/19/2022 Call trace: dump_backtrace+0xe0/0x130 show_stack+0x20/0x60 dump_stack_lvl+0x68/0x84 dump_stack+0x18/0x34 ubsan_epilogue+0x10/0x50 __ubsan_handle_out_of_bounds+0x80/0x90 acpi_ds_exec_end_op+0x1bc/0x6d8 acpi_ps_parse_loop+0x57c/0x618 acpi_ps_parse_aml+0x1e0/0x4b4 acpi_ps_execute_method+0x24c/0x2b8 acpi_ns_evaluate+0x3a8/0x4bc acpi_evaluate_object+0x15c/0x37c acpi_evaluate_integer+0x54/0x15c show_power+0x8c/0x12c [acpi_power_meter] Link: https://github.com/acpica/acpica/commit/90310989 Signed-off-by: Abhishek Mainkar Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/acpica/psopcode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index bef69e87a0a2..8c34c0ffb1d9 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -603,7 +603,7 @@ const struct acpi_opcode_info acpi_gbl_aml_op_info[AML_NUM_OPCODES] = { /* 7E */ ACPI_OP("Timer", ARGP_TIMER_OP, ARGI_TIMER_OP, ACPI_TYPE_ANY, AML_CLASS_EXECUTE, AML_TYPE_EXEC_0A_0T_1R, - AML_FLAGS_EXEC_0A_0T_1R), + AML_FLAGS_EXEC_0A_0T_1R | AML_NO_OPERAND_RESOLVE), /* ACPI 5.0 opcodes */ From 3b1107abdc2cabdf2044683fc2fa9743a7da5ccc Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Wed, 14 Jun 2023 09:23:21 -0300 Subject: [PATCH 1504/2093] kernel/fork: beware of __put_task_struct() calling context [ Upstream commit d243b34459cea30cfe5f3a9b2feb44e7daff9938 ] Under PREEMPT_RT, __put_task_struct() indirectly acquires sleeping locks. Therefore, it can't be called from an non-preemptible context. One practical example is splat inside inactive_task_timer(), which is called in a interrupt context: CPU: 1 PID: 2848 Comm: life Kdump: loaded Tainted: G W --------- Hardware name: HP ProLiant DL388p Gen8, BIOS P70 07/15/2012 Call Trace: dump_stack_lvl+0x57/0x7d mark_lock_irq.cold+0x33/0xba mark_lock+0x1e7/0x400 mark_usage+0x11d/0x140 __lock_acquire+0x30d/0x930 lock_acquire.part.0+0x9c/0x210 rt_spin_lock+0x27/0xe0 refill_obj_stock+0x3d/0x3a0 kmem_cache_free+0x357/0x560 inactive_task_timer+0x1ad/0x340 __run_hrtimer+0x8a/0x1a0 __hrtimer_run_queues+0x91/0x130 hrtimer_interrupt+0x10f/0x220 __sysvec_apic_timer_interrupt+0x7b/0xd0 sysvec_apic_timer_interrupt+0x4f/0xd0 asm_sysvec_apic_timer_interrupt+0x12/0x20 RIP: 0033:0x7fff196bf6f5 Instead of calling __put_task_struct() directly, we defer it using call_rcu(). A more natural approach would use a workqueue, but since in PREEMPT_RT, we can't allocate dynamic memory from atomic context, the code would become more complex because we would need to put the work_struct instance in the task_struct and initialize it when we allocate a new task_struct. The issue is reproducible with stress-ng: while true; do stress-ng --sched deadline --sched-period 1000000000 \ --sched-runtime 800000000 --sched-deadline \ 1000000000 --mmapfork 23 -t 20 done Reported-by: Hu Chunyu Suggested-by: Oleg Nesterov Suggested-by: Valentin Schneider Suggested-by: Peter Zijlstra Signed-off-by: Wander Lairson Costa Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230614122323.37957-2-wander@redhat.com Signed-off-by: Sasha Levin --- include/linux/sched/task.h | 28 +++++++++++++++++++++++++++- kernel/fork.c | 8 ++++++++ 2 files changed, 35 insertions(+), 1 deletion(-) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 357e0068497c..7291fb6399d2 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -112,10 +112,36 @@ static inline struct task_struct *get_task_struct(struct task_struct *t) } extern void __put_task_struct(struct task_struct *t); +extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); static inline void put_task_struct(struct task_struct *t) { - if (refcount_dec_and_test(&t->usage)) + if (!refcount_dec_and_test(&t->usage)) + return; + + /* + * under PREEMPT_RT, we can't call put_task_struct + * in atomic context because it will indirectly + * acquire sleeping locks. + * + * call_rcu() will schedule delayed_put_task_struct_rcu() + * to be called in process context. + * + * __put_task_struct() is called when + * refcount_dec_and_test(&t->usage) succeeds. + * + * This means that it can't "conflict" with + * put_task_struct_rcu_user() which abuses ->rcu the same + * way; rcu_users has a reference so task->usage can't be + * zero after rcu_users 1 -> 0 transition. + * + * delayed_free_task() also uses ->rcu, but it is only called + * when it fails to fork a process. Therefore, there is no + * way it can conflict with put_task_struct(). + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) + call_rcu(&t->rcu, __put_task_struct_rcu_cb); + else __put_task_struct(t); } diff --git a/kernel/fork.c b/kernel/fork.c index 41950ff90aa3..85617928041c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -852,6 +852,14 @@ void __put_task_struct(struct task_struct *tsk) } EXPORT_SYMBOL_GPL(__put_task_struct); +void __put_task_struct_rcu_cb(struct rcu_head *rhp) +{ + struct task_struct *task = container_of(rhp, struct task_struct, rcu); + + __put_task_struct(task); +} +EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); + void __init __weak arch_task_cache_init(void) { } /* From 83ed0cdb6ae0383dd14b02375c353773836884ed Mon Sep 17 00:00:00 2001 From: Zqiang Date: Fri, 16 Jun 2023 15:39:26 +0800 Subject: [PATCH 1505/2093] rcuscale: Move rcu_scale_writer() schedule_timeout_uninterruptible() to _idle() [ Upstream commit e60c122a1614b4f65b29a7bef9d83b9fd30e937a ] The rcuscale.holdoff module parameter can be used to delay the start of rcu_scale_writer() kthread. However, the hung-task timeout will trigger when the timeout specified by rcuscale.holdoff is greater than hung_task_timeout_secs: runqemu kvm nographic slirp qemuparams="-smp 4 -m 2048M" bootparams="rcuscale.shutdown=0 rcuscale.holdoff=300" [ 247.071753] INFO: task rcu_scale_write:59 blocked for more than 122 seconds. [ 247.072529] Not tainted 6.4.0-rc1-00134-gb9ed6de8d4ff #7 [ 247.073400] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 247.074331] task:rcu_scale_write state:D stack:30144 pid:59 ppid:2 flags:0x00004000 [ 247.075346] Call Trace: [ 247.075660] [ 247.075965] __schedule+0x635/0x1280 [ 247.076448] ? __pfx___schedule+0x10/0x10 [ 247.076967] ? schedule_timeout+0x2dc/0x4d0 [ 247.077471] ? __pfx_lock_release+0x10/0x10 [ 247.078018] ? enqueue_timer+0xe2/0x220 [ 247.078522] schedule+0x84/0x120 [ 247.078957] schedule_timeout+0x2e1/0x4d0 [ 247.079447] ? __pfx_schedule_timeout+0x10/0x10 [ 247.080032] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.080591] ? __pfx_process_timeout+0x10/0x10 [ 247.081163] ? __pfx_sched_set_fifo_low+0x10/0x10 [ 247.081760] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.082287] rcu_scale_writer+0x6b1/0x7f0 [ 247.082773] ? mark_held_locks+0x29/0xa0 [ 247.083252] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.083865] ? __pfx_rcu_scale_writer+0x10/0x10 [ 247.084412] kthread+0x179/0x1c0 [ 247.084759] ? __pfx_kthread+0x10/0x10 [ 247.085098] ret_from_fork+0x2c/0x50 [ 247.085433] This commit therefore replaces schedule_timeout_uninterruptible() with schedule_timeout_idle(). Signed-off-by: Zqiang Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/rcu/rcuscale.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 7854dc3226e1..0b88d96511ad 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -423,7 +423,7 @@ rcu_scale_writer(void *arg) sched_set_fifo_low(current); if (holdoff) - schedule_timeout_uninterruptible(holdoff * HZ); + schedule_timeout_idle(holdoff * HZ); /* * Wait until rcu_end_inkernel_boot() is called for normal GP tests From 9f10b4eb1b218223e0e7c8b013ac7d9f621e890c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 15 May 2023 19:00:10 -0700 Subject: [PATCH 1506/2093] scftorture: Forgive memory-allocation failure if KASAN [ Upstream commit 013608cd0812bdb21fc26d39ed8fdd2fc76e8b9b ] Kernels built with CONFIG_KASAN=y quarantine newly freed memory in order to better detect use-after-free errors. However, this can exhaust memory more quickly in allocator-heavy tests, which can result in spurious scftorture failure. This commit therefore forgives memory-allocation failure in kernels built with CONFIG_KASAN=y, but continues counting the errors for use in detailed test-result analyses. Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/scftorture.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/scftorture.c b/kernel/scftorture.c index 5d113aa59e77..83c33ba0ca7e 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -171,7 +171,8 @@ static void scf_torture_stats_print(void) scfs.n_all_wait += scf_stats_p[i].n_all_wait; } if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) || - atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs)) + atomic_read(&n_mb_out_errs) || + (!IS_ENABLED(CONFIG_KASAN) && atomic_read(&n_alloc_errs))) bangstr = "!!! "; pr_alert("%s %sscf_invoked_count %s: %lld resched: %lld single: %lld/%lld single_ofl: %lld/%lld single_rpc: %lld single_rpc_ofl: %lld many: %lld/%lld all: %lld/%lld ", SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count, scfs.n_resched, @@ -323,7 +324,8 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra preempt_disable(); if (scfsp->scfs_prim == SCF_PRIM_SINGLE || scfsp->scfs_wait) { scfcp = kmalloc(sizeof(*scfcp), GFP_ATOMIC); - if (WARN_ON_ONCE(!scfcp)) { + if (!scfcp) { + WARN_ON_ONCE(!IS_ENABLED(CONFIG_KASAN)); atomic_inc(&n_alloc_errs); } else { scfcp->scfc_cpu = -1; From 4cb0612cf260385273f7588bf864356e2a417983 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Tue, 18 Apr 2023 08:42:00 +0200 Subject: [PATCH 1507/2093] ACPI: video: Add backlight=native DMI quirk for Lenovo Ideapad Z470 [ Upstream commit 96b709be183c56293933ef45b8b75f8af268c6de ] The Lenovo Ideapad Z470 predates Windows 8, so it defaults to using acpi_video for backlight control. But this is not functional on this model. Add a DMI quirk to use the native backlight interface which works. Link: https://bugzilla.suse.com/show_bug.cgi?id=1208724 Signed-off-by: Jiri Slaby (SUSE) Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/video_detect.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 707d6811615b..073d26ddb6c2 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -443,6 +443,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "Lenovo IdeaPad S405"), }, }, + { + /* https://bugzilla.suse.com/show_bug.cgi?id=1208724 */ + .callback = video_detect_force_native, + /* Lenovo Ideapad Z470 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Z470"), + }, + }, { /* https://bugzilla.redhat.com/show_bug.cgi?id=1187004 */ .callback = video_detect_force_native, From 9d9b5cbc12f49fbdbbc454383981039005af8211 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Mon, 14 Aug 2023 20:40:12 +0800 Subject: [PATCH 1508/2093] perf/smmuv3: Enable HiSilicon Erratum 162001900 quirk for HIP08/09 [ Upstream commit 0242737dc4eb9f6e9a5ea594b3f93efa0b12f28d ] Some HiSilicon SMMU PMCG suffers the erratum 162001900 that the PMU disable control sometimes fail to disable the counters. This will lead to error or inaccurate data since before we enable the counters the counter's still counting for the event used in last perf session. This patch tries to fix this by hardening the global disable process. Before disable the PMU, writing an invalid event type (0xffff) to focibly stop the counters. Correspondingly restore each events on pmu::pmu_enable(). Signed-off-by: Yicong Yang Link: https://lore.kernel.org/r/20230814124012.58013-1-yangyicong@huawei.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- Documentation/arm64/silicon-errata.rst | 3 ++ drivers/acpi/arm64/iort.c | 5 ++- drivers/perf/arm_smmuv3_pmu.c | 46 +++++++++++++++++++++++++- include/linux/acpi_iort.h | 1 + 4 files changed, 53 insertions(+), 2 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index b3c8ac6a2c38..9000640f7f7a 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -193,6 +193,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | Hip08 SMMU PMCG | #162001800 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +| Hisilicon | Hip08 SMMU PMCG | #162001900 | N/A | +| | Hip09 SMMU PMCG | | | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 2e1cae53536f..3a6cf5675e60 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1699,7 +1699,10 @@ static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res, static struct acpi_platform_list pmcg_plat_info[] __initdata = { /* HiSilicon Hip08 Platform */ {"HISI ", "HIP08 ", 0, ACPI_SIG_IORT, greater_than_or_equal, - "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08}, + "Erratum #162001800, Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP08}, + /* HiSilicon Hip09 Platform */ + {"HISI ", "HIP09 ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, { } }; diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index 25a269d431e4..0e17c57ddb87 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -115,6 +115,7 @@ #define SMMU_PMCG_PA_SHIFT 12 #define SMMU_PMCG_EVCNTR_RDONLY BIT(0) +#define SMMU_PMCG_HARDEN_DISABLE BIT(1) static int cpuhp_state_num; @@ -159,6 +160,20 @@ static inline void smmu_pmu_enable(struct pmu *pmu) writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR); } +static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu, + struct perf_event *event, int idx); + +static inline void smmu_pmu_enable_quirk_hip08_09(struct pmu *pmu) +{ + struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu); + unsigned int idx; + + for_each_set_bit(idx, smmu_pmu->used_counters, smmu_pmu->num_counters) + smmu_pmu_apply_event_filter(smmu_pmu, smmu_pmu->events[idx], idx); + + smmu_pmu_enable(pmu); +} + static inline void smmu_pmu_disable(struct pmu *pmu) { struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu); @@ -167,6 +182,22 @@ static inline void smmu_pmu_disable(struct pmu *pmu) writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL); } +static inline void smmu_pmu_disable_quirk_hip08_09(struct pmu *pmu) +{ + struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu); + unsigned int idx; + + /* + * The global disable of PMU sometimes fail to stop the counting. + * Harden this by writing an invalid event type to each used counter + * to forcibly stop counting. + */ + for_each_set_bit(idx, smmu_pmu->used_counters, smmu_pmu->num_counters) + writel(0xffff, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx)); + + smmu_pmu_disable(pmu); +} + static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu, u32 idx, u64 value) { @@ -765,7 +796,10 @@ static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu) switch (model) { case IORT_SMMU_V3_PMCG_HISI_HIP08: /* HiSilicon Erratum 162001800 */ - smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY; + smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY | SMMU_PMCG_HARDEN_DISABLE; + break; + case IORT_SMMU_V3_PMCG_HISI_HIP09: + smmu_pmu->options |= SMMU_PMCG_HARDEN_DISABLE; break; } @@ -890,6 +924,16 @@ static int smmu_pmu_probe(struct platform_device *pdev) if (!dev->of_node) smmu_pmu_get_acpi_options(smmu_pmu); + /* + * For platforms suffer this quirk, the PMU disable sometimes fails to + * stop the counters. This will leads to inaccurate or error counting. + * Forcibly disable the counters with these quirk handler. + */ + if (smmu_pmu->options & SMMU_PMCG_HARDEN_DISABLE) { + smmu_pmu->pmu.pmu_enable = smmu_pmu_enable_quirk_hip08_09; + smmu_pmu->pmu.pmu_disable = smmu_pmu_disable_quirk_hip08_09; + } + /* Pick one CPU to be the preferred one to use */ smmu_pmu->on_cpu = raw_smp_processor_id(); WARN_ON(irq_set_affinity(smmu_pmu->irq, cpumask_of(smmu_pmu->on_cpu))); diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index b43be0987b19..a2a51fafa355 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -21,6 +21,7 @@ */ #define IORT_SMMU_V3_PMCG_GENERIC 0x00000000 /* Generic SMMUv3 PMCG */ #define IORT_SMMU_V3_PMCG_HISI_HIP08 0x00000001 /* HiSilicon HIP08 PMCG */ +#define IORT_SMMU_V3_PMCG_HISI_HIP09 0x00000002 /* HiSilicon HIP09 PMCG */ int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); From d42d342d313206ef0d08d72311b5d86c72a1756e Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Fri, 11 Aug 2023 09:54:37 +0800 Subject: [PATCH 1509/2093] perf/imx_ddr: speed up overflow frequency of cycle [ Upstream commit e89ecd8368860bf05437eabd07d292c316221cfc ] For i.MX8MP, we cannot ensure that cycle counter overflow occurs at least 4 times as often as other events. Due to byte counters will count for any event configured, it will overflow more often. And if byte counters overflow that related counters would stop since they share the COUNTER_CNTL. We can speed up cycle counter overflow frequency by setting counter parameter (CP) field of cycle counter. In this way, we can avoid stop counting byte counters when interrupt didn't come and the byte counters can be fetched or updated from each cycle counter overflow interrupt. Because we initialize CP filed to shorten counter0 overflow time, the cycle counter will start couting from a fixed/base value each time. We need to remove the base from the result too. Therefore, we could get precise result from cycle counter. Signed-off-by: Xu Yang Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20230811015438.1999307-1-xu.yang_2@nxp.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/perf/fsl_imx8_ddr_perf.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index cd4ce2b4906d..a4cda73b81c9 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -28,6 +28,8 @@ #define CNTL_CLEAR_MASK 0xFFFFFFFD #define CNTL_OVER_MASK 0xFFFFFFFE +#define CNTL_CP_SHIFT 16 +#define CNTL_CP_MASK (0xFF << CNTL_CP_SHIFT) #define CNTL_CSV_SHIFT 24 #define CNTL_CSV_MASK (0xFFU << CNTL_CSV_SHIFT) @@ -35,6 +37,8 @@ #define EVENT_CYCLES_COUNTER 0 #define NUM_COUNTERS 4 +/* For removing bias if cycle counter CNTL.CP is set to 0xf0 */ +#define CYCLES_COUNTER_MASK 0x0FFFFFFF #define AXI_MASKING_REVERT 0xffff0000 /* AXI_MASKING(MSB 16bits) + AXI_ID(LSB 16bits) */ #define to_ddr_pmu(p) container_of(p, struct ddr_pmu, pmu) @@ -429,6 +433,17 @@ static void ddr_perf_counter_enable(struct ddr_pmu *pmu, int config, writel(0, pmu->base + reg); val = CNTL_EN | CNTL_CLEAR; val |= FIELD_PREP(CNTL_CSV_MASK, config); + + /* + * On i.MX8MP we need to bias the cycle counter to overflow more often. + * We do this by initializing bits [23:16] of the counter value via the + * COUNTER_CTRL Counter Parameter (CP) field. + */ + if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED) { + if (counter == EVENT_CYCLES_COUNTER) + val |= FIELD_PREP(CNTL_CP_MASK, 0xf0); + } + writel(val, pmu->base + reg); } else { /* Disable counter */ @@ -468,6 +483,12 @@ static void ddr_perf_event_update(struct perf_event *event) int ret; new_raw_count = ddr_perf_read_counter(pmu, counter); + /* Remove the bias applied in ddr_perf_counter_enable(). */ + if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED) { + if (counter == EVENT_CYCLES_COUNTER) + new_raw_count &= CYCLES_COUNTER_MASK; + } + local64_add(new_raw_count, &event->count); /* From dc1d81ee9312dee73544ec88d356e644edd5c413 Mon Sep 17 00:00:00 2001 From: Tomislav Novak Date: Mon, 5 Jun 2023 12:19:23 -0700 Subject: [PATCH 1510/2093] hw_breakpoint: fix single-stepping when using bpf_overflow_handler [ Upstream commit d11a69873d9a7435fe6a48531e165ab80a8b1221 ] Arm platforms use is_default_overflow_handler() to determine if the hw_breakpoint code should single-step over the breakpoint trigger or let the custom handler deal with it. Since bpf_overflow_handler() currently isn't recognized as a default handler, attaching a BPF program to a PERF_TYPE_BREAKPOINT event causes it to keep firing (the instruction triggering the data abort exception is never skipped). For example: # bpftrace -e 'watchpoint:0x10000:4:w { print("hit") }' -c ./test Attaching 1 probe... hit hit [...] ^C (./test performs a single 4-byte store to 0x10000) This patch replaces the check with uses_default_overflow_handler(), which accounts for the bpf_overflow_handler() case by also testing if one of the perf_event_output functions gets invoked indirectly, via orig_default_handler. Signed-off-by: Tomislav Novak Tested-by: Samuel Gosselin # arm64 Reviewed-by: Catalin Marinas Acked-by: Alexei Starovoitov Link: https://lore.kernel.org/linux-arm-kernel/20220923203644.2731604-1-tnovak@fb.com/ Link: https://lore.kernel.org/r/20230605191923.1219974-1-tnovak@meta.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm/kernel/hw_breakpoint.c | 8 ++++---- arch/arm64/kernel/hw_breakpoint.c | 4 ++-- include/linux/perf_event.h | 22 +++++++++++++++++++--- 3 files changed, 25 insertions(+), 9 deletions(-) diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 054e9199f30d..dc0fb7a81371 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -626,7 +626,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, hw->address &= ~alignment_mask; hw->ctrl.len <<= offset; - if (is_default_overflow_handler(bp)) { + if (uses_default_overflow_handler(bp)) { /* * Mismatch breakpoints are required for single-stepping * breakpoints. @@ -798,7 +798,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, * Otherwise, insert a temporary mismatch breakpoint so that * we can single-step over the watchpoint trigger. */ - if (!is_default_overflow_handler(wp)) + if (!uses_default_overflow_handler(wp)) continue; step: enable_single_step(wp, instruction_pointer(regs)); @@ -811,7 +811,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, info->trigger = addr; pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); perf_bp_event(wp, regs); - if (is_default_overflow_handler(wp)) + if (uses_default_overflow_handler(wp)) enable_single_step(wp, instruction_pointer(regs)); } @@ -886,7 +886,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) info->trigger = addr; pr_debug("breakpoint fired: address = 0x%x\n", addr); perf_bp_event(bp, regs); - if (is_default_overflow_handler(bp)) + if (uses_default_overflow_handler(bp)) enable_single_step(bp, addr); goto unlock; } diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index b29a311bb055..9659a9555c63 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -654,7 +654,7 @@ static int breakpoint_handler(unsigned long unused, unsigned long esr, perf_bp_event(bp, regs); /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(bp)) + if (uses_default_overflow_handler(bp)) step = 1; unlock: rcu_read_unlock(); @@ -733,7 +733,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, static int watchpoint_report(struct perf_event *wp, unsigned long addr, struct pt_regs *regs) { - int step = is_default_overflow_handler(wp); + int step = uses_default_overflow_handler(wp); struct arch_hw_breakpoint *info = counter_arch_bp(wp); info->trigger = addr; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0031f7b4d9ab..63fae3c7ae43 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1139,15 +1139,31 @@ extern int perf_event_output(struct perf_event *event, struct pt_regs *regs); static inline bool -is_default_overflow_handler(struct perf_event *event) +__is_default_overflow_handler(perf_overflow_handler_t overflow_handler) { - if (likely(event->overflow_handler == perf_event_output_forward)) + if (likely(overflow_handler == perf_event_output_forward)) return true; - if (unlikely(event->overflow_handler == perf_event_output_backward)) + if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } +#define is_default_overflow_handler(event) \ + __is_default_overflow_handler((event)->overflow_handler) + +#ifdef CONFIG_BPF_SYSCALL +static inline bool uses_default_overflow_handler(struct perf_event *event) +{ + if (likely(is_default_overflow_handler(event))) + return true; + + return __is_default_overflow_handler(event->orig_overflow_handler); +} +#else +#define uses_default_overflow_handler(event) \ + is_default_overflow_handler(event) +#endif + extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, From 1ea7e47807279369c82718efd2677ea25c6579e3 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 18 Aug 2023 14:40:03 -0500 Subject: [PATCH 1511/2093] ACPI: x86: s2idle: Catch multiple ACPI_TYPE_PACKAGE objects [ Upstream commit 883cf0d4cf288313b71146ddebdf5d647b76c78b ] If a badly constructed firmware includes multiple `ACPI_TYPE_PACKAGE` objects while evaluating the AMD LPS0 _DSM, there will be a memory leak. Explicitly guard against this. Suggested-by: Bjorn Helgaas Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/x86/s2idle.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index ec84da6cc1bf..5510657d4be8 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -112,6 +112,12 @@ static void lpi_device_get_constraints_amd(void) union acpi_object *package = &out_obj->package.elements[i]; if (package->type == ACPI_TYPE_PACKAGE) { + if (lpi_constraints_table) { + acpi_handle_err(lps0_device_handle, + "Duplicate constraints list\n"); + goto free_acpi_buffer; + } + lpi_constraints_table = kcalloc(package->package.count, sizeof(*lpi_constraints_table), GFP_KERNEL); From a0300edca5df23b7b7913ff857c5a159000834da Mon Sep 17 00:00:00 2001 From: Zhangjin Wu Date: Sat, 8 Jul 2023 02:32:05 +0800 Subject: [PATCH 1512/2093] selftests/nolibc: fix up kernel parameters support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c388c9920da2679f62bec48d00ca9e80e9d0a364 ] kernel parameters allow pass two types of strings, one type is like 'noapic', another type is like 'panic=5', the first type is passed as arguments of the init program, the second type is passed as environment variables of the init program. when users pass kernel parameters like this: noapic NOLIBC_TEST=syscall our nolibc-test program will use the test setting from argv[1] and ignore the one from NOLIBC_TEST environment variable, and at last, it will print the following line and ignore the whole test setting. Ignoring unknown test name 'noapic' reversing the parsing order does solve the above issue: test = getenv("NOLIBC_TEST"); if (test) test = argv[1]; but it still doesn't work with such kernel parameters (without NOLIBC_TEST environment variable): noapic FOO=bar To support all of the potential kernel parameters, let's verify the test setting from both of argv[1] and NOLIBC_TEST environment variable. Reviewed-by: Thomas Weißschuh Signed-off-by: Zhangjin Wu Signed-off-by: Willy Tarreau Signed-off-by: Sasha Levin --- tools/testing/selftests/nolibc/nolibc-test.c | 33 ++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 78bced95ac63..f8e8e8d2a5e1 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -630,6 +630,35 @@ static struct test test_names[] = { { 0 } }; +int is_setting_valid(char *test) +{ + int idx, len, test_len, valid = 0; + char delimiter; + + if (!test) + return valid; + + test_len = strlen(test); + + for (idx = 0; test_names[idx].name; idx++) { + len = strlen(test_names[idx].name); + if (test_len < len) + continue; + + if (strncmp(test, test_names[idx].name, len) != 0) + continue; + + delimiter = test[len]; + if (delimiter != ':' && delimiter != ',' && delimiter != '\0') + continue; + + valid = 1; + break; + } + + return valid; +} + int main(int argc, char **argv, char **envp) { int min = 0; @@ -655,10 +684,10 @@ int main(int argc, char **argv, char **envp) * syscall:5-15[:.*],stdlib:8-10 */ test = argv[1]; - if (!test) + if (!is_setting_valid(test)) test = getenv("NOLIBC_TEST"); - if (test) { + if (is_setting_valid(test)) { char *comma, *colon, *dash, *value; do { From ac70101e5b94912c413e2e4d2e7e9d30ad38ea36 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 13 Jul 2023 11:44:19 +0200 Subject: [PATCH 1513/2093] devlink: remove reload failed checks in params get/set callbacks [ Upstream commit 633d76ad01ad0321a1ace3e5cc4fed06753d7ac4 ] The checks in question were introduced by: commit 6b4db2e528f6 ("devlink: Fix use-after-free after a failed reload"). That fixed an issue of reload with mlxsw driver. Back then, that was a valid fix, because there was a limitation in place that prevented drivers from registering/unregistering params when devlink instance was registered. It was possible to do the fix differently by changing drivers to register/unregister params in appropriate places making sure the ops operate only on memory which is allocated and initialized. But that, as a dependency, would require to remove the limitation mentioned above. Eventually, this limitation was lifted by: commit 1d18bb1a4ddd ("devlink: allow registering parameters after the instance") Also, the alternative fix (which also fixed another issue) was done by: commit 74cbc3c03c82 ("mlxsw: spectrum_acl_tcam: Move devlink param to TCAM code"). Therefore, the checks are no longer relevant. Each driver should make sure to have the params registered only when the memory the ops are working with is allocated and initialized. So remove the checks. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/devlink/leftover.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index 63188d6a50fe..032c7af065cd 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -5218,7 +5218,7 @@ static int devlink_param_get(struct devlink *devlink, const struct devlink_param *param, struct devlink_param_gset_ctx *ctx) { - if (!param->get || devlink->reload_failed) + if (!param->get) return -EOPNOTSUPP; return param->get(devlink, param->id, ctx); } @@ -5227,7 +5227,7 @@ static int devlink_param_set(struct devlink *devlink, const struct devlink_param *param, struct devlink_param_gset_ctx *ctx) { - if (!param->set || devlink->reload_failed) + if (!param->set) return -EOPNOTSUPP; return param->set(devlink, param->id, ctx); } From ad58d7ebbf936c3e9730cc3164af9753b276851c Mon Sep 17 00:00:00 2001 From: Azeem Shaikh Date: Tue, 20 Jun 2023 20:08:32 +0000 Subject: [PATCH 1514/2093] crypto: lrw,xts - Replace strlcpy with strscpy [ Upstream commit babb80b3ecc6f40c962e13c654ebcd27f25ee327 ] strlcpy() reads the entire source buffer first. This read may exceed the destination size limit. This is both inefficient and can lead to linear read overflows if a source string is not NUL-terminated [1]. In an effort to remove strlcpy() completely [2], replace strlcpy() here with strscpy(). Direct replacement is safe here since return value of -errno is used to check for truncation instead of sizeof(dest). [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [2] https://github.com/KSPP/linux/issues/89 Signed-off-by: Azeem Shaikh Reviewed-by: Kees Cook Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/lrw.c | 6 +++--- crypto/xts.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/crypto/lrw.c b/crypto/lrw.c index 8d59a66b6525..fb8892ed179f 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -357,10 +357,10 @@ static int lrw_create(struct crypto_template *tmpl, struct rtattr **tb) * cipher name. */ if (!strncmp(cipher_name, "ecb(", 4)) { - unsigned len; + int len; - len = strlcpy(ecb_name, cipher_name + 4, sizeof(ecb_name)); - if (len < 2 || len >= sizeof(ecb_name)) + len = strscpy(ecb_name, cipher_name + 4, sizeof(ecb_name)); + if (len < 2) goto err_free_inst; if (ecb_name[len - 1] != ')') diff --git a/crypto/xts.c b/crypto/xts.c index de6cbcf69bbd..b05020657cdc 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -396,10 +396,10 @@ static int xts_create(struct crypto_template *tmpl, struct rtattr **tb) * cipher name. */ if (!strncmp(cipher_name, "ecb(", 4)) { - unsigned len; + int len; - len = strlcpy(ctx->name, cipher_name + 4, sizeof(ctx->name)); - if (len < 2 || len >= sizeof(ctx->name)) + len = strscpy(ctx->name, cipher_name + 4, sizeof(ctx->name)); + if (len < 2) goto err_free_inst; if (ctx->name[len - 1] != ')') From 5760a72b3060150b587eff3e879648c7470efddd Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Wed, 12 Jul 2023 13:03:28 +0200 Subject: [PATCH 1515/2093] ice: Don't tx before switchdev is fully configured [ Upstream commit 7aa529a69e92b9aff585e569d5003f7c15d8d60b ] There is possibility that ice_eswitch_port_start_xmit might be called while some resources are still not allocated which might cause NULL pointer dereference. Fix this by checking if switchdev configuration was finished. Reviewed-by: Paul Menzel Reviewed-by: Simon Horman Signed-off-by: Wojciech Drewek Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_eswitch.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 2ffe5708a045..7de4a8a4b563 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -361,6 +361,9 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; + if (!vsi || !ice_is_switchdev_running(vsi->back)) + return NETDEV_TX_BUSY; + if (ice_is_reset_in_progress(vsi->back->state) || test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; From 1800a27a3dba3be8ce058069bf89b888577adecf Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Mon, 24 Jul 2023 13:11:07 +0300 Subject: [PATCH 1516/2093] wifi: ath9k: fix fortify warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 810e41cebb6c6e394f2068f839e1a3fc745a5dcc ] When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y, I've noticed the following: In function ‘fortify_memcpy_chk’, inlined from ‘ath_tx_complete_aggr’ at drivers/net/wireless/ath/ath9k/xmit.c:556:4, inlined from ‘ath_tx_process_buffer’ at drivers/net/wireless/ath/ath9k/xmit.c:773:3: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function ‘fortify_memcpy_chk’, inlined from ‘ath_tx_count_frames’ at drivers/net/wireless/ath/ath9k/xmit.c:473:3, inlined from ‘ath_tx_complete_aggr’ at drivers/net/wireless/ath/ath9k/xmit.c:572:2, inlined from ‘ath_tx_process_buffer’ at drivers/net/wireless/ath/ath9k/xmit.c:773:3: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In both cases, the compiler complains on: memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3); which is the legal way to copy both 'ba_low' and following 'ba_high' members of 'struct ath_tx_status' at once (that is, issue one 8-byte 'memcpy()' for two 4-byte fields). Since the fortification logic seems interprets this trick as an attempt to overread 4-byte 'ba_low', silence relevant warnings by using the convenient 'struct_group()' quirk. Suggested-by: Johannes Berg Signed-off-by: Dmitry Antipov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230620080855.396851-2-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/mac.h | 6 ++++-- drivers/net/wireless/ath/ath9k/xmit.c | 4 ++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h index af44b33814dd..f03d792732da 100644 --- a/drivers/net/wireless/ath/ath9k/mac.h +++ b/drivers/net/wireless/ath/ath9k/mac.h @@ -115,8 +115,10 @@ struct ath_tx_status { u8 qid; u16 desc_id; u8 tid; - u32 ba_low; - u32 ba_high; + struct_group(ba, + u32 ba_low; + u32 ba_high; + ); u32 evm0; u32 evm1; u32 evm2; diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index ba271a10d4ab..eeabdd67fbcc 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -462,7 +462,7 @@ static void ath_tx_count_frames(struct ath_softc *sc, struct ath_buf *bf, isaggr = bf_isaggr(bf); if (isaggr) { seq_st = ts->ts_seqnum; - memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3); + memcpy(ba, &ts->ba, WME_BA_BMP_SIZE >> 3); } while (bf) { @@ -545,7 +545,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, if (isaggr && txok) { if (ts->ts_flags & ATH9K_TX_BA) { seq_st = ts->ts_seqnum; - memcpy(ba, &ts->ba_low, WME_BA_BMP_SIZE >> 3); + memcpy(ba, &ts->ba, WME_BA_BMP_SIZE >> 3); } else { /* * AR5416 can become deaf/mute when BA From 2640a8e54f84259bc4e952ff6c59b9faf4e6219a Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Sun, 23 Jul 2023 12:04:02 +0800 Subject: [PATCH 1517/2093] wifi: ath9k: fix printk specifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 061115fbfb2ce5870c9a004d68dc63138c07c782 ] Smatch reports: ath_pci_probe() warn: argument 4 to %lx specifier is cast from pointer ath_ahb_probe() warn: argument 4 to %lx specifier is cast from pointer Fix it by modifying %lx to %p in the printk format string. Note that with this change, the pointer address will be printed as a hashed value by default. This is appropriate because the kernel should not leak kernel pointers to user space in an informational message. If someone wants to see the real address for debugging purposes, this can be achieved with the no_hash_pointers kernel option. Signed-off-by: Dongliang Mu Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230723040403.296723-1-dzm91@hust.edu.cn Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/ahb.c | 4 ++-- drivers/net/wireless/ath/ath9k/pci.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/ahb.c b/drivers/net/wireless/ath/ath9k/ahb.c index 9cd12b20b18d..9bfaadfa6c00 100644 --- a/drivers/net/wireless/ath/ath9k/ahb.c +++ b/drivers/net/wireless/ath/ath9k/ahb.c @@ -132,8 +132,8 @@ static int ath_ahb_probe(struct platform_device *pdev) ah = sc->sc_ah; ath9k_hw_name(ah, hw_name, sizeof(hw_name)); - wiphy_info(hw->wiphy, "%s mem=0x%lx, irq=%d\n", - hw_name, (unsigned long)mem, irq); + wiphy_info(hw->wiphy, "%s mem=0x%p, irq=%d\n", + hw_name, mem, irq); return 0; diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c index a074e23013c5..f0e3901e8182 100644 --- a/drivers/net/wireless/ath/ath9k/pci.c +++ b/drivers/net/wireless/ath/ath9k/pci.c @@ -988,8 +988,8 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) sc->sc_ah->msi_reg = 0; ath9k_hw_name(sc->sc_ah, hw_name, sizeof(hw_name)); - wiphy_info(hw->wiphy, "%s mem=0x%lx, irq=%d\n", - hw_name, (unsigned long)sc->mem, pdev->irq); + wiphy_info(hw->wiphy, "%s mem=0x%p, irq=%d\n", + hw_name, sc->mem, pdev->irq); return 0; From 4f621fe1acac5aaf7059761f2984e8b5357d6a33 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Thu, 29 Jun 2023 11:51:01 +0300 Subject: [PATCH 1518/2093] wifi: mwifiex: fix fortify warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dcce94b80a954a8968ff29fafcfb066d6197fa9a ] When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y, I've noticed the following: In function ‘fortify_memcpy_chk’, inlined from ‘mwifiex_construct_tdls_action_frame’ at drivers/net/wireless/marvell/mwifiex/tdls.c:765:3, inlined from ‘mwifiex_send_tdls_action_frame’ at drivers/net/wireless/marvell/mwifiex/tdls.c:856:6: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The compiler actually complains on: memmove(pos + ETH_ALEN, &mgmt->u.action.category, sizeof(mgmt->u.action.u.tdls_discover_resp)); and it happens because the fortification logic interprets this as an attempt to overread 1-byte 'u.action.category' member of 'struct ieee80211_mgmt'. To silence this warning, it's enough to pass an address of 'u.action' itself instead of an address of its first member. This also fixes an improper usage of 'sizeof()'. Since 'skb' is extended with 'sizeof(mgmt->u.action.u.tdls_discover_resp) + 1' bytes (where 1 is actually 'sizeof(mgmt->u.action.category)'), I assume that the same number of bytes should be copied. Suggested-by: Brian Norris Signed-off-by: Dmitry Antipov Reviewed-by: Brian Norris Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230629085115.180499-2-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/tdls.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index 97bb87c3676b..6c60621b6ccc 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -735,6 +735,7 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, int ret; u16 capab; struct ieee80211_ht_cap *ht_cap; + unsigned int extra; u8 radio, *pos; capab = priv->curr_bss_params.bss_descriptor.cap_info_bitmap; @@ -753,7 +754,10 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, switch (action_code) { case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: - skb_put(skb, sizeof(mgmt->u.action.u.tdls_discover_resp) + 1); + /* See the layout of 'struct ieee80211_mgmt'. */ + extra = sizeof(mgmt->u.action.u.tdls_discover_resp) + + sizeof(mgmt->u.action.category); + skb_put(skb, extra); mgmt->u.action.category = WLAN_CATEGORY_PUBLIC; mgmt->u.action.u.tdls_discover_resp.action_code = WLAN_PUB_ACTION_TDLS_DISCOVER_RES; @@ -762,8 +766,7 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, mgmt->u.action.u.tdls_discover_resp.capability = cpu_to_le16(capab); /* move back for addr4 */ - memmove(pos + ETH_ALEN, &mgmt->u.action.category, - sizeof(mgmt->u.action.u.tdls_discover_resp)); + memmove(pos + ETH_ALEN, &mgmt->u.action, extra); /* init address 4 */ eth_broadcast_addr(pos); From 5c8bbb79c7cbca65534badf360f3b1145759c7bc Mon Sep 17 00:00:00 2001 From: Matt Whitlock Date: Thu, 20 Apr 2023 15:24:51 -0400 Subject: [PATCH 1519/2093] mt76: mt7921: don't assume adequate headroom for SDIO headers [ Upstream commit 98c4d0abf5c478db1ad126ff0c187dbb84c0803c ] mt7921_usb_sdio_tx_prepare_skb() calls mt7921_usb_sdio_write_txwi() and mt7921_skb_add_usb_sdio_hdr(), both of which blindly assume that adequate headroom will be available in the passed skb. This assumption typically is satisfied when the skb was allocated in the net core for transmission via the mt7921 netdev (although even that is only an optimization and is not strictly guaranteed), but the assumption is sometimes not satisfied when the skb originated in the receive path of another netdev and was passed through to the mt7921, such as by the bridge layer. Blindly prepending bytes to an skb is always wrong. This commit introduces a call to skb_cow_head() before the call to mt7921_usb_sdio_write_txwi() in mt7921_usb_sdio_tx_prepare_skb() to ensure that at least MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE bytes can be pushed onto the skb. Without this fix, I can trivially cause kernel panics by bridging an MT7921AU-based USB 802.11ax interface with an Ethernet interface on an Intel Atom-based x86 system using its onboard RTL8169 PCI Ethernet adapter and also on an ARM-based Raspberry Pi 1 using its onboard SMSC9512 USB Ethernet adapter. Note that the panics do not occur in every system configuration, as they occur only if the receiving netdev leaves less headroom in its received skbs than the mt7921 needs for its SDIO headers. Here is an example stack trace of this panic on Raspberry Pi OS Lite 2023-02-21 running kernel 6.1.24+ [1]: skb_panic from skb_push+0x44/0x48 skb_push from mt7921_usb_sdio_tx_prepare_skb+0xd4/0x190 [mt7921_common] mt7921_usb_sdio_tx_prepare_skb [mt7921_common] from mt76u_tx_queue_skb+0x94/0x1d0 [mt76_usb] mt76u_tx_queue_skb [mt76_usb] from __mt76_tx_queue_skb+0x4c/0xc8 [mt76] __mt76_tx_queue_skb [mt76] from mt76_txq_schedule.part.0+0x13c/0x398 [mt76] mt76_txq_schedule.part.0 [mt76] from mt76_txq_schedule_all+0x24/0x30 [mt76] mt76_txq_schedule_all [mt76] from mt7921_tx_worker+0x58/0xf4 [mt7921_common] mt7921_tx_worker [mt7921_common] from __mt76_worker_fn+0x9c/0xec [mt76] __mt76_worker_fn [mt76] from kthread+0xbc/0xe0 kthread from ret_from_fork+0x14/0x34 After this fix, bridging the mt7921 interface works fine on both of my previously problematic systems. [1] https://github.com/raspberrypi/firmware/tree/5c276f55a4b21345cd4d6200a504ee991851ff7a Link: https://github.com/openwrt/openwrt/issues/11796 Signed-off-by: Matt Whitlock Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7921/mac.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 1c0d8cf19b8e..49ddca84f786 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -1167,6 +1167,10 @@ int mt7921_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (unlikely(tx_info->skb->len <= ETH_HLEN)) return -EINVAL; + err = skb_cow_head(skb, MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE); + if (err) + return err; + if (!wcid) wcid = &dev->mt76.global_wcid; From f04b40cb70a599c6336f782a963fc8115ba57f48 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Wed, 21 Jun 2023 12:36:55 +0300 Subject: [PATCH 1520/2093] wifi: wil6210: fix fortify warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1ad8237e971630c66a1a6194491e0837b64d00e0 ] When compiling with gcc 13.1 and CONFIG_FORTIFY_SOURCE=y, I've noticed the following: In function ‘fortify_memcpy_chk’, inlined from ‘wil_rx_crypto_check_edma’ at drivers/net/wireless/ath/wil6210/txrx_edma.c:566:2: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ where the compiler complains on: const u8 *pn; ... pn = (u8 *)&st->ext.pn_15_0; ... memcpy(cc->pn, pn, IEEE80211_GCMP_PN_LEN); and: In function ‘fortify_memcpy_chk’, inlined from ‘wil_rx_crypto_check’ at drivers/net/wireless/ath/wil6210/txrx.c:684:2: ./include/linux/fortify-string.h:529:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 529 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ where the compiler complains on: const u8 *pn = (u8 *)&d->mac.pn_15_0; ... memcpy(cc->pn, pn, IEEE80211_GCMP_PN_LEN); In both cases, the fortification logic interprets 'memcpy()' as 6-byte overread of 2-byte field 'pn_15_0' of 'struct wil_rx_status_extension' and 'pn_15_0' of 'struct vring_rx_mac', respectively. To silence these warnings, last two fields of the aforementioned structures are grouped using 'struct_group_attr(pn, __packed' quirk. Signed-off-by: Dmitry Antipov Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230621093711.80118-1-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/wil6210/txrx.c | 2 +- drivers/net/wireless/ath/wil6210/txrx.h | 6 ++++-- drivers/net/wireless/ath/wil6210/txrx_edma.c | 2 +- drivers/net/wireless/ath/wil6210/txrx_edma.h | 6 ++++-- 4 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c index 237cbd5c5060..f29ac6de7139 100644 --- a/drivers/net/wireless/ath/wil6210/txrx.c +++ b/drivers/net/wireless/ath/wil6210/txrx.c @@ -666,7 +666,7 @@ static int wil_rx_crypto_check(struct wil6210_priv *wil, struct sk_buff *skb) struct wil_tid_crypto_rx *c = mc ? &s->group_crypto_rx : &s->tid_crypto_rx[tid]; struct wil_tid_crypto_rx_single *cc = &c->key_id[key_id]; - const u8 *pn = (u8 *)&d->mac.pn_15_0; + const u8 *pn = (u8 *)&d->mac.pn; if (!cc->key_set) { wil_err_ratelimited(wil, diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h index 1ae1bec1b97f..689f68d89a44 100644 --- a/drivers/net/wireless/ath/wil6210/txrx.h +++ b/drivers/net/wireless/ath/wil6210/txrx.h @@ -343,8 +343,10 @@ struct vring_rx_mac { u32 d0; u32 d1; u16 w4; - u16 pn_15_0; - u32 pn_47_16; + struct_group_attr(pn, __packed, + u16 pn_15_0; + u32 pn_47_16; + ); } __packed; /* Rx descriptor - DMA part diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c index 201c8c35e0c9..1ba1f21ebea2 100644 --- a/drivers/net/wireless/ath/wil6210/txrx_edma.c +++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c @@ -548,7 +548,7 @@ static int wil_rx_crypto_check_edma(struct wil6210_priv *wil, s = &wil->sta[cid]; c = mc ? &s->group_crypto_rx : &s->tid_crypto_rx[tid]; cc = &c->key_id[key_id]; - pn = (u8 *)&st->ext.pn_15_0; + pn = (u8 *)&st->ext.pn; if (!cc->key_set) { wil_err_ratelimited(wil, diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h index c736f7413a35..ee90e225bb05 100644 --- a/drivers/net/wireless/ath/wil6210/txrx_edma.h +++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h @@ -330,8 +330,10 @@ struct wil_rx_status_extension { u32 d0; u32 d1; __le16 seq_num; /* only lower 12 bits */ - u16 pn_15_0; - u32 pn_47_16; + struct_group_attr(pn, __packed, + u16 pn_15_0; + u32 pn_47_16; + ); } __packed; struct wil_rx_status_extended { From 4eb79abf910a8872eefc1fb612b65e7d97636b5d Mon Sep 17 00:00:00 2001 From: John Watts Date: Sat, 22 Jul 2023 08:15:52 +1000 Subject: [PATCH 1521/2093] can: sun4i_can: Add acceptance register quirk [ Upstream commit 8cda0c6dfd42ee6f2586e7dffb553aaf1fcb62ca ] The Allwinner D1's CAN controllers have the ACPC and ACPM registers moved down. Compensate for this by adding an offset quirk for the acceptance registers. Signed-off-by: John Watts Link: https://lore.kernel.org/all/20230721221552.1973203-5-contact@jookia.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/sun4i_can.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 2b78f9197681..dd0c6cd76c5f 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -205,9 +205,11 @@ * struct sun4ican_quirks - Differences between SoC variants. * * @has_reset: SoC needs reset deasserted. + * @acp_offset: Offset of ACPC and ACPM registers */ struct sun4ican_quirks { bool has_reset; + int acp_offset; }; struct sun4ican_priv { @@ -216,6 +218,7 @@ struct sun4ican_priv { struct clk *clk; struct reset_control *reset; spinlock_t cmdreg_lock; /* lock for concurrent cmd register writes */ + int acp_offset; }; static const struct can_bittiming_const sun4ican_bittiming_const = { @@ -338,8 +341,8 @@ static int sun4i_can_start(struct net_device *dev) } /* set filters - we accept all */ - writel(0x00000000, priv->base + SUN4I_REG_ACPC_ADDR); - writel(0xFFFFFFFF, priv->base + SUN4I_REG_ACPM_ADDR); + writel(0x00000000, priv->base + SUN4I_REG_ACPC_ADDR + priv->acp_offset); + writel(0xFFFFFFFF, priv->base + SUN4I_REG_ACPM_ADDR + priv->acp_offset); /* clear error counters and error code capture */ writel(0, priv->base + SUN4I_REG_ERRC_ADDR); @@ -768,10 +771,12 @@ static const struct ethtool_ops sun4ican_ethtool_ops = { static const struct sun4ican_quirks sun4ican_quirks_a10 = { .has_reset = false, + .acp_offset = 0, }; static const struct sun4ican_quirks sun4ican_quirks_r40 = { .has_reset = true, + .acp_offset = 0, }; static const struct of_device_id sun4ican_of_match[] = { @@ -872,6 +877,7 @@ static int sun4ican_probe(struct platform_device *pdev) priv->base = addr; priv->clk = clk; priv->reset = reset; + priv->acp_offset = quirks->acp_offset; spin_lock_init(&priv->cmdreg_lock); platform_set_drvdata(pdev, dev); From ab0ae0af0a2d2753ecda21e8b82ef10703d58c6c Mon Sep 17 00:00:00 2001 From: John Watts Date: Sat, 22 Jul 2023 08:15:53 +1000 Subject: [PATCH 1522/2093] can: sun4i_can: Add support for the Allwinner D1 [ Upstream commit 8abb95250ae6af2d51993da8fcae18da2ce24cc4 ] The controllers present in the D1 are extremely similar to the R40 and require the same reset quirks, but An extra quirk is needed to support receiving packets. Signed-off-by: John Watts Link: https://lore.kernel.org/all/20230721221552.1973203-6-contact@jookia.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/Kconfig | 4 ++-- drivers/net/can/sun4i_can.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 3048ad77edb3..8236aabebb39 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -174,10 +174,10 @@ config CAN_SLCAN config CAN_SUN4I tristate "Allwinner A10 CAN controller" - depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST + depends on MACH_SUN4I || MACH_SUN7I || RISCV || COMPILE_TEST help Say Y here if you want to use CAN controller found on Allwinner - A10/A20 SoCs. + A10/A20/D1 SoCs. To compile this driver as a module, choose M here: the module will be called sun4i_can. diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index dd0c6cd76c5f..c3a6b028ea4d 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -91,6 +91,8 @@ #define SUN4I_REG_BUF12_ADDR 0x0070 /* CAN Tx/Rx Buffer 12 */ #define SUN4I_REG_ACPC_ADDR 0x0040 /* CAN Acceptance Code 0 */ #define SUN4I_REG_ACPM_ADDR 0x0044 /* CAN Acceptance Mask 0 */ +#define SUN4I_REG_ACPC_ADDR_D1 0x0028 /* CAN Acceptance Code 0 on the D1 */ +#define SUN4I_REG_ACPM_ADDR_D1 0x002C /* CAN Acceptance Mask 0 on the D1 */ #define SUN4I_REG_RBUF_RBACK_START_ADDR 0x0180 /* CAN transmit buffer start */ #define SUN4I_REG_RBUF_RBACK_END_ADDR 0x01b0 /* CAN transmit buffer end */ @@ -779,6 +781,11 @@ static const struct sun4ican_quirks sun4ican_quirks_r40 = { .acp_offset = 0, }; +static const struct sun4ican_quirks sun4ican_quirks_d1 = { + .has_reset = true, + .acp_offset = (SUN4I_REG_ACPC_ADDR_D1 - SUN4I_REG_ACPC_ADDR), +}; + static const struct of_device_id sun4ican_of_match[] = { { .compatible = "allwinner,sun4i-a10-can", @@ -789,6 +796,9 @@ static const struct of_device_id sun4ican_of_match[] = { }, { .compatible = "allwinner,sun8i-r40-can", .data = &sun4ican_quirks_r40 + }, { + .compatible = "allwinner,sun20i-d1-can", + .data = &sun4ican_quirks_d1 }, { /* sentinel */ }, @@ -915,4 +925,4 @@ module_platform_driver(sun4i_can_driver); MODULE_AUTHOR("Peter Chen "); MODULE_AUTHOR("Gerhard Bertelsmann "); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_DESCRIPTION("CAN driver for Allwinner SoCs (A10/A20)"); +MODULE_DESCRIPTION("CAN driver for Allwinner SoCs (A10/A20/D1)"); From d5372a1f0cdf0db2be937f56dab7acde98b28136 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 28 Jul 2023 17:48:13 -0700 Subject: [PATCH 1523/2093] net: Use sockaddr_storage for getsockopt(SO_PEERNAME). [ Upstream commit 8936bf53a091ad6a34b480c22002f1cb2422ab38 ] Commit df8fc4e934c1 ("kbuild: Enable -fstrict-flex-arrays=3") started applying strict rules to standard string functions. It does not work well with conventional socket code around each protocol- specific sockaddr_XXX struct, which is cast from sockaddr_storage and has a bigger size than fortified functions expect. See these commits: commit 06d4c8a80836 ("af_unix: Fix fortify_panic() in unix_bind_bsd().") commit ecb4534b6a1c ("af_unix: Terminate sun_path when bind()ing pathname socket.") commit a0ade8404c3b ("af_packet: Fix warning of fortified memcpy() in packet_getname().") We must cast the protocol-specific address back to sockaddr_storage to call such functions. However, in the case of getsockaddr(SO_PEERNAME), the rationale is a bit unclear as the buffer is defined by char[128] which is the same size as sockaddr_storage. Let's use sockaddr_storage explicitly. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index e5858fa5d6d5..0ee2e33bbe5f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1774,14 +1774,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, case SO_PEERNAME: { - char address[128]; + struct sockaddr_storage address; - lv = sock->ops->getname(sock, (struct sockaddr *)address, 2); + lv = sock->ops->getname(sock, (struct sockaddr *)&address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; - if (copy_to_sockptr(optval, address, len)) + if (copy_to_sockptr(optval, &address, len)) return -EFAULT; goto lenout; } From e5d94c98a72f5f8047facb290d3af748fe86b461 Mon Sep 17 00:00:00 2001 From: xu xin Date: Mon, 7 Aug 2023 01:54:08 +0000 Subject: [PATCH 1524/2093] net/ipv4: return the real errno instead of -EINVAL [ Upstream commit c67180efc507e04a87f22aa68bd7dd832db006b7 ] For now, No matter what error pointer ip_neigh_for_gw() returns, ip_finish_output2() always return -EINVAL, which may mislead the upper users. For exemple, an application uses sendto to send an UDP packet, but when the neighbor table overflows, sendto() will get a value of -EINVAL, and it will cause users to waste a lot of time checking parameters for errors. Return the real errno instead of -EINVAL. Signed-off-by: xu xin Reviewed-by: Yang Yang Cc: Si Hao Reviewed-by: Kuniyuki Iwashima Reviewed-by: Vadim Fedorenko Link: https://lore.kernel.org/r/20230807015408.248237-1-xu.xin16@zte.com.cn Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/ip_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ebd2cea5b7d7..66908ce2dd11 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -234,7 +234,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); - return -EINVAL; + return PTR_ERR(neigh); } static int ip_finish_output_gso(struct net *net, struct sock *sk, From d3ad023a39f1127dcfd331c562673355dc078650 Mon Sep 17 00:00:00 2001 From: Mark O'Donovan Date: Fri, 4 Aug 2023 09:32:18 +0000 Subject: [PATCH 1525/2093] crypto: lib/mpi - avoid null pointer deref in mpi_cmp_ui() [ Upstream commit 9e47a758b70167c9301d2b44d2569f86c7796f2d ] During NVMeTCP Authentication a controller can trigger a kernel oops by specifying the 8192 bit Diffie Hellman group and passing a correctly sized, but zeroed Diffie Hellamn value. mpi_cmp_ui() was detecting this if the second parameter was 0, but 1 is passed from dh_is_pubkey_valid(). This causes the null pointer u->d to be dereferenced towards the end of mpi_cmp_ui() Signed-off-by: Mark O'Donovan Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- lib/mpi/mpi-cmp.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/lib/mpi/mpi-cmp.c b/lib/mpi/mpi-cmp.c index c4cfa3ff0581..0835b6213235 100644 --- a/lib/mpi/mpi-cmp.c +++ b/lib/mpi/mpi-cmp.c @@ -25,8 +25,12 @@ int mpi_cmp_ui(MPI u, unsigned long v) mpi_limb_t limb = v; mpi_normalize(u); - if (!u->nlimbs && !limb) - return 0; + if (u->nlimbs == 0) { + if (v == 0) + return 0; + else + return -1; + } if (u->sign) return -1; if (u->nlimbs > 1) From 06e2b5ad72b60f90bfe565c201346532e271f484 Mon Sep 17 00:00:00 2001 From: Ying Hsu Date: Wed, 5 Jul 2023 21:06:47 +0000 Subject: [PATCH 1526/2093] Bluetooth: Fix hci_suspend_sync crash [ Upstream commit 573ebae162111063eedc6c838a659ba628f66a0f ] If hci_unregister_dev() frees the hci_dev object but hci_suspend_notifier may still be accessing it, it can cause the program to crash. Here's the call trace: <4>[102152.653246] Call Trace: <4>[102152.653254] hci_suspend_sync+0x109/0x301 [bluetooth] <4>[102152.653259] hci_suspend_dev+0x78/0xcd [bluetooth] <4>[102152.653263] hci_suspend_notifier+0x42/0x7a [bluetooth] <4>[102152.653268] notifier_call_chain+0x43/0x6b <4>[102152.653271] __blocking_notifier_call_chain+0x48/0x69 <4>[102152.653273] __pm_notifier_call_chain+0x22/0x39 <4>[102152.653276] pm_suspend+0x287/0x57c <4>[102152.653278] state_store+0xae/0xe5 <4>[102152.653281] kernfs_fop_write+0x109/0x173 <4>[102152.653284] __vfs_write+0x16f/0x1a2 <4>[102152.653287] ? selinux_file_permission+0xca/0x16f <4>[102152.653289] ? security_file_permission+0x36/0x109 <4>[102152.653291] vfs_write+0x114/0x21d <4>[102152.653293] __x64_sys_write+0x7b/0xdb <4>[102152.653296] do_syscall_64+0x59/0x194 <4>[102152.653299] entry_SYSCALL_64_after_hwframe+0x5c/0xc1 This patch holds the reference count of the hci_dev object while processing it in hci_suspend_notifier to avoid potential crash caused by the race condition. Signed-off-by: Ying Hsu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/hci_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 146553c0054f..fa4dd5fab0d4 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2436,6 +2436,9 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return NOTIFY_DONE; + /* To avoid a potential race with hci_unregister_dev. */ + hci_dev_hold(hdev); + if (action == PM_SUSPEND_PREPARE) ret = hci_suspend_dev(hdev); else if (action == PM_POST_SUSPEND) @@ -2445,6 +2448,7 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", action, ret); + hci_dev_put(hdev); return NOTIFY_DONE; } From c2b226f223fb4c4e06273592e41d2a8d15f814d9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 11 Aug 2023 07:22:26 +0000 Subject: [PATCH 1527/2093] netlink: convert nlk->flags to atomic flags [ Upstream commit 8fe08d70a2b61b35a0a1235c78cf321e7528351f ] sk_diag_put_flags(), netlink_setsockopt(), netlink_getsockopt() and others use nlk->flags without correct locking. Use set_bit(), clear_bit(), test_bit(), assign_bit() to remove data-races. Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 90 ++++++++++++++-------------------------- net/netlink/af_netlink.h | 22 ++++++---- net/netlink/diag.c | 10 ++--- 3 files changed, 48 insertions(+), 74 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ed123cf462af..387e430a35cc 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -84,7 +84,7 @@ struct listeners { static inline int netlink_is_kernel(struct sock *sk) { - return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET; + return nlk_test_bit(KERNEL_SOCKET, sk); } struct netlink_table *nl_table __read_mostly; @@ -349,9 +349,7 @@ static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, static void netlink_overrun(struct sock *sk) { - struct netlink_sock *nlk = nlk_sk(sk); - - if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) { + if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; @@ -1391,9 +1389,7 @@ EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { - const struct netlink_sock *nlk = nlk_sk(NETLINK_CB(skb).sk); - - return nlk->flags & NETLINK_F_STRICT_CHK; + return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); } EXPORT_SYMBOL_GPL(netlink_strict_get_check); @@ -1437,7 +1433,7 @@ static void do_one_broadcast(struct sock *sk, return; if (!net_eq(sock_net(sk), p->net)) { - if (!(nlk->flags & NETLINK_F_LISTEN_ALL_NSID)) + if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) return; if (!peernet_has_id(sock_net(sk), p->net)) @@ -1470,7 +1466,7 @@ static void do_one_broadcast(struct sock *sk, netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; - if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; goto out; } @@ -1485,7 +1481,7 @@ static void do_one_broadcast(struct sock *sk, val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); - if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; } else { p->congested |= val; @@ -1565,7 +1561,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) !test_bit(p->group - 1, nlk->groups)) goto out; - if (p->code == ENOBUFS && nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) { + if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { ret = 1; goto out; } @@ -1632,7 +1628,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; - int err; + int nr = -1; if (level != SOL_NETLINK) return -ENOPROTOOPT; @@ -1643,14 +1639,12 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case NETLINK_PKTINFO: - if (val) - nlk->flags |= NETLINK_F_RECV_PKTINFO; - else - nlk->flags &= ~NETLINK_F_RECV_PKTINFO; - err = 0; + nr = NETLINK_F_RECV_PKTINFO; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { + int err; + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); @@ -1670,61 +1664,38 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); - err = 0; break; } case NETLINK_BROADCAST_ERROR: - if (val) - nlk->flags |= NETLINK_F_BROADCAST_SEND_ERROR; - else - nlk->flags &= ~NETLINK_F_BROADCAST_SEND_ERROR; - err = 0; + nr = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: + assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); if (val) { - nlk->flags |= NETLINK_F_RECV_NO_ENOBUFS; clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); - } else { - nlk->flags &= ~NETLINK_F_RECV_NO_ENOBUFS; } - err = 0; break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; - - if (val) - nlk->flags |= NETLINK_F_LISTEN_ALL_NSID; - else - nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID; - err = 0; + nr = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: - if (val) - nlk->flags |= NETLINK_F_CAP_ACK; - else - nlk->flags &= ~NETLINK_F_CAP_ACK; - err = 0; + nr = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: - if (val) - nlk->flags |= NETLINK_F_EXT_ACK; - else - nlk->flags &= ~NETLINK_F_EXT_ACK; - err = 0; + nr = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: - if (val) - nlk->flags |= NETLINK_F_STRICT_CHK; - else - nlk->flags &= ~NETLINK_F_STRICT_CHK; - err = 0; + nr = NETLINK_F_STRICT_CHK; break; default: - err = -ENOPROTOOPT; + return -ENOPROTOOPT; } - return err; + if (nr >= 0) + assign_bit(nr, &nlk->flags, val); + return 0; } static int netlink_getsockopt(struct socket *sock, int level, int optname, @@ -1791,7 +1762,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; len = sizeof(int); - val = nlk->flags & flag ? 1 : 0; + val = test_bit(flag, &nlk->flags); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) @@ -1968,9 +1939,9 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(*addr); } - if (nlk->flags & NETLINK_F_RECV_PKTINFO) + if (nlk_test_bit(RECV_PKTINFO, sk)) netlink_cmsg_recv_pktinfo(msg, skb); - if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) + if (nlk_test_bit(LISTEN_ALL_NSID, sk)) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); @@ -2047,7 +2018,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, goto out_sock_release; nlk = nlk_sk(sk); - nlk->flags |= NETLINK_F_KERNEL_SOCKET; + set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); netlink_table_grab(); if (!nl_table[unit].registered) { @@ -2183,7 +2154,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); - if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) { + if (extack->_msg && test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)) nlmsg_end(skb, nlh); @@ -2312,8 +2283,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { - struct netlink_sock *nlk, *nlk2; struct netlink_callback *cb; + struct netlink_sock *nlk; struct sock *sk; int ret; @@ -2348,8 +2319,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; - nlk2 = nlk_sk(NETLINK_CB(skb).sk); - cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK); + cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); if (control->start) { ret = control->start(cb); @@ -2391,7 +2361,7 @@ netlink_ack_tlv_len(struct netlink_sock *nlk, int err, { size_t tlvlen; - if (!extack || !(nlk->flags & NETLINK_F_EXT_ACK)) + if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) return 0; tlvlen = 0; @@ -2463,7 +2433,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, * requests to cap the error message, and get extra error data if * requested. */ - if (err && !(nlk->flags & NETLINK_F_CAP_ACK)) + if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 5f454c8de6a4..b30b8fc760f7 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -8,14 +8,16 @@ #include /* flags */ -#define NETLINK_F_KERNEL_SOCKET 0x1 -#define NETLINK_F_RECV_PKTINFO 0x2 -#define NETLINK_F_BROADCAST_SEND_ERROR 0x4 -#define NETLINK_F_RECV_NO_ENOBUFS 0x8 -#define NETLINK_F_LISTEN_ALL_NSID 0x10 -#define NETLINK_F_CAP_ACK 0x20 -#define NETLINK_F_EXT_ACK 0x40 -#define NETLINK_F_STRICT_CHK 0x80 +enum { + NETLINK_F_KERNEL_SOCKET, + NETLINK_F_RECV_PKTINFO, + NETLINK_F_BROADCAST_SEND_ERROR, + NETLINK_F_RECV_NO_ENOBUFS, + NETLINK_F_LISTEN_ALL_NSID, + NETLINK_F_CAP_ACK, + NETLINK_F_EXT_ACK, + NETLINK_F_STRICT_CHK, +}; #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) #define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long)) @@ -23,10 +25,10 @@ struct netlink_sock { /* struct sock has to be the first member of netlink_sock */ struct sock sk; + unsigned long flags; u32 portid; u32 dst_portid; u32 dst_group; - u32 flags; u32 subscriptions; u32 ngroups; unsigned long *groups; @@ -54,6 +56,8 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } +#define nlk_test_bit(nr, sk) test_bit(NETLINK_F_##nr, &nlk_sk(sk)->flags) + struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index e4f21b1067bc..9c4f231be275 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -27,15 +27,15 @@ static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb) if (nlk->cb_running) flags |= NDIAG_FLAG_CB_RUNNING; - if (nlk->flags & NETLINK_F_RECV_PKTINFO) + if (nlk_test_bit(RECV_PKTINFO, sk)) flags |= NDIAG_FLAG_PKTINFO; - if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR) + if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) flags |= NDIAG_FLAG_BROADCAST_ERROR; - if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS) + if (nlk_test_bit(RECV_NO_ENOBUFS, sk)) flags |= NDIAG_FLAG_NO_ENOBUFS; - if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID) + if (nlk_test_bit(LISTEN_ALL_NSID, sk)) flags |= NDIAG_FLAG_LISTEN_ALL_NSID; - if (nlk->flags & NETLINK_F_CAP_ACK) + if (nlk_test_bit(CAP_ACK, sk)) flags |= NDIAG_FLAG_CAP_ACK; return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags); From b62e8838e988c9a83b1456cc43abc0368884ffd5 Mon Sep 17 00:00:00 2001 From: Alexander Steffen Date: Tue, 13 Jun 2023 20:02:59 +0200 Subject: [PATCH 1528/2093] tpm_tis: Resend command to recover from data transfer errors [ Upstream commit 280db21e153d8810ce3b93640c63ae922bcb9e8e ] Similar to the transmission of TPM responses, also the transmission of TPM commands may become corrupted. Instead of aborting when detecting such issues, try resending the command again. Signed-off-by: Alexander Steffen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 44f71f2c8cfa..5889d9edaf94 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -498,10 +498,17 @@ static int tpm_tis_send_main(struct tpm_chip *chip, const u8 *buf, size_t len) int rc; u32 ordinal; unsigned long dur; + unsigned int try; - rc = tpm_tis_send_data(chip, buf, len); - if (rc < 0) - return rc; + for (try = 0; try < TPM_RETRY; try++) { + rc = tpm_tis_send_data(chip, buf, len); + if (rc >= 0) + /* Data transfer done successfully */ + break; + else if (rc != -EIO) + /* Data transfer failed, not recoverable */ + return rc; + } rc = tpm_tis_verify_crc(priv, len, buf); if (rc < 0) { From a13c1f6c324a944f7b99eebd00d297319320b00d Mon Sep 17 00:00:00 2001 From: Giulio Benetti Date: Fri, 11 Aug 2023 23:48:53 +0200 Subject: [PATCH 1529/2093] mmc: sdhci-esdhc-imx: improve ESDHC_FLAG_ERR010450 [ Upstream commit 5ae4b0d8875caa44946e579420c7fd5740d58653 ] Errata ERR010450 only shows up if voltage is 1.8V, but if the device is supplied by 3v3 the errata can be ignored. So let's check for if quirk SDHCI_QUIRK2_NO_1_8_V is defined or not before limiting the frequency. Cc: Jim Reinhart Cc: James Autry Cc: Matthew Maron Signed-off-by: Giulio Benetti Acked-by: Haibo Chen Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20230811214853.8623-1-giulio.benetti@benettiengineering.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/sdhci-esdhc-imx.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index b63cf1f9e8fb..3c7b32c0d3f3 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -171,8 +171,8 @@ #define ESDHC_FLAG_HS400 BIT(9) /* * The IP has errata ERR010450 - * uSDHC: Due to the I/O timing limit, for SDR mode, SD card clock can't - * exceed 150MHz, for DDR mode, SD card clock can't exceed 45MHz. + * uSDHC: At 1.8V due to the I/O timing limit, for SDR mode, SD card + * clock can't exceed 150MHz, for DDR mode, SD card clock can't exceed 45MHz. */ #define ESDHC_FLAG_ERR010450 BIT(10) /* The IP supports HS400ES mode */ @@ -932,7 +932,8 @@ static inline void esdhc_pltfm_set_clock(struct sdhci_host *host, | ESDHC_CLOCK_MASK); sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL); - if (imx_data->socdata->flags & ESDHC_FLAG_ERR010450) { + if ((imx_data->socdata->flags & ESDHC_FLAG_ERR010450) && + (!(host->quirks2 & SDHCI_QUIRK2_NO_1_8_V))) { unsigned int max_clock; max_clock = imx_data->is_ddr ? 45000000 : 150000000; From 1c27b73ffa90e83e72371d6ef68f9ec0eebdc79e Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Mon, 21 Aug 2023 09:32:18 +0800 Subject: [PATCH 1530/2093] alx: fix OOB-read compiler warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3a198c95c95da10ad844cbeade2fe40bdf14c411 ] The following message shows up when compiling with W=1: In function ‘fortify_memcpy_chk’, inlined from ‘alx_get_ethtool_stats’ at drivers/net/ethernet/atheros/alx/ethtool.c:297:2: ./include/linux/fortify-string.h:592:4: error: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 592 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In order to get alx stats altogether, alx_get_ethtool_stats() reads beyond hw->stats.rx_ok. Fix this warning by directly copying hw->stats, and refactor the unnecessarily complicated BUILD_BUG_ON btw. Signed-off-by: GONG, Ruiqi Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230821013218.1614265-1-gongruiqi@huaweicloud.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/atheros/alx/ethtool.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c index b716adacd815..7f6b69a52367 100644 --- a/drivers/net/ethernet/atheros/alx/ethtool.c +++ b/drivers/net/ethernet/atheros/alx/ethtool.c @@ -292,9 +292,8 @@ static void alx_get_ethtool_stats(struct net_device *netdev, spin_lock(&alx->stats_lock); alx_update_hw_stats(hw); - BUILD_BUG_ON(sizeof(hw->stats) - offsetof(struct alx_hw_stats, rx_ok) < - ALX_NUM_STATS * sizeof(u64)); - memcpy(data, &hw->stats.rx_ok, ALX_NUM_STATS * sizeof(u64)); + BUILD_BUG_ON(sizeof(hw->stats) != ALX_NUM_STATS * sizeof(u64)); + memcpy(data, &hw->stats, sizeof(hw->stats)); spin_unlock(&alx->stats_lock); } From 7ae7a1378a119780c8c17a6b5fc03011c3bb7029 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 15 Aug 2023 17:51:05 +0200 Subject: [PATCH 1531/2093] wifi: mac80211: check S1G action frame size [ Upstream commit 19e4a47ee74718a22e963e8a647c8c3bfe8bb05c ] Before checking the action code, check that it even exists in the frame. Reported-by: syzbot+be9c824e6f269d608288@syzkaller.appspotmail.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/rx.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 55dc0610e863..c4c80037df91 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3625,6 +3625,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) break; goto queue; case WLAN_CATEGORY_S1G: + if (len < offsetofend(typeof(*mgmt), + u.action.u.s1g.action_code)) + break; + switch (mgmt->u.action.u.s1g.action_code) { case WLAN_S1G_TWT_SETUP: case WLAN_S1G_TWT_TEARDOWN: From 28b07e30bc1465fdc0d71919739310ec311abe42 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Wed, 9 Aug 2023 15:45:03 +0800 Subject: [PATCH 1532/2093] netfilter: ebtables: fix fortify warnings in size_entry_mwt() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a7ed3465daa240bdf01a5420f64336fee879c09d ] When compiling with gcc 13 and CONFIG_FORTIFY_SOURCE=y, the following warning appears: In function ‘fortify_memcpy_chk’, inlined from ‘size_entry_mwt’ at net/bridge/netfilter/ebtables.c:2118:2: ./include/linux/fortify-string.h:592:25: error: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 592 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The compiler is complaining: memcpy(&offsets[1], &entry->watchers_offset, sizeof(offsets) - sizeof(offsets[0])); where memcpy reads beyong &entry->watchers_offset to copy {watchers,target,next}_offset altogether into offsets[]. Silence the warning by wrapping these three up via struct_group(). Signed-off-by: GONG, Ruiqi Reviewed-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- include/uapi/linux/netfilter_bridge/ebtables.h | 14 ++++++++------ net/bridge/netfilter/ebtables.c | 3 +-- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index a494cf43a755..b0caad82b693 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -182,12 +182,14 @@ struct ebt_entry { unsigned char sourcemsk[ETH_ALEN]; unsigned char destmac[ETH_ALEN]; unsigned char destmsk[ETH_ALEN]; - /* sizeof ebt_entry + matches */ - unsigned int watchers_offset; - /* sizeof ebt_entry + matches + watchers */ - unsigned int target_offset; - /* sizeof ebt_entry + matches + watchers + target */ - unsigned int next_offset; + __struct_group(/* no tag */, offsets, /* no attrs */, + /* sizeof ebt_entry + matches */ + unsigned int watchers_offset; + /* sizeof ebt_entry + matches + watchers */ + unsigned int target_offset; + /* sizeof ebt_entry + matches + watchers + target */ + unsigned int next_offset; + ); unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 757ec46fc45a..aa23479b20b2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2115,8 +2115,7 @@ static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *ba return ret; offsets[0] = sizeof(struct ebt_entry); /* matches come first */ - memcpy(&offsets[1], &entry->watchers_offset, - sizeof(offsets) - sizeof(offsets[0])); + memcpy(&offsets[1], &entry->offsets, sizeof(entry->offsets)); if (state->buf_kern_start) { buf_start = state->buf_kern_start + state->buf_kern_offset; From 676a423410131d111a264d29aecbe6aadd57fb22 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 15 Aug 2023 18:09:00 +0200 Subject: [PATCH 1533/2093] wifi: cfg80211: reject auth/assoc to AP with our address [ Upstream commit 5d4e04bf3a0f098bd9033de3a5291810fa14c7a6 ] If the AP uses our own address as its MLD address or BSSID, then clearly something's wrong. Reject such connections so we don't try and fail later. Reported-by: syzbot+2676771ed06a6df166ad@syzkaller.appspotmail.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/mlme.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 581df7f4c524..e7fa0608341d 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -277,6 +277,11 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, ether_addr_equal(req->bss->bssid, wdev->u.client.connected_addr)) return -EALREADY; + if (ether_addr_equal(req->bss->bssid, dev->dev_addr) || + (req->link_id >= 0 && + ether_addr_equal(req->ap_mld_addr, dev->dev_addr))) + return -EINVAL; + return rdev_auth(rdev, dev, req); } @@ -331,6 +336,9 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, if (req->links[i].bss == req->links[j].bss) return -EINVAL; } + + if (ether_addr_equal(req->links[i].bss->bssid, dev->dev_addr)) + return -EINVAL; } if (wdev->connected && @@ -338,6 +346,11 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, !ether_addr_equal(wdev->u.client.connected_addr, req->prev_bssid))) return -EALREADY; + if ((req->bss && ether_addr_equal(req->bss->bssid, dev->dev_addr)) || + (req->link_id >= 0 && + ether_addr_equal(req->ap_mld_addr, dev->dev_addr))) + return -EINVAL; + cfg80211_oper_and_ht_capa(&req->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); cfg80211_oper_and_vht_capa(&req->vht_capa_mask, From d7b0fe3487d203c04ee1bda91a63bd4dd398c350 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 15 Aug 2023 18:32:03 +0200 Subject: [PATCH 1534/2093] wifi: cfg80211: ocb: don't leave if not joined [ Upstream commit abc76cf552e13cfa88a204b362a86b0e08e95228 ] If there's no OCB state, don't ask the driver/mac80211 to leave, since that's just confusing. Since set/clear the chandef state, that's a simple check. Reported-by: syzbot+09d1cd2f71e6dd3bfd2c@syzkaller.appspotmail.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/ocb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/wireless/ocb.c b/net/wireless/ocb.c index 27a1732264f9..29afaf3da54f 100644 --- a/net/wireless/ocb.c +++ b/net/wireless/ocb.c @@ -68,6 +68,9 @@ int __cfg80211_leave_ocb(struct cfg80211_registered_device *rdev, if (!rdev->ops->leave_ocb) return -EOPNOTSUPP; + if (!wdev->u.ocb.chandef.chan) + return -ENOTCONN; + err = rdev_leave_ocb(rdev, dev); if (!err) memset(&wdev->u.ocb.chandef, 0, sizeof(wdev->u.ocb.chandef)); From 7e1cda5cf07f848e6b50b4e5e7761ffbce905a3d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 15 Aug 2023 18:41:32 +0200 Subject: [PATCH 1535/2093] wifi: mac80211: check for station first in client probe [ Upstream commit 67dfa589aa8806c7959cbca2f4613b8d41c75a06 ] When probing a client, first check if we have it, and then check for the channel context, otherwise you can trigger the warning there easily by probing when the AP isn't even started yet. Since a client existing means the AP is also operating, we can then keep the warning. Also simplify the moved code a bit. Reported-by: syzbot+999fac712d84878a7379@syzkaller.appspotmail.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/cfg.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 23a44edcb11f..cf3453b532d6 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3991,19 +3991,20 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, mutex_lock(&local->mtx); rcu_read_lock(); + sta = sta_info_get_bss(sdata, peer); + if (!sta) { + ret = -ENOLINK; + goto unlock; + } + + qos = sta->sta.wme; + chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (WARN_ON(!chanctx_conf)) { ret = -EINVAL; goto unlock; } band = chanctx_conf->def.chan->band; - sta = sta_info_get_bss(sdata, peer); - if (sta) { - qos = sta->sta.wme; - } else { - ret = -ENOLINK; - goto unlock; - } if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | From b9a175e3b250b0dc6e152988040aa5014e98e61e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 15 Aug 2023 21:28:01 +0200 Subject: [PATCH 1536/2093] wifi: mac80211_hwsim: drop short frames [ Upstream commit fba360a047d5eeeb9d4b7c3a9b1c8308980ce9a6 ] While technically some control frames like ACK are shorter and end after Address 1, such frames shouldn't be forwarded through wmediumd or similar userspace, so require the full 3-address header to avoid accessing invalid memory if shorter frames are passed in. Reported-by: syzbot+b2645b5bf1512b81fa22@syzkaller.appspotmail.com Reviewed-by: Jeff Johnson Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/mac80211_hwsim.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index da5c355405f6..db70cef854bc 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4906,14 +4906,15 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, frame_data_len = nla_len(info->attrs[HWSIM_ATTR_FRAME]); frame_data = (void *)nla_data(info->attrs[HWSIM_ATTR_FRAME]); + if (frame_data_len < sizeof(struct ieee80211_hdr_3addr) || + frame_data_len > IEEE80211_MAX_DATA_LEN) + goto err; + /* Allocate new skb here */ skb = alloc_skb(frame_data_len, GFP_KERNEL); if (skb == NULL) goto err; - if (frame_data_len > IEEE80211_MAX_DATA_LEN) - goto err; - /* Copy the data */ skb_put_data(skb, frame_data, frame_data_len); From d5feaef143b6217657f07e4d9f13a2a2da6a4ee1 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 22 Aug 2023 12:38:40 -0700 Subject: [PATCH 1537/2093] libbpf: Free btf_vmlinux when closing bpf_object [ Upstream commit 29d67fdebc42af6466d1909c60fdd1ef4f3e5240 ] I hit a memory leak when testing bpf_program__set_attach_target(). Basically, set_attach_target() may allocate btf_vmlinux, for example, when setting attach target for bpf_iter programs. But btf_vmlinux is freed only in bpf_object_load(), which means if we only open bpf object but not load it, setting attach target may leak btf_vmlinux. So let's free btf_vmlinux in bpf_object__close() anyway. Signed-off-by: Hao Luo Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230822193840.1509809-1-haoluo@google.com Signed-off-by: Sasha Levin --- tools/lib/bpf/libbpf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index eeb2693128d8..10f15a3e3a95 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -8173,6 +8173,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object_unload(obj); btf__free(obj->btf); + btf__free(obj->btf_vmlinux); btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) From 8178dac6ee2cc2164996d1e6a796301535a6784b Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 15 Jun 2023 22:19:00 +0200 Subject: [PATCH 1538/2093] drm/bridge: tc358762: Instruct DSI host to generate HSE packets [ Upstream commit 362fa8f6e6a05089872809f4465bab9d011d05b3 ] This bridge seems to need the HSE packet, otherwise the image is shifted up and corrupted at the bottom. This makes the bridge work with Samsung DSIM on i.MX8MM and i.MX8MP. Signed-off-by: Marek Vasut Reviewed-by: Sam Ravnborg Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230615201902.566182-3-marex@denx.de Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358762.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/tc358762.c b/drivers/gpu/drm/bridge/tc358762.c index 7f4fce1aa998..8db981e7759b 100644 --- a/drivers/gpu/drm/bridge/tc358762.c +++ b/drivers/gpu/drm/bridge/tc358762.c @@ -216,7 +216,7 @@ static int tc358762_probe(struct mipi_dsi_device *dsi) dsi->lanes = 1; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | - MIPI_DSI_MODE_LPM; + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_VIDEO_HSE; ret = tc358762_parse_dt(ctx); if (ret < 0) From 766cc11e854eae64d1bb35a3d34d091f5b85afa9 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Tue, 20 Jun 2023 23:19:03 -0700 Subject: [PATCH 1539/2093] drm/edid: Add quirk for OSVR HDK 2.0 [ Upstream commit 98d4cb705bc00afd4a9a71cc1e84f7111682639a ] The OSVR virtual reality headset HDK 2.0 uses a different EDID vendor and device identifier than the HDK 1.1 - 1.4 headsets. Add the HDK 2.0 vendor and device identifier to the quirks table so that window managers do not try to display the desktop screen on the headset display. Closes: https://gitlab.freedesktop.org/drm/misc/-/issues/30 Signed-off-by: Ralph Campbell Tested-by: Ralph Campbell Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20230621061903.3422648-1-rcampbell@nvidia.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_edid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 739e0d40cca6..5ed77e3361fd 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -231,6 +231,7 @@ static const struct edid_quirk { /* OSVR HDK and HDK2 VR Headsets */ EDID_QUIRK('S', 'V', 'R', 0x1019, EDID_QUIRK_NON_DESKTOP), + EDID_QUIRK('A', 'U', 'O', 0x1111, EDID_QUIRK_NON_DESKTOP), }; /* From 03499a685773c06a6c76989b9ca5a006a897d83e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Jun 2023 13:44:38 +0200 Subject: [PATCH 1540/2093] arm64: dts: qcom: sm6125-pdx201: correct ramoops pmsg-size [ Upstream commit c42f5452de6ad2599c6e5e2a64c180a4ac835d27 ] There is no 'msg-size' property in ramoops, so assume intention was for 'pmsg-size': sm6125-sony-xperia-seine-pdx201.dtb: ramoops@ffc00000: Unevaluated properties are not allowed ('msg-size' was unexpected) Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230618114442.140185-3-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts b/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts index e1ab5b518994..4a77b650c0d8 100644 --- a/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts +++ b/arch/arm64/boot/dts/qcom/sm6125-sony-xperia-seine-pdx201.dts @@ -73,7 +73,7 @@ pstore_mem: ramoops@ffc00000 { reg = <0x0 0xffc40000 0x0 0xc0000>; record-size = <0x1000>; console-size = <0x40000>; - msg-size = <0x20000 0x20000>; + pmsg-size = <0x20000>; }; cmdline_mem: memory@ffd00000 { From 23f9d0c6719960eba1242ea6a274b40d2fb896e1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Jun 2023 13:44:40 +0200 Subject: [PATCH 1541/2093] arm64: dts: qcom: sm6350: correct ramoops pmsg-size [ Upstream commit c86b97a72065e06eacb993dc71fa9febc93422af ] There is no 'msg-size' property in ramoops, so assume intention was for 'pmsg-size': sm6350-sony-xperia-lena-pdx213.dtb: ramoops@ffc00000: Unevaluated properties are not allowed ('msg-size' was unexpected) Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230618114442.140185-5-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm6350.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 34c8de4f43fb..cea7ca3f326f 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -346,7 +346,7 @@ ramoops: ramoops@ffc00000 { reg = <0 0xffc00000 0 0x100000>; record-size = <0x1000>; console-size = <0x40000>; - msg-size = <0x20000 0x20000>; + pmsg-size = <0x20000>; ecc-size = <16>; no-map; }; From 41ff904a7c46495c0340aa7ab78c969bd86370cd Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Jun 2023 13:44:41 +0200 Subject: [PATCH 1542/2093] arm64: dts: qcom: sm8150-kumano: correct ramoops pmsg-size [ Upstream commit 4e6b942f092653ebcdbbc0819b2d1f08ab415bdc ] There is no 'msg-size' property in ramoops, so assume intention was for 'pmsg-size': sm8150-sony-xperia-kumano-griffin.dtb: ramoops@ffc00000: Unevaluated properties are not allowed ('msg-size' was unexpected) Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230618114442.140185-6-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi b/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi index 04c71f74ab72..c9aa7764fc59 100644 --- a/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150-sony-xperia-kumano.dtsi @@ -127,7 +127,7 @@ ramoops@ffc00000 { reg = <0x0 0xffc00000 0x0 0x100000>; record-size = <0x1000>; console-size = <0x40000>; - msg-size = <0x20000 0x20000>; + pmsg-size = <0x20000>; ecc-size = <16>; no-map; }; From 306c7903de14203b701cfb6f03a1eb82666f38fa Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Jun 2023 13:44:42 +0200 Subject: [PATCH 1543/2093] arm64: dts: qcom: sm8250-edo: correct ramoops pmsg-size [ Upstream commit 7dc3606f91427414d00a2fb09e6e0e32c14c2093 ] There is no 'msg-size' property in ramoops, so assume intention was for 'pmsg-size': sm8250-sony-xperia-edo-pdx206.dtb: ramoops@ffc00000: Unevaluated properties are not allowed ('msg-size' was unexpected) Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230618114442.140185-7-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi index 3b710c6a326a..3b306dfb91e0 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250-sony-xperia-edo.dtsi @@ -126,7 +126,7 @@ ramoops@ffc00000 { reg = <0x0 0xffc00000 0x0 0x100000>; record-size = <0x1000>; console-size = <0x40000>; - msg-size = <0x20000 0x20000>; + pmsg-size = <0x20000>; ecc-size = <16>; no-map; }; From 4630c27c5529fe66fda23ec1763918745c8bb192 Mon Sep 17 00:00:00 2001 From: Rong Tao Date: Sun, 16 Apr 2023 23:05:17 +0800 Subject: [PATCH 1544/2093] samples/hw_breakpoint: Fix kernel BUG 'invalid opcode: 0000' [ Upstream commit 910e230d5f1bb72c54532e94fbb1705095c7bab6 ] Macro symbol_put() is defined as __symbol_put(__stringify(x)) ksym_name = "jiffies" symbol_put(ksym_name) will be resolved as __symbol_put("ksym_name") which is clearly wrong. So symbol_put must be replaced with __symbol_put. When we uninstall hw_breakpoint.ko (rmmod), a kernel bug occurs with the following error: [11381.854152] kernel BUG at kernel/module/main.c:779! [11381.854159] invalid opcode: 0000 [#2] PREEMPT SMP PTI [11381.854163] CPU: 8 PID: 59623 Comm: rmmod Tainted: G D OE 6.2.9-200.fc37.x86_64 #1 [11381.854167] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./B360M-HDV, BIOS P3.20 10/23/2018 [11381.854169] RIP: 0010:__symbol_put+0xa2/0xb0 [11381.854175] Code: 00 e8 92 d2 f7 ff 65 8b 05 c3 2f e6 78 85 c0 74 1b 48 8b 44 24 30 65 48 2b 04 25 28 00 00 00 75 12 48 83 c4 38 c3 cc cc cc cc <0f> 0b 0f 1f 44 00 00 eb de e8 c0 df d8 00 90 90 90 90 90 90 90 90 [11381.854178] RSP: 0018:ffffad8ec6ae7dd0 EFLAGS: 00010246 [11381.854181] RAX: 0000000000000000 RBX: ffffffffc1fd1240 RCX: 000000000000000c [11381.854184] RDX: 000000000000006b RSI: ffffffffc02bf7c7 RDI: ffffffffc1fd001c [11381.854186] RBP: 000055a38b76e7c8 R08: ffffffff871ccfe0 R09: 0000000000000000 [11381.854188] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 [11381.854190] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [11381.854192] FS: 00007fbf7c62c740(0000) GS:ffff8c5badc00000(0000) knlGS:0000000000000000 [11381.854195] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [11381.854197] CR2: 000055a38b7793f8 CR3: 0000000363e1e001 CR4: 00000000003726e0 [11381.854200] DR0: ffffffffb3407980 DR1: 0000000000000000 DR2: 0000000000000000 [11381.854202] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [11381.854204] Call Trace: [11381.854207] [11381.854212] s_module_exit+0xc/0xff0 [symbol_getput] [11381.854219] __do_sys_delete_module.constprop.0+0x198/0x2f0 [11381.854225] do_syscall_64+0x58/0x80 [11381.854231] ? exit_to_user_mode_prepare+0x180/0x1f0 [11381.854237] ? syscall_exit_to_user_mode+0x17/0x40 [11381.854241] ? do_syscall_64+0x67/0x80 [11381.854245] ? syscall_exit_to_user_mode+0x17/0x40 [11381.854248] ? do_syscall_64+0x67/0x80 [11381.854252] ? exc_page_fault+0x70/0x170 [11381.854256] entry_SYSCALL_64_after_hwframe+0x72/0xdc Signed-off-by: Rong Tao Reviewed-by: Petr Mladek Signed-off-by: Luis Chamberlain Signed-off-by: Sasha Levin --- samples/hw_breakpoint/data_breakpoint.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c index 418c46fe5ffc..9debd128b2ab 100644 --- a/samples/hw_breakpoint/data_breakpoint.c +++ b/samples/hw_breakpoint/data_breakpoint.c @@ -70,7 +70,7 @@ static int __init hw_break_module_init(void) static void __exit hw_break_module_exit(void) { unregister_wide_hw_breakpoint(sample_hbp); - symbol_put(ksym_name); + __symbol_put(ksym_name); printk(KERN_INFO "HW Breakpoint for %s write uninstalled\n", ksym_name); } From 2ec715bf881696b23caa06953c8c9309c2ce5224 Mon Sep 17 00:00:00 2001 From: Leo Ma Date: Thu, 6 Jul 2023 16:17:03 -0400 Subject: [PATCH 1545/2093] drm/amd/display: Fix underflow issue on 175hz timing [ Upstream commit 735688eb905db529efea0c78466fccc1461c3fde ] [Why] Screen underflows happen on 175hz timing for 3 plane overlay case. [How] Based on dst y prefetch value clamp to equ or oto for bandwidth calculation. Reviewed-by: Dillon Varone Acked-by: Alex Hung Signed-off-by: Leo Ma Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../amd/display/dc/dml/dcn32/display_mode_vba_util_32.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index b53feeaf5cf1..23e4be2ad63f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3454,6 +3454,7 @@ bool dml32_CalculatePrefetchSchedule( double TimeForFetchingMetaPTE = 0; double TimeForFetchingRowInVBlank = 0; double LinesToRequestPrefetchPixelData = 0; + double LinesForPrefetchBandwidth = 0; unsigned int HostVMDynamicLevelsTrips; double trip_to_mem; double Tvm_trips; @@ -3883,11 +3884,15 @@ bool dml32_CalculatePrefetchSchedule( TimeForFetchingMetaPTE = Tvm_oto; TimeForFetchingRowInVBlank = Tr0_oto; *PrefetchBandwidth = prefetch_bw_oto; + /* Clamp to oto for bandwidth calculation */ + LinesForPrefetchBandwidth = dst_y_prefetch_oto; } else { *DestinationLinesForPrefetch = dst_y_prefetch_equ; TimeForFetchingMetaPTE = Tvm_equ; TimeForFetchingRowInVBlank = Tr0_equ; *PrefetchBandwidth = prefetch_bw_equ; + /* Clamp to equ for bandwidth calculation */ + LinesForPrefetchBandwidth = dst_y_prefetch_equ; } *DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0; @@ -3895,7 +3900,7 @@ bool dml32_CalculatePrefetchSchedule( *DestinationLinesToRequestRowInVBlank = dml_ceil(4.0 * TimeForFetchingRowInVBlank / LineTime, 1.0) / 4.0; - LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch - + LinesToRequestPrefetchPixelData = LinesForPrefetchBandwidth - *DestinationLinesToRequestVMInVBlank - 2 * *DestinationLinesToRequestRowInVBlank; #ifdef __DML_VBA_DEBUG__ From d843bcc7adc97dec627347cdd823fb0afd7e40cb Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 31 Jul 2023 16:37:43 -0500 Subject: [PATCH 1546/2093] ASoC: SOF: topology: simplify code to prevent static analysis warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 55cb3dc271d81f1982c949a2ac483a6daf613b92 ] make KCFLAGS='-fanalyzer' sound/soc/sof/intel/ reports a possible NULL pointer dereference. sound/soc/sof/topology.c:1136:21: error: dereference of NULL ‘w’ [CWE-476] [-Werror=analyzer-null-dereference] 1136 | strcmp(w->sname, rtd->dai_link->stream_name)) The code is rather confusing and can be simplified to make static analysis happy. No functionality change. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Daniel Baluta Reviewed-by: Yaochun Hung Link: https://lore.kernel.org/r/20230731213748.440285-4-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/topology.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 872e44408298..e7305ce57ea1 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -1086,16 +1086,17 @@ static void sof_disconnect_dai_widget(struct snd_soc_component *scomp, { struct snd_soc_card *card = scomp->card; struct snd_soc_pcm_runtime *rtd; + const char *sname = w->sname; struct snd_soc_dai *cpu_dai; int i; - if (!w->sname) + if (!sname) return; list_for_each_entry(rtd, &card->rtd_list, list) { /* does stream match DAI link ? */ if (!rtd->dai_link->stream_name || - strcmp(w->sname, rtd->dai_link->stream_name)) + strcmp(sname, rtd->dai_link->stream_name)) continue; switch (w->id) { From cc4553c14fbbe0bcc40e0c53ad12e9668894f294 Mon Sep 17 00:00:00 2001 From: Uday M Bhat Date: Mon, 31 Jul 2023 16:42:38 -0500 Subject: [PATCH 1547/2093] ASoC: Intel: sof_sdw: Update BT offload config for soundwire config [ Upstream commit a14aded9299187bb17ef90700eb2cf1120ef5885 ] For soundwire config, SSP1 is used for BT offload. This is enabled in sof_sdw_quirk_table Reviewed-by: Kai Vehmanen Reviewed-by: Ranjani Sridharan Reviewed-by: Bard Liao Signed-off-by: Uday M Bhat Signed-off-by: Jairaj Arava Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230731214257.444605-5-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/boards/sof_sdw.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 064b6feb7616..414ac9027381 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -388,7 +388,9 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Google"), DMI_MATCH(DMI_PRODUCT_NAME, "Rex"), }, - .driver_data = (void *)(SOF_SDW_PCH_DMIC), + .driver_data = (void *)(SOF_SDW_PCH_DMIC | + SOF_BT_OFFLOAD_SSP(1) | + SOF_SSP_BT_OFFLOAD_PRESENT), }, /* LunarLake devices */ { From 2d027da82a96153eaa22570e549e5d43cbfd84fc Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 2 Aug 2023 10:01:04 -0500 Subject: [PATCH 1548/2093] ALSA: hda: intel-dsp-cfg: add LunarLake support [ Upstream commit d2852b8c045ebd31d753b06f2810df5be30ed56a ] One more PCI ID for the road. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20230802150105.24604-5-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/intel-dsp-config.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 317bdf6dcbef..2873420c9aca 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -481,6 +481,14 @@ static const struct config_entry config_table[] = { }, #endif +/* Lunar Lake */ +#if IS_ENABLED(CONFIG_SND_SOC_SOF_LUNARLAKE) + /* Lunarlake-P */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = PCI_DEVICE_ID_INTEL_HDA_LNL_P, + }, +#endif }; static const struct config_entry *snd_intel_dsp_find_config From 506d2ee72af2ffc4173537eb001d7d4d57781ec7 Mon Sep 17 00:00:00 2001 From: Austin Zheng Date: Wed, 26 Jul 2023 10:40:48 -0400 Subject: [PATCH 1549/2093] drm/amd/display: Use DTBCLK as refclk instead of DPREFCLK [ Upstream commit 4a30cc2bd281fa176a68b5305cd3695d636152ad ] [Why] Flash of corruption observed when UCLK switching after transitioning from DTBCLK to DPREFCLK on subVP(DP) + subVP(HDMI) config Scenario where DPREFCLK is required instead of DTBCLK is not expected [How] Always set the DTBCLK source as DTBCLK0 Reviewed-by: Alvin Lee Acked-by: Tom Chung Signed-off-by: Austin Zheng Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c index ffbb739d85b6..8496ff4a25e3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c @@ -290,7 +290,8 @@ static void dccg32_set_dpstreamclk( struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); /* set the dtbclk_p source */ - dccg32_set_dtbclk_p_src(dccg, src, otg_inst); + /* always program refclk as DTBCLK. No use-case expected to require DPREFCLK as refclk */ + dccg32_set_dtbclk_p_src(dccg, DTBCLK0, otg_inst); /* enabled to select one of the DTBCLKs for pipe */ switch (dp_hpo_inst) { From 2c0f5b6972ebfd6224065fd3c59d04f85a8af795 Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Mon, 24 Jul 2023 16:57:36 -0400 Subject: [PATCH 1550/2093] drm/amd/display: Blocking invalid 420 modes on HDMI TMDS for DCN31 [ Upstream commit 026a71babf48efb6b9884a3a66fa31aec9e1ea54 ] [Why & How] HDMI TMDS does not have ODM support. Filtering 420 modes that exceed the 4096 FMT limitation on DCN31 will resolve intermittent corruptions issues. Reviewed-by: Nicholas Kazlauskas Acked-by: Tom Chung Signed-off-by: Leo Chen Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index ebc04b72b284..9c84561ff3bc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -4133,7 +4133,9 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } if (v->OutputFormat[k] == dm_420 && v->HActive[k] > DCN31_MAX_FMT_420_BUFFER_WIDTH && v->ODMCombineEnablePerState[i][k] != dm_odm_combine_mode_4to1) { - if (v->HActive[k] / 2 > DCN31_MAX_FMT_420_BUFFER_WIDTH) { + if (v->Output[k] == dm_hdmi) { + FMTBufferExceeded = true; + } else if (v->HActive[k] / 2 > DCN31_MAX_FMT_420_BUFFER_WIDTH) { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_4to1; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine4To1; From a101b1bdd24acf648a55b86d8b429b76e1bd202b Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Wed, 26 Jul 2023 22:44:13 -0400 Subject: [PATCH 1551/2093] drm/amd/display: Blocking invalid 420 modes on HDMI TMDS for DCN314 [ Upstream commit 4c6107a653ccf361cb1b6ba35d558a1a5e6e57ac ] [Why & How] HDMI TMDS does not have ODM support. Filtering 420 modes that exceed the 4096 FMT limitation on DCN314 will resolve intermittent corruptions issues. Reviewed-by: Nicholas Kazlauskas Acked-by: Tom Chung Signed-off-by: Leo Chen Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 4998b211ccac..5b47ccde6424 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -4225,7 +4225,9 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ } if (v->OutputFormat[k] == dm_420 && v->HActive[k] > DCN314_MAX_FMT_420_BUFFER_WIDTH && v->ODMCombineEnablePerState[i][k] != dm_odm_combine_mode_4to1) { - if (v->HActive[k] / 2 > DCN314_MAX_FMT_420_BUFFER_WIDTH) { + if (v->Output[k] == dm_hdmi) { + FMTBufferExceeded = true; + } else if (v->HActive[k] / 2 > DCN314_MAX_FMT_420_BUFFER_WIDTH) { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_4to1; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine4To1; From edddbdb8122e82a2427c1b9c9df4497f3aacc0bc Mon Sep 17 00:00:00 2001 From: Tuo Li Date: Fri, 30 Jun 2023 10:19:06 +0800 Subject: [PATCH 1552/2093] drm/exynos: fix a possible null-pointer dereference due to data race in exynos_drm_crtc_atomic_disable() [ Upstream commit 2e63972a2de14482d0eae1a03a73e379f1c3f44c ] The variable crtc->state->event is often protected by the lock crtc->dev->event_lock when is accessed. However, it is accessed as a condition of an if statement in exynos_drm_crtc_atomic_disable() without holding the lock: if (crtc->state->event && !crtc->state->active) However, if crtc->state->event is changed to NULL by another thread right after the conditions of the if statement is checked to be true, a null-pointer dereference can occur in drm_crtc_send_vblank_event(): e->pipe = pipe; To fix this possible null-pointer dereference caused by data race, the spin lock coverage is extended to protect the if statement as well as the function call to drm_crtc_send_vblank_event(). Reported-by: BassCheck Link: https://sites.google.com/view/basscheck/home Signed-off-by: Tuo Li Reviewed-by: Krzysztof Kozlowski Added relevant link. Signed-off-by: Inki Dae Signed-off-by: Sasha Levin --- drivers/gpu/drm/exynos/exynos_drm_crtc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index 4153f302de7c..d19e796c2061 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -39,13 +39,12 @@ static void exynos_drm_crtc_atomic_disable(struct drm_crtc *crtc, if (exynos_crtc->ops->atomic_disable) exynos_crtc->ops->atomic_disable(exynos_crtc); + spin_lock_irq(&crtc->dev->event_lock); if (crtc->state->event && !crtc->state->active) { - spin_lock_irq(&crtc->dev->event_lock); drm_crtc_send_vblank_event(crtc, crtc->state->event); - spin_unlock_irq(&crtc->dev->event_lock); - crtc->state->event = NULL; } + spin_unlock_irq(&crtc->dev->event_lock); } static int exynos_crtc_atomic_check(struct drm_crtc *crtc, From 4c743c1dd2ee2a72951660b6798d4d7f7674f87b Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Tue, 25 Jul 2023 09:32:26 +0200 Subject: [PATCH 1553/2093] drm/mediatek: dp: Change logging to dev for mtk_dp_aux_transfer() [ Upstream commit fd70e2019bfbcb0ed90c5e23839bf510ce6acf8f ] Change logging from drm_{err,info}() to dev_{err,info}() in functions mtk_dp_aux_transfer() and mtk_dp_aux_do_transfer(): this will be essential to avoid getting NULL pointer kernel panics if any kind of error happens during AUX transfers happening before the bridge is attached. This may potentially start happening in a later commit implementing aux-bus support, as AUX transfers will be triggered from the panel driver (for EDID) before the mtk-dp bridge gets attached, and it's done in preparation for the same. Signed-off-by: AngeloGioacchino Del Regno Tested-by: Chen-Yu Tsai Reviewed-by: CK Hu Reviewed-by: Alexandre Mergnat Link: https://patchwork.kernel.org/project/dri-devel/patch/20230725073234.55892-4-angelogioacchino.delregno@collabora.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_dp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 4c249939a6c3..395a190274cf 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -847,7 +847,7 @@ static int mtk_dp_aux_do_transfer(struct mtk_dp *mtk_dp, bool is_read, u8 cmd, u32 phy_status = mtk_dp_read(mtk_dp, MTK_DP_AUX_P0_3628) & AUX_RX_PHY_STATE_AUX_TX_P0_MASK; if (phy_status != AUX_RX_PHY_STATE_AUX_TX_P0_RX_IDLE) { - drm_err(mtk_dp->drm_dev, + dev_err(mtk_dp->dev, "AUX Rx Aux hang, need SW reset\n"); return -EIO; } @@ -2062,7 +2062,7 @@ static ssize_t mtk_dp_aux_transfer(struct drm_dp_aux *mtk_aux, is_read = true; break; default: - drm_err(mtk_aux->drm_dev, "invalid aux cmd = %d\n", + dev_err(mtk_dp->dev, "invalid aux cmd = %d\n", msg->request); ret = -EINVAL; goto err; @@ -2078,7 +2078,7 @@ static ssize_t mtk_dp_aux_transfer(struct drm_dp_aux *mtk_aux, to_access, &msg->reply); if (ret) { - drm_info(mtk_dp->drm_dev, + dev_info(mtk_dp->dev, "Failed to do AUX transfer: %d\n", ret); goto err; } From 4e547968a6e4b58d6ca8accbe73141c8a84f8d9e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 4 Aug 2023 13:38:01 +0300 Subject: [PATCH 1554/2093] bus: ti-sysc: Configure uart quirks for k3 SoC [ Upstream commit 03a711d3cb83692733f865312f49e665c49de6de ] Enable the uart quirks similar to the earlier SoCs. Let's assume we are likely going to need a k3 specific quirk mask separate from the earlier SoCs, so let's not start changing the revision register mask at this point. Note that SYSC_QUIRK_LEGACY_IDLE will be needed until we can remove the need for pm_runtime_irq_safe() from 8250_omap driver. Reviewed-by: Nishanth Menon Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index ac36b01cf6d5..ddde1427c90c 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1548,6 +1548,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47424e03, 0xffffffff, + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), /* Quirks that need to be set based on the module address */ SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff, From 4f7d853b4590fc20e90dd50e346c02811a8c5b08 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 22 Jul 2023 15:53:53 +0800 Subject: [PATCH 1555/2093] md: raid1: fix potential OOB in raid1_remove_disk() [ Upstream commit 8b0472b50bcf0f19a5119b00a53b63579c8e1e4d ] If rddev->raid_disk is greater than mddev->raid_disks, there will be an out-of-bounds in raid1_remove_disk(). We have already found similar reports as follows: 1) commit d17f744e883b ("md-raid10: fix KASAN warning") 2) commit 1ebc2cec0b7d ("dm raid: fix KASAN warning in raid5_remove_disk") Fix this bug by checking whether the "number" variable is valid. Signed-off-by: Zhang Shurong Reviewed-by: Yu Kuai Link: https://lore.kernel.org/r/tencent_0D24426FAC6A21B69AC0C03CE4143A508F09@qq.com Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/raid1.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ac64c587191b..72303c620174 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1826,6 +1826,10 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct r1conf *conf = mddev->private; int err = 0; int number = rdev->raid_disk; + + if (unlikely(number >= conf->raid_disks)) + goto abort; + struct raid1_info *p = conf->mirrors + number; if (rdev != p->rdev) From 035bc86fbf2b6c2fe8e90c6705d0ca9afa546edc Mon Sep 17 00:00:00 2001 From: Georg Ottinger Date: Tue, 15 Aug 2023 12:03:40 +0200 Subject: [PATCH 1556/2093] ext2: fix datatype of block number in ext2_xattr_set2() [ Upstream commit e88076348425b7d0491c8c98d8732a7df8de7aa3 ] I run a small server that uses external hard drives for backups. The backup software I use uses ext2 filesystems with 4KiB block size and the server is running SELinux and therefore relies on xattr. I recently upgraded the hard drives from 4TB to 12TB models. I noticed that after transferring some TBs I got a filesystem error "Freeing blocks not in datazone - block = 18446744071529317386, count = 1" and the backup process stopped. Trying to fix the fs with e2fsck resulted in a completely corrupted fs. The error probably came from ext2_free_blocks(), and because of the large number 18e19 this problem immediately looked like some kind of integer overflow. Whereas the 4TB fs was about 1e9 blocks, the new 12TB is about 3e9 blocks. So, searching the ext2 code, I came across the line in fs/ext2/xattr.c:745 where ext2_new_block() is called and the resulting block number is stored in the variable block as an int datatype. If a block with a block number greater than INT32_MAX is returned, this variable overflows and the call to sb_getblk() at line fs/ext2/xattr.c:750 fails, then the call to ext2_free_blocks() produces the error. Signed-off-by: Georg Ottinger Signed-off-by: Jan Kara Message-Id: <20230815100340.22121-1-g.ottinger@gmx.at> Signed-off-by: Sasha Levin --- fs/ext2/xattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 641abfa4b718..2f89b1073307 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -744,10 +744,10 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, /* We need to allocate a new block */ ext2_fsblk_t goal = ext2_group_first_block_no(sb, EXT2_I(inode)->i_block_group); - int block = ext2_new_block(inode, goal, &error); + ext2_fsblk_t block = ext2_new_block(inode, goal, &error); if (error) goto cleanup; - ea_idebug(inode, "creating block %d", block); + ea_idebug(inode, "creating block %lu", block); new_bh = sb_getblk(sb, block); if (unlikely(!new_bh)) { From 2f7a36448f51d08d3a83f1514abcca4b680bcd3c Mon Sep 17 00:00:00 2001 From: Andrew Kanner Date: Sat, 1 Jul 2023 17:05:42 +0300 Subject: [PATCH 1557/2093] fs/jfs: prevent double-free in dbUnmount() after failed jfs_remount() [ Upstream commit cade5397e5461295f3cb87880534b6a07cafa427 ] Syzkaller reported the following issue: ================================================================== BUG: KASAN: double-free in slab_free mm/slub.c:3787 [inline] BUG: KASAN: double-free in __kmem_cache_free+0x71/0x110 mm/slub.c:3800 Free of addr ffff888086408000 by task syz-executor.4/12750 [...] Call Trace: [...] kasan_report_invalid_free+0xac/0xd0 mm/kasan/report.c:482 ____kasan_slab_free+0xfb/0x120 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook+0x12e/0x1a0 mm/slub.c:1807 slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x71/0x110 mm/slub.c:3800 dbUnmount+0xf4/0x110 fs/jfs/jfs_dmap.c:264 jfs_umount+0x248/0x3b0 fs/jfs/jfs_umount.c:87 jfs_put_super+0x86/0x190 fs/jfs/super.c:194 generic_shutdown_super+0x130/0x310 fs/super.c:492 kill_block_super+0x79/0xd0 fs/super.c:1386 deactivate_locked_super+0xa7/0xf0 fs/super.c:332 cleanup_mnt+0x494/0x520 fs/namespace.c:1291 task_work_run+0x243/0x300 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop+0x124/0x150 kernel/entry/common.c:171 exit_to_user_mode_prepare+0xb2/0x140 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x26/0x60 kernel/entry/common.c:296 do_syscall_64+0x49/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] Allocated by task 13352: kasan_save_stack mm/kasan/common.c:45 [inline] kasan_set_track+0x3d/0x60 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:371 [inline] __kasan_kmalloc+0x97/0xb0 mm/kasan/common.c:380 kmalloc include/linux/slab.h:580 [inline] dbMount+0x54/0x980 fs/jfs/jfs_dmap.c:164 jfs_mount+0x1dd/0x830 fs/jfs/jfs_mount.c:121 jfs_fill_super+0x590/0xc50 fs/jfs/super.c:556 mount_bdev+0x26c/0x3a0 fs/super.c:1359 legacy_get_tree+0xea/0x180 fs/fs_context.c:610 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 13352: kasan_save_stack mm/kasan/common.c:45 [inline] kasan_set_track+0x3d/0x60 mm/kasan/common.c:52 kasan_save_free_info+0x27/0x40 mm/kasan/generic.c:518 ____kasan_slab_free+0xd6/0x120 mm/kasan/common.c:236 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook+0x12e/0x1a0 mm/slub.c:1807 slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x71/0x110 mm/slub.c:3800 dbUnmount+0xf4/0x110 fs/jfs/jfs_dmap.c:264 jfs_mount_rw+0x545/0x740 fs/jfs/jfs_mount.c:247 jfs_remount+0x3db/0x710 fs/jfs/super.c:454 reconfigure_super+0x3bc/0x7b0 fs/super.c:935 vfs_fsconfig_locked fs/fsopen.c:254 [inline] __do_sys_fsconfig fs/fsopen.c:439 [inline] __se_sys_fsconfig+0xad5/0x1060 fs/fsopen.c:314 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] JFS_SBI(ipbmap->i_sb)->bmap wasn't set to NULL after kfree() in dbUnmount(). Syzkaller uses faultinject to reproduce this KASAN double-free warning. The issue is triggered if either diMount() or dbMount() fail in jfs_remount(), since diUnmount() or dbUnmount() already happened in such a case - they will do double-free on next execution: jfs_umount or jfs_remount. Tested on both upstream and jfs-next by syzkaller. Reported-and-tested-by: syzbot+6a93efb725385bc4b2e9@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000471f2d05f1ce8bad@google.com/T/ Link: https://syzkaller.appspot.com/bug?extid=6a93efb725385bc4b2e9 Signed-off-by: Andrew Kanner Signed-off-by: Dave Kleikamp Signed-off-by: Sasha Levin --- fs/jfs/jfs_dmap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index bd4ef43b0203..e9d075cbd71a 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -269,6 +269,7 @@ int dbUnmount(struct inode *ipbmap, int mounterror) /* free the memory for the in-memory bmap. */ kfree(bmp); + JFS_SBI(ipbmap->i_sb)->bmap = NULL; return (0); } From 4de3a603010e0ca334487de24c6aab0777b7f808 Mon Sep 17 00:00:00 2001 From: Liu Shixin via Jfs-discussion Date: Thu, 1 Dec 2022 20:46:28 +0800 Subject: [PATCH 1558/2093] jfs: fix invalid free of JFS_IP(ipimap)->i_imap in diUnmount [ Upstream commit 6e2bda2c192d0244b5a78b787ef20aa10cb319b7 ] syzbot found an invalid-free in diUnmount: BUG: KASAN: double-free in slab_free mm/slub.c:3661 [inline] BUG: KASAN: double-free in __kmem_cache_free+0x71/0x110 mm/slub.c:3674 Free of addr ffff88806f410000 by task syz-executor131/3632 CPU: 0 PID: 3632 Comm: syz-executor131 Not tainted 6.1.0-rc7-syzkaller-00012-gca57f02295f1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x28e lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:284 print_report+0x107/0x1f0 mm/kasan/report.c:395 kasan_report_invalid_free+0xac/0xd0 mm/kasan/report.c:460 ____kasan_slab_free+0xfb/0x120 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1724 [inline] slab_free_freelist_hook+0x12e/0x1a0 mm/slub.c:1750 slab_free mm/slub.c:3661 [inline] __kmem_cache_free+0x71/0x110 mm/slub.c:3674 diUnmount+0xef/0x100 fs/jfs/jfs_imap.c:195 jfs_umount+0x108/0x370 fs/jfs/jfs_umount.c:63 jfs_put_super+0x86/0x190 fs/jfs/super.c:194 generic_shutdown_super+0x130/0x310 fs/super.c:492 kill_block_super+0x79/0xd0 fs/super.c:1428 deactivate_locked_super+0xa7/0xf0 fs/super.c:332 cleanup_mnt+0x494/0x520 fs/namespace.c:1186 task_work_run+0x243/0x300 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x664/0x2070 kernel/exit.c:820 do_group_exit+0x1fd/0x2b0 kernel/exit.c:950 __do_sys_exit_group kernel/exit.c:961 [inline] __se_sys_exit_group kernel/exit.c:959 [inline] __x64_sys_exit_group+0x3b/0x40 kernel/exit.c:959 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] JFS_IP(ipimap)->i_imap is not setting to NULL after free in diUnmount. If jfs_remount() free JFS_IP(ipimap)->i_imap but then failed at diMount(). JFS_IP(ipimap)->i_imap will be freed once again. Fix this problem by setting JFS_IP(ipimap)->i_imap to NULL after free. Reported-by: syzbot+90a11e6b1e810785c6ff@syzkaller.appspotmail.com Signed-off-by: Liu Shixin Signed-off-by: Dave Kleikamp Signed-off-by: Sasha Levin --- fs/jfs/jfs_imap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 799d3837e7c2..4899663996d8 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -193,6 +193,7 @@ int diUnmount(struct inode *ipimap, int mounterror) * free in-memory control structure */ kfree(imap); + JFS_IP(ipimap)->i_imap = NULL; return (0); } From 09066c19d9457c208f94c652577abe42b28dd026 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 31 Jul 2023 12:55:01 +0100 Subject: [PATCH 1559/2093] PCI: dwc: Provide deinit callback for i.MX [ Upstream commit fc8b24c28bec19fc0621d108b9ee81ddfdedb25a ] The i.MX integration for the DesignWare PCI controller has a _host_exit() operation which undoes everything that the _host_init() operation does but does not wire this up as the host_deinit callback for the core, or call it in any path other than suspend. This means that if we ever unwind the initial probe of the device, for example because it fails, the regulator core complains that the regulators for the device were left enabled: imx6q-pcie 33800000.pcie: iATU: unroll T, 4 ob, 4 ib, align 64K, limit 16G imx6q-pcie 33800000.pcie: Phy link never came up imx6q-pcie 33800000.pcie: Phy link never came up imx6q-pcie: probe of 33800000.pcie failed with error -110 ------------[ cut here ]------------ WARNING: CPU: 2 PID: 46 at drivers/regulator/core.c:2396 _regulator_put+0x110/0x128 Wire up the callback so that the core can clean up after itself. Link: https://lore.kernel.org/r/20230731-pci-imx-regulator-cleanup-v2-1-fc8fa5c9893d@kernel.org Tested-by: Fabio Estevam Signed-off-by: Mark Brown Signed-off-by: Lorenzo Pieralisi Reviewed-by: Richard Zhu Acked-by: Manivannan Sadhasivam Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pci-imx6.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 47db2d20568e..388354a8e31c 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -999,6 +999,7 @@ static void imx6_pcie_host_exit(struct dw_pcie_rp *pp) static const struct dw_pcie_host_ops imx6_pcie_host_ops = { .host_init = imx6_pcie_host_init, + .host_deinit = imx6_pcie_host_exit, }; static const struct dw_pcie_ops dw_pcie_ops = { From ee378f45a70d09b51373ba495d30d99ef12219c1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A5rten=20Lindahl?= Date: Tue, 8 Aug 2023 09:37:32 +0100 Subject: [PATCH 1560/2093] ARM: 9317/1: kexec: Make smp stop calls asynchronous MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8922ba71c969d2a0c01a94372a71477d879470de ] If a panic is triggered by a hrtimer interrupt all online cpus will be notified and set offline. But as highlighted by commit 19dbdcb8039c ("smp: Warn on function calls from softirq context") this call should not be made synchronous with disabled interrupts: softdog: Initiating panic Kernel panic - not syncing: Software Watchdog Timer expired WARNING: CPU: 1 PID: 0 at kernel/smp.c:753 smp_call_function_many_cond unwind_backtrace: show_stack dump_stack_lvl __warn warn_slowpath_fmt smp_call_function_many_cond smp_call_function crash_smp_send_stop.part.0 machine_crash_shutdown __crash_kexec panic softdog_fire __hrtimer_run_queues hrtimer_interrupt Make the smp call for machine_crash_nonpanic_core() asynchronous. Signed-off-by: Mårten Lindahl Signed-off-by: Russell King (Oracle) Signed-off-by: Sasha Levin --- arch/arm/kernel/machine_kexec.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index f567032a09c0..6d1938d1b4df 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -92,16 +92,28 @@ void machine_crash_nonpanic_core(void *unused) } } +static DEFINE_PER_CPU(call_single_data_t, cpu_stop_csd) = + CSD_INIT(machine_crash_nonpanic_core, NULL); + void crash_smp_send_stop(void) { static int cpus_stopped; unsigned long msecs; + call_single_data_t *csd; + int cpu, this_cpu = raw_smp_processor_id(); if (cpus_stopped) return; atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); - smp_call_function(machine_crash_nonpanic_core, NULL, false); + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + + csd = &per_cpu(cpu_stop_csd, cpu); + smp_call_function_single_async(cpu, csd); + } + msecs = 1000; /* Wait at most a second for the other cpus to stop */ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { mdelay(1); From 96f27ff732208dce6468016e7a7d5032bd1bfc23 Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Thu, 10 Nov 2022 09:19:29 +0800 Subject: [PATCH 1561/2093] powerpc/pseries: fix possible memory leak in ibmebus_bus_init() [ Upstream commit afda85b963c12947e298ad85d757e333aa40fd74 ] If device_register() returns error in ibmebus_bus_init(), name of kobject which is allocated in dev_set_name() called in device_add() is leaked. As comment of device_add() says, it should call put_device() to drop the reference count that was set in device_initialize() when it fails, so the name can be freed in kobject_cleanup(). Signed-off-by: ruanjinjie Signed-off-by: Michael Ellerman Link: https://msgid.link/20221110011929.3709774-1-ruanjinjie@huawei.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/ibmebus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index a870cada7acd..ed5fc70b7353 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -455,6 +455,7 @@ static int __init ibmebus_bus_init(void) if (err) { printk(KERN_WARNING "%s: device_register returned %i\n", __func__, err); + put_device(&ibmebus_bus_device); bus_unregister(&ibmebus_bus_type); return err; From 9318c3ae155bc902953a50d0f667453f5c4eb269 Mon Sep 17 00:00:00 2001 From: Nirmal Patel Date: Thu, 10 Aug 2023 17:50:29 -0400 Subject: [PATCH 1562/2093] PCI: vmd: Disable bridge window for domain reset [ Upstream commit f73eedc90bf73d48e8368e6b0b4ad76a7fffaef7 ] During domain reset process vmd_domain_reset() clears PCI configuration space of VMD root ports. But certain platform has observed following errors and failed to boot. ... DMAR: VT-d detected Invalidation Queue Error: Reason f DMAR: VT-d detected Invalidation Time-out Error: SID ffff DMAR: VT-d detected Invalidation Completion Error: SID ffff DMAR: QI HEAD: UNKNOWN qw0 = 0x0, qw1 = 0x0 DMAR: QI PRIOR: UNKNOWN qw0 = 0x0, qw1 = 0x0 DMAR: Invalidation Time-out Error (ITE) cleared The root cause is that memset_io() clears prefetchable memory base/limit registers and prefetchable base/limit 32 bits registers sequentially. This seems to be enabling prefetchable memory if the device disabled prefetchable memory originally. Here is an example (before memset_io()): PCI configuration space for 10000:00:00.0: 86 80 30 20 06 00 10 00 04 00 04 06 00 00 01 00 00 00 00 00 00 00 00 00 00 01 01 00 00 00 00 20 00 00 00 00 01 00 01 00 ff ff ff ff 75 05 00 00 ... So, prefetchable memory is ffffffff00000000-575000fffff, which is disabled. When memset_io() clears prefetchable base 32 bits register, the prefetchable memory becomes 0000000000000000-575000fffff, which is enabled and incorrect. Here is the quote from section 7.5.1.3.9 of PCI Express Base 6.0 spec: The Prefetchable Memory Limit register must be programmed to a smaller value than the Prefetchable Memory Base register if there is no prefetchable memory on the secondary side of the bridge. This is believed to be the reason for the failure and in addition the sequence of operation in vmd_domain_reset() is not following the PCIe specs. Disable the bridge window by executing a sequence of operations borrowed from pci_disable_bridge_window() and pci_setup_bridge_io(), that comply with the PCI specifications. Link: https://lore.kernel.org/r/20230810215029.1177379-1-nirmal.patel@linux.intel.com Signed-off-by: Nirmal Patel Signed-off-by: Lorenzo Pieralisi Signed-off-by: Sasha Levin --- drivers/pci/controller/vmd.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index d1eb17e3f147..d4c9b888a79d 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -526,8 +526,23 @@ static void vmd_domain_reset(struct vmd_dev *vmd) PCI_CLASS_BRIDGE_PCI)) continue; - memset_io(base + PCI_IO_BASE, 0, - PCI_ROM_ADDRESS1 - PCI_IO_BASE); + /* + * Temporarily disable the I/O range before updating + * PCI_IO_BASE. + */ + writel(0x0000ffff, base + PCI_IO_BASE_UPPER16); + /* Update lower 16 bits of I/O base/limit */ + writew(0x00f0, base + PCI_IO_BASE); + /* Update upper 16 bits of I/O base/limit */ + writel(0, base + PCI_IO_BASE_UPPER16); + + /* MMIO Base/Limit */ + writel(0x0000fff0, base + PCI_MEMORY_BASE); + + /* Prefetchable MMIO Base/Limit */ + writel(0, base + PCI_PREF_LIMIT_UPPER32); + writel(0x0000fff0, base + PCI_PREF_MEMORY_BASE); + writel(0xffffffff, base + PCI_PREF_BASE_UPPER32); } } } From b78796126f80268dd279309dd2c4f315e3fe9328 Mon Sep 17 00:00:00 2001 From: Yong-Xuan Wang Date: Mon, 7 Aug 2023 05:56:21 +0000 Subject: [PATCH 1563/2093] PCI: fu740: Set the number of MSI vectors [ Upstream commit 551a60e1225e71fff8efd9390204c505b0870e0f ] The iMSI-RX module of the DW PCIe controller provides multiple sets of MSI_CTRL_INT_i_* registers, and each set is capable of handling 32 MSI interrupts. However, the fu740 PCIe controller driver only enabled one set of MSI_CTRL_INT_i_* registers, as the total number of supported interrupts was not specified. Set the supported number of MSI vectors to enable all the MSI_CTRL_INT_i_* registers on the fu740 PCIe core, allowing the system to fully utilize the available MSI interrupts. Link: https://lore.kernel.org/r/20230807055621.2431-1-yongxuan.wang@sifive.com Signed-off-by: Yong-Xuan Wang Signed-off-by: Lorenzo Pieralisi Reviewed-by: Serge Semin Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-fu740.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c index 0c90583c078b..1e9b44b8bba4 100644 --- a/drivers/pci/controller/dwc/pcie-fu740.c +++ b/drivers/pci/controller/dwc/pcie-fu740.c @@ -299,6 +299,7 @@ static int fu740_pcie_probe(struct platform_device *pdev) pci->dev = dev; pci->ops = &dw_pcie_ops; pci->pp.ops = &fu740_pcie_host_ops; + pci->pp.num_vectors = MAX_MSI_IRQS; /* SiFive specific region: mgmt */ afp->mgmt_base = devm_platform_ioremap_resource_byname(pdev, "mgmt"); From 8ba9d91c8f21f070af2049f114c206a8f2d5c71e Mon Sep 17 00:00:00 2001 From: Lu Hongfei Date: Tue, 30 May 2023 18:17:18 +0800 Subject: [PATCH 1564/2093] media: mdp3: Fix resource leaks in of_find_device_by_node [ Upstream commit 35ca8ce495366909b4c2e701d1356570dd40c4e2 ] Use put_device to release the object get through of_find_device_by_node, avoiding resource leaks. Signed-off-by: Lu Hongfei Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c index 7bc05f42a23c..9a3f46c1f6ba 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c @@ -775,11 +775,13 @@ static int mdp_get_subsys_id(struct device *dev, struct device_node *node, ret = cmdq_dev_get_client_reg(&comp_pdev->dev, &cmdq_reg, index); if (ret != 0) { dev_err(&comp_pdev->dev, "cmdq_dev_get_subsys fail!\n"); + put_device(&comp_pdev->dev); return -EINVAL; } comp->subsys_id = cmdq_reg.subsys; dev_dbg(&comp_pdev->dev, "subsys id=%d\n", cmdq_reg.subsys); + put_device(&comp_pdev->dev); return 0; } From 0143f282b15f7cedc0392ea10050fb6000fd16e6 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Thu, 6 Jul 2023 00:06:54 +0800 Subject: [PATCH 1565/2093] media: dvb-usb-v2: af9035: Fix null-ptr-deref in af9035_i2c_master_xfer [ Upstream commit 7bf744f2de0a848fb1d717f5831b03db96feae89 ] In af9035_i2c_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach af9035_i2c_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Signed-off-by: Zhang Shurong Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin [ moved variable declaration to fix build issues in older kernels - gregkh ] Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/dvb-usb-v2/af9035.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c index 1e9c8d01523b..cd6f5374414d 100644 --- a/drivers/media/usb/dvb-usb-v2/af9035.c +++ b/drivers/media/usb/dvb-usb-v2/af9035.c @@ -270,6 +270,7 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap, struct dvb_usb_device *d = i2c_get_adapdata(adap); struct state *state = d_to_priv(d); int ret; + u32 reg; if (mutex_lock_interruptible(&d->i2c_mutex) < 0) return -EAGAIN; @@ -322,8 +323,10 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap, ret = -EOPNOTSUPP; } else if ((msg[0].addr == state->af9033_i2c_addr[0]) || (msg[0].addr == state->af9033_i2c_addr[1])) { + if (msg[0].len < 3 || msg[1].len < 1) + return -EOPNOTSUPP; /* demod access via firmware interface */ - u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | + reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | msg[0].buf[2]; if (msg[0].addr == state->af9033_i2c_addr[1]) @@ -381,17 +384,16 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap, ret = -EOPNOTSUPP; } else if ((msg[0].addr == state->af9033_i2c_addr[0]) || (msg[0].addr == state->af9033_i2c_addr[1])) { + if (msg[0].len < 3) + return -EOPNOTSUPP; /* demod access via firmware interface */ - u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | + reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 | msg[0].buf[2]; if (msg[0].addr == state->af9033_i2c_addr[1]) reg |= 0x100000; - ret = (msg[0].len >= 3) ? af9035_wr_regs(d, reg, - &msg[0].buf[3], - msg[0].len - 3) - : -EOPNOTSUPP; + ret = af9035_wr_regs(d, reg, &msg[0].buf[3], msg[0].len - 3); } else { /* I2C write */ u8 buf[MAX_XFER_SIZE]; From 08dfcbd03b2b7f918c4f87c6ff637054e510df74 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 8 Jul 2023 18:22:52 +0800 Subject: [PATCH 1566/2093] media: dw2102: Fix null-ptr-deref in dw2102_i2c_transfer() [ Upstream commit 5ae544d94abc8ff77b1b9bf8774def3fa5689b5b ] In dw2102_i2c_transfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach dw2102_i2c_transfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 950e252cb469 ("[media] dw2102: limit messages to buffer size") Signed-off-by: Zhang Shurong Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/dw2102.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 8747960e6146..356fc728d59a 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -128,6 +128,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], switch (num) { case 2: + if (msg[0].len < 1) { + num = -EOPNOTSUPP; + break; + } /* read stv0299 register */ value = msg[0].buf[0];/* register */ for (i = 0; i < msg[1].len; i++) { @@ -139,6 +143,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], case 1: switch (msg[0].addr) { case 0x68: + if (msg[0].len < 2) { + num = -EOPNOTSUPP; + break; + } /* write to stv0299 register */ buf6[0] = 0x2a; buf6[1] = msg[0].buf[0]; @@ -148,6 +156,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], break; case 0x60: if (msg[0].flags == 0) { + if (msg[0].len < 4) { + num = -EOPNOTSUPP; + break; + } /* write to tuner pll */ buf6[0] = 0x2c; buf6[1] = 5; @@ -159,6 +171,10 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], dw210x_op_rw(d->udev, 0xb2, 0, 0, buf6, 7, DW210X_WRITE_MSG); } else { + if (msg[0].len < 1) { + num = -EOPNOTSUPP; + break; + } /* read from tuner */ dw210x_op_rw(d->udev, 0xb5, 0, 0, buf6, 1, DW210X_READ_MSG); @@ -166,12 +182,20 @@ static int dw2102_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], } break; case (DW2102_RC_QUERY): + if (msg[0].len < 2) { + num = -EOPNOTSUPP; + break; + } dw210x_op_rw(d->udev, 0xb8, 0, 0, buf6, 2, DW210X_READ_MSG); msg[0].buf[0] = buf6[0]; msg[0].buf[1] = buf6[1]; break; case (DW2102_VOLTAGE_CTRL): + if (msg[0].len < 1) { + num = -EOPNOTSUPP; + break; + } buf6[0] = 0x30; buf6[1] = msg[0].buf[0]; dw210x_op_rw(d->udev, 0xb2, 0, 0, From abb6fd93e05e80668d2317fe1110bc99b05034c3 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 8 Jul 2023 23:24:11 +0800 Subject: [PATCH 1567/2093] media: af9005: Fix null-ptr-deref in af9005_i2c_xfer [ Upstream commit f4ee84f27625ce1fdf41e8483fa0561a1b837d10 ] In af9005_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach af9005_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Signed-off-by: Zhang Shurong Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/af9005.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c index 0827bf3d4e8c..13604e6acdb8 100644 --- a/drivers/media/usb/dvb-usb/af9005.c +++ b/drivers/media/usb/dvb-usb/af9005.c @@ -422,6 +422,10 @@ static int af9005_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], if (ret == 0) ret = 2; } else { + if (msg[0].len < 2) { + ret = -EOPNOTSUPP; + goto unlock; + } /* write one or more registers */ reg = msg[0].buf[0]; addr = msg[0].addr; @@ -431,6 +435,7 @@ static int af9005_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = 1; } +unlock: mutex_unlock(&d->i2c_mutex); return ret; } From 14b94154a72388b57221a2a73795c0ea61a95373 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sun, 9 Jul 2023 00:02:20 +0800 Subject: [PATCH 1568/2093] media: anysee: fix null-ptr-deref in anysee_master_xfer [ Upstream commit c30411266fd67ea3c02a05c157231654d5a3bdc9 ] In anysee_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach anysee_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Signed-off-by: Zhang Shurong Signed-off-by: Hans Verkuil [hverkuil: add spaces around +] Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/anysee.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c index aa45b5d263f6..a1235d0cce92 100644 --- a/drivers/media/usb/dvb-usb-v2/anysee.c +++ b/drivers/media/usb/dvb-usb-v2/anysee.c @@ -202,7 +202,7 @@ static int anysee_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { - if (msg[i].len > 2 || msg[i+1].len > 60) { + if (msg[i].len != 2 || msg[i + 1].len > 60) { ret = -EOPNOTSUPP; break; } From 6ab7ea4e17d6a605d05308adf8f3408924770cba Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sun, 9 Jul 2023 00:28:17 +0800 Subject: [PATCH 1569/2093] media: az6007: Fix null-ptr-deref in az6007_i2c_xfer() [ Upstream commit 1047f9343011f2cedc73c64829686206a7e9fc3f ] In az6007_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach az6007_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Signed-off-by: Zhang Shurong Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/az6007.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/az6007.c b/drivers/media/usb/dvb-usb-v2/az6007.c index 7524c90f5da6..6cbfe75791c2 100644 --- a/drivers/media/usb/dvb-usb-v2/az6007.c +++ b/drivers/media/usb/dvb-usb-v2/az6007.c @@ -788,6 +788,10 @@ static int az6007_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], if (az6007_xfer_debug) printk(KERN_DEBUG "az6007: I2C W addr=0x%x len=%d\n", addr, msgs[i].len); + if (msgs[i].len < 1) { + ret = -EIO; + goto err; + } req = AZ6007_I2C_WR; index = msgs[i].buf[0]; value = addr | (1 << 8); @@ -802,6 +806,10 @@ static int az6007_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], if (az6007_xfer_debug) printk(KERN_DEBUG "az6007: I2C R addr=0x%x len=%d\n", addr, msgs[i].len); + if (msgs[i].len < 1) { + ret = -EIO; + goto err; + } req = AZ6007_I2C_RD; index = msgs[i].buf[0]; value = addr; From dfcd3c010209927b9f45b860f046635dc32e32e1 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Mon, 10 Jul 2023 13:32:13 +0800 Subject: [PATCH 1570/2093] media: dvb-usb-v2: gl861: Fix null-ptr-deref in gl861_i2c_master_xfer [ Upstream commit b97719a66970601cd3151a3e2020f4454a1c4ff6 ] In gl861_i2c_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach gl861_i2c_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Signed-off-by: Zhang Shurong Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/gl861.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb-v2/gl861.c b/drivers/media/usb/dvb-usb-v2/gl861.c index 0c434259c36f..c71e7b93476d 100644 --- a/drivers/media/usb/dvb-usb-v2/gl861.c +++ b/drivers/media/usb/dvb-usb-v2/gl861.c @@ -120,7 +120,7 @@ static int gl861_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } else if (num == 2 && !(msg[0].flags & I2C_M_RD) && (msg[1].flags & I2C_M_RD)) { /* I2C write + read */ - if (msg[0].len > 1 || msg[1].len > sizeof(ctx->buf)) { + if (msg[0].len != 1 || msg[1].len > sizeof(ctx->buf)) { ret = -EOPNOTSUPP; goto err; } From b2a019ec8b338683f66f5a339a010d8cb554c51c Mon Sep 17 00:00:00 2001 From: Justin Tee Date: Wed, 12 Jul 2023 11:05:18 -0700 Subject: [PATCH 1571/2093] scsi: lpfc: Abort outstanding ELS cmds when mailbox timeout error is detected [ Upstream commit 089ea22e374aa20043e72243c47b5867d5419d38 ] A mailbox timeout error usually indicates something has gone wrong, and a follow up reset of the HBA is a typical recovery mechanism. Introduce a MBX_TMO_ERR flag to detect such cases and have lpfc_els_flush_cmd abort ELS commands if the MBX_TMO_ERR flag condition was set. This ensures all of the registered SGL resources meant for ELS traffic are not leaked after an HBA reset. Signed-off-by: Justin Tee Link: https://lore.kernel.org/r/20230712180522.112722-9-justintee8345@gmail.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc.h | 1 + drivers/scsi/lpfc/lpfc_els.c | 25 ++++++++++++++++++------- drivers/scsi/lpfc/lpfc_init.c | 20 +++++++++++++++++--- drivers/scsi/lpfc/lpfc_sli.c | 8 +++++++- 4 files changed, 43 insertions(+), 11 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 9ad233b40a9e..664ac3069c4b 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -895,6 +895,7 @@ enum lpfc_irq_chann_mode { enum lpfc_hba_bit_flags { FABRIC_COMANDS_BLOCKED, HBA_PCI_ERR, + MBX_TMO_ERR, }; struct lpfc_hba { diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 43ebb41ded59..6b5ce9869e6b 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -9410,11 +9410,13 @@ void lpfc_els_flush_cmd(struct lpfc_vport *vport) { LIST_HEAD(abort_list); + LIST_HEAD(cancel_list); struct lpfc_hba *phba = vport->phba; struct lpfc_sli_ring *pring; struct lpfc_iocbq *tmp_iocb, *piocb; u32 ulp_command; unsigned long iflags = 0; + bool mbx_tmo_err; lpfc_fabric_abort_vport(vport); @@ -9436,15 +9438,16 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) if (phba->sli_rev == LPFC_SLI_REV4) spin_lock(&pring->ring_lock); + mbx_tmo_err = test_bit(MBX_TMO_ERR, &phba->bit_flags); /* First we need to issue aborts to outstanding cmds on txcmpl */ list_for_each_entry_safe(piocb, tmp_iocb, &pring->txcmplq, list) { - if (piocb->cmd_flag & LPFC_IO_LIBDFC) + if (piocb->cmd_flag & LPFC_IO_LIBDFC && !mbx_tmo_err) continue; if (piocb->vport != vport) continue; - if (piocb->cmd_flag & LPFC_DRIVER_ABORTED) + if (piocb->cmd_flag & LPFC_DRIVER_ABORTED && !mbx_tmo_err) continue; /* On the ELS ring we can have ELS_REQUESTs or @@ -9463,8 +9466,8 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) */ if (phba->link_state == LPFC_LINK_DOWN) piocb->cmd_cmpl = lpfc_cmpl_els_link_down; - } - if (ulp_command == CMD_GEN_REQUEST64_CR) + } else if (ulp_command == CMD_GEN_REQUEST64_CR || + mbx_tmo_err) list_add_tail(&piocb->dlist, &abort_list); } @@ -9476,11 +9479,19 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) list_for_each_entry_safe(piocb, tmp_iocb, &abort_list, dlist) { spin_lock_irqsave(&phba->hbalock, iflags); list_del_init(&piocb->dlist); - lpfc_sli_issue_abort_iotag(phba, pring, piocb, NULL); + if (mbx_tmo_err) + list_move_tail(&piocb->list, &cancel_list); + else + lpfc_sli_issue_abort_iotag(phba, pring, piocb, NULL); + spin_unlock_irqrestore(&phba->hbalock, iflags); } - /* Make sure HBA is alive */ - lpfc_issue_hb_tmo(phba); + if (!list_empty(&cancel_list)) + lpfc_sli_cancel_iocbs(phba, &cancel_list, IOSTAT_LOCAL_REJECT, + IOERR_SLI_ABORTED); + else + /* Make sure HBA is alive */ + lpfc_issue_hb_tmo(phba); if (!list_empty(&abort_list)) lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index d54fd153cb11..f59de61803dc 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -7563,6 +7563,8 @@ lpfc_disable_pci_dev(struct lpfc_hba *phba) void lpfc_reset_hba(struct lpfc_hba *phba) { + int rc = 0; + /* If resets are disabled then set error state and return. */ if (!phba->cfg_enable_hba_reset) { phba->link_state = LPFC_HBA_ERROR; @@ -7573,13 +7575,25 @@ lpfc_reset_hba(struct lpfc_hba *phba) if (phba->sli.sli_flag & LPFC_SLI_ACTIVE) { lpfc_offline_prep(phba, LPFC_MBX_WAIT); } else { + if (test_bit(MBX_TMO_ERR, &phba->bit_flags)) { + /* Perform a PCI function reset to start from clean */ + rc = lpfc_pci_function_reset(phba); + lpfc_els_flush_all_cmd(phba); + } lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); lpfc_sli_flush_io_rings(phba); } lpfc_offline(phba); - lpfc_sli_brdrestart(phba); - lpfc_online(phba); - lpfc_unblock_mgmt_io(phba); + clear_bit(MBX_TMO_ERR, &phba->bit_flags); + if (unlikely(rc)) { + lpfc_printf_log(phba, KERN_ERR, LOG_SLI, + "8888 PCI function reset failed rc %x\n", + rc); + } else { + lpfc_sli_brdrestart(phba); + lpfc_online(phba); + lpfc_unblock_mgmt_io(phba); + } } /** diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index b44bb3ae22ad..427a6ac803e5 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -3919,6 +3919,8 @@ void lpfc_poll_eratt(struct timer_list *t) uint64_t sli_intr, cnt; phba = from_timer(phba, t, eratt_poll); + if (!(phba->hba_flag & HBA_SETUP)) + return; /* Here we will also keep track of interrupts per sec of the hba */ sli_intr = phba->sli.slistat.sli_intr; @@ -7712,7 +7714,9 @@ lpfc_sli4_repost_sgl_list(struct lpfc_hba *phba, spin_unlock_irq(&phba->hbalock); } else { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "3161 Failure to post sgl to port.\n"); + "3161 Failure to post sgl to port,status %x " + "blkcnt %d totalcnt %d postcnt %d\n", + status, block_cnt, total_cnt, post_cnt); return -EIO; } @@ -8495,6 +8499,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) spin_unlock_irq(&phba->hbalock); } } + phba->hba_flag &= ~HBA_SETUP; lpfc_sli4_dip(phba); @@ -9317,6 +9322,7 @@ lpfc_mbox_timeout_handler(struct lpfc_hba *phba) * would get IOCB_ERROR from lpfc_sli_issue_iocb, allowing * it to fail all outstanding SCSI IO. */ + set_bit(MBX_TMO_ERR, &phba->bit_flags); spin_lock_irq(&phba->pport->work_port_lock); phba->pport->work_port_events &= ~WORKER_MBOX_TMO; spin_unlock_irq(&phba->pport->work_port_lock); From 257092cb544c7843376b3e161f789e666ef06c98 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 20 Jul 2023 08:20:51 +0200 Subject: [PATCH 1572/2093] media: tuners: qt1010: replace BUG_ON with a regular error [ Upstream commit ee630b29ea44d1851bb6c903f400956604834463 ] BUG_ON is unnecessary here, and in addition it confuses smatch. Replacing this with an error return help resolve this smatch warning: drivers/media/tuners/qt1010.c:350 qt1010_init() error: buffer overflow 'i2c_data' 34 <= 34 Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/tuners/qt1010.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/media/tuners/qt1010.c b/drivers/media/tuners/qt1010.c index 60931367b82c..48fc79cd4027 100644 --- a/drivers/media/tuners/qt1010.c +++ b/drivers/media/tuners/qt1010.c @@ -345,11 +345,12 @@ static int qt1010_init(struct dvb_frontend *fe) else valptr = &tmpval; - BUG_ON(i >= ARRAY_SIZE(i2c_data) - 1); - - err = qt1010_init_meas1(priv, i2c_data[i+1].reg, - i2c_data[i].reg, - i2c_data[i].val, valptr); + if (i >= ARRAY_SIZE(i2c_data) - 1) + err = -EIO; + else + err = qt1010_init_meas1(priv, i2c_data[i + 1].reg, + i2c_data[i].reg, + i2c_data[i].val, valptr); i++; break; } From 96a0bf5827e7035d5121560952cd047b92fb4a40 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 21 Jul 2023 10:23:42 +0200 Subject: [PATCH 1573/2093] media: pci: cx23885: replace BUG with error return [ Upstream commit 2e1796fd4904fdd6062a8e4589778ea899ea0c8d ] It was completely unnecessary to use BUG in buffer_prepare(). Just replace it with an error return. This also fixes a smatch warning: drivers/media/pci/cx23885/cx23885-video.c:422 buffer_prepare() error: uninitialized symbol 'ret'. Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/pci/cx23885/cx23885-video.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c index 671fc0588e43..9af2c5596121 100644 --- a/drivers/media/pci/cx23885/cx23885-video.c +++ b/drivers/media/pci/cx23885/cx23885-video.c @@ -413,7 +413,7 @@ static int buffer_prepare(struct vb2_buffer *vb) dev->height >> 1); break; default: - BUG(); + return -EINVAL; /* should not happen */ } dprintk(2, "[%p/%d] buffer_init - %dx%d %dbpp 0x%08x - dma=0x%08lx\n", buf, buf->vb.vb2_buf.index, From bbc9c3652708108738009e096d608ece3cd9fa8a Mon Sep 17 00:00:00 2001 From: Xiaolei Wang Date: Fri, 16 Jun 2023 10:19:51 +0800 Subject: [PATCH 1574/2093] usb: cdns3: Put the cdns set active part outside the spin lock [ Upstream commit 2319b9c87fe243327285f2fefd7374ffd75a65fc ] The device may be scheduled during the resume process, so this cannot appear in atomic operations. Since pm_runtime_set_active will resume suppliers, put set active outside the spin lock, which is only used to protect the struct cdns data structure, otherwise the kernel will report the following warning: BUG: sleeping function called from invalid context at drivers/base/power/runtime.c:1163 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 651, name: sh preempt_count: 1, expected: 0 RCU nest depth: 0, expected: 0 CPU: 0 PID: 651 Comm: sh Tainted: G WC 6.1.20 #1 Hardware name: Freescale i.MX8QM MEK (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 show_stack+0x18/0x30 dump_stack_lvl+0x64/0x80 dump_stack+0x1c/0x38 __might_resched+0x1fc/0x240 __might_sleep+0x68/0xc0 __pm_runtime_resume+0x9c/0xe0 rpm_get_suppliers+0x68/0x1b0 __pm_runtime_set_status+0x298/0x560 cdns_resume+0xb0/0x1c0 cdns3_controller_resume.isra.0+0x1e0/0x250 cdns3_plat_resume+0x28/0x40 Signed-off-by: Xiaolei Wang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20230616021952.1025854-1-xiaolei.wang@windriver.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/cdns3/cdns3-plat.c | 3 ++- drivers/usb/cdns3/cdnsp-pci.c | 3 ++- drivers/usb/cdns3/core.c | 15 +++++++++++---- drivers/usb/cdns3/core.h | 7 +++++-- 4 files changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/usb/cdns3/cdns3-plat.c b/drivers/usb/cdns3/cdns3-plat.c index 2bc5d094548b..726b2e4f67e4 100644 --- a/drivers/usb/cdns3/cdns3-plat.c +++ b/drivers/usb/cdns3/cdns3-plat.c @@ -256,9 +256,10 @@ static int cdns3_controller_resume(struct device *dev, pm_message_t msg) cdns3_set_platform_suspend(cdns->dev, false, false); spin_lock_irqsave(&cdns->lock, flags); - cdns_resume(cdns, !PMSG_IS_AUTO(msg)); + cdns_resume(cdns); cdns->in_lpm = false; spin_unlock_irqrestore(&cdns->lock, flags); + cdns_set_active(cdns, !PMSG_IS_AUTO(msg)); if (cdns->wakeup_pending) { cdns->wakeup_pending = false; enable_irq(cdns->wakeup_irq); diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c index 29f433c5a6f3..a85db23fa19f 100644 --- a/drivers/usb/cdns3/cdnsp-pci.c +++ b/drivers/usb/cdns3/cdnsp-pci.c @@ -210,8 +210,9 @@ static int __maybe_unused cdnsp_pci_resume(struct device *dev) int ret; spin_lock_irqsave(&cdns->lock, flags); - ret = cdns_resume(cdns, 1); + ret = cdns_resume(cdns); spin_unlock_irqrestore(&cdns->lock, flags); + cdns_set_active(cdns, 1); return ret; } diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index dbcdf3b24b47..7b20d2d5c262 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -522,9 +522,8 @@ int cdns_suspend(struct cdns *cdns) } EXPORT_SYMBOL_GPL(cdns_suspend); -int cdns_resume(struct cdns *cdns, u8 set_active) +int cdns_resume(struct cdns *cdns) { - struct device *dev = cdns->dev; enum usb_role real_role; bool role_changed = false; int ret = 0; @@ -556,15 +555,23 @@ int cdns_resume(struct cdns *cdns, u8 set_active) if (cdns->roles[cdns->role]->resume) cdns->roles[cdns->role]->resume(cdns, cdns_power_is_lost(cdns)); + return 0; +} +EXPORT_SYMBOL_GPL(cdns_resume); + +void cdns_set_active(struct cdns *cdns, u8 set_active) +{ + struct device *dev = cdns->dev; + if (set_active) { pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); } - return 0; + return; } -EXPORT_SYMBOL_GPL(cdns_resume); +EXPORT_SYMBOL_GPL(cdns_set_active); #endif /* CONFIG_PM_SLEEP */ MODULE_AUTHOR("Peter Chen "); diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h index 2d332a788871..4a4dbc2c1561 100644 --- a/drivers/usb/cdns3/core.h +++ b/drivers/usb/cdns3/core.h @@ -125,10 +125,13 @@ int cdns_init(struct cdns *cdns); int cdns_remove(struct cdns *cdns); #ifdef CONFIG_PM_SLEEP -int cdns_resume(struct cdns *cdns, u8 set_active); +int cdns_resume(struct cdns *cdns); int cdns_suspend(struct cdns *cdns); +void cdns_set_active(struct cdns *cdns, u8 set_active); #else /* CONFIG_PM_SLEEP */ -static inline int cdns_resume(struct cdns *cdns, u8 set_active) +static inline int cdns_resume(struct cdns *cdns) +{ return 0; } +static inline int cdns_set_active(struct cdns *cdns, u8 set_active) { return 0; } static inline int cdns_suspend(struct cdns *cdns) { return 0; } From 826e9c91a203a2e2d383d45a557ec0408549bfcc Mon Sep 17 00:00:00 2001 From: Ma Ke Date: Wed, 28 Jun 2023 16:15:11 +0800 Subject: [PATCH 1575/2093] usb: gadget: fsl_qe_udc: validate endpoint index for ch9 udc [ Upstream commit ce9daa2efc0872a9a68ea51dc8000df05893ef2e ] We should verify the bound of the array to assure that host may not manipulate the index to point past endpoint array. Signed-off-by: Ma Ke Acked-by: Li Yang Link: https://lore.kernel.org/r/20230628081511.186850-1-make_ruc2021@163.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/fsl_qe_udc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 3b1cc8fa30c8..72b6d74b3498 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -1959,9 +1959,13 @@ static void ch9getstatus(struct qe_udc *udc, u8 request_type, u16 value, } else if ((request_type & USB_RECIP_MASK) == USB_RECIP_ENDPOINT) { /* Get endpoint status */ int pipe = index & USB_ENDPOINT_NUMBER_MASK; - struct qe_ep *target_ep = &udc->eps[pipe]; + struct qe_ep *target_ep; u16 usep; + if (pipe >= USB_MAX_ENDPOINTS) + goto stall; + target_ep = &udc->eps[pipe]; + /* stall if endpoint doesn't exist */ if (!target_ep->ep.desc) goto stall; From 6c440fec96af102b0c0783d8ae3370636c0f6643 Mon Sep 17 00:00:00 2001 From: Chenyuan Mi Date: Tue, 25 Jul 2023 09:24:07 +0000 Subject: [PATCH 1576/2093] tools: iio: iio_generic_buffer: Fix some integer type and calculation [ Upstream commit 49d736313d0975ddeb156f4f59801da833f78b30 ] In function size_from_channelarray(), the return value 'bytes' is defined as int type. However, the calcution of 'bytes' in this function is designed to use the unsigned int type. So it is necessary to change 'bytes' type to unsigned int to avoid integer overflow. The size_from_channelarray() is called in main() function, its return value is directly multipled by 'buf_len' and then used as the malloc() parameter. The 'buf_len' is completely controllable by user, thus a multiplication overflow may occur here. This could allocate an unexpected small area. Signed-off-by: Chenyuan Mi Link: https://lore.kernel.org/r/20230725092407.62545-1-michenyuan@huawei.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- tools/iio/iio_generic_buffer.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index f8deae4e26a1..44bbf80f0cfd 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -51,9 +51,9 @@ enum autochan { * Has the side effect of filling the channels[i].location values used * in processing the buffer output. **/ -static int size_from_channelarray(struct iio_channel_info *channels, int num_channels) +static unsigned int size_from_channelarray(struct iio_channel_info *channels, int num_channels) { - int bytes = 0; + unsigned int bytes = 0; int i = 0; while (i < num_channels) { @@ -348,7 +348,7 @@ int main(int argc, char **argv) ssize_t read_size; int dev_num = -1, trig_num = -1; char *buffer_access = NULL; - int scan_size; + unsigned int scan_size; int noevents = 0; int notrigger = 0; char *dummy; @@ -674,7 +674,16 @@ int main(int argc, char **argv) } scan_size = size_from_channelarray(channels, num_channels); - data = malloc(scan_size * buf_len); + + size_t total_buf_len = scan_size * buf_len; + + if (scan_size > 0 && total_buf_len / scan_size != buf_len) { + ret = -EFAULT; + perror("Integer overflow happened when calculate scan_size * buf_len"); + goto error; + } + + data = malloc(total_buf_len); if (!data) { ret = -ENOMEM; goto error; From 4738bf8b2d3635c2944b81b2a84d97b8c8b0978d Mon Sep 17 00:00:00 2001 From: Konstantin Shelekhin Date: Sat, 22 Jul 2023 18:26:37 +0300 Subject: [PATCH 1577/2093] scsi: target: iscsi: Fix buffer overflow in lio_target_nacl_info_show() [ Upstream commit 801f287c93ff95582b0a2d2163f12870a2f076d4 ] The function lio_target_nacl_info_show() uses sprintf() in a loop to print details for every iSCSI connection in a session without checking for the buffer length. With enough iSCSI connections it's possible to overflow the buffer provided by configfs and corrupt the memory. This patch replaces sprintf() with sysfs_emit_at() that checks for buffer boundries. Signed-off-by: Konstantin Shelekhin Link: https://lore.kernel.org/r/20230722152657.168859-2-k.shelekhin@yadro.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/iscsi_target_configfs.c | 54 ++++++++++---------- 1 file changed, 27 insertions(+), 27 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 5d0f51822414..c142a67dc7cc 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -533,102 +533,102 @@ static ssize_t lio_target_nacl_info_show(struct config_item *item, char *page) spin_lock_bh(&se_nacl->nacl_sess_lock); se_sess = se_nacl->nacl_sess; if (!se_sess) { - rb += sprintf(page+rb, "No active iSCSI Session for Initiator" + rb += sysfs_emit_at(page, rb, "No active iSCSI Session for Initiator" " Endpoint: %s\n", se_nacl->initiatorname); } else { sess = se_sess->fabric_sess_ptr; - rb += sprintf(page+rb, "InitiatorName: %s\n", + rb += sysfs_emit_at(page, rb, "InitiatorName: %s\n", sess->sess_ops->InitiatorName); - rb += sprintf(page+rb, "InitiatorAlias: %s\n", + rb += sysfs_emit_at(page, rb, "InitiatorAlias: %s\n", sess->sess_ops->InitiatorAlias); - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "LIO Session ID: %u ISID: 0x%6ph TSIH: %hu ", sess->sid, sess->isid, sess->tsih); - rb += sprintf(page+rb, "SessionType: %s\n", + rb += sysfs_emit_at(page, rb, "SessionType: %s\n", (sess->sess_ops->SessionType) ? "Discovery" : "Normal"); - rb += sprintf(page+rb, "Session State: "); + rb += sysfs_emit_at(page, rb, "Session State: "); switch (sess->session_state) { case TARG_SESS_STATE_FREE: - rb += sprintf(page+rb, "TARG_SESS_FREE\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_FREE\n"); break; case TARG_SESS_STATE_ACTIVE: - rb += sprintf(page+rb, "TARG_SESS_STATE_ACTIVE\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_ACTIVE\n"); break; case TARG_SESS_STATE_LOGGED_IN: - rb += sprintf(page+rb, "TARG_SESS_STATE_LOGGED_IN\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_LOGGED_IN\n"); break; case TARG_SESS_STATE_FAILED: - rb += sprintf(page+rb, "TARG_SESS_STATE_FAILED\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_FAILED\n"); break; case TARG_SESS_STATE_IN_CONTINUE: - rb += sprintf(page+rb, "TARG_SESS_STATE_IN_CONTINUE\n"); + rb += sysfs_emit_at(page, rb, "TARG_SESS_STATE_IN_CONTINUE\n"); break; default: - rb += sprintf(page+rb, "ERROR: Unknown Session" + rb += sysfs_emit_at(page, rb, "ERROR: Unknown Session" " State!\n"); break; } - rb += sprintf(page+rb, "---------------------[iSCSI Session" + rb += sysfs_emit_at(page, rb, "---------------------[iSCSI Session" " Values]-----------------------\n"); - rb += sprintf(page+rb, " CmdSN/WR : CmdSN/WC : ExpCmdSN" + rb += sysfs_emit_at(page, rb, " CmdSN/WR : CmdSN/WC : ExpCmdSN" " : MaxCmdSN : ITT : TTT\n"); max_cmd_sn = (u32) atomic_read(&sess->max_cmd_sn); - rb += sprintf(page+rb, " 0x%08x 0x%08x 0x%08x 0x%08x" + rb += sysfs_emit_at(page, rb, " 0x%08x 0x%08x 0x%08x 0x%08x" " 0x%08x 0x%08x\n", sess->cmdsn_window, (max_cmd_sn - sess->exp_cmd_sn) + 1, sess->exp_cmd_sn, max_cmd_sn, sess->init_task_tag, sess->targ_xfer_tag); - rb += sprintf(page+rb, "----------------------[iSCSI" + rb += sysfs_emit_at(page, rb, "----------------------[iSCSI" " Connections]-------------------------\n"); spin_lock(&sess->conn_lock); list_for_each_entry(conn, &sess->sess_conn_list, conn_list) { - rb += sprintf(page+rb, "CID: %hu Connection" + rb += sysfs_emit_at(page, rb, "CID: %hu Connection" " State: ", conn->cid); switch (conn->conn_state) { case TARG_CONN_STATE_FREE: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_FREE\n"); break; case TARG_CONN_STATE_XPT_UP: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_XPT_UP\n"); break; case TARG_CONN_STATE_IN_LOGIN: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_IN_LOGIN\n"); break; case TARG_CONN_STATE_LOGGED_IN: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_LOGGED_IN\n"); break; case TARG_CONN_STATE_IN_LOGOUT: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_IN_LOGOUT\n"); break; case TARG_CONN_STATE_LOGOUT_REQUESTED: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_LOGOUT_REQUESTED\n"); break; case TARG_CONN_STATE_CLEANUP_WAIT: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "TARG_CONN_STATE_CLEANUP_WAIT\n"); break; default: - rb += sprintf(page+rb, + rb += sysfs_emit_at(page, rb, "ERROR: Unknown Connection State!\n"); break; } - rb += sprintf(page+rb, " Address %pISc %s", &conn->login_sockaddr, + rb += sysfs_emit_at(page, rb, " Address %pISc %s", &conn->login_sockaddr, (conn->network_transport == ISCSI_TCP) ? "TCP" : "SCTP"); - rb += sprintf(page+rb, " StatSN: 0x%08x\n", + rb += sysfs_emit_at(page, rb, " StatSN: 0x%08x\n", conn->stat_sn); } spin_unlock(&sess->conn_lock); From a3c9315a8c7808653cdee15b760cc864ed82891a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 3 Aug 2023 15:56:42 +0200 Subject: [PATCH 1578/2093] serial: cpm_uart: Avoid suspicious locking [ Upstream commit 36ef11d311f405e55ad8e848c19b212ff71ef536 ] CHECK drivers/tty/serial/cpm_uart/cpm_uart_core.c drivers/tty/serial/cpm_uart/cpm_uart_core.c:1271:39: warning: context imbalance in 'cpm_uart_console_write' - unexpected unlock Allthough 'nolock' is not expected to change, sparse find the following form suspicious: if (unlikely(nolock)) { local_irq_save(flags); } else { spin_lock_irqsave(&pinfo->port.lock, flags); } cpm_uart_early_write(pinfo, s, count, true); if (unlikely(nolock)) { local_irq_restore(flags); } else { spin_unlock_irqrestore(&pinfo->port.lock, flags); } Rewrite it a more obvious form: if (unlikely(oops_in_progress)) { local_irq_save(flags); cpm_uart_early_write(pinfo, s, count, true); local_irq_restore(flags); } else { spin_lock_irqsave(&pinfo->port.lock, flags); cpm_uart_early_write(pinfo, s, count, true); spin_unlock_irqrestore(&pinfo->port.lock, flags); } Signed-off-by: Christophe Leroy Link: https://lore.kernel.org/r/f7da5cdc9287960185829cfef681a7d8614efa1f.1691068700.git.christophe.leroy@csgroup.eu Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/cpm_uart/cpm_uart_core.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index b4369ed45ae2..bb25691f5000 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -1257,19 +1257,14 @@ static void cpm_uart_console_write(struct console *co, const char *s, { struct uart_cpm_port *pinfo = &cpm_uart_ports[co->index]; unsigned long flags; - int nolock = oops_in_progress; - if (unlikely(nolock)) { + if (unlikely(oops_in_progress)) { local_irq_save(flags); - } else { - spin_lock_irqsave(&pinfo->port.lock, flags); - } - - cpm_uart_early_write(pinfo, s, count, true); - - if (unlikely(nolock)) { + cpm_uart_early_write(pinfo, s, count, true); local_irq_restore(flags); } else { + spin_lock_irqsave(&pinfo->port.lock, flags); + cpm_uart_early_write(pinfo, s, count, true); spin_unlock_irqrestore(&pinfo->port.lock, flags); } } From 48c135c30ad2ea5075a0f24c6fe3de56b3cb3194 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Fri, 7 Jul 2023 21:58:47 +0800 Subject: [PATCH 1579/2093] misc: open-dice: make OPEN_DICE depend on HAS_IOMEM [ Upstream commit aefc8b57af7787c80686e49a5841e9289cb11f53 ] On s390 systems (aka mainframes), it has classic channel devices for networking and permanent storage that are currently even more common than PCI devices. Hence it could have a fully functional s390 kernel with CONFIG_PCI=n, then the relevant iomem mapping functions [including ioremap(), devm_ioremap(), etc.] are not available. Here let OPEN_DICE depend on HAS_IOMEM so that it won't be built to cause below compiling error if PCI is unset: ------ ERROR: modpost: "devm_memremap" [drivers/misc/open-dice.ko] undefined! ERROR: modpost: "devm_memunmap" [drivers/misc/open-dice.ko] undefined! ------ Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202306211329.ticOJCSv-lkp@intel.com/ Signed-off-by: Baoquan He Cc: Derek Kiernan Cc: Dragan Cvetic Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230707135852.24292-4-bhe@redhat.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 358ad56f6524..0cef98319f0e 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -474,6 +474,7 @@ config HISI_HIKEY_USB config OPEN_DICE tristate "Open Profile for DICE driver" depends on OF_RESERVED_MEM + depends on HAS_IOMEM help This driver exposes a DICE reserved memory region to userspace via a character device. The memory region contains Compound Device From 8e3556f2f49777bd462dac9959d2dd31116479d7 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Wed, 9 Aug 2023 10:44:31 +0800 Subject: [PATCH 1580/2093] usb: ehci: add workaround for chipidea PORTSC.PEC bug [ Upstream commit dda4b60ed70bd670eefda081f70c0cb20bbeb1fa ] Some NXP processor using chipidea IP has a bug when frame babble is detected. As per 4.15.1.1.1 Serial Bus Babble: A babble condition also exists if IN transaction is in progress at High-speed SOF2 point. This is called frame babble. The host controller must disable the port to which the frame babble is detected. The USB controller has disabled the port (PE cleared) and has asserted USBERRINT when frame babble is detected, but PEC is not asserted. Therefore, the SW isn't aware that port has been disabled. Then the SW keeps sending packets to this port, but all of the transfers will fail. This workaround will firstly assert PCD by SW when USBERRINT is detected and then judge whether port change has really occurred or not by polling roothub status. Because the PEC doesn't get asserted in our case, this patch will also assert it by SW when specific conditions are satisfied. Signed-off-by: Xu Yang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20230809024432.535160-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/ehci-hcd.c | 8 ++++++-- drivers/usb/host/ehci-hub.c | 10 +++++++++- drivers/usb/host/ehci.h | 10 ++++++++++ 3 files changed, 25 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index a1930db0da1c..802bfafb1012 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -755,10 +755,14 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) /* normal [4.15.1.2] or error [4.15.1.1] completion */ if (likely ((status & (STS_INT|STS_ERR)) != 0)) { - if (likely ((status & STS_ERR) == 0)) + if (likely ((status & STS_ERR) == 0)) { INCR(ehci->stats.normal); - else + } else { + /* Force to check port status */ + if (ehci->has_ci_pec_bug) + status |= STS_PCD; INCR(ehci->stats.error); + } bh = 1; } diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index efe30e3be22f..1aee392e8492 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -674,7 +674,8 @@ ehci_hub_status_data (struct usb_hcd *hcd, char *buf) if ((temp & mask) != 0 || test_bit(i, &ehci->port_c_suspend) || (ehci->reset_done[i] && time_after_eq( - jiffies, ehci->reset_done[i]))) { + jiffies, ehci->reset_done[i])) + || ehci_has_ci_pec_bug(ehci, temp)) { if (i < 7) buf [0] |= 1 << (i + 1); else @@ -875,6 +876,13 @@ int ehci_hub_control( if (temp & PORT_PEC) status |= USB_PORT_STAT_C_ENABLE << 16; + if (ehci_has_ci_pec_bug(ehci, temp)) { + status |= USB_PORT_STAT_C_ENABLE << 16; + ehci_info(ehci, + "PE is cleared by HW port:%d PORTSC:%08x\n", + wIndex + 1, temp); + } + if ((temp & PORT_OCC) && (!ignore_oc && !ehci->spurious_oc)){ status |= USB_PORT_STAT_C_OVERCURRENT << 16; diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index ad3f13a3eaf1..5c0e25742e17 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -207,6 +207,7 @@ struct ehci_hcd { /* one per controller */ unsigned has_fsl_port_bug:1; /* FreeScale */ unsigned has_fsl_hs_errata:1; /* Freescale HS quirk */ unsigned has_fsl_susp_errata:1; /* NXP SUSP quirk */ + unsigned has_ci_pec_bug:1; /* ChipIdea PEC bug */ unsigned big_endian_mmio:1; unsigned big_endian_desc:1; unsigned big_endian_capbase:1; @@ -707,6 +708,15 @@ ehci_port_speed(struct ehci_hcd *ehci, unsigned int portsc) */ #define ehci_has_fsl_susp_errata(e) ((e)->has_fsl_susp_errata) +/* + * Some Freescale/NXP processors using ChipIdea IP have a bug in which + * disabling the port (PE is cleared) does not cause PEC to be asserted + * when frame babble is detected. + */ +#define ehci_has_ci_pec_bug(e, portsc) \ + ((e)->has_ci_pec_bug && ((e)->command & CMD_PSE) \ + && !(portsc & PORT_PEC) && !(portsc & PORT_PE)) + /* * While most USB host controllers implement their registers in * little-endian format, a minority (celleb companion chip) implement From 91f400233edc1354e80b9f6b9370dc1d0e11095b Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Wed, 9 Aug 2023 10:44:32 +0800 Subject: [PATCH 1581/2093] usb: chipidea: add workaround for chipidea PEC bug [ Upstream commit 12e6ac69cc7e7d3367599ae26a92a0f9a18bc728 ] Some NXP processors using ChipIdea USB IP have a bug when frame babble is detected. Issue description: In USB camera test, our controller is host in HS mode. In ISOC IN, when device sends data across the micro frame, it causes the babble in host controller. This will clear the PE bit. In spec, it also requires to set the PEC bit and then set the PCI bit. Without the PCI interrupt, the software does not know the PE is cleared. This will add a flag CI_HDRC_HAS_PORTSC_PEC_MISSED to some impacted platform datas. And the ehci host driver will assert PEC by SW when specific conditions are satisfied. Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20230809024432.535160-2-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/chipidea/ci.h | 1 + drivers/usb/chipidea/ci_hdrc_imx.c | 4 +++- drivers/usb/chipidea/core.c | 2 ++ drivers/usb/chipidea/host.c | 1 + include/linux/usb/chipidea.h | 1 + 5 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 85a803c135ab..2ff83911219f 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -253,6 +253,7 @@ struct ci_hdrc { bool id_event; bool b_sess_valid_event; bool imx28_write_fix; + bool has_portsc_pec_bug; bool supports_runtime_pm; bool in_lpm; bool wakeup_int; diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index caa91117ba42..984087bbf3e2 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -67,11 +67,13 @@ static const struct ci_hdrc_imx_platform_flag imx7d_usb_data = { static const struct ci_hdrc_imx_platform_flag imx7ulp_usb_data = { .flags = CI_HDRC_SUPPORTS_RUNTIME_PM | + CI_HDRC_HAS_PORTSC_PEC_MISSED | CI_HDRC_PMQOS, }; static const struct ci_hdrc_imx_platform_flag imx8ulp_usb_data = { - .flags = CI_HDRC_SUPPORTS_RUNTIME_PM, + .flags = CI_HDRC_SUPPORTS_RUNTIME_PM | + CI_HDRC_HAS_PORTSC_PEC_MISSED, }; static const struct of_device_id ci_hdrc_imx_dt_ids[] = { diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 71f172ecfaab..b9227f41cf1c 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1038,6 +1038,8 @@ static int ci_hdrc_probe(struct platform_device *pdev) CI_HDRC_IMX28_WRITE_FIX); ci->supports_runtime_pm = !!(ci->platdata->flags & CI_HDRC_SUPPORTS_RUNTIME_PM); + ci->has_portsc_pec_bug = !!(ci->platdata->flags & + CI_HDRC_HAS_PORTSC_PEC_MISSED); platform_set_drvdata(pdev, ci); ret = hw_device_init(ci, base); diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index bc3634a54c6b..3b08c5e81170 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -151,6 +151,7 @@ static int host_start(struct ci_hdrc *ci) ehci->has_hostpc = ci->hw_bank.lpm; ehci->has_tdi_phy_lpm = ci->hw_bank.lpm; ehci->imx28_write_fix = ci->imx28_write_fix; + ehci->has_ci_pec_bug = ci->has_portsc_pec_bug; priv = (struct ehci_ci_priv *)ehci->priv; priv->reg_vbus = NULL; diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index ee38835ed77c..0b4f2d5faa08 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -63,6 +63,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_IMX_IS_HSIC BIT(14) #define CI_HDRC_PMQOS BIT(15) #define CI_HDRC_PHY_VBUS_CONTROL BIT(16) +#define CI_HDRC_HAS_PORTSC_PEC_MISSED BIT(17) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 From 240571c49f764a2b51ab09c5fd7d558e7b1c5014 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 1 Aug 2023 10:14:30 +0300 Subject: [PATCH 1582/2093] media: pci: ipu3-cio2: Initialise timing struct to avoid a compiler warning [ Upstream commit 9d7531be3085a8f013cf173ccc4e72e3cf493538 ] Initialise timing struct in cio2_hw_init() to zero in order to avoid a compiler warning. The warning was a false positive. Reported-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/pci/intel/ipu3/ipu3-cio2-main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c b/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c index 3b76a9d0383a..1bbe58b24d99 100644 --- a/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c +++ b/drivers/media/pci/intel/ipu3/ipu3-cio2-main.c @@ -354,7 +354,7 @@ static int cio2_hw_init(struct cio2_device *cio2, struct cio2_queue *q) void __iomem *const base = cio2->base; u8 lanes, csi2bus = q->csi2.port; u8 sensor_vc = SENSOR_VIR_CH_DFLT; - struct cio2_csi2_timing timing; + struct cio2_csi2_timing timing = { 0 }; int i, r; fmt = cio2_find_format(NULL, &q->subdev_fmt.code); From 48aebbe801e78a8932404c122ed0e880ccedc220 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 5 Aug 2023 16:41:13 +0800 Subject: [PATCH 1583/2093] kobject: Add sanity check for kset->kobj.ktype in kset_register() [ Upstream commit 4d0fe8c52bb3029d83e323c961221156ab98680b ] When I register a kset in the following way: static struct kset my_kset; kobject_set_name(&my_kset.kobj, "my_kset"); ret = kset_register(&my_kset); A null pointer dereference exception is occurred: [ 4453.568337] Unable to handle kernel NULL pointer dereference at \ virtual address 0000000000000028 ... ... [ 4453.810361] Call trace: [ 4453.813062] kobject_get_ownership+0xc/0x34 [ 4453.817493] kobject_add_internal+0x98/0x274 [ 4453.822005] kset_register+0x5c/0xb4 [ 4453.825820] my_kobj_init+0x44/0x1000 [my_kset] ... ... Because I didn't initialize my_kset.kobj.ktype. According to the description in Documentation/core-api/kobject.rst: - A ktype is the type of object that embeds a kobject. Every structure that embeds a kobject needs a corresponding ktype. So add sanity check to make sure kset->kobj.ktype is not NULL. Signed-off-by: Zhen Lei Link: https://lore.kernel.org/r/20230805084114.1298-2-thunder.leizhen@huaweicloud.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- lib/kobject.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/lib/kobject.c b/lib/kobject.c index aa375a5d9441..207fd22ad3bd 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -850,6 +850,11 @@ int kset_register(struct kset *k) if (!k) return -EINVAL; + if (!k->kobj.ktype) { + pr_err("must have a ktype to be initialized properly!\n"); + return -EINVAL; + } + kset_init(k); err = kobject_add_internal(&k->kobj); if (err) From ee42bfc791aa3cd78e29046f26a09d189beb3efb Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 7 Aug 2023 10:11:40 -0700 Subject: [PATCH 1584/2093] interconnect: Fix locking for runpm vs reclaim [ Upstream commit af42269c3523492d71ebbe11fefae2653e9cdc78 ] For cases where icc_bw_set() can be called in callbaths that could deadlock against shrinker/reclaim, such as runpm resume, we need to decouple the icc locking. Introduce a new icc_bw_lock for cases where we need to serialize bw aggregation and update to decouple that from paths that require memory allocation such as node/link creation/ destruction. Fixes this lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc8-debug+ #554 Not tainted ------------------------------------------------------ ring0/132 is trying to acquire lock: ffffff80871916d0 (&gmu->lock){+.+.}-{3:3}, at: a6xx_pm_resume+0xf0/0x234 but task is already holding lock: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 (dma_fence_map){++++}-{0:0}: __dma_fence_might_wait+0x74/0xc0 dma_resv_lockdep+0x1f4/0x2f4 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #3 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}: fs_reclaim_acquire+0x80/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 topology_parse_cpu_capacity+0x8c/0x178 get_cpu_for_node+0x88/0xc4 parse_cluster+0x1b0/0x28c parse_cluster+0x8c/0x28c init_cpu_topology+0x168/0x188 smp_prepare_cpus+0x24/0xf8 kernel_init_freeable+0x18c/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #2 (fs_reclaim){+.+.}-{0:0}: __fs_reclaim_acquire+0x3c/0x48 fs_reclaim_acquire+0x54/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 kzalloc.constprop.0+0x14/0x20 icc_node_create_nolock+0x4c/0xc4 icc_node_create+0x38/0x58 qcom_icc_rpmh_probe+0x1b8/0x248 platform_probe+0x70/0xc4 really_probe+0x158/0x290 __driver_probe_device+0xc8/0xe0 driver_probe_device+0x44/0x100 __driver_attach+0xf8/0x108 bus_for_each_dev+0x78/0xc4 driver_attach+0x2c/0x38 bus_add_driver+0xd0/0x1d8 driver_register+0xbc/0xf8 __platform_driver_register+0x30/0x3c qnoc_driver_init+0x24/0x30 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #1 (icc_lock){+.+.}-{3:3}: __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 icc_set_bw+0x88/0x2b4 _set_opp_bw+0x8c/0xd8 _set_opp+0x19c/0x300 dev_pm_opp_set_opp+0x84/0x94 a6xx_gmu_resume+0x18c/0x804 a6xx_pm_resume+0xf8/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc adreno_load_gpu+0xc4/0x17c msm_open+0x50/0x120 drm_file_alloc+0x17c/0x228 drm_open_helper+0x74/0x118 drm_open+0xa0/0x144 drm_stub_open+0xd4/0xe4 chrdev_open+0x1b8/0x1e4 do_dentry_open+0x2f8/0x38c vfs_open+0x34/0x40 path_openat+0x64c/0x7b4 do_filp_open+0x54/0xc4 do_sys_openat2+0x9c/0x100 do_sys_open+0x50/0x7c __arm64_sys_openat+0x28/0x34 invoke_syscall+0x8c/0x128 el0_svc_common.constprop.0+0xa0/0x11c do_el0_svc+0xac/0xbc el0_svc+0x48/0xa0 el0t_64_sync_handler+0xac/0x13c el0t_64_sync+0x190/0x194 -> #0 (&gmu->lock){+.+.}-{3:3}: __lock_acquire+0xe00/0x1060 lock_acquire+0x1e0/0x2f8 __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 a6xx_pm_resume+0xf0/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc pm_runtime_get_sync.isra.0+0x14/0x20 msm_gpu_submit+0x58/0x178 msm_job_run+0x78/0x150 drm_sched_main+0x290/0x370 kthread+0xf0/0x100 ret_from_fork+0x10/0x20 other info that might help us debug this: Chain exists of: &gmu->lock --> mmu_notifier_invalidate_range_start --> dma_fence_map Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(dma_fence_map); lock(mmu_notifier_invalidate_range_start); lock(dma_fence_map); lock(&gmu->lock); *** DEADLOCK *** 2 locks held by ring0/132: #0: ffffff8087191170 (&gpu->lock){+.+.}-{3:3}, at: msm_job_run+0x64/0x150 #1: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150 stack backtrace: CPU: 7 PID: 132 Comm: ring0 Not tainted 6.2.0-rc8-debug+ #554 Hardware name: Google Lazor (rev1 - 2) with LTE (DT) Call trace: dump_backtrace.part.0+0xb4/0xf8 show_stack+0x20/0x38 dump_stack_lvl+0x9c/0xd0 dump_stack+0x18/0x34 print_circular_bug+0x1b4/0x1f0 check_noncircular+0x78/0xac __lock_acquire+0xe00/0x1060 lock_acquire+0x1e0/0x2f8 __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 a6xx_pm_resume+0xf0/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc pm_runtime_get_sync.isra.0+0x14/0x20 msm_gpu_submit+0x58/0x178 msm_job_run+0x78/0x150 drm_sched_main+0x290/0x370 kthread+0xf0/0x100 ret_from_fork+0x10/0x20 Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20230807171148.210181-7-robdclark@gmail.com Signed-off-by: Georgi Djakov Signed-off-by: Sasha Levin --- drivers/interconnect/core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index cfa52c6369d0..f4a493d78ee9 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -29,6 +29,7 @@ static LIST_HEAD(icc_providers); static int providers_count; static bool synced_state; static DEFINE_MUTEX(icc_lock); +static DEFINE_MUTEX(icc_bw_lock); static struct dentry *icc_debugfs_dir; static void icc_summary_show_one(struct seq_file *s, struct icc_node *n) @@ -632,7 +633,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) if (WARN_ON(IS_ERR(path) || !path->num_nodes)) return -EINVAL; - mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock); old_avg = path->reqs[0].avg_bw; old_peak = path->reqs[0].peak_bw; @@ -664,7 +665,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) apply_constraints(path); } - mutex_unlock(&icc_lock); + mutex_unlock(&icc_bw_lock); trace_icc_set_bw_end(path, ret); @@ -967,6 +968,7 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) return; mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock); node->provider = provider; list_add_tail(&node->node_list, &provider->nodes); @@ -992,6 +994,7 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = 0; node->peak_bw = 0; + mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_node_add); @@ -1129,6 +1132,7 @@ void icc_sync_state(struct device *dev) return; mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock); synced_state = true; list_for_each_entry(p, &icc_providers, provider_list) { dev_dbg(p->dev, "interconnect provider is in synced state\n"); From 13ebf3ff08b046fc798dc82a42d73713cb03eded Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 17 Jul 2023 21:52:03 +0206 Subject: [PATCH 1585/2093] printk: Keep non-panic-CPUs out of console lock [ Upstream commit 51a1d258e50e03a0216bf42b6af9ff34ec402ac1 ] When in a panic situation, non-panic CPUs should avoid holding the console lock so as not to contend with the panic CPU. This is already implemented with abandon_console_lock_in_panic(), which is checked after each printed line. However, non-panic CPUs should also avoid trying to acquire the console lock during a panic. Modify console_trylock() to fail and console_lock() to block() when called from a non-panic CPU during a panic. Signed-off-by: John Ogness Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230717194607.145135-4-john.ogness@linutronix.de Signed-off-by: Sasha Levin --- kernel/printk/printk.c | 45 ++++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 19 deletions(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index e4f1e7478b52..4b9429f3fd6d 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2552,6 +2552,25 @@ static int console_cpu_notify(unsigned int cpu) return 0; } +/* + * Return true when this CPU should unlock console_sem without pushing all + * messages to the console. This reduces the chance that the console is + * locked when the panic CPU tries to use it. + */ +static bool abandon_console_lock_in_panic(void) +{ + if (!panic_in_progress()) + return false; + + /* + * We can use raw_smp_processor_id() here because it is impossible for + * the task to be migrated to the panic_cpu, or away from it. If + * panic_cpu has already been set, and we're not currently executing on + * that CPU, then we never will be. + */ + return atomic_read(&panic_cpu) != raw_smp_processor_id(); +} + /** * console_lock - lock the console system for exclusive use. * @@ -2564,6 +2583,10 @@ void console_lock(void) { might_sleep(); + /* On panic, the console_lock must be left to the panic cpu. */ + while (abandon_console_lock_in_panic()) + msleep(1000); + down_console_sem(); if (console_suspended) return; @@ -2582,6 +2605,9 @@ EXPORT_SYMBOL(console_lock); */ int console_trylock(void) { + /* On panic, the console_lock must be left to the panic cpu. */ + if (abandon_console_lock_in_panic()) + return 0; if (down_trylock_console_sem()) return 0; if (console_suspended) { @@ -2600,25 +2626,6 @@ int is_console_locked(void) } EXPORT_SYMBOL(is_console_locked); -/* - * Return true when this CPU should unlock console_sem without pushing all - * messages to the console. This reduces the chance that the console is - * locked when the panic CPU tries to use it. - */ -static bool abandon_console_lock_in_panic(void) -{ - if (!panic_in_progress()) - return false; - - /* - * We can use raw_smp_processor_id() here because it is impossible for - * the task to be migrated to the panic_cpu, or away from it. If - * panic_cpu has already been set, and we're not currently executing on - * that CPU, then we never will be. - */ - return atomic_read(&panic_cpu) != raw_smp_processor_id(); -} - /* * Check if the given console is currently capable and allowed to print * records. From 6ca28642dd9adfd0f7a1ad2eae29763377f2c6fe Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 17 Jul 2023 21:52:05 +0206 Subject: [PATCH 1586/2093] printk: Consolidate console deferred printing [ Upstream commit 696ffaf50e1f8dbc66223ff614473f945f5fb8d8 ] Printing to consoles can be deferred for several reasons: - explicitly with printk_deferred() - printk() in NMI context - recursive printk() calls The current implementation is not consistent. For printk_deferred(), irq work is scheduled twice. For NMI und recursive, panic CPU suppression and caller delays are not properly enforced. Correct these inconsistencies by consolidating the deferred printing code so that vprintk_deferred() is the top-level function for deferred printing and vprintk_emit() will perform whichever irq_work queueing is appropriate. Also add kerneldoc for wake_up_klogd() and defer_console_output() to clarify their differences and appropriate usage. Signed-off-by: John Ogness Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230717194607.145135-6-john.ogness@linutronix.de Signed-off-by: Sasha Levin --- kernel/printk/printk.c | 35 ++++++++++++++++++++++++++++------- kernel/printk/printk_safe.c | 9 ++------- 2 files changed, 30 insertions(+), 14 deletions(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 4b9429f3fd6d..cc53fb77f77c 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2269,7 +2269,11 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } - wake_up_klogd(); + if (in_sched) + defer_console_output(); + else + wake_up_klogd(); + return printed_len; } EXPORT_SYMBOL(vprintk_emit); @@ -3490,11 +3494,33 @@ static void __wake_up_klogd(int val) preempt_enable(); } +/** + * wake_up_klogd - Wake kernel logging daemon + * + * Use this function when new records have been added to the ringbuffer + * and the console printing of those records has already occurred or is + * known to be handled by some other context. This function will only + * wake the logging daemon. + * + * Context: Any context. + */ void wake_up_klogd(void) { __wake_up_klogd(PRINTK_PENDING_WAKEUP); } +/** + * defer_console_output - Wake kernel logging daemon and trigger + * console printing in a deferred context + * + * Use this function when new records have been added to the ringbuffer, + * this context is responsible for console printing those records, but + * the current context is not allowed to perform the console printing. + * Trigger an irq_work context to perform the console printing. This + * function also wakes the logging daemon. + * + * Context: Any context. + */ void defer_console_output(void) { /* @@ -3511,12 +3537,7 @@ void printk_trigger_flush(void) int vprintk_deferred(const char *fmt, va_list args) { - int r; - - r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); - defer_console_output(); - - return r; + return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); } int _printk_deferred(const char *fmt, ...) diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index ef0f9a2044da..6d10927a07d8 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -38,13 +38,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ - if (this_cpu_read(printk_context) || in_nmi()) { - int len; - - len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); - defer_console_output(); - return len; - } + if (this_cpu_read(printk_context) || in_nmi()) + return vprintk_deferred(fmt, args); /* No obstacles. */ return vprintk_default(fmt, args); From b4539ff7a48d898bfb9c97c54bee8fd568db9d8b Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 17 Oct 2022 20:22:10 +0300 Subject: [PATCH 1587/2093] dma-buf: Add unlocked variant of attachment-mapping functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 19d6634d8789573a9212ce78dbb4348ffd4f7f78 ] Add unlocked variant of dma_buf_map/unmap_attachment() that will be used by drivers that don't take the reservation lock explicitly. Acked-by: Sumit Semwal Acked-by: Christian König Signed-off-by: Dmitry Osipenko Link: https://patchwork.freedesktop.org/patch/msgid/20221017172229.42269-3-dmitry.osipenko@collabora.com Stable-dep-of: a2cb9cd6a394 ("misc: fastrpc: Fix incorrect DMA mapping unmap request") Signed-off-by: Sasha Levin --- drivers/dma-buf/dma-buf.c | 53 +++++++++++++++++++++++++++++++++++++++ include/linux/dma-buf.h | 6 +++++ 2 files changed, 59 insertions(+) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index eb6b59363c4f..3d58514d0482 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1105,6 +1105,34 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, } EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment, DMA_BUF); +/** + * dma_buf_map_attachment_unlocked - Returns the scatterlist table of the attachment; + * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the + * dma_buf_ops. + * @attach: [in] attachment whose scatterlist is to be returned + * @direction: [in] direction of DMA transfer + * + * Unlocked variant of dma_buf_map_attachment(). + */ +struct sg_table * +dma_buf_map_attachment_unlocked(struct dma_buf_attachment *attach, + enum dma_data_direction direction) +{ + struct sg_table *sg_table; + + might_sleep(); + + if (WARN_ON(!attach || !attach->dmabuf)) + return ERR_PTR(-EINVAL); + + dma_resv_lock(attach->dmabuf->resv, NULL); + sg_table = dma_buf_map_attachment(attach, direction); + dma_resv_unlock(attach->dmabuf->resv); + + return sg_table; +} +EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment_unlocked, DMA_BUF); + /** * dma_buf_unmap_attachment - unmaps and decreases usecount of the buffer;might * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of @@ -1141,6 +1169,31 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, } EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment, DMA_BUF); +/** + * dma_buf_unmap_attachment_unlocked - unmaps and decreases usecount of the buffer;might + * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of + * dma_buf_ops. + * @attach: [in] attachment to unmap buffer from + * @sg_table: [in] scatterlist info of the buffer to unmap + * @direction: [in] direction of DMA transfer + * + * Unlocked variant of dma_buf_unmap_attachment(). + */ +void dma_buf_unmap_attachment_unlocked(struct dma_buf_attachment *attach, + struct sg_table *sg_table, + enum dma_data_direction direction) +{ + might_sleep(); + + if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) + return; + + dma_resv_lock(attach->dmabuf->resv, NULL); + dma_buf_unmap_attachment(attach, sg_table, direction); + dma_resv_unlock(attach->dmabuf->resv); +} +EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment_unlocked, DMA_BUF); + /** * dma_buf_move_notify - notify attachments that DMA-buf is moving * diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 71731796c8c3..9c31f1f430d8 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -627,6 +627,12 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); +struct sg_table * +dma_buf_map_attachment_unlocked(struct dma_buf_attachment *attach, + enum dma_data_direction direction); +void dma_buf_unmap_attachment_unlocked(struct dma_buf_attachment *attach, + struct sg_table *sg_table, + enum dma_data_direction direction); int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); From 5a5641755ca893185adae19bf9cde14cecc5527f Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 17 Oct 2022 20:22:19 +0300 Subject: [PATCH 1588/2093] misc: fastrpc: Prepare to dynamic dma-buf locking specification MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 791da5c7fedbc1d662445ec030d8f86872f6184c ] Prepare fastrpc to the common dynamic dma-buf locking convention by starting to use the unlocked versions of dma-buf API functions. Acked-by: Christian König Acked-by: Srinivas Kandagatla Signed-off-by: Dmitry Osipenko Link: https://patchwork.freedesktop.org/patch/msgid/20221017172229.42269-12-dmitry.osipenko@collabora.com Stable-dep-of: a2cb9cd6a394 ("misc: fastrpc: Fix incorrect DMA mapping unmap request") Signed-off-by: Sasha Levin --- drivers/misc/fastrpc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 13518cac076c..e9291694922b 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -310,8 +310,8 @@ static void fastrpc_free_map(struct kref *ref) return; } } - dma_buf_unmap_attachment(map->attach, map->table, - DMA_BIDIRECTIONAL); + dma_buf_unmap_attachment_unlocked(map->attach, map->table, + DMA_BIDIRECTIONAL); dma_buf_detach(map->buf, map->attach); dma_buf_put(map->buf); } @@ -736,7 +736,7 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, goto attach_err; } - map->table = dma_buf_map_attachment(map->attach, DMA_BIDIRECTIONAL); + map->table = dma_buf_map_attachment_unlocked(map->attach, DMA_BIDIRECTIONAL); if (IS_ERR(map->table)) { err = PTR_ERR(map->table); goto map_err; From 8332311cd02a445147256f52a8ee0789048c60fc Mon Sep 17 00:00:00 2001 From: Ekansh Gupta Date: Fri, 11 Aug 2023 12:56:42 +0100 Subject: [PATCH 1589/2093] misc: fastrpc: Fix incorrect DMA mapping unmap request [ Upstream commit a2cb9cd6a3949a3804ad9fd7da234892ce6719ec ] Scatterlist table is obtained during map create request and the same table is used for DMA mapping unmap. In case there is any failure while getting the sg_table, ERR_PTR is returned instead of sg_table. When the map is getting freed, there is only a non-NULL check of sg_table which will also be true in case failure was returned instead of sg_table. This would result in improper unmap request. Add proper check before setting map table to avoid bad unmap request. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Cc: stable Signed-off-by: Ekansh Gupta Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230811115643.38578-3-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/fastrpc.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index e9291694922b..4c51d216f3d4 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -711,6 +711,7 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, { struct fastrpc_session_ctx *sess = fl->sctx; struct fastrpc_map *map = NULL; + struct sg_table *table; int err = 0; if (!fastrpc_map_lookup(fl, fd, ppmap, true)) @@ -736,11 +737,12 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, goto attach_err; } - map->table = dma_buf_map_attachment_unlocked(map->attach, DMA_BIDIRECTIONAL); - if (IS_ERR(map->table)) { - err = PTR_ERR(map->table); + table = dma_buf_map_attachment_unlocked(map->attach, DMA_BIDIRECTIONAL); + if (IS_ERR(table)) { + err = PTR_ERR(table); goto map_err; } + map->table = table; map->phys = sg_dma_address(map->table->sgl); map->phys += ((u64)fl->sctx->sid << 32); From 44751b057c2479508cf3bf2799e6a3e6d296ec22 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 18 Nov 2022 16:28:11 +0800 Subject: [PATCH 1590/2093] MIPS: Use "grep -E" instead of "egrep" [ Upstream commit d42f0c6ad502c9f612410e125ebdf290cce8bdc3 ] The latest version of grep claims the egrep is now obsolete so the build now contains warnings that look like: egrep: warning: egrep is obsolescent; using grep -E fix this up by moving the related file to use "grep -E" instead. Here are the steps to install the latest grep: wget http://ftp.gnu.org/gnu/grep/grep-3.8.tar.gz tar xf grep-3.8.tar.gz cd grep-3.8 && ./configure && make sudo make install export PATH=/usr/local/bin:$PATH Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer Stable-dep-of: 4fe4a6374c4d ("MIPS: Only fiddle with CHECKFLAGS if `need-compiler'") Signed-off-by: Sasha Levin --- arch/mips/Makefile | 2 +- arch/mips/vdso/Makefile | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index ee8f47aef98b..dd6486097e1d 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -352,7 +352,7 @@ KBUILD_LDFLAGS += -m $(ld-emul) ifdef need-compiler CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \ - egrep -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \ + grep -E -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \ sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g') endif diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index f72658b3a53f..1f7d5c6c10b0 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -71,7 +71,7 @@ KCOV_INSTRUMENT := n # Check that we don't have PIC 'jalr t9' calls left quiet_cmd_vdso_mips_check = VDSOCHK $@ - cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | egrep -h "jalr.*t9" > /dev/null; \ + cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | grep -E -h "jalr.*t9" > /dev/null; \ then (echo >&2 "$@: PIC 'jalr t9' calls are not supported"; \ rm -f $@; /bin/false); fi From 31242daa108b9b480371e3f88e945fd720cd38a0 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Mon, 31 Jul 2023 19:16:32 +0800 Subject: [PATCH 1591/2093] btrfs: add a helper to read the superblock metadata_uuid [ Upstream commit 4844c3664a72d36cc79752cb651c78860b14c240 ] In some cases, we need to read the FSID from the superblock when the metadata_uuid is not set, and otherwise, read the metadata_uuid. So, add a helper. Reviewed-by: Johannes Thumshirn Tested-by: Guilherme G. Piccoli Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 6bfe3959b0e7 ("btrfs: compare the correct fsid/metadata_uuid in btrfs_validate_super") Signed-off-by: Sasha Levin --- fs/btrfs/volumes.c | 8 ++++++++ fs/btrfs/volumes.h | 1 + 2 files changed, 9 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 567c5c010f93..a40ebd2321d0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -663,6 +663,14 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, return -EINVAL; } +u8 *btrfs_sb_fsid_ptr(struct btrfs_super_block *sb) +{ + bool has_metadata_uuid = (btrfs_super_incompat_flags(sb) & + BTRFS_FEATURE_INCOMPAT_METADATA_UUID); + + return has_metadata_uuid ? sb->metadata_uuid : sb->fsid; +} + /* * Handle scanned device having its CHANGING_FSID_V2 flag set and the fs_devices * being created with a disk that has already completed its fsid change. Such diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 099def5613b8..ec2260177038 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -757,5 +757,6 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr); +u8 *btrfs_sb_fsid_ptr(struct btrfs_super_block *sb); #endif From 2174731a17b04bc01d0c9e68414dca7091a59cbe Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Mon, 31 Jul 2023 19:16:35 +0800 Subject: [PATCH 1592/2093] btrfs: compare the correct fsid/metadata_uuid in btrfs_validate_super [ Upstream commit 6bfe3959b0e7a526f5c64747801a8613f002f05a ] The function btrfs_validate_super() should verify the metadata_uuid in the provided superblock argument. Because, all its callers expect it to do that. Such as in the following stacks: write_all_supers() sb = fs_info->super_for_commit; btrfs_validate_write_super(.., sb) btrfs_validate_super(.., sb, ..) scrub_one_super() btrfs_validate_super(.., sb, ..) And check_dev_super() btrfs_validate_super(.., sb, ..) However, it currently verifies the fs_info::super_copy::metadata_uuid instead. Fix this using the correct metadata_uuid in the superblock argument. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Johannes Thumshirn Tested-by: Guilherme G. Piccoli Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 64daae693afd..c44f1fcc1909 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2728,13 +2728,11 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } - if (btrfs_fs_incompat(fs_info, METADATA_UUID) && - memcmp(fs_info->fs_devices->metadata_uuid, - fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) { + if (memcmp(fs_info->fs_devices->metadata_uuid, btrfs_sb_fsid_ptr(sb), + BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, "superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU", - fs_info->super_copy->metadata_uuid, - fs_info->fs_devices->metadata_uuid); + btrfs_sb_fsid_ptr(sb), fs_info->fs_devices->metadata_uuid); ret = -EINVAL; } From 00cf1dc13c1f5207693abe59d6e26d8fd0ed7673 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 3 Feb 2023 16:06:12 +0100 Subject: [PATCH 1593/2093] block: factor out a bvec_set_page helper [ Upstream commit d58cdfae6a22e5079656c487aad669597a0635c8 ] Add a helper to initialize a bvec based of a page pointer. This will help removing various open code bvec initializations. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230203150634.3199647-2-hch@lst.de Signed-off-by: Jens Axboe Stable-dep-of: 1f0bbf28940c ("nvmet-tcp: pass iov_len instead of sg->length to bvec_set_page()") Signed-off-by: Sasha Levin --- block/bio-integrity.c | 7 +------ block/bio.c | 12 ++---------- include/linux/bvec.h | 15 +++++++++++++++ 3 files changed, 18 insertions(+), 16 deletions(-) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 91ffee6fc8cb..4533eb491661 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -124,23 +124,18 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_vec *iv; if (bip->bip_vcnt >= bip->bip_max_vcnt) { printk(KERN_ERR "%s: bip_vec full\n", __func__); return 0; } - iv = bip->bip_vec + bip->bip_vcnt; - if (bip->bip_vcnt && bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits, &bip->bip_vec[bip->bip_vcnt - 1], offset)) return 0; - iv->bv_page = page; - iv->bv_len = len; - iv->bv_offset = offset; + bvec_set_page(&bip->bip_vec[bip->bip_vcnt], page, len, offset); bip->bip_vcnt++; return len; diff --git a/block/bio.c b/block/bio.c index d5cd825d6efc..9ec72a78f114 100644 --- a/block/bio.c +++ b/block/bio.c @@ -976,10 +976,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, if (bio->bi_vcnt >= queue_max_segments(q)) return 0; - bvec = &bio->bi_io_vec[bio->bi_vcnt]; - bvec->bv_page = page; - bvec->bv_len = len; - bvec->bv_offset = offset; + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset); bio->bi_vcnt++; bio->bi_iter.bi_size += len; return len; @@ -1055,15 +1052,10 @@ EXPORT_SYMBOL_GPL(bio_add_zone_append_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off) { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; - WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); - bv->bv_page = page; - bv->bv_offset = off; - bv->bv_len = len; - + bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off); bio->bi_iter.bi_size += len; bio->bi_vcnt++; } diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 35c25dff651a..9e3dac51eb26 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -35,6 +35,21 @@ struct bio_vec { unsigned int bv_offset; }; +/** + * bvec_set_page - initialize a bvec based off a struct page + * @bv: bvec to initialize + * @page: page the bvec should point to + * @len: length of the bvec + * @offset: offset into the page + */ +static inline void bvec_set_page(struct bio_vec *bv, struct page *page, + unsigned int len, unsigned int offset) +{ + bv->bv_page = page; + bv->bv_len = len; + bv->bv_offset = offset; +} + struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ From 5ee5c928dbb6dfb8f613efc2688eddf311c74e23 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 3 Feb 2023 16:06:17 +0100 Subject: [PATCH 1594/2093] nvmet: use bvec_set_page to initialize bvecs [ Upstream commit fc41c97a3a7b08131e6998bc7692f95729f9d359 ] Use the bvec_set_page helper to initialize bvecs. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230203150634.3199647-7-hch@lst.de Signed-off-by: Jens Axboe Stable-dep-of: 1f0bbf28940c ("nvmet-tcp: pass iov_len instead of sg->length to bvec_set_page()") Signed-off-by: Sasha Levin --- drivers/nvme/target/io-cmd-file.c | 10 ++-------- drivers/nvme/target/tcp.c | 5 ++--- 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 871c4f32f443..2d068439b129 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -73,13 +73,6 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns) return ret; } -static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg) -{ - bv->bv_page = sg_page(sg); - bv->bv_offset = sg->offset; - bv->bv_len = sg->length; -} - static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, unsigned long nr_segs, size_t count, int ki_flags) { @@ -146,7 +139,8 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) memset(&req->f.iocb, 0, sizeof(struct kiocb)); for_each_sg(req->sg, sg, req->sg_cnt, i) { - nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg); + bvec_set_page(&req->f.bvec[bv_cnt], sg_page(sg), sg->length, + sg->offset); len += req->f.bvec[bv_cnt].bv_len; total_len += req->f.bvec[bv_cnt].bv_len; bv_cnt++; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index cc05c094de22..c5759eb503d0 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -321,9 +321,8 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) while (length) { u32 iov_len = min_t(u32, length, sg->length - sg_offset); - iov->bv_page = sg_page(sg); - iov->bv_len = sg->length; - iov->bv_offset = sg->offset + sg_offset; + bvec_set_page(iov, sg_page(sg), sg->length, + sg->offset + sg_offset); length -= iov_len; sg = sg_next(sg); From 64561352c0f2140ff1ee9b4f5d920bc1fce6b56e Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Wed, 9 Aug 2023 15:56:45 +0530 Subject: [PATCH 1595/2093] nvmet-tcp: pass iov_len instead of sg->length to bvec_set_page() [ Upstream commit 1f0bbf28940cf5edad90ab57b62aa8197bf5e836 ] iov_len is the valid data length, so pass iov_len instead of sg->length to bvec_set_page(). Fixes: 5bfaba275ae6 ("nvmet-tcp: don't map pages which can't come from HIGHMEM") Signed-off-by: Rakshana Sridhar Signed-off-by: Varun Prakash Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/target/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index c5759eb503d0..5e29da94f72d 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -321,7 +321,7 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) while (length) { u32 iov_len = min_t(u32, length, sg->length - sg_offset); - bvec_set_page(iov, sg_page(sg), sg->length, + bvec_set_page(iov, sg_page(sg), iov_len, sg->offset + sg_offset); length -= iov_len; From cbf226355ee3abb98ff266c3ed8ddacae7bfcfa6 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 4 Sep 2023 10:14:20 +0800 Subject: [PATCH 1596/2093] drm: gm12u320: Fix the timeout usage for usb_bulk_msg() [ Upstream commit 7583028d359db3cd0072badcc576b4f9455fd27a ] The timeout arg of usb_bulk_msg() is ms already, which has been converted to jiffies by msecs_to_jiffies() in usb_start_wait_urb(). So fix the usage by removing the redundant msecs_to_jiffies() in the macros. And as Hans suggested, also remove msecs_to_jiffies() for the IDLE_TIMEOUT macro to make it consistent here and so change IDLE_TIMEOUT to msecs_to_jiffies(IDLE_TIMEOUT) where it is used. Fixes: e4f86e437164 ("drm: Add Grain Media GM12U320 driver v2") Signed-off-by: Jinjie Ruan Suggested-by: Hans de Goede Reviewed-by: Hans de Goede Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230904021421.1663892-1-ruanjinjie@huawei.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/tiny/gm12u320.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c index 7441d992a5d7..8b0a9059d3fd 100644 --- a/drivers/gpu/drm/tiny/gm12u320.c +++ b/drivers/gpu/drm/tiny/gm12u320.c @@ -69,10 +69,10 @@ MODULE_PARM_DESC(eco_mode, "Turn on Eco mode (less bright, more silent)"); #define READ_STATUS_SIZE 13 #define MISC_VALUE_SIZE 4 -#define CMD_TIMEOUT msecs_to_jiffies(200) -#define DATA_TIMEOUT msecs_to_jiffies(1000) -#define IDLE_TIMEOUT msecs_to_jiffies(2000) -#define FIRST_FRAME_TIMEOUT msecs_to_jiffies(2000) +#define CMD_TIMEOUT 200 +#define DATA_TIMEOUT 1000 +#define IDLE_TIMEOUT 2000 +#define FIRST_FRAME_TIMEOUT 2000 #define MISC_REQ_GET_SET_ECO_A 0xff #define MISC_REQ_GET_SET_ECO_B 0x35 @@ -388,7 +388,7 @@ static void gm12u320_fb_update_work(struct work_struct *work) * switches back to showing its logo. */ queue_delayed_work(system_long_wq, &gm12u320->fb_update.work, - IDLE_TIMEOUT); + msecs_to_jiffies(IDLE_TIMEOUT)); return; err: From bc912eed8a1a673adf2678281f87f96a2f288e86 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Thu, 31 Aug 2023 22:09:29 +0800 Subject: [PATCH 1597/2093] scsi: qla2xxx: Fix NULL vs IS_ERR() bug for debugfs_create_dir() [ Upstream commit d0b0822e32dbae80bbcb3cc86f34d28539d913df ] Since both debugfs_create_dir() and debugfs_create_file() return ERR_PTR and never NULL, use IS_ERR() instead of checking for NULL. Fixes: 1e98fb0f9208 ("scsi: qla2xxx: Setup debugfs entries for remote ports") Signed-off-by: Jinjie Ruan Link: https://lore.kernel.org/r/20230831140930.3166359-1-ruanjinjie@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_dfs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c index f060e593685d..a7a364760b80 100644 --- a/drivers/scsi/qla2xxx/qla_dfs.c +++ b/drivers/scsi/qla2xxx/qla_dfs.c @@ -116,7 +116,7 @@ qla2x00_dfs_create_rport(scsi_qla_host_t *vha, struct fc_port *fp) sprintf(wwn, "pn-%016llx", wwn_to_u64(fp->port_name)); fp->dfs_rport_dir = debugfs_create_dir(wwn, vha->dfs_rport_root); - if (!fp->dfs_rport_dir) + if (IS_ERR(fp->dfs_rport_dir)) return; if (NVME_TARGET(vha->hw, fp)) debugfs_create_file("dev_loss_tmo", 0600, fp->dfs_rport_dir, @@ -708,14 +708,14 @@ qla2x00_dfs_setup(scsi_qla_host_t *vha) if (IS_QLA27XX(ha) || IS_QLA83XX(ha) || IS_QLA28XX(ha)) { ha->tgt.dfs_naqp = debugfs_create_file("naqp", 0400, ha->dfs_dir, vha, &dfs_naqp_ops); - if (!ha->tgt.dfs_naqp) { + if (IS_ERR(ha->tgt.dfs_naqp)) { ql_log(ql_log_warn, vha, 0xd011, "Unable to create debugFS naqp node.\n"); goto out; } } vha->dfs_rport_root = debugfs_create_dir("rports", ha->dfs_dir); - if (!vha->dfs_rport_root) { + if (IS_ERR(vha->dfs_rport_root)) { ql_log(ql_log_warn, vha, 0xd012, "Unable to create debugFS rports node.\n"); goto out; From 03425393f41ccbfd8831321317bfe6a6ded64bf3 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 12 Sep 2023 10:10:39 +0900 Subject: [PATCH 1598/2093] selftests: tracing: Fix to unmount tracefs for recovering environment [ Upstream commit 7e021da80f48582171029714f8a487347f29dddb ] Fix to unmount the tracefs if the ftracetest mounted it for recovering system environment. If the tracefs is already mounted, this does nothing. Suggested-by: Mark Brown Link: https://lore.kernel.org/all/29fce076-746c-4650-8358-b4e0fa215cf7@sirena.org.uk/ Fixes: cbd965bde74c ("ftrace/selftests: Return the skip code when tracing directory not configured in kernel") Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Reviewed-by: Mark Brown Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/ftrace/ftracetest | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..ef0edb7a71e3 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -30,6 +30,9 @@ err_ret=1 # kselftest skip code is 4 err_skip=4 +# umount required +UMOUNT_DIR="" + # cgroup RT scheduling prevents chrt commands from succeeding, which # induces failures in test wakeup tests. Disable for the duration of # the tests. @@ -44,6 +47,9 @@ setup() { cleanup() { echo $sched_rt_runtime_orig > $sched_rt_runtime + if [ -n "${UMOUNT_DIR}" ]; then + umount ${UMOUNT_DIR} ||: + fi } errexit() { # message @@ -155,11 +161,13 @@ if [ -z "$TRACING_DIR" ]; then mount -t tracefs nodev /sys/kernel/tracing || errexit "Failed to mount /sys/kernel/tracing" TRACING_DIR="/sys/kernel/tracing" + UMOUNT_DIR=${TRACING_DIR} # If debugfs exists, then so does /sys/kernel/debug elif [ -d "/sys/kernel/debug" ]; then mount -t debugfs nodev /sys/kernel/debug || errexit "Failed to mount /sys/kernel/debug" TRACING_DIR="/sys/kernel/debug/tracing" + UMOUNT_DIR=${TRACING_DIR} else err_ret=$err_skip errexit "debugfs and tracefs are not configured in this kernel" From e9b8e266105a6ef495ddc817b5d924c5915d8017 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Aug 2023 12:55:46 +0200 Subject: [PATCH 1599/2093] x86/ibt: Suppress spurious ENDBR [ Upstream commit 25e73b7e3f72a25aa30cbb2eecb49036e0acf066 ] It was reported that under certain circumstances GCC emits ENDBR instructions for _THIS_IP_ usage. Specifically, when it appears at the start of a basic block -- but not elsewhere. Since _THIS_IP_ is never used for control flow, these ENDBR instructions are completely superfluous. Override the _THIS_IP_ definition for x86_64 to avoid this. Less ENDBR instructions is better. Fixes: 156ff4a544ae ("x86/ibt: Base IBT bits") Reported-by: David Kaplan Reviewed-by: Andrew Cooper Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230802110323.016197440@infradead.org Signed-off-by: Sasha Levin --- arch/x86/include/asm/linkage.h | 8 ++++++++ include/linux/instruction_pointer.h | 5 +++++ 2 files changed, 13 insertions(+) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index f484d656d34e..3a0282a6a55d 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -8,6 +8,14 @@ #undef notrace #define notrace __attribute__((no_instrument_function)) +#ifdef CONFIG_64BIT +/* + * The generic version tends to create spurious ENDBR instructions under + * certain conditions. + */ +#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; }) +#endif + #ifdef CONFIG_X86_32 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) #endif /* CONFIG_X86_32 */ diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h index cda1f706eaeb..aa0b3ffea935 100644 --- a/include/linux/instruction_pointer.h +++ b/include/linux/instruction_pointer.h @@ -2,7 +2,12 @@ #ifndef _LINUX_INSTRUCTION_POINTER_H #define _LINUX_INSTRUCTION_POINTER_H +#include + #define _RET_IP_ (unsigned long)__builtin_return_address(0) + +#ifndef _THIS_IP_ #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) +#endif #endif /* _LINUX_INSTRUCTION_POINTER_H */ From dd8fce4e2da5f2966694cb9179fc8cc908f27525 Mon Sep 17 00:00:00 2001 From: Song Shuai Date: Wed, 6 Sep 2023 17:58:17 +0800 Subject: [PATCH 1600/2093] riscv: kexec: Align the kexeced kernel entry [ Upstream commit 1bfb2b618d52e59a4ef1896b46c4698ad2be66b7 ] The current riscv boot protocol requires 2MB alignment for RV64 and 4MB alignment for RV32. In KEXEC_FILE path, the elf_find_pbase() function should align the kexeced kernel entry according to the requirement, otherwise the kexeced kernel would silently BUG at the setup_vm(). Fixes: 8acea455fafa ("RISC-V: Support for kexec_file on panic") Signed-off-by: Song Shuai Link: https://lore.kernel.org/r/20230906095817.364390-1-songshuaishuai@tinylab.org Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/kernel/elf_kexec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index c08bb5c3b385..b3b96ff46d19 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -98,7 +98,13 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len, kbuf.image = image; kbuf.buf_min = lowest_paddr; kbuf.buf_max = ULONG_MAX; - kbuf.buf_align = PAGE_SIZE; + + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 + * + */ + kbuf.buf_align = PMD_SIZE; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE); kbuf.top_down = false; From 1cd41d1669bcbc5052afa897f85608a62ff3fb30 Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Thu, 31 Aug 2023 20:34:59 +0200 Subject: [PATCH 1601/2093] scsi: target: core: Fix target_cmd_counter leak [ Upstream commit d14e3e553e05cb763964c991fe6acb0a6a1c6f9c ] The target_cmd_counter struct allocated via target_alloc_cmd_counter() is never freed, resulting in leaks across various transport types, e.g.: unreferenced object 0xffff88801f920120 (size 96): comm "sh", pid 102, jiffies 4294892535 (age 713.412s) hex dump (first 32 bytes): 07 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 38 01 92 1f 80 88 ff ff ........8....... backtrace: [<00000000e58a6252>] kmalloc_trace+0x11/0x20 [<0000000043af4b2f>] target_alloc_cmd_counter+0x17/0x90 [target_core_mod] [<000000007da2dfa7>] target_setup_session+0x2d/0x140 [target_core_mod] [<0000000068feef86>] tcm_loop_tpg_nexus_store+0x19b/0x350 [tcm_loop] [<000000006a80e021>] configfs_write_iter+0xb1/0x120 [<00000000e9f4d860>] vfs_write+0x2e4/0x3c0 [<000000008143433b>] ksys_write+0x80/0xb0 [<00000000a7df29b2>] do_syscall_64+0x42/0x90 [<0000000053f45fb8>] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Free the structure alongside the corresponding iscsit_conn / se_sess parent. Signed-off-by: David Disseldorp Link: https://lore.kernel.org/r/20230831183459.6938-1-ddiss@suse.de Fixes: becd9be6069e ("scsi: target: Move sess cmd counter to new struct") Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/target_core_transport.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 687adc9e086c..0686882bcbda 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -264,6 +264,7 @@ void target_free_cmd_counter(struct target_cmd_counter *cmd_cnt) percpu_ref_put(&cmd_cnt->refcnt); percpu_ref_exit(&cmd_cnt->refcnt); + kfree(cmd_cnt); } EXPORT_SYMBOL_GPL(target_free_cmd_counter); From 6069b9d8056d540b188ae72d00db71d3e6be7068 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Wed, 6 Sep 2023 11:08:09 +0800 Subject: [PATCH 1602/2093] scsi: lpfc: Fix the NULL vs IS_ERR() bug for debugfs_create_file() [ Upstream commit 7dcc683db3639eadd11bf0d59a09088a43de5e22 ] Since debugfs_create_file() returns ERR_PTR and never NULL, use IS_ERR() to check the return value. Fixes: 2fcbc569b9f5 ("scsi: lpfc: Make debugfs ktime stats generic for NVME and SCSI") Fixes: 4c47efc140fa ("scsi: lpfc: Move SCSI and NVME Stats to hardware queue structures") Fixes: 6a828b0f6192 ("scsi: lpfc: Support non-uniform allocation of MSIX vectors to hardware queues") Fixes: 95bfc6d8ad86 ("scsi: lpfc: Make FW logging dynamically configurable") Fixes: 9f77870870d8 ("scsi: lpfc: Add debugfs support for cm framework buffers") Fixes: c490850a0947 ("scsi: lpfc: Adapt partitioned XRI lists to efficient sharing") Signed-off-by: Jinjie Ruan Link: https://lore.kernel.org/r/20230906030809.2847970-1-ruanjinjie@huawei.com Reviewed-by: Justin Tee Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_debugfs.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 3e365e5e194a..250d423710ca 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -6069,7 +6069,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) phba->hba_debugfs_root, phba, &lpfc_debugfs_op_multixripools); - if (!phba->debug_multixri_pools) { + if (IS_ERR(phba->debug_multixri_pools)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "0527 Cannot create debugfs multixripools\n"); goto debug_failed; @@ -6081,7 +6081,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) debugfs_create_file(name, S_IFREG | 0644, phba->hba_debugfs_root, phba, &lpfc_cgn_buffer_op); - if (!phba->debug_cgn_buffer) { + if (IS_ERR(phba->debug_cgn_buffer)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "6527 Cannot create debugfs " "cgn_buffer\n"); @@ -6094,7 +6094,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) debugfs_create_file(name, S_IFREG | 0644, phba->hba_debugfs_root, phba, &lpfc_rx_monitor_op); - if (!phba->debug_rx_monitor) { + if (IS_ERR(phba->debug_rx_monitor)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "6528 Cannot create debugfs " "rx_monitor\n"); @@ -6107,7 +6107,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) debugfs_create_file(name, 0644, phba->hba_debugfs_root, phba, &lpfc_debugfs_ras_log); - if (!phba->debug_ras_log) { + if (IS_ERR(phba->debug_ras_log)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "6148 Cannot create debugfs" " ras_log\n"); @@ -6128,7 +6128,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) debugfs_create_file(name, S_IFREG | 0644, phba->hba_debugfs_root, phba, &lpfc_debugfs_op_lockstat); - if (!phba->debug_lockstat) { + if (IS_ERR(phba->debug_lockstat)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "4610 Can't create debugfs lockstat\n"); goto debug_failed; @@ -6354,7 +6354,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) debugfs_create_file(name, 0644, vport->vport_debugfs_root, vport, &lpfc_debugfs_op_scsistat); - if (!vport->debug_scsistat) { + if (IS_ERR(vport->debug_scsistat)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "4611 Cannot create debugfs scsistat\n"); goto debug_failed; @@ -6365,7 +6365,7 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) debugfs_create_file(name, 0644, vport->vport_debugfs_root, vport, &lpfc_debugfs_op_ioktime); - if (!vport->debug_ioktime) { + if (IS_ERR(vport->debug_ioktime)) { lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT, "0815 Cannot create debugfs ioktime\n"); goto debug_failed; From 038249ee7264b331d6161f315257a4058f00f265 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 15 Sep 2023 09:55:39 +0200 Subject: [PATCH 1603/2093] panic: Reenable preemption in WARN slowpath [ Upstream commit cccd32816506cbac3a4c65d9dff51b3125ef1a03 ] Commit: 5a5d7e9badd2 ("cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG") amended warn_slowpath_fmt() to disable preemption until the WARN splat has been emitted. However the commit neglected to reenable preemption in the !fmt codepath, i.e. when a WARN splat is emitted without additional format string. One consequence is that users may see more splats than intended. E.g. a WARN splat emitted in a work item results in at least two extra splats: BUG: workqueue leaked lock or atomic (emitted by process_one_work()) BUG: scheduling while atomic (emitted by worker_thread() -> schedule()) Ironically the point of the commit was to *avoid* extra splats. ;) Fix it. Fixes: 5a5d7e9badd2 ("cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG") Signed-off-by: Lukas Wunner Signed-off-by: Ingo Molnar Cc: Linus Torvalds Cc: Thomas Gleixner Cc: Paul E. McKenney Link: https://lore.kernel.org/r/3ec48fde01e4ee6505f77908ba351bad200ae3d1.1694763684.git.lukas@wunner.de Signed-off-by: Sasha Levin --- kernel/panic.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/panic.c b/kernel/panic.c index ca5452afb456..63e94f3bd8dc 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -695,6 +695,7 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint, if (!fmt) { __warn(file, line, __builtin_return_address(0), taint, NULL, NULL); + warn_rcu_exit(rcu); return; } From 2074cb608cb538e242fb1d43c2de37b0962ea4ac Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Sep 2023 10:02:21 +0300 Subject: [PATCH 1604/2093] x86/boot/compressed: Reserve more memory for page tables [ Upstream commit f530ee95b72e77b09c141c4b1a4b94d1199ffbd9 ] The decompressor has a hard limit on the number of page tables it can allocate. This limit is defined at compile-time and will cause boot failure if it is reached. The kernel is very strict and calculates the limit precisely for the worst-case scenario based on the current configuration. However, it is easy to forget to adjust the limit when a new use-case arises. The worst-case scenario is rarely encountered during sanity checks. In the case of enabling 5-level paging, a use-case was overlooked. The limit needs to be increased by one to accommodate the additional level. This oversight went unnoticed until Aaron attempted to run the kernel via kexec with 5-level paging and unaccepted memory enabled. Update wost-case calculations to include 5-level paging. To address this issue, let's allocate some extra space for page tables. 128K should be sufficient for any use-case. The logic can be simplified by using a single value for all kernel configurations. [ Also add a warning, should this memory run low - by Dave Hansen. ] Fixes: 34bbb0009f3b ("x86/boot/compressed: Enable 5-level paging during decompression stage") Reported-by: Aaron Lu Signed-off-by: Kirill A. Shutemov Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915070221.10266-1-kirill.shutemov@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/boot/compressed/ident_map_64.c | 8 +++++ arch/x86/include/asm/boot.h | 47 +++++++++++++++++-------- 2 files changed, 40 insertions(+), 15 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 321a5011042d..b4155273df89 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -67,6 +67,14 @@ static void *alloc_pgt_page(void *context) return NULL; } + /* Consumed more tables than expected? */ + if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) { + debug_putstr("pgt_buf running low in " __FILE__ "\n"); + debug_putstr("Need to raise BOOT_PGT_SIZE?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + } + entry = pages->pgt_buf + pages->pgt_buf_offset; pages->pgt_buf_offset += PAGE_SIZE; diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 9191280d9ea3..215d37f7dde8 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -40,23 +40,40 @@ #ifdef CONFIG_X86_64 # define BOOT_STACK_SIZE 0x4000 -# define BOOT_INIT_PGT_SIZE (6*4096) -# ifdef CONFIG_RANDOMIZE_BASE /* - * Assuming all cross the 512GB boundary: - * 1 page for level4 - * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel - * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP). - * Total is 19 pages. + * Used by decompressor's startup_32() to allocate page tables for identity + * mapping of the 4G of RAM in 4-level paging mode: + * - 1 level4 table; + * - 1 level3 table; + * - 4 level2 table that maps everything with 2M pages; + * + * The additional level5 table needed for 5-level paging is allocated from + * trampoline_32bit memory. */ -# ifdef CONFIG_X86_VERBOSE_BOOTUP -# define BOOT_PGT_SIZE (19*4096) -# else /* !CONFIG_X86_VERBOSE_BOOTUP */ -# define BOOT_PGT_SIZE (17*4096) -# endif -# else /* !CONFIG_RANDOMIZE_BASE */ -# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE -# endif +# define BOOT_INIT_PGT_SIZE (6*4096) + +/* + * Total number of page tables kernel_add_identity_map() can allocate, + * including page tables consumed by startup_32(). + * + * Worst-case scenario: + * - 5-level paging needs 1 level5 table; + * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel, + * assuming all of them cross 256T boundary: + * + 4*2 level4 table; + * + 4*2 level3 table; + * + 4*2 level2 table; + * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM): + * + 1 level4 table; + * + 1 level3 table; + * + 1 level2 table; + * Total: 28 tables + * + * Add 4 spare table in case decompressor touches anything beyond what is + * accounted above. Warn if it happens. + */ +# define BOOT_PGT_SIZE_WARN (28*4096) +# define BOOT_PGT_SIZE (32*4096) #else /* !CONFIG_X86_64 */ # define BOOT_STACK_SIZE 0x1000 From 0dea06849924818e4dd679b3e406edcfdd20c801 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 14 Sep 2023 10:01:38 -0700 Subject: [PATCH 1605/2093] x86/purgatory: Remove LTO flags [ Upstream commit 75b2f7e4c9e0fd750a5a27ca9736d1daa7a3762a ] -flto* implies -ffunction-sections. With LTO enabled, ld.lld generates multiple .text sections for purgatory.ro: $ readelf -S purgatory.ro | grep " .text" [ 1] .text PROGBITS 0000000000000000 00000040 [ 7] .text.purgatory PROGBITS 0000000000000000 000020e0 [ 9] .text.warn PROGBITS 0000000000000000 000021c0 [13] .text.sha256_upda PROGBITS 0000000000000000 000022f0 [15] .text.sha224_upda PROGBITS 0000000000000000 00002be0 [17] .text.sha256_fina PROGBITS 0000000000000000 00002bf0 [19] .text.sha224_fina PROGBITS 0000000000000000 00002cc0 This causes WARNING from kexec_purgatory_setup_sechdrs(): WARNING: CPU: 26 PID: 110894 at kernel/kexec_file.c:919 kexec_load_purgatory+0x37f/0x390 Fix this by disabling LTO for purgatory. [ AFAICT, x86 is the only arch that supports LTO and purgatory. ] We could also fix this with an explicit linker script to rejoin .text.* sections back into .text. However, given the benefit of LTOing purgatory is small, simply disable the production of more .text.* sections for now. Fixes: b33fff07e3e3 ("x86, build: allow LTO to be selected") Signed-off-by: Song Liu Signed-off-by: Ingo Molnar Reviewed-by: Nick Desaulniers Reviewed-by: Sami Tolvanen Link: https://lore.kernel.org/r/20230914170138.995606-1-song@kernel.org Signed-off-by: Sasha Levin --- arch/x86/purgatory/Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 42abd6af1198..d28e0987aa85 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -19,6 +19,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS # optimization flags. KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) +# When LTO is enabled, llvm emits many text sections, which is not supported +# by kexec. Remove -flto=* flags. +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib From 2076b4b677c31b99e8ce9bcab783ec4fb6adc15b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 25 Jul 2023 10:25:36 +0200 Subject: [PATCH 1606/2093] samples/hw_breakpoint: fix building without module unloading [ Upstream commit b9080468caeddc58a91edd1c3a7d212ea82b0d1d ] __symbol_put() is really meant as an internal helper and is not available when module unloading is disabled, unlike the previously used symbol_put(): samples/hw_breakpoint/data_breakpoint.c: In function 'hw_break_module_exit': samples/hw_breakpoint/data_breakpoint.c:73:9: error: implicit declaration of function '__symbol_put'; did you mean '__symbol_get'? [-Werror=implicit-function-declaration] The hw_break_module_exit() function is not actually used when module unloading is disabled, but it still causes the build failure for an undefined identifier. Enclose this one call in an appropriate #ifdef to clarify what the requirement is. Leaving out the entire exit function would also work but feels less clar in this case. Fixes: 910e230d5f1bb ("samples/hw_breakpoint: Fix kernel BUG 'invalid opcode: 0000'") Fixes: d8a84d33a4954 ("samples/hw_breakpoint: drop use of kallsyms_lookup_name()") Signed-off-by: Arnd Bergmann Reviewed-by: Petr Mladek Signed-off-by: Luis Chamberlain Signed-off-by: Sasha Levin --- samples/hw_breakpoint/data_breakpoint.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c index 9debd128b2ab..b99322f188e5 100644 --- a/samples/hw_breakpoint/data_breakpoint.c +++ b/samples/hw_breakpoint/data_breakpoint.c @@ -70,7 +70,9 @@ static int __init hw_break_module_init(void) static void __exit hw_break_module_exit(void) { unregister_wide_hw_breakpoint(sample_hbp); +#ifdef CONFIG_MODULE_UNLOAD __symbol_put(ksym_name); +#endif printk(KERN_INFO "HW Breakpoint for %s write uninstalled\n", ksym_name); } From ba4f28a1d3626201108439a0272deb3076dbcbb1 Mon Sep 17 00:00:00 2001 From: Nigel Croxon Date: Mon, 11 Sep 2023 14:25:23 -0700 Subject: [PATCH 1607/2093] md/raid1: fix error: ISO C90 forbids mixed declarations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit df203da47f4428bc286fc99318936416253a321c ] There is a compile error when this commit is added: md: raid1: fix potential OOB in raid1_remove_disk() drivers/md/raid1.c: In function 'raid1_remove_disk': drivers/md/raid1.c:1844:9: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 1844 |         struct raid1_info *p = conf->mirrors + number;     |         ^~~~~~ That's because the new code was inserted before the struct. The change is move the struct command above this commit. Fixes: 8b0472b50bcf ("md: raid1: fix potential OOB in raid1_remove_disk()") Signed-off-by: Nigel Croxon Signed-off-by: Song Liu Link: https://lore.kernel.org/r/46d929d0-2aab-4cf2-b2bf-338963e8ba5a@redhat.com Signed-off-by: Sasha Levin --- drivers/md/raid1.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 72303c620174..30f906a67def 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1826,12 +1826,11 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct r1conf *conf = mddev->private; int err = 0; int number = rdev->raid_disk; + struct raid1_info *p = conf->mirrors + number; if (unlikely(number >= conf->raid_disks)) goto abort; - struct raid1_info *p = conf->mirrors + number; - if (rdev != p->rdev) p = conf->mirrors + conf->raid_disks + number; From 3494a0066d8a7baf236a471841d8a81cee969e15 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Sep 2023 21:03:28 -0400 Subject: [PATCH 1608/2093] Revert "SUNRPC: Fail faster on bad verifier" commit e86fcf0820d914389b46658a5a7e8969c3af2d53 upstream. This reverts commit 0701214cd6e66585a999b132eb72ae0489beb724. The premise of this commit was incorrect. There are exactly 2 cases where rpcauth_checkverf() will return an error: 1) If there was an XDR decode problem (i.e. garbage data). 2) If gss_validate() had a problem verifying the RPCSEC_GSS MIC. In the second case, there are again 2 subcases: a) The GSS context expires, in which case gss_validate() will force a new context negotiation on retry by invalidating the cred. b) The sequence number check failed because an RPC call timed out, and the client retransmitted the request using a new sequence number, as required by RFC2203. In neither subcase is this a fatal error. Reported-by: Russell Cattelan Fixes: 0701214cd6e6 ("SUNRPC: Fail faster on bad verifier") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/clnt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d2ee56634308..b0258507b236 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2710,7 +2710,7 @@ rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr) out_verifier: trace_rpc_bad_verifier(task); - goto out_err; + goto out_garbage; out_msg_denied: error = -EACCES; From 6a84939cc7dd6f970c2621ded82c4d9ea0068b1b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 12 Jul 2023 20:58:49 +0200 Subject: [PATCH 1609/2093] attr: block mode changes of symlinks commit 5d1f903f75a80daa4dfb3d84e114ec8ecbf29956 upstream. Changing the mode of symlinks is meaningless as the vfs doesn't take the mode of a symlink into account during path lookup permission checking. However, the vfs doesn't block mode changes on symlinks. This however, has lead to an untenable mess roughly classifiable into the following two categories: (1) Filesystems that don't implement a i_op->setattr() for symlinks. Such filesystems may or may not know that without i_op->setattr() defined, notify_change() falls back to simple_setattr() causing the inode's mode in the inode cache to be changed. That's a generic issue as this will affect all non-size changing inode attributes including ownership changes. Example: afs (2) Filesystems that fail with EOPNOTSUPP but change the mode of the symlink nonetheless. Some filesystems will happily update the mode of a symlink but still return EOPNOTSUPP. This is the biggest source of confusion for userspace. The EOPNOTSUPP in this case comes from POSIX ACLs. Specifically it comes from filesystems that call posix_acl_chmod(), e.g., btrfs via if (!err && attr->ia_valid & ATTR_MODE) err = posix_acl_chmod(idmap, dentry, inode->i_mode); Filesystems including btrfs don't implement i_op->set_acl() so posix_acl_chmod() will report EOPNOTSUPP. When posix_acl_chmod() is called, most filesystems will have finished updating the inode. Perversely, this has the consequences that this behavior may depend on two kconfig options and mount options: * CONFIG_POSIX_ACL={y,n} * CONFIG_${FSTYPE}_POSIX_ACL={y,n} * Opt_acl, Opt_noacl Example: btrfs, ext4, xfs The only way to change the mode on a symlink currently involves abusing an O_PATH file descriptor in the following manner: fd = openat(-1, "/path/to/link", O_CLOEXEC | O_PATH | O_NOFOLLOW); char path[PATH_MAX]; snprintf(path, sizeof(path), "/proc/self/fd/%d", fd); chmod(path, 0000); But for most major filesystems with POSIX ACL support such as btrfs, ext4, ceph, tmpfs, xfs and others this will fail with EOPNOTSUPP with the mode still updated due to the aforementioned posix_acl_chmod() nonsense. So, given that for all major filesystems this would fail with EOPNOTSUPP and that both glibc (cf. [1]) and musl (cf. [2]) outright block mode changes on symlinks we should just try and block mode changes on symlinks directly in the vfs and have a clean break with this nonsense. If this causes any regressions, we do the next best thing and fix up all filesystems that do return EOPNOTSUPP with the mode updated to not call posix_acl_chmod() on symlinks. But as usual, let's try the clean cut solution first. It's a simple patch that can be easily reverted. Not marking this for backport as I'll do that manually if we're reasonably sure that this works and there are no strong objections. We could block this in chmod_common() but it's more appropriate to do it notify_change() as it will also mean that we catch filesystems that change symlink permissions explicitly or accidently. Similar proposals were floated in the past as in [3] and [4] and again recently in [5]. There's also a couple of bugs about this inconsistency as in [6] and [7]. Link: https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/fchmodat.c;h=99527a3727e44cb8661ee1f743068f108ec93979;hb=HEAD [1] Link: https://git.musl-libc.org/cgit/musl/tree/src/stat/fchmodat.c [2] Link: https://lore.kernel.org/all/20200911065733.GA31579@infradead.org [3] Link: https://sourceware.org/legacy-ml/libc-alpha/2020-02/msg00518.html [4] Link: https://lore.kernel.org/lkml/87lefmbppo.fsf@oldenburg.str.redhat.com [5] Link: https://sourceware.org/legacy-ml/libc-alpha/2020-02/msg00467.html [6] Link: https://sourceware.org/bugzilla/show_bug.cgi?id=14578#c17 [7] Reviewed-by: Aleksa Sarai Reviewed-by: Christoph Hellwig Cc: stable@vger.kernel.org # please backport to all LTSes but not before v6.6-rc2 is tagged Suggested-by: Christoph Hellwig Suggested-by: Florian Weimer Message-Id: <20230712-vfs-chmod-symlinks-v2-1-08cfb92b61dd@kernel.org> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/attr.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index 9b9a70e0cc54..3172f57f71f8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -394,9 +394,25 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, return error; if ((ia_valid & ATTR_MODE)) { - umode_t amode = attr->ia_mode; + /* + * Don't allow changing the mode of symlinks: + * + * (1) The vfs doesn't take the mode of symlinks into account + * during permission checking. + * (2) This has never worked correctly. Most major filesystems + * did return EOPNOTSUPP due to interactions with POSIX ACLs + * but did still updated the mode of the symlink. + * This inconsistency led system call wrapper providers such + * as libc to block changing the mode of symlinks with + * EOPNOTSUPP already. + * (3) To even do this in the first place one would have to use + * specific file descriptors and quite some effort. + */ + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + /* Flag setting protected by i_mutex */ - if (is_sxid(amode)) + if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } From 17854d92fa4a7d40463a83d558774b6f8ba1749a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 4 Sep 2023 14:17:56 +0300 Subject: [PATCH 1610/2093] ovl: fix failed copyup of fileattr on a symlink commit ab048302026d7701e7fbd718917e0dbcff0c4223 upstream. Some local filesystems support setting persistent fileattr flags (e.g. FS_NOATIME_FL) on directories and regular files via ioctl. Some of those persistent fileattr flags are reflected to vfs as in-memory inode flags (e.g. S_NOATIME). Overlayfs uses the in-memory inode flags (e.g. S_NOATIME) on a lower file as an indication that a the lower file may have persistent inode fileattr flags (e.g. FS_NOATIME_FL) that need to be copied to upper file. However, in some cases, the S_NOATIME in-memory flag could be a false indication for persistent FS_NOATIME_FL fileattr. For example, with NFS and FUSE lower fs, as was the case in the two bug reports, the S_NOATIME flag is set unconditionally for all inodes. Users cannot set persistent fileattr flags on symlinks and special files, but in some local fs, such as ext4/btrfs/tmpfs, the FS_NOATIME_FL fileattr flag are inheritted to symlinks and special files from parent directory. In both cases described above, when lower symlink has the S_NOATIME flag, overlayfs will try to copy the symlink's fileattrs and fail with error ENOXIO, because it could not open the symlink for the ioctl security hook. To solve this failure, do not attempt to copyup fileattrs for anything other than directories and regular files. Reported-by: Ruiwen Zhao Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217850 Fixes: 72db82115d2b ("ovl: copy up sync/noatime fileattr flags") Cc: # v5.15 Reviewed-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/copy_up.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index edc1ebff33f5..e6d711f42607 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -580,7 +580,8 @@ static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp) if (err) return err; - if (inode->i_flags & OVL_COPY_I_FLAGS_MASK) { + if (inode->i_flags & OVL_COPY_I_FLAGS_MASK && + (S_ISREG(c->stat.mode) || S_ISDIR(c->stat.mode))) { /* * Copy the fileattr inode flags that are the source of already * copied i_flags From e7dcf8339a0f3290944a301d22063d96c9aa4f70 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Tue, 22 Aug 2023 20:50:59 +0300 Subject: [PATCH 1611/2093] ovl: fix incorrect fdput() on aio completion commit 724768a39374d35b70eaeae8dd87048a2ec7ae8e upstream. ovl_{read,write}_iter() always call fdput(real) to put one or zero refcounts of the real file, but for aio, whether it was submitted or not, ovl_aio_put() also calls fdput(), which is not balanced. This is only a problem in the less common case when FDPUT_FPUT flag is set. To fix the problem use get_file() to take file refcount and use fput() instead of fdput() in ovl_aio_put(). Fixes: 2406a307ac7d ("ovl: implement async IO routines") Cc: # v5.6 Reviewed-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/file.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 6011f955436b..cc0c077165bd 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -19,7 +19,6 @@ struct ovl_aio_req { struct kiocb iocb; refcount_t ref; struct kiocb *orig_iocb; - struct fd fd; }; static struct kmem_cache *ovl_aio_request_cachep; @@ -260,7 +259,7 @@ static rwf_t ovl_iocb_to_rwf(int ifl) static inline void ovl_aio_put(struct ovl_aio_req *aio_req) { if (refcount_dec_and_test(&aio_req->ref)) { - fdput(aio_req->fd); + fput(aio_req->iocb.ki_filp); kmem_cache_free(ovl_aio_request_cachep, aio_req); } } @@ -325,10 +324,9 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (!aio_req) goto out; - aio_req->fd = real; real.flags = 0; aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, real.file); + kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_complete = ovl_aio_rw_complete; refcount_set(&aio_req->ref, 2); ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter); @@ -396,10 +394,9 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) /* Pacify lockdep, same trick as done in aio_write() */ __sb_writers_release(file_inode(real.file)->i_sb, SB_FREEZE_WRITE); - aio_req->fd = real; real.flags = 0; aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, real.file); + kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_flags = ifl; aio_req->iocb.ki_complete = ovl_aio_rw_complete; refcount_set(&aio_req->ref, 2); From 6a1d1365fafe1b63e6c52ef72b40b1443a11f78c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 14 Sep 2023 16:51:09 +0100 Subject: [PATCH 1612/2093] io_uring/net: fix iter retargeting for selected buf commit c21a8027ad8a68c340d0d58bf1cc61dcb0bc4d2f upstream. When using selected buffer feature, io_uring delays data iter setup until later. If io_setup_async_msg() is called before that it might see not correctly setup iterator. Pre-init nr_segs and judge from its state whether we repointing. Cc: stable@vger.kernel.org Reported-by: syzbot+a4c6e5ef999b68b26ed1@syzkaller.appspotmail.com Fixes: 0455d4ccec548 ("io_uring: add POLL_FIRST support for send/sendmsg and recv/recvmsg") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0000000000002770be06053c7757@google.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/net.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/io_uring/net.c b/io_uring/net.c index 7245218fdbe2..9fe1aada3ad0 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -170,6 +170,10 @@ static int io_setup_async_msg(struct io_kiocb *req, memcpy(async_msg, kmsg, sizeof(*kmsg)); if (async_msg->msg.msg_name) async_msg->msg.msg_name = &async_msg->addr; + + if ((req->flags & REQ_F_BUFFER_SELECT) && !async_msg->msg.msg_iter.nr_segs) + return -EAGAIN; + /* if were using fast_iov, set it to the new one */ if (!kmsg->free_iov) { size_t fast_idx = kmsg->msg.msg_iter.iov - kmsg->fast_iov; @@ -529,6 +533,7 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { iomsg->msg.msg_name = &iomsg->addr; + iomsg->msg.msg_iter.nr_segs = 0; #ifdef CONFIG_COMPAT if (req->ctx->compat) From f07c0bc27b0ec72f5de1495b20a13b496e162be0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 12 Sep 2023 14:38:58 -0700 Subject: [PATCH 1613/2093] nvme: avoid bogus CRTO values MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6cc834ba62998c65c42d0c63499bdd35067151ec upstream. Some devices are reporting controller ready mode support, but return 0 for CRTO. These devices require a much higher time to ready than that, so they are failing to initialize after the driver starter preferring that value over CAP.TO. The spec requires that CAP.TO match the appropritate CRTO value, or be set to 0xff if CRTO is larger than that. This means that CAP.TO can be used to validate if CRTO is reliable, and provides an appropriate fallback for setting the timeout value if not. Use whichever is larger. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217863 Reported-by: Cláudio Sampaio Reported-by: Felix Yan Tested-by: Felix Yan Based-on-a-patch-by: Felix Yan Cc: stable@vger.kernel.org Signed-off-by: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/nvme/host/core.c | 54 ++++++++++++++++++++++++++-------------- 1 file changed, 35 insertions(+), 19 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fd73db8a535d..25ddfabc58f7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2368,25 +2368,8 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) else ctrl->ctrl_config = NVME_CC_CSS_NVM; - if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { - u32 crto; - - ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); - if (ret) { - dev_err(ctrl->device, "Reading CRTO failed (%d)\n", - ret); - return ret; - } - - if (ctrl->cap & NVME_CAP_CRMS_CRIMS) { - ctrl->ctrl_config |= NVME_CC_CRIME; - timeout = NVME_CRTO_CRIMT(crto); - } else { - timeout = NVME_CRTO_CRWMT(crto); - } - } else { - timeout = NVME_CAP_TIMEOUT(ctrl->cap); - } + if (ctrl->cap & NVME_CAP_CRMS_CRWMS && ctrl->cap & NVME_CAP_CRMS_CRIMS) + ctrl->ctrl_config |= NVME_CC_CRIME; ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT; ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE; @@ -2400,6 +2383,39 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) if (ret) return ret; + /* CAP value may change after initial CC write */ + ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); + if (ret) + return ret; + + timeout = NVME_CAP_TIMEOUT(ctrl->cap); + if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { + u32 crto, ready_timeout; + + ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); + if (ret) { + dev_err(ctrl->device, "Reading CRTO failed (%d)\n", + ret); + return ret; + } + + /* + * CRTO should always be greater or equal to CAP.TO, but some + * devices are known to get this wrong. Use the larger of the + * two values. + */ + if (ctrl->ctrl_config & NVME_CC_CRIME) + ready_timeout = NVME_CRTO_CRIMT(crto); + else + ready_timeout = NVME_CRTO_CRWMT(crto); + + if (ready_timeout < timeout) + dev_warn_once(ctrl->device, "bad crto:%x cap:%llx\n", + crto, ctrl->cap); + else + timeout = ready_timeout; + } + ctrl->ctrl_config |= NVME_CC_ENABLE; ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); if (ret) From 98ea94f1627b6b5689ecb23bdd56673bef42e814 Mon Sep 17 00:00:00 2001 From: Mariusz Tkaczyk Date: Thu, 14 Sep 2023 17:24:16 +0200 Subject: [PATCH 1614/2093] md: Put the right device in md_seq_next commit c8870379a21fbd9ad14ca36204ccfbe9d25def43 upstream. If there are multiple arrays in system and one mddevice is marked with MD_DELETED and md_seq_next() is called in the middle of removal then it _get()s proper device but it may _put() deleted one. As a result, active counter may never be zeroed for mddevice and it cannot be removed. Put the device which has been _get with previous md_seq_next() call. Cc: stable@vger.kernel.org Fixes: 12a6caf27324 ("md: only delete entries from all_mddevs when the disk is freed") Reported-by: AceLan Kao Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217798 Cc: Yu Kuai Signed-off-by: Mariusz Tkaczyk Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230914152416.10819-1-mariusz.tkaczyk@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 86b2acfba1a7..e87507d29895 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8228,7 +8228,7 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) spin_unlock(&all_mddevs_lock); if (to_put) - mddev_put(mddev); + mddev_put(to_put); return next_mddev; } From 216eae7d7dea5fdd854d7decb44fcf3b719548a0 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Fri, 8 Sep 2023 10:36:44 -0400 Subject: [PATCH 1615/2093] Revert "drm/amd: Disable S/G for APUs when 64GB or more host memory" commit 169ed4ece8373f02f10642eae5240e3d1ef5c038 upstream. This reverts commit 70e64c4d522b732e31c6475a3be2349de337d321. Since, we now have an actual fix for this issue, we can get rid of this workaround as it can cause pin failures if enough VRAM isn't carved out by the BIOS. Cc: stable@vger.kernel.org # 6.1+ Acked-by: Harry Wentland Reviewed-by: Alex Deucher Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 ------------------- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++-- 3 files changed, 3 insertions(+), 29 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 0c962f996aff..c46c6fbd235e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1266,7 +1266,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); -bool amdgpu_sg_display_supported(struct amdgpu_device *adev); bool amdgpu_device_pcie_dynamic_switching_supported(void); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); bool amdgpu_device_aspm_support_quirk(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 9aac9e755609..5f5999cea7d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1336,32 +1336,6 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; } -/* - * On APUs with >= 64GB white flickering has been observed w/ SG enabled. - * Disable S/G on such systems until we have a proper fix. - * https://gitlab.freedesktop.org/drm/amd/-/issues/2354 - * https://gitlab.freedesktop.org/drm/amd/-/issues/2735 - */ -bool amdgpu_sg_display_supported(struct amdgpu_device *adev) -{ - switch (amdgpu_sg_display) { - case -1: - break; - case 0: - return false; - case 1: - return true; - default: - return false; - } - if ((totalram_pages() << (PAGE_SHIFT - 10)) + - (adev->gmc.real_vram_size / 1024) >= 64000000) { - DRM_WARN("Disabling S/G due to >=64GB RAM\n"); - return false; - } - return true; -} - /* * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic * speed switching. Until we have confirmation from Intel that a specific host diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c8e562dcd99d..208eeff50390 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1634,8 +1634,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } break; } - if (init_data.flags.gpu_vm_support) - init_data.flags.gpu_vm_support = amdgpu_sg_display_supported(adev); + if (init_data.flags.gpu_vm_support && + (amdgpu_sg_display == 0)) + init_data.flags.gpu_vm_support = false; if (init_data.flags.gpu_vm_support) adev->mode_info.gpu_vm_support = true; From d7b2abd87d1fcdb47811f90090a363e7ca15cb14 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 Sep 2023 13:14:23 -0600 Subject: [PATCH 1616/2093] dm: don't attempt to queue IO under RCU protection commit a9ce385344f916cd1c36a33905e564f5581beae9 upstream. dm looks up the table for IO based on the request type, with an assumption that if the request is marked REQ_NOWAIT, it's fine to attempt to submit that IO while under RCU read lock protection. This is not OK, as REQ_NOWAIT just means that we should not be sleeping waiting on other IO, it does not mean that we can't potentially schedule. A simple test case demonstrates this quite nicely: int main(int argc, char *argv[]) { struct iovec iov; int fd; fd = open("/dev/dm-0", O_RDONLY | O_DIRECT); posix_memalign(&iov.iov_base, 4096, 4096); iov.iov_len = 4096; preadv2(fd, &iov, 1, 0, RWF_NOWAIT); return 0; } which will instantly spew: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:306 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 5580, name: dm-nowait preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 INFO: lockdep is turned off. CPU: 7 PID: 5580 Comm: dm-nowait Not tainted 6.6.0-rc1-g39956d2dcd81 #132 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 Call Trace: dump_stack_lvl+0x11d/0x1b0 __might_resched+0x3c3/0x5e0 ? preempt_count_sub+0x150/0x150 mempool_alloc+0x1e2/0x390 ? mempool_resize+0x7d0/0x7d0 ? lock_sync+0x190/0x190 ? lock_release+0x4b7/0x670 ? internal_get_user_pages_fast+0x868/0x2d40 bio_alloc_bioset+0x417/0x8c0 ? bvec_alloc+0x200/0x200 ? internal_get_user_pages_fast+0xb8c/0x2d40 bio_alloc_clone+0x53/0x100 dm_submit_bio+0x27f/0x1a20 ? lock_release+0x4b7/0x670 ? blk_try_enter_queue+0x1a0/0x4d0 ? dm_dax_direct_access+0x260/0x260 ? rcu_is_watching+0x12/0xb0 ? blk_try_enter_queue+0x1cc/0x4d0 __submit_bio+0x239/0x310 ? __bio_queue_enter+0x700/0x700 ? kvm_clock_get_cycles+0x40/0x60 ? ktime_get+0x285/0x470 submit_bio_noacct_nocheck+0x4d9/0xb80 ? should_fail_request+0x80/0x80 ? preempt_count_sub+0x150/0x150 ? lock_release+0x4b7/0x670 ? __bio_add_page+0x143/0x2d0 ? iov_iter_revert+0x27/0x360 submit_bio_noacct+0x53e/0x1b30 submit_bio_wait+0x10a/0x230 ? submit_bio_wait_endio+0x40/0x40 __blkdev_direct_IO_simple+0x4f8/0x780 ? blkdev_bio_end_io+0x4c0/0x4c0 ? stack_trace_save+0x90/0xc0 ? __bio_clone+0x3c0/0x3c0 ? lock_release+0x4b7/0x670 ? lock_sync+0x190/0x190 ? atime_needs_update+0x3bf/0x7e0 ? timestamp_truncate+0x21b/0x2d0 ? inode_owner_or_capable+0x240/0x240 blkdev_direct_IO.part.0+0x84a/0x1810 ? rcu_is_watching+0x12/0xb0 ? lock_release+0x4b7/0x670 ? blkdev_read_iter+0x40d/0x530 ? reacquire_held_locks+0x4e0/0x4e0 ? __blkdev_direct_IO_simple+0x780/0x780 ? rcu_is_watching+0x12/0xb0 ? __mark_inode_dirty+0x297/0xd50 ? preempt_count_add+0x72/0x140 blkdev_read_iter+0x2a4/0x530 do_iter_readv_writev+0x2f2/0x3c0 ? generic_copy_file_range+0x1d0/0x1d0 ? fsnotify_perm.part.0+0x25d/0x630 ? security_file_permission+0xd8/0x100 do_iter_read+0x31b/0x880 ? import_iovec+0x10b/0x140 vfs_readv+0x12d/0x1a0 ? vfs_iter_read+0xb0/0xb0 ? rcu_is_watching+0x12/0xb0 ? rcu_is_watching+0x12/0xb0 ? lock_release+0x4b7/0x670 do_preadv+0x1b3/0x260 ? do_readv+0x370/0x370 __x64_sys_preadv2+0xef/0x150 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5af41ad806 Code: 41 54 41 89 fc 55 44 89 c5 53 48 89 cb 48 83 ec 18 80 3d e4 dd 0d 00 00 74 7a 45 89 c1 49 89 ca 45 31 c0 b8 47 01 00 00 0f 05 <48> 3d 00 f0 ff ff 0f 87 be 00 00 00 48 85 c0 79 4a 48 8b 0d da 55 RSP: 002b:00007ffd3145c7f0 EFLAGS: 00000246 ORIG_RAX: 0000000000000147 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5af41ad806 RDX: 0000000000000001 RSI: 00007ffd3145c850 RDI: 0000000000000003 RBP: 0000000000000008 R08: 0000000000000000 R09: 0000000000000008 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 00007ffd3145c850 R14: 000055f5f0431dd8 R15: 0000000000000001 where in fact it is dm itself that attempts to allocate a bio clone with GFP_NOIO under the rcu read lock, regardless of the request type. Fix this by getting rid of the special casing for REQ_NOWAIT, and just use the normal SRCU protected table lookup. Get rid of the bio based table locking helpers at the same time, as they are now unused. Cc: stable@vger.kernel.org Fixes: 563a225c9fd2 ("dm: introduce dm_{get,put}_live_table_bio called from dm_submit_bio") Signed-off-by: Jens Axboe Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm.c | 23 ++--------------------- 1 file changed, 2 insertions(+), 21 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index acf7e7551c94..0ec85d159bcd 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -707,24 +707,6 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU) rcu_read_unlock(); } -static inline struct dm_table *dm_get_live_table_bio(struct mapped_device *md, - int *srcu_idx, blk_opf_t bio_opf) -{ - if (bio_opf & REQ_NOWAIT) - return dm_get_live_table_fast(md); - else - return dm_get_live_table(md, srcu_idx); -} - -static inline void dm_put_live_table_bio(struct mapped_device *md, int srcu_idx, - blk_opf_t bio_opf) -{ - if (bio_opf & REQ_NOWAIT) - dm_put_live_table_fast(md); - else - dm_put_live_table(md, srcu_idx); -} - static char *_dm_claim_ptr = "I belong to device-mapper"; /* @@ -1805,9 +1787,8 @@ static void dm_submit_bio(struct bio *bio) struct mapped_device *md = bio->bi_bdev->bd_disk->private_data; int srcu_idx; struct dm_table *map; - blk_opf_t bio_opf = bio->bi_opf; - map = dm_get_live_table_bio(md, &srcu_idx, bio_opf); + map = dm_get_live_table(md, &srcu_idx); /* If suspended, or map not yet available, queue this IO for later */ if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) || @@ -1823,7 +1804,7 @@ static void dm_submit_bio(struct bio *bio) dm_split_and_process_bio(md, map, bio); out: - dm_put_live_table_bio(md, srcu_idx, bio_opf); + dm_put_live_table(md, srcu_idx); } static bool dm_poll_dm_io(struct dm_io *io, struct io_comp_batch *iob, From 32247b9526bfdaeef85f7339d9b4f913c7370f92 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 29 Aug 2023 11:34:52 +0100 Subject: [PATCH 1617/2093] btrfs: fix lockdep splat and potential deadlock after failure running delayed items commit e110f8911ddb93e6f55da14ccbbe705397b30d0b upstream. When running delayed items we are holding a delayed node's mutex and then we will attempt to modify a subvolume btree to insert/update/delete the delayed items. However if have an error during the insertions for example, btrfs_insert_delayed_items() may return with a path that has locked extent buffers (a leaf at the very least), and then we attempt to release the delayed node at __btrfs_run_delayed_items(), which requires taking the delayed node's mutex, causing an ABBA type of deadlock. This was reported by syzbot and the lockdep splat is the following: WARNING: possible circular locking dependency detected 6.5.0-rc7-syzkaller-00024-g93f5de5f648d #0 Not tainted ------------------------------------------------------ syz-executor.2/13257 is trying to acquire lock: ffff88801835c0c0 (&delayed_node->mutex){+.+.}-{3:3}, at: __btrfs_release_delayed_node+0x9a/0xaa0 fs/btrfs/delayed-inode.c:256 but task is already holding lock: ffff88802a5ab8e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_lock+0x3c/0x2a0 fs/btrfs/locking.c:198 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (btrfs-tree-00){++++}-{3:3}: __lock_release kernel/locking/lockdep.c:5475 [inline] lock_release+0x36f/0x9d0 kernel/locking/lockdep.c:5781 up_write+0x79/0x580 kernel/locking/rwsem.c:1625 btrfs_tree_unlock_rw fs/btrfs/locking.h:189 [inline] btrfs_unlock_up_safe+0x179/0x3b0 fs/btrfs/locking.c:239 search_leaf fs/btrfs/ctree.c:1986 [inline] btrfs_search_slot+0x2511/0x2f80 fs/btrfs/ctree.c:2230 btrfs_insert_empty_items+0x9c/0x180 fs/btrfs/ctree.c:4376 btrfs_insert_delayed_item fs/btrfs/delayed-inode.c:746 [inline] btrfs_insert_delayed_items fs/btrfs/delayed-inode.c:824 [inline] __btrfs_commit_inode_delayed_items+0xd24/0x2410 fs/btrfs/delayed-inode.c:1111 __btrfs_run_delayed_items+0x1db/0x430 fs/btrfs/delayed-inode.c:1153 flush_space+0x269/0xe70 fs/btrfs/space-info.c:723 btrfs_async_reclaim_metadata_space+0x106/0x350 fs/btrfs/space-info.c:1078 process_one_work+0x92c/0x12c0 kernel/workqueue.c:2600 worker_thread+0xa63/0x1210 kernel/workqueue.c:2751 kthread+0x2b8/0x350 kernel/kthread.c:389 ret_from_fork+0x2e/0x60 arch/x86/kernel/process.c:145 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 -> #0 (&delayed_node->mutex){+.+.}-{3:3}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 __mutex_lock_common+0x1d8/0x2530 kernel/locking/mutex.c:603 __mutex_lock kernel/locking/mutex.c:747 [inline] mutex_lock_nested+0x1b/0x20 kernel/locking/mutex.c:799 __btrfs_release_delayed_node+0x9a/0xaa0 fs/btrfs/delayed-inode.c:256 btrfs_release_delayed_node fs/btrfs/delayed-inode.c:281 [inline] __btrfs_run_delayed_items+0x2b5/0x430 fs/btrfs/delayed-inode.c:1156 btrfs_commit_transaction+0x859/0x2ff0 fs/btrfs/transaction.c:2276 btrfs_sync_file+0xf56/0x1330 fs/btrfs/file.c:1988 vfs_fsync_range fs/sync.c:188 [inline] vfs_fsync fs/sync.c:202 [inline] do_fsync fs/sync.c:212 [inline] __do_sys_fsync fs/sync.c:220 [inline] __se_sys_fsync fs/sync.c:218 [inline] __x64_sys_fsync+0x196/0x1e0 fs/sync.c:218 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(btrfs-tree-00); lock(&delayed_node->mutex); lock(btrfs-tree-00); lock(&delayed_node->mutex); *** DEADLOCK *** 3 locks held by syz-executor.2/13257: #0: ffff88802c1ee370 (btrfs_trans_num_writers){++++}-{0:0}, at: spin_unlock include/linux/spinlock.h:391 [inline] #0: ffff88802c1ee370 (btrfs_trans_num_writers){++++}-{0:0}, at: join_transaction+0xb87/0xe00 fs/btrfs/transaction.c:287 #1: ffff88802c1ee398 (btrfs_trans_num_extwriters){++++}-{0:0}, at: join_transaction+0xbb2/0xe00 fs/btrfs/transaction.c:288 #2: ffff88802a5ab8e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_lock+0x3c/0x2a0 fs/btrfs/locking.c:198 stack backtrace: CPU: 0 PID: 13257 Comm: syz-executor.2 Not tainted 6.5.0-rc7-syzkaller-00024-g93f5de5f648d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 check_noncircular+0x375/0x4a0 kernel/locking/lockdep.c:2195 check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 __mutex_lock_common+0x1d8/0x2530 kernel/locking/mutex.c:603 __mutex_lock kernel/locking/mutex.c:747 [inline] mutex_lock_nested+0x1b/0x20 kernel/locking/mutex.c:799 __btrfs_release_delayed_node+0x9a/0xaa0 fs/btrfs/delayed-inode.c:256 btrfs_release_delayed_node fs/btrfs/delayed-inode.c:281 [inline] __btrfs_run_delayed_items+0x2b5/0x430 fs/btrfs/delayed-inode.c:1156 btrfs_commit_transaction+0x859/0x2ff0 fs/btrfs/transaction.c:2276 btrfs_sync_file+0xf56/0x1330 fs/btrfs/file.c:1988 vfs_fsync_range fs/sync.c:188 [inline] vfs_fsync fs/sync.c:202 [inline] do_fsync fs/sync.c:212 [inline] __do_sys_fsync fs/sync.c:220 [inline] __se_sys_fsync fs/sync.c:218 [inline] __x64_sys_fsync+0x196/0x1e0 fs/sync.c:218 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f3ad047cae9 Code: 28 00 00 00 75 (...) RSP: 002b:00007f3ad12510c8 EFLAGS: 00000246 ORIG_RAX: 000000000000004a RAX: ffffffffffffffda RBX: 00007f3ad059bf80 RCX: 00007f3ad047cae9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000005 RBP: 00007f3ad04c847a R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007f3ad059bf80 R15: 00007ffe56af92f8 ------------[ cut here ]------------ Fix this by releasing the path before releasing the delayed node in the error path at __btrfs_run_delayed_items(). Reported-by: syzbot+a379155f07c134ea9879@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/000000000000abba27060403b5bd@google.com/ CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/delayed-inode.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index cac5169eaf8d..d2cbb7733c7d 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1148,20 +1148,33 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) ret = __btrfs_commit_inode_delayed_items(trans, path, curr_node); if (ret) { - btrfs_release_delayed_node(curr_node); - curr_node = NULL; btrfs_abort_transaction(trans, ret); break; } prev_node = curr_node; curr_node = btrfs_next_delayed_node(curr_node); + /* + * See the comment below about releasing path before releasing + * node. If the commit of delayed items was successful the path + * should always be released, but in case of an error, it may + * point to locked extent buffers (a leaf at the very least). + */ + ASSERT(path->nodes[0] == NULL); btrfs_release_delayed_node(prev_node); } + /* + * Release the path to avoid a potential deadlock and lockdep splat when + * releasing the delayed node, as that requires taking the delayed node's + * mutex. If another task starts running delayed items before we take + * the mutex, it will first lock the mutex and then it may try to lock + * the same btree path (leaf). + */ + btrfs_free_path(path); + if (curr_node) btrfs_release_delayed_node(curr_node); - btrfs_free_path(path); trans->block_rsv = block_rsv; return ret; From 52932bbc6d4b4f2996d61d1c7d623019c66d5d5f Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 22 Aug 2023 13:50:51 +0800 Subject: [PATCH 1618/2093] btrfs: fix a compilation error if DEBUG is defined in btree_dirty_folio commit 5e0e879926c1ce7e1f5e0dfaacaf2d105f7d8a05 upstream. [BUG] After commit 72a69cd03082 ("btrfs: subpage: pack all subpage bitmaps into a larger bitmap"), the DEBUG section of btree_dirty_folio() would no longer compile. [CAUSE] If DEBUG is defined, we would do extra checks for btree_dirty_folio(), mostly to make sure the range we marked dirty has an extent buffer and that extent buffer is dirty. For subpage, we need to iterate through all the extent buffers covered by that page range, and make sure they all matches the criteria. However commit 72a69cd03082 ("btrfs: subpage: pack all subpage bitmaps into a larger bitmap") changes how we store the bitmap, we pack all the 16 bits bitmaps into a larger bitmap, which would save some space. This means we no longer have btrfs_subpage::dirty_bitmap, instead the dirty bitmap is starting at btrfs_subpage_info::dirty_offset, and has a length of btrfs_subpage_info::bitmap_nr_bits. [FIX] Although I'm not sure if it still makes sense to maintain such code, at least let it compile. This patch would let us test the bits one by one through the bitmaps. CC: stable@vger.kernel.org # 6.1+ Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c44f1fcc1909..d1dae29a3d01 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -859,6 +859,7 @@ static bool btree_dirty_folio(struct address_space *mapping, struct folio *folio) { struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb); + struct btrfs_subpage_info *spi = fs_info->subpage_info; struct btrfs_subpage *subpage; struct extent_buffer *eb; int cur_bit = 0; @@ -872,18 +873,19 @@ static bool btree_dirty_folio(struct address_space *mapping, btrfs_assert_tree_write_locked(eb); return filemap_dirty_folio(mapping, folio); } + + ASSERT(spi); subpage = folio_get_private(folio); - ASSERT(subpage->dirty_bitmap); - while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) { + for (cur_bit = spi->dirty_offset; + cur_bit < spi->dirty_offset + spi->bitmap_nr_bits; + cur_bit++) { unsigned long flags; u64 cur; - u16 tmp = (1 << cur_bit); spin_lock_irqsave(&subpage->lock, flags); - if (!(tmp & subpage->dirty_bitmap)) { + if (!test_bit(cur_bit, subpage->bitmaps)) { spin_unlock_irqrestore(&subpage->lock, flags); - cur_bit++; continue; } spin_unlock_irqrestore(&subpage->lock, flags); @@ -896,7 +898,7 @@ static bool btree_dirty_folio(struct address_space *mapping, btrfs_assert_tree_write_locked(eb); free_extent_buffer(eb); - cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits); + cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits) - 1; } return filemap_dirty_folio(mapping, folio); } From 50e385d98b2a52480836ea41c142b81eeeb277af Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Sat, 26 Aug 2023 11:28:20 +0100 Subject: [PATCH 1619/2093] btrfs: release path before inode lookup during the ino lookup ioctl commit ee34a82e890a7babb5585daf1a6dd7d4d1cf142a upstream. During the ino lookup ioctl we can end up calling btrfs_iget() to get an inode reference while we are holding on a root's btree. If btrfs_iget() needs to lookup the inode from the root's btree, because it's not currently loaded in memory, then it will need to lock another or the same path in the same root btree. This may result in a deadlock and trigger the following lockdep splat: WARNING: possible circular locking dependency detected 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Not tainted ------------------------------------------------------ syz-executor277/5012 is trying to acquire lock: ffff88802df41710 (btrfs-tree-01){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 but task is already holding lock: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (btrfs-tree-00){++++}-{3:3}: down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_search_slot+0x13a4/0x2f80 fs/btrfs/ctree.c:2302 btrfs_init_root_free_objectid+0x148/0x320 fs/btrfs/disk-io.c:4955 btrfs_init_fs_root fs/btrfs/disk-io.c:1128 [inline] btrfs_get_root_ref+0x5ae/0xae0 fs/btrfs/disk-io.c:1338 btrfs_get_fs_root fs/btrfs/disk-io.c:1390 [inline] open_ctree+0x29c8/0x3030 fs/btrfs/disk-io.c:3494 btrfs_fill_super+0x1c7/0x2f0 fs/btrfs/super.c:1154 btrfs_mount_root+0x7e0/0x910 fs/btrfs/super.c:1519 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 fc_mount fs/namespace.c:1112 [inline] vfs_kern_mount+0xbc/0x150 fs/namespace.c:1142 btrfs_mount+0x39f/0xb50 fs/btrfs/super.c:1579 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 do_new_mount+0x28f/0xae0 fs/namespace.c:3335 do_mount fs/namespace.c:3675 [inline] __do_sys_mount fs/namespace.c:3884 [inline] __se_sys_mount+0x2d9/0x3c0 fs/namespace.c:3861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #0 (btrfs-tree-01){++++}-{3:3}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- rlock(btrfs-tree-00); lock(btrfs-tree-01); lock(btrfs-tree-00); rlock(btrfs-tree-01); *** DEADLOCK *** 1 lock held by syz-executor277/5012: #0: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 stack backtrace: CPU: 1 PID: 5012 Comm: syz-executor277 Not tainted 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 check_noncircular+0x375/0x4a0 kernel/locking/lockdep.c:2195 check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f0bec94ea39 Fix this simply by releasing the path before calling btrfs_iget() as at point we don't need the path anymore. Reported-by: syzbot+bf66ad948981797d2f1d@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/00000000000045fa140603c4a969@google.com/ Fixes: 23d0b79dfaed ("btrfs: Add unprivileged version of ino_lookup ioctl") CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ioctl.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 9de647e48e7e..2e29fafe0e7d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2850,6 +2850,13 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, goto out_put; } + /* + * We don't need the path anymore, so release it and + * avoid deadlocks and lockdep warnings in case + * btrfs_iget() needs to lookup the inode from its root + * btree and lock the same leaf. + */ + btrfs_release_path(path); temp_inode = btrfs_iget(sb, key2.objectid, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); @@ -2870,7 +2877,6 @@ static int btrfs_search_path_in_tree_user(struct user_namespace *mnt_userns, goto out_put; } - btrfs_release_path(path); key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid; From 1f89e6daf2b0be458c3cd8a5f328a839a71581fd Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 24 Aug 2023 16:59:04 -0400 Subject: [PATCH 1620/2093] btrfs: check for BTRFS_FS_ERROR in pending ordered assert commit 4ca8e03cf2bfaeef7c85939fa1ea0c749cd116ab upstream. If we do fast tree logging we increment a counter on the current transaction for every ordered extent we need to wait for. This means we expect the transaction to still be there when we clear pending on the ordered extent. However if we happen to abort the transaction and clean it up, there could be no running transaction, and thus we'll trip the "ASSERT(trans)" check. This is obviously incorrect, and the code properly deals with the case that the transaction doesn't exist. Fix this ASSERT() to only fire if there's no trans and we don't have BTRFS_FS_ERROR() set on the file system. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ordered-data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e54f8280031f..bd0c7157e387 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -580,7 +580,7 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, refcount_inc(&trans->use_count); spin_unlock(&fs_info->trans_lock); - ASSERT(trans); + ASSERT(trans || BTRFS_FS_ERROR(fs_info)); if (trans) { if (atomic_dec_and_test(&trans->pending_ordered)) wake_up(&trans->pending_wait); From d65553fe52817484f01273fc69a7f7d7ff8663ff Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Sep 2023 22:47:13 -0400 Subject: [PATCH 1621/2093] tracing: Have tracing_max_latency inc the trace array ref count commit 7d660c9b2bc95107f90a9f4c4759be85309a6550 upstream. The tracing_max_latency file points to the trace_array max_latency field. For an instance, if the file is opened and the instance is deleted, reading or writing to the file will cause a use after free. Up the ref count of the trace_array when tracing_max_latency is opened. Link: https://lkml.kernel.org/r/20230907024803.666889383@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Cc: Zheng Yejian Fixes: 8530dec63e7b4 ("tracing: Add tracing_check_open_get_tr()") Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 54ccdca39531..a9a54581694e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1729,7 +1729,7 @@ static void trace_create_maxlat_file(struct trace_array *tr, init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); tr->d_max_latency = trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, - d_tracer, &tr->max_latency, + d_tracer, tr, &tracing_max_lat_fops); } @@ -1762,7 +1762,7 @@ void latency_fsnotify(struct trace_array *tr) #define trace_create_maxlat_file(tr, d_tracer) \ trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, \ - d_tracer, &tr->max_latency, &tracing_max_lat_fops) + d_tracer, tr, &tracing_max_lat_fops) #endif @@ -6604,14 +6604,18 @@ static ssize_t tracing_max_lat_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - return tracing_nsecs_read(filp->private_data, ubuf, cnt, ppos); + struct trace_array *tr = filp->private_data; + + return tracing_nsecs_read(&tr->max_latency, ubuf, cnt, ppos); } static ssize_t tracing_max_lat_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos); + struct trace_array *tr = filp->private_data; + + return tracing_nsecs_write(&tr->max_latency, ubuf, cnt, ppos); } #endif @@ -7668,10 +7672,11 @@ static const struct file_operations tracing_thresh_fops = { #ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_max_lat_read, .write = tracing_max_lat_write, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; #endif From 0c2982b01501c0bc91002171dfc7cd93e0f9e172 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Sep 2023 22:47:16 -0400 Subject: [PATCH 1622/2093] tracing: Have event inject files inc the trace array ref count commit e5c624f027ac74f97e97c8f36c69228ac9f1102d upstream. The event inject files add events for a specific trace array. For an instance, if the file is opened and the instance is deleted, reading or writing to the file will cause a use after free. Up the ref count of the trace_array when a event inject file is opened. Link: https://lkml.kernel.org/r/20230907024804.292337868@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Cc: Zheng Yejian Fixes: 6c3edaf9fd6a ("tracing: Introduce trace event injection") Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_inject.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index d6b4935a78c0..dbecfbb73d23 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -328,7 +328,8 @@ event_inject_read(struct file *file, char __user *buf, size_t size, } const struct file_operations event_inject_fops = { - .open = tracing_open_generic, + .open = tracing_open_file_tr, .read = event_inject_read, .write = event_inject_write, + .release = tracing_release_file_tr, }; From a46bf337a20f9edd3c8041b025639842280d0575 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Sep 2023 22:47:12 -0400 Subject: [PATCH 1623/2093] tracing: Increase trace array ref count on enable and filter files commit f5ca233e2e66dc1c249bf07eefa37e34a6c9346a upstream. When the trace event enable and filter files are opened, increment the trace array ref counter, otherwise they can be accessed when the trace array is being deleted. The ref counter keeps the trace array from being deleted while those files are opened. Link: https://lkml.kernel.org/r/20230907024803.456187066@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Fixes: 8530dec63e7b4 ("tracing: Add tracing_check_open_get_tr()") Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Reported-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 27 +++++++++++++++++++++++++++ kernel/trace/trace.h | 2 ++ kernel/trace/trace_events.c | 6 ++++-- 3 files changed, 33 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a9a54581694e..1ea3f969c36b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4899,6 +4899,33 @@ int tracing_open_generic_tr(struct inode *inode, struct file *filp) return 0; } +/* + * The private pointer of the inode is the trace_event_file. + * Update the tr ref count associated to it. + */ +int tracing_open_file_tr(struct inode *inode, struct file *filp) +{ + struct trace_event_file *file = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(file->tr); + if (ret) + return ret; + + filp->private_data = inode->i_private; + + return 0; +} + +int tracing_release_file_tr(struct inode *inode, struct file *filp) +{ + struct trace_event_file *file = inode->i_private; + + trace_array_put(file->tr); + + return 0; +} + static int tracing_mark_open(struct inode *inode, struct file *filp) { stream_open(inode, filp); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index dbb86b0dd3b7..7e6d5101bdb0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -590,6 +590,8 @@ void tracing_reset_all_online_cpus(void); void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); +int tracing_open_file_tr(struct inode *inode, struct file *filp); +int tracing_release_file_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0447c46ef4d7..9da418442a06 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2101,9 +2101,10 @@ static const struct file_operations ftrace_set_event_notrace_pid_fops = { }; static const struct file_operations ftrace_enable_fops = { - .open = tracing_open_generic, + .open = tracing_open_file_tr, .read = event_enable_read, .write = event_enable_write, + .release = tracing_release_file_tr, .llseek = default_llseek, }; @@ -2120,9 +2121,10 @@ static const struct file_operations ftrace_event_id_fops = { }; static const struct file_operations ftrace_event_filter_fops = { - .open = tracing_open_generic, + .open = tracing_open_file_tr, .read = event_filter_read, .write = event_filter_write, + .release = tracing_release_file_tr, .llseek = default_llseek, }; From 6dc57c3a1d1361b570b8a77b1c5cb11b5b5706f9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Sep 2023 22:47:14 -0400 Subject: [PATCH 1624/2093] tracing: Have current_trace inc the trace array ref count commit 9b37febc578b2e1ad76a105aab11d00af5ec3d27 upstream. The current_trace updates the trace array tracer. For an instance, if the file is opened and the instance is deleted, reading or writing to the file will cause a use after free. Up the ref count of the trace array when current_trace is opened. Link: https://lkml.kernel.org/r/20230907024803.877687227@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Cc: Zheng Yejian Fixes: 8530dec63e7b4 ("tracing: Add tracing_check_open_get_tr()") Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1ea3f969c36b..5951a0cb3e27 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7708,10 +7708,11 @@ static const struct file_operations tracing_max_lat_fops = { #endif static const struct file_operations set_tracer_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_set_trace_read, .write = tracing_set_trace_write, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; static const struct file_operations tracing_pipe_fops = { From 2617afde0c3db285778734b0ccad9a55b4f9cda2 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 6 Sep 2023 22:47:15 -0400 Subject: [PATCH 1625/2093] tracing: Have option files inc the trace array ref count commit 7e2cfbd2d3c86afcd5c26b5c4b1dd251f63c5838 upstream. The option files update the options for a given trace array. For an instance, if the file is opened and the instance is deleted, reading or writing to the file will cause a use after free. Up the ref count of the trace_array when an option file is opened. Link: https://lkml.kernel.org/r/20230907024804.086679464@goodmis.org Link: https://lore.kernel.org/all/1cb3aee2-19af-c472-e265-05176fe9bd84@huawei.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Cc: Zheng Yejian Fixes: 8530dec63e7b4 ("tracing: Add tracing_check_open_get_tr()") Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5951a0cb3e27..9db92a6e1463 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8905,12 +8905,33 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +static int tracing_open_options(struct inode *inode, struct file *filp) +{ + struct trace_option_dentry *topt = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(topt->tr); + if (ret) + return ret; + + filp->private_data = inode->i_private; + return 0; +} + +static int tracing_release_options(struct inode *inode, struct file *file) +{ + struct trace_option_dentry *topt = file->private_data; + + trace_array_put(topt->tr); + return 0; +} static const struct file_operations trace_options_fops = { - .open = tracing_open_generic, + .open = tracing_open_options, .read = trace_options_read, .write = trace_options_write, .llseek = generic_file_llseek, + .release = tracing_release_options, }; /* From 978b86fbdb2acf69a3630931f0c4f07a30734f2f Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Mon, 11 Sep 2023 16:23:58 +0200 Subject: [PATCH 1626/2093] selinux: fix handling of empty opts in selinux_fs_context_submount() commit ccf1dab96be4caed7c5235b1cfdb606ac161b996 upstream. selinux_set_mnt_opts() relies on the fact that the mount options pointer is always NULL when all options are unset (specifically in its !selinux_initialized() branch. However, the new selinux_fs_context_submount() hook breaks this rule by allocating a new structure even if no options are set. That causes any submount created before a SELinux policy is loaded to be rejected in selinux_set_mnt_opts(). Fix this by making selinux_fs_context_submount() leave fc->security set to NULL when there are no options to be copied from the reference superblock. Cc: Reported-by: Adam Williamson Link: https://bugzilla.redhat.com/show_bug.cgi?id=2236345 Fixes: d80a8f1b58c2 ("vfs, security: Fix automount superblock LSM init problem, preventing NFS sb sharing") Signed-off-by: Ondrej Mosnacek Reviewed-by: Jeff Layton Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/selinux/hooks.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 26c9e4da4efc..d88c399b0e86 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2769,14 +2769,20 @@ static int selinux_umount(struct vfsmount *mnt, int flags) static int selinux_fs_context_submount(struct fs_context *fc, struct super_block *reference) { - const struct superblock_security_struct *sbsec; + const struct superblock_security_struct *sbsec = selinux_superblock(reference); struct selinux_mnt_opts *opts; + /* + * Ensure that fc->security remains NULL when no options are set + * as expected by selinux_set_mnt_opts(). + */ + if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT))) + return 0; + opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; - sbsec = selinux_superblock(reference); if (sbsec->flags & FSCONTEXT_MNT) opts->fscontext_sid = sbsec->sid; if (sbsec->flags & CONTEXT_MNT) From dcf3caeee4322a3a7c4d8356d9a6bbf8a68140a1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Sat, 9 Sep 2023 07:12:30 -0400 Subject: [PATCH 1627/2093] nfsd: fix change_info in NFSv4 RENAME replies commit fdd2630a7398191e84822612e589062063bd4f3d upstream. nfsd sends the transposed directory change info in the RENAME reply. The source directory is in save_fh and the target is in current_fh. Reported-by: Zhi Li Reported-by: Benjamin Coddington Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2218844 Signed-off-by: Jeff Layton Cc: Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/nfs4proc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a90e792a94d7..a9105e95b59c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1029,8 +1029,8 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, rename->rn_tname, rename->rn_tnamelen); if (status) return status; - set_change_info(&rename->rn_sinfo, &cstate->current_fh); - set_change_info(&rename->rn_tinfo, &cstate->save_fh); + set_change_info(&rename->rn_sinfo, &cstate->save_fh); + set_change_info(&rename->rn_tinfo, &cstate->current_fh); return nfs_ok; } From 8b0f7d55b22e1b2ddcd6f337e00dc96b3f444abe Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 5 Sep 2023 14:26:08 -0400 Subject: [PATCH 1628/2093] tracefs: Add missing lockdown check to tracefs_create_dir() commit 51aab5ffceb43e05119eb059048fd75765d2bc21 upstream. The function tracefs_create_dir() was missing a lockdown check and was called by the RV code. This gave an inconsistent behavior of this function returning success while other tracefs functions failed. This caused the inode being freed by the wrong kmem_cache. Link: https://lkml.kernel.org/r/20230905182711.692687042@goodmis.org Link: https://lore.kernel.org/all/202309050916.58201dc6-oliver.sang@intel.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Andrew Morton Cc: Ajay Kaher Cc: Ching-lin Yu Fixes: bf8e602186ec4 ("tracing: Do not create tracefs files if tracefs lockdown is in effect") Reported-by: kernel test robot Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- fs/tracefs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index da85b3979195..6541d917e15e 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -556,6 +556,9 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent, */ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent) { + if (security_locked_down(LOCKDOWN_TRACEFS)) + return NULL; + return __create_dir(name, parent, &simple_dir_inode_operations); } From 30057f4add4148edfef9f94e32f839c2224e5ebe Mon Sep 17 00:00:00 2001 From: Tommy Huang Date: Wed, 6 Sep 2023 08:49:10 +0800 Subject: [PATCH 1629/2093] i2c: aspeed: Reset the i2c controller when timeout occurs commit fee465150b458351b6d9b9f66084f3cc3022b88b upstream. Reset the i2c controller when an i2c transfer timeout occurs. The remaining interrupts and device should be reset to avoid unpredictable controller behavior. Fixes: 2e57b7cebb98 ("i2c: aspeed: Add multi-master use case support") Cc: # v5.1+ Signed-off-by: Tommy Huang Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-aspeed.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index c64c381b69b7..866c52afb8b0 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -698,13 +698,16 @@ static int aspeed_i2c_master_xfer(struct i2c_adapter *adap, if (time_left == 0) { /* - * If timed out and bus is still busy in a multi master - * environment, attempt recovery at here. + * In a multi-master setup, if a timeout occurs, attempt + * recovery. But if the bus is idle, we still need to reset the + * i2c controller to clear the remaining interrupts. */ if (bus->multi_master && (readl(bus->base + ASPEED_I2C_CMD_REG) & ASPEED_I2CD_BUS_BUSY_STS)) aspeed_i2c_recover_bus(bus); + else + aspeed_i2c_reset(bus); /* * If timed out and the state is still pending, drop the pending From a3517ee1d4e625bdf262dbad5d76d9df4fac83a4 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Mon, 4 Sep 2023 22:42:56 +0200 Subject: [PATCH 1630/2093] ata: libata: disallow dev-initiated LPM transitions to unsupported states MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 24e0e61db3cb86a66824531989f1df80e0939f26 upstream. In AHCI 1.3.1, the register description for CAP.SSC: "When cleared to ‘0’, software must not allow the HBA to initiate transitions to the Slumber state via agressive link power management nor the PxCMD.ICC field in each port, and the PxSCTL.IPM field in each port must be programmed to disallow device initiated Slumber requests." In AHCI 1.3.1, the register description for CAP.PSC: "When cleared to ‘0’, software must not allow the HBA to initiate transitions to the Partial state via agressive link power management nor the PxCMD.ICC field in each port, and the PxSCTL.IPM field in each port must be programmed to disallow device initiated Partial requests." Ensure that we always set the corresponding bits in PxSCTL.IPM, such that a device is not allowed to initiate transitions to power states which are unsupported by the HBA. DevSleep is always initiated by the HBA, however, for completeness, set the corresponding bit in PxSCTL.IPM such that agressive link power management cannot transition to DevSleep if DevSleep is not supported. sata_link_scr_lpm() is used by libahci, ata_piix and libata-pmp. However, only libahci has the ability to read the CAP/CAP2 register to see if these features are supported. Therefore, in order to not introduce any regressions on ata_piix or libata-pmp, create flags that indicate that the respective feature is NOT supported. This way, the behavior for ata_piix and libata-pmp should remain unchanged. This change is based on a patch originally submitted by Runa Guo-oc. Signed-off-by: Niklas Cassel Fixes: 1152b2617a6e ("libata: implement sata_link_scr_lpm() and make ata_dev_set_feature() global") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman --- drivers/ata/ahci.c | 9 +++++++++ drivers/ata/libata-sata.c | 19 ++++++++++++++++--- include/linux/libata.h | 4 ++++ 3 files changed, 29 insertions(+), 3 deletions(-) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 1645335b8d2d..805645efb3cc 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1884,6 +1884,15 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) else dev_info(&pdev->dev, "SSS flag set, parallel bus scan disabled\n"); + if (!(hpriv->cap & HOST_CAP_PART)) + host->flags |= ATA_HOST_NO_PART; + + if (!(hpriv->cap & HOST_CAP_SSC)) + host->flags |= ATA_HOST_NO_SSC; + + if (!(hpriv->cap2 & HOST_CAP2_SDS)) + host->flags |= ATA_HOST_NO_DEVSLP; + if (pi.flags & ATA_FLAG_EM) ahci_reset_em(host); diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index fd4dccc25389..71a00842eb5e 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -394,10 +394,23 @@ int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy, case ATA_LPM_MED_POWER_WITH_DIPM: case ATA_LPM_MIN_POWER_WITH_PARTIAL: case ATA_LPM_MIN_POWER: - if (ata_link_nr_enabled(link) > 0) - /* no restrictions on LPM transitions */ + if (ata_link_nr_enabled(link) > 0) { + /* assume no restrictions on LPM transitions */ scontrol &= ~(0x7 << 8); - else { + + /* + * If the controller does not support partial, slumber, + * or devsleep, then disallow these transitions. + */ + if (link->ap->host->flags & ATA_HOST_NO_PART) + scontrol |= (0x1 << 8); + + if (link->ap->host->flags & ATA_HOST_NO_SSC) + scontrol |= (0x2 << 8); + + if (link->ap->host->flags & ATA_HOST_NO_DEVSLP) + scontrol |= (0x4 << 8); + } else { /* empty port, power off */ scontrol &= ~0xf; scontrol |= (0x1 << 2); diff --git a/include/linux/libata.h b/include/linux/libata.h index 9713f4d8f15f..4c9b322bb3d8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -216,6 +216,10 @@ enum { ATA_HOST_PARALLEL_SCAN = (1 << 2), /* Ports on this host can be scanned in parallel */ ATA_HOST_IGNORE_ATA = (1 << 3), /* Ignore ATA devices on this host. */ + ATA_HOST_NO_PART = (1 << 4), /* Host does not support partial */ + ATA_HOST_NO_SSC = (1 << 5), /* Host does not support slumber */ + ATA_HOST_NO_DEVSLP = (1 << 6), /* Host does not support devslp */ + /* bits 24:31 of host->flags are reserved for LLD specific flags */ /* various lengths of time */ From 890e1e5dd8babd301e56a4643d224c481fa2e51a Mon Sep 17 00:00:00 2001 From: Szuying Chen Date: Thu, 7 Sep 2023 16:17:10 +0800 Subject: [PATCH 1631/2093] ata: libahci: clear pending interrupt status commit 737dd811a3dbfd7edd4ad2ba5152e93d99074f83 upstream. When a CRC error occurs, the HBA asserts an interrupt to indicate an interface fatal error (PxIS.IFS). The ISR clears PxIE and PxIS, then does error recovery. If the adapter receives another SDB FIS with an error (PxIS.TFES) from the device before the start of the EH recovery process, the interrupt signaling the new SDB cannot be serviced as PxIE was cleared already. This in turn results in the HBA inability to issue any command during the error recovery process after setting PxCMD.ST to 1 because PxIS.TFES is still set. According to AHCI 1.3.1 specifications section 6.2.2, fatal errors notified by setting PxIS.HBFS, PxIS.HBDS, PxIS.IFS or PxIS.TFES will cause the HBA to enter the ERR:Fatal state. In this state, the HBA shall not issue any new commands. To avoid this situation, introduce the function ahci_port_clear_pending_irq() to clear pending interrupts before executing a COMRESET. This follows the AHCI 1.3.1 - section 6.2.2.2 specification. Signed-off-by: Szuying Chen Fixes: e0bfd149973d ("[PATCH] ahci: stop engine during hard reset") Cc: stable@vger.kernel.org Reviewed-by: Niklas Cassel Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libahci.c | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 954386a2b500..1b1671c027cd 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1255,6 +1255,26 @@ static ssize_t ahci_activity_show(struct ata_device *dev, char *buf) return sprintf(buf, "%d\n", emp->blink_policy); } +static void ahci_port_clear_pending_irq(struct ata_port *ap) +{ + struct ahci_host_priv *hpriv = ap->host->private_data; + void __iomem *port_mmio = ahci_port_base(ap); + u32 tmp; + + /* clear SError */ + tmp = readl(port_mmio + PORT_SCR_ERR); + dev_dbg(ap->host->dev, "PORT_SCR_ERR 0x%x\n", tmp); + writel(tmp, port_mmio + PORT_SCR_ERR); + + /* clear port IRQ */ + tmp = readl(port_mmio + PORT_IRQ_STAT); + dev_dbg(ap->host->dev, "PORT_IRQ_STAT 0x%x\n", tmp); + if (tmp) + writel(tmp, port_mmio + PORT_IRQ_STAT); + + writel(1 << ap->port_no, hpriv->mmio + HOST_IRQ_STAT); +} + static void ahci_port_init(struct device *dev, struct ata_port *ap, int port_no, void __iomem *mmio, void __iomem *port_mmio) @@ -1269,18 +1289,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, if (rc) dev_warn(dev, "%s (%d)\n", emsg, rc); - /* clear SError */ - tmp = readl(port_mmio + PORT_SCR_ERR); - dev_dbg(dev, "PORT_SCR_ERR 0x%x\n", tmp); - writel(tmp, port_mmio + PORT_SCR_ERR); - - /* clear port IRQ */ - tmp = readl(port_mmio + PORT_IRQ_STAT); - dev_dbg(dev, "PORT_IRQ_STAT 0x%x\n", tmp); - if (tmp) - writel(tmp, port_mmio + PORT_IRQ_STAT); - - writel(1 << port_no, mmio + HOST_IRQ_STAT); + ahci_port_clear_pending_irq(ap); /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); @@ -1601,6 +1610,8 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class, tf.status = ATA_BUSY; ata_tf_to_fis(&tf, 0, 0, d2h_fis); + ahci_port_clear_pending_irq(ap); + rc = sata_link_hardreset(link, timing, deadline, online, ahci_check_ready); From c2cb422dca0bff85e6e4452b48b8544482892ee2 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Mon, 28 Aug 2023 15:10:18 -0700 Subject: [PATCH 1632/2093] scsi: megaraid_sas: Fix deadlock on firmware crashdump commit 0b0747d507bffb827e40fc0f9fb5883fffc23477 upstream. The following processes run into a deadlock. CPU 41 was waiting for CPU 29 to handle a CSD request while holding spinlock "crashdump_lock", but CPU 29 was hung by that spinlock with IRQs disabled. PID: 17360 TASK: ffff95c1090c5c40 CPU: 41 COMMAND: "mrdiagd" !# 0 [ffffb80edbf37b58] __read_once_size at ffffffff9b871a40 include/linux/compiler.h:185:0 !# 1 [ffffb80edbf37b58] atomic_read at ffffffff9b871a40 arch/x86/include/asm/atomic.h:27:0 !# 2 [ffffb80edbf37b58] dump_stack at ffffffff9b871a40 lib/dump_stack.c:54:0 # 3 [ffffb80edbf37b78] csd_lock_wait_toolong at ffffffff9b131ad5 kernel/smp.c:364:0 # 4 [ffffb80edbf37b78] __csd_lock_wait at ffffffff9b131ad5 kernel/smp.c:384:0 # 5 [ffffb80edbf37bf8] csd_lock_wait at ffffffff9b13267a kernel/smp.c:394:0 # 6 [ffffb80edbf37bf8] smp_call_function_many at ffffffff9b13267a kernel/smp.c:843:0 # 7 [ffffb80edbf37c50] smp_call_function at ffffffff9b13279d kernel/smp.c:867:0 # 8 [ffffb80edbf37c50] on_each_cpu at ffffffff9b13279d kernel/smp.c:976:0 # 9 [ffffb80edbf37c78] flush_tlb_kernel_range at ffffffff9b085c4b arch/x86/mm/tlb.c:742:0 #10 [ffffb80edbf37cb8] __purge_vmap_area_lazy at ffffffff9b23a1e0 mm/vmalloc.c:701:0 #11 [ffffb80edbf37ce0] try_purge_vmap_area_lazy at ffffffff9b23a2cc mm/vmalloc.c:722:0 #12 [ffffb80edbf37ce0] free_vmap_area_noflush at ffffffff9b23a2cc mm/vmalloc.c:754:0 #13 [ffffb80edbf37cf8] free_unmap_vmap_area at ffffffff9b23bb3b mm/vmalloc.c:764:0 #14 [ffffb80edbf37cf8] remove_vm_area at ffffffff9b23bb3b mm/vmalloc.c:1509:0 #15 [ffffb80edbf37d18] __vunmap at ffffffff9b23bb8a mm/vmalloc.c:1537:0 #16 [ffffb80edbf37d40] vfree at ffffffff9b23bc85 mm/vmalloc.c:1612:0 #17 [ffffb80edbf37d58] megasas_free_host_crash_buffer [megaraid_sas] at ffffffffc020b7f2 drivers/scsi/megaraid/megaraid_sas_fusion.c:3932:0 #18 [ffffb80edbf37d80] fw_crash_state_store [megaraid_sas] at ffffffffc01f804d drivers/scsi/megaraid/megaraid_sas_base.c:3291:0 #19 [ffffb80edbf37dc0] dev_attr_store at ffffffff9b56dd7b drivers/base/core.c:758:0 #20 [ffffb80edbf37dd0] sysfs_kf_write at ffffffff9b326acf fs/sysfs/file.c:144:0 #21 [ffffb80edbf37de0] kernfs_fop_write at ffffffff9b325fd4 fs/kernfs/file.c:316:0 #22 [ffffb80edbf37e20] __vfs_write at ffffffff9b29418a fs/read_write.c:480:0 #23 [ffffb80edbf37ea8] vfs_write at ffffffff9b294462 fs/read_write.c:544:0 #24 [ffffb80edbf37ee8] SYSC_write at ffffffff9b2946ec fs/read_write.c:590:0 #25 [ffffb80edbf37ee8] SyS_write at ffffffff9b2946ec fs/read_write.c:582:0 #26 [ffffb80edbf37f30] do_syscall_64 at ffffffff9b003ca9 arch/x86/entry/common.c:298:0 #27 [ffffb80edbf37f58] entry_SYSCALL_64 at ffffffff9ba001b1 arch/x86/entry/entry_64.S:238:0 PID: 17355 TASK: ffff95c1090c3d80 CPU: 29 COMMAND: "mrdiagd" !# 0 [ffffb80f2d3c7d30] __read_once_size at ffffffff9b0f2ab0 include/linux/compiler.h:185:0 !# 1 [ffffb80f2d3c7d30] native_queued_spin_lock_slowpath at ffffffff9b0f2ab0 kernel/locking/qspinlock.c:368:0 # 2 [ffffb80f2d3c7d58] pv_queued_spin_lock_slowpath at ffffffff9b0f244b arch/x86/include/asm/paravirt.h:674:0 # 3 [ffffb80f2d3c7d58] queued_spin_lock_slowpath at ffffffff9b0f244b arch/x86/include/asm/qspinlock.h:53:0 # 4 [ffffb80f2d3c7d68] queued_spin_lock at ffffffff9b8961a6 include/asm-generic/qspinlock.h:90:0 # 5 [ffffb80f2d3c7d68] do_raw_spin_lock_flags at ffffffff9b8961a6 include/linux/spinlock.h:173:0 # 6 [ffffb80f2d3c7d68] __raw_spin_lock_irqsave at ffffffff9b8961a6 include/linux/spinlock_api_smp.h:122:0 # 7 [ffffb80f2d3c7d68] _raw_spin_lock_irqsave at ffffffff9b8961a6 kernel/locking/spinlock.c:160:0 # 8 [ffffb80f2d3c7d88] fw_crash_buffer_store [megaraid_sas] at ffffffffc01f8129 drivers/scsi/megaraid/megaraid_sas_base.c:3205:0 # 9 [ffffb80f2d3c7dc0] dev_attr_store at ffffffff9b56dd7b drivers/base/core.c:758:0 #10 [ffffb80f2d3c7dd0] sysfs_kf_write at ffffffff9b326acf fs/sysfs/file.c:144:0 #11 [ffffb80f2d3c7de0] kernfs_fop_write at ffffffff9b325fd4 fs/kernfs/file.c:316:0 #12 [ffffb80f2d3c7e20] __vfs_write at ffffffff9b29418a fs/read_write.c:480:0 #13 [ffffb80f2d3c7ea8] vfs_write at ffffffff9b294462 fs/read_write.c:544:0 #14 [ffffb80f2d3c7ee8] SYSC_write at ffffffff9b2946ec fs/read_write.c:590:0 #15 [ffffb80f2d3c7ee8] SyS_write at ffffffff9b2946ec fs/read_write.c:582:0 #16 [ffffb80f2d3c7f30] do_syscall_64 at ffffffff9b003ca9 arch/x86/entry/common.c:298:0 #17 [ffffb80f2d3c7f58] entry_SYSCALL_64 at ffffffff9ba001b1 arch/x86/entry/entry_64.S:238:0 The lock is used to synchronize different sysfs operations, it doesn't protect any resource that will be touched by an interrupt. Consequently it's not required to disable IRQs. Replace the spinlock with a mutex to fix the deadlock. Signed-off-by: Junxiao Bi Link: https://lore.kernel.org/r/20230828221018.19471-1-junxiao.bi@oracle.com Reviewed-by: Mike Christie Cc: stable@vger.kernel.org Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/megaraid/megaraid_sas.h | 2 +- drivers/scsi/megaraid/megaraid_sas_base.c | 21 +++++++++------------ 2 files changed, 10 insertions(+), 13 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 2ef9d41fc6f4..e5215db9ee4d 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2332,7 +2332,7 @@ struct megasas_instance { u32 support_morethan256jbod; /* FW support for more than 256 PD/JBOD */ bool use_seqnum_jbod_fp; /* Added for PD sequence */ bool smp_affinity_enable; - spinlock_t crashdump_lock; + struct mutex crashdump_lock; struct megasas_register_set __iomem *reg_set; u32 __iomem *reply_post_host_index_addr[MR_MAX_MSIX_REG_ARRAY]; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 13ee8e4c4f57..e392a984c7b8 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3272,14 +3272,13 @@ fw_crash_buffer_store(struct device *cdev, struct megasas_instance *instance = (struct megasas_instance *) shost->hostdata; int val = 0; - unsigned long flags; if (kstrtoint(buf, 0, &val) != 0) return -EINVAL; - spin_lock_irqsave(&instance->crashdump_lock, flags); + mutex_lock(&instance->crashdump_lock); instance->fw_crash_buffer_offset = val; - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return strlen(buf); } @@ -3294,24 +3293,23 @@ fw_crash_buffer_show(struct device *cdev, unsigned long dmachunk = CRASH_DMA_BUF_SIZE; unsigned long chunk_left_bytes; unsigned long src_addr; - unsigned long flags; u32 buff_offset; - spin_lock_irqsave(&instance->crashdump_lock, flags); + mutex_lock(&instance->crashdump_lock); buff_offset = instance->fw_crash_buffer_offset; if (!instance->crash_dump_buf || !((instance->fw_crash_state == AVAILABLE) || (instance->fw_crash_state == COPYING))) { dev_err(&instance->pdev->dev, "Firmware crash dump is not available\n"); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return -EINVAL; } if (buff_offset > (instance->fw_crash_buffer_size * dmachunk)) { dev_err(&instance->pdev->dev, "Firmware crash dump offset is out of range\n"); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return 0; } @@ -3323,7 +3321,7 @@ fw_crash_buffer_show(struct device *cdev, src_addr = (unsigned long)instance->crash_buf[buff_offset / dmachunk] + (buff_offset % dmachunk); memcpy(buf, (void *)src_addr, size); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); return size; } @@ -3348,7 +3346,6 @@ fw_crash_state_store(struct device *cdev, struct megasas_instance *instance = (struct megasas_instance *) shost->hostdata; int val = 0; - unsigned long flags; if (kstrtoint(buf, 0, &val) != 0) return -EINVAL; @@ -3362,9 +3359,9 @@ fw_crash_state_store(struct device *cdev, instance->fw_crash_state = val; if ((val == COPIED) || (val == COPY_ERROR)) { - spin_lock_irqsave(&instance->crashdump_lock, flags); + mutex_lock(&instance->crashdump_lock); megasas_free_host_crash_buffer(instance); - spin_unlock_irqrestore(&instance->crashdump_lock, flags); + mutex_unlock(&instance->crashdump_lock); if (val == COPY_ERROR) dev_info(&instance->pdev->dev, "application failed to " "copy Firmware crash dump\n"); @@ -7423,7 +7420,7 @@ static inline void megasas_init_ctrl_params(struct megasas_instance *instance) init_waitqueue_head(&instance->int_cmd_wait_q); init_waitqueue_head(&instance->abort_cmd_wait_q); - spin_lock_init(&instance->crashdump_lock); + mutex_init(&instance->crashdump_lock); spin_lock_init(&instance->mfi_pool_lock); spin_lock_init(&instance->hba_lock); spin_lock_init(&instance->stream_lock); From 89365b624af5ef466ff6370865f65e8556301d5d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 12 Sep 2023 08:27:36 +0900 Subject: [PATCH 1633/2093] scsi: pm8001: Setup IRQs on resume commit c91774818b041ed290df29fb1dc0725be9b12e83 upstream. The function pm8001_pci_resume() only calls pm8001_request_irq() without calling pm8001_setup_irq(). This causes the IRQ allocation to fail, which leads all drives being removed from the system. Fix this issue by integrating the code for pm8001_setup_irq() directly inside pm8001_request_irq() so that MSI-X setup is performed both during normal initialization and resume operations. Fixes: dbf9bfe61571 ("[SCSI] pm8001: add SAS/SATA HBA driver") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20230911232745.325149-2-dlemoal@kernel.org Acked-by: Jack Wang Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/pm8001/pm8001_init.c | 51 +++++++++++-------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 7a7d63aa90e2..da65234add43 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -274,7 +274,6 @@ static irqreturn_t pm8001_interrupt_handler_intx(int irq, void *dev_id) return ret; } -static u32 pm8001_setup_irq(struct pm8001_hba_info *pm8001_ha); static u32 pm8001_request_irq(struct pm8001_hba_info *pm8001_ha); /** @@ -295,13 +294,6 @@ static int pm8001_alloc(struct pm8001_hba_info *pm8001_ha, pm8001_dbg(pm8001_ha, INIT, "pm8001_alloc: PHY:%x\n", pm8001_ha->chip->n_phy); - /* Setup Interrupt */ - rc = pm8001_setup_irq(pm8001_ha); - if (rc) { - pm8001_dbg(pm8001_ha, FAIL, - "pm8001_setup_irq failed [ret: %d]\n", rc); - goto err_out; - } /* Request Interrupt */ rc = pm8001_request_irq(pm8001_ha); if (rc) @@ -1021,47 +1013,38 @@ static u32 pm8001_request_msix(struct pm8001_hba_info *pm8001_ha) } #endif -static u32 pm8001_setup_irq(struct pm8001_hba_info *pm8001_ha) -{ - struct pci_dev *pdev; - - pdev = pm8001_ha->pdev; - -#ifdef PM8001_USE_MSIX - if (pci_find_capability(pdev, PCI_CAP_ID_MSIX)) - return pm8001_setup_msix(pm8001_ha); - pm8001_dbg(pm8001_ha, INIT, "MSIX not supported!!!\n"); -#endif - return 0; -} - /** * pm8001_request_irq - register interrupt * @pm8001_ha: our ha struct. */ static u32 pm8001_request_irq(struct pm8001_hba_info *pm8001_ha) { - struct pci_dev *pdev; + struct pci_dev *pdev = pm8001_ha->pdev; +#ifdef PM8001_USE_MSIX int rc; - pdev = pm8001_ha->pdev; + if (pci_find_capability(pdev, PCI_CAP_ID_MSIX)) { + rc = pm8001_setup_msix(pm8001_ha); + if (rc) { + pm8001_dbg(pm8001_ha, FAIL, + "pm8001_setup_irq failed [ret: %d]\n", rc); + return rc; + } -#ifdef PM8001_USE_MSIX - if (pdev->msix_cap && pci_msi_enabled()) - return pm8001_request_msix(pm8001_ha); - else { - pm8001_dbg(pm8001_ha, INIT, "MSIX not supported!!!\n"); - goto intx; + if (pdev->msix_cap && pci_msi_enabled()) + return pm8001_request_msix(pm8001_ha); } + + pm8001_dbg(pm8001_ha, INIT, "MSIX not supported!!!\n"); #endif -intx: /* initialize the INT-X interrupt */ pm8001_ha->irq_vector[0].irq_id = 0; pm8001_ha->irq_vector[0].drv_inst = pm8001_ha; - rc = request_irq(pdev->irq, pm8001_interrupt_handler_intx, IRQF_SHARED, - pm8001_ha->name, SHOST_TO_SAS_HA(pm8001_ha->shost)); - return rc; + + return request_irq(pdev->irq, pm8001_interrupt_handler_intx, + IRQF_SHARED, pm8001_ha->name, + SHOST_TO_SAS_HA(pm8001_ha->shost)); } /** From 97d4186c350317e5b4c0ee32eaa0284f226f156d Mon Sep 17 00:00:00 2001 From: Shida Zhang Date: Thu, 3 Aug 2023 14:09:38 +0800 Subject: [PATCH 1634/2093] ext4: fix rec_len verify error commit 7fda67e8c3ab6069f75888f67958a6d30454a9f6 upstream. With the configuration PAGE_SIZE 64k and filesystem blocksize 64k, a problem occurred when more than 13 million files were directly created under a directory: EXT4-fs error (device xx): ext4_dx_csum_set:492: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D. EXT4-fs error (device xx): ext4_dx_csum_verify:463: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D. EXT4-fs error (device xx): dx_probe:856: inode #xxxx: block 8188: comm xxxxx: Directory index failed checksum When enough files are created, the fake_dirent->reclen will be 0xffff. it doesn't equal to the blocksize 65536, i.e. 0x10000. But it is not the same condition when blocksize equals to 4k. when enough files are created, the fake_dirent->reclen will be 0x1000. it equals to the blocksize 4k, i.e. 0x1000. The problem seems to be related to the limitation of the 16-bit field when the blocksize is set to 64k. To address this, helpers like ext4_rec_len_{from,to}_disk has already been introduced to complete the conversion between the encoded and the plain form of rec_len. So fix this one by using the helper, and all the other in this file too. Cc: stable@kernel.org Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes") Suggested-by: Andreas Dilger Suggested-by: Darrick J. Wong Signed-off-by: Shida Zhang Reviewed-by: Andreas Dilger Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20230803060938.1929759-1-zhangshida@kylinos.cn Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6a08fc31a66d..bbfb37390723 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -343,17 +343,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, struct buffer_head *bh) { struct ext4_dir_entry_tail *t; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); #ifdef PARANOID struct ext4_dir_entry *d, *top; d = (struct ext4_dir_entry *)bh->b_data; top = (struct ext4_dir_entry *)(bh->b_data + - (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); - while (d < top && d->rec_len) + (blocksize - sizeof(struct ext4_dir_entry_tail))); + while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize)) d = (struct ext4_dir_entry *)(((void *)d) + - le16_to_cpu(d->rec_len)); + ext4_rec_len_from_disk(d->rec_len, blocksize)); if (d != top) return NULL; @@ -364,7 +364,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, #endif if (t->det_reserved_zero1 || - le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) || + (ext4_rec_len_from_disk(t->det_rec_len, blocksize) != + sizeof(struct ext4_dir_entry_tail)) || t->det_reserved_zero2 || t->det_reserved_ft != EXT4_FT_DIR_CSUM) return NULL; @@ -445,13 +446,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, struct ext4_dir_entry *dp; struct dx_root_info *root; int count_offset; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); + unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize); - if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) + if (rlen == blocksize) count_offset = 8; - else if (le16_to_cpu(dirent->rec_len) == 12) { + else if (rlen == 12) { dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); - if (le16_to_cpu(dp->rec_len) != - EXT4_BLOCK_SIZE(inode->i_sb) - 12) + if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12) return NULL; root = (struct dx_root_info *)(((void *)dp + 12)); if (root->reserved_zero || @@ -1315,6 +1317,7 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, unsigned int buflen = bh->b_size; char *base = bh->b_data; struct dx_hash_info h = *hinfo; + int blocksize = EXT4_BLOCK_SIZE(dir->i_sb); if (ext4_has_metadata_csum(dir->i_sb)) buflen -= sizeof(struct ext4_dir_entry_tail); @@ -1335,11 +1338,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; - map_tail->size = le16_to_cpu(de->rec_len); + map_tail->size = ext4_rec_len_from_disk(de->rec_len, + blocksize); count++; cond_resched(); } - de = ext4_next_entry(de, dir->i_sb->s_blocksize); + de = ext4_next_entry(de, blocksize); } return count; } From 4422080e777e3fa740e2920fe4de53cfad7fcef2 Mon Sep 17 00:00:00 2001 From: Yifan Zhang Date: Fri, 8 Sep 2023 16:46:39 +0800 Subject: [PATCH 1635/2093] drm/amd/display: fix the white screen issue when >= 64GB DRAM commit ef064187a9709393a981a56cce1e31880fd97107 upstream. Dropping bit 31:4 of page table base is wrong, it makes page table base points to wrong address if phys addr is beyond 64GB; dropping page_table_start/end bit 31:4 is unnecessary since dcn20_vmid_setup will do that. Also, while we are at it, cleanup the assignments using upper_32_bits()/lower_32_bits() and AMDGPU_GPU_PAGE_SHIFT. Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354 Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Acked-by: Harry Wentland Reviewed-by: Alex Deucher Signed-off-by: Yifan Zhang Co-developed-by: Hamza Mahfooz Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 208eeff50390..18274ff5082a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1265,11 +1265,15 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); - page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF; - page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12); - page_table_end.high_part = (u32)(adev->gmc.gart_end >> 44) & 0xF; - page_table_end.low_part = (u32)(adev->gmc.gart_end >> 12); - page_table_base.high_part = upper_32_bits(pt_base) & 0xF; + page_table_start.high_part = upper_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_start.low_part = lower_32_bits(adev->gmc.gart_start >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.high_part = upper_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_end.low_part = lower_32_bits(adev->gmc.gart_end >> + AMDGPU_GPU_PAGE_SHIFT); + page_table_base.high_part = upper_32_bits(pt_base); page_table_base.low_part = lower_32_bits(pt_base); pa_config->system_aperture.start_addr = (uint64_t)logical_addr_low << 18; From 45ea58f9dbf8faecc733e4f1db06a55fc0e7e6a7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 20 Sep 2023 12:57:00 +0200 Subject: [PATCH 1636/2093] Revert "memcg: drop kmem.limit_in_bytes" This reverts commit 21ef9e11205fca43785eecf7d4a99528d4de5701 which is commit 86327e8eb94c52eca4f93cfece2e29d1bf52acbf upstream. It breaks existing runc systems, as the tool always thinks the file should be present. Reported-by: Jeremi Piotrowski Link: https://lore.kernel.org/r/20230920081101.GA12096@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net Cc: Michal Hocko Cc: Shakeel Butt Cc: Johannes Weiner Cc: Roman Gushchin Cc: Muchun Song Cc: Tejun Heo Cc: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cgroup-v1/memory.rst | 2 ++ mm/memcontrol.c | 10 ++++++++++ 2 files changed, 12 insertions(+) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 34911ce5e4b5..2524061836ac 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -91,6 +91,8 @@ Brief summary of control files. memory.oom_control set/show oom controls. memory.numa_stat show the number of memory usage per numa node + memory.kmem.limit_in_bytes This knob is deprecated and writing to + it will return -ENOTSUPP. memory.kmem.usage_in_bytes show current kernel memory allocation memory.kmem.failcnt show the number of kernel memory usage hits limits diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0a403b241718..67b6d8238b3e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3841,6 +3841,10 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, case _MEMSWAP: ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; + case _KMEM: + /* kmem.limit_in_bytes is deprecated. */ + ret = -EOPNOTSUPP; + break; case _TCP: ret = memcg_update_tcp_max(memcg, nr_pages); break; @@ -5051,6 +5055,12 @@ static struct cftype mem_cgroup_legacy_files[] = { .seq_show = memcg_numa_stat_show, }, #endif + { + .name = "kmem.limit_in_bytes", + .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), From 4c6bb91581796d34466d85bc06c9393d27f83101 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 25 Aug 2023 15:28:00 +0200 Subject: [PATCH 1637/2093] drm/amdgpu: fix amdgpu_cs_p1_user_fence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 35588314e963938dfdcdb792c9170108399377d6 upstream. The offset is just 32bits here so this can potentially overflow if somebody specifies a large value. Instead reduce the size to calculate the last possible offset. The error handling path incorrectly drops the reference to the user fence BO resulting in potential reference count underflow. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 02a112d00d41..462416031564 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -120,7 +120,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, struct drm_gem_object *gobj; struct amdgpu_bo *bo; unsigned long size; - int r; gobj = drm_gem_object_lookup(p->filp, data->handle); if (gobj == NULL) @@ -132,23 +131,14 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, drm_gem_object_put(gobj); size = amdgpu_bo_size(bo); - if (size != PAGE_SIZE || (data->offset + 8) > size) { - r = -EINVAL; - goto error_unref; - } + if (size != PAGE_SIZE || data->offset > (size - 8)) + return -EINVAL; - if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) { - r = -EINVAL; - goto error_unref; - } + if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) + return -EINVAL; *offset = data->offset; - return 0; - -error_unref: - amdgpu_bo_unref(&bo); - return r; } static int amdgpu_cs_p1_bo_handles(struct amdgpu_cs_parser *p, From b93aeb6352b0229e3c5ca5ca4ff015b015aff33c Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 14 Feb 2023 08:49:15 -0500 Subject: [PATCH 1638/2093] net/sched: Retire rsvp classifier commit 265b4da82dbf5df04bee5a5d46b7474b1aaf326a upstream. The rsvp classifier has served us well for about a quarter of a century but has has not been getting much maintenance attention due to lack of known users. Signed-off-by: Jamal Hadi Salim Acked-by: Jiri Pirko Signed-off-by: Paolo Abeni Signed-off-by: Kyle Zeng Signed-off-by: Greg Kroah-Hartman --- net/sched/Kconfig | 28 - net/sched/Makefile | 2 - net/sched/cls_rsvp.c | 24 - net/sched/cls_rsvp.h | 764 ------------------ net/sched/cls_rsvp6.c | 24 - .../tc-testing/tc-tests/filters/rsvp.json | 203 ----- 6 files changed, 1045 deletions(-) delete mode 100644 net/sched/cls_rsvp.c delete mode 100644 net/sched/cls_rsvp.h delete mode 100644 net/sched/cls_rsvp6.c delete mode 100644 tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bcdd6e925343..24cf0bf7c80e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -548,34 +548,6 @@ config CLS_U32_MARK help Say Y here to be able to use netfilter marks as u32 key. -config NET_CLS_RSVP - tristate "IPv4 Resource Reservation Protocol (RSVP)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp. - -config NET_CLS_RSVP6 - tristate "IPv6 Resource Reservation Protocol (RSVP6)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6 protocol. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp6. - config NET_CLS_FLOW tristate "Flow classifier" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index b7dbac5c519f..8a33a35fc50d 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -69,8 +69,6 @@ obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o -obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c deleted file mode 100644 index de1c1d4da597..000000000000 --- a/net/sched/cls_rsvp.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4. - * - * Authors: Alexey Kuznetsov, - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define RSVP_DST_LEN 1 -#define RSVP_ID "rsvp" -#define RSVP_OPS cls_rsvp_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h deleted file mode 100644 index b00a7dbd0587..000000000000 --- a/net/sched/cls_rsvp.h +++ /dev/null @@ -1,764 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers. - * - * Authors: Alexey Kuznetsov, - */ - -/* - Comparing to general packet classification problem, - RSVP needs only several relatively simple rules: - - * (dst, protocol) are always specified, - so that we are able to hash them. - * src may be exact, or may be wildcard, so that - we can keep a hash table plus one wildcard entry. - * source port (or flow label) is important only if src is given. - - IMPLEMENTATION. - - We use a two level hash table: The top level is keyed by - destination address and protocol ID, every bucket contains a list - of "rsvp sessions", identified by destination address, protocol and - DPI(="Destination Port ID"): triple (key, mask, offset). - - Every bucket has a smaller hash table keyed by source address - (cf. RSVP flowspec) and one wildcard entry for wildcard reservations. - Every bucket is again a list of "RSVP flows", selected by - source address and SPI(="Source Port ID" here rather than - "security parameter index"): triple (key, mask, offset). - - - NOTE 1. All the packets with IPv6 extension headers (but AH and ESP) - and all fragmented packets go to the best-effort traffic class. - - - NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires - only one "Generalized Port Identifier". So that for classic - ah, esp (and udp,tcp) both *pi should coincide or one of them - should be wildcard. - - At first sight, this redundancy is just a waste of CPU - resources. But DPI and SPI add the possibility to assign different - priorities to GPIs. Look also at note 4 about tunnels below. - - - NOTE 3. One complication is the case of tunneled packets. - We implement it as following: if the first lookup - matches a special session with "tunnelhdr" value not zero, - flowid doesn't contain the true flow ID, but the tunnel ID (1...255). - In this case, we pull tunnelhdr bytes and restart lookup - with tunnel ID added to the list of keys. Simple and stupid 8)8) - It's enough for PIMREG and IPIP. - - - NOTE 4. Two GPIs make it possible to parse even GRE packets. - F.e. DPI can select ETH_P_IP (and necessary flags to make - tunnelhdr correct) in GRE protocol field and SPI matches - GRE key. Is it not nice? 8)8) - - - Well, as result, despite its simplicity, we get a pretty - powerful classification engine. */ - - -struct rsvp_head { - u32 tmap[256/32]; - u32 hgenerator; - u8 tgenerator; - struct rsvp_session __rcu *ht[256]; - struct rcu_head rcu; -}; - -struct rsvp_session { - struct rsvp_session __rcu *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; - /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter __rcu *ht[16 + 1]; - struct rcu_head rcu; -}; - - -struct rsvp_filter { - struct rsvp_filter __rcu *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; - - struct tcf_result res; - struct tcf_exts exts; - - u32 handle; - struct rsvp_session *sess; - struct rcu_work rwork; -}; - -static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) -{ - unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; - - h ^= h>>16; - h ^= h>>8; - return (h ^ protocol ^ tunnelid) & 0xFF; -} - -static inline unsigned int hash_src(__be32 *src) -{ - unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; - - h ^= h>>16; - h ^= h>>8; - h ^= h>>4; - return h & 0xF; -} - -#define RSVP_APPLY_RESULT() \ -{ \ - int r = tcf_exts_exec(skb, &f->exts, res); \ - if (r < 0) \ - continue; \ - else if (r > 0) \ - return r; \ -} - -static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct rsvp_head *head = rcu_dereference_bh(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1, h2; - __be32 *dst, *src; - u8 protocol; - u8 tunnelid = 0; - u8 *xprt; -#if RSVP_DST_LEN == 4 - struct ipv6hdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ipv6_hdr(skb); -#else - struct iphdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ip_hdr(skb); -#endif -restart: - -#if RSVP_DST_LEN == 4 - src = &nhptr->saddr.s6_addr32[0]; - dst = &nhptr->daddr.s6_addr32[0]; - protocol = nhptr->nexthdr; - xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); -#else - src = &nhptr->saddr; - dst = &nhptr->daddr; - protocol = nhptr->protocol; - xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (ip_is_fragment(nhptr)) - return -1; -#endif - - h1 = hash_dst(dst, protocol, tunnelid); - h2 = hash_src(src); - - for (s = rcu_dereference_bh(head->ht[h1]); s; - s = rcu_dereference_bh(s->next)) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && - protocol == s->protocol && - !(s->dpi.mask & - (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - tunnelid == s->tunnelid) { - - for (f = rcu_dereference_bh(s->ht[h2]); f; - f = rcu_dereference_bh(f->next)) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && - !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) -#if RSVP_DST_LEN == 4 - && - src[0] == f->src[0] && - src[1] == f->src[1] && - src[2] == f->src[2] -#endif - ) { - *res = f->res; - RSVP_APPLY_RESULT(); - -matched: - if (f->tunnelhdr == 0) - return 0; - - tunnelid = f->res.classid; - nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); - goto restart; - } - } - - /* And wildcard bucket... */ - for (f = rcu_dereference_bh(s->ht[16]); f; - f = rcu_dereference_bh(f->next)) { - *res = f->res; - RSVP_APPLY_RESULT(); - goto matched; - } - return -1; - } - } - return -1; -} - -static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter __rcu **ins; - struct rsvp_filter *pins; - unsigned int h1 = h & 0xFF; - unsigned int h2 = (h >> 8) & 0xFF; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ; - ins = &pins->next, pins = rtnl_dereference(*ins)) { - if (pins->handle == h) { - RCU_INIT_POINTER(n->next, pins->next); - rcu_assign_pointer(*ins, n); - return; - } - } - } - - /* Something went wrong if we are trying to replace a non-existent - * node. Mind as well halt instead of silently failing. - */ - BUG_ON(1); -} - -static void *rsvp_get(struct tcf_proto *tp, u32 handle) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1 = handle & 0xFF; - unsigned int h2 = (handle >> 8) & 0xFF; - - if (h2 > 16) - return NULL; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->handle == handle) - return f; - } - } - return NULL; -} - -static int rsvp_init(struct tcf_proto *tp) -{ - struct rsvp_head *data; - - data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); - if (data) { - rcu_assign_pointer(tp->root, data); - return 0; - } - return -ENOBUFS; -} - -static void __rsvp_delete_filter(struct rsvp_filter *f) -{ - tcf_exts_destroy(&f->exts); - tcf_exts_put_net(&f->exts); - kfree(f); -} - -static void rsvp_delete_filter_work(struct work_struct *work) -{ - struct rsvp_filter *f = container_of(to_rcu_work(work), - struct rsvp_filter, - rwork); - rtnl_lock(); - __rsvp_delete_filter(f); - rtnl_unlock(); -} - -static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -{ - tcf_unbind_filter(tp, &f->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (tcf_exts_get_net(&f->exts)) - tcf_queue_work(&f->rwork, rsvp_delete_filter_work); - else - __rsvp_delete_filter(f); -} - -static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int h1, h2; - - if (data == NULL) - return; - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - - while ((s = rtnl_dereference(data->ht[h1])) != NULL) { - RCU_INIT_POINTER(data->ht[h1], s->next); - - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - while ((f = rtnl_dereference(s->ht[h2])) != NULL) { - rcu_assign_pointer(s->ht[h2], f->next); - rsvp_delete_filter(tp, f); - } - } - kfree_rcu(s, rcu); - } - } - kfree_rcu(data, rcu); -} - -static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = arg; - struct rsvp_filter __rcu **fp; - unsigned int h = f->handle; - struct rsvp_session __rcu **sp; - struct rsvp_session *nsp, *s = f->sess; - int i, h1; - - fp = &s->ht[(h >> 8) & 0xFF]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - if (nfp == f) { - RCU_INIT_POINTER(*fp, f->next); - rsvp_delete_filter(tp, f); - - /* Strip tree */ - - for (i = 0; i <= 16; i++) - if (s->ht[i]) - goto out; - - /* OK, session has no flows */ - sp = &head->ht[h & 0xFF]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if (nsp == s) { - RCU_INIT_POINTER(*sp, s->next); - kfree_rcu(s, rcu); - goto out; - } - } - - break; - } - } - -out: - *last = true; - for (h1 = 0; h1 < 256; h1++) { - if (rcu_access_pointer(head->ht[h1])) { - *last = false; - break; - } - } - - return 0; -} - -static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int i = 0xFFFF; - - while (i-- > 0) { - u32 h; - - if ((data->hgenerator += 0x10000) == 0) - data->hgenerator = 0x10000; - h = data->hgenerator|salt; - if (!rsvp_get(tp, h)) - return h; - } - return 0; -} - -static int tunnel_bts(struct rsvp_head *data) -{ - int n = data->tgenerator >> 5; - u32 b = 1 << (data->tgenerator & 0x1F); - - if (data->tmap[n] & b) - return 0; - data->tmap[n] |= b; - return 1; -} - -static void tunnel_recycle(struct rsvp_head *data) -{ - struct rsvp_session __rcu **sht = data->ht; - u32 tmap[256/32]; - int h1, h2; - - memset(tmap, 0, sizeof(tmap)); - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - for (s = rtnl_dereference(sht[h1]); s; - s = rtnl_dereference(s->next)) { - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->tunnelhdr == 0) - continue; - data->tgenerator = f->res.classid; - tunnel_bts(data); - } - } - } - } - - memcpy(data->tmap, tmap, sizeof(tmap)); -} - -static u32 gen_tunnel(struct rsvp_head *data) -{ - int i, k; - - for (k = 0; k < 2; k++) { - for (i = 255; i > 0; i--) { - if (++data->tgenerator == 0) - data->tgenerator = 1; - if (tunnel_bts(data)) - return data->tgenerator; - } - tunnel_recycle(data); - } - return 0; -} - -static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { - [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, -}; - -static int rsvp_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, struct nlattr **tca, - void **arg, u32 flags, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - struct rsvp_filter *f, *nfp; - struct rsvp_filter __rcu **fp; - struct rsvp_session *nsp, *s; - struct rsvp_session __rcu **sp; - struct tc_rsvp_pinfo *pinfo = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_RSVP_MAX + 1]; - struct tcf_exts e; - unsigned int h1, h2; - __be32 *dst; - int err; - - if (opt == NULL) - return handle ? -EINVAL : 0; - - err = nla_parse_nested_deprecated(tb, TCA_RSVP_MAX, opt, rsvp_policy, - NULL); - if (err < 0) - return err; - - err = tcf_exts_init(&e, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, flags, - extack); - if (err < 0) - goto errout2; - - f = *arg; - if (f) { - /* Node exists: adjust only classid */ - struct rsvp_filter *n; - - if (f->handle != handle && handle) - goto errout2; - - n = kmemdup(f, sizeof(*f), GFP_KERNEL); - if (!n) { - err = -ENOMEM; - goto errout2; - } - - err = tcf_exts_init(&n->exts, net, TCA_RSVP_ACT, - TCA_RSVP_POLICE); - if (err < 0) { - kfree(n); - goto errout2; - } - - if (tb[TCA_RSVP_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } - - tcf_exts_change(&n->exts, &e); - rsvp_replace(tp, n, handle); - return 0; - } - - /* Now more serious part... */ - err = -EINVAL; - if (handle) - goto errout2; - if (tb[TCA_RSVP_DST] == NULL) - goto errout2; - - err = -ENOBUFS; - f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL); - if (f == NULL) - goto errout2; - - err = tcf_exts_init(&f->exts, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - goto errout; - h2 = 16; - if (tb[TCA_RSVP_SRC]) { - memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); - h2 = hash_src(f->src); - } - if (tb[TCA_RSVP_PINFO]) { - pinfo = nla_data(tb[TCA_RSVP_PINFO]); - f->spi = pinfo->spi; - f->tunnelhdr = pinfo->tunnelhdr; - } - if (tb[TCA_RSVP_CLASSID]) - f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - - dst = nla_data(tb[TCA_RSVP_DST]); - h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0); - - err = -ENOMEM; - if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0) - goto errout; - - if (f->tunnelhdr) { - err = -EINVAL; - if (f->res.classid > 255) - goto errout; - - err = -ENOMEM; - if (f->res.classid == 0 && - (f->res.classid = gen_tunnel(data)) == 0) - goto errout; - } - - for (sp = &data->ht[h1]; - (s = rtnl_dereference(*sp)) != NULL; - sp = &s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && - pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - pinfo->tunnelid == s->tunnelid) { - -insert: - /* OK, we found appropriate session */ - - fp = &s->ht[h2]; - - f->sess = s; - if (f->tunnelhdr == 0) - tcf_bind_filter(tp, &f->res, base); - - tcf_exts_change(&f->exts, &e); - - fp = &s->ht[h2]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - __u32 mask = nfp->spi.mask & f->spi.mask; - - if (mask != f->spi.mask) - break; - } - RCU_INIT_POINTER(f->next, nfp); - rcu_assign_pointer(*fp, f); - - *arg = f; - return 0; - } - } - - /* No session found. Create new one. */ - - err = -ENOBUFS; - s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL); - if (s == NULL) - goto errout; - memcpy(s->dst, dst, sizeof(s->dst)); - - if (pinfo) { - s->dpi = pinfo->dpi; - s->protocol = pinfo->protocol; - s->tunnelid = pinfo->tunnelid; - } - sp = &data->ht[h1]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) - break; - } - RCU_INIT_POINTER(s->next, nsp); - rcu_assign_pointer(*sp, s); - - goto insert; - -errout: - tcf_exts_destroy(&f->exts); - kfree(f); -errout2: - tcf_exts_destroy(&e); - return err; -} - -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg, - bool rtnl_held) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - unsigned int h, h1; - - if (arg->stop) - return; - - for (h = 0; h < 256; h++) { - struct rsvp_session *s; - - for (s = rtnl_dereference(head->ht[h]); s; - s = rtnl_dereference(s->next)) { - for (h1 = 0; h1 <= 16; h1++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h1]); f; - f = rtnl_dereference(f->next)) { - if (!tc_cls_stats_dump(tp, arg, f)) - return; - } - } - } - } -} - -static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) -{ - struct rsvp_filter *f = fh; - struct rsvp_session *s; - struct nlattr *nest; - struct tc_rsvp_pinfo pinfo; - - if (f == NULL) - return skb->len; - s = f->sess; - - t->tcm_handle = f->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) - goto nla_put_failure; - pinfo.dpi = s->dpi; - pinfo.spi = f->spi; - pinfo.protocol = s->protocol; - pinfo.tunnelid = s->tunnelid; - pinfo.tunnelhdr = f->tunnelhdr; - pinfo.pad = 0; - if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) - goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) - goto nla_put_failure; - if (((f->handle >> 8) & 0xFF) != 16 && - nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &f->exts) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &f->exts) < 0) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, - unsigned long base) -{ - struct rsvp_filter *f = fh; - - tc_cls_bind_class(classid, cl, q, &f->res, base); -} - -static struct tcf_proto_ops RSVP_OPS __read_mostly = { - .kind = RSVP_ID, - .classify = rsvp_classify, - .init = rsvp_init, - .destroy = rsvp_destroy, - .get = rsvp_get, - .change = rsvp_change, - .delete = rsvp_delete, - .walk = rsvp_walk, - .dump = rsvp_dump, - .bind_class = rsvp_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_rsvp(void) -{ - return register_tcf_proto_ops(&RSVP_OPS); -} - -static void __exit exit_rsvp(void) -{ - unregister_tcf_proto_ops(&RSVP_OPS); -} - -module_init(init_rsvp) -module_exit(exit_rsvp) diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c deleted file mode 100644 index 64078846000e..000000000000 --- a/net/sched/cls_rsvp6.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6. - * - * Authors: Alexey Kuznetsov, - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define RSVP_DST_LEN 4 -#define RSVP_ID "rsvp6" -#define RSVP_OPS cls_rsvp6_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json b/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json deleted file mode 100644 index bdcbaa4c5663..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json +++ /dev/null @@ -1,203 +0,0 @@ -[ - { - "id": "2141", - "name": "Add rsvp filter with tcp proto and specific IP address", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto tcp session 198.168.10.64", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*session 198.168.10.64 ipproto tcp", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "5267", - "name": "Add rsvp filter with udp proto and specific IP address", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*session 1.1.1.1 ipproto udp", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2819", - "name": "Add rsvp filter with src ip and src port", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 sender 2.2.2.2/5021 classid 1:1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp sender 2.2.2.2/5021", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "c967", - "name": "Add rsvp filter with tunnelid and continue action", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnelid 2 classid 1:1 action continue", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp tunnelid 2.*action order [0-9]+: gact action continue", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "5463", - "name": "Add rsvp filter with tunnel and pipe action", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnel 2 skip 1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*tunnel 2 skip 1 session 1.1.1.1 ipproto udp.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2332", - "name": "Add rsvp filter with miltiple actions", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 7 rsvp ipproto udp session 1.1.1.1 classid 1:1 action skbedit mark 7 pipe action gact drop", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp.*action order [0-9]+: skbedit mark 7 pipe.*action order [0-9]+: gact action drop", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8879", - "name": "Add rsvp filter with tunnel and skp flag", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnel 2 skip 1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*tunnel 2 skip 1 session 1.1.1.1 ipproto udp.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8261", - "name": "List rsvp filters", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 classid 1:1", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto tcp session 2.2.2.2/1234 classid 2:1" - ], - "cmdUnderTest": "$TC filter show dev $DEV1 parent ffff:", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh", - "matchCount": "2", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8989", - "name": "Delete rsvp filter", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 tunnelid 9 classid 2:1" - ], - "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 tunnelid 9 classid 2:1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 2:1 session 1.1.1.1/1234 ipproto udp tunnelid 9", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - } -] From 0db211ec0f1d32b93486e8f6565249ad4d1bece5 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 7 Aug 2023 10:11:41 -0700 Subject: [PATCH 1639/2093] interconnect: Teach lockdep about icc_bw_lock order commit 13619170303878e1dae86d9a58b039475c957fcf upstream. Teach lockdep that icc_bw_lock is needed in code paths that could deadlock if they trigger reclaim. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20230807171148.210181-8-robdclark@gmail.com Signed-off-by: Georgi Djakov Cc: Guenter Roeck Cc: Jon Hunter Signed-off-by: Greg Kroah-Hartman --- drivers/interconnect/core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index f4a493d78ee9..e4b2d9ef61b4 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1145,13 +1145,21 @@ void icc_sync_state(struct device *dev) } } } + mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_sync_state); static int __init icc_init(void) { - struct device_node *root = of_find_node_by_path("/"); + struct device_node *root; + + /* Teach lockdep about lock ordering wrt. shrinker: */ + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&icc_bw_lock); + fs_reclaim_release(GFP_KERNEL); + + root = of_find_node_by_path("/"); providers_count = of_count_icc_providers(root); of_node_put(root); From d23900f974e0fb995b36ef47283a5aa74ca25f51 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 23 Sep 2023 11:11:13 +0200 Subject: [PATCH 1640/2093] Linux 6.1.55 Link: https://lore.kernel.org/r/20230920112835.549467415@linuxfoundation.org Tested-by: SeongJae Park Tested-by: Salvatore Bonaccorso Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Bagas Sanjaya Tested-by: Takeshi Ogasawara Tested-by: Ron Economos Tested-by: Linux Kernel Functional Testing Tested-by: Joel Fernandes (Google) Tested-by: Conor Dooley Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 844afa653fdd..3d839824a722 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 54 +SUBLEVEL = 55 EXTRAVERSION = NAME = Curry Ramen From dbe0f49aaf96fd972d1d3ae1f4985c7d0837917d Mon Sep 17 00:00:00 2001 From: Jiyong Park Date: Mon, 25 Sep 2023 10:02:14 +0900 Subject: [PATCH 1641/2093] ANDROID: Move microdroid and crashdump defconfigs to common They don't have device-specific modules. They are just generic configs that are different from GKI. Bug: 301852599 Bug: 302301911 Test: run following commands tools/bazel run //common:kernel_aarch64_microdroid_dist tools/bazel run //common:kernel_x86_64_microdroid_dist tools/bazel run //common:kernel_aarch64_microdroid_config -- menuconfig tools/bazel run //common:kernel_x86_64_microdroid_config -- menuconfig tools/bazel run //common:kernel_aarch64_crashdump_dist tools/bazel run //common:kernel_x86_64_crashdump_dist tools/bazel run //common:kernel_aarch64_crashdump_config -- menuconfig tools/bazel run //common:kernel_x86_64_crashdump_config -- menuconfig Change-Id: I8908a7499451ace0740979b694eb5fcc68398c61 Signed-off-by: Jiyong Park (cherry picked from commit ae5ea9043de17f2ec08a92317add206590784bd9) --- BUILD.bazel | 96 ++++++++ arch/arm64/configs/crashdump_defconfig | 81 +++++++ arch/arm64/configs/microdroid_defconfig | 216 ++++++++++++++++++ arch/x86/configs/crashdump_defconfig | 87 +++++++ arch/x86/configs/microdroid_defconfig | 290 ++++++++++++++++++++++++ build.config.crashdump | 1 + build.config.crashdump.aarch64 | 7 + build.config.crashdump.x86_64 | 7 + build.config.microdroid | 1 + build.config.microdroid.aarch64 | 7 + build.config.microdroid.x86_64 | 7 + 11 files changed, 800 insertions(+) create mode 100644 arch/arm64/configs/crashdump_defconfig create mode 100644 arch/arm64/configs/microdroid_defconfig create mode 100644 arch/x86/configs/crashdump_defconfig create mode 100644 arch/x86/configs/microdroid_defconfig create mode 100644 build.config.crashdump create mode 100644 build.config.crashdump.aarch64 create mode 100644 build.config.crashdump.x86_64 create mode 100644 build.config.microdroid create mode 100644 build.config.microdroid.aarch64 create mode 100644 build.config.microdroid.x86_64 diff --git a/BUILD.bazel b/BUILD.bazel index a9f5348d052e..d16cef6dbcae 100644 --- a/BUILD.bazel +++ b/BUILD.bazel @@ -4,6 +4,7 @@ load("@bazel_skylib//rules:write_file.bzl", "write_file") load("//build/bazel_common_rules/dist:dist.bzl", "copy_to_dist_dir") load("//build/kernel/kleaf:common_kernels.bzl", "define_common_kernels") +load("//build/kernel/kleaf:constants.bzl", "X86_64_OUTS") load( "//build/kernel/kleaf:kernel.bzl", "checkpatch", @@ -124,6 +125,101 @@ define_common_kernels(target_configs = { }, }) +# Microdroid is not a real device. The kernel image is built with special +# configs to reduce the size. Hence, not using mixed build. +kernel_build( + name = "kernel_aarch64_microdroid", + srcs = ["//common:kernel_aarch64_sources"], + outs = [ + "Image", + "System.map", + "modules.builtin", + "modules.builtin.modinfo", + "vmlinux", + "vmlinux.symvers", + ], + build_config = "build.config.microdroid.aarch64", + make_goals = [ + "Image", + ], +) + +copy_to_dist_dir( + name = "kernel_aarch64_microdroid_dist", + data = [ + ":kernel_aarch64_microdroid", + ], + dist_dir = "out/kernel_aarch64_microdroid/dist", + flat = True, + log = "info", +) + +# Microdroid is not a real device. The kernel image is built with special +# configs to reduce the size. Hence, not using mixed build. +kernel_build( + name = "kernel_x86_64_microdroid", + srcs = ["//common:kernel_x86_64_sources"], + outs = X86_64_OUTS, + arch = "x86_64", + build_config = "build.config.microdroid.x86_64", + make_goals = [ + "bzImage", + ], +) + +copy_to_dist_dir( + name = "kernel_x86_64_microdroid_dist", + data = [ + ":kernel_x86_64_microdroid", + ], + dist_dir = "out/kernel_x86_64_microdroid/dist", + flat = True, + log = "info", +) + +kernel_build( + name = "kernel_aarch64_crashdump", + srcs = ["//common:kernel_aarch64_sources"], + outs = [ + "Image", + ], + build_config = "build.config.crashdump.aarch64", + make_goals = [ + "Image", + ], +) + +copy_to_dist_dir( + name = "kernel_aarch64_crashdump_dist", + data = [ + ":kernel_aarch64_crashdump", + ], + dist_dir = "out/kernel_aarch64_crashdump/dist", + flat = True, + log = "info", +) + +kernel_build( + name = "kernel_x86_64_crashdump", + srcs = ["//common:kernel_x86_64_sources"], + outs = X86_64_OUTS, + arch = "x86_64", + build_config = "build.config.crashdump.x86_64", + make_goals = [ + "bzImage", + ], +) + +copy_to_dist_dir( + name = "kernel_x86_64_crashdump_dist", + data = [ + ":kernel_x86_64_crashdump", + ], + dist_dir = "out/kernel_x86_64_crashdump/dist", + flat = True, + log = "info", +) + _DB845C_MODULE_OUTS = [ # keep sorted "crypto/michael_mic.ko", diff --git a/arch/arm64/configs/crashdump_defconfig b/arch/arm64/configs/crashdump_defconfig new file mode 100644 index 000000000000..75866b00b403 --- /dev/null +++ b/arch/arm64/configs/crashdump_defconfig @@ -0,0 +1,81 @@ +# CONFIG_WERROR is not set +# CONFIG_LOCALVERSION_AUTO is not set +# CONFIG_SWAP is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_PREEMPT=y +# CONFIG_CPU_ISOLATION is not set +CONFIG_LOG_BUF_SHIFT=15 +CONFIG_LOG_CPU_MAX_BUF_SHIFT=10 +# CONFIG_UTS_NS is not set +# CONFIG_TIME_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZ4 is not set +# CONFIG_RD_ZSTD is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_COMPAT_BRK is not set +# CONFIG_SLAB_MERGE_DEFAULT is not set +# CONFIG_SLUB_CPU_PARTIAL is not set +CONFIG_ARM64_VA_BITS_48=y +CONFIG_NR_CPUS=2 +CONFIG_CRASH_DUMP=y +# CONFIG_RODATA_FULL_DEFAULT_ENABLED is not set +# CONFIG_ARM64_TAGGED_ADDR_ABI is not set +# CONFIG_ARM64_SVE is not set +# CONFIG_EFI is not set +# CONFIG_SUSPEND is not set +CONFIG_JUMP_LABEL=y +# CONFIG_SECCOMP is not set +# CONFIG_STACKPROTECTOR is not set +# CONFIG_VMAP_STACK is not set +# CONFIG_MQ_IOSCHED_DEADLINE is not set +# CONFIG_MQ_IOSCHED_KYBER is not set +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_BINFMT_SCRIPT is not set +# CONFIG_SPECULATIVE_PAGE_FAULT is not set +CONFIG_PCI=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCI_ENDPOINT=y +CONFIG_DEVTMPFS=y +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +CONFIG_ARM_SCMI_PROTOCOL=y +# CONFIG_ARM_SMCCC_SOC_ID is not set +# CONFIG_BLK_DEV is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_VIRTIO_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set +# CONFIG_HWMON is not set +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_VIRTIO_PCI=y +# CONFIG_VIRTIO_PCI_LEGACY is not set +# CONFIG_VHOST_MENU is not set +# CONFIG_ARM_ARCH_TIMER_EVTSTREAM is not set +# CONFIG_FSL_ERRATUM_A008585 is not set +# CONFIG_HISILICON_ERRATUM_161010101 is not set +# CONFIG_ARM64_ERRATUM_858921 is not set +# CONFIG_IOMMU_SUPPORT is not set +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_XZ_DEC=y +# CONFIG_SYMBOLIC_ERRNAME is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/arm64/configs/microdroid_defconfig b/arch/arm64/configs/microdroid_defconfig new file mode 100644 index 000000000000..3f8fb833040c --- /dev/null +++ b/arch/arm64/configs/microdroid_defconfig @@ -0,0 +1,216 @@ +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y +CONFIG_IRQ_TIME_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_RCU_EXPERT=y +CONFIG_RCU_BOOST=y +CONFIG_RCU_NOCB_CPU=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +# CONFIG_UTS_NS is not set +# CONFIG_TIME_NS is not set +# CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_ZSTD is not set +CONFIG_BOOT_CONFIG=y +CONFIG_PROFILING=y +CONFIG_SCHED_MC=y +CONFIG_NR_CPUS=32 +CONFIG_PARAVIRT_TIME_ACCOUNTING=y +CONFIG_KEXEC_FILE=y +CONFIG_ARM64_SW_TTBR0_PAN=y +CONFIG_RANDOMIZE_BASE=y +# CONFIG_RANDOMIZE_MODULE_REGION_FULL is not set +CONFIG_CMDLINE="stack_depot_disable=on kasan.stacktrace=off cgroup_disable=pressure ioremap_guard panic=-1 bootconfig" +CONFIG_CMDLINE_EXTEND=y +# CONFIG_EFI is not set +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_VIRTUALIZATION=y +CONFIG_JUMP_LABEL=y +CONFIG_SHADOW_CALL_STACK=y +CONFIG_CFI_CLANG=y +CONFIG_MODULES=y +CONFIG_BLK_DEV_ZONED=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y +CONFIG_PARTITION_ADVANCED=y +# CONFIG_MSDOS_PARTITION is not set +CONFIG_IOSCHED_BFQ=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=y +# CONFIG_SLAB_MERGE_DEFAULT is not set +CONFIG_SLAB_FREELIST_RANDOM=y +CONFIG_SLAB_FREELIST_HARDENED=y +CONFIG_SHUFFLE_PAGE_ALLOCATOR=y +# CONFIG_COMPAT_BRK is not set +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=32768 +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y +CONFIG_ANON_VMA_NAME=y +CONFIG_USERFAULTFD=y +CONFIG_LRU_GEN=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_XFRM_INTERFACE=y +CONFIG_XFRM_MIGRATE=y +CONFIG_XFRM_STATISTICS=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_NET_IPIP=y +CONFIG_NET_IPGRE_DEMUX=y +CONFIG_NET_IPGRE=y +CONFIG_NET_IPVTI=y +CONFIG_INET_ESP=y +CONFIG_INET_UDP_DIAG=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_VTI=y +CONFIG_IPV6_GRE=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y +# CONFIG_WIRELESS is not set +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCIEAER=y +CONFIG_PCI_IOV=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCIE_DW_PLAT_EP=y +CONFIG_PCIE_KIRIN=y +CONFIG_PCI_ENDPOINT=y +CONFIG_FW_LOADER_USER_HELPER=y +# CONFIG_FW_CACHE is not set +CONFIG_ARM_SCMI_PROTOCOL=y +# CONFIG_ARM_SCMI_POWER_DOMAIN is not set +CONFIG_ZRAM=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_LOOP_MIN_COUNT=16 +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_OPEN_DICE=y +CONFIG_VCPU_STALL_DETECTOR=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_INIT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set +CONFIG_SERIAL_8250_CONSOLE=y +# CONFIG_SERIAL_8250_PCI is not set +CONFIG_SERIAL_8250_RUNTIME_UARTS=0 +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_NULL_TTY=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_CCTRNG=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVPORT is not set +CONFIG_POWER_RESET_SYSCON=y +# CONFIG_HWMON is not set +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_CORE=y +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_EDAC=y +CONFIG_RTC_CLASS=y +# CONFIG_RTC_NVMEM is not set +CONFIG_RTC_DRV_PL030=y +CONFIG_RTC_DRV_PL031=y +CONFIG_DMABUF_HEAPS=y +CONFIG_DMABUF_SYSFS_STATS=y +CONFIG_UIO=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_STAGING=y +CONFIG_HWSPINLOCK=y +CONFIG_EXT4_FS=y +# CONFIG_EXT4_USE_FOR_EXT2 is not set +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +# CONFIG_DNOTIFY is not set +CONFIG_FUSE_FS=y +CONFIG_TMPFS=y +CONFIG_EROFS_FS=y +# CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_UNICODE=y +CONFIG_SECURITY=y +CONFIG_SECURITYFS=y +CONFIG_SECURITY_NETWORK=y +CONFIG_HARDENED_USERCOPY=y +CONFIG_STATIC_USERMODEHELPER=y +CONFIG_STATIC_USERMODEHELPER_PATH="" +CONFIG_SECURITY_SELINUX=y +CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y +CONFIG_CRYPTO_DES=y +CONFIG_CRYPTO_ADIANTUM=y +CONFIG_CRYPTO_HCTR2=y +CONFIG_CRYPTO_CHACHA20POLY1305=y +CONFIG_CRYPTO_BLAKE2B=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_XCBC=y +CONFIG_CRYPTO_LZO=y +CONFIG_CRYPTO_LZ4=y +CONFIG_CRYPTO_ZSTD=y +CONFIG_CRYPTO_ANSI_CPRNG=y +CONFIG_TRACE_MMIO_ACCESS=y +CONFIG_XZ_DEC=y +CONFIG_DMA_RESTRICTED_POOL=y +CONFIG_PRINTK_TIME=y +CONFIG_PRINTK_CALLER=y +CONFIG_DYNAMIC_DEBUG_CORE=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO_DWARF5=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_INFO_COMPRESSED=y +CONFIG_HEADERS_INSTALL=y +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_UBSAN=y +CONFIG_UBSAN_TRAP=y +CONFIG_UBSAN_LOCAL_BOUNDS=y +# CONFIG_UBSAN_SHIFT is not set +# CONFIG_UBSAN_BOOL is not set +# CONFIG_UBSAN_ENUM is not set +CONFIG_PAGE_OWNER=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_KASAN=y +CONFIG_KASAN_HW_TAGS=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PANIC_TIMEOUT=-1 +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHEDSTATS=y +# CONFIG_DEBUG_PREEMPT is not set +CONFIG_BUG_ON_DATA_CORRUPTION=y +CONFIG_HIST_TRIGGERS=y +CONFIG_PID_IN_CONTEXTIDR=y +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/x86/configs/crashdump_defconfig b/arch/x86/configs/crashdump_defconfig new file mode 100644 index 000000000000..5177d6e4619b --- /dev/null +++ b/arch/x86/configs/crashdump_defconfig @@ -0,0 +1,87 @@ +# CONFIG_WERROR is not set +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_KERNEL_LZ4=y +# CONFIG_SWAP is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_PREEMPT=y +CONFIG_LOG_BUF_SHIFT=12 +CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT=12 +# CONFIG_UTS_NS is not set +# CONFIG_TIME_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +# CONFIG_RD_ZSTD is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_COMPAT_BRK is not set +# CONFIG_SLAB_MERGE_DEFAULT is not set +# CONFIG_RETPOLINE is not set +# CONFIG_X86_EXTENDED_PLATFORM is not set +# CONFIG_SCHED_OMIT_FRAME_POINTER is not set +# CONFIG_X86_MCE is not set +# CONFIG_PERF_EVENTS_AMD_UNCORE is not set +# CONFIG_X86_IOPL_IOPERM is not set +# CONFIG_MICROCODE is not set +# CONFIG_X86_5LEVEL is not set +# CONFIG_MTRR_SANITIZER is not set +# CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS is not set +CONFIG_CRASH_DUMP=y +CONFIG_PHYSICAL_START=0x100000 +# CONFIG_RANDOMIZE_BASE is not set +CONFIG_LEGACY_VSYSCALL_NONE=y +# CONFIG_SUSPEND is not set +# CONFIG_ACPI is not set +# CONFIG_VIRTUALIZATION is not set +CONFIG_JUMP_LABEL=y +# CONFIG_SECCOMP is not set +# CONFIG_STACKPROTECTOR is not set +# CONFIG_VMAP_STACK is not set +# CONFIG_MQ_IOSCHED_DEADLINE is not set +# CONFIG_MQ_IOSCHED_KYBER is not set +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_BINFMT_SCRIPT is not set +# CONFIG_SPARSEMEM_VMEMMAP is not set +# CONFIG_COMPACTION is not set +CONFIG_PCI=y +CONFIG_PCI_ENDPOINT=y +CONFIG_DEVTMPFS=y +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_DMIID is not set +# CONFIG_BLK_DEV is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO_I8042 is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_DEV_BUS=y +# CONFIG_SERIAL_DEV_CTRL_TTYPORT is not set +CONFIG_VIRTIO_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set +# CONFIG_HWMON is not set +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_VIRTIO_PCI=y +# CONFIG_VIRTIO_PCI_LEGACY is not set +# CONFIG_VHOST_MENU is not set +# CONFIG_X86_PLATFORM_DEVICES is not set +# CONFIG_IOMMU_SUPPORT is not set +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +# CONFIG_PAGE_TABLE_ISOLATION is not set +# CONFIG_SYMBOLIC_ERRNAME is not set +# CONFIG_X86_VERBOSE_BOOTUP is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/x86/configs/microdroid_defconfig b/arch/x86/configs/microdroid_defconfig new file mode 100644 index 000000000000..d2539f0adce9 --- /dev/null +++ b/arch/x86/configs/microdroid_defconfig @@ -0,0 +1,290 @@ +CONFIG_KERNEL_LZ4=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y +CONFIG_IRQ_TIME_ACCOUNTING=y +CONFIG_TASKSTATS=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_RCU_EXPERT=y +CONFIG_RCU_BOOST=y +CONFIG_RCU_NOCB_CPU=y +CONFIG_UCLAMP_TASK=y +CONFIG_UCLAMP_BUCKETS_COUNT=20 +CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_SCHED=y +CONFIG_UCLAMP_TASK_GROUP=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +# CONFIG_UTS_NS is not set +# CONFIG_TIME_NS is not set +# CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +CONFIG_BOOT_CONFIG=y +CONFIG_PROFILING=y +CONFIG_SMP=y +CONFIG_X86_X2APIC=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_PARAVIRT_TIME_ACCOUNTING=y +CONFIG_NR_CPUS=32 +# CONFIG_X86_MCE is not set +CONFIG_EFI=y +CONFIG_KEXEC_FILE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="stack_depot_disable=on cgroup_disable=pressure ioremap_guard panic=-1 bootconfig acpi=noirq" +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_TIMES=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_BLK_DEV_ZONED=y +CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y +CONFIG_PARTITION_ADVANCED=y +# CONFIG_MSDOS_PARTITION is not set +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=y +# CONFIG_SLAB_MERGE_DEFAULT is not set +CONFIG_SLAB_FREELIST_RANDOM=y +CONFIG_SLAB_FREELIST_HARDENED=y +CONFIG_SHUFFLE_PAGE_ALLOCATOR=y +# CONFIG_COMPAT_BRK is not set +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=32768 +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_TRANSPARENT_HUGEPAGE_MADVISE=y +CONFIG_ANON_VMA_NAME=y +CONFIG_USERFAULTFD=y +CONFIG_LRU_GEN=y +CONFIG_DAMON=y +CONFIG_DAMON_PADDR=y +CONFIG_DAMON_RECLAIM=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_XFRM_INTERFACE=y +CONFIG_XFRM_MIGRATE=y +CONFIG_XFRM_STATISTICS=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_NET_IPIP=y +CONFIG_NET_IPGRE_DEMUX=y +CONFIG_NET_IPGRE=y +CONFIG_NET_IPVTI=y +CONFIG_INET_ESP=y +CONFIG_INET_UDP_DIAG=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_VTI=y +CONFIG_IPV6_GRE=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y +CONFIG_CGROUP_NET_PRIO=y +# CONFIG_WIRELESS is not set +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCIEAER=y +CONFIG_PCI_MSI=y +CONFIG_PCI_IOV=y +CONFIG_PCIE_DW_PLAT_EP=y +CONFIG_PCI_ENDPOINT=y +CONFIG_FW_LOADER_USER_HELPER=y +# CONFIG_FW_CACHE is not set +CONFIG_OF=y +CONFIG_ZRAM=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_LOOP_MIN_COUNT=16 +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_INIT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set +CONFIG_SERIAL_8250_CONSOLE=y +# CONFIG_SERIAL_8250_PCI is not set +CONFIG_SERIAL_8250_RUNTIME_UARTS=0 +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_NULL_TTY=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVPORT is not set +CONFIG_HPET=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_GENERIC_PLATFORM=y +# CONFIG_HWMON is not set +CONFIG_THERMAL_NETLINK=y +CONFIG_THERMAL_STATISTICS=y +CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS=100 +CONFIG_THERMAL_WRITABLE_TRIPS=y +CONFIG_THERMAL_GOV_USER_SPACE=y +CONFIG_CPU_THERMAL=y +CONFIG_THERMAL_EMULATION=y +# CONFIG_X86_PKG_TEMP_THERMAL is not set +CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_CORE=y +CONFIG_MFD_SYSCON=y +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_EDAC=y +CONFIG_RTC_CLASS=y +CONFIG_DMABUF_HEAPS=y +CONFIG_DMABUF_SYSFS_STATS=y +CONFIG_UIO=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_STAGING=y +CONFIG_LIBNVDIMM=y +CONFIG_EXT4_FS=y +# CONFIG_EXT4_USE_FOR_EXT2 is not set +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +# CONFIG_DNOTIFY is not set +CONFIG_FUSE_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_EFIVAR_FS is not set +CONFIG_EROFS_FS=y +# CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_CODEPAGE_737=y +CONFIG_NLS_CODEPAGE_775=y +CONFIG_NLS_CODEPAGE_850=y +CONFIG_NLS_CODEPAGE_852=y +CONFIG_NLS_CODEPAGE_855=y +CONFIG_NLS_CODEPAGE_857=y +CONFIG_NLS_CODEPAGE_860=y +CONFIG_NLS_CODEPAGE_861=y +CONFIG_NLS_CODEPAGE_862=y +CONFIG_NLS_CODEPAGE_863=y +CONFIG_NLS_CODEPAGE_864=y +CONFIG_NLS_CODEPAGE_865=y +CONFIG_NLS_CODEPAGE_866=y +CONFIG_NLS_CODEPAGE_869=y +CONFIG_NLS_CODEPAGE_936=y +CONFIG_NLS_CODEPAGE_950=y +CONFIG_NLS_CODEPAGE_932=y +CONFIG_NLS_CODEPAGE_949=y +CONFIG_NLS_CODEPAGE_874=y +CONFIG_NLS_ISO8859_8=y +CONFIG_NLS_CODEPAGE_1250=y +CONFIG_NLS_CODEPAGE_1251=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_ISO8859_2=y +CONFIG_NLS_ISO8859_3=y +CONFIG_NLS_ISO8859_4=y +CONFIG_NLS_ISO8859_5=y +CONFIG_NLS_ISO8859_6=y +CONFIG_NLS_ISO8859_7=y +CONFIG_NLS_ISO8859_9=y +CONFIG_NLS_ISO8859_13=y +CONFIG_NLS_ISO8859_14=y +CONFIG_NLS_ISO8859_15=y +CONFIG_NLS_KOI8_R=y +CONFIG_NLS_KOI8_U=y +CONFIG_NLS_MAC_ROMAN=y +CONFIG_NLS_MAC_CELTIC=y +CONFIG_NLS_MAC_CENTEURO=y +CONFIG_NLS_MAC_CROATIAN=y +CONFIG_NLS_MAC_CYRILLIC=y +CONFIG_NLS_MAC_GAELIC=y +CONFIG_NLS_MAC_GREEK=y +CONFIG_NLS_MAC_ICELAND=y +CONFIG_NLS_MAC_INUIT=y +CONFIG_NLS_MAC_ROMANIAN=y +CONFIG_NLS_MAC_TURKISH=y +CONFIG_NLS_UTF8=y +CONFIG_UNICODE=y +CONFIG_SECURITY=y +CONFIG_SECURITYFS=y +CONFIG_SECURITY_NETWORK=y +CONFIG_HARDENED_USERCOPY=y +CONFIG_STATIC_USERMODEHELPER=y +CONFIG_STATIC_USERMODEHELPER_PATH="" +CONFIG_SECURITY_SELINUX=y +CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y +CONFIG_CRYPTO_DES=y +CONFIG_CRYPTO_ADIANTUM=y +CONFIG_CRYPTO_HCTR2=y +CONFIG_CRYPTO_CHACHA20POLY1305=y +CONFIG_CRYPTO_BLAKE2B=y +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_XCBC=y +CONFIG_CRYPTO_LZO=y +CONFIG_CRYPTO_LZ4=y +CONFIG_CRYPTO_ZSTD=y +CONFIG_CRYPTO_ANSI_CPRNG=y +CONFIG_CRYPTO_AES_NI_INTEL=y +CONFIG_CRYPTO_POLYVAL_CLMUL_NI=y +CONFIG_CRYPTO_SHA256_SSSE3=y +CONFIG_CRYPTO_SHA512_SSSE3=y +CONFIG_CRC8=y +CONFIG_XZ_DEC=y +CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG_CORE=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO_DWARF5=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_INFO_COMPRESSED=y +CONFIG_HEADERS_INSTALL=y +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_UBSAN=y +CONFIG_UBSAN_TRAP=y +CONFIG_UBSAN_LOCAL_BOUNDS=y +# CONFIG_UBSAN_SHIFT is not set +# CONFIG_UBSAN_BOOL is not set +# CONFIG_UBSAN_ENUM is not set +CONFIG_PAGE_OWNER=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_KFENCE=y +CONFIG_KFENCE_SAMPLE_INTERVAL=500 +CONFIG_KFENCE_NUM_OBJECTS=63 +CONFIG_PANIC_ON_OOPS=y +CONFIG_PANIC_TIMEOUT=-1 +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHEDSTATS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y +CONFIG_HIST_TRIGGERS=y +CONFIG_UNWINDER_FRAME_POINTER=y diff --git a/build.config.crashdump b/build.config.crashdump new file mode 100644 index 000000000000..8a4214358308 --- /dev/null +++ b/build.config.crashdump @@ -0,0 +1 @@ +DEFCONFIG=crashdump_defconfig diff --git a/build.config.crashdump.aarch64 b/build.config.crashdump.aarch64 new file mode 100644 index 000000000000..20a8acc98912 --- /dev/null +++ b/build.config.crashdump.aarch64 @@ -0,0 +1,7 @@ +KERNEL_DIR=common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.aarch64 +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.crashdump + +# No modules +IN_KERNEL_MODULES= diff --git a/build.config.crashdump.x86_64 b/build.config.crashdump.x86_64 new file mode 100644 index 000000000000..18eed729a8c1 --- /dev/null +++ b/build.config.crashdump.x86_64 @@ -0,0 +1,7 @@ +KERNEL_DIR=common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.x86_64 +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.crashdump + +# No modules +IN_KERNEL_MODULES= diff --git a/build.config.microdroid b/build.config.microdroid new file mode 100644 index 000000000000..d31e0d5587f3 --- /dev/null +++ b/build.config.microdroid @@ -0,0 +1 @@ +DEFCONFIG=microdroid_defconfig diff --git a/build.config.microdroid.aarch64 b/build.config.microdroid.aarch64 new file mode 100644 index 000000000000..a8ffa55bc2ad --- /dev/null +++ b/build.config.microdroid.aarch64 @@ -0,0 +1,7 @@ +KERNEL_DIR=common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.aarch64 +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.microdroid + +# No modules +IN_KERNEL_MODULES= diff --git a/build.config.microdroid.x86_64 b/build.config.microdroid.x86_64 new file mode 100644 index 000000000000..10cd8b23a748 --- /dev/null +++ b/build.config.microdroid.x86_64 @@ -0,0 +1,7 @@ +KERNEL_DIR=common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.common +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.x86_64 +. ${ROOT_DIR}/${KERNEL_DIR}/build.config.microdroid + +# No modules +IN_KERNEL_MODULES= From 9e3a2d05a62f7376995689aae2bc27c9e0a84acd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 30 Sep 2023 16:10:53 +0000 Subject: [PATCH 1642/2093] ANDROID: GKI: Fix firmware: smccc build error In commit 0ca5de8309f9 ("firmware: smccc: Fix use of uninitialised results structure"), a unused variable was removed, but in the android-specific changes in the function, the variable was still needed, so it broke the build. Fix this up by putting the variable back as it is required and set it properly. Fixes: 0ca5de8309f9 ("firmware: smccc: Fix use of uninitialised results structure") Change-Id: Icef4bcc0403f4f09fb7ca3a72346007af79f7f8e Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/smccc/soc_id.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c index 29299ff5e7db..1a466f5687f1 100644 --- a/drivers/firmware/smccc/soc_id.c +++ b/drivers/firmware/smccc/soc_id.c @@ -34,6 +34,7 @@ static struct soc_device_attribute *soc_dev_attr; static int __init smccc_soc_init(void) { + struct arm_smccc_res res; int soc_id_rev, soc_id_version; static char soc_id_str[20], soc_id_rev_str[12]; static char soc_id_jep106_id_str[12]; @@ -54,17 +55,7 @@ static int __init smccc_soc_init(void) return 0; } - if (soc_id_version < 0) { - pr_err("Invalid SoC Version: %x\n", soc_id_version); - return -EINVAL; - } - - soc_id_rev = arm_smccc_get_soc_id_revision(); - if (soc_id_rev < 0) { - pr_err("Invalid SoC Revision: %x\n", soc_id_rev); - return -EINVAL; - } - + soc_id_version = arm_smccc_get_version(); soc_id_rev = res.a0; soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); From f16fd0b11f0f4d41846b5102b1656ea1fc9ac7a0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:34:37 -0400 Subject: [PATCH 1643/2093] NFS: Fix error handling for O_DIRECT write scheduling [ Upstream commit 954998b60caa8f2a3bf3abe490de6f08d283687a ] If we fail to schedule a request for transmission, there are 2 possibilities: 1) Either we hit a fatal error, and we just want to drop the remaining requests on the floor. 2) We were asked to try again, in which case we should allow the outstanding RPC calls to complete, so that we can recoalesce requests and try again. Fixes: d600ad1f2bdb ("NFS41: pop some layoutget errors to application") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/direct.c | 66 +++++++++++++++++++++++++++++++++++-------------- 1 file changed, 48 insertions(+), 18 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 3bb530d4bb5c..d71762f32b6c 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -530,10 +530,9 @@ nfs_direct_write_scan_commit_list(struct inode *inode, static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { struct nfs_pageio_descriptor desc; - struct nfs_page *req, *tmp; + struct nfs_page *req; LIST_HEAD(reqs); struct nfs_commit_info cinfo; - LIST_HEAD(failed); nfs_init_cinfo_from_dreq(&cinfo, dreq); nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); @@ -551,27 +550,36 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; - list_for_each_entry_safe(req, tmp, &reqs, wb_list) { + while (!list_empty(&reqs)) { + req = nfs_list_entry(reqs.next); /* Bump the transmission count */ req->wb_nio++; if (!nfs_pageio_add_request(&desc, req)) { - nfs_list_move_request(req, &failed); spin_lock(&cinfo.inode->i_lock); - dreq->flags = 0; - if (desc.pg_error < 0) + if (dreq->error < 0) { + desc.pg_error = dreq->error; + } else if (desc.pg_error != -EAGAIN) { + dreq->flags = 0; + if (!desc.pg_error) + desc.pg_error = -EIO; dreq->error = desc.pg_error; - else - dreq->error = -EIO; + } else + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; spin_unlock(&cinfo.inode->i_lock); + break; } nfs_release_request(req); } nfs_pageio_complete(&desc); - while (!list_empty(&failed)) { - req = nfs_list_entry(failed.next); + while (!list_empty(&reqs)) { + req = nfs_list_entry(reqs.next); nfs_list_remove_request(req); nfs_unlock_and_release_request(req); + if (desc.pg_error == -EAGAIN) + nfs_mark_request_commit(req, NULL, &cinfo, 0); + else + nfs_release_request(req); } if (put_dreq(dreq)) @@ -796,9 +804,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; + struct nfs_commit_info cinfo; ssize_t result = 0; size_t requested_bytes = 0; size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); + bool defer = false; trace_nfs_direct_write_schedule_iovec(dreq); @@ -839,19 +849,39 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, break; } - nfs_lock_request(req); - req->wb_index = pos >> PAGE_SHIFT; - req->wb_offset = pos & ~PAGE_MASK; - if (!nfs_pageio_add_request(&desc, req)) { - result = desc.pg_error; - nfs_unlock_and_release_request(req); - break; - } pgbase = 0; bytes -= req_len; requested_bytes += req_len; pos += req_len; dreq->bytes_left -= req_len; + + if (defer) { + nfs_mark_request_commit(req, NULL, &cinfo, 0); + continue; + } + + nfs_lock_request(req); + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (nfs_pageio_add_request(&desc, req)) + continue; + + /* Exit on hard errors */ + if (desc.pg_error < 0 && desc.pg_error != -EAGAIN) { + result = desc.pg_error; + nfs_unlock_and_release_request(req); + break; + } + + /* If the error is soft, defer remaining requests */ + nfs_init_cinfo_from_dreq(&cinfo, dreq); + spin_lock(&cinfo.inode->i_lock); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&cinfo.inode->i_lock); + nfs_unlock_request(req); + nfs_mark_request_commit(req, NULL, &cinfo, 0); + desc.pg_error = 0; + defer = true; } nfs_direct_release_pages(pagevec, npages); kvfree(pagevec); From 4d98038e5bd939bd13cc4e602dfe60cd5110efa8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:34:38 -0400 Subject: [PATCH 1644/2093] NFS: Fix O_DIRECT locking issues [ Upstream commit 7c6339322ce0c6128acbe36aacc1eeb986dd7bf1 ] The dreq fields are protected by the dreq->lock. Fixes: 954998b60caa ("NFS: Fix error handling for O_DIRECT write scheduling") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/direct.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index d71762f32b6c..449d248fc1ec 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -555,7 +555,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) /* Bump the transmission count */ req->wb_nio++; if (!nfs_pageio_add_request(&desc, req)) { - spin_lock(&cinfo.inode->i_lock); + spin_lock(&dreq->lock); if (dreq->error < 0) { desc.pg_error = dreq->error; } else if (desc.pg_error != -EAGAIN) { @@ -565,7 +565,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) dreq->error = desc.pg_error; } else dreq->flags = NFS_ODIRECT_RESCHED_WRITES; - spin_unlock(&cinfo.inode->i_lock); + spin_unlock(&dreq->lock); break; } nfs_release_request(req); @@ -875,9 +875,9 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, /* If the error is soft, defer remaining requests */ nfs_init_cinfo_from_dreq(&cinfo, dreq); - spin_lock(&cinfo.inode->i_lock); + spin_lock(&dreq->lock); dreq->flags = NFS_ODIRECT_RESCHED_WRITES; - spin_unlock(&cinfo.inode->i_lock); + spin_unlock(&dreq->lock); nfs_unlock_request(req); nfs_mark_request_commit(req, NULL, &cinfo, 0); desc.pg_error = 0; From 1f49386d67792424028acfe781d466b010f8fa3f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:34:39 -0400 Subject: [PATCH 1645/2093] NFS: More O_DIRECT accounting fixes for error paths [ Upstream commit 8982f7aff39fb526aba4441fff2525fcedd5e1a3 ] If we hit a fatal error when retransmitting, we do need to record the removal of the request from the count of written bytes. Fixes: 031d73ed768a ("NFS: Fix O_DIRECT accounting of number of bytes read/written") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/direct.c | 47 +++++++++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 16 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 449d248fc1ec..d879c3229efd 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -93,12 +93,10 @@ nfs_direct_handle_truncated(struct nfs_direct_req *dreq, dreq->max_count = dreq_len; if (dreq->count > dreq_len) dreq->count = dreq_len; - - if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) - dreq->error = hdr->error; - else /* Clear outstanding error if this is EOF */ - dreq->error = 0; } + + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && !dreq->error) + dreq->error = hdr->error; } static void @@ -120,6 +118,18 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq, dreq->count = dreq_len; } +static void nfs_direct_truncate_request(struct nfs_direct_req *dreq, + struct nfs_page *req) +{ + loff_t offs = req_offset(req); + size_t req_start = (size_t)(offs - dreq->io_start); + + if (req_start < dreq->max_count) + dreq->max_count = req_start; + if (req_start < dreq->count) + dreq->count = req_start; +} + /** * nfs_swap_rw - NFS address space operation for swap I/O * @iocb: target I/O control block @@ -539,10 +549,6 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) nfs_direct_join_group(&reqs, dreq->inode); - dreq->count = 0; - dreq->max_count = 0; - list_for_each_entry(req, &reqs, wb_list) - dreq->max_count += req->wb_bytes; nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo); get_dreq(dreq); @@ -576,10 +582,14 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) req = nfs_list_entry(reqs.next); nfs_list_remove_request(req); nfs_unlock_and_release_request(req); - if (desc.pg_error == -EAGAIN) + if (desc.pg_error == -EAGAIN) { nfs_mark_request_commit(req, NULL, &cinfo, 0); - else + } else { + spin_lock(&dreq->lock); + nfs_direct_truncate_request(dreq, req); + spin_unlock(&dreq->lock); nfs_release_request(req); + } } if (put_dreq(dreq)) @@ -599,8 +609,6 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) if (status < 0) { /* Errors in commit are fatal */ dreq->error = status; - dreq->max_count = 0; - dreq->count = 0; dreq->flags = NFS_ODIRECT_DONE; } else { status = dreq->error; @@ -611,7 +619,12 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) while (!list_empty(&data->pages)) { req = nfs_list_entry(data->pages.next); nfs_list_remove_request(req); - if (status >= 0 && !nfs_write_match_verf(verf, req)) { + if (status < 0) { + spin_lock(&dreq->lock); + nfs_direct_truncate_request(dreq, req); + spin_unlock(&dreq->lock); + nfs_release_request(req); + } else if (!nfs_write_match_verf(verf, req)) { dreq->flags = NFS_ODIRECT_RESCHED_WRITES; /* * Despite the reboot, the write was successful, @@ -619,7 +632,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) */ req->wb_nio = 0; nfs_mark_request_commit(req, NULL, &cinfo, 0); - } else /* Error or match */ + } else nfs_release_request(req); nfs_unlock_and_release_request(req); } @@ -672,6 +685,7 @@ static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) while (!list_empty(&reqs)) { req = nfs_list_entry(reqs.next); nfs_list_remove_request(req); + nfs_direct_truncate_request(dreq, req); nfs_release_request(req); nfs_unlock_and_release_request(req); } @@ -721,7 +735,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) } nfs_direct_count_bytes(dreq, hdr); - if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags)) { + if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags) && + !test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { if (!dreq->flags) dreq->flags = NFS_ODIRECT_DO_COMMIT; flags = dreq->flags; From d4729af1c73cfacb64facda3d196e25940f0e7a5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:34:40 -0400 Subject: [PATCH 1646/2093] NFS: Use the correct commit info in nfs_join_page_group() [ Upstream commit b193a78ddb5ee7dba074d3f28dc050069ba083c0 ] Ensure that nfs_clear_request_commit() updates the correct counters when it removes them from the commit list. Fixes: ed5d588fe47f ("NFS: Try to join page groups before an O_DIRECT retransmission") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/direct.c | 8 +++++--- fs/nfs/write.c | 23 ++++++++++++----------- include/linux/nfs_page.h | 4 +++- 3 files changed, 20 insertions(+), 15 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index d879c3229efd..04ebe9633630 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -500,7 +500,9 @@ static void nfs_direct_add_page_head(struct list_head *list, kref_get(&head->wb_kref); } -static void nfs_direct_join_group(struct list_head *list, struct inode *inode) +static void nfs_direct_join_group(struct list_head *list, + struct nfs_commit_info *cinfo, + struct inode *inode) { struct nfs_page *req, *subreq; @@ -522,7 +524,7 @@ static void nfs_direct_join_group(struct list_head *list, struct inode *inode) nfs_release_request(subreq); } } while ((subreq = subreq->wb_this_page) != req); - nfs_join_page_group(req, inode); + nfs_join_page_group(req, cinfo, inode); } } @@ -547,7 +549,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) nfs_init_cinfo_from_dreq(&cinfo, dreq); nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); - nfs_direct_join_group(&reqs, dreq->inode); + nfs_direct_join_group(&reqs, &cinfo, dreq->inode); nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo); get_dreq(dreq); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f41d24b54fd1..0a8aed0ac994 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -58,7 +58,8 @@ static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; static const struct nfs_commit_completion_ops nfs_commit_completion_ops; static const struct nfs_rw_ops nfs_rw_write_ops; static void nfs_inode_remove_request(struct nfs_page *req); -static void nfs_clear_request_commit(struct nfs_page *req); +static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, + struct nfs_page *req); static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, struct inode *inode); static struct nfs_page * @@ -502,8 +503,8 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, * the (former) group. All subrequests are removed from any write or commit * lists, unlinked from the group and destroyed. */ -void -nfs_join_page_group(struct nfs_page *head, struct inode *inode) +void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo, + struct inode *inode) { struct nfs_page *subreq; struct nfs_page *destroy_list = NULL; @@ -533,7 +534,7 @@ nfs_join_page_group(struct nfs_page *head, struct inode *inode) * Commit list removal accounting is done after locks are dropped */ subreq = head; do { - nfs_clear_request_commit(subreq); + nfs_clear_request_commit(cinfo, subreq); subreq = subreq->wb_this_page; } while (subreq != head); @@ -567,8 +568,10 @@ nfs_lock_and_join_requests(struct page *page) { struct inode *inode = page_file_mapping(page)->host; struct nfs_page *head; + struct nfs_commit_info cinfo; int ret; + nfs_init_cinfo_from_inode(&cinfo, inode); /* * A reference is taken only on the head request which acts as a * reference to the whole page group - the group will not be destroyed @@ -585,7 +588,7 @@ nfs_lock_and_join_requests(struct page *page) return ERR_PTR(ret); } - nfs_join_page_group(head, inode); + nfs_join_page_group(head, &cinfo, inode); return head; } @@ -956,18 +959,16 @@ nfs_clear_page_commit(struct page *page) } /* Called holding the request lock on @req */ -static void -nfs_clear_request_commit(struct nfs_page *req) +static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, + struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { struct nfs_open_context *ctx = nfs_req_openctx(req); struct inode *inode = d_inode(ctx->dentry); - struct nfs_commit_info cinfo; - nfs_init_cinfo_from_inode(&cinfo, inode); mutex_lock(&NFS_I(inode)->commit_mutex); - if (!pnfs_clear_request_commit(req, &cinfo)) { - nfs_request_remove_commit_list(req, &cinfo); + if (!pnfs_clear_request_commit(req, cinfo)) { + nfs_request_remove_commit_list(req, cinfo); } mutex_unlock(&NFS_I(inode)->commit_mutex); nfs_clear_page_commit(req->wb_page); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index ba7e2e4b0926..e39a8cf8b179 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -145,7 +145,9 @@ extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); extern struct nfs_page *nfs_page_group_lock_head(struct nfs_page *req); extern int nfs_page_group_lock_subrequests(struct nfs_page *head); -extern void nfs_join_page_group(struct nfs_page *head, struct inode *inode); +extern void nfs_join_page_group(struct nfs_page *head, + struct nfs_commit_info *cinfo, + struct inode *inode); extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); From edd1f06145101dab83497806bb6162641255ef50 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:34:41 -0400 Subject: [PATCH 1647/2093] NFS: More fixes for nfs_direct_write_reschedule_io() [ Upstream commit b11243f720ee5f9376861099019c8542969b6318 ] Ensure that all requests are put back onto the commit list so that they can be rescheduled. Fixes: 4daaeba93822 ("NFS: Fix nfs_direct_write_reschedule_io()") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/direct.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 04ebe9633630..5a976fa343df 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -782,18 +782,23 @@ static void nfs_write_sync_pgio_error(struct list_head *head, int error) static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; + struct nfs_page *req; + struct nfs_commit_info cinfo; trace_nfs_direct_write_reschedule_io(dreq); + nfs_init_cinfo_from_dreq(&cinfo, dreq); spin_lock(&dreq->lock); - if (dreq->error == 0) { + if (dreq->error == 0) dreq->flags = NFS_ODIRECT_RESCHED_WRITES; - /* fake unstable write to let common nfs resend pages */ - hdr->verf.committed = NFS_UNSTABLE; - hdr->good_bytes = hdr->args.offset + hdr->args.count - - hdr->io_start; - } + set_bit(NFS_IOHDR_REDO, &hdr->flags); spin_unlock(&dreq->lock); + while (!list_empty(&hdr->pages)) { + req = nfs_list_entry(hdr->pages.next); + nfs_list_remove_request(req); + nfs_unlock_request(req); + nfs_mark_request_commit(req, NULL, &cinfo, 0); + } } static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { From 13acbca81eeeb6c205117f602400bbf77bf5948b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:43:58 -0400 Subject: [PATCH 1648/2093] NFS/pNFS: Report EINVAL errors from connect() to the server [ Upstream commit dd7d7ee3ba2a70d12d02defb478790cf57d5b87b ] With IPv6, connect() can occasionally return EINVAL if a route is unavailable. If this happens during I/O to a data server, we want to report it using LAYOUTERROR as an inability to connect. Fixes: dd52128afdde ("NFSv4.1/pnfs Ensure flexfiles reports all connection related errors") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/flexfilelayout/flexfilelayout.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 1ec79ccf89ad..5c69a6e9ab3e 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1235,6 +1235,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -EPFNOSUPPORT: case -EPROTONOSUPPORT: case -EOPNOTSUPP: + case -EINVAL: case -ECONNREFUSED: case -ECONNRESET: case -EHOSTDOWN: From 839e07de9a0a5de098283e53d243e14a1f4bc92c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Sep 2023 12:50:09 -0400 Subject: [PATCH 1649/2093] SUNRPC: Mark the cred for revalidation if the server rejects it [ Upstream commit 611fa42dfa9d2f3918ac5f4dd5705dfad81b323d ] If the server rejects the credential as being stale, or bad, then we should mark it for revalidation before retransmitting. Fixes: 7f5667a5f8c4 ("SUNRPC: Clean up rpc_verify_header()") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- net/sunrpc/clnt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b0258507b236..ff6728e41e04 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2736,6 +2736,7 @@ rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr) case rpc_autherr_rejectedverf: case rpcsec_gsserr_credproblem: case rpcsec_gsserr_ctxproblem: + rpcauth_invalcred(task); if (!task->tk_cred_retry) break; task->tk_cred_retry--; From f86a2c2ea085b659d806292dcb753685fd517526 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Thu, 13 Jul 2023 13:02:38 -0400 Subject: [PATCH 1650/2093] NFSv4.1: use EXCHGID4_FLAG_USE_PNFS_DS for DS server [ Upstream commit 51d674a5e4889f1c8e223ac131cf218e1631e423 ] After receiving the location(s) of the DS server(s) in the GETDEVINCEINFO, create the request for the clientid to such server and indicate that the client is connecting to a DS. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker Stable-dep-of: 806a3bc421a1 ("NFSv4.1: fix pnfs MDS=DS session trunking") Signed-off-by: Sasha Levin --- fs/nfs/nfs4client.c | 3 +++ fs/nfs/nfs4proc.c | 4 ++++ 2 files changed, 7 insertions(+) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d3051b051a56..d3e2b0867dc1 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -231,6 +231,8 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + if (test_bit(NFS_CS_DS, &cl_init->init_flags)) + __set_bit(NFS_CS_DS, &clp->cl_flags); /* * Set up the connection to the server before we add add to the * global list. @@ -993,6 +995,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, if (mds_srv->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + __set_bit(NFS_CS_DS, &cl_init.init_flags); /* * Set an authflavor equual to the MDS value. Use the MDS nfs_client * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2dec0fed1ba1..acb1346da13e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8794,6 +8794,8 @@ nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred, #ifdef CONFIG_NFS_V4_1_MIGRATION calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR; #endif + if (test_bit(NFS_CS_DS, &clp->cl_flags)) + calldata->args.flags |= EXCHGID4_FLAG_USE_PNFS_DS; msg.rpc_argp = &calldata->args; msg.rpc_resp = &calldata->res; task_setup_data.callback_data = calldata; @@ -8871,6 +8873,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre /* Save the EXCHANGE_ID verifier session trunk tests */ memcpy(clp->cl_confirm.data, argp->verifier.data, sizeof(clp->cl_confirm.data)); + if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS) + set_bit(NFS_CS_DS, &clp->cl_flags); out: trace_nfs4_exchange_id(clp, status); rpc_put_task(task); From a997d583571bc4431ee3b10b54759251aa23d668 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 30 Aug 2023 15:29:34 -0400 Subject: [PATCH 1651/2093] NFSv4.1: fix pnfs MDS=DS session trunking [ Upstream commit 806a3bc421a115fbb287c1efce63a48c54ee804b ] Currently, when GETDEVICEINFO returns multiple locations where each is a different IP but the server's identity is same as MDS, then nfs4_set_ds_client() finds the existing nfs_client structure which has the MDS's max_connect value (and if it's 1), then the 1st IP on the DS's list will get dropped due to MDS trunking rules. Other IPs would be added as they fall under the pnfs trunking rules. For the list of IPs the 1st goes thru calling nfs4_set_ds_client() which will eventually call nfs4_add_trunk() and call into rpc_clnt_test_and_add_xprt() which has the check for MDS trunking. The other IPs (after the 1st one), would call rpc_clnt_add_xprt() which doesn't go thru that check. nfs4_add_trunk() is called when MDS trunking is happening and it needs to enforce the usage of max_connect mount option of the 1st mount. However, this shouldn't be applied to pnfs flow. Instead, this patch proposed to treat MDS=DS as DS trunking and make sure that MDS's max_connect limit does not apply to the 1st IP returned in the GETDEVICEINFO list. It does so by marking the newly created client with a new flag NFS_CS_PNFS which then used to pass max_connect value to use into the rpc_clnt_test_and_add_xprt() instead of the existing rpc client's max_connect value set by the MDS connection. For example, mount was done without max_connect value set so MDS's rpc client has cl_max_connect=1. Upon calling into rpc_clnt_test_and_add_xprt() and using rpc client's value, the caller passes in max_connect value which is previously been set in the pnfs path (as a part of handling GETDEVICEINFO list of IPs) in nfs4_set_ds_client(). However, when NFS_CS_PNFS flag is not set and we know we are doing MDS trunking, comparing a new IP of the same server, we then set the max_connect value to the existing MDS's value and pass that into rpc_clnt_test_and_add_xprt(). Fixes: dc48e0abee24 ("SUNRPC enforce creation of no more than max_connect xprts") Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4client.c | 6 +++++- include/linux/nfs_fs_sb.h | 1 + net/sunrpc/clnt.c | 11 +++++++---- 3 files changed, 13 insertions(+), 5 deletions(-) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d3e2b0867dc1..84b345efcec0 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -416,6 +416,8 @@ static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old) .net = old->cl_net, .servername = old->cl_hostname, }; + int max_connect = test_bit(NFS_CS_PNFS, &clp->cl_flags) ? + clp->cl_max_connect : old->cl_max_connect; if (clp->cl_proto != old->cl_proto) return; @@ -429,7 +431,7 @@ static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old) xprt_args.addrlen = clp_salen; rpc_clnt_add_xprt(old->cl_rpcclient, &xprt_args, - rpc_clnt_test_and_add_xprt, NULL); + rpc_clnt_test_and_add_xprt, &max_connect); } /** @@ -996,6 +998,8 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); __set_bit(NFS_CS_DS, &cl_init.init_flags); + __set_bit(NFS_CS_PNFS, &cl_init.init_flags); + cl_init.max_connect = NFS_MAX_TRANSPORTS; /* * Set an authflavor equual to the MDS value. Use the MDS nfs_client * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ea2f7e6b1b0b..ef8ba5fbc650 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -48,6 +48,7 @@ struct nfs_client { #define NFS_CS_NOPING 6 /* - don't ping on connect */ #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ +#define NFS_CS_PNFS 9 /* - Server used for pnfs */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index ff6728e41e04..b3f6f67ed252 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2890,19 +2890,22 @@ static const struct rpc_call_ops rpc_cb_add_xprt_call_ops = { * @clnt: pointer to struct rpc_clnt * @xps: pointer to struct rpc_xprt_switch, * @xprt: pointer struct rpc_xprt - * @dummy: unused + * @in_max_connect: pointer to the max_connect value for the passed in xprt transport */ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, - void *dummy) + void *in_max_connect) { struct rpc_cb_add_xprt_calldata *data; struct rpc_task *task; + int max_connect = clnt->cl_max_connect; - if (xps->xps_nunique_destaddr_xprts + 1 > clnt->cl_max_connect) { + if (in_max_connect) + max_connect = *(int *)in_max_connect; + if (xps->xps_nunique_destaddr_xprts + 1 > max_connect) { rcu_read_lock(); pr_warn("SUNRPC: reached max allowed number (%d) did not add " - "transport to server: %s\n", clnt->cl_max_connect, + "transport to server: %s\n", max_connect, rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); rcu_read_unlock(); return -EINVAL; From ae68541d528532fe5e6ebddba697f1e96f00f846 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 18 Aug 2023 12:51:49 +0300 Subject: [PATCH 1652/2093] media: v4l: Use correct dependency for camera sensor drivers [ Upstream commit 86e16b87afac20779da1228d690a95c54d7e2ad0 ] The Kconfig option that enables compiling camera sensor drivers is VIDEO_CAMERA_SENSOR rather than MEDIA_CAMERA_SUPPORT as it was previously. Fix this. Also select VIDEO_OV7670 for marvell platform drivers only if MEDIA_SUBDRV_AUTOSELECT and VIDEO_CAMERA_SENSOR are enabled. Reported-by: Randy Dunlap Fixes: 7d3c7d2a2914 ("media: i2c: Add a camera sensor top level menu") Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/marvell/Kconfig | 4 ++-- drivers/media/usb/em28xx/Kconfig | 4 ++-- drivers/media/usb/go7007/Kconfig | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/media/platform/marvell/Kconfig b/drivers/media/platform/marvell/Kconfig index ec1a16734a28..d6499ffe30e8 100644 --- a/drivers/media/platform/marvell/Kconfig +++ b/drivers/media/platform/marvell/Kconfig @@ -7,7 +7,7 @@ config VIDEO_CAFE_CCIC depends on V4L_PLATFORM_DRIVERS depends on PCI && I2C && VIDEO_DEV depends on COMMON_CLK - select VIDEO_OV7670 + select VIDEO_OV7670 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR select VIDEOBUF2_VMALLOC select VIDEOBUF2_DMA_CONTIG select VIDEOBUF2_DMA_SG @@ -22,7 +22,7 @@ config VIDEO_MMP_CAMERA depends on I2C && VIDEO_DEV depends on ARCH_MMP || COMPILE_TEST depends on COMMON_CLK - select VIDEO_OV7670 + select VIDEO_OV7670 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR select I2C_GPIO select VIDEOBUF2_VMALLOC select VIDEOBUF2_DMA_CONTIG diff --git a/drivers/media/usb/em28xx/Kconfig b/drivers/media/usb/em28xx/Kconfig index b3c472b8c5a9..cb61fd6cc6c6 100644 --- a/drivers/media/usb/em28xx/Kconfig +++ b/drivers/media/usb/em28xx/Kconfig @@ -12,8 +12,8 @@ config VIDEO_EM28XX_V4L2 select VIDEO_SAA711X if MEDIA_SUBDRV_AUTOSELECT select VIDEO_TVP5150 if MEDIA_SUBDRV_AUTOSELECT select VIDEO_MSP3400 if MEDIA_SUBDRV_AUTOSELECT - select VIDEO_MT9V011 if MEDIA_SUBDRV_AUTOSELECT && MEDIA_CAMERA_SUPPORT - select VIDEO_OV2640 if MEDIA_SUBDRV_AUTOSELECT && MEDIA_CAMERA_SUPPORT + select VIDEO_MT9V011 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR + select VIDEO_OV2640 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR help This is a video4linux driver for Empia 28xx based TV cards. diff --git a/drivers/media/usb/go7007/Kconfig b/drivers/media/usb/go7007/Kconfig index 4ff79940ad8d..b2a15d9fb1f3 100644 --- a/drivers/media/usb/go7007/Kconfig +++ b/drivers/media/usb/go7007/Kconfig @@ -12,8 +12,8 @@ config VIDEO_GO7007 select VIDEO_TW2804 if MEDIA_SUBDRV_AUTOSELECT select VIDEO_TW9903 if MEDIA_SUBDRV_AUTOSELECT select VIDEO_TW9906 if MEDIA_SUBDRV_AUTOSELECT - select VIDEO_OV7640 if MEDIA_SUBDRV_AUTOSELECT && MEDIA_CAMERA_SUPPORT select VIDEO_UDA1342 if MEDIA_SUBDRV_AUTOSELECT + select VIDEO_OV7640 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR help This is a video4linux driver for the WIS GO7007 MPEG encoder chip. From 2d9757480b436505a8ffc42cf9241ee88400dc55 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 22 Aug 2023 11:10:34 +0300 Subject: [PATCH 1653/2093] media: via: Use correct dependency for camera sensor drivers [ Upstream commit 41425941dfcf47cc6df8e500af6ff16a7be6539f ] The via camera controller driver selected ov7670 driver, however now that driver has dependencies and may no longer be selected unconditionally. Reported-by: Randy Dunlap Fixes: 7d3c7d2a2914 ("media: i2c: Add a camera sensor top level menu") Signed-off-by: Sakari Ailus Acked-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/via/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/via/Kconfig b/drivers/media/platform/via/Kconfig index 8926eb0803b2..6e603c038248 100644 --- a/drivers/media/platform/via/Kconfig +++ b/drivers/media/platform/via/Kconfig @@ -7,7 +7,7 @@ config VIDEO_VIA_CAMERA depends on V4L_PLATFORM_DRIVERS depends on FB_VIA && VIDEO_DEV select VIDEOBUF2_DMA_SG - select VIDEO_OV7670 + select VIDEO_OV7670 if VIDEO_CAMERA_SENSOR help Driver support for the integrated camera controller in VIA Chrome9 chipsets. Currently only tested on OLPC xo-1.5 systems From df9950d37df113db59495fa09d060754366a2b7c Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 18 Sep 2023 14:17:11 +0100 Subject: [PATCH 1654/2093] netfs: Only call folio_start_fscache() one time for each folio [ Upstream commit df1c357f25d808e30b216188330e708e09e1a412 ] If a network filesystem using netfs implements a clamp_length() function, it can set subrequest lengths smaller than a page size. When we loop through the folios in netfs_rreq_unlock_folios() to set any folios to be written back, we need to make sure we only call folio_start_fscache() once for each folio. Otherwise, this simple testcase: mount -o fsc,rsize=1024,wsize=1024 127.0.0.1:/export /mnt/nfs dd if=/dev/zero of=/mnt/nfs/file.bin bs=4096 count=1 1+0 records in 1+0 records out 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.0126359 s, 324 kB/s echo 3 > /proc/sys/vm/drop_caches cat /mnt/nfs/file.bin > /dev/null will trigger an oops similar to the following: page dumped because: VM_BUG_ON_FOLIO(folio_test_private_2(folio)) ------------[ cut here ]------------ kernel BUG at include/linux/netfs.h:44! ... CPU: 5 PID: 134 Comm: kworker/u16:5 Kdump: loaded Not tainted 6.4.0-rc5 ... RIP: 0010:netfs_rreq_unlock_folios+0x68e/0x730 [netfs] ... Call Trace: netfs_rreq_assess+0x497/0x660 [netfs] netfs_subreq_terminated+0x32b/0x610 [netfs] nfs_netfs_read_completion+0x14e/0x1a0 [nfs] nfs_read_completion+0x2f9/0x330 [nfs] rpc_free_task+0x72/0xa0 [sunrpc] rpc_async_release+0x46/0x70 [sunrpc] process_one_work+0x3bd/0x710 worker_thread+0x89/0x610 kthread+0x181/0x1c0 ret_from_fork+0x29/0x50 Fixes: 3d3c95046742 ("netfs: Provide readahead and readpage netfs helpers" Link: https://bugzilla.redhat.com/show_bug.cgi?id=2210612 Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Signed-off-by: David Howells Link: https://lore.kernel.org/r/20230608214137.856006-1-dwysocha@redhat.com/ # v1 Link: https://lore.kernel.org/r/20230915185704.1082982-1-dwysocha@redhat.com/ # v2 Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/netfs/buffered_read.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7679a68e8193..caa0a053e8a9 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -47,12 +47,14 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) xas_for_each(&xas, folio, last_page) { loff_t pg_end; bool pg_failed = false; + bool folio_started; if (xas_retry(&xas, folio)) continue; pg_end = folio_pos(folio) + folio_size(folio) - 1; + folio_started = false; for (;;) { loff_t sreq_end; @@ -60,8 +62,10 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { folio_start_fscache(folio); + folio_started = true; + } pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) From dbf1a719850577bb51fc7512a3972994b797a17b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 9 Aug 2023 12:44:20 +0200 Subject: [PATCH 1655/2093] dm: fix a race condition in retrieve_deps [ Upstream commit f6007dce0cd35d634d9be91ef3515a6385dcee16 ] There's a race condition in the multipath target when retrieve_deps races with multipath_message calling dm_get_device and dm_put_device. retrieve_deps walks the list of open devices without holding any lock but multipath may add or remove devices to the list while it is running. The end result may be memory corruption or use-after-free memory access. See this description of a UAF with multipath_message(): https://listman.redhat.com/archives/dm-devel/2022-October/052373.html Fix this bug by introducing a new rw semaphore "devices_lock". We grab devices_lock for read in retrieve_deps and we grab it for write in dm_get_device and dm_put_device. Reported-by: Luo Meng Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org Tested-by: Li Lingfeng Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-core.h | 1 + drivers/md/dm-ioctl.c | 7 ++++++- drivers/md/dm-table.c | 32 ++++++++++++++++++++++++-------- 3 files changed, 31 insertions(+), 9 deletions(-) diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 28c641352de9..71dcd8fd4050 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -214,6 +214,7 @@ struct dm_table { /* a list of devices used by this table */ struct list_head devices; + struct rw_semaphore devices_lock; /* events get handed up using this callback */ void (*event_fn)(void *); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 2afd2d2a0f40..206e6ce554dc 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1566,6 +1566,8 @@ static void retrieve_deps(struct dm_table *table, struct dm_dev_internal *dd; struct dm_target_deps *deps; + down_read(&table->devices_lock); + deps = get_result_buffer(param, param_size, &len); /* @@ -1580,7 +1582,7 @@ static void retrieve_deps(struct dm_table *table, needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; - return; + goto out; } /* @@ -1592,6 +1594,9 @@ static void retrieve_deps(struct dm_table *table, deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev); param->data_size = param->data_start + needed; + +out: + up_read(&table->devices_lock); } static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 288f600ee56d..dac6a5f25f2b 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -134,6 +134,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); + init_rwsem(&t->devices_lock); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -362,15 +363,19 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, return -ENODEV; } + down_write(&t->devices_lock); + dd = find_device(&t->devices, dev); if (!dd) { dd = kmalloc(sizeof(*dd), GFP_KERNEL); - if (!dd) - return -ENOMEM; + if (!dd) { + r = -ENOMEM; + goto unlock_ret_r; + } if ((r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev))) { kfree(dd); - return r; + goto unlock_ret_r; } refcount_set(&dd->count, 1); @@ -380,12 +385,17 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { r = upgrade_mode(dd, mode, t->md); if (r) - return r; + goto unlock_ret_r; } refcount_inc(&dd->count); out: + up_write(&t->devices_lock); *result = dd->dm_dev; return 0; + +unlock_ret_r: + up_write(&t->devices_lock); + return r; } EXPORT_SYMBOL(dm_get_device); @@ -421,9 +431,12 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, void dm_put_device(struct dm_target *ti, struct dm_dev *d) { int found = 0; - struct list_head *devices = &ti->table->devices; + struct dm_table *t = ti->table; + struct list_head *devices = &t->devices; struct dm_dev_internal *dd; + down_write(&t->devices_lock); + list_for_each_entry(dd, devices, list) { if (dd->dm_dev == d) { found = 1; @@ -432,14 +445,17 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } if (!found) { DMERR("%s: device %s not in table devices list", - dm_device_name(ti->table->md), d->name); - return; + dm_device_name(t->md), d->name); + goto unlock_ret; } if (refcount_dec_and_test(&dd->count)) { - dm_put_table_device(ti->table->md, d); + dm_put_table_device(t->md, d); list_del(&dd->list); kfree(dd); } + +unlock_ret: + up_write(&t->devices_lock); } EXPORT_SYMBOL(dm_put_device); From 0d1a761dec2259c0ed159ea6a19d3103aa80e0e1 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 28 Aug 2023 09:06:42 +0100 Subject: [PATCH 1656/2093] btrfs: improve error message after failure to add delayed dir index item [ Upstream commit 91bfe3104b8db0310f76f2dcb6aacef24c889366 ] If we fail to add a delayed dir index item because there's already another item with the same index number, we print an error message (and then BUG). However that message isn't very helpful to debug anything because we don't know what's the index number and what are the values of index counters in the inode and its delayed inode (index_cnt fields of struct btrfs_inode and struct btrfs_delayed_node). So update the error message to include the index number and counters. We actually had a recent case where this issue was hit by a syzbot report (see the link below). Link: https://lore.kernel.org/linux-btrfs/00000000000036e1290603e097e0@google.com/ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 2c58c3931ede ("btrfs: remove BUG() after failure to insert delayed dir index item") Signed-off-by: Sasha Levin --- fs/btrfs/delayed-inode.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index d2cbb7733c7d..34e843460e4d 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1506,9 +1506,10 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, ret = __btrfs_add_delayed_item(delayed_node, delayed_item); if (unlikely(ret)) { btrfs_err(trans->fs_info, - "err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)", - name_len, name, delayed_node->root->root_key.objectid, - delayed_node->inode_id, ret); +"error adding delayed dir index item, name: %.*s, index: %llu, root: %llu, dir: %llu, dir->index_cnt: %llu, delayed_node->index_cnt: %llu, error: %d", + name_len, name, index, btrfs_root_id(delayed_node->root), + delayed_node->inode_id, dir->index_cnt, + delayed_node->index_cnt, ret); BUG(); } mutex_unlock(&delayed_node->mutex); From 39c4a9522db0072570d602e9b365119e17fb9f4f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 28 Aug 2023 09:06:43 +0100 Subject: [PATCH 1657/2093] btrfs: remove BUG() after failure to insert delayed dir index item [ Upstream commit 2c58c3931ede7cd08cbecf1f1a4acaf0a04a41a9 ] Instead of calling BUG() when we fail to insert a delayed dir index item into the delayed node's tree, we can just release all the resources we have allocated/acquired before and return the error to the caller. This is fine because all existing call chains undo anything they have done before calling btrfs_insert_delayed_dir_index() or BUG_ON (when creating pending snapshots in the transaction commit path). So remove the BUG() call and do proper error handling. This relates to a syzbot report linked below, but does not fix it because it only prevents hitting a BUG(), it does not fix the issue where somehow we attempt to use twice the same index number for different index items. Link: https://lore.kernel.org/linux-btrfs/00000000000036e1290603e097e0@google.com/ CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/delayed-inode.c | 74 +++++++++++++++++++++++++--------------- 1 file changed, 47 insertions(+), 27 deletions(-) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 34e843460e4d..9dacf72a75d0 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1421,7 +1421,29 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info) btrfs_wq_run_delayed_node(delayed_root, fs_info, BTRFS_DELAYED_BATCH); } -/* Will return 0 or -ENOMEM */ +static void btrfs_release_dir_index_item_space(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + const u64 bytes = btrfs_calc_insert_metadata_size(fs_info, 1); + + if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) + return; + + /* + * Adding the new dir index item does not require touching another + * leaf, so we can release 1 unit of metadata that was previously + * reserved when starting the transaction. This applies only to + * the case where we had a transaction start and excludes the + * transaction join case (when replaying log trees). + */ + trace_btrfs_space_reservation(fs_info, "transaction", + trans->transid, bytes, 0); + btrfs_block_rsv_release(fs_info, trans->block_rsv, bytes, NULL); + ASSERT(trans->bytes_reserved >= bytes); + trans->bytes_reserved -= bytes; +} + +/* Will return 0, -ENOMEM or -EEXIST (index number collision, unexpected). */ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, const char *name, int name_len, struct btrfs_inode *dir, @@ -1463,6 +1485,27 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, mutex_lock(&delayed_node->mutex); + /* + * First attempt to insert the delayed item. This is to make the error + * handling path simpler in case we fail (-EEXIST). There's no risk of + * any other task coming in and running the delayed item before we do + * the metadata space reservation below, because we are holding the + * delayed node's mutex and that mutex must also be locked before the + * node's delayed items can be run. + */ + ret = __btrfs_add_delayed_item(delayed_node, delayed_item); + if (unlikely(ret)) { + btrfs_err(trans->fs_info, +"error adding delayed dir index item, name: %.*s, index: %llu, root: %llu, dir: %llu, dir->index_cnt: %llu, delayed_node->index_cnt: %llu, error: %d", + name_len, name, index, btrfs_root_id(delayed_node->root), + delayed_node->inode_id, dir->index_cnt, + delayed_node->index_cnt, ret); + btrfs_release_delayed_item(delayed_item); + btrfs_release_dir_index_item_space(trans); + mutex_unlock(&delayed_node->mutex); + goto release_node; + } + if (delayed_node->index_item_leaves == 0 || delayed_node->curr_index_batch_size + data_len > leaf_data_size) { delayed_node->curr_index_batch_size = data_len; @@ -1480,37 +1523,14 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, * impossible. */ if (WARN_ON(ret)) { - mutex_unlock(&delayed_node->mutex); btrfs_release_delayed_item(delayed_item); + mutex_unlock(&delayed_node->mutex); goto release_node; } delayed_node->index_item_leaves++; - } else if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) { - const u64 bytes = btrfs_calc_insert_metadata_size(fs_info, 1); - - /* - * Adding the new dir index item does not require touching another - * leaf, so we can release 1 unit of metadata that was previously - * reserved when starting the transaction. This applies only to - * the case where we had a transaction start and excludes the - * transaction join case (when replaying log trees). - */ - trace_btrfs_space_reservation(fs_info, "transaction", - trans->transid, bytes, 0); - btrfs_block_rsv_release(fs_info, trans->block_rsv, bytes, NULL); - ASSERT(trans->bytes_reserved >= bytes); - trans->bytes_reserved -= bytes; - } - - ret = __btrfs_add_delayed_item(delayed_node, delayed_item); - if (unlikely(ret)) { - btrfs_err(trans->fs_info, -"error adding delayed dir index item, name: %.*s, index: %llu, root: %llu, dir: %llu, dir->index_cnt: %llu, delayed_node->index_cnt: %llu, error: %d", - name_len, name, index, btrfs_root_id(delayed_node->root), - delayed_node->inode_id, dir->index_cnt, - delayed_node->index_cnt, ret); - BUG(); + } else { + btrfs_release_dir_index_item_space(trans); } mutex_unlock(&delayed_node->mutex); From 1e3c25df7d403a5980262840821ed256f112c804 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 1 Aug 2023 22:32:00 +0800 Subject: [PATCH 1658/2093] ext4: replace the traditional ternary conditional operator with with max()/min() [ Upstream commit de8bf0e5ee7482585450357c6d4eddec8efc5cb7 ] Replace the traditional ternary conditional operator with with max()/min() Signed-off-by: Kemeng Shi Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20230801143204.2284343-7-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Stable-dep-of: 45e4ab320c9b ("ext4: move setting of trimmed bit into ext4_try_to_trim_range()") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 016925b1a090..a2c5024943d8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -6430,8 +6430,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) void *bitmap; bitmap = e4b->bd_bitmap; - start = (e4b->bd_info->bb_first_free > start) ? - e4b->bd_info->bb_first_free : start; + start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -6648,8 +6647,7 @@ ext4_mballoc_query_range( ext4_lock_group(sb, group); - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; + start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; From b4d5db1c77facf76e9685a921e75caa459b9aaad Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 13 Sep 2023 17:04:54 +0200 Subject: [PATCH 1659/2093] ext4: move setting of trimmed bit into ext4_try_to_trim_range() [ Upstream commit 45e4ab320c9b5fa67b1fc3b6a9b381cfcc0c8488 ] Currently we set the group's trimmed bit in ext4_trim_all_free() based on return value of ext4_try_to_trim_range(). However when we will want to abort trimming because of suspend attempt, we want to return success from ext4_try_to_trim_range() but not set the trimmed bit. Instead implementing awkward propagation of this information, just move setting of trimmed bit into ext4_try_to_trim_range() when the whole group is trimmed. Cc: stable@kernel.org Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230913150504.9054-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 46 +++++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a2c5024943d8..41f0385f85d3 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -6420,6 +6420,16 @@ __acquires(bitlock) return ret; } +static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, + ext4_group_t grp) +{ + if (grp < ext4_get_groups_count(sb)) + return EXT4_CLUSTERS_PER_GROUP(sb) - 1; + return (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp) - 1) >> + EXT4_CLUSTER_BITS(sb); +} + static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) @@ -6427,9 +6437,12 @@ __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { ext4_grpblk_t next, count, free_count; + bool set_trimmed = false; void *bitmap; bitmap = e4b->bd_bitmap; + if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + set_trimmed = true; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -6444,16 +6457,14 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) int ret = ext4_trim_extent(sb, start, next - start, e4b); if (ret && ret != -EOPNOTSUPP) - break; + return count; count += next - start; } free_count += next - start; start = next + 1; - if (fatal_signal_pending(current)) { - count = -ERESTARTSYS; - break; - } + if (fatal_signal_pending(current)) + return -ERESTARTSYS; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); @@ -6465,6 +6476,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) break; } + if (set_trimmed) + EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); + return count; } @@ -6475,7 +6489,6 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count - * @set_trimmed: set the trimmed flag if at least one block is trimmed * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy @@ -6485,7 +6498,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks, bool set_trimmed) + ext4_grpblk_t minblocks) { struct ext4_buddy e4b; int ret; @@ -6502,13 +6515,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || - minblocks < EXT4_SB(sb)->s_last_trim_minblks) { + minblocks < EXT4_SB(sb)->s_last_trim_minblks) ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0 && set_trimmed) - EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); - } else { + else ret = 0; - } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -6541,7 +6551,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); - bool whole_group, eof = false; int ret = 0; start = range->start >> sb->s_blocksize_bits; @@ -6560,10 +6569,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks - 1) { + if (end >= max_blks - 1) end = max_blks - 1; - eof = true; - } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -6577,7 +6584,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; - whole_group = true; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); @@ -6596,13 +6602,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ - if (group == last_group) { + if (group == last_group) end = last_cluster; - whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1; - } if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen, whole_group); + end, minlen); if (cnt < 0) { ret = cnt; break; From 6bb88a0344c02c004f0ba653be04aaab921bc213 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 13 Sep 2023 17:04:55 +0200 Subject: [PATCH 1660/2093] ext4: do not let fstrim block system suspend [ Upstream commit 5229a658f6453362fbb9da6bf96872ef25a7097e ] Len Brown has reported that system suspend sometimes fail due to inability to freeze a task working in ext4_trim_fs() for one minute. Trimming a large filesystem on a disk that slowly processes discard requests can indeed take a long time. Since discard is just an advisory call, it is perfectly fine to interrupt it at any time and the return number of discarded blocks until that moment. Do that when we detect the task is being frozen. Cc: stable@kernel.org Reported-by: Len Brown Suggested-by: Dave Chinner References: https://bugzilla.kernel.org/show_bug.cgi?id=216322 Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230913150504.9054-2-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 41f0385f85d3..3c8300e08f41 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -16,6 +16,7 @@ #include #include #include +#include #include /* @@ -6430,6 +6431,11 @@ static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, EXT4_CLUSTER_BITS(sb); } +static bool ext4_trim_interrupted(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) @@ -6463,8 +6469,8 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) free_count += next - start; start = next + 1; - if (fatal_signal_pending(current)) - return -ERESTARTSYS; + if (ext4_trim_interrupted()) + return count; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); @@ -6586,6 +6592,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { + if (ext4_trim_interrupted()) + break; grp = ext4_get_group_info(sb, group); if (!grp) continue; From 59dab3bf0b8fc08eb802721c0532f13dd89209b8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 22 Sep 2023 18:30:13 +0200 Subject: [PATCH 1661/2093] netfilter: nf_tables: don't skip expired elements during walk commit 24138933b97b055d486e8064b4a1721702442a9b upstream. There is an asymmetry between commit/abort and preparation phase if the following conditions are met: 1. set is a verdict map ("1.2.3.4 : jump foo") 2. timeouts are enabled In this case, following sequence is problematic: 1. element E in set S refers to chain C 2. userspace requests removal of set S 3. kernel does a set walk to decrement chain->use count for all elements from preparation phase 4. kernel does another set walk to remove elements from the commit phase (or another walk to do a chain->use increment for all elements from abort phase) If E has already expired in 1), it will be ignored during list walk, so its use count won't have been changed. Then, when set is culled, ->destroy callback will zap the element via nf_tables_set_elem_destroy(), but this function is only safe for elements that have been deactivated earlier from the preparation phase: lack of earlier deactivate removes the element but leaks the chain use count, which results in a WARN splat when the chain gets removed later, plus a leak of the nft_chain structure. Update pipapo_get() not to skip expired elements, otherwise flush command reports bogus ENOENT errors. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support") Fixes: 9d0982927e79 ("netfilter: nft_hash: add support for timeouts") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 4 ++++ net/netfilter/nft_set_hash.c | 2 -- net/netfilter/nft_set_pipapo.c | 18 ++++++++++++------ net/netfilter/nft_set_rbtree.c | 2 -- 4 files changed, 16 insertions(+), 10 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3c5cac9bd9b7..475c556f4991 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5386,8 +5386,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); struct nft_set_dump_args *args; + if (nft_set_elem_expired(ext)) + return 0; + args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem); } diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 0b73cb0e752f..24caa31fa231 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -278,8 +278,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&he->ext)) - goto cont; if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 8c16681884b7..b6a994ba72f3 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -566,8 +566,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext) || - (genmask && + if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; @@ -601,8 +600,17 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + struct nft_pipapo_elem *ret; + + ret = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(ret)) + return ret; + + if (nft_set_elem_expired(&ret->ext)) + return ERR_PTR(-ENOENT); + + return ret; } /** @@ -2024,8 +2032,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, goto cont; e = f->mt[r].e; - if (nft_set_elem_expired(&e->ext)) - goto cont; elem.priv = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 8d73fffd2d09..39956e5341c9 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -552,8 +552,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&rbe->ext)) - goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; From ea3eb9f2192e4fc33b795673e56c97a21987f868 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:14 +0200 Subject: [PATCH 1662/2093] netfilter: nf_tables: GC transaction API to avoid race with control plane commit 5f68718b34a531a556f2f50300ead2862278da26 upstream. The set types rhashtable and rbtree use a GC worker to reclaim memory. From system work queue, in periodic intervals, a scan of the table is done. The major caveat here is that the nft transaction mutex is not held. This causes a race between control plane and GC when they attempt to delete the same element. We cannot grab the netlink mutex from the work queue, because the control plane has to wait for the GC work queue in case the set is to be removed, so we get following deadlock: cpu 1 cpu2 GC work transaction comes in , lock nft mutex `acquire nft mutex // BLOCKS transaction asks to remove the set set destruction calls cancel_work_sync() cancel_work_sync will now block forever, because it is waiting for the mutex the caller already owns. This patch adds a new API that deals with garbage collection in two steps: 1) Lockless GC of expired elements sets on the NFT_SET_ELEM_DEAD_BIT so they are not visible via lookup. Annotate current GC sequence in the GC transaction. Enqueue GC transaction work as soon as it is full. If ruleset is updated, then GC transaction is aborted and retried later. 2) GC work grabs the mutex. If GC sequence has changed then this GC transaction lost race with control plane, abort it as it contains stale references to objects and let GC try again later. If the ruleset is intact, then this GC transaction deactivates and removes the elements and it uses call_rcu() to destroy elements. Note that no elements are removed from GC lockless path, the _DEAD bit is set and pointers are collected. GC catchall does not remove the elements anymore too. There is a new set->dead flag that is set on to abort the GC transaction to deal with set->ops->destroy() path which removes the remaining elements in the set from commit_release, where no mutex is held. To deal with GC when mutex is held, which allows safe deactivate and removal, add sync GC API which releases the set element object via call_rcu(). This is used by rbtree and pipapo backends which also perform garbage collection from control plane path. Since element removal from sets can happen from control plane and element garbage collection/timeout, it is necessary to keep the set structure alive until all elements have been deactivated and destroyed. We cannot do a cancel_work_sync or flush_work in nft_set_destroy because its called with the transaction mutex held, but the aforementioned async work queue might be blocked on the very mutex that nft_set_destroy() callchain is sitting on. This gives us the choice of ABBA deadlock or UaF. To avoid both, add set->refs refcount_t member. The GC API can then increment the set refcount and release it once the elements have been free'd. Set backends are adapted to use the GC transaction API in a follow up patch entitled: ("netfilter: nf_tables: use gc transaction API in set backends") This is joint work with Florian Westphal. Fixes: cfed7e1b1f8e ("netfilter: nf_tables: add set garbage collection helpers") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/net/netfilter/nf_tables.h | 64 +++++++- net/netfilter/nf_tables_api.c | 248 ++++++++++++++++++++++++++++-- 2 files changed, 300 insertions(+), 12 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c752b6f50979..3b76370683c8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -507,6 +507,7 @@ struct nft_set_elem_expr { * * @list: table set list node * @bindings: list of set bindings + * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set @@ -536,6 +537,7 @@ struct nft_set_elem_expr { struct nft_set { struct list_head list; struct list_head bindings; + refcount_t refs; struct nft_table *table; possible_net_t net; char *name; @@ -557,7 +559,8 @@ struct nft_set { struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - u16 flags:14, + u16 flags:13, + dead:1, genmask:2; u8 klen; u8 dlen; @@ -1577,6 +1580,32 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) clear_bit(NFT_SET_ELEM_BUSY_BIT, word); } +#define NFT_SET_ELEM_DEAD_MASK (1 << 3) + +#if defined(__LITTLE_ENDIAN_BITFIELD) +#define NFT_SET_ELEM_DEAD_BIT 3 +#elif defined(__BIG_ENDIAN_BITFIELD) +#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 3) +#else +#error +#endif + +static inline void nft_set_elem_dead(struct nft_set_ext *ext) +{ + unsigned long *word = (unsigned long *)ext; + + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + set_bit(NFT_SET_ELEM_DEAD_BIT, word); +} + +static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) +{ + unsigned long *word = (unsigned long *)ext; + + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + return test_bit(NFT_SET_ELEM_DEAD_BIT, word); +} + /** * struct nft_trans - nf_tables object update in transaction * @@ -1708,6 +1737,38 @@ struct nft_trans_flowtable { #define nft_trans_flowtable_flags(trans) \ (((struct nft_trans_flowtable *)trans->data)->flags) +#define NFT_TRANS_GC_BATCHCOUNT 256 + +struct nft_trans_gc { + struct list_head list; + struct net *net; + struct nft_set *set; + u32 seq; + u8 count; + void *priv[NFT_TRANS_GC_BATCHCOUNT]; + struct rcu_head rcu; +}; + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_destroy(struct nft_trans_gc *trans); + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); + +void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq); + +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); @@ -1735,6 +1796,7 @@ struct nftables_pernet { u64 table_handle; unsigned int base_seq; u8 validate_state; + unsigned int gc_seq; }; extern unsigned int nf_tables_net_id; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 475c556f4991..e8e18a54958f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -31,7 +31,9 @@ static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); +static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); +static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, @@ -122,6 +124,9 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); +static void nft_trans_gc_work(struct work_struct *work); +static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -583,10 +588,6 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem); - static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -4854,6 +4855,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); + refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -4921,6 +4923,14 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, } } +static void nft_set_put(struct nft_set *set) +{ + if (refcount_dec_and_test(&set->refs)) { + kfree(set->name); + kvfree(set); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; @@ -4933,8 +4943,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); - kfree(set->name); - kvfree(set); + nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, @@ -6051,7 +6060,8 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && - !nft_set_elem_expired(ext)) + !nft_set_elem_expired(ext) && + !nft_set_elem_is_dead(ext)) return ext; } @@ -6704,9 +6714,9 @@ static void nft_setelem_data_activate(const struct net *net, nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -9093,6 +9103,207 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, + struct nft_trans_gc *trans) +{ + void **priv = trans->priv; + unsigned int i; + + for (i = 0; i < trans->count; i++) { + struct nft_set_elem elem = { + .priv = priv[i], + }; + + nft_setelem_data_deactivate(ctx->net, trans->set, &elem); + nft_setelem_remove(ctx->net, trans->set, &elem); + } +} + +void nft_trans_gc_destroy(struct nft_trans_gc *trans) +{ + nft_set_put(trans->set); + put_net(trans->net); + kfree(trans); +} + +static void nft_trans_gc_trans_free(struct rcu_head *rcu) +{ + struct nft_set_elem elem = {}; + struct nft_trans_gc *trans; + struct nft_ctx ctx = {}; + unsigned int i; + + trans = container_of(rcu, struct nft_trans_gc, rcu); + ctx.net = read_pnet(&trans->set->net); + + for (i = 0; i < trans->count; i++) { + elem.priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, &elem)) + atomic_dec(&trans->set->nelems); + + nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + } + + nft_trans_gc_destroy(trans); +} + +static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) +{ + struct nftables_pernet *nft_net; + struct nft_ctx ctx = {}; + + nft_net = nft_pernet(trans->net); + + mutex_lock(&nft_net->commit_mutex); + + /* Check for race with transaction, otherwise this batch refers to + * stale objects that might not be there anymore. Skip transaction if + * set has been destroyed from control plane transaction in case gc + * worker loses race. + */ + if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { + mutex_unlock(&nft_net->commit_mutex); + return false; + } + + ctx.net = trans->net; + ctx.table = trans->set->table; + + nft_trans_gc_setelem_remove(&ctx, trans); + mutex_unlock(&nft_net->commit_mutex); + + return true; +} + +static void nft_trans_gc_work(struct work_struct *work) +{ + struct nft_trans_gc *trans, *next; + LIST_HEAD(trans_gc_list); + + spin_lock(&nf_tables_destroy_list_lock); + list_splice_init(&nf_tables_gc_list, &trans_gc_list); + spin_unlock(&nf_tables_destroy_list_lock); + + list_for_each_entry_safe(trans, next, &trans_gc_list, list) { + list_del(&trans->list); + if (!nft_trans_gc_work_done(trans)) { + nft_trans_gc_destroy(trans); + continue; + } + call_rcu(&trans->rcu, nft_trans_gc_trans_free); + } +} + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp) +{ + struct net *net = read_pnet(&set->net); + struct nft_trans_gc *trans; + + trans = kzalloc(sizeof(*trans), gfp); + if (!trans) + return NULL; + + refcount_inc(&set->refs); + trans->set = set; + trans->net = get_net(net); + trans->seq = gc_seq; + + return trans; +} + +void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) +{ + trans->priv[trans->count++] = priv; +} + +static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) +{ + spin_lock(&nf_tables_gc_list_lock); + list_add_tail(&trans->list, &nf_tables_gc_list); + spin_unlock(&nf_tables_gc_list_lock); + + schedule_work(&trans_gc_work); +} + +static int nft_trans_gc_space(struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp) +{ + if (nft_trans_gc_space(gc)) + return gc; + + nft_trans_gc_queue_work(gc); + + return nft_trans_gc_alloc(gc->set, gc_seq, gfp); +} + +void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) +{ + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + nft_trans_gc_queue_work(trans); +} + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) +{ + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) + return NULL; + + if (nft_trans_gc_space(gc)) + return gc; + + call_rcu(&gc->rcu, nft_trans_gc_trans_free); + + return nft_trans_gc_alloc(gc->set, 0, gfp); +} + +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) +{ + WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); + + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + call_rcu(&trans->rcu, nft_trans_gc_trans_free); +} + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + struct nft_set_elem_catchall *catchall; + const struct nft_set *set = gc->set; + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + if (nft_set_elem_is_dead(ext)) + goto dead_elem; + + nft_set_elem_dead(ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + return NULL; + + nft_trans_gc_elem_add(gc, catchall->elem); + } + + return gc; +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -9255,11 +9466,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; - unsigned int base_seq; LIST_HEAD(adl); int err; @@ -9336,6 +9547,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) WRITE_ONCE(nft_net->base_seq, base_seq); + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9424,6 +9639,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSET: + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_DELSET, GFP_KERNEL); @@ -9523,6 +9739,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); + + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); nf_tables_commit_release(net); return 0; @@ -10555,6 +10773,7 @@ static int __net_init nf_tables_init_net(struct net *net) mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; nft_net->validate_state = NFT_VALIDATE_SKIP; + nft_net->gc_seq = 0; return 0; } @@ -10583,10 +10802,16 @@ static void __net_exit nf_tables_exit_net(struct net *net) WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } +static void nf_tables_exit_batch(struct list_head *net_exit_list) +{ + flush_work(&trans_gc_work); +} + static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; @@ -10658,6 +10883,7 @@ static void __exit nf_tables_module_exit(void) nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); + cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); From df650d6a4bf47248261b61ef6b174d7c54034d15 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:15 +0200 Subject: [PATCH 1663/2093] netfilter: nf_tables: adapt set backend to use GC transaction API commit f6c383b8c31a93752a52697f8430a71dcbc46adf upstream. Use the GC transaction API to replace the old and buggy gc API and the busy mark approach. No set elements are removed from async garbage collection anymore, instead the _DEAD bit is set on so the set element is not visible from lookup path anymore. Async GC enqueues transaction work that might be aborted and retried later. rbtree and pipapo set backends does not set on the _DEAD bit from the sync GC path since this runs in control plane path where mutex is held. In this case, set elements are deactivated, removed and then released via RCU callback, sync GC never fails. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support") Fixes: 9d0982927e79 ("netfilter: nft_hash: add support for timeouts") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 7 +- net/netfilter/nft_set_hash.c | 77 +++++++++++------- net/netfilter/nft_set_pipapo.c | 50 +++++++++--- net/netfilter/nft_set_rbtree.c | 144 ++++++++++++++++++++------------- 4 files changed, 174 insertions(+), 104 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e8e18a54958f..e179d1132f2f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6153,7 +6153,6 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, if (nft_setelem_is_catchall(set, elem)) { nft_set_elem_change_active(net, set, ext); - nft_set_elem_clear_busy(ext); } else { set->ops->activate(net, set, elem); } @@ -6168,8 +6167,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext) || - nft_set_elem_mark_busy(ext)) + if (!nft_is_active(net, ext)) continue; kfree(elem->priv); @@ -6880,8 +6878,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask) || - nft_set_elem_mark_busy(ext)) + if (!nft_set_elem_active(ext, genmask)) continue; elem.priv = catchall->elem; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 24caa31fa231..2f067e4596b0 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -59,6 +59,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; + if (nft_set_elem_is_dead(&he->ext)) + return 1; if (nft_set_elem_expired(&he->ext)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) @@ -188,7 +190,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); - nft_set_elem_clear_busy(&he->ext); } static bool nft_rhash_flush(const struct net *net, @@ -196,12 +197,9 @@ static bool nft_rhash_flush(const struct net *net, { struct nft_rhash_elem *he = priv; - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) { - nft_set_elem_change_active(net, set, &he->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &he->ext); + + return true; } static void *nft_rhash_deactivate(const struct net *net, @@ -218,9 +216,8 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); - if (he != NULL && - !nft_rhash_flush(net, set, he)) - he = NULL; + if (he) + nft_set_elem_change_active(net, set, &he->ext); rcu_read_unlock(); @@ -312,25 +309,48 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, static void nft_rhash_gc(struct work_struct *work) { + struct nftables_pernet *nft_net; struct nft_set *set; struct nft_rhash_elem *he; struct nft_rhash *priv; - struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; + struct nft_trans_gc *gc; + struct net *net; + u32 gc_seq; priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - break; + if (PTR_ERR(he) != -EAGAIN) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } continue; } + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + + if (nft_set_elem_is_dead(&he->ext)) + goto dead_elem; + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) && nft_rhash_expr_needs_gc_run(set, &he->ext)) goto needs_gc_run; @@ -338,26 +358,26 @@ static void nft_rhash_gc(struct work_struct *work) if (!nft_set_elem_expired(&he->ext)) continue; needs_gc_run: - if (nft_set_elem_mark_busy(&he->ext)) - continue; + nft_set_elem_dead(&he->ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb == NULL) - break; - rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); + nft_trans_gc_elem_add(gc, he); } + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: + /* catchall list iteration requires rcu read side lock. */ rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); - he = nft_set_catchall_gc(set); - if (he) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, he); - } - nft_set_gc_batch_complete(gcb); + if (gc) + nft_trans_gc_queue_async_done(gc); + +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } @@ -420,7 +440,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx, }; cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)&rhash_ctx); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index b6a994ba72f3..a307a227d28d 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1544,16 +1544,34 @@ static void pipapo_drop(struct nft_pipapo_match *m, } } +static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, + struct nft_pipapo_elem *e) + +{ + struct nft_set_elem elem = { + .priv = e, + }; + + nft_setelem_data_deactivate(net, set, &elem); +} + /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) { + struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; + struct nft_trans_gc *gc; + + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; @@ -1577,13 +1595,20 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) f--; i--; e = f->mt[rulemap[i].to].e; - if (nft_set_elem_expired(&e->ext) && - !nft_set_elem_mark_busy(&e->ext)) { - priv->dirty = true; - pipapo_drop(m, rulemap); - rcu_barrier(); - nft_set_elem_destroy(set, e, true); + /* synchronous gc never fails, there is no need to set on + * NFT_SET_ELEM_DEAD_BIT. + */ + if (nft_set_elem_expired(&e->ext)) { + priv->dirty = true; + + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (!gc) + break; + + nft_pipapo_gc_deactivate(net, set, e); + pipapo_drop(m, rulemap); + nft_trans_gc_elem_add(gc, e); /* And check again current first rule, which is now the * first we haven't checked. @@ -1593,11 +1618,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) } } - e = nft_set_catchall_gc(set); - if (e) - nft_set_elem_destroy(set, e, true); - - priv->last_gc = jiffies; + gc = nft_trans_gc_catchall(gc, 0); + if (gc) { + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } /** @@ -1733,7 +1758,6 @@ static void nft_pipapo_activate(const struct net *net, return; nft_set_elem_change_active(net, set, &e->ext); - nft_set_elem_clear_busy(&e->ext); } /** diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 39956e5341c9..f9d4c8fcbbf8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } +static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) +{ + return nft_set_elem_expired(&rbe->ext) || + nft_set_elem_is_dead(&rbe->ext); +} + static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) @@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set continue; } - if (nft_set_elem_expired(&rbe->ext)) + if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { @@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && + !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -215,6 +221,18 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set_elem elem = { + .priv = rbe, + }; + + nft_setelem_data_deactivate(net, set, &elem); + rb_erase(&rbe->node, &priv->root); +} + static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe, @@ -222,11 +240,12 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); + struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; - struct nft_set_gc_batch *gcb; + struct nft_trans_gc *gc; - gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); - if (!gcb) + gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); + if (!gc) return -ENOMEM; /* search for end interval coming before this element. @@ -244,17 +263,28 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + nft_rbtree_gc_remove(net, set, priv, rbe_prev); - rb_erase(&rbe_prev->node, &priv->root); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_prev); + /* There is always room in this trans gc for this element, + * memory allocation never actually happens, hence, the warning + * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, + * this is synchronous gc which never fails. + */ + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe_prev); } - rb_erase(&rbe->node, &priv->root); - atomic_dec(&set->nelems); + nft_rbtree_gc_remove(net, set, priv, rbe); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; - nft_set_gc_batch_add(gcb, rbe); - nft_set_gc_batch_complete(gcb); + nft_trans_gc_elem_add(gc, rbe); + + nft_trans_gc_queue_sync_done(gc); return 0; } @@ -482,7 +512,6 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); - nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -490,12 +519,9 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - if (!nft_set_elem_mark_busy(&rbe->ext) || - !nft_is_active(net, &rbe->ext)) { - nft_set_elem_change_active(net, set, &rbe->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &rbe->ext); + + return true; } static void *nft_rbtree_deactivate(const struct net *net, @@ -570,26 +596,40 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, static void nft_rbtree_gc(struct work_struct *work) { - struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; - struct nft_set_gc_batch *gcb = NULL; + struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct nftables_pernet *nft_net; struct nft_rbtree *priv; + struct nft_trans_gc *gc; struct rb_node *node; struct nft_set *set; + unsigned int gc_seq; struct net *net; - u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); - genmask = nft_genmask_cur(net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (!nft_set_elem_active(&rbe->ext, genmask)) - continue; + if (nft_set_elem_is_dead(&rbe->ext)) + goto dead_elem; /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is @@ -602,46 +642,36 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) { - rbe_end = NULL; + nft_set_elem_dead(&rbe->ext); + + if (!rbe_end) continue; - } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - rbe_prev = NULL; - } - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (!gcb) - break; + nft_set_elem_dead(&rbe_end->ext); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - rbe_prev = rbe; + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - if (rbe_end) { - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_end); - rb_erase(&rbe_end->node, &priv->root); - rbe_end = NULL; - } - node = rb_next(node); - if (!node) - break; + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, rbe); } - if (rbe_prev) - rb_erase(&rbe_prev->node, &priv->root); + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); - rbe = nft_set_catchall_gc(set); - if (rbe) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, rbe); - } - nft_set_gc_batch_complete(gcb); - + if (gc) + nft_trans_gc_queue_async_done(gc); +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } From 4ead4f74b3a9162b205f702d72d4a3421356dbc1 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:16 +0200 Subject: [PATCH 1664/2093] netfilter: nft_set_hash: mark set element as dead when deleting from packet path upstream c92db3030492b8ad1d0faace7a93bbcf53850d0c commit. Set on the NFT_SET_ELEM_DEAD_BIT flag on this element, instead of performing element removal which might race with an ongoing transaction. Enable gc when dynamic flag is set on since dynset deletion requires garbage collection after this patch. Fixes: d0a8d877da97 ("netfilter: nft_dynset: support for element deletion") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_hash.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 2f067e4596b0..cef5df846000 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -249,7 +249,9 @@ static bool nft_rhash_delete(const struct nft_set *set, if (he == NULL) return false; - return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0; + nft_set_elem_dead(&he->ext); + + return true; } static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, @@ -412,7 +414,7 @@ static int nft_rhash_init(const struct nft_set *set, return err; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); - if (set->flags & NFT_SET_TIMEOUT) + if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL)) nft_rhash_gc_init(set); return 0; From 0b9af4860a61f55cf716267b5ae5df34aacc4b39 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:17 +0200 Subject: [PATCH 1665/2093] netfilter: nf_tables: remove busy mark and gc batch API commit a2dd0233cbc4d8a0abb5f64487487ffc9265beb5 upstream. Ditch it, it has been replace it by the GC transaction API and it has no clients anymore. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/net/netfilter/nf_tables.h | 98 +------------------------------ net/netfilter/nf_tables_api.c | 48 +-------------- 2 files changed, 4 insertions(+), 142 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3b76370683c8..2d501dd90152 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -594,7 +594,6 @@ struct nft_set *nft_set_lookup_global(const struct net *net, struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set); -void *nft_set_catchall_gc(const struct nft_set *set); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { @@ -811,62 +810,6 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem); -/** - * struct nft_set_gc_batch_head - nf_tables set garbage collection batch - * - * @rcu: rcu head - * @set: set the elements belong to - * @cnt: count of elements - */ -struct nft_set_gc_batch_head { - struct rcu_head rcu; - const struct nft_set *set; - unsigned int cnt; -}; - -#define NFT_SET_GC_BATCH_SIZE ((PAGE_SIZE - \ - sizeof(struct nft_set_gc_batch_head)) / \ - sizeof(void *)) - -/** - * struct nft_set_gc_batch - nf_tables set garbage collection batch - * - * @head: GC batch head - * @elems: garbage collection elements - */ -struct nft_set_gc_batch { - struct nft_set_gc_batch_head head; - void *elems[NFT_SET_GC_BATCH_SIZE]; -}; - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp); -void nft_set_gc_batch_release(struct rcu_head *rcu); - -static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb) -{ - if (gcb != NULL) - call_rcu(&gcb->head.rcu, nft_set_gc_batch_release); -} - -static inline struct nft_set_gc_batch * -nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb, - gfp_t gfp) -{ - if (gcb != NULL) { - if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems)) - return gcb; - nft_set_gc_batch_complete(gcb); - } - return nft_set_gc_batch_alloc(set, gfp); -} - -static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, - void *elem) -{ - gcb->elems[gcb->head.cnt++] = elem; -} - struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type @@ -1545,47 +1488,12 @@ static inline void nft_set_elem_change_active(const struct net *net, #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ -/* - * We use a free bit in the genmask field to indicate the element - * is busy, meaning it is currently being processed either by - * the netlink API or GC. - * - * Even though the genmask is only a single byte wide, this works - * because the extension structure if fully constant once initialized, - * so there are no non-atomic write accesses unless it is already - * marked busy. - */ -#define NFT_SET_ELEM_BUSY_MASK (1 << 2) +#define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT 2 +#define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) -#else -#error -#endif - -static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext) -{ - unsigned long *word = (unsigned long *)ext; - - BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); - return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word); -} - -static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) -{ - unsigned long *word = (unsigned long *)ext; - - clear_bit(NFT_SET_ELEM_BUSY_BIT, word); -} - -#define NFT_SET_ELEM_DEAD_MASK (1 << 3) - -#if defined(__LITTLE_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_DEAD_BIT 3 -#elif defined(__BIG_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 3) +#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e179d1132f2f..a38d87256b8f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6069,29 +6069,6 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); -void *nft_set_catchall_gc(const struct nft_set *set) -{ - struct nft_set_elem_catchall *catchall, *next; - struct nft_set_ext *ext; - void *elem = NULL; - - list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - - if (!nft_set_elem_expired(ext) || - nft_set_elem_mark_busy(ext)) - continue; - - elem = catchall->elem; - list_del_rcu(&catchall->list); - kfree_rcu(catchall, rcu); - break; - } - - return elem; -} -EXPORT_SYMBOL_GPL(nft_set_catchall_gc); - static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, @@ -6562,7 +6539,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_elem_free; } - ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; + ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { @@ -6949,29 +6926,6 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return err; } -void nft_set_gc_batch_release(struct rcu_head *rcu) -{ - struct nft_set_gc_batch *gcb; - unsigned int i; - - gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); - for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); - kfree(gcb); -} - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp) -{ - struct nft_set_gc_batch *gcb; - - gcb = kzalloc(sizeof(*gcb), gfp); - if (gcb == NULL) - return gcb; - gcb->head.set = set; - return gcb; -} - /* * Stateful objects */ From 59ee68c437c562170265194a99698c805a686bb3 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 22 Sep 2023 18:30:18 +0200 Subject: [PATCH 1666/2093] netfilter: nf_tables: don't fail inserts if duplicate has expired commit 7845914f45f066497ac75b30c50dbc735e84e884 upstream. nftables selftests fail: run-tests.sh testcases/sets/0044interval_overlap_0 Expected: 0-2 . 0-3, got: W: [FAILED] ./testcases/sets/0044interval_overlap_0: got 1 Insertion must ignore duplicate but expired entries. Moreover, there is a strange asymmetry in nft_pipapo_activate: It refetches the current element, whereas the other ->activate callbacks (bitmap, hash, rhash, rbtree) use elem->priv. Same for .remove: other set implementations take elem->priv, nft_pipapo_remove fetches elem->priv, then does a relookup, remove this. I suspect this was the reason for the change that prompted the removal of the expired check in pipapo_get() in the first place, but skipping exired elements there makes no sense to me, this helper is used for normal get requests, insertions (duplicate check) and deactivate callback. In first two cases expired elements must be skipped. For ->deactivate(), this gets called for DELSETELEM, so it seems to me that expired elements should be skipped as well, i.e. delete request should fail with -ENOENT error. Fixes: 24138933b97b ("netfilter: nf_tables: don't skip expired elements during walk") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo.c | 23 ++++------------------- 1 file changed, 4 insertions(+), 19 deletions(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index a307a227d28d..58bd514260b9 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -566,6 +566,8 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; if (last) { + if (nft_set_elem_expired(&f->mt[b].e->ext)) + goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; @@ -600,17 +602,8 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - struct nft_pipapo_elem *ret; - - ret = pipapo_get(net, set, (const u8 *)elem->key.val.data, + return pipapo_get(net, set, (const u8 *)elem->key.val.data, nft_genmask_cur(net)); - if (IS_ERR(ret)) - return ret; - - if (nft_set_elem_expired(&ret->ext)) - return ERR_PTR(-ENOENT); - - return ret; } /** @@ -1751,11 +1744,7 @@ static void nft_pipapo_activate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_pipapo_elem *e; - - e = pipapo_get(net, set, (const u8 *)elem->key.val.data, 0); - if (IS_ERR(e)) - return; + struct nft_pipapo_elem *e = elem->priv; nft_set_elem_change_active(net, set, &e->ext); } @@ -1969,10 +1958,6 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, data = (const u8 *)nft_set_ext_key(&e->ext); - e = pipapo_get(net, set, data, 0); - if (IS_ERR(e)) - return; - while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const u8 *match_start, *match_end; From 41113aa5698ad7a82635bcb747d483e4458d518d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:19 +0200 Subject: [PATCH 1667/2093] netfilter: nf_tables: fix GC transaction races with netns and netlink event exit path commit 6a33d8b73dfac0a41f3877894b38082bd0c9a5bc upstream. Netlink event path is missing a synchronization point with GC transactions. Add GC sequence number update to netns release path and netlink event path, any GC transaction losing race will be discarded. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 36 +++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a38d87256b8f..693dd05fdad6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9413,6 +9413,22 @@ static void nft_set_commit_update(struct list_head *set_update_list) } } +static unsigned int nft_gc_seq_begin(struct nftables_pernet *nft_net) +{ + unsigned int gc_seq; + + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + + return gc_seq; +} + +static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq) +{ + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -9498,9 +9514,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) WRITE_ONCE(nft_net->base_seq, base_seq); - /* Bump gc counter, it becomes odd, this is the busy mark. */ - gc_seq = READ_ONCE(nft_net->gc_seq); - WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + gc_seq = nft_gc_seq_begin(nft_net); /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9691,7 +9705,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); - WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + nft_gc_seq_end(nft_net, gc_seq); nf_tables_commit_release(net); return 0; @@ -10674,6 +10688,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, struct net *net = n->net; unsigned int deleted; bool restart = false; + unsigned int gc_seq; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; @@ -10681,6 +10696,9 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, nft_net = nft_pernet(net); deleted = 0; mutex_lock(&nft_net->commit_mutex); + + gc_seq = nft_gc_seq_begin(nft_net); + if (!list_empty(&nf_tables_destroy_list)) nf_tables_trans_destroy_flush_work(); again: @@ -10703,6 +10721,8 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, if (restart) goto again; } + nft_gc_seq_end(nft_net, gc_seq); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; @@ -10741,12 +10761,20 @@ static void __net_exit nf_tables_pre_exit_net(struct net *net) static void __net_exit nf_tables_exit_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); + unsigned int gc_seq; mutex_lock(&nft_net->commit_mutex); + + gc_seq = nft_gc_seq_begin(nft_net); + if (!list_empty(&nft_net->commit_list) || !list_empty(&nft_net->module_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); + __nft_release_tables(net); + + nft_gc_seq_end(nft_net, gc_seq); + mutex_unlock(&nft_net->commit_mutex); WARN_ON_ONCE(!list_empty(&nft_net->tables)); WARN_ON_ONCE(!list_empty(&nft_net->module_list)); From afa584c35065051a11ae3ea3cc105b634053fcd8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:20 +0200 Subject: [PATCH 1668/2093] netfilter: nf_tables: GC transaction race with netns dismantle commit 02c6c24402bf1c1e986899c14ba22a10b510916b upstream. Use maybe_get_net() since GC workqueue might race with netns exit path. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 693dd05fdad6..53ee6ac16f9e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9155,9 +9155,14 @@ struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, if (!trans) return NULL; + trans->net = maybe_get_net(net); + if (!trans->net) { + kfree(trans); + return NULL; + } + refcount_inc(&set->refs); trans->set = set; - trans->net = get_net(net); trans->seq = gc_seq; return trans; From 5d319f7a81431c6bb32eb4dc7d7975f99e2c8c66 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:21 +0200 Subject: [PATCH 1669/2093] netfilter: nf_tables: GC transaction race with abort path commit 720344340fb9be2765bbaab7b292ece0a4570eae upstream. Abort path is missing a synchronization point with GC transactions. Add GC sequence number hence any GC transaction losing race will be discarded. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 53ee6ac16f9e..0455af9a66af 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9969,7 +9969,12 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); - int ret = __nf_tables_abort(net, action); + unsigned int gc_seq; + int ret; + + gc_seq = nft_gc_seq_begin(nft_net); + ret = __nf_tables_abort(net, action); + nft_gc_seq_end(nft_net, gc_seq); mutex_unlock(&nft_net->commit_mutex); From 620e594be334f48c172f0ef01a2cee84536a703a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:22 +0200 Subject: [PATCH 1670/2093] netfilter: nf_tables: use correct lock to protect gc_list commit 8357bc946a2abc2a10ca40e5a2105d2b4c57515e upstream. Use nf_tables_gc_list_lock spinlock, not nf_tables_destroy_list_lock to protect the gc_list. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0455af9a66af..47f3632c78bf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9131,9 +9131,9 @@ static void nft_trans_gc_work(struct work_struct *work) struct nft_trans_gc *trans, *next; LIST_HEAD(trans_gc_list); - spin_lock(&nf_tables_destroy_list_lock); + spin_lock(&nf_tables_gc_list_lock); list_splice_init(&nf_tables_gc_list, &trans_gc_list); - spin_unlock(&nf_tables_destroy_list_lock); + spin_unlock(&nf_tables_gc_list_lock); list_for_each_entry_safe(trans, next, &trans_gc_list, list) { list_del(&trans->list); From a42ac74c966604c70f60fc9ee961beae20733f09 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 22 Sep 2023 18:30:23 +0200 Subject: [PATCH 1671/2093] netfilter: nf_tables: defer gc run if previous batch is still pending commit 8e51830e29e12670b4c10df070a4ea4c9593e961 upstream. Don't queue more gc work, else we may queue the same elements multiple times. If an element is flagged as dead, this can mean that either the previous gc request was invalidated/discarded by a transaction or that the previous request is still pending in the system work queue. The latter will happen if the gc interval is set to a very low value, e.g. 1ms, and system work queue is backlogged. The sets refcount is 1 if no previous gc requeusts are queued, so add a helper for this and skip gc run if old requests are pending. Add a helper for this and skip the gc run in this case. Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- include/net/netfilter/nf_tables.h | 5 +++++ net/netfilter/nft_set_hash.c | 3 +++ net/netfilter/nft_set_rbtree.c | 3 +++ 3 files changed, 11 insertions(+) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2d501dd90152..12777a5b60cd 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -581,6 +581,11 @@ static inline void *nft_set_priv(const struct nft_set *set) return (void *)set->data; } +static inline bool nft_set_gc_is_pending(const struct nft_set *s) +{ + return refcount_read(&s->refs) != 1; +} + static inline struct nft_set *nft_set_container_of(const void *priv) { return (void *)priv - offsetof(struct nft_set, data); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index cef5df846000..524763659f25 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -326,6 +326,9 @@ static void nft_rhash_gc(struct work_struct *work) nft_net = nft_pernet(net); gc_seq = READ_ONCE(nft_net->gc_seq); + if (nft_set_gc_is_pending(set)) + goto done; + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); if (!gc) goto done; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index f9d4c8fcbbf8..c6435e709231 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -611,6 +611,9 @@ static void nft_rbtree_gc(struct work_struct *work) nft_net = nft_pernet(net); gc_seq = READ_ONCE(nft_net->gc_seq); + if (nft_set_gc_is_pending(set)) + goto done; + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); if (!gc) goto done; From 9a8c544158f68f656d1734eb5ba00c4f817b76b1 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:24 +0200 Subject: [PATCH 1672/2093] netfilter: nft_set_rbtree: skip sync GC for new elements in this transaction commit 2ee52ae94baabf7ee09cf2a8d854b990dac5d0e4 upstream. New elements in this transaction might expired before such transaction ends. Skip sync GC for such elements otherwise commit path might walk over an already released object. Once transaction is finished, async GC will collect such expired element. Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_rbtree.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index c6435e709231..f250b5399344 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -312,6 +312,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); + u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); int d, err; @@ -357,8 +358,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (!nft_set_elem_active(&rbe->ext, genmask)) continue; - /* perform garbage collection to avoid bogus overlap reports. */ - if (nft_set_elem_expired(&rbe->ext)) { + /* perform garbage collection to avoid bogus overlap reports + * but skip new elements in this transaction. + */ + if (nft_set_elem_expired(&rbe->ext) && + nft_set_elem_active(&rbe->ext, cur_genmask)) { err = nft_rbtree_gc_elem(set, priv, rbe, genmask); if (err < 0) return err; From 92b4b4bde94033b03a030964bc003cdfd8c44e16 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:25 +0200 Subject: [PATCH 1673/2093] netfilter: nft_set_rbtree: use read spinlock to avoid datapath contention commit 96b33300fba880ec0eafcf3d82486f3463b4b6da upstream. rbtree GC does not modify the datastructure, instead it collects expired elements and it enqueues a GC transaction. Use a read spinlock instead to avoid data contention while GC worker is running. Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_rbtree.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index f250b5399344..70491ba98dec 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -622,8 +622,7 @@ static void nft_rbtree_gc(struct work_struct *work) if (!gc) goto done; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); + read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { /* Ruleset has been updated, try later. */ @@ -673,8 +672,7 @@ static void nft_rbtree_gc(struct work_struct *work) gc = nft_trans_gc_catchall(gc, gc_seq); try_later: - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + read_unlock_bh(&priv->lock); if (gc) nft_trans_gc_queue_async_done(gc); From 8c643a8e040d4ab4e705087bd7442bee7fc262a2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:26 +0200 Subject: [PATCH 1674/2093] netfilter: nft_set_pipapo: call nft_trans_gc_queue_sync() in catchall GC commit 4a9e12ea7e70223555ec010bec9f711089ce96f6 upstream. pipapo needs to enqueue GC transactions for catchall elements through nft_trans_gc_queue_sync(). Add nft_trans_gc_catchall_sync() and nft_trans_gc_catchall_async() to handle GC transaction queueing accordingly. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/net/netfilter/nf_tables.h | 5 +++-- net/netfilter/nf_tables_api.c | 22 +++++++++++++++++++--- net/netfilter/nft_set_hash.c | 2 +- net/netfilter/nft_set_pipapo.c | 2 +- net/netfilter/nft_set_rbtree.c | 2 +- 5 files changed, 25 insertions(+), 8 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 12777a5b60cd..eb2103a9a7dd 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1675,8 +1675,9 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq); +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq); +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 47f3632c78bf..6e67fb999a25 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9233,8 +9233,9 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) call_rcu(&trans->rcu, nft_trans_gc_trans_free); } -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq) +static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq, + bool sync) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; @@ -9250,7 +9251,11 @@ struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, nft_set_elem_dead(ext); dead_elem: - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (sync) + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + else + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) return NULL; @@ -9260,6 +9265,17 @@ struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, return gc; } +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + return nft_trans_gc_catchall(gc, gc_seq, false); +} + +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) +{ + return nft_trans_gc_catchall(gc, 0, true); +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 524763659f25..eca20dc60138 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -372,7 +372,7 @@ static void nft_rhash_gc(struct work_struct *work) nft_trans_gc_elem_add(gc, he); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: /* catchall list iteration requires rcu read side lock. */ diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 58bd514260b9..7248a1737ee1 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1611,7 +1611,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall(gc, 0); + gc = nft_trans_gc_catchall_sync(gc); if (gc) { nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 70491ba98dec..487572dcd614 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -669,7 +669,7 @@ static void nft_rbtree_gc(struct work_struct *work) nft_trans_gc_elem_add(gc, rbe); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: read_unlock_bh(&priv->lock); From 973288e9d9886750684876eec70e0bc55b10607c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:27 +0200 Subject: [PATCH 1675/2093] netfilter: nft_set_pipapo: stop GC iteration if GC transaction allocation fails commit 6d365eabce3c018a80f6e0379b17df2abb17405e upstream. nft_trans_gc_queue_sync() enqueues the GC transaction and it allocates a new one. If this allocation fails, then stop this GC sync run and retry later. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 7248a1737ee1..83f5f276c3bf 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1597,7 +1597,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (!gc) - break; + return; nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); From be4fbbbcd2f20c2cd0421f530f45c5545c3a4886 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 22 Sep 2023 18:30:28 +0200 Subject: [PATCH 1676/2093] netfilter: nft_set_hash: try later when GC hits EAGAIN on iteration commit b079155faae94e9b3ab9337e82100a914ebb4e8d upstream. Skip GC run if iterator rewinds to the beginning with EAGAIN, otherwise GC might collect the same element more than once. Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_hash.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index eca20dc60138..2013de934cef 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -338,12 +338,9 @@ static void nft_rhash_gc(struct work_struct *work) while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) { - nft_trans_gc_destroy(gc); - gc = NULL; - goto try_later; - } - continue; + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; } /* Ruleset has been updated, try later. */ From 7e5d732e6902eb6a37b35480796838a145ae5f07 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 22 Sep 2023 18:30:29 +0200 Subject: [PATCH 1677/2093] netfilter: nf_tables: fix memleak when more than 255 elements expired commit cf5000a7787cbc10341091d37245a42c119d26c5 upstream. When more than 255 elements expired we're supposed to switch to a new gc container structure. This never happens: u8 type will wrap before reaching the boundary and nft_trans_gc_space() always returns true. This means we recycle the initial gc container structure and lose track of the elements that came before. While at it, don't deref 'gc' after we've passed it to call_rcu. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Reported-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/net/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index eb2103a9a7dd..05d7a60a0e1f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1657,7 +1657,7 @@ struct nft_trans_gc { struct net *net; struct nft_set *set; u32 seq; - u8 count; + u16 count; void *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6e67fb999a25..b22f2d9ee4af 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9190,12 +9190,15 @@ static int nft_trans_gc_space(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { + struct nft_set *set; + if (nft_trans_gc_space(gc)) return gc; + set = gc->set; nft_trans_gc_queue_work(gc); - return nft_trans_gc_alloc(gc->set, gc_seq, gfp); + return nft_trans_gc_alloc(set, gc_seq, gfp); } void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) @@ -9210,15 +9213,18 @@ void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) { + struct nft_set *set; + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) return NULL; if (nft_trans_gc_space(gc)) return gc; + set = gc->set; call_rcu(&gc->rcu, nft_trans_gc_trans_free); - return nft_trans_gc_alloc(gc->set, 0, gfp); + return nft_trans_gc_alloc(set, 0, gfp); } void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) From 7a7fd891022a692ecfa1e32b6eb3de417669afd2 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 7 Sep 2023 11:05:04 +0200 Subject: [PATCH 1678/2093] ASoC: meson: spdifin: start hw on dai probe [ Upstream commit aedf323b66b2b875137422ecb7d2525179759076 ] For spdif input to report the locked rate correctly, even when no capture is running, the HW and reference clock must be started as soon as the dai is probed. Fixes: 5ce5658375e6 ("ASoC: meson: add axg spdif input") Signed-off-by: Jerome Brunet Link: https://lore.kernel.org/r/20230907090504.12700-1-jbrunet@baylibre.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/meson/axg-spdifin.c | 49 ++++++++++++----------------------- 1 file changed, 17 insertions(+), 32 deletions(-) diff --git a/sound/soc/meson/axg-spdifin.c b/sound/soc/meson/axg-spdifin.c index e2cc4c4be758..97e81ec4a78c 100644 --- a/sound/soc/meson/axg-spdifin.c +++ b/sound/soc/meson/axg-spdifin.c @@ -112,34 +112,6 @@ static int axg_spdifin_prepare(struct snd_pcm_substream *substream, return 0; } -static int axg_spdifin_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); - int ret; - - ret = clk_prepare_enable(priv->refclk); - if (ret) { - dev_err(dai->dev, - "failed to enable spdifin reference clock\n"); - return ret; - } - - regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, - SPDIFIN_CTRL0_EN); - - return 0; -} - -static void axg_spdifin_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); - - regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); - clk_disable_unprepare(priv->refclk); -} - static void axg_spdifin_write_mode_param(struct regmap *map, int mode, unsigned int val, unsigned int num_per_reg, @@ -251,25 +223,38 @@ static int axg_spdifin_dai_probe(struct snd_soc_dai *dai) ret = axg_spdifin_sample_mode_config(dai, priv); if (ret) { dev_err(dai->dev, "mode configuration failed\n"); - clk_disable_unprepare(priv->pclk); - return ret; + goto pclk_err; } + ret = clk_prepare_enable(priv->refclk); + if (ret) { + dev_err(dai->dev, + "failed to enable spdifin reference clock\n"); + goto pclk_err; + } + + regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, + SPDIFIN_CTRL0_EN); + return 0; + +pclk_err: + clk_disable_unprepare(priv->pclk); + return ret; } static int axg_spdifin_dai_remove(struct snd_soc_dai *dai) { struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); + regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); + clk_disable_unprepare(priv->refclk); clk_disable_unprepare(priv->pclk); return 0; } static const struct snd_soc_dai_ops axg_spdifin_ops = { .prepare = axg_spdifin_prepare, - .startup = axg_spdifin_startup, - .shutdown = axg_spdifin_shutdown, }; static int axg_spdifin_iec958_info(struct snd_kcontrol *kcontrol, From 1e01b127685fcdd6041ef087776b88094acc2f3d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 10 Sep 2023 19:04:45 +0200 Subject: [PATCH 1679/2093] netfilter: nf_tables: disallow element removal on anonymous sets [ Upstream commit 23a3bfd4ba7acd36abf52b78605f61b21bdac216 ] Anonymous sets need to be populated once at creation and then they are bound to rule since 938154b93be8 ("netfilter: nf_tables: reject unbound anonymous set before commit phase"), otherwise transaction reports EINVAL. Userspace does not need to delete elements of anonymous sets that are not yet bound, reject this with EOPNOTSUPP. From flush command path, skip anonymous sets, they are expected to be bound already. Otherwise, EINVAL is hit at the end of this transaction for unbound sets. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b22f2d9ee4af..521f8c3cb698 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1437,8 +1437,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, set)) continue; - if (nft_set_is_anonymous(set) && - !list_empty(&set->bindings)) + if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); @@ -6907,8 +6906,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && - (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) + if (nft_set_is_anonymous(set)) + return -EOPNOTSUPP; + + if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); From e388671635acf470f0986d874389148fd234620b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 11 Sep 2023 15:28:14 +0200 Subject: [PATCH 1680/2093] bpf: Avoid deadlock when using queue and stack maps from NMI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a34a9f1a19afe9c60ca0ea61dfeee63a1c2baac8 ] Sysbot discovered that the queue and stack maps can deadlock if they are being used from a BPF program that can be called from NMI context (such as one that is attached to a perf HW counter event). To fix this, add an in_nmi() check and use raw_spin_trylock() in NMI context, erroring out if grabbing the lock fails. Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Hsin-Wei Hung Tested-by: Hsin-Wei Hung Co-developed-by: Hsin-Wei Hung Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20230911132815.717240-1-toke@redhat.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/queue_stack_maps.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8a5e060de63b..a8fe640318c6 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -102,7 +102,12 @@ static int __queue_map_get(struct bpf_map *map, void *value, bool delete) int err = 0; void *ptr; - raw_spin_lock_irqsave(&qs->lock, flags); + if (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, flags); + } if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -132,7 +137,12 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete) void *ptr; u32 index; - raw_spin_lock_irqsave(&qs->lock, flags); + if (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, flags); + } if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -197,7 +207,12 @@ static int queue_stack_map_push_elem(struct bpf_map *map, void *value, if (flags & BPF_NOEXIST || flags > BPF_EXIST) return -EINVAL; - raw_spin_lock_irqsave(&qs->lock, irq_flags); + if (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, irq_flags); + } if (queue_stack_map_is_full(qs)) { if (!replace) { From 293e4920f7154972e58349c92a003eaa342fad50 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 12 Sep 2023 13:32:40 +0200 Subject: [PATCH 1681/2093] ASoC: rt5640: Revert "Fix sleep in atomic context" [ Upstream commit fa6a0c0c1dd53b3949ca56bf7213648dfd6a62ee ] Commit 70a6404ff610 ("ASoC: rt5640: Fix sleep in atomic context") not only switched from request_irq() to request_threaded_irq(), to fix the sleep in atomic context issue, but it also added devm management of the IRQ by actually switching to devm_request_threaded_irq() (without any explanation in the commit message for this change). This is wrong since the IRQ was already explicitly managed by the driver. On unbind the ASoC core will call rt5640_set_jack(NULL) which in turn will call rt5640_disable_jack_detect() which frees the IRQ already. So now we have a double free. Besides the unexplained switch to devm being wrong, the actual fix for the sleep in atomic context issue also is not the best solution. The only thing which rt5640_irq() does is cancel + (re-)queue the jack_work delayed_work. This can be done in a single non sleeping call by replacing queue_delayed_work() with mod_delayed_work(), which does not sleep. Using mod_delayed_work() is a much better fix then adding a thread which does nothing other then queuing a work-item. This patch is a straight revert of the troublesome changes, the switch to mod_delayed_work() is done in a separate follow-up patch. Fixes: 70a6404ff610 ("ASoC: rt5640: Fix sleep in atomic context") Cc: Sameer Pujar Cc: Oder Chiou Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230912113245.320159-2-hdegoede@redhat.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt5640.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index a7071d0a2562..0f8e6dd214b0 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2562,10 +2562,9 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component, if (jack_data && jack_data->use_platform_clock) rt5640->use_platform_clock = jack_data->use_platform_clock; - ret = devm_request_threaded_irq(component->dev, rt5640->irq, - NULL, rt5640_irq, - IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - "rt5640", rt5640); + ret = request_irq(rt5640->irq, rt5640_irq, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "rt5640", rt5640); if (ret) { dev_warn(component->dev, "Failed to reguest IRQ %d: %d\n", rt5640->irq, ret); rt5640_disable_jack_detect(component); @@ -2618,9 +2617,8 @@ static void rt5640_enable_hda_jack_detect( rt5640->jack = jack; - ret = devm_request_threaded_irq(component->dev, rt5640->irq, - NULL, rt5640_irq, IRQF_TRIGGER_RISING | IRQF_ONESHOT, - "rt5640", rt5640); + ret = request_irq(rt5640->irq, rt5640_irq, + IRQF_TRIGGER_RISING | IRQF_ONESHOT, "rt5640", rt5640); if (ret) { dev_warn(component->dev, "Failed to reguest IRQ %d: %d\n", rt5640->irq, ret); rt5640->irq = -ENXIO; From 1698854b03a5190a44712ca827ed9c5b5793d090 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 12 Sep 2023 13:32:44 +0200 Subject: [PATCH 1682/2093] ASoC: rt5640: Fix IRQ not being free-ed for HDA jack detect mode [ Upstream commit 8c8bf3df6b7c0ed1c4dd373b23eb0ce13a63f452 ] Set "rt5640->irq_requested = true" after a successful request_irq() in rt5640_enable_hda_jack_detect(), so that rt5640_disable_jack_detect() properly frees the IRQ. This fixes the IRQ not being freed on rmmod / driver unbind. Fixes: 2b9c8d2b3c89 ("ASoC: rt5640: Add the HDA header support") Cc: Oder Chiou Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230912113245.320159-6-hdegoede@redhat.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt5640.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 0f8e6dd214b0..37ea4d854cb5 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2624,6 +2624,7 @@ static void rt5640_enable_hda_jack_detect( rt5640->irq = -ENXIO; return; } + rt5640->irq_requested = true; /* sync initial jack state */ queue_delayed_work(system_long_wq, &rt5640->jack_work, 0); From 09424e88126e254bec6c61ce58de51e67f53c6b7 Mon Sep 17 00:00:00 2001 From: Knyazev Arseniy Date: Wed, 13 Sep 2023 10:33:43 +0500 Subject: [PATCH 1683/2093] ALSA: hda/realtek: Splitting the UX3402 into two separate models [ Upstream commit 07058dceb038a4b0dd49af07118b6b2a685bb4a6 ] UX3402VA and UX3402ZA models require different hex values, so comibining them into one model is incorrect. Fixes: 491a4ccd8a02 ("ALSA: hda/realtek: Add quirk for ASUS Zenbook using CS35L41") Signed-off-by: Knyazev Arseniy Link: https://lore.kernel.org/r/20230913053343.119798-1-poseaydone@ya.ru Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f70e0ad81607..57e07aa4e136 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9657,7 +9657,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), - SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), From f5a75b3d31d3a99ec7b7f8809d177d6fd5a81352 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 12 Sep 2023 10:56:07 +0200 Subject: [PATCH 1684/2093] netfilter: conntrack: fix extension size table [ Upstream commit 4908d5af16676b9d2901830551c2af911e452524 ] The size table is incorrect due to copypaste error, this reserves more size than needed. TSTAMP reserved 32 instead of 16 bytes. TIMEOUT reserved 16 instead of 8 bytes. Fixes: 5f31edc0676b ("netfilter: conntrack: move extension sizes into core") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_extend.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 0b513f7bf9f3..dd62cc12e775 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -40,10 +40,10 @@ static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = { [NF_CT_EXT_ECACHE] = sizeof(struct nf_conntrack_ecache), #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP - [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_acct), + [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_tstamp), #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT - [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_tstamp), + [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_timeout), #endif #ifdef CONFIG_NF_CONNTRACK_LABELS [NF_CT_EXT_LABELS] = sizeof(struct nf_conn_labels), From bf560c8a83cacdab01056db47eba74d162d19e48 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 12 Sep 2023 16:16:25 +0200 Subject: [PATCH 1685/2093] selftests: tls: swap the TX and RX sockets in some tests [ Upstream commit c326ca98446e0ae4fee43a40acf79412b74cfedb ] tls.sendmsg_large and tls.sendmsg_multiple are trying to send through the self->cfd socket (only configured with TLS_RX) and to receive through the self->fd socket (only configured with TLS_TX), so they're not using kTLS at all. Swap the sockets. Fixes: 7f657d5bf507 ("selftests: tls: add selftests for TLS sockets") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- tools/testing/selftests/net/tls.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index c0ad8385441f..5b80fb155d54 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -551,11 +551,11 @@ TEST_F(tls, sendmsg_large) msg.msg_iov = &vec; msg.msg_iovlen = 1; - EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len); + EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); } while (recvs++ < sends) { - EXPECT_NE(recv(self->fd, mem, send_len, 0), -1); + EXPECT_NE(recv(self->cfd, mem, send_len, 0), -1); } free(mem); @@ -584,9 +584,9 @@ TEST_F(tls, sendmsg_multiple) msg.msg_iov = vec; msg.msg_iovlen = iov_len; - EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len); + EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len); buf = malloc(total_len); - EXPECT_NE(recv(self->fd, buf, total_len, 0), -1); + EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1); for (i = 0; i < iov_len; i++) { EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp, strlen(test_strs[i])), From 488ea2a3e2666022f79abfdd7d12e8305fc27a40 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Wed, 13 Sep 2023 09:39:05 +0300 Subject: [PATCH 1686/2093] net/core: Fix ETH_P_1588 flow dissector [ Upstream commit 75ad80ed88a182ab2ad5513e448cf07b403af5c3 ] When a PTP ethernet raw frame with a size of more than 256 bytes followed by a 0xff pattern is sent to __skb_flow_dissect, nhoff value calculation is wrong. For example: hdr->message_length takes the wrong value (0xffff) and it does not replicate real header length. In this case, 'nhoff' value was overridden and the PTP header was badly dissected. This leads to a kernel crash. net/core: flow_dissector net/core flow dissector nhoff = 0x0000000e net/core flow dissector hdr->message_length = 0x0000ffff net/core flow dissector nhoff = 0x0001000d (u16 overflow) ... skb linear: 00000000: 00 a0 c9 00 00 00 00 a0 c9 00 00 00 88 skb frag: 00000000: f7 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Using the size of the ptp_header struct will allow the corrected calculation of the nhoff value. net/core flow dissector nhoff = 0x0000000e net/core flow dissector nhoff = 0x00000030 (sizeof ptp_header) ... skb linear: 00000000: 00 a0 c9 00 00 00 00 a0 c9 00 00 00 88 f7 ff ff skb linear: 00000010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff skb linear: 00000020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff skb frag: 00000000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Kernel trace: [ 74.984279] ------------[ cut here ]------------ [ 74.989471] kernel BUG at include/linux/skbuff.h:2440! [ 74.995237] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [ 75.001098] CPU: 4 PID: 0 Comm: swapper/4 Tainted: G U 5.15.85-intel-ese-standard-lts #1 [ 75.011629] Hardware name: Intel Corporation A-Island (CPU:AlderLake)/A-Island (ID:06), BIOS SB_ADLP.01.01.00.01.03.008.D-6A9D9E73-dirty Mar 30 2023 [ 75.026507] RIP: 0010:eth_type_trans+0xd0/0x130 [ 75.031594] Code: 03 88 47 78 eb c7 8b 47 68 2b 47 6c 48 8b 97 c0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb ab <0f> 0b b8 00 01 00 00 eb a2 48 85 ff 74 eb 48 8d 54 24 06 31 f6 b9 [ 75.052612] RSP: 0018:ffff9948c0228de0 EFLAGS: 00010297 [ 75.058473] RAX: 00000000000003f2 RBX: ffff8e47047dc300 RCX: 0000000000001003 [ 75.066462] RDX: ffff8e4e8c9ea040 RSI: ffff8e4704e0a000 RDI: ffff8e47047dc300 [ 75.074458] RBP: ffff8e4704e2acc0 R08: 00000000000003f3 R09: 0000000000000800 [ 75.082466] R10: 000000000000000d R11: ffff9948c0228dec R12: ffff8e4715e4e010 [ 75.090461] R13: ffff9948c0545018 R14: 0000000000000001 R15: 0000000000000800 [ 75.098464] FS: 0000000000000000(0000) GS:ffff8e4e8fb00000(0000) knlGS:0000000000000000 [ 75.107530] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 75.113982] CR2: 00007f5eb35934a0 CR3: 0000000150e0a002 CR4: 0000000000770ee0 [ 75.121980] PKRU: 55555554 [ 75.125035] Call Trace: [ 75.127792] [ 75.130063] ? eth_get_headlen+0xa4/0xc0 [ 75.134472] igc_process_skb_fields+0xcd/0x150 [ 75.139461] igc_poll+0xc80/0x17b0 [ 75.143272] __napi_poll+0x27/0x170 [ 75.147192] net_rx_action+0x234/0x280 [ 75.151409] __do_softirq+0xef/0x2f4 [ 75.155424] irq_exit_rcu+0xc7/0x110 [ 75.159432] common_interrupt+0xb8/0xd0 [ 75.163748] [ 75.166112] [ 75.168473] asm_common_interrupt+0x22/0x40 [ 75.173175] RIP: 0010:cpuidle_enter_state+0xe2/0x350 [ 75.178749] Code: 85 c0 0f 8f 04 02 00 00 31 ff e8 39 6c 67 ff 45 84 ff 74 12 9c 58 f6 c4 02 0f 85 50 02 00 00 31 ff e8 52 b0 6d ff fb 45 85 f6 <0f> 88 b1 00 00 00 49 63 ce 4c 2b 2c 24 48 89 c8 48 6b d1 68 48 c1 [ 75.199757] RSP: 0018:ffff9948c013bea8 EFLAGS: 00000202 [ 75.205614] RAX: ffff8e4e8fb00000 RBX: ffffb948bfd23900 RCX: 000000000000001f [ 75.213619] RDX: 0000000000000004 RSI: ffffffff94206161 RDI: ffffffff94212e20 [ 75.221620] RBP: 0000000000000004 R08: 000000117568973a R09: 0000000000000001 [ 75.229622] R10: 000000000000afc8 R11: ffff8e4e8fb29ce4 R12: ffffffff945ae980 [ 75.237628] R13: 000000117568973a R14: 0000000000000004 R15: 0000000000000000 [ 75.245635] ? cpuidle_enter_state+0xc7/0x350 [ 75.250518] cpuidle_enter+0x29/0x40 [ 75.254539] do_idle+0x1d9/0x260 [ 75.258166] cpu_startup_entry+0x19/0x20 [ 75.262582] secondary_startup_64_no_verify+0xc2/0xcb [ 75.268259] [ 75.270721] Modules linked in: 8021q snd_sof_pci_intel_tgl snd_sof_intel_hda_common tpm_crb snd_soc_hdac_hda snd_sof_intel_hda snd_hda_ext_core snd_sof_pci snd_sof snd_sof_xtensa_dsp snd_soc_acpi_intel_match snd_soc_acpi snd_soc_core snd_compress iTCO_wdt ac97_bus intel_pmc_bxt mei_hdcp iTCO_vendor_support snd_hda_codec_hdmi pmt_telemetry intel_pmc_core pmt_class snd_hda_intel x86_pkg_temp_thermal snd_intel_dspcfg snd_hda_codec snd_hda_core kvm_intel snd_pcm snd_timer kvm snd mei_me soundcore tpm_tis irqbypass i2c_i801 mei tpm_tis_core pcspkr intel_rapl_msr tpm i2c_smbus intel_pmt thermal sch_fq_codel uio uhid i915 drm_buddy video drm_display_helper drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm fuse configfs [ 75.342736] ---[ end trace 3785f9f360400e3a ]--- [ 75.347913] RIP: 0010:eth_type_trans+0xd0/0x130 [ 75.352984] Code: 03 88 47 78 eb c7 8b 47 68 2b 47 6c 48 8b 97 c0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb ab <0f> 0b b8 00 01 00 00 eb a2 48 85 ff 74 eb 48 8d 54 24 06 31 f6 b9 [ 75.373994] RSP: 0018:ffff9948c0228de0 EFLAGS: 00010297 [ 75.379860] RAX: 00000000000003f2 RBX: ffff8e47047dc300 RCX: 0000000000001003 [ 75.387856] RDX: ffff8e4e8c9ea040 RSI: ffff8e4704e0a000 RDI: ffff8e47047dc300 [ 75.395864] RBP: ffff8e4704e2acc0 R08: 00000000000003f3 R09: 0000000000000800 [ 75.403857] R10: 000000000000000d R11: ffff9948c0228dec R12: ffff8e4715e4e010 [ 75.411863] R13: ffff9948c0545018 R14: 0000000000000001 R15: 0000000000000800 [ 75.419875] FS: 0000000000000000(0000) GS:ffff8e4e8fb00000(0000) knlGS:0000000000000000 [ 75.428946] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 75.435403] CR2: 00007f5eb35934a0 CR3: 0000000150e0a002 CR4: 0000000000770ee0 [ 75.443410] PKRU: 55555554 [ 75.446477] Kernel panic - not syncing: Fatal exception in interrupt [ 75.453738] Kernel Offset: 0x11c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 75.465794] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fixes: 4f1cc51f3488 ("net: flow_dissector: Parse PTP L2 packet header") Signed-off-by: Sasha Neftin Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/flow_dissector.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3288490590f2..0c85c8a9e752 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1366,7 +1366,7 @@ bool __skb_flow_dissect(const struct net *net, break; } - nhoff += ntohs(hdr->message_length); + nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } From ee79256b161513e6da8d76253d44a06319af9d99 Mon Sep 17 00:00:00 2001 From: Chen Ni Date: Fri, 15 Sep 2023 02:13:44 +0000 Subject: [PATCH 1687/2093] ASoC: hdaudio.c: Add missing check for devm_kstrdup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c04efbfd76d23157e64e6d6147518c187ab4233a ] Because of the potential failure of the devm_kstrdup(), the dl[i].codecs->name could be NULL. Therefore, we need to check it and return -ENOMEM in order to transfer the error. Fixes: 97030a43371e ("ASoC: Intel: avs: Add HDAudio machine board") Signed-off-by: Chen Ni Reviewed-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20230915021344.3078-1-nichen@iscas.ac.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/avs/boards/hdaudio.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/intel/avs/boards/hdaudio.c b/sound/soc/intel/avs/boards/hdaudio.c index 073663ba140d..a65939f30ac4 100644 --- a/sound/soc/intel/avs/boards/hdaudio.c +++ b/sound/soc/intel/avs/boards/hdaudio.c @@ -54,6 +54,9 @@ static int avs_create_dai_links(struct device *dev, struct hda_codec *codec, int return -ENOMEM; dl[i].codecs->name = devm_kstrdup(dev, cname, GFP_KERNEL); + if (!dl[i].codecs->name) + return -ENOMEM; + dl[i].codecs->dai_name = pcm->name; dl[i].num_codecs = 1; dl[i].num_cpus = 1; From 66823a9025bcc7f5ba70df051cc0e40355966b3d Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Fri, 15 Sep 2023 14:02:11 +0800 Subject: [PATCH 1688/2093] ASoC: imx-audmix: Fix return error with devm_clk_get() [ Upstream commit b19a5733de255cabba5feecabf6e900638b582d1 ] The devm_clk_get() can return -EPROBE_DEFER error, modify the error code to be -EINVAL is not correct, which cause the -EPROBE_DEFER error is not correctly handled. This patch is to fix the return error code. Fixes: b86ef5367761 ("ASoC: fsl: Add Audio Mixer machine driver") Signed-off-by: Shengjiu Wang Reviewed-by: Daniel Baluta Link: https://lore.kernel.org/r/1694757731-18308-1-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/imx-audmix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index d8e99b263ab2..cbe24d5b4e46 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -320,7 +320,7 @@ static int imx_audmix_probe(struct platform_device *pdev) if (IS_ERR(priv->cpu_mclk)) { ret = PTR_ERR(priv->cpu_mclk); dev_err(&cpu_pdev->dev, "failed to get DAI mclk1: %d\n", ret); - return -EINVAL; + return ret; } priv->audmix_pdev = audmix_pdev; From 65976385d49fcfbc72866957a4a1d09b4c698f7a Mon Sep 17 00:00:00 2001 From: Shinas Rasheed Date: Wed, 13 Sep 2023 01:41:56 -0700 Subject: [PATCH 1689/2093] octeon_ep: fix tx dma unmap len values in SG [ Upstream commit 350db8a59eb392bf42e62b6b2a37d56b5833012b ] Lengths of SG pointers are kept in the following order in the SG entries in hardware. 63 48|47 32|31 16|15 0 ----------------------------------------- | Len 0 | Len 1 | Len 2 | Len 3 | ----------------------------------------- | Ptr 0 | ----------------------------------------- | Ptr 1 | ----------------------------------------- | Ptr 2 | ----------------------------------------- | Ptr 3 | ----------------------------------------- Dma pointers have to be unmapped based on their respective lengths given in this format. Fixes: 37d79d059606 ("octeon_ep: add Tx/Rx processing and interrupt support") Signed-off-by: Shinas Rasheed Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../net/ethernet/marvell/octeon_ep/octep_main.c | 8 ++++---- .../net/ethernet/marvell/octeon_ep/octep_tx.c | 8 ++++---- .../net/ethernet/marvell/octeon_ep/octep_tx.h | 16 +++++++++++++++- 3 files changed, 23 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index d4ec46d1c8cf..61354f798503 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -726,13 +726,13 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb, dma_map_sg_err: if (si > 0) { dma_unmap_single(iq->dev, sglist[0].dma_ptr[0], - sglist[0].len[0], DMA_TO_DEVICE); - sglist[0].len[0] = 0; + sglist[0].len[3], DMA_TO_DEVICE); + sglist[0].len[3] = 0; } while (si > 1) { dma_unmap_page(iq->dev, sglist[si >> 2].dma_ptr[si & 3], - sglist[si >> 2].len[si & 3], DMA_TO_DEVICE); - sglist[si >> 2].len[si & 3] = 0; + sglist[si >> 2].len[3 - (si & 3)], DMA_TO_DEVICE); + sglist[si >> 2].len[3 - (si & 3)] = 0; si--; } tx_buffer->gather = 0; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c index 5a520d37bea0..d0adb82d65c3 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c @@ -69,12 +69,12 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget) compl_sg++; dma_unmap_single(iq->dev, tx_buffer->sglist[0].dma_ptr[0], - tx_buffer->sglist[0].len[0], DMA_TO_DEVICE); + tx_buffer->sglist[0].len[3], DMA_TO_DEVICE); i = 1; /* entry 0 is main skb, unmapped above */ while (frags--) { dma_unmap_page(iq->dev, tx_buffer->sglist[i >> 2].dma_ptr[i & 3], - tx_buffer->sglist[i >> 2].len[i & 3], DMA_TO_DEVICE); + tx_buffer->sglist[i >> 2].len[3 - (i & 3)], DMA_TO_DEVICE); i++; } @@ -131,13 +131,13 @@ static void octep_iq_free_pending(struct octep_iq *iq) dma_unmap_single(iq->dev, tx_buffer->sglist[0].dma_ptr[0], - tx_buffer->sglist[0].len[0], + tx_buffer->sglist[0].len[3], DMA_TO_DEVICE); i = 1; /* entry 0 is main skb, unmapped above */ while (frags--) { dma_unmap_page(iq->dev, tx_buffer->sglist[i >> 2].dma_ptr[i & 3], - tx_buffer->sglist[i >> 2].len[i & 3], DMA_TO_DEVICE); + tx_buffer->sglist[i >> 2].len[3 - (i & 3)], DMA_TO_DEVICE); i++; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h index 2ef57980eb47..21e75ff9f5e7 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h @@ -17,7 +17,21 @@ #define TX_BUFTYPE_NET_SG 2 #define NUM_TX_BUFTYPES 3 -/* Hardware format for Scatter/Gather list */ +/* Hardware format for Scatter/Gather list + * + * 63 48|47 32|31 16|15 0 + * ----------------------------------------- + * | Len 0 | Len 1 | Len 2 | Len 3 | + * ----------------------------------------- + * | Ptr 0 | + * ----------------------------------------- + * | Ptr 1 | + * ----------------------------------------- + * | Ptr 2 | + * ----------------------------------------- + * | Ptr 3 | + * ----------------------------------------- + */ struct octep_tx_sglist_desc { u16 len[4]; dma_addr_t dma_ptr[4]; From 211aac2ef6fffab208df8cc386f997dca8c2b85a Mon Sep 17 00:00:00 2001 From: Radoslaw Tyl Date: Mon, 7 Aug 2023 14:59:40 +0200 Subject: [PATCH 1690/2093] iavf: do not process adminq tasks when __IAVF_IN_REMOVE_TASK is set [ Upstream commit c8de44b577eb540e8bfea55afe1d0904bb571b7a ] Prevent schedule operations for adminq during device remove and when __IAVF_IN_REMOVE_TASK flag is set. Currently, the iavf_down function adds operations for adminq that shouldn't be processed when the device is in the __IAVF_REMOVE state. Reproduction: echo 4 > /sys/bus/pci/devices/0000:17:00.0/sriov_numvfs ip link set dev ens1f0 vf 0 trust on ip link set dev ens1f0 vf 1 trust on ip link set dev ens1f0 vf 2 trust on ip link set dev ens1f0 vf 3 trust on ip link set dev ens1f0 vf 0 mac 00:22:33:44:55:66 ip link set dev ens1f0 vf 1 mac 00:22:33:44:55:67 ip link set dev ens1f0 vf 2 mac 00:22:33:44:55:68 ip link set dev ens1f0 vf 3 mac 00:22:33:44:55:69 echo 0000:17:02.0 > /sys/bus/pci/devices/0000\:17\:02.0/driver/unbind echo 0000:17:02.1 > /sys/bus/pci/devices/0000\:17\:02.1/driver/unbind echo 0000:17:02.2 > /sys/bus/pci/devices/0000\:17\:02.2/driver/unbind echo 0000:17:02.3 > /sys/bus/pci/devices/0000\:17\:02.3/driver/unbind sleep 10 echo 0000:17:02.0 > /sys/bus/pci/drivers/iavf/bind echo 0000:17:02.1 > /sys/bus/pci/drivers/iavf/bind echo 0000:17:02.2 > /sys/bus/pci/drivers/iavf/bind echo 0000:17:02.3 > /sys/bus/pci/drivers/iavf/bind modprobe vfio-pci echo 8086 154c > /sys/bus/pci/drivers/vfio-pci/new_id qemu-system-x86_64 -accel kvm -m 4096 -cpu host \ -drive file=centos9.qcow2,if=none,id=virtio-disk0 \ -device virtio-blk-pci,drive=virtio-disk0,bootindex=0 -smp 4 \ -device vfio-pci,host=17:02.0 -net none \ -device vfio-pci,host=17:02.1 -net none \ -device vfio-pci,host=17:02.2 -net none \ -device vfio-pci,host=17:02.3 -net none \ -daemonize -vnc :5 Current result: There is a probability that the mac of VF in guest is inconsistent with it in host Expected result: When passthrough NIC VF to guest, the VF in guest should always get the same mac as it in host. Fixes: 14756b2ae265 ("iavf: Fix __IAVF_RESETTING state usage") Signed-off-by: Radoslaw Tyl Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 22bc57ee2422..a02e8d6a4d1d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1433,7 +1433,8 @@ void iavf_down(struct iavf_adapter *adapter) iavf_clear_fdir_filters(adapter); iavf_clear_adv_rss_conf(adapter); - if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && + !(test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait From 16fd3c37d1cabdab3d5f6398787dad6822adcee2 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 15 Sep 2023 15:40:15 +0300 Subject: [PATCH 1691/2093] ASoC: SOF: core: Only call sof_ops_free() on remove if the probe was successful [ Upstream commit 31bb7bd9ffee50d09ec931998b823a86132ab807 ] All the fail paths during probe will free up the ops, on remove we should only free it if the probe was successful. Fixes: bc433fd76fae ("ASoC: SOF: Add ops_free") Signed-off-by: Peter Ujfalusi Reviewed-by: Bard Liao Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Rander Wang Link: https://lore.kernel.org/r/20230915124015.19637-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 75a1e2c6539f..eaa16755a270 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -461,10 +461,9 @@ int snd_sof_device_remove(struct device *dev) snd_sof_ipc_free(sdev); snd_sof_free_debug(sdev); snd_sof_remove(sdev); + sof_ops_free(sdev); } - sof_ops_free(sdev); - /* release firmware */ snd_sof_fw_unload(sdev); From 00bbedbd7c5ab55c5a9731fcffeac0654c6d0a6e Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Thu, 7 Sep 2023 17:02:50 +0200 Subject: [PATCH 1692/2093] iavf: add iavf_schedule_aq_request() helper [ Upstream commit ed4cad33df9e272feaa6698b33359b29c2929564 ] Add helper for set iavf aq request AVF_FLAG_AQ_* and immediately schedule watchdog_task. Helper will be used in cases where it is necessary to run aq requests asap Signed-off-by: Petr Oros Co-developed-by: Michal Schmidt Signed-off-by: Michal Schmidt Co-developed-by: Ivan Vecera Signed-off-by: Ivan Vecera Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Stable-dep-of: 5f3d319a2486 ("iavf: schedule a request immediately after add/delete vlan") Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 2 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 10 ++++------ 3 files changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 543931c06bb1..06cfd567866c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -521,7 +521,7 @@ void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); -void iavf_schedule_request_stats(struct iavf_adapter *adapter); +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_finish_config(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index fe912b1c468e..c13b4fa659ee 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -362,7 +362,7 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, unsigned int i; /* Explicitly request stats refresh */ - iavf_schedule_request_stats(adapter); + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_REQUEST_STATS); iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index a02e8d6a4d1d..ee04670b77b3 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -322,15 +322,13 @@ void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) } /** - * iavf_schedule_request_stats - Set the flags and schedule statistics request + * iavf_schedule_aq_request - Set the flags and schedule aq request * @adapter: board private structure - * - * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly - * request and refresh ethtool stats + * @flags: requested aq flags **/ -void iavf_schedule_request_stats(struct iavf_adapter *adapter) +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags) { - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + adapter->aq_required |= flags; mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } From 0546cd573404d86ed53f07bed1a072dc2e808430 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Thu, 7 Sep 2023 17:02:51 +0200 Subject: [PATCH 1693/2093] iavf: schedule a request immediately after add/delete vlan [ Upstream commit 5f3d319a248654a805bafc9e7094bcea47dac6c7 ] When the iavf driver wants to reconfigure the VLAN filters (iavf_add_vlan, iavf_del_vlan), it sets a flag in aq_required: adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; or: adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; This is later processed by the watchdog_task, but it runs periodically every 2 seconds, so it can be a long time before it processes the request. In the worst case, the interface is unable to receive traffic for more than 2 seconds for no objective reason. Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Petr Oros Co-developed-by: Michal Schmidt Signed-off-by: Michal Schmidt Co-developed-by: Ivan Vecera Signed-off-by: Ivan Vecera Reviewed-by: Ahmed Zaki Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index ee04670b77b3..a39f7f0d6ab0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -829,7 +829,7 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, list_add_tail(&f->list, &adapter->vlan_filter_list); f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); } clearout: @@ -851,7 +851,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { f->state = IAVF_VLAN_REMOVE; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); } spin_unlock_bh(&adapter->mac_vlan_list_lock); From d98bad2998fdcb8b1907d3c32fbdf77bb03c840e Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 7 Sep 2023 17:44:57 +0200 Subject: [PATCH 1694/2093] i40e: Fix VF VLAN offloading when port VLAN is configured [ Upstream commit d0d362ffa33da4acdcf7aee2116ceef8c8fef658 ] If port VLAN is configured on a VF then any other VLANs on top of this VF are broken. During i40e_ndo_set_vf_port_vlan() call the i40e driver reset the VF and iavf driver asks PF (using VIRTCHNL_OP_GET_VF_RESOURCES) for VF capabilities but this reset occurs too early, prior setting of vf->info.pvid field and because this field can be zero during i40e_vc_get_vf_resources_msg() then VIRTCHNL_VF_OFFLOAD_VLAN capability is reported to iavf driver. This is wrong because iavf driver should not report VLAN offloading capability when port VLAN is configured as i40e does not support QinQ offloading. Fix the issue by moving VF reset after setting of vf->port_vlan_id field. Without this patch: $ echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs $ ip link set enp2s0f0 vf 0 vlan 3 $ ip link set enp2s0f0v0 up $ ip link add link enp2s0f0v0 name vlan4 type vlan id 4 $ ip link set vlan4 up ... $ ethtool -k enp2s0f0v0 | grep vlan-offload rx-vlan-offload: on tx-vlan-offload: on $ dmesg -l err | grep iavf [1292500.742914] iavf 0000:02:02.0: Failed to add VLAN filter, error IAVF_ERR_INVALID_QP_ID With this patch: $ echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs $ ip link set enp2s0f0 vf 0 vlan 3 $ ip link set enp2s0f0v0 up $ ip link add link enp2s0f0v0 name vlan4 type vlan id 4 $ ip link set vlan4 up ... $ ethtool -k enp2s0f0v0 | grep vlan-offload rx-vlan-offload: off [requested on] tx-vlan-offload: off [requested on] $ dmesg -l err | grep iavf Fixes: f9b4b6278d51 ("i40e: Reset the VF upon conflicting VLAN configuration") Signed-off-by: Ivan Vecera Reviewed-by: Jesse Brandeburg Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index cb7cf672f697..547e67d9470b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4397,9 +4397,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, goto error_pvid; i40e_vlan_stripping_enable(vsi); - i40e_vc_reset_vf(vf, true); - /* During reset the VF got a new VSI, so refresh a pointer. */ - vsi = pf->vsi[vf->lan_vsi_idx]; + /* Locked once because multiple functions below iterate list */ spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -4485,6 +4483,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, */ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; + ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni); if (ret) { dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n"); From f2c6e5945da5c63d4f3eaf5667b31342420aea77 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Wed, 30 Aug 2023 03:07:43 +0200 Subject: [PATCH 1695/2093] netfilter, bpf: Adjust timeouts of non-confirmed CTs in bpf_ct_insert_entry() [ Upstream commit 837723b22a63cfbff584655b009b9d488d0e9087 ] bpf_nf testcase fails on s390x: bpf_skb_ct_lookup() cannot find the entry that was added by bpf_ct_insert_entry() within the same BPF function. The reason is that this entry is deleted by nf_ct_gc_expired(). The CT timeout starts ticking after the CT confirmation; therefore nf_conn.timeout is initially set to the timeout value, and __nf_conntrack_confirm() sets it to the deadline value. bpf_ct_insert_entry() sets IPS_CONFIRMED_BIT, but does not adjust the timeout, making its value meaningless and causing false positives. Fix the problem by making bpf_ct_insert_entry() adjust the timeout, like __nf_conntrack_confirm(). Fixes: 2cdaa3eefed8 ("netfilter: conntrack: restore IPS_CONFIRMED out of nf_conntrack_hash_check_insert()") Signed-off-by: Ilya Leoshkevich Signed-off-by: Daniel Borkmann Cc: Florian Westphal Link: https://lore.kernel.org/bpf/20230830011128.1415752-3-iii@linux.ibm.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_bpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 8639e7efd0e2..816283f0aa59 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -384,6 +384,8 @@ struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; + if (!nf_ct_is_confirmed(nfct)) + nfct->timeout += nfct_time_stamp; nfct->status |= IPS_CONFIRMED; err = nf_conntrack_hash_check_insert(nfct); if (err < 0) { From 40b5032c99519777ad4e04ce3814842e135622a5 Mon Sep 17 00:00:00 2001 From: David Christensen Date: Thu, 14 Sep 2023 18:02:52 -0400 Subject: [PATCH 1696/2093] ionic: fix 16bit math issue when PAGE_SIZE >= 64KB [ Upstream commit 8f6b846b0a86c3cbae8a25b772651cfc2270ad0a ] The ionic device supports a maximum buffer length of 16 bits (see ionic_rxq_desc or ionic_rxq_sg_elem). When adding new buffers to the receive rings, the function ionic_rx_fill() uses 16bit math when calculating the number of pages to allocate for an RX descriptor, given the interface's MTU setting. If the system PAGE_SIZE >= 64KB, and the buf_info->page_offset is 0, the remain_len value will never decrement from the original MTU value and the frag_len value will always be 0, causing additional pages to be allocated as scatter- gather elements unnecessarily. A similar math issue exists in ionic_rx_frags(), but no failures have been observed here since a 64KB page should not normally require any scatter-gather elements at any legal Ethernet MTU size. Fixes: 4b0a7539a372 ("ionic: implement Rx page reuse") Signed-off-by: David Christensen Reviewed-by: Shannon Nelson Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/pensando/ionic/ionic_dev.h | 1 + drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 10 +++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index ad8a2a4453b7..93a425842166 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -180,6 +180,7 @@ typedef void (*ionic_desc_cb)(struct ionic_queue *q, struct ionic_desc_info *desc_info, struct ionic_cq_info *cq_info, void *cb_arg); +#define IONIC_MAX_BUF_LEN ((u16)-1) #define IONIC_PAGE_SIZE PAGE_SIZE #define IONIC_PAGE_SPLIT_SZ (PAGE_SIZE / 2) #define IONIC_PAGE_GFP_MASK (GFP_ATOMIC | __GFP_NOWARN |\ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index f8f5eb130768..4684b9f194a6 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -207,7 +207,8 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q, return NULL; } - frag_len = min_t(u16, len, IONIC_PAGE_SIZE - buf_info->page_offset); + frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN, + IONIC_PAGE_SIZE - buf_info->page_offset)); len -= frag_len; dma_sync_single_for_cpu(dev, @@ -444,7 +445,8 @@ void ionic_rx_fill(struct ionic_queue *q) /* fill main descriptor - buf[0] */ desc->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset); - frag_len = min_t(u16, len, IONIC_PAGE_SIZE - buf_info->page_offset); + frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN, + IONIC_PAGE_SIZE - buf_info->page_offset)); desc->len = cpu_to_le16(frag_len); remain_len -= frag_len; buf_info++; @@ -463,7 +465,9 @@ void ionic_rx_fill(struct ionic_queue *q) } sg_elem->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset); - frag_len = min_t(u16, remain_len, IONIC_PAGE_SIZE - buf_info->page_offset); + frag_len = min_t(u16, remain_len, min_t(u32, IONIC_MAX_BUF_LEN, + IONIC_PAGE_SIZE - + buf_info->page_offset)); sg_elem->len = cpu_to_le16(frag_len); remain_len -= frag_len; buf_info++; From 54228157fb57757f832fd1ac3d13b01a9108d7a7 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 13 Sep 2023 11:06:15 -0700 Subject: [PATCH 1697/2093] igc: Fix infinite initialization loop with early XDP redirect [ Upstream commit cb47b1f679c4d83a5fa5f1852e472f844e41a3da ] When an XDP redirect happens before the link is ready, that transmission will not finish and will timeout, causing an adapter reset. If the redirects do not stop, the adapter will not stop resetting. Wait for the driver to signal that there's a carrier before allowing transmissions to proceed. Previous code was relying that when __IGC_DOWN is cleared, the NIC is ready to transmit as all the queues are ready, what happens is that the carrier presence will only be signaled later, after the watchdog workqueue has a chance to run. And during this interval (between clearing __IGC_DOWN and the watchdog running) if any transmission happens the timeout is emitted (detected by igc_tx_timeout()) which causes the reset, with the potential for the infinite loop. Fixes: 4ff320361092 ("igc: Add support for XDP_REDIRECT action") Reported-by: Ferenc Fejes Closes: https://lore.kernel.org/netdev/0caf33cf6adb3a5bf137eeaa20e89b167c9986d5.camel@ericsson.com/ Signed-off-by: Vinicius Costa Gomes Tested-by: Ferenc Fejes Reviewed-by: Maciej Fijalkowski Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 2f3947cf513b..1ac836a55cd3 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6322,7 +6322,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, struct igc_ring *ring; int i, drops; - if (unlikely(test_bit(__IGC_DOWN, &adapter->state))) + if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) From 2712545e535d7a2e4c53b9c9658a9c88c6055862 Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Thu, 14 Sep 2023 22:12:57 -0700 Subject: [PATCH 1698/2093] ipv4: fix null-deref in ipv4_link_failure [ Upstream commit 0113d9c9d1ccc07f5a3710dac4aa24b6d711278c ] Currently, we assume the skb is associated with a device before calling __ip_options_compile, which is not always the case if it is re-routed by ipvs. When skb->dev is NULL, dev_net(skb->dev) will become null-dereference. This patch adds a check for the edge case and switch to use the net_device from the rtable when skb->dev is NULL. Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") Suggested-by: David Ahern Signed-off-by: Kyle Zeng Cc: Stephen Suryaputra Cc: Vadim Fedorenko Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/route.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a04ffc128e22..84a0a71a6f4e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) From 5734d22c9ea0a9d394b5e668c8e163bb3eaa3b95 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 17:11:11 +0000 Subject: [PATCH 1699/2093] scsi: iscsi_tcp: restrict to TCP sockets [ Upstream commit f4f82c52a0ead5ab363d207d06f81b967d09ffb8 ] Nothing prevents iscsi_sw_tcp_conn_bind() to receive file descriptor pointing to non TCP socket (af_unix for example). Return -EINVAL if this is attempted, instead of crashing the kernel. Fixes: 7ba247138907 ("[SCSI] open-iscsi/linux-iscsi-5 Initiator: Initiator code") Signed-off-by: Eric Dumazet Cc: Lee Duncan Cc: Chris Leech Cc: Mike Christie Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: open-iscsi@googlegroups.com Cc: linux-scsi@vger.kernel.org Reviewed-by: Mike Christie Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/scsi/iscsi_tcp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 8009eab3b7be..56ade4630970 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -724,6 +724,10 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session, return -EEXIST; } + err = -EINVAL; + if (!sk_is_tcp(sock->sk)) + goto free_socket; + err = iscsi_conn_bind(cls_session, cls_conn, is_leading); if (err) goto free_socket; From c2019f0a68169a344bda40b12180c4da08be21f2 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Aug 2023 11:26:01 +0530 Subject: [PATCH 1700/2093] powerpc/perf/hv-24x7: Update domain value check [ Upstream commit 4ff3ba4db5943cac1045e3e4a3c0463ea10f6930 ] Valid domain value is in range 1 to HV_PERF_DOMAIN_MAX. Current code has check for domain value greater than or equal to HV_PERF_DOMAIN_MAX. But the check for domain value 0 is missing. Fix this issue by adding check for domain value 0. Before: # ./perf stat -v -e hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ sleep 1 Using CPUID 00800200 Control descriptor is not initialized Error: The sys_perf_event_open() syscall returned with 5 (Input/output error) for event (hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/). /bin/dmesg | grep -i perf may provide additional information. Result from dmesg: [ 37.819387] hv-24x7: hcall failed: [0 0x60040000 0x100 0] => ret 0xfffffffffffffffc (-4) detail=0x2000000 failing ix=0 After: # ./perf stat -v -e hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ sleep 1 Using CPUID 00800200 Control descriptor is not initialized Warning: hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ event is not supported by the kernel. failed to read counter hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ Fixes: ebd4a5a3ebd9 ("powerpc/perf/hv-24x7: Minor improvements") Reported-by: Krishan Gopal Sarawast Signed-off-by: Kajol Jain Tested-by: Disha Goel Signed-off-by: Michael Ellerman Link: https://msgid.link/20230825055601.360083-1-kjain@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/perf/hv-24x7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 33c23225fd54..7dda59923ed6 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1431,7 +1431,7 @@ static int h_24x7_event_init(struct perf_event *event) } domain = event_get_domain(event); - if (domain >= HV_PERF_DOMAIN_MAX) { + if (domain == 0 || domain >= HV_PERF_DOMAIN_MAX) { pr_devel("invalid domain %d\n", domain); return -EINVAL; } From 73be49248a04746096339a48a33fa2f03bd85969 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 19:00:35 +0000 Subject: [PATCH 1701/2093] dccp: fix dccp_v4_err()/dccp_v6_err() again [ Upstream commit 6af289746a636f71f4c0535a9801774118486c7a ] dh->dccph_x is the 9th byte (offset 8) in "struct dccp_hdr", not in the "byte 7" as Jann claimed. We need to make sure the ICMP messages are big enough, using more standard ways (no more assumptions). syzbot reported: BUG: KMSAN: uninit-value in pskb_may_pull_reason include/linux/skbuff.h:2667 [inline] BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2681 [inline] BUG: KMSAN: uninit-value in dccp_v6_err+0x426/0x1aa0 net/dccp/ipv6.c:94 pskb_may_pull_reason include/linux/skbuff.h:2667 [inline] pskb_may_pull include/linux/skbuff.h:2681 [inline] dccp_v6_err+0x426/0x1aa0 net/dccp/ipv6.c:94 icmpv6_notify+0x4c7/0x880 net/ipv6/icmp.c:867 icmpv6_rcv+0x19d5/0x30d0 ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438 ip6_input_finish net/ipv6/ip6_input.c:483 [inline] NF_HOOK include/linux/netfilter.h:304 [inline] ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492 ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586 dst_input include/net/dst.h:468 [inline] ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:304 [inline] ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310 __netif_receive_skb_one_core net/core/dev.c:5523 [inline] __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5637 netif_receive_skb_internal net/core/dev.c:5723 [inline] netif_receive_skb+0x58/0x660 net/core/dev.c:5782 tun_rx_batched+0x83b/0x920 tun_get_user+0x564c/0x6940 drivers/net/tun.c:2002 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:1985 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x8ef/0x15c0 fs/read_write.c:584 ksys_write+0x20f/0x4c0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12f/0xb70 mm/slab.h:767 slab_alloc_node mm/slub.c:3478 [inline] kmem_cache_alloc_node+0x577/0xa80 mm/slub.c:3523 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:559 __alloc_skb+0x318/0x740 net/core/skbuff.c:650 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6313 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2795 tun_alloc_skb drivers/net/tun.c:1531 [inline] tun_get_user+0x23cf/0x6940 drivers/net/tun.c:1846 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:1985 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x8ef/0x15c0 fs/read_write.c:584 ksys_write+0x20f/0x4c0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 0 PID: 4995 Comm: syz-executor153 Not tainted 6.6.0-rc1-syzkaller-00014-ga747acc0b752 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/04/2023 Fixes: 977ad86c2a1b ("dccp: Fix out of bounds access in DCCP error handler") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Jann Horn Reviewed-by: Jann Horn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/dccp/ipv4.c | 9 ++------- net/dccp/ipv6.c | 9 ++------- 2 files changed, 4 insertions(+), 14 deletions(-) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8f5d3c088111..247179d4c886 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -255,13 +255,8 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 2b09e2644b13..6fb34eaf1237 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -83,13 +83,8 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmpv6_notify()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; From eef16bfdb212da60f5144689f2967fb25b051a2b Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 17 Aug 2023 13:55:58 -0400 Subject: [PATCH 1702/2093] x86/mm, kexec, ima: Use memblock_free_late() from ima_free_kexec_buffer() [ Upstream commit 34cf99c250d5cd2530b93a57b0de31d3aaf8685b ] The code calling ima_free_kexec_buffer() runs long after the memblock allocator has already been torn down, potentially resulting in a use after free in memblock_isolate_range(). With KASAN or KFENCE, this use after free will result in a BUG from the idle task, and a subsequent kernel panic. Switch ima_free_kexec_buffer() over to memblock_free_late() to avoid that bug. Fixes: fee3ff99bc67 ("powerpc: Move arch independent ima kexec functions to drivers/of/kexec.c") Suggested-by: Mike Rappoport Signed-off-by: Rik van Riel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230817135558.67274c83@imladris.surriel.com Signed-off-by: Sasha Levin --- arch/x86/kernel/setup.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 892609cde4a2..804a252382da 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -363,15 +363,11 @@ static void __init add_early_ima_buffer(u64 phys_addr) #if defined(CONFIG_HAVE_IMA_KEXEC) && !defined(CONFIG_OF_FLATTREE) int __init ima_free_kexec_buffer(void) { - int rc; - if (!ima_kexec_buffer_size) return -ENOENT; - rc = memblock_phys_free(ima_kexec_buffer_phys, - ima_kexec_buffer_size); - if (rc) - return rc; + memblock_free_late(ima_kexec_buffer_phys, + ima_kexec_buffer_size); ima_kexec_buffer_phys = 0; ima_kexec_buffer_size = 0; From 8ef5cc6b4ef0ac687aa4f45bde723b03e30f7fd6 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Fri, 15 Sep 2023 20:10:02 +0200 Subject: [PATCH 1703/2093] net: hsr: Properly parse HSRv1 supervisor frames. [ Upstream commit 295de650d3aaf9e50258465c5f1c84b465d836f6 ] While adding support for parsing the redbox supervision frames, the author added `pull_size' and `total_pull_size' to track the amount of bytes that were pulled from the skb during while parsing the skb so it can be reverted/ pushed back at the end. In the process probably copy&paste error occurred and for the HSRv1 case the ethhdr was used instead of the hsr_tag. Later the hsr_tag was used instead of hsr_sup_tag. The later error didn't matter because both structs have the size so HSRv0 was still working. It broke however HSRv1 parsing because struct ethhdr is larger than struct hsr_tag. Reinstate the old pulling flow and pull first ethhdr, hsr_tag in v1 case followed by hsr_sup_tag. [bigeasy: commit message] Fixes: eafaa88b3eb7 ("net: hsr: Add support for redbox supervision frames")' Suggested-by: Tristram.Ha@microchip.com Signed-off-by: Lukasz Majewski Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/hsr/hsr_framereg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index a16f0445023a..0b0199878095 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -295,13 +295,13 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) /* And leave the HSR tag. */ if (ethhdr->h_proto == htons(ETH_P_HSR)) { - pull_size = sizeof(struct ethhdr); + pull_size = sizeof(struct hsr_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; } /* And leave the HSR sup tag. */ - pull_size = sizeof(struct hsr_tag); + pull_size = sizeof(struct hsr_sup_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; From 98a5a7f344fa4bad2e12496513248d381865f75f Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 13 Sep 2023 14:27:19 -0700 Subject: [PATCH 1704/2093] platform/x86: intel_scu_ipc: Check status after timeout in busy_loop() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e0b4ab3bb92bda8d12f55842614362989d5b2cb3 ] It's possible for the polling loop in busy_loop() to get scheduled away for a long time. status = ipc_read_status(scu); // status = IPC_STATUS_BUSY if (!(status & IPC_STATUS_BUSY)) If this happens, then the status bit could change while the task is scheduled away and this function would never read the status again after timing out. Instead, the function will return -ETIMEDOUT when it's possible that scheduling didn't work out and the status bit was cleared. Bit polling code should always check the bit being polled one more time after the timeout in case this happens. Fix this by reading the status once more after the while loop breaks. The readl_poll_timeout() macro implements all of this, and it is shorter, so use that macro here to consolidate code and fix this. There were some concerns with using readl_poll_timeout() because it uses timekeeping, and timekeeping isn't running early on or during the late stages of system suspend or early stages of system resume, but an audit of the code concluded that this code isn't called during those times so it is safe to use the macro. Cc: Prashant Malani Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg Reviewed-by: Kuppuswamy Sathyanarayanan Fixes: e7b7ab3847c9 ("platform/x86: intel_scu_ipc: Sleeping is fine when polling") Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230913212723.3055315-2-swboyd@chromium.org Reviewed-by: Ilpo Järvinen Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel_scu_ipc.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index e7a3e3402817..96675bea88b1 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -232,19 +233,15 @@ static inline u32 ipc_data_readl(struct intel_scu_ipc_dev *scu, u32 offset) /* Wait till scu status is busy */ static inline int busy_loop(struct intel_scu_ipc_dev *scu) { - unsigned long end = jiffies + IPC_TIMEOUT; + u8 status; + int err; - do { - u32 status; + err = readx_poll_timeout(ipc_read_status, scu, status, !(status & IPC_STATUS_BUSY), + 100, jiffies_to_usecs(IPC_TIMEOUT)); + if (err) + return err; - status = ipc_read_status(scu); - if (!(status & IPC_STATUS_BUSY)) - return (status & IPC_STATUS_ERR) ? -EIO : 0; - - usleep_range(50, 100); - } while (time_before(jiffies, end)); - - return -ETIMEDOUT; + return (status & IPC_STATUS_ERR) ? -EIO : 0; } /* Wait till ipc ioc interrupt is received or timeout in 10 HZ */ From 9624445958413246497d422b596d04c1f72c0bf9 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 13 Sep 2023 14:27:20 -0700 Subject: [PATCH 1705/2093] platform/x86: intel_scu_ipc: Check status upon timeout in ipc_wait_for_interrupt() [ Upstream commit 427fada620733e6474d783ae6037a66eae42bf8c ] It's possible for the completion in ipc_wait_for_interrupt() to timeout, simply because the interrupt was delayed in being processed. A timeout in itself is not an error. This driver should check the status register upon a timeout to ensure that scheduling or interrupt processing delays don't affect the outcome of the IPC return value. CPU0 SCU ---- --- ipc_wait_for_interrupt() wait_for_completion_timeout(&scu->cmd_complete) [TIMEOUT] status[IPC_STATUS_BUSY]=0 Fix this problem by reading the status bit in all cases, regardless of the timeout. If the completion times out, we'll assume the problem was that the IPC_STATUS_BUSY bit was still set, but if the status bit is cleared in the meantime we know that we hit some scheduling delay and we should just check the error bit. Cc: Prashant Malani Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg Fixes: ed12f295bfd5 ("ipc: Added support for IPC interrupt mode") Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230913212723.3055315-3-swboyd@chromium.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel_scu_ipc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 96675bea88b1..be97cfae4b0f 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -249,10 +249,12 @@ static inline int ipc_wait_for_interrupt(struct intel_scu_ipc_dev *scu) { int status; - if (!wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT)) - return -ETIMEDOUT; + wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT); status = ipc_read_status(scu); + if (status & IPC_STATUS_BUSY) + return -ETIMEDOUT; + if (status & IPC_STATUS_ERR) return -EIO; From b34121a8fec1ed43935cdfa382fae5141be1ede1 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 13 Sep 2023 14:27:21 -0700 Subject: [PATCH 1706/2093] platform/x86: intel_scu_ipc: Don't override scu in intel_scu_ipc_dev_simple_command() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit efce78584e583226e9a1f6cb2fb555d6ff47c3e7 ] Andy discovered this bug during patch review. The 'scu' argument to this function shouldn't be overridden by the function itself. It doesn't make any sense. Looking at the commit history, we see that commit f57fa18583f5 ("platform/x86: intel_scu_ipc: Introduce new SCU IPC API") removed the setting of the scu to ipcdev in other functions, but not this one. That was an oversight. Remove this line so that we stop overriding the scu instance that is used by this function. Reported-by: Andy Shevchenko Closes: https://lore.kernel.org/r/ZPjdZ3xNmBEBvNiS@smile.fi.intel.com Cc: Prashant Malani Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg Fixes: f57fa18583f5 ("platform/x86: intel_scu_ipc: Introduce new SCU IPC API") Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230913212723.3055315-4-swboyd@chromium.org Reviewed-by: Ilpo Järvinen Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel_scu_ipc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index be97cfae4b0f..dfe010f1ee08 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -444,7 +444,6 @@ int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, mutex_unlock(&ipclock); return -ENODEV; } - scu = ipcdev; cmdval = sub << 12 | cmd; ipc_command(scu, cmdval); err = intel_scu_ipc_check_status(scu); From 7f301aa243b9df34a7a2aa7c166a0cd79b37dd43 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 13 Sep 2023 14:27:22 -0700 Subject: [PATCH 1707/2093] platform/x86: intel_scu_ipc: Fail IPC send if still busy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 85e654c9f722853a595fa941dca60c157b707b86 ] It's possible for interrupts to get significantly delayed to the point that callers of intel_scu_ipc_dev_command() and friends can call the function once, hit a timeout, and call it again while the interrupt still hasn't been processed. This driver will get seriously confused if the interrupt is finally processed after the second IPC has been sent with ipc_command(). It won't know which IPC has been completed. This could be quite disastrous if calling code assumes something has happened upon return from intel_scu_ipc_dev_simple_command() when it actually hasn't. Let's avoid this scenario by simply returning -EBUSY in this case. Hopefully higher layers will know to back off or fail gracefully when this happens. It's all highly unlikely anyway, but it's better to be correct here as we have no way to know which IPC the status register is telling us about if we send a second IPC while the previous IPC is still processing. Cc: Prashant Malani Cc: Kuppuswamy Sathyanarayanan Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg Fixes: ed12f295bfd5 ("ipc: Added support for IPC interrupt mode") Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230913212723.3055315-5-swboyd@chromium.org Reviewed-by: Ilpo Järvinen Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel_scu_ipc.c | 40 +++++++++++++++++++--------- 1 file changed, 28 insertions(+), 12 deletions(-) diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index dfe010f1ee08..189c5460edd8 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -266,6 +266,24 @@ static int intel_scu_ipc_check_status(struct intel_scu_ipc_dev *scu) return scu->irq > 0 ? ipc_wait_for_interrupt(scu) : busy_loop(scu); } +static struct intel_scu_ipc_dev *intel_scu_ipc_get(struct intel_scu_ipc_dev *scu) +{ + u8 status; + + if (!scu) + scu = ipcdev; + if (!scu) + return ERR_PTR(-ENODEV); + + status = ipc_read_status(scu); + if (status & IPC_STATUS_BUSY) { + dev_dbg(&scu->dev, "device is busy\n"); + return ERR_PTR(-EBUSY); + } + + return scu; +} + /* Read/Write power control(PMIC in Langwell, MSIC in PenWell) registers */ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, u32 count, u32 op, u32 id) @@ -279,11 +297,10 @@ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, memset(cbuf, 0, sizeof(cbuf)); mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } for (nc = 0; nc < count; nc++, offset += 2) { @@ -438,12 +455,12 @@ int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, int err; mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } + cmdval = sub << 12 | cmd; ipc_command(scu, cmdval); err = intel_scu_ipc_check_status(scu); @@ -483,11 +500,10 @@ int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, return -EINVAL; mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } memcpy(inbuf, in, inlen); From 755195b2d2df4d70952e5e5122c2cd590821be80 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 4 Sep 2023 22:04:45 -0700 Subject: [PATCH 1708/2093] x86/srso: Fix srso_show_state() side effect [ Upstream commit a8cf700c17d9ca6cb8ee7dc5c9330dbac3948237 ] Reading the 'spec_rstack_overflow' sysfs file can trigger an unnecessary MSR write, and possibly even a (handled) exception if the microcode hasn't been updated. Avoid all that by just checking X86_FEATURE_IBPB_BRTYPE instead, which gets set by srso_select_mitigation() if the updated microcode exists. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Josh Poimboeuf Signed-off-by: Ingo Molnar Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Nikolay Borisov Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/27d128899cb8aee9eb2b57ddc996742b0c1d776b.1693889988.git.jpoimboe@kernel.org Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3a893ab398a0..5f38d60532a9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2692,7 +2692,7 @@ static ssize_t srso_show_state(char *buf) return sysfs_emit(buf, "%s%s\n", srso_strings[srso_mitigation], - (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); + boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode"); } static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, From adbcec23c8423e3d5df1839c5ae91599dcf703cb Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 4 Sep 2023 22:04:48 -0700 Subject: [PATCH 1709/2093] x86/srso: Fix SBPB enablement for spec_rstack_overflow=off [ Upstream commit 01b057b2f4cc2d905a0bd92195657dbd9a7005ab ] If the user has requested no SRSO mitigation, other mitigations can use the lighter-weight SBPB instead of IBPB. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Josh Poimboeuf Signed-off-by: Ingo Molnar Signed-off-by: Borislav Petkov (AMD) Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/b20820c3cfd1003171135ec8d762a0b957348497.1693889988.git.jpoimboe@kernel.org Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 5f38d60532a9..263df737d5cd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2414,7 +2414,7 @@ static void __init srso_select_mitigation(void) switch (srso_cmd) { case SRSO_CMD_OFF: - return; + goto pred_cmd; case SRSO_CMD_MICROCODE: if (has_microcode) { From 430f18eed1c1b255cc3e51e0820f4cd6f2898827 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Mon, 18 Sep 2023 15:48:36 +0800 Subject: [PATCH 1710/2093] net: hns3: add cmdq check for vf periodic service task [ Upstream commit bd3caddf299a640efb66c6022efed7fe744db626 ] When the vf cmdq is disabled, there is no need to keep these task running. So this patch skip these task when the cmdq is disabled. Fixes: ff200099d271 ("net: hns3: remove unnecessary work in hclgevf_main") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index b1b14850e958..72cf5145e15a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1909,7 +1909,8 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev) unsigned long delta = round_jiffies_relative(HZ); struct hnae3_handle *handle = &hdev->nic; - if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) + if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state) || + test_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state)) return; if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) { From ed6a0b21b6acd8128e10a9553e50b5dec0c18e82 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Mon, 18 Sep 2023 15:48:37 +0800 Subject: [PATCH 1711/2093] net: hns3: fix GRE checksum offload issue [ Upstream commit f9f651261130cdcb7adc9a3e365b356bc2749ab3 ] The device_version V3 hardware can't offload the checksum for IP in GRE packets, but can do it for NvGRE. So default to disable the checksum and GSO offload for GRE, but keep the ability to enable it when only using NvGRE. Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 8aae179554a8..04c9baca1b0f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3352,6 +3352,15 @@ static void hns3_set_default_feature(struct net_device *netdev) NETIF_F_HW_TC); netdev->hw_enc_features |= netdev->vlan_features | NETIF_F_TSO_MANGLEID; + + /* The device_version V3 hardware can't offload the checksum for IP in + * GRE packets, but can do it for NvGRE. So default to disable the + * checksum and GSO offload for GRE. + */ + if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2) { + netdev->features &= ~NETIF_F_GSO_GRE; + netdev->features &= ~NETIF_F_GSO_GRE_CSUM; + } } static int hns3_alloc_buffer(struct hns3_enet_ring *ring, From d3f7af41de523dc13792a7497f7f1f3613fc9098 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Mon, 18 Sep 2023 15:48:38 +0800 Subject: [PATCH 1712/2093] net: hns3: only enable unicast promisc when mac table full [ Upstream commit f2ed304922a55690529bcca59678dd92d7466ce8 ] Currently, the driver will enable unicast promisc for the function once configure mac address fail. It's unreasonable when the failure is caused by using same mac address with other functions. So only enable unicast promisc when mac table full. Fixes: c631c696823c ("net: hns3: refactor the promisc mode setting") Signed-off-by: Jian Shen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 884e45fb6b72..a8019eac2b33 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8930,7 +8930,7 @@ static void hclge_update_overflow_flags(struct hclge_vport *vport, if (mac_type == HCLGE_MAC_ADDR_UC) { if (is_all_added) vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_UPE; - else + else if (hclge_is_umv_space_full(vport, true)) vport->overflow_promisc_flags |= HNAE3_OVERFLOW_UPE; } else { if (is_all_added) From b1b85b3d767e646e2ea3222b92e5c74865d6d1cd Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Mon, 18 Sep 2023 15:48:39 +0800 Subject: [PATCH 1713/2093] net: hns3: fix fail to delete tc flower rules during reset issue [ Upstream commit 1a7be66e4685b8541546222c305cce9710718a88 ] Firmware does not respond driver commands during reset Therefore, rule will fail to delete while the firmware is resetting So, if failed to delete rule, set rule state to TO_DEL, and the rule will be deleted when periodic task being scheduled. Fixes: 0205ec041ec6 ("net: hns3: add support for hw tc offload of tc flower") Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index a8019eac2b33..e44c5076262b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -7454,6 +7454,12 @@ static int hclge_del_cls_flower(struct hnae3_handle *handle, ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, rule->location, NULL, false); if (ret) { + /* if tcam config fail, set rule state to TO_DEL, + * so the rule will be deleted when periodic + * task being scheduled. + */ + hclge_update_fd_list(hdev, HCLGE_FD_TO_DEL, rule->location, NULL); + set_bit(HCLGE_STATE_FD_TBL_CHANGED, &hdev->state); spin_unlock_bh(&hdev->fd_rule_lock); return ret; } From 69d7eef31ee1f4821e6248cbd49df02d57009428 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Mon, 18 Sep 2023 15:48:40 +0800 Subject: [PATCH 1714/2093] net: hns3: add 5ms delay before clear firmware reset irq source [ Upstream commit 0770063096d5da4a8e467b6e73c1646a75589628 ] Currently the reset process in hns3 and firmware watchdog init process is asynchronous. we think firmware watchdog initialization is completed before hns3 clear the firmware interrupt source. However, firmware initialization may not complete early. so we add delay before hns3 clear firmware interrupt source and 5 ms delay is enough to avoid second firmware reset interrupt. Fixes: c1a81619d73a ("net: hns3: Add mailbox interrupt handling to PF driver") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e44c5076262b..3e1d202d60ce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3662,9 +3662,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type, u32 regclr) { +#define HCLGE_IMP_RESET_DELAY 5 + switch (event_type) { case HCLGE_VECTOR0_EVENT_PTP: case HCLGE_VECTOR0_EVENT_RST: + if (regclr == BIT(HCLGE_VECTOR0_IMPRESET_INT_B)) + mdelay(HCLGE_IMP_RESET_DELAY); + hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr); break; case HCLGE_VECTOR0_EVENT_MBX: From 89f9f20b1cbd36d99d5a248a4bf8d11d4fd049a2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 18 Sep 2023 09:13:51 +0000 Subject: [PATCH 1715/2093] net: bridge: use DEV_STATS_INC() [ Upstream commit 44bdb313da57322c9b3c108eb66981c6ec6509f4 ] syzbot/KCSAN reported data-races in br_handle_frame_finish() [1] This function can run from multiple cpus without mutual exclusion. Adopt SMP safe DEV_STATS_INC() to update dev->stats fields. Handles updates to dev->stats.tx_dropped while we are at it. [1] BUG: KCSAN: data-race in br_handle_frame_finish / br_handle_frame_finish read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 1: br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189 br_nf_hook_thresh+0x1ed/0x220 br_nf_pre_routing_finish_ipv6+0x50f/0x540 NF_HOOK include/linux/netfilter.h:304 [inline] br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178 br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508 nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline] nf_hook_bridge_pre net/bridge/br_input.c:272 [inline] br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417 __netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417 __netif_receive_skb_one_core net/core/dev.c:5521 [inline] __netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637 process_backlog+0x21f/0x380 net/core/dev.c:5965 __napi_poll+0x60/0x3b0 net/core/dev.c:6527 napi_poll net/core/dev.c:6594 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6727 __do_softirq+0xc1/0x265 kernel/softirq.c:553 run_ksoftirqd+0x17/0x20 kernel/softirq.c:921 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:388 ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 0: br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189 br_nf_hook_thresh+0x1ed/0x220 br_nf_pre_routing_finish_ipv6+0x50f/0x540 NF_HOOK include/linux/netfilter.h:304 [inline] br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178 br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508 nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline] nf_hook_bridge_pre net/bridge/br_input.c:272 [inline] br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417 __netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417 __netif_receive_skb_one_core net/core/dev.c:5521 [inline] __netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637 process_backlog+0x21f/0x380 net/core/dev.c:5965 __napi_poll+0x60/0x3b0 net/core/dev.c:6527 napi_poll net/core/dev.c:6594 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6727 __do_softirq+0xc1/0x265 kernel/softirq.c:553 do_softirq+0x5e/0x90 kernel/softirq.c:454 __local_bh_enable_ip+0x64/0x70 kernel/softirq.c:381 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:167 [inline] _raw_spin_unlock_bh+0x36/0x40 kernel/locking/spinlock.c:210 spin_unlock_bh include/linux/spinlock.h:396 [inline] batadv_tt_local_purge+0x1a8/0x1f0 net/batman-adv/translation-table.c:1356 batadv_tt_purge+0x2b/0x630 net/batman-adv/translation-table.c:3560 process_one_work kernel/workqueue.c:2630 [inline] process_scheduled_works+0x5b8/0xa30 kernel/workqueue.c:2703 worker_thread+0x525/0x730 kernel/workqueue.c:2784 kthread+0x1d7/0x210 kernel/kthread.c:388 ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 value changed: 0x00000000000d7190 -> 0x00000000000d7191 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 14848 Comm: kworker/u4:11 Not tainted 6.6.0-rc1-syzkaller-00236-gad8a69f361b9 #0 Fixes: 1c29fc4989bc ("[BRIDGE]: keep track of received multicast packets") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Roopa Prabhu Cc: Nikolay Aleksandrov Cc: bridge@lists.linux-foundation.org Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230918091351.1356153-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/bridge/br_forward.c | 4 ++-- net/bridge/br_input.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index bd54f17e3c3d..4e3394a7d7d4 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -124,7 +124,7 @@ static int deliver_clone(const struct net_bridge_port *prev, skb = skb_clone(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return -ENOMEM; } @@ -263,7 +263,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, skb = skb_copy(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 68b3e850bcb9..6bb272894c96 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -164,12 +164,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst && mdst->host_joined) || br_multicast_is_router(brmctx, skb)) { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } mcast_hit = true; } else { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } break; case BR_PKT_UNICAST: From 2f0acb0736ecc3eb85dc80ad2790d634dcb10b58 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Mon, 18 Sep 2023 20:30:11 +0800 Subject: [PATCH 1716/2093] team: fix null-ptr-deref when team device type is changed [ Upstream commit 492032760127251e5540a5716a70996bacf2a3fd ] Get a null-ptr-deref bug as follows with reproducer [1]. BUG: kernel NULL pointer dereference, address: 0000000000000228 ... RIP: 0010:vlan_dev_hard_header+0x35/0x140 [8021q] ... Call Trace: ? __die+0x24/0x70 ? page_fault_oops+0x82/0x150 ? exc_page_fault+0x69/0x150 ? asm_exc_page_fault+0x26/0x30 ? vlan_dev_hard_header+0x35/0x140 [8021q] ? vlan_dev_hard_header+0x8e/0x140 [8021q] neigh_connected_output+0xb2/0x100 ip6_finish_output2+0x1cb/0x520 ? nf_hook_slow+0x43/0xc0 ? ip6_mtu+0x46/0x80 ip6_finish_output+0x2a/0xb0 mld_sendpack+0x18f/0x250 mld_ifc_work+0x39/0x160 process_one_work+0x1e6/0x3f0 worker_thread+0x4d/0x2f0 ? __pfx_worker_thread+0x10/0x10 kthread+0xe5/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 [1] $ teamd -t team0 -d -c '{"runner": {"name": "loadbalance"}}' $ ip link add name t-dummy type dummy $ ip link add link t-dummy name t-dummy.100 type vlan id 100 $ ip link add name t-nlmon type nlmon $ ip link set t-nlmon master team0 $ ip link set t-nlmon nomaster $ ip link set t-dummy up $ ip link set team0 up $ ip link set t-dummy.100 down $ ip link set t-dummy.100 master team0 When enslave a vlan device to team device and team device type is changed from non-ether to ether, header_ops of team device is changed to vlan_header_ops. That is incorrect and will trigger null-ptr-deref for vlan->real_dev in vlan_dev_hard_header() because team device is not a vlan device. Cache eth_header_ops in team_setup(), then assign cached header_ops to header_ops of team net device when its type is changed from non-ether to ether to fix the bug. Fixes: 1d76efe1577b ("team: add support for non-ethernet devices") Suggested-by: Hangbin Liu Reviewed-by: Hangbin Liu Signed-off-by: Ziyang Xuan Reviewed-by: Jiri Pirko Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230918123011.1884401-1-william.xuanziyang@huawei.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/team/team.c | 10 +++++++++- include/linux/if_team.h | 2 ++ 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 921ca59822b0..556b2d1cd2ac 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2127,7 +2127,12 @@ static const struct ethtool_ops team_ethtool_ops = { static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { - dev->header_ops = port_dev->header_ops; + struct team *team = netdev_priv(dev); + + if (port_dev->type == ARPHRD_ETHER) + dev->header_ops = team->header_ops_cache; + else + dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; @@ -2174,8 +2179,11 @@ static int team_dev_type_check_change(struct net_device *dev, static void team_setup(struct net_device *dev) { + struct team *team = netdev_priv(dev); + ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; + team->header_ops_cache = dev->header_ops; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 8de6b6e67829..34bcba5a7067 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -189,6 +189,8 @@ struct team { struct net_device *dev; /* associated netdevice */ struct team_pcpu_stats __percpu *pcpu_stats; + const struct header_ops *header_ops_cache; + struct mutex lock; /* used for overall locking, e.g. port lists write */ /* From 51fa66024a5eabf270164f2dc82a48ffb35a12e9 Mon Sep 17 00:00:00 2001 From: Artem Chernyshev Date: Mon, 18 Sep 2023 16:56:23 +0300 Subject: [PATCH 1717/2093] net: rds: Fix possible NULL-pointer dereference [ Upstream commit f1d95df0f31048f1c59092648997686e3f7d9478 ] In rds_rdma_cm_event_handler_cmn() check, if conn pointer exists before dereferencing it as rdma_set_service_type() argument Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: fd261ce6a30e ("rds: rdma: update rdma transport for tos") Signed-off-by: Artem Chernyshev Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/rds/rdma_transport.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index d36f3f6b4351..b15cf316b23a 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -86,11 +86,13 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_RESOLVED: - rdma_set_service_type(cm_id, conn->c_tos); - rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); - /* XXX do we need to clean up if this fails? */ - ret = rdma_resolve_route(cm_id, - RDS_RDMA_RESOLVE_TIMEOUT_MS); + if (conn) { + rdma_set_service_type(cm_id, conn->c_tos); + rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); + /* XXX do we need to clean up if this fails? */ + ret = rdma_resolve_route(cm_id, + RDS_RDMA_RESOLVE_TIMEOUT_MS); + } break; case RDMA_CM_EVENT_ROUTE_RESOLVED: From c4b0facd5c20ceae3d07018a3417f06302fa9cd1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 15 Sep 2023 15:18:11 +0200 Subject: [PATCH 1718/2093] netfilter: nf_tables: disable toggling dormant table state more than once [ Upstream commit c9bd26513b3a11b3adb3c2ed8a31a01a87173ff1 ] nft -f -< Cc: Bing-Jhong Billy Jheng Cc: info@starlabs.sg Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 521f8c3cb698..1d6a37430ff6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1211,6 +1211,10 @@ static int nf_tables_updtable(struct nft_ctx *ctx) flags & NFT_TABLE_F_OWNER)) return -EOPNOTSUPP; + /* No dormant off/on/off/on games in single transaction */ + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) From ea5a61d58886ae875f1b4a371999f2a8b58cf26d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 19 Sep 2023 20:04:45 +0200 Subject: [PATCH 1719/2093] netfilter: ipset: Fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP [ Upstream commit 7433b6d2afd512d04398c73aa984d1e285be125b ] Kyle Zeng reported that there is a race between IPSET_CMD_ADD and IPSET_CMD_SWAP in netfilter/ip_set, which can lead to the invocation of `__ip_set_put` on a wrong `set`, triggering the `BUG_ON(set->ref == 0);` check in it. The race is caused by using the wrong reference counter, i.e. the ref counter instead of ref_netlink. Fixes: 24e227896bbf ("netfilter: ipset: Add schedule point in call_ad().") Reported-by: Kyle Zeng Closes: https://lore.kernel.org/netfilter-devel/ZPZqetxOmH+w%2Fmyc@westworld/#r Tested-by: Kyle Zeng Signed-off-by: Jozsef Kadlecsik Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/ipset/ip_set_core.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 9a6b64779e64..20eede37d522 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -682,6 +682,14 @@ __ip_set_put(struct ip_set *set) /* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need * a separate reference counter */ +static void +__ip_set_get_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + set->ref_netlink++; + write_unlock_bh(&ip_set_ref_lock); +} + static void __ip_set_put_netlink(struct ip_set *set) { @@ -1695,11 +1703,11 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, do { if (retried) { - __ip_set_get(set); + __ip_set_get_netlink(set); nfnl_unlock(NFNL_SUBSYS_IPSET); cond_resched(); nfnl_lock(NFNL_SUBSYS_IPSET); - __ip_set_put(set); + __ip_set_put_netlink(set); } ip_set_lock(set); From 987a7f5311ba1fd4ccf3637c09e6424741aacd01 Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Tue, 12 Sep 2023 14:22:47 -0700 Subject: [PATCH 1720/2093] i915/pmu: Move execlist stats initialization to execlist specific setup [ Upstream commit c524cd40e8a2a1a36f4898eaf2024beefeb815f3 ] engine->stats is a union of execlist and guc stat objects. When execlist specific fields are initialized, the initial state of guc stats is affected. This results in bad busyness values when using GuC mode. Move the execlist initialization from common code to execlist specific code. Fixes: 77cdd054dd2c ("drm/i915/pmu: Connect engine busyness stats from GuC to pmu") Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Alan Previn Link: https://patchwork.freedesktop.org/patch/msgid/20230912212247.1828681-1-umesh.nerlige.ramappa@intel.com (cherry picked from commit 4485bd519f5d6d620a29d0547ff3c982bdeeb468) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 1 - drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index b458547e1fc6..07967adce16a 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -541,7 +541,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, DRIVER_CAPS(i915)->has_logical_contexts = true; ewma__engine_latency_init(&engine->latency); - seqcount_init(&engine->stats.execlists.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index fc4a84628985..f903ee1ce06e 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3546,6 +3546,8 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) logical_ring_default_vfuncs(engine); logical_ring_default_irqs(engine); + seqcount_init(&engine->stats.execlists.lock); + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) rcs_submission_override(engine); From d64e738adc5cc49824fd7b4ce43b86926aa1b27b Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 20 Sep 2023 12:46:27 +0200 Subject: [PATCH 1721/2093] locking/seqlock: Do the lockdep annotation before locking in do_write_seqcount_begin_nested() [ Upstream commit 41b43b6c6e30a832c790b010a06772e793bca193 ] It was brought up by Tetsuo that the following sequence: write_seqlock_irqsave() printk_deferred_enter() could lead to a deadlock if the lockdep annotation within write_seqlock_irqsave() triggers. The problem is that the sequence counter is incremented before the lockdep annotation is performed. The lockdep splat would then attempt to invoke printk() but the reader side, of the same seqcount, could have a tty_port::lock acquired waiting for the sequence number to become even again. The other lockdep annotations come before the actual locking because "we want to see the locking error before it happens". There is no reason why seqcount should be different here. Do the lockdep annotation first then perform the locking operation (the sequence increment). Fixes: 1ca7d67cf5d5a ("seqcount: Add lockdep functionality to seqcount/seqlock structures") Reported-by: Tetsuo Handa Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230920104627._DTHgPyA@linutronix.de Closes: https://lore.kernel.org/20230621130641.-5iueY1I@linutronix.de Signed-off-by: Sasha Levin --- include/linux/seqlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 3926e9027947..d778af83c8f3 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -512,8 +512,8 @@ do { \ static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { - do_raw_write_seqcount_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); + do_raw_write_seqcount_begin(s); } /** From 26f1829c853860b60cf52175c875ad501e875dfd Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 18 Sep 2023 17:36:09 +0200 Subject: [PATCH 1722/2093] net: ena: Flush XDP packets on error. [ Upstream commit 6f411fb5ca9419090bee6a0a46425e0a5060b734 ] xdp_do_flush() should be invoked before leaving the NAPI poll function after a XDP-redirect. This is not the case if the driver leaves via the error path (after having a redirect in one of its previous iterations). Invoke xdp_do_flush() also in the error path. Cc: Arthur Kiyanovski Cc: David Arinzon Cc: Noam Dagan Cc: Saeed Bishara Cc: Shay Agroskin Fixes: a318c70ad152b ("net: ena: introduce XDP redirect implementation") Acked-by: Arthur Kiyanovski Signed-off-by: Sebastian Andrzej Siewior Acked-by: Jesper Dangaard Brouer Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 5ce01ac72637..42a66b74c1e5 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1778,6 +1778,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, return work_done; error: + if (xdp_flags & ENA_XDP_REDIRECT) + xdp_do_flush(); + adapter = netdev_priv(rx_ring->netdev); if (rc == -ENOSPC) { From 98ebbdefe4909b20df35ecba5e9685378d6b8d25 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 18 Sep 2023 17:36:10 +0200 Subject: [PATCH 1723/2093] bnxt_en: Flush XDP for bnxt_poll_nitroa0()'s NAPI [ Upstream commit edc0140cc3b7b91874ebe70eb7d2a851e8817ccc ] bnxt_poll_nitroa0() invokes bnxt_rx_pkt() which can run a XDP program which in turn can return XDP_REDIRECT. bnxt_rx_pkt() is also used by __bnxt_poll_work() which flushes (xdp_do_flush()) the packets after each round. bnxt_poll_nitroa0() lacks this feature. xdp_do_flush() should be invoked before leaving the NAPI callback. Invoke xdp_do_flush() after a redirect in bnxt_poll_nitroa0() NAPI. Cc: Michael Chan Fixes: f18c2b77b2e4e ("bnxt_en: optimized XDP_REDIRECT support") Reviewed-by: Andy Gospodarek Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Michael Chan Acked-by: Jesper Dangaard Brouer Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 969db3c45d17..e81cb825dff4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2654,6 +2654,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) struct rx_cmp_ext *rxcmp1; u32 cp_cons, tmp_raw_cons; u32 raw_cons = cpr->cp_raw_cons; + bool flush_xdp = false; u32 rx_pkts = 0; u8 event = 0; @@ -2688,6 +2689,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) rx_pkts++; else if (rc == -EBUSY) /* partial completion */ break; + if (event & BNXT_REDIRECT_EVENT) + flush_xdp = true; } else if (unlikely(TX_CMP_TYPE(txcmp) == CMPL_BASE_TYPE_HWRM_DONE)) { bnxt_hwrm_handler(bp, txcmp); @@ -2707,6 +2710,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) if (event & BNXT_AGG_EVENT) bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + if (flush_xdp) + xdp_do_flush(); if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) { napi_complete_done(napi, rx_pkts); From cae59ae73106febd68612bf7f70064398253e3ad Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 18 Sep 2023 17:36:11 +0200 Subject: [PATCH 1724/2093] octeontx2-pf: Do xdp_do_flush() after redirects. [ Upstream commit 70b2b6892645e58ed6f051dad7f8d1083f0ad553 ] xdp_do_flush() should be invoked before leaving the NAPI poll function if XDP-redirect has been performed. Invoke xdp_do_flush() before leaving NAPI. Cc: Geetha sowjanya Cc: Subbaraya Sundeep Cc: Sunil Goutham Cc: hariprasad Fixes: 06059a1a9a4a5 ("octeontx2-pf: Add XDP support to netdev PF") Signed-off-by: Sebastian Andrzej Siewior Acked-by: Geethasowjanya Akula Acked-by: Jesper Dangaard Brouer Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- .../marvell/octeontx2/nic/otx2_txrx.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 7af223b0a37f..5704fb75fa47 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -29,7 +29,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct bpf_prog *prog, struct nix_cqe_rx_s *cqe, - struct otx2_cq_queue *cq); + struct otx2_cq_queue *cq, + bool *need_xdp_flush); static int otx2_nix_cq_op_status(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) @@ -340,7 +341,7 @@ static bool otx2_check_rcv_errors(struct otx2_nic *pfvf, static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, struct napi_struct *napi, struct otx2_cq_queue *cq, - struct nix_cqe_rx_s *cqe) + struct nix_cqe_rx_s *cqe, bool *need_xdp_flush) { struct nix_rx_parse_s *parse = &cqe->parse; struct nix_rx_sg_s *sg = &cqe->sg; @@ -356,7 +357,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, } if (pfvf->xdp_prog) - if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq)) + if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq, need_xdp_flush)) return; skb = napi_get_frags(napi); @@ -389,6 +390,7 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, struct napi_struct *napi, struct otx2_cq_queue *cq, int budget) { + bool need_xdp_flush = false; struct nix_cqe_rx_s *cqe; int processed_cqe = 0; @@ -410,13 +412,15 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, cq->cq_head++; cq->cq_head &= (cq->cqe_cnt - 1); - otx2_rcv_pkt_handler(pfvf, napi, cq, cqe); + otx2_rcv_pkt_handler(pfvf, napi, cq, cqe, &need_xdp_flush); cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; cqe->sg.seg_addr = 0x00; processed_cqe++; cq->pend_cqe--; } + if (need_xdp_flush) + xdp_do_flush(); /* Free CQEs to HW */ otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR, @@ -1323,7 +1327,8 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx) static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct bpf_prog *prog, struct nix_cqe_rx_s *cqe, - struct otx2_cq_queue *cq) + struct otx2_cq_queue *cq, + bool *need_xdp_flush) { unsigned char *hard_start, *data; int qidx = cq->cq_idx; @@ -1360,8 +1365,10 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, DMA_FROM_DEVICE); - if (!err) + if (!err) { + *need_xdp_flush = true; return true; + } put_page(page); break; default: From c5c9ee3887232d9c9c1313212dd4ca9d5e08e337 Mon Sep 17 00:00:00 2001 From: Muhammad Husaini Zulkifli Date: Tue, 19 Sep 2023 10:03:31 -0700 Subject: [PATCH 1725/2093] igc: Expose tx-usecs coalesce setting to user [ Upstream commit 1703b2e0de653b459ca6230be32ce7f2ea0ae7ee ] When users attempt to obtain the coalesce setting using the ethtool command, current code always returns 0 for tx-usecs. This is because I225/6 always uses a queue pair setting, hence tx_coalesce_usecs does not return a value during the igc_ethtool_get_coalesce() callback process. The pair queue condition checking in igc_ethtool_get_coalesce() is removed by this patch so that the user gets information of the value of tx-usecs. Even if i225/6 is using queue pair setting, there is no harm in notifying the user of the tx-usecs. The implementation of the current code may have previously been a copy of the legacy code i210. Since I225 has the queue pair setting enabled, tx-usecs will always adhere to the user-set rx-usecs value. An error message will appear when the user attempts to set the tx-usecs value for the input parameters because, by default, they should only set the rx-usecs value. This patch also adds the helper function to get the previous rx coalesce value similar to tx coalesce. How to test: User can get the coalesce value using ethtool command. Example command: Get: ethtool -c Previous output: rx-usecs: 3 rx-frames: n/a rx-usecs-irq: n/a rx-frames-irq: n/a tx-usecs: 0 tx-frames: n/a tx-usecs-irq: n/a tx-frames-irq: n/a New output: rx-usecs: 3 rx-frames: n/a rx-usecs-irq: n/a rx-frames-irq: n/a tx-usecs: 3 tx-frames: n/a tx-usecs-irq: n/a tx-frames-irq: n/a Fixes: 8c5ad0dae93c ("igc: Add ethtool support") Signed-off-by: Muhammad Husaini Zulkifli Tested-by: Naama Meir Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230919170331.1581031-1-anthony.l.nguyen@intel.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_ethtool.c | 31 ++++++++++++-------- 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 511fc3f41208..9166fde40c77 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -867,6 +867,18 @@ static void igc_ethtool_get_stats(struct net_device *netdev, spin_unlock(&adapter->stats64_lock); } +static int igc_ethtool_get_previous_rx_coalesce(struct igc_adapter *adapter) +{ + return (adapter->rx_itr_setting <= 3) ? + adapter->rx_itr_setting : adapter->rx_itr_setting >> 2; +} + +static int igc_ethtool_get_previous_tx_coalesce(struct igc_adapter *adapter) +{ + return (adapter->tx_itr_setting <= 3) ? + adapter->tx_itr_setting : adapter->tx_itr_setting >> 2; +} + static int igc_ethtool_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, @@ -874,17 +886,8 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev, { struct igc_adapter *adapter = netdev_priv(netdev); - if (adapter->rx_itr_setting <= 3) - ec->rx_coalesce_usecs = adapter->rx_itr_setting; - else - ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; - - if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) { - if (adapter->tx_itr_setting <= 3) - ec->tx_coalesce_usecs = adapter->tx_itr_setting; - else - ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; - } + ec->rx_coalesce_usecs = igc_ethtool_get_previous_rx_coalesce(adapter); + ec->tx_coalesce_usecs = igc_ethtool_get_previous_tx_coalesce(adapter); return 0; } @@ -909,8 +912,12 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, ec->tx_coalesce_usecs == 2) return -EINVAL; - if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs) + if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && + ec->tx_coalesce_usecs != igc_ethtool_get_previous_tx_coalesce(adapter)) { + NL_SET_ERR_MSG_MOD(extack, + "Queue Pair mode enabled, both Rx and Tx coalescing controlled by rx-usecs"); return -EINVAL; + } /* If ITR is disabled, disable DMAC */ if (ec->rx_coalesce_usecs == 0) { From 1d45e6d9951d426a550a0411a718b9384f2181f3 Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer Date: Thu, 14 Sep 2023 12:30:20 -0400 Subject: [PATCH 1726/2093] proc: nommu: /proc//maps: release mmap read lock [ Upstream commit 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 ] The no-MMU implementation of /proc//map doesn't normally release the mmap read lock, because it uses !IS_ERR_OR_NULL(_vml) to determine whether to release the lock. Since _vml is NULL when the end of the mappings is reached, the lock is not released. Reading /proc/1/maps twice doesn't cause a hang because it only takes the read lock, which can be taken multiple times and therefore doesn't show any problem if the lock isn't released. Instead, you need to perform some operation that attempts to take the write lock after reading /proc//maps. To actually reproduce the bug, compile the following code as 'proc_maps_bug': #include #include #include int main(int argc, char *argv[]) { void *buf; sleep(1); buf = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); puts("mmap returned"); return 0; } Then, run: ./proc_maps_bug &; cat /proc/$!/maps; fg Without this patch, mmap() will hang and the command will never complete. This code was incorrectly adapted from the MMU implementation, which at the time released the lock in m_next() before returning the last entry. The MMU implementation has diverged further from the no-MMU version since then, so this patch brings their locking and error handling into sync, fixing the bug and hopefully avoiding similar issues in the future. Link: https://lkml.kernel.org/r/20230914163019.4050530-2-ben.wolsieffer@hefring.com Fixes: 47fecca15c09 ("fs/proc/task_nommu.c: don't use priv->task->mm") Signed-off-by: Ben Wolsieffer Acked-by: Oleg Nesterov Cc: Giulio Benetti Cc: Greg Ungerer Cc: Signed-off-by: Andrew Morton Stable-dep-of: fe4419801617 ("proc: nommu: fix empty /proc//maps") Signed-off-by: Sasha Levin --- fs/proc/task_nommu.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 2fd06f52b6a4..bfcf17f75ed5 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -205,11 +205,16 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } @@ -218,23 +223,21 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (vma) return vma; - mmap_read_unlock(mm); - mmput(mm); return NULL; } -static void m_stop(struct seq_file *m, void *_vml) +static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(_vml)) { - mmap_read_unlock(priv->mm); - mmput(priv->mm); - } - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } static void *m_next(struct seq_file *m, void *_p, loff_t *pos) From 7e4f49cd2bd7ded92c33f975fe2ad5e7c7d77f72 Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer Date: Fri, 15 Sep 2023 12:00:56 -0400 Subject: [PATCH 1727/2093] proc: nommu: fix empty /proc//maps [ Upstream commit fe4419801617514765974f3e796269bc512ad146 ] On no-MMU, /proc//maps reads as an empty file. This happens because find_vma(mm, 0) always returns NULL (assuming no vma actually contains the zero address, which is normally the case). To fix this bug and improve the maintainability in the future, this patch makes the no-MMU implementation as similar as possible to the MMU implementation. The only remaining differences are the lack of hold/release_task_mempolicy and the extra code to shoehorn the gate vma into the iterator. This has been tested on top of 6.5.3 on an STM32F746. Link: https://lkml.kernel.org/r/20230915160055.971059-2-ben.wolsieffer@hefring.com Fixes: 0c563f148043 ("proc: remove VMA rbtree use from nommu") Signed-off-by: Ben Wolsieffer Cc: Davidlohr Bueso Cc: Giulio Benetti Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Oleg Nesterov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/proc/internal.h | 2 -- fs/proc/task_nommu.c | 37 ++++++++++++++++++++++--------------- 2 files changed, 22 insertions(+), 17 deletions(-) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index b701d0207edf..6b921826d85b 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -289,9 +289,7 @@ struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; -#ifdef CONFIG_MMU struct vma_iterator iter; -#endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index bfcf17f75ed5..dc05780f93e1 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -188,15 +188,28 @@ static int show_map(struct seq_file *m, void *_p) return nommu_vma_show(m, _p); } -static void *m_start(struct seq_file *m, loff_t *pos) +static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, + loff_t *ppos) +{ + struct vm_area_struct *vma = vma_next(&priv->iter); + + if (vma) { + *ppos = vma->vm_start; + } else { + *ppos = -1UL; + } + + return vma; +} + +static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; + unsigned long last_addr = *ppos; struct mm_struct *mm; - struct vm_area_struct *vma; - unsigned long addr = *pos; - /* See m_next(). Zero at the start or after lseek. */ - if (addr == -1UL) + /* See proc_get_vma(). Zero at the start or after lseek. */ + if (last_addr == -1UL) return NULL; /* pin the task and mm whilst we play with them */ @@ -218,12 +231,9 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-EINTR); } - /* start the next element from addr */ - vma = find_vma(mm, addr); - if (vma) - return vma; + vma_iter_init(&priv->iter, mm, last_addr); - return NULL; + return proc_get_vma(priv, ppos); } static void m_stop(struct seq_file *m, void *v) @@ -240,12 +250,9 @@ static void m_stop(struct seq_file *m, void *v) priv->task = NULL; } -static void *m_next(struct seq_file *m, void *_p, loff_t *pos) +static void *m_next(struct seq_file *m, void *_p, loff_t *ppos) { - struct vm_area_struct *vma = _p; - - *pos = vma->vm_end; - return find_vma(vma->vm_mm, vma->vm_end); + return proc_get_vma(m->private, ppos); } static const struct seq_operations proc_pid_maps_ops = { From 908b3b5e97d25e879de3d1f172a255665491c2c3 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Tue, 19 Sep 2023 13:38:04 -0500 Subject: [PATCH 1728/2093] cifs: Fix UAF in cifs_demultiplex_thread() [ Upstream commit d527f51331cace562393a8038d870b3e9916686f ] There is a UAF when xfstests on cifs: BUG: KASAN: use-after-free in smb2_is_network_name_deleted+0x27/0x160 Read of size 4 at addr ffff88810103fc08 by task cifsd/923 CPU: 1 PID: 923 Comm: cifsd Not tainted 6.1.0-rc4+ #45 ... Call Trace: dump_stack_lvl+0x34/0x44 print_report+0x171/0x472 kasan_report+0xad/0x130 kasan_check_range+0x145/0x1a0 smb2_is_network_name_deleted+0x27/0x160 cifs_demultiplex_thread.cold+0x172/0x5a4 kthread+0x165/0x1a0 ret_from_fork+0x1f/0x30 Allocated by task 923: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_slab_alloc+0x54/0x60 kmem_cache_alloc+0x147/0x320 mempool_alloc+0xe1/0x260 cifs_small_buf_get+0x24/0x60 allocate_buffers+0xa1/0x1c0 cifs_demultiplex_thread+0x199/0x10d0 kthread+0x165/0x1a0 ret_from_fork+0x1f/0x30 Freed by task 921: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x40 ____kasan_slab_free+0x143/0x1b0 kmem_cache_free+0xe3/0x4d0 cifs_small_buf_release+0x29/0x90 SMB2_negotiate+0x8b7/0x1c60 smb2_negotiate+0x51/0x70 cifs_negotiate_protocol+0xf0/0x160 cifs_get_smb_ses+0x5fa/0x13c0 mount_get_conns+0x7a/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The UAF is because: mount(pid: 921) | cifsd(pid: 923) -------------------------------|------------------------------- | cifs_demultiplex_thread SMB2_negotiate | cifs_send_recv | compound_send_recv | smb_send_rqst | wait_for_response | wait_event_state [1] | | standard_receive3 | cifs_handle_standard | handle_mid | mid->resp_buf = buf; [2] | dequeue_mid [3] KILL the process [4] | resp_iov[i].iov_base = buf | free_rsp_buf [5] | | is_network_name_deleted [6] | callback 1. After send request to server, wait the response until mid->mid_state != SUBMITTED; 2. Receive response from server, and set it to mid; 3. Set the mid state to RECEIVED; 4. Kill the process, the mid state already RECEIVED, get 0; 5. Handle and release the negotiate response; 6. UAF. It can be easily reproduce with add some delay in [3] - [6]. Only sync call has the problem since async call's callback is executed in cifsd process. Add an extra state to mark the mid state to READY before wakeup the waitter, then it can get the resp safely. Fixes: ec637e3ffb6b ("[CIFS] Avoid extra large buffer allocation (and memcpy) in cifs_readpages") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Zhang Xiaoxu Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/cifsglob.h | 1 + fs/smb/client/transport.c | 34 +++++++++++++++++++++++----------- 2 files changed, 24 insertions(+), 11 deletions(-) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 03f34ec63e10..39602f39aea8 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1776,6 +1776,7 @@ static inline bool is_retryable_error(int error) #define MID_RETRY_NEEDED 8 /* session closed while this request out */ #define MID_RESPONSE_MALFORMED 0x10 #define MID_SHUTDOWN 0x20 +#define MID_RESPONSE_READY 0x40 /* ready for other process handle the rsp */ /* Flags */ #define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index e03ffcf7e201..87aea456ee90 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -35,6 +35,8 @@ void cifs_wake_up_task(struct mid_q_entry *mid) { + if (mid->mid_state == MID_RESPONSE_RECEIVED) + mid->mid_state = MID_RESPONSE_READY; wake_up_process(mid->callback_data); } @@ -87,7 +89,8 @@ static void __release_mid(struct kref *refcount) struct TCP_Server_Info *server = midEntry->server; if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) && - midEntry->mid_state == MID_RESPONSE_RECEIVED && + (midEntry->mid_state == MID_RESPONSE_RECEIVED || + midEntry->mid_state == MID_RESPONSE_READY) && server->ops->handle_cancelled_mid) server->ops->handle_cancelled_mid(midEntry, server); @@ -759,7 +762,8 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ) int error; error = wait_event_state(server->response_q, - midQ->mid_state != MID_REQUEST_SUBMITTED, + midQ->mid_state != MID_REQUEST_SUBMITTED && + midQ->mid_state != MID_RESPONSE_RECEIVED, (TASK_KILLABLE|TASK_FREEZABLE_UNSAFE)); if (error < 0) return -ERESTARTSYS; @@ -912,7 +916,7 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) spin_lock(&server->mid_lock); switch (mid->mid_state) { - case MID_RESPONSE_RECEIVED: + case MID_RESPONSE_READY: spin_unlock(&server->mid_lock); return rc; case MID_RETRY_NEEDED: @@ -1011,6 +1015,9 @@ cifs_compound_callback(struct mid_q_entry *mid) credits.instance = server->reconnect_instance; add_credits(server, &credits, mid->optype); + + if (mid->mid_state == MID_RESPONSE_RECEIVED) + mid->mid_state = MID_RESPONSE_READY; } static void @@ -1206,7 +1213,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, send_cancel(server, &rqst[i], midQ[i]); spin_lock(&server->mid_lock); midQ[i]->mid_flags |= MID_WAIT_CANCELLED; - if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED || + midQ[i]->mid_state == MID_RESPONSE_RECEIVED) { midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; @@ -1227,7 +1235,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, } if (!midQ[i]->resp_buf || - midQ[i]->mid_state != MID_RESPONSE_RECEIVED) { + midQ[i]->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_dbg(FYI, "Bad MID state?\n"); goto out; @@ -1414,7 +1422,8 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, if (rc != 0) { send_cancel(server, &rqst, midQ); spin_lock(&server->mid_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; spin_unlock(&server->mid_lock); @@ -1431,7 +1440,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, } if (!midQ->resp_buf || !out_buf || - midQ->mid_state != MID_RESPONSE_RECEIVED) { + midQ->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_server_dbg(VFS, "Bad MID state?\n"); goto out; @@ -1555,14 +1564,16 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, /* Wait for a reply - allow signals to interrupt. */ rc = wait_event_interruptible(server->response_q, - (!(midQ->mid_state == MID_REQUEST_SUBMITTED)) || + (!(midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED)) || ((server->tcpStatus != CifsGood) && (server->tcpStatus != CifsNew))); /* Were we interrupted by a signal ? */ spin_lock(&server->srv_lock); if ((rc == -ERESTARTSYS) && - (midQ->mid_state == MID_REQUEST_SUBMITTED) && + (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) && ((server->tcpStatus == CifsGood) || (server->tcpStatus == CifsNew))) { spin_unlock(&server->srv_lock); @@ -1593,7 +1604,8 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, if (rc) { send_cancel(server, &rqst, midQ); spin_lock(&server->mid_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; spin_unlock(&server->mid_lock); @@ -1613,7 +1625,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, return rc; /* rcvd frame is ok */ - if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_RECEIVED) { + if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_tcon_dbg(VFS, "Bad MID state?\n"); goto out; From 50a096aab61f6a50903de750b0d694aa60fe6a38 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 3 Sep 2023 08:13:21 +0200 Subject: [PATCH 1729/2093] gpio: tb10x: Fix an error handling path in tb10x_gpio_probe() [ Upstream commit b547b5e52a0587e6b25ea520bf2f9e03d00cbcb6 ] If an error occurs after a successful irq_domain_add_linear() call, it should be undone by a corresponding irq_domain_remove(), as already done in the remove function. Fixes: c6ce2b6bffe5 ("gpio: add TB10x GPIO driver") Signed-off-by: Christophe JAILLET Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-tb10x.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c index de6afa3f9716..05357473d2a1 100644 --- a/drivers/gpio/gpio-tb10x.c +++ b/drivers/gpio/gpio-tb10x.c @@ -195,7 +195,7 @@ static int tb10x_gpio_probe(struct platform_device *pdev) handle_edge_irq, IRQ_NOREQUEST, IRQ_NOPROBE, IRQ_GC_INIT_MASK_CACHE); if (ret) - return ret; + goto err_remove_domain; gc = tb10x_gpio->domain->gc->gc[0]; gc->reg_base = tb10x_gpio->base; @@ -209,6 +209,10 @@ static int tb10x_gpio_probe(struct platform_device *pdev) } return 0; + +err_remove_domain: + irq_domain_remove(tb10x_gpio->domain); + return ret; } static int tb10x_gpio_remove(struct platform_device *pdev) From 976c8c1c40731c7579f7f52646cae86f17711703 Mon Sep 17 00:00:00 2001 From: Xiaoke Wang Date: Thu, 3 Mar 2022 20:39:14 +0800 Subject: [PATCH 1730/2093] i2c: mux: demux-pinctrl: check the return value of devm_kstrdup() [ Upstream commit 7c0195fa9a9e263df204963f88a22b21688ffb66 ] devm_kstrdup() returns pointer to allocated string on success, NULL on failure. So it is better to check the return value of it. Fixes: e35478eac030 ("i2c: mux: demux-pinctrl: run properly with multiple instances") Signed-off-by: Xiaoke Wang Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/muxes/i2c-demux-pinctrl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index f7a7405d4350..8e8688e8de0f 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -243,6 +243,10 @@ static int i2c_demux_pinctrl_probe(struct platform_device *pdev) props[i].name = devm_kstrdup(&pdev->dev, "status", GFP_KERNEL); props[i].value = devm_kstrdup(&pdev->dev, "ok", GFP_KERNEL); + if (!props[i].name || !props[i].value) { + err = -ENOMEM; + goto err_rollback; + } props[i].length = 3; of_changeset_init(&priv->chan[i].chgset); From fb9cfb28bdde57f49137d76e7a54dbd61206d337 Mon Sep 17 00:00:00 2001 From: Liang He Date: Wed, 22 Mar 2023 12:29:51 +0800 Subject: [PATCH 1731/2093] i2c: mux: gpio: Add missing fwnode_handle_put() [ Upstream commit db6aee6083a56ac4a6cd1b08fff7938072bcd0a3 ] In i2c_mux_gpio_probe_fw(), we should add fwnode_handle_put() when break out of the iteration device_for_each_child_node() as it will automatically increase and decrease the refcounter. Fixes: 98b2b712bc85 ("i2c: i2c-mux-gpio: Enable this driver in ACPI land") Signed-off-by: Liang He Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/muxes/i2c-mux-gpio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/muxes/i2c-mux-gpio.c b/drivers/i2c/muxes/i2c-mux-gpio.c index 73a23e117ebe..0930a51c8c7c 100644 --- a/drivers/i2c/muxes/i2c-mux-gpio.c +++ b/drivers/i2c/muxes/i2c-mux-gpio.c @@ -105,8 +105,10 @@ static int i2c_mux_gpio_probe_fw(struct gpiomux *mux, } else if (is_acpi_node(child)) { rc = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), values + i); - if (rc) + if (rc) { + fwnode_handle_put(child); return dev_err_probe(dev, rc, "Cannot get address\n"); + } } i++; From 70a1df9e0b4405aef12b490a806b5e46ed582bb6 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Wed, 20 Sep 2023 14:41:09 +0100 Subject: [PATCH 1732/2093] i2c: xiic: Correct return value check for xiic_reinit() [ Upstream commit 59851fb05d759f13662be143eff0aae605815b0e ] The error paths for xiic_reinit() return negative values on failure and 0 on success - this error message therefore is triggered on _success_ rather than failure. Correct the condition so it's only shown on failure as intended. Fixes: 8fa9c9388053 ("i2c: xiic: return value of xiic_reinit") Signed-off-by: Daniel Scally Acked-by: Michal Simek Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-xiic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index b41a6709e47f..b27bfc776599 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -420,7 +420,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) * reset the IP instead of just flush fifos */ ret = xiic_reinit(i2c); - if (!ret) + if (ret < 0) dev_dbg(i2c->adap.dev.parent, "reinit failed\n"); if (i2c->rx_msg) { From 226590fbd96717fce218878044df3568c825ba8e Mon Sep 17 00:00:00 2001 From: Aleksey Nasibulin Date: Wed, 12 Jul 2023 03:40:17 +0200 Subject: [PATCH 1733/2093] ARM: dts: BCM5301X: Extend RAM to full 256MB for Linksys EA6500 V2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 91994e59079dcb455783d3f9ea338eea6f671af3 ] Linksys ea6500-v2 have 256MB of ram. Currently we only use 128MB. Expand the definition to use all the available RAM. Fixes: 03e96644d7a8 ("ARM: dts: BCM5301X: Add basic DT for Linksys EA6500 V2") Signed-off-by: Aleksey Nasibulin Signed-off-by: Christian Marangi Cc: stable@vger.kernel.org Acked-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230712014017.28123-1-ansuelsmth@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts b/arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts index f1412ba83def..0454423fe166 100644 --- a/arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts +++ b/arch/arm/boot/dts/bcm4708-linksys-ea6500-v2.dts @@ -19,7 +19,8 @@ chosen { memory@0 { device_type = "memory"; - reg = <0x00000000 0x08000000>; + reg = <0x00000000 0x08000000>, + <0x88000000 0x08000000>; }; gpio-keys { From 05951f5c26b4fd3ba31dbed6a8c12541439068a0 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 14 Jul 2023 17:37:20 +0200 Subject: [PATCH 1734/2093] ARM: dts: samsung: exynos4210-i9100: Fix LCD screen's physical size [ Upstream commit b3f3fc32e5ff1e848555af8616318cc667457f90 ] The previous values were completely bogus, and resulted in the computed DPI ratio being much lower than reality, causing applications and UIs to misbehave. The new values were measured by myself with a ruler. Signed-off-by: Paul Cercueil Acked-by: Sam Ravnborg Fixes: 8620cc2f99b7 ("ARM: dts: exynos: Add devicetree file for the Galaxy S2") Cc: # v5.8+ Link: https://lore.kernel.org/r/20230714153720.336990-1-paul@crapouillou.net Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm/boot/dts/exynos4210-i9100.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/exynos4210-i9100.dts b/arch/arm/boot/dts/exynos4210-i9100.dts index bba85011ecc9..53e023fc1cac 100644 --- a/arch/arm/boot/dts/exynos4210-i9100.dts +++ b/arch/arm/boot/dts/exynos4210-i9100.dts @@ -201,8 +201,8 @@ lcd@0 { power-on-delay = <10>; reset-delay = <10>; - panel-width-mm = <90>; - panel-height-mm = <154>; + panel-width-mm = <56>; + panel-height-mm = <93>; display-timings { timing { From 21e5e3c3f71c772ac4b96fe1aaaceea9cfca736d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Jul 2023 13:53:33 +0200 Subject: [PATCH 1735/2093] ARM: dts: qcom: msm8974pro-castor: correct inverted X of touchscreen [ Upstream commit 43db69268149049540b1d2bbe8a69e59d5cb43b6 ] There is no syna,f11-flip-x property, so assume intention was to use touchscreen-inverted-x. Fixes: ab80661883de ("ARM: dts: qcom: msm8974: Add Sony Xperia Z2 Tablet") Cc: Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230720115335.137354-4-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- .../arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts b/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts index 3f45f5c5d37b..4abc85c18169 100644 --- a/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts +++ b/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts @@ -131,8 +131,8 @@ rmi-f01@1 { rmi-f11@11 { reg = <0x11>; - syna,f11-flip-x = <1>; syna,sensor-type = <1>; + touchscreen-inverted-x; }; }; }; From 064f57151dff199e7839114068b4f80f202f3f5d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Jul 2023 13:53:34 +0200 Subject: [PATCH 1736/2093] ARM: dts: qcom: msm8974pro-castor: correct touchscreen function names [ Upstream commit 31fba16c19c45b2b3a7c23b0bfef80aed1b29050 ] The node names for functions of Synaptics RMI4 touchscreen must be as "rmi4-fXX", as required by bindings and Linux driver. qcom-msm8974pro-sony-xperia-shinano-castor.dtb: synaptics@2c: Unevaluated properties are not allowed ('rmi-f01@1', 'rmi-f11@11' were unexpected) Fixes: ab80661883de ("ARM: dts: qcom: msm8974: Add Sony Xperia Z2 Tablet") Cc: Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230720115335.137354-5-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- .../boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts b/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts index 4abc85c18169..a572ac630c1b 100644 --- a/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts +++ b/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts @@ -124,12 +124,12 @@ synaptics@2c { syna,startup-delay-ms = <10>; - rmi-f01@1 { + rmi4-f01@1 { reg = <0x1>; syna,nosleep = <1>; }; - rmi-f11@11 { + rmi4-f11@11 { reg = <0x11>; syna,sensor-type = <1>; touchscreen-inverted-x; From 3134156e3421c24ff3c34cc9989e0a9b22fca76c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Jul 2023 13:53:35 +0200 Subject: [PATCH 1737/2093] ARM: dts: qcom: msm8974pro-castor: correct touchscreen syna,nosleep-mode [ Upstream commit 7c74379afdfee7b13f1cd8ff1ad6e0f986aec96c ] There is no syna,nosleep property in Synaptics RMI4 touchscreen: qcom-msm8974pro-sony-xperia-shinano-castor.dtb: synaptics@2c: rmi4-f01@1: 'syna,nosleep' does not match any of the regexes: 'pinctrl-[0-9]+' Fixes: ab80661883de ("ARM: dts: qcom: msm8974: Add Sony Xperia Z2 Tablet") Cc: Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230720115335.137354-6-krzysztof.kozlowski@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- .../arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts b/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts index a572ac630c1b..cc49bb777df8 100644 --- a/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts +++ b/arch/arm/boot/dts/qcom-msm8974pro-sony-xperia-shinano-castor.dts @@ -126,7 +126,7 @@ synaptics@2c { rmi4-f01@1 { reg = <0x1>; - syna,nosleep = <1>; + syna,nosleep-mode = <1>; }; rmi4-f11@11 { From 8b3b859bf8bed573c7abcc7b17f638b56a0ee287 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 8 Nov 2022 22:33:21 +0800 Subject: [PATCH 1738/2093] f2fs: optimize iteration over sparse directories [ Upstream commit 59237a21776f70ffb0420611c23e7158e1317037 ] Wei Chen reports a kernel bug as blew: INFO: task syz-executor.0:29056 blocked for more than 143 seconds. Not tainted 5.15.0-rc5 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:14632 pid:29056 ppid: 6574 flags:0x00000004 Call Trace: __schedule+0x4a1/0x1720 schedule+0x36/0xe0 rwsem_down_write_slowpath+0x322/0x7a0 fscrypt_ioctl_set_policy+0x11f/0x2a0 __f2fs_ioctl+0x1a9f/0x5780 f2fs_ioctl+0x89/0x3a0 __x64_sys_ioctl+0xe8/0x140 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae Eric did some investigation on this issue, quoted from reply of Eric: "Well, the quality of this bug report has a lot to be desired (not on upstream kernel, reproducer is full of totally irrelevant stuff, not sent to the mailing list of the filesystem whose disk image is being fuzzed, etc.). But what is going on is that f2fs_empty_dir() doesn't consider the case of a directory with an extremely large i_size on a malicious disk image. Specifically, the reproducer mounts an f2fs image with a directory that has an i_size of 14814520042850357248, then calls FS_IOC_SET_ENCRYPTION_POLICY on it. That results in a call to f2fs_empty_dir() to check whether the directory is empty. f2fs_empty_dir() then iterates through all 3616826182336513 blocks the directory allegedly contains to check whether any contain anything. i_rwsem is held during this, so anything else that tries to take it will hang." In order to solve this issue, let's use f2fs_get_next_page_offset() to speed up iteration by skipping holes for all below functions: - f2fs_empty_dir - f2fs_readdir - find_in_level The way why we can speed up iteration was described in 'commit 3cf4574705b4 ("f2fs: introduce get_next_page_offset to speed up SEEK_DATA")'. Meanwhile, in f2fs_empty_dir(), let's use f2fs_find_data_page() instead f2fs_get_lock_data_page(), due to i_rwsem was held in caller of f2fs_empty_dir(), there shouldn't be any races, so it's fine to not lock dentry page during lookuping dirents in the page. Link: https://lore.kernel.org/lkml/536944df-a0ae-1dd8-148f-510b476e1347@kernel.org/T/ Reported-by: Wei Chen Cc: Eric Biggers Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Stable-dep-of: d2d9bb3b6d2f ("f2fs: get out of a repeat loop when getting a locked data page") Signed-off-by: Sasha Levin --- fs/f2fs/data.c | 17 ++++++++++++----- fs/f2fs/dir.c | 34 ++++++++++++++++++++++++---------- fs/f2fs/f2fs.h | 5 +++-- fs/f2fs/gc.c | 4 ++-- 4 files changed, 41 insertions(+), 19 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c230824ab5e6..0faed0575f8a 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1212,7 +1212,8 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) } struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, - blk_opf_t op_flags, bool for_write) + blk_opf_t op_flags, bool for_write, + pgoff_t *next_pgofs) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; @@ -1238,12 +1239,17 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); - if (err) + if (err) { + if (err == -ENOENT && next_pgofs) + *next_pgofs = f2fs_get_next_page_offset(&dn, index); goto put_err; + } f2fs_put_dnode(&dn); if (unlikely(dn.data_blkaddr == NULL_ADDR)) { err = -ENOENT; + if (next_pgofs) + *next_pgofs = index + 1; goto put_err; } if (dn.data_blkaddr != NEW_ADDR && @@ -1287,7 +1293,8 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, return ERR_PTR(err); } -struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index) +struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, + pgoff_t *next_pgofs) { struct address_space *mapping = inode->i_mapping; struct page *page; @@ -1297,7 +1304,7 @@ struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index) return page; f2fs_put_page(page, 0); - page = f2fs_get_read_data_page(inode, index, 0, false); + page = f2fs_get_read_data_page(inode, index, 0, false, next_pgofs); if (IS_ERR(page)) return page; @@ -1323,7 +1330,7 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, struct address_space *mapping = inode->i_mapping; struct page *page; repeat: - page = f2fs_get_read_data_page(inode, index, 0, for_write); + page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL); if (IS_ERR(page)) return page; diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index bf5ba75b75d2..8373eba3a133 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -340,6 +340,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, unsigned int bidx, end_block; struct page *dentry_page; struct f2fs_dir_entry *de = NULL; + pgoff_t next_pgofs; bool room = false; int max_slots; @@ -350,12 +351,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, le32_to_cpu(fname->hash) % nbucket); end_block = bidx + nblock; - for (; bidx < end_block; bidx++) { + while (bidx < end_block) { /* no need to allocate new dentry pages to all the indices */ - dentry_page = f2fs_find_data_page(dir, bidx); + dentry_page = f2fs_find_data_page(dir, bidx, &next_pgofs); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) { room = true; + bidx = next_pgofs; continue; } else { *res_page = dentry_page; @@ -376,6 +378,8 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, if (max_slots >= s) room = true; f2fs_put_page(dentry_page, 0); + + bidx++; } if (!de && room && F2FS_I(dir)->chash != fname->hash) { @@ -963,7 +967,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, bool f2fs_empty_dir(struct inode *dir) { - unsigned long bidx; + unsigned long bidx = 0; struct page *dentry_page; unsigned int bit_pos; struct f2fs_dentry_block *dentry_blk; @@ -972,13 +976,17 @@ bool f2fs_empty_dir(struct inode *dir) if (f2fs_has_inline_dentry(dir)) return f2fs_empty_inline_dir(dir); - for (bidx = 0; bidx < nblock; bidx++) { - dentry_page = f2fs_get_lock_data_page(dir, bidx, false); + while (bidx < nblock) { + pgoff_t next_pgofs; + + dentry_page = f2fs_find_data_page(dir, bidx, &next_pgofs); if (IS_ERR(dentry_page)) { - if (PTR_ERR(dentry_page) == -ENOENT) + if (PTR_ERR(dentry_page) == -ENOENT) { + bidx = next_pgofs; continue; - else + } else { return false; + } } dentry_blk = page_address(dentry_page); @@ -990,10 +998,12 @@ bool f2fs_empty_dir(struct inode *dir) NR_DENTRY_IN_BLOCK, bit_pos); - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); if (bit_pos < NR_DENTRY_IN_BLOCK) return false; + + bidx++; } return true; } @@ -1111,7 +1121,8 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) goto out_free; } - for (; n < npages; n++, ctx->pos = n * NR_DENTRY_IN_BLOCK) { + for (; n < npages; ctx->pos = n * NR_DENTRY_IN_BLOCK) { + pgoff_t next_pgofs; /* allow readdir() to be interrupted */ if (fatal_signal_pending(current)) { @@ -1125,11 +1136,12 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) page_cache_sync_readahead(inode->i_mapping, ra, file, n, min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); - dentry_page = f2fs_find_data_page(inode, n); + dentry_page = f2fs_find_data_page(inode, n, &next_pgofs); if (IS_ERR(dentry_page)) { err = PTR_ERR(dentry_page); if (err == -ENOENT) { err = 0; + n = next_pgofs; continue; } else { goto out_free; @@ -1148,6 +1160,8 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) } f2fs_put_page(dentry_page, 0); + + n++; } out_free: fscrypt_fname_free_buffer(&fstr); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 37dca728ff96..f56abb39601a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3784,8 +3784,9 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn); int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index); int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index); struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, - blk_opf_t op_flags, bool for_write); -struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index); + blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs); +struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, + pgoff_t *next_pgofs); struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, bool for_write); struct page *f2fs_get_new_data_page(struct inode *inode, diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index aa4d513daa8f..ec7212f7a9b7 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1600,8 +1600,8 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, continue; } - data_page = f2fs_get_read_data_page(inode, - start_bidx, REQ_RAHEAD, true); + data_page = f2fs_get_read_data_page(inode, start_bidx, + REQ_RAHEAD, true, NULL); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (IS_ERR(data_page)) { iput(inode); From a84ac8995ac70728fc599501f4d781327f0e7f27 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 19 Jan 2023 10:47:00 -0800 Subject: [PATCH 1739/2093] f2fs: get out of a repeat loop when getting a locked data page [ Upstream commit d2d9bb3b6d2fbccb5b33d3a85a2830971625a4ea ] https://bugzilla.kernel.org/show_bug.cgi?id=216050 Somehow we're getting a page which has a different mapping. Let's avoid the infinite loop. Cc: Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/data.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0faed0575f8a..a982f91b71eb 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1329,18 +1329,14 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, { struct address_space *mapping = inode->i_mapping; struct page *page; -repeat: + page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL); if (IS_ERR(page)) return page; /* wait for read completion */ lock_page(page); - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); - goto repeat; - } - if (unlikely(!PageUptodate(page))) { + if (unlikely(page->mapping != mapping || !PageUptodate(page))) { f2fs_put_page(page, 1); return ERR_PTR(-EIO); } From 03b808058a88c4ab2847f4bb28fd047e7b54401a Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Tue, 25 Jul 2023 11:24:47 +0200 Subject: [PATCH 1740/2093] s390/pkey: fix PKEY_TYPE_EP11_AES handling in PKEY_CLR2SECK2 IOCTL [ Upstream commit da2863f15945de100b95c72d5656541d30956c5d ] Commit 'fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys")' introduced PKEY_TYPE_EP11_AES for the PKEY_CLR2SECK2 IOCTL to convert an AES clearkey into a securekey of this type. Unfortunately, all PKEY_CLR2SECK2 IOCTL requests with type PKEY_TYPE_EP11_AES return with an error (-EINVAL). Fix the handling for PKEY_TYPE_EP11_AES in PKEY_CLR2SECK2 IOCTL, so that userspace can convert clearkey blobs into PKEY_TYPE_EP11_AES securekey blobs. Cc: stable@vger.kernel.org # v5.10+ Fixes: fa6999e326fe ("s390/pkey: support CCA and EP11 secure ECC private keys") Signed-off-by: Holger Dengler Reviewed-by: Ingo Franzki Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- drivers/s390/crypto/pkey_api.c | 16 +++++-- drivers/s390/crypto/zcrypt_ep11misc.c | 61 ++++++++++++++++++++------- drivers/s390/crypto/zcrypt_ep11misc.h | 3 +- 3 files changed, 60 insertions(+), 20 deletions(-) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 2b92ec20ed68..df0f19e6d923 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -212,7 +212,8 @@ static int pkey_clr2ep11key(const u8 *clrkey, size_t clrkeylen, card = apqns[i] >> 16; dom = apqns[i] & 0xFFFF; rc = ep11_clr2keyblob(card, dom, clrkeylen * 8, - 0, clrkey, keybuf, keybuflen); + 0, clrkey, keybuf, keybuflen, + PKEY_TYPE_EP11); if (rc == 0) break; } @@ -627,6 +628,11 @@ static int pkey_clr2seckey2(const struct pkey_apqn *apqns, size_t nr_apqns, if (*keybufsize < MINEP11AESKEYBLOBSIZE) return -EINVAL; break; + case PKEY_TYPE_EP11_AES: + if (*keybufsize < (sizeof(struct ep11kblob_header) + + MINEP11AESKEYBLOBSIZE)) + return -EINVAL; + break; default: return -EINVAL; } @@ -645,9 +651,11 @@ static int pkey_clr2seckey2(const struct pkey_apqn *apqns, size_t nr_apqns, for (i = 0, rc = -ENODEV; i < nr_apqns; i++) { card = apqns[i].card; dom = apqns[i].domain; - if (ktype == PKEY_TYPE_EP11) { + if (ktype == PKEY_TYPE_EP11 || + ktype == PKEY_TYPE_EP11_AES) { rc = ep11_clr2keyblob(card, dom, ksize, kflags, - clrkey, keybuf, keybufsize); + clrkey, keybuf, keybufsize, + ktype); } else if (ktype == PKEY_TYPE_CCA_DATA) { rc = cca_clr2seckey(card, dom, ksize, clrkey, keybuf); @@ -1361,7 +1369,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, apqns = _copy_apqns_from_user(kcs.apqns, kcs.apqn_entries); if (IS_ERR(apqns)) return PTR_ERR(apqns); - kkey = kmalloc(klen, GFP_KERNEL); + kkey = kzalloc(klen, GFP_KERNEL); if (!kkey) { kfree(apqns); return -ENOMEM; diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 20bbeec1a1a2..77e1ffaafaea 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -1000,12 +1000,12 @@ static int ep11_cryptsingle(u16 card, u16 domain, return rc; } -static int ep11_unwrapkey(u16 card, u16 domain, - const u8 *kek, size_t keksize, - const u8 *enckey, size_t enckeysize, - u32 mech, const u8 *iv, - u32 keybitsize, u32 keygenflags, - u8 *keybuf, size_t *keybufsize) +static int _ep11_unwrapkey(u16 card, u16 domain, + const u8 *kek, size_t keksize, + const u8 *enckey, size_t enckeysize, + u32 mech, const u8 *iv, + u32 keybitsize, u32 keygenflags, + u8 *keybuf, size_t *keybufsize) { struct uw_req_pl { struct pl_head head; @@ -1042,7 +1042,6 @@ static int ep11_unwrapkey(u16 card, u16 domain, struct ep11_cprb *req = NULL, *rep = NULL; struct ep11_target_dev target; struct ep11_urb *urb = NULL; - struct ep11keyblob *kb; size_t req_pl_size; int api, rc = -ENOMEM; u8 *p; @@ -1124,14 +1123,9 @@ static int ep11_unwrapkey(u16 card, u16 domain, goto out; } - /* copy key blob and set header values */ + /* copy key blob */ memcpy(keybuf, rep_pl->data, rep_pl->data_len); *keybufsize = rep_pl->data_len; - kb = (struct ep11keyblob *)keybuf; - kb->head.type = TOKTYPE_NON_CCA; - kb->head.len = rep_pl->data_len; - kb->head.version = TOKVER_EP11_AES; - kb->head.bitlen = keybitsize; out: kfree(req); @@ -1140,6 +1134,42 @@ static int ep11_unwrapkey(u16 card, u16 domain, return rc; } +static int ep11_unwrapkey(u16 card, u16 domain, + const u8 *kek, size_t keksize, + const u8 *enckey, size_t enckeysize, + u32 mech, const u8 *iv, + u32 keybitsize, u32 keygenflags, + u8 *keybuf, size_t *keybufsize, + u8 keybufver) +{ + struct ep11kblob_header *hdr; + size_t hdr_size, pl_size; + u8 *pl; + int rc; + + rc = ep11_kb_split(keybuf, *keybufsize, keybufver, + &hdr, &hdr_size, &pl, &pl_size); + if (rc) + return rc; + + rc = _ep11_unwrapkey(card, domain, kek, keksize, enckey, enckeysize, + mech, iv, keybitsize, keygenflags, + pl, &pl_size); + if (rc) + return rc; + + *keybufsize = hdr_size + pl_size; + + /* update header information */ + hdr = (struct ep11kblob_header *)keybuf; + hdr->type = TOKTYPE_NON_CCA; + hdr->len = *keybufsize; + hdr->version = keybufver; + hdr->bitlen = keybitsize; + + return 0; +} + static int ep11_wrapkey(u16 card, u16 domain, const u8 *key, size_t keysize, u32 mech, const u8 *iv, @@ -1274,7 +1304,8 @@ static int ep11_wrapkey(u16 card, u16 domain, } int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, - const u8 *clrkey, u8 *keybuf, size_t *keybufsize) + const u8 *clrkey, u8 *keybuf, size_t *keybufsize, + u32 keytype) { int rc; u8 encbuf[64], *kek = NULL; @@ -1321,7 +1352,7 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, /* Step 3: import the encrypted key value as a new key */ rc = ep11_unwrapkey(card, domain, kek, keklen, encbuf, encbuflen, 0, def_iv, - keybitsize, 0, keybuf, keybufsize); + keybitsize, 0, keybuf, keybufsize, keytype); if (rc) { DEBUG_ERR( "%s importing key value as new key failed,, rc=%d\n", diff --git a/drivers/s390/crypto/zcrypt_ep11misc.h b/drivers/s390/crypto/zcrypt_ep11misc.h index ed328c354bad..b7f9cbe3d58d 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.h +++ b/drivers/s390/crypto/zcrypt_ep11misc.h @@ -113,7 +113,8 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, * Generate EP11 AES secure key with given clear key value. */ int ep11_clr2keyblob(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, - const u8 *clrkey, u8 *keybuf, size_t *keybufsize); + const u8 *clrkey, u8 *keybuf, size_t *keybufsize, + u32 keytype); /* * Build a list of ep11 apqns meeting the following constrains: From dc1ab6577475b0460ba4261cd9caec37bd62ca0b Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Wed, 26 Jul 2023 18:57:19 +0530 Subject: [PATCH 1741/2093] arm64: dts: qcom: sdm845-db845c: Mark cont splash memory region as reserved [ Upstream commit 110e70fccce4f22b53986ae797d665ffb1950aa6 ] Adding a reserved memory region for the framebuffer memory (the splash memory region set up by the bootloader). It fixes a kernel panic (arm-smmu: Unhandled context fault at this particular memory region) reported on DB845c running v5.10.y. Cc: stable@vger.kernel.org # v5.10+ Reviewed-by: Caleb Connolly Signed-off-by: Amit Pundir Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230726132719.2117369-2-amit.pundir@linaro.org Signed-off-by: Bjorn Andersson Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index c289bf0903b4..c9efcb894a52 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -100,6 +100,14 @@ hdmi_con: endpoint { }; }; + reserved-memory { + /* Cont splash region set up by the bootloader */ + cont_splash_mem: framebuffer@9d400000 { + reg = <0x0 0x9d400000 0x0 0x2400000>; + no-map; + }; + }; + lt9611_1v8: lt9611-vdd18-regulator { compatible = "regulator-fixed"; regulator-name = "LT9611_1V8"; @@ -512,6 +520,7 @@ &i2c14 { }; &mdss { + memory-region = <&cont_splash_mem>; status = "okay"; }; From 1cccd28aa59199503bbad2eca0d9a3f8cdbba8f1 Mon Sep 17 00:00:00 2001 From: Pradeep Kumar Chitrapu Date: Mon, 17 Apr 2023 13:35:02 +0300 Subject: [PATCH 1742/2093] wifi: ath11k: fix tx status reporting in encap offload mode [ Upstream commit 6257c702264c44d74c6b71f0c62a7665da2dc356 ] ieee80211_tx_status() treats packets in 802.11 frame format and tries to extract sta address from packet header. When tx encap offload is enabled, this becomes invalid operation. Hence, switch to using ieee80211_tx_status_ext() after filling in station address for handling both 802.11 and 802.3 frames. Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1 Signed-off-by: Pradeep Kumar Chitrapu Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230403195738.25367-2-quic_pradeepc@quicinc.com Stable-dep-of: 29d15589f084 ("wifi: ath11k: Cleanup mac80211 references on failure during tx_complete") Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp.h | 4 +++ drivers/net/wireless/ath/ath11k/dp_tx.c | 33 ++++++++++++++++++++++++- drivers/net/wireless/ath/ath11k/dp_tx.h | 1 + 3 files changed, 37 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h index be9eafc872b3..232fd2e638bf 100644 --- a/drivers/net/wireless/ath/ath11k/dp.h +++ b/drivers/net/wireless/ath/ath11k/dp.h @@ -303,12 +303,16 @@ struct ath11k_dp { #define HTT_TX_WBM_COMP_STATUS_OFFSET 8 +#define HTT_INVALID_PEER_ID 0xffff + /* HTT tx completion is overlaid in wbm_release_ring */ #define HTT_TX_WBM_COMP_INFO0_STATUS GENMASK(12, 9) #define HTT_TX_WBM_COMP_INFO0_REINJECT_REASON GENMASK(16, 13) #define HTT_TX_WBM_COMP_INFO0_REINJECT_REASON GENMASK(16, 13) #define HTT_TX_WBM_COMP_INFO1_ACK_RSSI GENMASK(31, 24) +#define HTT_TX_WBM_COMP_INFO2_SW_PEER_ID GENMASK(15, 0) +#define HTT_TX_WBM_COMP_INFO2_VALID BIT(21) struct htt_tx_wbm_completion { u32 info0; diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c index 8afbba236935..08a28464eb7a 100644 --- a/drivers/net/wireless/ath/ath11k/dp_tx.c +++ b/drivers/net/wireless/ath/ath11k/dp_tx.c @@ -316,10 +316,12 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab, struct dp_tx_ring *tx_ring, struct ath11k_dp_htt_wbm_tx_status *ts) { + struct ieee80211_tx_status status = { 0 }; struct sk_buff *msdu; struct ieee80211_tx_info *info; struct ath11k_skb_cb *skb_cb; struct ath11k *ar; + struct ath11k_peer *peer; spin_lock(&tx_ring->tx_idr_lock); msdu = idr_remove(&tx_ring->txbuf_idr, ts->msdu_id); @@ -341,6 +343,11 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab, dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE); + if (!skb_cb->vif) { + dev_kfree_skb_any(msdu); + return; + } + memset(&info->status, 0, sizeof(info->status)); if (ts->acked) { @@ -355,7 +362,23 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab, } } - ieee80211_tx_status(ar->hw, msdu); + spin_lock_bh(&ab->base_lock); + peer = ath11k_peer_find_by_id(ab, ts->peer_id); + if (!peer || !peer->sta) { + ath11k_dbg(ab, ATH11K_DBG_DATA, + "dp_tx: failed to find the peer with peer_id %d\n", + ts->peer_id); + spin_unlock_bh(&ab->base_lock); + dev_kfree_skb_any(msdu); + return; + } + spin_unlock_bh(&ab->base_lock); + + status.sta = peer->sta; + status.info = info; + status.skb = msdu; + + ieee80211_tx_status_ext(ar->hw, &status); } static void @@ -379,7 +402,15 @@ ath11k_dp_tx_process_htt_tx_complete(struct ath11k_base *ab, ts.msdu_id = msdu_id; ts.ack_rssi = FIELD_GET(HTT_TX_WBM_COMP_INFO1_ACK_RSSI, status_desc->info1); + + if (FIELD_GET(HTT_TX_WBM_COMP_INFO2_VALID, status_desc->info2)) + ts.peer_id = FIELD_GET(HTT_TX_WBM_COMP_INFO2_SW_PEER_ID, + status_desc->info2); + else + ts.peer_id = HTT_INVALID_PEER_ID; + ath11k_dp_tx_htt_tx_complete_buf(ab, tx_ring, &ts); + break; case HAL_WBM_REL_HTT_TX_COMP_STATUS_REINJ: case HAL_WBM_REL_HTT_TX_COMP_STATUS_INSPECT: diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.h b/drivers/net/wireless/ath/ath11k/dp_tx.h index e87d65bfbf06..68a21ea9b934 100644 --- a/drivers/net/wireless/ath/ath11k/dp_tx.h +++ b/drivers/net/wireless/ath/ath11k/dp_tx.h @@ -13,6 +13,7 @@ struct ath11k_dp_htt_wbm_tx_status { u32 msdu_id; bool acked; int ack_rssi; + u16 peer_id; }; void ath11k_dp_tx_update_txcompl(struct ath11k *ar, struct hal_tx_status *ts); From 3a8ac77a70cca44ed23880517e8b2ccb16269017 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 22 Aug 2023 16:42:24 +0300 Subject: [PATCH 1743/2093] wifi: ath11k: Cleanup mac80211 references on failure during tx_complete [ Upstream commit 29d15589f084d71a4ea8c544039c5839db0236e2 ] When a function is using functions from mac80211 to free an skb then it should do it consistently and not switch to the generic dev_kfree_skb_any (or similar functions). Otherwise (like in the error handlers), mac80211 will will not be aware of the freed skb and thus not clean up related information in its internal data structures. Not doing so lead in the past to filled up structure which then prevented new clients to connect. Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices") Fixes: 6257c702264c ("wifi: ath11k: fix tx status reporting in encap offload mode") Cc: stable@vger.kernel.org Signed-off-by: Sven Eckelmann Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230802-ath11k-ack_status_leak-v2-2-c0af729d6229@narfation.org Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp_tx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c index 08a28464eb7a..64c8ccac22d2 100644 --- a/drivers/net/wireless/ath/ath11k/dp_tx.c +++ b/drivers/net/wireless/ath/ath11k/dp_tx.c @@ -344,7 +344,7 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab, dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE); if (!skb_cb->vif) { - dev_kfree_skb_any(msdu); + ieee80211_free_txskb(ar->hw, msdu); return; } @@ -566,12 +566,12 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar, dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE); if (unlikely(!rcu_access_pointer(ab->pdevs_active[ar->pdev_idx]))) { - dev_kfree_skb_any(msdu); + ieee80211_free_txskb(ar->hw, msdu); return; } if (unlikely(!skb_cb->vif)) { - dev_kfree_skb_any(msdu); + ieee80211_free_txskb(ar->hw, msdu); return; } From 35c02a333d523d9da0b482b0d751cdeb95c068ae Mon Sep 17 00:00:00 2001 From: Shreyas Deodhar Date: Wed, 21 Dec 2022 20:39:32 -0800 Subject: [PATCH 1744/2093] scsi: qla2xxx: Select qpair depending on which CPU post_cmd() gets called [ Upstream commit 1d201c81d4cc6840735bbcc99e6031503e5cf3b8 ] In current I/O path, Tx and Rx may not be processed on same CPU. This may lead to thrashing and optimum performance may not be achieved. Pick qpair such that Tx and Rx are processed on same CPU. Signed-off-by: Shreyas Deodhar Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen Stable-dep-of: 59f10a05b5c7 ("scsi: qla2xxx: Use raw_smp_processor_id() instead of smp_processor_id()") Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_def.h | 2 ++ drivers/scsi/qla2xxx/qla_init.c | 2 -- drivers/scsi/qla2xxx/qla_inline.h | 55 +++++++++++++++++++++++++++++++ drivers/scsi/qla2xxx/qla_isr.c | 3 +- drivers/scsi/qla2xxx/qla_nvme.c | 4 +++ drivers/scsi/qla2xxx/qla_os.c | 6 ++++ 6 files changed, 69 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 7d282906598f..817efdd32ad6 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3475,6 +3475,7 @@ struct qla_msix_entry { int have_irq; int in_use; uint32_t vector; + uint32_t vector_base0; uint16_t entry; char name[30]; void *handle; @@ -4133,6 +4134,7 @@ struct qla_hw_data { struct req_que **req_q_map; struct rsp_que **rsp_q_map; struct qla_qpair **queue_pair_map; + struct qla_qpair **qp_cpu_map; unsigned long req_qid_map[(QLA_MAX_QUEUES / 8) / sizeof(unsigned long)]; unsigned long rsp_qid_map[(QLA_MAX_QUEUES / 8) / sizeof(unsigned long)]; unsigned long qpair_qid_map[(QLA_MAX_QUEUES / 8) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 36abdb0de169..79de31e7e8b2 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -9758,8 +9758,6 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, qpair->req = ha->req_q_map[req_id]; qpair->rsp->req = qpair->req; qpair->rsp->qpair = qpair; - /* init qpair to this cpu. Will adjust at run time. */ - qla_cpu_update(qpair, raw_smp_processor_id()); if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif) { if (ha->fw_attributes & BIT_4) diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index a7b5d1114682..d5cf9db2a8ea 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -573,3 +573,58 @@ fcport_is_bigger(fc_port_t *fcport) { return !fcport_is_smaller(fcport); } + +static inline struct qla_qpair * +qla_mapq_nvme_select_qpair(struct qla_hw_data *ha, struct qla_qpair *qpair) +{ + int cpuid = smp_processor_id(); + + if (qpair->cpuid != cpuid && + ha->qp_cpu_map[cpuid]) { + qpair = ha->qp_cpu_map[cpuid]; + } + return qpair; +} + +static inline void +qla_mapq_init_qp_cpu_map(struct qla_hw_data *ha, + struct qla_msix_entry *msix, + struct qla_qpair *qpair) +{ + const struct cpumask *mask; + unsigned int cpu; + + if (!ha->qp_cpu_map) + return; + mask = pci_irq_get_affinity(ha->pdev, msix->vector_base0); + qpair->cpuid = cpumask_first(mask); + for_each_cpu(cpu, mask) { + ha->qp_cpu_map[cpu] = qpair; + } + msix->cpuid = qpair->cpuid; +} + +static inline void +qla_mapq_free_qp_cpu_map(struct qla_hw_data *ha) +{ + if (ha->qp_cpu_map) { + kfree(ha->qp_cpu_map); + ha->qp_cpu_map = NULL; + } +} + +static inline int qla_mapq_alloc_qp_cpu_map(struct qla_hw_data *ha) +{ + scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev); + + if (!ha->qp_cpu_map) { + ha->qp_cpu_map = kcalloc(NR_CPUS, sizeof(struct qla_qpair *), + GFP_KERNEL); + if (!ha->qp_cpu_map) { + ql_log(ql_log_fatal, vha, 0x0180, + "Unable to allocate memory for qp_cpu_map ptrs.\n"); + return -1; + } + } + return 0; +} diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 0111249cc877..a5e6246127ed 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3819,7 +3819,6 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, if (rsp->qpair->cpuid != smp_processor_id() || !rsp->qpair->rcv_intr) { rsp->qpair->rcv_intr = 1; - qla_cpu_update(rsp->qpair, smp_processor_id()); } #define __update_rsp_in(_is_shadow_hba, _rsp, _rsp_in) \ @@ -4425,6 +4424,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp) for (i = 0; i < ha->msix_count; i++) { qentry = &ha->msix_entries[i]; qentry->vector = pci_irq_vector(ha->pdev, i); + qentry->vector_base0 = i; qentry->entry = i; qentry->have_irq = 0; qentry->in_use = 0; @@ -4652,5 +4652,6 @@ int qla25xx_request_irq(struct qla_hw_data *ha, struct qla_qpair *qpair, } msix->have_irq = 1; msix->handle = qpair; + qla_mapq_init_qp_cpu_map(ha, msix, qpair); return ret; } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index c9a6fc882a80..9941b38eac93 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -609,6 +609,7 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, fc_port_t *fcport; struct srb_iocb *nvme; struct scsi_qla_host *vha; + struct qla_hw_data *ha; int rval; srb_t *sp; struct qla_qpair *qpair = hw_queue_handle; @@ -629,6 +630,7 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, return -ENODEV; vha = fcport->vha; + ha = vha->hw; if (test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) return -EBUSY; @@ -643,6 +645,8 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, if (fcport->nvme_flag & NVME_FLAG_RESETTING) return -EBUSY; + qpair = qla_mapq_nvme_select_qpair(ha, qpair); + /* Alloc SRB structure */ sp = qla2xxx_get_qpair_sp(vha, qpair, fcport, GFP_ATOMIC); if (!sp) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 78f7cd16967f..b33ffec1cb75 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -480,6 +480,11 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req, "Unable to allocate memory for queue pair ptrs.\n"); goto fail_qpair_map; } + if (qla_mapq_alloc_qp_cpu_map(ha) != 0) { + kfree(ha->queue_pair_map); + ha->queue_pair_map = NULL; + goto fail_qpair_map; + } } /* @@ -554,6 +559,7 @@ static void qla2x00_free_queues(struct qla_hw_data *ha) ha->base_qpair = NULL; } + qla_mapq_free_qp_cpu_map(ha); spin_lock_irqsave(&ha->hardware_lock, flags); for (cnt = 0; cnt < ha->max_req_queues; cnt++) { if (!test_bit(cnt, ha->req_qid_map)) From 52c7b41ad6ee53222f4ee2f0c099a6ed8291a168 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Thu, 31 Aug 2023 16:51:46 +0530 Subject: [PATCH 1745/2093] scsi: qla2xxx: Use raw_smp_processor_id() instead of smp_processor_id() [ Upstream commit 59f10a05b5c7b675256a66e3161741239889ff80 ] The following call trace was observed: localhost kernel: nvme nvme0: NVME-FC{0}: controller connect complete localhost kernel: BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u129:4/75092 localhost kernel: nvme nvme0: NVME-FC{0}: new ctrl: NQN "nqn.1992-08.com.netapp:sn.b42d198afb4d11ecad6d00a098d6abfa:subsystem.PR_Channel2022_RH84_subsystem_291" localhost kernel: caller is qla_nvme_post_cmd+0x216/0x1380 [qla2xxx] localhost kernel: CPU: 6 PID: 75092 Comm: kworker/u129:4 Kdump: loaded Tainted: G B W OE --------- --- 5.14.0-70.22.1.el9_0.x86_64+debug #1 localhost kernel: Hardware name: HPE ProLiant XL420 Gen10/ProLiant XL420 Gen10, BIOS U39 01/13/2022 localhost kernel: Workqueue: nvme-wq nvme_async_event_work [nvme_core] localhost kernel: Call Trace: localhost kernel: dump_stack_lvl+0x57/0x7d localhost kernel: check_preemption_disabled+0xc8/0xd0 localhost kernel: qla_nvme_post_cmd+0x216/0x1380 [qla2xxx] Use raw_smp_processor_id() instead of smp_processor_id(). Also use queue_work() across the driver instead of queue_work_on() thus avoiding usage of smp_processor_id() when CONFIG_DEBUG_PREEMPT is enabled. Cc: stable@vger.kernel.org Suggested-by: John Garry Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230831112146.32595-2-njavali@marvell.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_inline.h | 2 +- drivers/scsi/qla2xxx/qla_isr.c | 6 +++--- drivers/scsi/qla2xxx/qla_target.c | 3 +-- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 4 ++-- 4 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index d5cf9db2a8ea..e66441355f7a 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -577,7 +577,7 @@ fcport_is_bigger(fc_port_t *fcport) static inline struct qla_qpair * qla_mapq_nvme_select_qpair(struct qla_hw_data *ha, struct qla_qpair *qpair) { - int cpuid = smp_processor_id(); + int cpuid = raw_smp_processor_id(); if (qpair->cpuid != cpuid && ha->qp_cpu_map[cpuid]) { diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index a5e6246127ed..cf1025c91726 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3817,7 +3817,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, if (!ha->flags.fw_started) return; - if (rsp->qpair->cpuid != smp_processor_id() || !rsp->qpair->rcv_intr) { + if (rsp->qpair->cpuid != raw_smp_processor_id() || !rsp->qpair->rcv_intr) { rsp->qpair->rcv_intr = 1; } @@ -4305,7 +4305,7 @@ qla2xxx_msix_rsp_q(int irq, void *dev_id) } ha = qpair->hw; - queue_work_on(smp_processor_id(), ha->wq, &qpair->q_work); + queue_work(ha->wq, &qpair->q_work); return IRQ_HANDLED; } @@ -4331,7 +4331,7 @@ qla2xxx_msix_rsp_q_hs(int irq, void *dev_id) wrt_reg_dword(®->hccr, HCCRX_CLR_RISC_INT); spin_unlock_irqrestore(&ha->hardware_lock, flags); - queue_work_on(smp_processor_id(), ha->wq, &qpair->q_work); + queue_work(ha->wq, &qpair->q_work); return IRQ_HANDLED; } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 545473a0ffc8..5a5beb41786e 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4442,8 +4442,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, queue_work_on(cmd->se_cmd.cpuid, qla_tgt_wq, &cmd->work); } else if (ha->msix_count) { if (cmd->atio.u.isp24.fcp_cmnd.rddata) - queue_work_on(smp_processor_id(), qla_tgt_wq, - &cmd->work); + queue_work(qla_tgt_wq, &cmd->work); else queue_work_on(cmd->se_cmd.cpuid, qla_tgt_wq, &cmd->work); diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 8fa0056b56dd..e54ee6770e79 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -310,7 +310,7 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd) cmd->trc_flags |= TRC_CMD_DONE; INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free); - queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work); + queue_work(tcm_qla2xxx_free_wq, &cmd->work); } /* @@ -557,7 +557,7 @@ static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd) cmd->trc_flags |= TRC_DATA_IN; cmd->cmd_in_wq = 1; INIT_WORK(&cmd->work, tcm_qla2xxx_handle_data_work); - queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work); + queue_work(tcm_qla2xxx_free_wq, &cmd->work); } static int tcm_qla2xxx_chk_dif_tags(uint32_t tag) From 9becfff9f91e350fd4d6f16e9f117f9227258fb0 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Thu, 9 Feb 2023 18:23:16 -0500 Subject: [PATCH 1746/2093] drm/amdkfd: Flush TLB after unmapping for GFX v9.4.3 [ Upstream commit 75dda67c7213c3e0d17244a8c42547c27ee746f8 ] kfd_flush_tlb_after_unmap should return true for GFX v9.4.3, to do TLB heavyweight flush after unmapping from GPU to guarantee that the GPU will not access pages after they have been unmapped. This also helps improve the mapping to GPU performance. Without this, KFD accidently flush TLB after mapping to GPU because the vm update sequence number is increased by previous unmapping. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Stable-dep-of: edcfe22985d0 ("drm/amdkfd: Insert missing TLB flush on GFX10 and later") Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 6d6588b9beed..f374f112f7b7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1349,9 +1349,9 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type); static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) { - return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) || - (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && - dev->adev->sdma.instance[0].fw_version >= 18) || + return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3) || + KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) || + (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) || KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0); } From cdfcaa4e80430003dbba1bdb86f9fde5480ddbe5 Mon Sep 17 00:00:00 2001 From: Harish Kasiviswanathan Date: Mon, 11 Sep 2023 14:49:06 -0400 Subject: [PATCH 1747/2093] drm/amdkfd: Insert missing TLB flush on GFX10 and later [ Upstream commit edcfe22985d09ee8e2346c9217f5a52ab150099f ] Heavy-weight TLB flush is required after unmap on all GPUs for correctness and security. Signed-off-by: Harish Kasiviswanathan Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index f374f112f7b7..ec8a576ac5a9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1349,8 +1349,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type); static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) { - return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3) || - KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) || + return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) || (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) || KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0); } From cca10592ffd5e1abfe9479b4b056e81fb9872330 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 19 Sep 2023 11:44:42 +0930 Subject: [PATCH 1748/2093] btrfs: reset destination buffer when read_extent_buffer() gets invalid range [ Upstream commit 74ee79142c0a344d4eae2eb7012ebc4e82254109 ] Commit f98b6215d7d1 ("btrfs: extent_io: do extra check for extent buffer read write functions") changed how we handle invalid extent buffer range for read_extent_buffer(). Previously if the range is invalid we just set the destination to zero, but after the patch we do nothing and error out. This can lead to smatch static checker errors like: fs/btrfs/print-tree.c:186 print_uuid_item() error: uninitialized symbol 'subvol_id'. fs/btrfs/tests/extent-io-tests.c:338 check_eb_bitmap() error: uninitialized symbol 'has'. fs/btrfs/tests/extent-io-tests.c:353 check_eb_bitmap() error: uninitialized symbol 'has'. fs/btrfs/uuid-tree.c:203 btrfs_uuid_tree_remove() error: uninitialized symbol 'read_subid'. fs/btrfs/uuid-tree.c:353 btrfs_uuid_tree_iterate() error: uninitialized symbol 'subid_le'. fs/btrfs/uuid-tree.c:72 btrfs_uuid_tree_lookup() error: uninitialized symbol 'data'. fs/btrfs/volumes.c:7415 btrfs_dev_stats_value() error: uninitialized symbol 'val'. Fix those warnings by reverting back to the old memset() behavior. By this we keep the static checker happy and would still make a lot of noise when such invalid ranges are passed in. Reported-by: Dan Carpenter Fixes: f98b6215d7d1 ("btrfs: extent_io: do extra check for extent buffer read write functions") Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/extent_io.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 0ad69041954f..afcc96a1f427 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5184,8 +5184,14 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, char *dst = (char *)dstv; unsigned long i = get_eb_page_index(start); - if (check_eb_range(eb, start, len)) + if (check_eb_range(eb, start, len)) { + /* + * Invalid range hit, reset the memory, so callers won't get + * some random garbage for their uninitialzed memory. + */ + memset(dstv, 0, len); return; + } offset = get_eb_offset_in_page(eb, start); From c01b2e0ee22ef8b4dd7509a93aecc0ac0826bae4 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 18 Sep 2023 19:55:51 +0800 Subject: [PATCH 1749/2093] vfio/mdev: Fix a null-ptr-deref bug for mdev_unregister_parent() [ Upstream commit c777b11d34e0f47dbbc4b018ef65ad030f2b283a ] Inject fault while probing mdpy.ko, if kstrdup() of create_dir() fails in kobject_add_internal() in kobject_init_and_add() in mdev_type_add() in parent_create_sysfs_files(), it will return 0 and probe successfully. And when rmmod mdpy.ko, the mdpy_dev_exit() will call mdev_unregister_parent(), the mdev_type_remove() may traverse uninitialized parent->types[i] in parent_remove_sysfs_files(), and it will cause below null-ptr-deref. If mdev_type_add() fails, return the error code and kset_unregister() to fix the issue. general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] CPU: 2 PID: 10215 Comm: rmmod Tainted: G W N 6.6.0-rc2+ #20 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:__kobject_del+0x62/0x1c0 Code: 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 51 01 00 00 48 b8 00 00 00 00 00 fc ff df 48 8b 6b 28 48 8d 7d 10 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 24 01 00 00 48 8b 75 10 48 89 df 48 8d 6b 3c e8 RSP: 0018:ffff88810695fd30 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffffa0270268 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000000004 RDI: 0000000000000010 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed10233a4ef1 R10: ffff888119d2778b R11: 0000000063666572 R12: 0000000000000000 R13: fffffbfff404e2d4 R14: dffffc0000000000 R15: ffffffffa0271660 FS: 00007fbc81981540(0000) GS:ffff888119d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc14a142dc0 CR3: 0000000110a62003 CR4: 0000000000770ee0 DR0: ffffffff8fb0bce8 DR1: ffffffff8fb0bce9 DR2: ffffffff8fb0bcea DR3: ffffffff8fb0bceb DR6: 00000000fffe0ff0 DR7: 0000000000000600 PKRU: 55555554 Call Trace: ? die_addr+0x3d/0xa0 ? exc_general_protection+0x144/0x220 ? asm_exc_general_protection+0x22/0x30 ? __kobject_del+0x62/0x1c0 kobject_del+0x32/0x50 parent_remove_sysfs_files+0xd6/0x170 [mdev] mdev_unregister_parent+0xfb/0x190 [mdev] ? mdev_register_parent+0x270/0x270 [mdev] ? find_module_all+0x9d/0xe0 mdpy_dev_exit+0x17/0x63 [mdpy] __do_sys_delete_module.constprop.0+0x2fa/0x4b0 ? module_flags+0x300/0x300 ? __fput+0x4e7/0xa00 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fbc813221b7 Code: 73 01 c3 48 8b 0d d1 8c 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d a1 8c 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffe780e0648 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 00007ffe780e06a8 RCX: 00007fbc813221b7 RDX: 000000000000000a RSI: 0000000000000800 RDI: 000055e214df9b58 RBP: 000055e214df9af0 R08: 00007ffe780df5c1 R09: 0000000000000000 R10: 00007fbc8139ecc0 R11: 0000000000000206 R12: 00007ffe780e0870 R13: 00007ffe780e0ed0 R14: 000055e214df9260 R15: 000055e214df9af0 Modules linked in: mdpy(-) mdev vfio_iommu_type1 vfio [last unloaded: mdpy] Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace 0000000000000000 ]--- RIP: 0010:__kobject_del+0x62/0x1c0 Code: 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 51 01 00 00 48 b8 00 00 00 00 00 fc ff df 48 8b 6b 28 48 8d 7d 10 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 24 01 00 00 48 8b 75 10 48 89 df 48 8d 6b 3c e8 RSP: 0018:ffff88810695fd30 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffffa0270268 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000000004 RDI: 0000000000000010 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed10233a4ef1 R10: ffff888119d2778b R11: 0000000063666572 R12: 0000000000000000 R13: fffffbfff404e2d4 R14: dffffc0000000000 R15: ffffffffa0271660 FS: 00007fbc81981540(0000) GS:ffff888119d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc14a142dc0 CR3: 0000000110a62003 CR4: 0000000000770ee0 DR0: ffffffff8fb0bce8 DR1: ffffffff8fb0bce9 DR2: ffffffff8fb0bcea DR3: ffffffff8fb0bceb DR6: 00000000fffe0ff0 DR7: 0000000000000600 PKRU: 55555554 Kernel panic - not syncing: Fatal exception Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Rebooting in 1 seconds.. Fixes: da44c340c4fe ("vfio/mdev: simplify mdev_type handling") Signed-off-by: Jinjie Ruan Reviewed-by: Eric Farman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230918115551.1423193-1-ruanjinjie@huawei.com Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/mdev/mdev_sysfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index abe3359dd477..16b007c6bbb5 100644 --- a/drivers/vfio/mdev/mdev_sysfs.c +++ b/drivers/vfio/mdev/mdev_sysfs.c @@ -233,7 +233,8 @@ int parent_create_sysfs_files(struct mdev_parent *parent) out_err: while (--i >= 0) mdev_type_remove(parent->types[i]); - return 0; + kset_unregister(parent->mdev_types_kset); + return ret; } static ssize_t remove_store(struct device *dev, struct device_attribute *attr, From d3dc8acb60f84f21bf62dcdc6a319db4f0b01a4b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Sep 2023 09:06:56 +0200 Subject: [PATCH 1750/2093] MIPS: Alchemy: only build mmc support helpers if au1xmmc is enabled [ Upstream commit ef8f8f04a0b25e8f294b24350e8463a8d6a9ba0b ] While commit d4a5c59a955b ("mmc: au1xmmc: force non-modular build and remove symbol_get usage") to be built in, it can still build a kernel without MMC support and thuse no mmc_detect_change symbol at all. Add ifdefs to build the mmc support code in the alchemy arch code conditional on mmc support. Fixes: d4a5c59a955b ("mmc: au1xmmc: force non-modular build and remove symbol_get usage") Reported-by: kernel test robot Signed-off-by: Christoph Hellwig Acked-by: Randy Dunlap Tested-by: Randy Dunlap # build-tested Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/alchemy/devboards/db1000.c | 4 ++++ arch/mips/alchemy/devboards/db1200.c | 6 ++++++ arch/mips/alchemy/devboards/db1300.c | 4 ++++ 3 files changed, 14 insertions(+) diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index 50de86eb8784..3183df60ad33 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -164,6 +164,7 @@ static struct platform_device db1x00_audio_dev = { /******************************************************************************/ +#ifdef CONFIG_MMC_AU1X static irqreturn_t db1100_mmc_cd(int irq, void *ptr) { mmc_detect_change(ptr, msecs_to_jiffies(500)); @@ -369,6 +370,7 @@ static struct platform_device db1100_mmc1_dev = { .num_resources = ARRAY_SIZE(au1100_mmc1_res), .resource = au1100_mmc1_res, }; +#endif /* CONFIG_MMC_AU1X */ /******************************************************************************/ @@ -432,8 +434,10 @@ static struct platform_device *db1x00_devs[] = { static struct platform_device *db1100_devs[] = { &au1100_lcd_device, +#ifdef CONFIG_MMC_AU1X &db1100_mmc0_dev, &db1100_mmc1_dev, +#endif }; int __init db1000_dev_setup(void) diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c index 76080c71a2a7..f521874ebb07 100644 --- a/arch/mips/alchemy/devboards/db1200.c +++ b/arch/mips/alchemy/devboards/db1200.c @@ -326,6 +326,7 @@ static struct platform_device db1200_ide_dev = { /**********************************************************************/ +#ifdef CONFIG_MMC_AU1X /* SD carddetects: they're supposed to be edge-triggered, but ack * doesn't seem to work (CPLD Rev 2). Instead, the screaming one * is disabled and its counterpart enabled. The 200ms timeout is @@ -584,6 +585,7 @@ static struct platform_device pb1200_mmc1_dev = { .num_resources = ARRAY_SIZE(au1200_mmc1_res), .resource = au1200_mmc1_res, }; +#endif /* CONFIG_MMC_AU1X */ /**********************************************************************/ @@ -751,7 +753,9 @@ static struct platform_device db1200_audiodma_dev = { static struct platform_device *db1200_devs[] __initdata = { NULL, /* PSC0, selected by S6.8 */ &db1200_ide_dev, +#ifdef CONFIG_MMC_AU1X &db1200_mmc0_dev, +#endif &au1200_lcd_dev, &db1200_eth_dev, &db1200_nand_dev, @@ -762,7 +766,9 @@ static struct platform_device *db1200_devs[] __initdata = { }; static struct platform_device *pb1200_devs[] __initdata = { +#ifdef CONFIG_MMC_AU1X &pb1200_mmc1_dev, +#endif }; /* Some peripheral base addresses differ on the PB1200 */ diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c index ff61901329c6..d377e043b49f 100644 --- a/arch/mips/alchemy/devboards/db1300.c +++ b/arch/mips/alchemy/devboards/db1300.c @@ -450,6 +450,7 @@ static struct platform_device db1300_ide_dev = { /**********************************************************************/ +#ifdef CONFIG_MMC_AU1X static irqreturn_t db1300_mmc_cd(int irq, void *ptr) { disable_irq_nosync(irq); @@ -632,6 +633,7 @@ static struct platform_device db1300_sd0_dev = { .resource = au1300_sd0_res, .num_resources = ARRAY_SIZE(au1300_sd0_res), }; +#endif /* CONFIG_MMC_AU1X */ /**********************************************************************/ @@ -767,8 +769,10 @@ static struct platform_device *db1300_dev[] __initdata = { &db1300_5waysw_dev, &db1300_nand_dev, &db1300_ide_dev, +#ifdef CONFIG_MMC_AU1X &db1300_sd0_dev, &db1300_sd1_dev, +#endif &db1300_lcd_dev, &db1300_ac97_dev, &db1300_i2s_dev, From 404b8bc41872b9d5ebf1bfb8b6fa02cfb8b00449 Mon Sep 17 00:00:00 2001 From: Charles Kearney Date: Wed, 20 Sep 2023 21:53:39 +0000 Subject: [PATCH 1751/2093] spi: spi-gxp: BUG: Correct spi write return value [ Upstream commit 1a8196a93e493c0a50b800cb09cef60b124eee15 ] Bug fix to correct return value of gxp_spi_write function to zero. Completion of succesful operation should return zero. Fixes: 730bc8ba5e9e spi: spi-gxp: Add support for HPE GXP SoCs Signed-off-by: Charles Kearney Link: https://lore.kernel.org/r/20230920215339.4125856-2-charles.kearney@hpe.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-gxp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-gxp.c b/drivers/spi/spi-gxp.c index c900c2f39b57..21b07e251851 100644 --- a/drivers/spi/spi-gxp.c +++ b/drivers/spi/spi-gxp.c @@ -195,7 +195,7 @@ static ssize_t gxp_spi_write(struct gxp_spi_chip *chip, const struct spi_mem_op return ret; } - return write_len; + return 0; } static int do_gxp_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op) From e6389d61b72023f8a82fc3f8bd55002c172d96be Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 3 Apr 2023 21:02:42 +0200 Subject: [PATCH 1752/2093] drm/bridge: ti-sn65dsi83: Do not generate HFP/HBP/HSA and EOT packet [ Upstream commit ca161b259cc84fe1f4a2ce4c73c3832cf6f713f1 ] Do not generate the HS front and back porch gaps, the HSA gap and EOT packet, as per "SN65DSI83 datasheet SLLSEC1I - SEPTEMBER 2012 - REVISED OCTOBER 2020", page 22, these packets are not required. This makes the TI SN65DSI83 bridge work with Samsung DSIM on i.MX8MN. Signed-off-by: Marek Vasut Reviewed-by: Laurent Pinchart Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230403190242.224490-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/ti-sn65dsi83.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 55efd3eb6672..3f43b44145a8 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -655,7 +655,9 @@ static int sn65dsi83_host_attach(struct sn65dsi83 *ctx) dsi->lanes = dsi_lanes; dsi->format = MIPI_DSI_FMT_RGB888; - dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | + MIPI_DSI_MODE_VIDEO_NO_HFP | MIPI_DSI_MODE_VIDEO_NO_HBP | + MIPI_DSI_MODE_VIDEO_NO_HSA | MIPI_DSI_MODE_NO_EOT_PACKET; ret = devm_mipi_dsi_attach(dev, dsi); if (ret < 0) { From 771eb7c3f3fb1912cef4f6a26377aade2b78269c Mon Sep 17 00:00:00 2001 From: Julien Panis Date: Mon, 21 Aug 2023 16:24:18 +0200 Subject: [PATCH 1753/2093] bus: ti-sysc: Use fsleep() instead of usleep_range() in sysc_reset() [ Upstream commit d929b2b7464f95ec01e47f560b1e687482ba8929 ] The am335x-evm started producing boot errors because of subtle timing changes: Unhandled fault: external abort on non-linefetch (0x1008) at 0xf03c1010 ... sysc_reset from sysc_probe+0xf60/0x1514 sysc_probe from platform_probe+0x5c/0xbc ... The fix consists in using the appropriate sleep function in sysc reset. For flexible sleeping, fsleep is recommended. Here, sysc delay parameter can take any value in [0 - 255] us range. As a result, fsleep() should be used, calling udelay() for a sysc delay lower than 10 us. Signed-off-by: Julien Panis Fixes: e709ed70d122 ("bus: ti-sysc: Fix missing reset delay handling") Message-ID: <20230821-fix-ti-sysc-reset-v1-1-5a0a5d8fae55@baylibre.com> Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index ddde1427c90c..6ac79417b512 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2166,8 +2166,7 @@ static int sysc_reset(struct sysc *ddata) } if (ddata->cfg.srst_udelay) - usleep_range(ddata->cfg.srst_udelay, - ddata->cfg.srst_udelay * 2); + fsleep(ddata->cfg.srst_udelay); if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); From 3a21635aed622a0de22cd5be01da370a319354e9 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Wed, 6 Sep 2023 18:34:42 -0500 Subject: [PATCH 1754/2093] bus: ti-sysc: Fix missing AM35xx SoC matching [ Upstream commit 11729caa520950e17cd81bc43ffc477c46cf791e ] Commit feaa8baee82a ("bus: ti-sysc: Implement SoC revision handling") created a list of SoC types searching for strings based on names and wildcards which associates the SoC to different families. The OMAP34xx and OMAP35xx are treated as SOC_3430 while OMAP36xx and OMAP37xx are treated as SOC_3630, but the AM35xx isn't listed. The AM35xx is mostly an OMAP3430, and a later commit a12315d6d270 ("bus: ti-sysc: Make omap3 gpt12 quirk handling SoC specific") looks for the SOC type and behaves in a certain way if it's SOC_3430. This caused a regression on the AM3517 causing it to return two errors: ti-sysc: probe of 48318000.target-module failed with error -16 ti-sysc: probe of 49032000.target-module failed with error -16 Fix this by treating the creating SOC_AM35 and inserting it between the SOC_3430 and SOC_3630. If it is treaed the same way as the SOC_3430 when checking the status of sysc_check_active_timer, the error conditions will disappear. Fixes: a12315d6d270 ("bus: ti-sysc: Make omap3 gpt12 quirk handling SoC specific") Fixes: feaa8baee82a ("bus: ti-sysc: Implement SoC revision handling") Signed-off-by: Adam Ford Message-ID: <20230906233442.270835-1-aford173@gmail.com> Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 6ac79417b512..d56e7b61bb5a 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -38,6 +38,7 @@ enum sysc_soc { SOC_2420, SOC_2430, SOC_3430, + SOC_AM35, SOC_3630, SOC_4430, SOC_4460, @@ -1878,7 +1879,7 @@ static void sysc_pre_reset_quirk_dss(struct sysc *ddata) dev_warn(ddata->dev, "%s: timed out %08x !+ %08x\n", __func__, val, irq_mask); - if (sysc_soc->soc == SOC_3430) { + if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35) { /* Clear DSS_SDI_CONTROL */ sysc_write(ddata, 0x44, 0); @@ -3042,6 +3043,7 @@ static void ti_sysc_idle(struct work_struct *work) static const struct soc_device_attribute sysc_soc_match[] = { SOC_FLAG("OMAP242*", SOC_2420), SOC_FLAG("OMAP243*", SOC_2430), + SOC_FLAG("AM35*", SOC_AM35), SOC_FLAG("OMAP3[45]*", SOC_3430), SOC_FLAG("OMAP3[67]*", SOC_3630), SOC_FLAG("OMAP443*", SOC_4430), @@ -3248,7 +3250,7 @@ static int sysc_check_active_timer(struct sysc *ddata) * can be dropped if we stop supporting old beagleboard revisions * A to B4 at some point. */ - if (sysc_soc->soc == SOC_3430) + if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35) error = -ENXIO; else error = -EBUSY; From a135c881381558552d3245654b5703a1451cb75f Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 17 Jul 2023 17:12:45 +0100 Subject: [PATCH 1755/2093] firmware: arm_scmi: Harden perf domain info access [ Upstream commit 3da82112355bba263597fcbb24d275fc57e69e7e ] Harden internal accesses to domain info in the SCMI perf protocol. Signed-off-by: Cristian Marussi Link: https://lore.kernel.org/r/20230717161246.1761777-2-cristian.marussi@arm.com Signed-off-by: Sudeep Holla Stable-dep-of: c3638b851bc1 ("firmware: arm_scmi: Fixup perf power-cost/microwatt support") Signed-off-by: Sasha Levin --- drivers/firmware/arm_scmi/perf.c | 89 +++++++++++++++++++++++--------- 1 file changed, 64 insertions(+), 25 deletions(-) diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index ecf5c4de851b..43dd242ecc49 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -139,7 +139,7 @@ struct perf_dom_info { struct scmi_perf_info { u32 version; - int num_domains; + u16 num_domains; enum scmi_power_scale power_scale; u64 stats_addr; u32 stats_size; @@ -356,11 +356,26 @@ static int scmi_perf_mb_limits_set(const struct scmi_protocol_handle *ph, return ret; } +static inline struct perf_dom_info * +scmi_perf_domain_lookup(const struct scmi_protocol_handle *ph, u32 domain) +{ + struct scmi_perf_info *pi = ph->get_priv(ph); + + if (domain >= pi->num_domains) + return ERR_PTR(-EINVAL); + + return pi->dom_info + domain; +} + static int scmi_perf_limits_set(const struct scmi_protocol_handle *ph, u32 domain, u32 max_perf, u32 min_perf) { struct scmi_perf_info *pi = ph->get_priv(ph); - struct perf_dom_info *dom = pi->dom_info + domain; + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); if (PROTOCOL_REV_MAJOR(pi->version) >= 0x3 && !max_perf && !min_perf) return -EINVAL; @@ -408,8 +423,11 @@ static int scmi_perf_mb_limits_get(const struct scmi_protocol_handle *ph, static int scmi_perf_limits_get(const struct scmi_protocol_handle *ph, u32 domain, u32 *max_perf, u32 *min_perf) { - struct scmi_perf_info *pi = ph->get_priv(ph); - struct perf_dom_info *dom = pi->dom_info + domain; + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); if (dom->fc_info && dom->fc_info[PERF_FC_LIMIT].get_addr) { struct scmi_fc_info *fci = &dom->fc_info[PERF_FC_LIMIT]; @@ -449,8 +467,11 @@ static int scmi_perf_mb_level_set(const struct scmi_protocol_handle *ph, static int scmi_perf_level_set(const struct scmi_protocol_handle *ph, u32 domain, u32 level, bool poll) { - struct scmi_perf_info *pi = ph->get_priv(ph); - struct perf_dom_info *dom = pi->dom_info + domain; + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); if (dom->fc_info && dom->fc_info[PERF_FC_LEVEL].set_addr) { struct scmi_fc_info *fci = &dom->fc_info[PERF_FC_LEVEL]; @@ -490,8 +511,11 @@ static int scmi_perf_mb_level_get(const struct scmi_protocol_handle *ph, static int scmi_perf_level_get(const struct scmi_protocol_handle *ph, u32 domain, u32 *level, bool poll) { - struct scmi_perf_info *pi = ph->get_priv(ph); - struct perf_dom_info *dom = pi->dom_info + domain; + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); if (dom->fc_info && dom->fc_info[PERF_FC_LEVEL].get_addr) { *level = ioread32(dom->fc_info[PERF_FC_LEVEL].get_addr); @@ -574,13 +598,14 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph, unsigned long freq; struct scmi_opp *opp; struct perf_dom_info *dom; - struct scmi_perf_info *pi = ph->get_priv(ph); domain = scmi_dev_domain_id(dev); if (domain < 0) - return domain; + return -EINVAL; - dom = pi->dom_info + domain; + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); for (opp = dom->opp, idx = 0; idx < dom->opp_count; idx++, opp++) { freq = opp->perf * dom->mult_factor; @@ -603,14 +628,17 @@ static int scmi_dvfs_transition_latency_get(const struct scmi_protocol_handle *ph, struct device *dev) { + int domain; struct perf_dom_info *dom; - struct scmi_perf_info *pi = ph->get_priv(ph); - int domain = scmi_dev_domain_id(dev); + domain = scmi_dev_domain_id(dev); if (domain < 0) - return domain; + return -EINVAL; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); - dom = pi->dom_info + domain; /* uS to nS */ return dom->opp[dom->opp_count - 1].trans_latency_us * 1000; } @@ -618,8 +646,11 @@ scmi_dvfs_transition_latency_get(const struct scmi_protocol_handle *ph, static int scmi_dvfs_freq_set(const struct scmi_protocol_handle *ph, u32 domain, unsigned long freq, bool poll) { - struct scmi_perf_info *pi = ph->get_priv(ph); - struct perf_dom_info *dom = pi->dom_info + domain; + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); return scmi_perf_level_set(ph, domain, freq / dom->mult_factor, poll); } @@ -630,11 +661,14 @@ static int scmi_dvfs_freq_get(const struct scmi_protocol_handle *ph, u32 domain, int ret; u32 level; struct scmi_perf_info *pi = ph->get_priv(ph); - struct perf_dom_info *dom = pi->dom_info + domain; ret = scmi_perf_level_get(ph, domain, &level, poll); - if (!ret) + if (!ret) { + struct perf_dom_info *dom = pi->dom_info + domain; + + /* Note domain is validated implicitly by scmi_perf_level_get */ *freq = level * dom->mult_factor; + } return ret; } @@ -643,15 +677,14 @@ static int scmi_dvfs_est_power_get(const struct scmi_protocol_handle *ph, u32 domain, unsigned long *freq, unsigned long *power) { - struct scmi_perf_info *pi = ph->get_priv(ph); struct perf_dom_info *dom; unsigned long opp_freq; int idx, ret = -EINVAL; struct scmi_opp *opp; - dom = pi->dom_info + domain; - if (!dom) - return -EIO; + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return PTR_ERR(dom); for (opp = dom->opp, idx = 0; idx < dom->opp_count; idx++, opp++) { opp_freq = opp->perf * dom->mult_factor; @@ -670,10 +703,16 @@ static int scmi_dvfs_est_power_get(const struct scmi_protocol_handle *ph, static bool scmi_fast_switch_possible(const struct scmi_protocol_handle *ph, struct device *dev) { + int domain; struct perf_dom_info *dom; - struct scmi_perf_info *pi = ph->get_priv(ph); - dom = pi->dom_info + scmi_dev_domain_id(dev); + domain = scmi_dev_domain_id(dev); + if (domain < 0) + return false; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return false; return dom->fc_info && dom->fc_info[PERF_FC_LEVEL].set_addr; } From 64adb41644fcd2d6127a2b0aeae5c9fcdb1ecbbe Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Sat, 12 Aug 2023 02:18:18 +0530 Subject: [PATCH 1756/2093] firmware: arm_scmi: Fixup perf power-cost/microwatt support [ Upstream commit c3638b851bc1ca0022dca9d6ca4beaa6ef03a216 ] The perf power scale value would currently be reported as bogowatts if the platform firmware supports microwatt power scale and meets the perf major version requirements. Fix this by populating version information in the driver private data before the call to protocol attributes is made. CC: Chandra Sekhar Lingutla Fixes: 3630cd8130ce ("firmware: arm_scmi: Add SCMI v3.1 perf power-cost in microwatts") Signed-off-by: Sibi Sankar Reviewed-by: Cristian Marussi Link: https://lore.kernel.org/r/20230811204818.30928-1-quic_sibis@quicinc.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_scmi/perf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 43dd242ecc49..431bda9165c3 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -858,6 +858,8 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph) if (!pinfo) return -ENOMEM; + pinfo->version = version; + ret = scmi_perf_attributes_get(ph, pinfo); if (ret) return ret; @@ -877,8 +879,6 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph) scmi_perf_domain_init_fc(ph, domain, &dom->fc_info); } - pinfo->version = version; - return ph->set_priv(ph, pinfo); } From 1ea6975aa68aeb05a8ee95a64023d1c6edea54f7 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Wed, 6 Sep 2023 01:48:15 -0700 Subject: [PATCH 1757/2093] power: supply: mt6370: Fix missing error code in mt6370_chg_toggle_cfo() [ Upstream commit 779873ec81306d2c40c459fa7c91a5d40655510d ] When mt6370_chg_field_get() suceeds, ret is set to zero and returning zero when flash led is still in strobe mode looks incorrect. Fixes: 233cb8a47d65 ("power: supply: mt6370: Add MediaTek MT6370 charger driver") Signed-off-by: Harshit Mogalapalli Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: ChiaEn Wu Link: https://lore.kernel.org/r/20230906084815.2827930-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/mt6370-charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/mt6370-charger.c b/drivers/power/supply/mt6370-charger.c index f27dae5043f5..a9641bd3d8cf 100644 --- a/drivers/power/supply/mt6370-charger.c +++ b/drivers/power/supply/mt6370-charger.c @@ -324,7 +324,7 @@ static int mt6370_chg_toggle_cfo(struct mt6370_priv *priv) if (fl_strobe) { dev_err(priv->dev, "Flash led is still in strobe mode\n"); - return ret; + return -EINVAL; } /* cfo off */ From efad31b6c062f61b7a61c8b1a200d0a74087a35a Mon Sep 17 00:00:00 2001 From: Zhifeng Tang Date: Thu, 24 Aug 2023 17:26:24 +0800 Subject: [PATCH 1758/2093] clk: sprd: Fix thm_parents incorrect configuration [ Upstream commit b7b20cfe6f849c2682c5f7d3f50ede6321a5d04c ] The thm*_clk have two clock sources 32k and 250k,excluding 32m. Fixes: af3bd36573e3 ("clk: sprd: Add clocks support for UMS512") Signed-off-by: Zhifeng Tang Acked-by: Chunyan Zhang Reviewed-by: Baolin Wang Link: https://lore.kernel.org/r/20230824092624.20020-1-zhifeng.tang@unisoc.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/sprd/ums512-clk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sprd/ums512-clk.c b/drivers/clk/sprd/ums512-clk.c index fc25bdd85e4e..f43bb10bd5ae 100644 --- a/drivers/clk/sprd/ums512-clk.c +++ b/drivers/clk/sprd/ums512-clk.c @@ -800,7 +800,7 @@ static SPRD_MUX_CLK_DATA(uart1_clk, "uart1-clk", uart_parents, 0x250, 0, 3, UMS512_MUX_FLAG); static const struct clk_parent_data thm_parents[] = { - { .fw_name = "ext-32m" }, + { .fw_name = "ext-32k" }, { .hw = &clk_250k.hw }, }; static SPRD_MUX_CLK_DATA(thm0_clk, "thm0-clk", thm_parents, From ea4efaf54685d66c25b9bab7b1462361e991e6c3 Mon Sep 17 00:00:00 2001 From: Timo Alho Date: Tue, 12 Sep 2023 14:29:50 +0300 Subject: [PATCH 1759/2093] clk: tegra: fix error return case for recalc_rate [ Upstream commit a47b44fbb13f5e7a981b4515dcddc93a321ae89c ] tegra-bpmp clocks driver makes implicit conversion of signed error code to unsigned value in recalc_rate operation. The behavior for recalc_rate, according to it's specification, should be that "If the driver cannot figure out a rate for this clock, it must return 0." Fixes: ca6f2796eef7 ("clk: tegra: Add BPMP clock driver") Signed-off-by: Timo Alho Signed-off-by: Mikko Perttunen Link: https://lore.kernel.org/r/20230912112951.2330497-1-cyndis@kapsi.fi Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/tegra/clk-bpmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-bpmp.c b/drivers/clk/tegra/clk-bpmp.c index d82a71f10c2c..39241662a412 100644 --- a/drivers/clk/tegra/clk-bpmp.c +++ b/drivers/clk/tegra/clk-bpmp.c @@ -159,7 +159,7 @@ static unsigned long tegra_bpmp_clk_recalc_rate(struct clk_hw *hw, err = tegra_bpmp_clk_transfer(clk->bpmp, &msg); if (err < 0) - return err; + return 0; return response.rate; } From fe4da07a7f1b4706c9d6d375b9661bd9eb5a4f91 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 2 Oct 2022 11:20:02 +0200 Subject: [PATCH 1760/2093] ARM: dts: omap: correct indentation [ Upstream commit 8ae9c7a69fa14e95d032e64d8d758e3f85bee132 ] Do not use spaces for indentation. Link: https://lore.kernel.org/r/20221002092002.68880-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Stable-dep-of: 6469b2feade8 ("ARM: dts: ti: omap: Fix bandgap thermal cells addressing for omap3/4") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi | 6 +-- arch/arm/boot/dts/omap-gpmc-smsc9221.dtsi | 6 +-- arch/arm/boot/dts/omap3-cm-t3517.dts | 12 ++--- arch/arm/boot/dts/omap3-gta04.dtsi | 6 +-- arch/arm/boot/dts/omap3-ldp.dts | 2 +- arch/arm/boot/dts/omap3-n900.dts | 38 +++++++-------- arch/arm/boot/dts/omap3-zoom3.dts | 44 +++++++++--------- arch/arm/boot/dts/omap4-cpu-thermal.dtsi | 24 +++++----- arch/arm/boot/dts/omap5-cm-t54.dts | 56 +++++++++++------------ 9 files changed, 97 insertions(+), 97 deletions(-) diff --git a/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi b/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi index ce6c235f68ec..3046ec572632 100644 --- a/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi +++ b/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi @@ -8,9 +8,9 @@ / { vddvario: regulator-vddvario { - compatible = "regulator-fixed"; - regulator-name = "vddvario"; - regulator-always-on; + compatible = "regulator-fixed"; + regulator-name = "vddvario"; + regulator-always-on; }; vdd33a: regulator-vdd33a { diff --git a/arch/arm/boot/dts/omap-gpmc-smsc9221.dtsi b/arch/arm/boot/dts/omap-gpmc-smsc9221.dtsi index e7534fe9c53c..bc8961f3690f 100644 --- a/arch/arm/boot/dts/omap-gpmc-smsc9221.dtsi +++ b/arch/arm/boot/dts/omap-gpmc-smsc9221.dtsi @@ -12,9 +12,9 @@ / { vddvario: regulator-vddvario { - compatible = "regulator-fixed"; - regulator-name = "vddvario"; - regulator-always-on; + compatible = "regulator-fixed"; + regulator-name = "vddvario"; + regulator-always-on; }; vdd33a: regulator-vdd33a { diff --git a/arch/arm/boot/dts/omap3-cm-t3517.dts b/arch/arm/boot/dts/omap3-cm-t3517.dts index 3b8349094baa..f25c0a84a190 100644 --- a/arch/arm/boot/dts/omap3-cm-t3517.dts +++ b/arch/arm/boot/dts/omap3-cm-t3517.dts @@ -11,12 +11,12 @@ / { model = "CompuLab CM-T3517"; compatible = "compulab,omap3-cm-t3517", "ti,am3517", "ti,omap3"; - vmmc: regulator-vmmc { - compatible = "regulator-fixed"; - regulator-name = "vmmc"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - }; + vmmc: regulator-vmmc { + compatible = "regulator-fixed"; + regulator-name = "vmmc"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; wl12xx_vmmc2: wl12xx_vmmc2 { compatible = "regulator-fixed"; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 2dbee248a126..da578719ac5a 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -332,7 +332,7 @@ OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0) /* dss_data21.dss_data21 */ OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0) /* dss_data22.dss_data22 */ OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0) /* dss_data23.dss_data23 */ >; - }; + }; gps_pins: pinmux_gps_pins { pinctrl-single,pins = < @@ -869,8 +869,8 @@ &mcbsp4 { /* GSM voice PCM */ }; &hdqw1w { - pinctrl-names = "default"; - pinctrl-0 = <&hdq_pins>; + pinctrl-names = "default"; + pinctrl-0 = <&hdq_pins>; }; /* image signal processor within OMAP3 SoC */ diff --git a/arch/arm/boot/dts/omap3-ldp.dts b/arch/arm/boot/dts/omap3-ldp.dts index 36fc8805e0c1..85f33bbb566f 100644 --- a/arch/arm/boot/dts/omap3-ldp.dts +++ b/arch/arm/boot/dts/omap3-ldp.dts @@ -301,5 +301,5 @@ &usb_otg_hs { &vaux1 { /* Needed for ads7846 */ - regulator-name = "vcc"; + regulator-name = "vcc"; }; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index dd7971556449..98a67581bdd2 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -236,27 +236,27 @@ gpmc_pins: pinmux_gpmc_pins { pinctrl-single,pins = < /* address lines */ - OMAP3_CORE1_IOPAD(0x207a, PIN_OUTPUT | MUX_MODE0) /* gpmc_a1.gpmc_a1 */ - OMAP3_CORE1_IOPAD(0x207c, PIN_OUTPUT | MUX_MODE0) /* gpmc_a2.gpmc_a2 */ - OMAP3_CORE1_IOPAD(0x207e, PIN_OUTPUT | MUX_MODE0) /* gpmc_a3.gpmc_a3 */ + OMAP3_CORE1_IOPAD(0x207a, PIN_OUTPUT | MUX_MODE0) /* gpmc_a1.gpmc_a1 */ + OMAP3_CORE1_IOPAD(0x207c, PIN_OUTPUT | MUX_MODE0) /* gpmc_a2.gpmc_a2 */ + OMAP3_CORE1_IOPAD(0x207e, PIN_OUTPUT | MUX_MODE0) /* gpmc_a3.gpmc_a3 */ /* data lines, gpmc_d0..d7 not muxable according to TRM */ - OMAP3_CORE1_IOPAD(0x209e, PIN_INPUT | MUX_MODE0) /* gpmc_d8.gpmc_d8 */ - OMAP3_CORE1_IOPAD(0x20a0, PIN_INPUT | MUX_MODE0) /* gpmc_d9.gpmc_d9 */ - OMAP3_CORE1_IOPAD(0x20a2, PIN_INPUT | MUX_MODE0) /* gpmc_d10.gpmc_d10 */ - OMAP3_CORE1_IOPAD(0x20a4, PIN_INPUT | MUX_MODE0) /* gpmc_d11.gpmc_d11 */ - OMAP3_CORE1_IOPAD(0x20a6, PIN_INPUT | MUX_MODE0) /* gpmc_d12.gpmc_d12 */ - OMAP3_CORE1_IOPAD(0x20a8, PIN_INPUT | MUX_MODE0) /* gpmc_d13.gpmc_d13 */ - OMAP3_CORE1_IOPAD(0x20aa, PIN_INPUT | MUX_MODE0) /* gpmc_d14.gpmc_d14 */ - OMAP3_CORE1_IOPAD(0x20ac, PIN_INPUT | MUX_MODE0) /* gpmc_d15.gpmc_d15 */ + OMAP3_CORE1_IOPAD(0x209e, PIN_INPUT | MUX_MODE0) /* gpmc_d8.gpmc_d8 */ + OMAP3_CORE1_IOPAD(0x20a0, PIN_INPUT | MUX_MODE0) /* gpmc_d9.gpmc_d9 */ + OMAP3_CORE1_IOPAD(0x20a2, PIN_INPUT | MUX_MODE0) /* gpmc_d10.gpmc_d10 */ + OMAP3_CORE1_IOPAD(0x20a4, PIN_INPUT | MUX_MODE0) /* gpmc_d11.gpmc_d11 */ + OMAP3_CORE1_IOPAD(0x20a6, PIN_INPUT | MUX_MODE0) /* gpmc_d12.gpmc_d12 */ + OMAP3_CORE1_IOPAD(0x20a8, PIN_INPUT | MUX_MODE0) /* gpmc_d13.gpmc_d13 */ + OMAP3_CORE1_IOPAD(0x20aa, PIN_INPUT | MUX_MODE0) /* gpmc_d14.gpmc_d14 */ + OMAP3_CORE1_IOPAD(0x20ac, PIN_INPUT | MUX_MODE0) /* gpmc_d15.gpmc_d15 */ /* * gpmc_ncs0, gpmc_nadv_ale, gpmc_noe, gpmc_nwe, gpmc_wait0 not muxable * according to TRM. OneNAND seems to require PIN_INPUT on clock. */ - OMAP3_CORE1_IOPAD(0x20b0, PIN_OUTPUT | MUX_MODE0) /* gpmc_ncs1.gpmc_ncs1 */ - OMAP3_CORE1_IOPAD(0x20be, PIN_INPUT | MUX_MODE0) /* gpmc_clk.gpmc_clk */ - >; + OMAP3_CORE1_IOPAD(0x20b0, PIN_OUTPUT | MUX_MODE0) /* gpmc_ncs1.gpmc_ncs1 */ + OMAP3_CORE1_IOPAD(0x20be, PIN_INPUT | MUX_MODE0) /* gpmc_clk.gpmc_clk */ + >; }; i2c1_pins: pinmux_i2c1_pins { @@ -738,12 +738,12 @@ tpa6130a2: tpa6130a2@60 { si4713: si4713@63 { compatible = "silabs,si4713"; - reg = <0x63>; + reg = <0x63>; - interrupts-extended = <&gpio2 21 IRQ_TYPE_EDGE_FALLING>; /* 53 */ - reset-gpios = <&gpio6 3 GPIO_ACTIVE_HIGH>; /* 163 */ - vio-supply = <&vio>; - vdd-supply = <&vaux1>; + interrupts-extended = <&gpio2 21 IRQ_TYPE_EDGE_FALLING>; /* 53 */ + reset-gpios = <&gpio6 3 GPIO_ACTIVE_HIGH>; /* 163 */ + vio-supply = <&vio>; + vdd-supply = <&vaux1>; }; bq24150a: bq24150a@6b { diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts index 0482676d1830..ce58b1f208e8 100644 --- a/arch/arm/boot/dts/omap3-zoom3.dts +++ b/arch/arm/boot/dts/omap3-zoom3.dts @@ -23,9 +23,9 @@ memory@80000000 { }; vddvario: regulator-vddvario { - compatible = "regulator-fixed"; - regulator-name = "vddvario"; - regulator-always-on; + compatible = "regulator-fixed"; + regulator-name = "vddvario"; + regulator-always-on; }; vdd33a: regulator-vdd33a { @@ -84,28 +84,28 @@ OMAP3_CORE1_IOPAD(0x21d0, PIN_INPUT_PULLUP | MUX_MODE3) /* mcspi1_cs1.sdmmc3_cmd uart1_pins: pinmux_uart1_pins { pinctrl-single,pins = < - OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT | MUX_MODE0) /* uart1_cts.uart1_cts */ - OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE0) /* uart1_rts.uart1_rts */ - OMAP3_CORE1_IOPAD(0x2182, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart1_rx.uart1_rx */ - OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE0) /* uart1_tx.uart1_tx */ + OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT | MUX_MODE0) /* uart1_cts.uart1_cts */ + OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE0) /* uart1_rts.uart1_rts */ + OMAP3_CORE1_IOPAD(0x2182, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart1_rx.uart1_rx */ + OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE0) /* uart1_tx.uart1_tx */ >; }; uart2_pins: pinmux_uart2_pins { pinctrl-single,pins = < - OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */ - OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ - OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */ - OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */ + OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */ + OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ + OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */ + OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */ >; }; uart3_pins: pinmux_uart3_pins { pinctrl-single,pins = < - OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */ - OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */ - OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */ - OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */ + OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */ + OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */ + OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */ + OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */ >; }; @@ -205,22 +205,22 @@ wlcore: wlcore@2 { }; &uart1 { - pinctrl-names = "default"; - pinctrl-0 = <&uart1_pins>; + pinctrl-names = "default"; + pinctrl-0 = <&uart1_pins>; }; &uart2 { - pinctrl-names = "default"; - pinctrl-0 = <&uart2_pins>; + pinctrl-names = "default"; + pinctrl-0 = <&uart2_pins>; }; &uart3 { - pinctrl-names = "default"; - pinctrl-0 = <&uart3_pins>; + pinctrl-names = "default"; + pinctrl-0 = <&uart3_pins>; }; &uart4 { - status = "disabled"; + status = "disabled"; }; &usb_otg_hs { diff --git a/arch/arm/boot/dts/omap4-cpu-thermal.dtsi b/arch/arm/boot/dts/omap4-cpu-thermal.dtsi index 4d7eeb133dad..801b4f10350c 100644 --- a/arch/arm/boot/dts/omap4-cpu-thermal.dtsi +++ b/arch/arm/boot/dts/omap4-cpu-thermal.dtsi @@ -13,20 +13,20 @@ cpu_thermal: cpu_thermal { polling-delay = <1000>; /* milliseconds */ /* sensor ID */ - thermal-sensors = <&bandgap 0>; + thermal-sensors = <&bandgap 0>; cpu_trips: trips { - cpu_alert0: cpu_alert { - temperature = <100000>; /* millicelsius */ - hysteresis = <2000>; /* millicelsius */ - type = "passive"; - }; - cpu_crit: cpu_crit { - temperature = <125000>; /* millicelsius */ - hysteresis = <2000>; /* millicelsius */ - type = "critical"; - }; - }; + cpu_alert0: cpu_alert { + temperature = <100000>; /* millicelsius */ + hysteresis = <2000>; /* millicelsius */ + type = "passive"; + }; + cpu_crit: cpu_crit { + temperature = <125000>; /* millicelsius */ + hysteresis = <2000>; /* millicelsius */ + type = "critical"; + }; + }; cpu_cooling_maps: cooling-maps { map0 { diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index e62ea8b6d53f..af288d63a26a 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -84,36 +84,36 @@ led1 { }; lcd0: display { - compatible = "startek,startek-kd050c", "panel-dpi"; - label = "lcd"; + compatible = "startek,startek-kd050c", "panel-dpi"; + label = "lcd"; - pinctrl-names = "default"; - pinctrl-0 = <&lcd_pins>; + pinctrl-names = "default"; + pinctrl-0 = <&lcd_pins>; - enable-gpios = <&gpio8 3 GPIO_ACTIVE_HIGH>; + enable-gpios = <&gpio8 3 GPIO_ACTIVE_HIGH>; - panel-timing { - clock-frequency = <33000000>; - hactive = <800>; - vactive = <480>; - hfront-porch = <40>; - hback-porch = <40>; - hsync-len = <43>; - vback-porch = <29>; - vfront-porch = <13>; - vsync-len = <3>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; + panel-timing { + clock-frequency = <33000000>; + hactive = <800>; + vactive = <480>; + hfront-porch = <40>; + hback-porch = <40>; + hsync-len = <43>; + vback-porch = <29>; + vfront-porch = <13>; + vsync-len = <3>; + hsync-active = <0>; + vsync-active = <0>; + de-active = <1>; + pixelclk-active = <1>; + }; - port { - lcd_in: endpoint { - remote-endpoint = <&dpi_lcd_out>; - }; - }; - }; + port { + lcd_in: endpoint { + remote-endpoint = <&dpi_lcd_out>; + }; + }; + }; hdmi0: connector0 { compatible = "hdmi-connector"; @@ -644,8 +644,8 @@ &usbhsehci { }; &usb3 { - extcon = <&extcon_usb3>; - vbus-supply = <&smps10_out1_reg>; + extcon = <&extcon_usb3>; + vbus-supply = <&smps10_out1_reg>; }; &cpu0 { From 4ccb05618b4d2aa54bc342979d69985d3141bd81 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 11 Sep 2023 07:07:38 +0300 Subject: [PATCH 1761/2093] ARM: dts: ti: omap: Fix bandgap thermal cells addressing for omap3/4 [ Upstream commit 6469b2feade8fd82d224dd3734e146536f3e9f0e ] Fix "thermal_sys: cpu_thermal: Failed to read thermal-sensors cells: -2" error on boot for omap3/4. This is caused by wrong addressing in the dts for bandgap sensor for single sensor instances. Note that omap4-cpu-thermal.dtsi is shared across omap4/5 and dra7, so we can't just change the addressing in omap4-cpu-thermal.dtsi. Cc: Ivaylo Dimitrov Cc: Carl Philipp Klemm Cc: Merlijn Wajer Cc: Pavel Machek Reviewed-by: Sebastian Reichel Fixes: a761d517bbb1 ("ARM: dts: omap3: Add cpu_thermal zone") Fixes: 0bbf6c54d100 ("arm: dts: add omap4 CPU thermal data") Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/boot/dts/omap3-cpu-thermal.dtsi | 3 +-- arch/arm/boot/dts/omap4-cpu-thermal.dtsi | 5 ++++- arch/arm/boot/dts/omap443x.dtsi | 1 + arch/arm/boot/dts/omap4460.dtsi | 1 + 4 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/omap3-cpu-thermal.dtsi b/arch/arm/boot/dts/omap3-cpu-thermal.dtsi index 0da759f8e2c2..7dd2340bc5e4 100644 --- a/arch/arm/boot/dts/omap3-cpu-thermal.dtsi +++ b/arch/arm/boot/dts/omap3-cpu-thermal.dtsi @@ -12,8 +12,7 @@ cpu_thermal: cpu-thermal { polling-delay = <1000>; /* milliseconds */ coefficients = <0 20000>; - /* sensor ID */ - thermal-sensors = <&bandgap 0>; + thermal-sensors = <&bandgap>; cpu_trips: trips { cpu_alert0: cpu_alert { diff --git a/arch/arm/boot/dts/omap4-cpu-thermal.dtsi b/arch/arm/boot/dts/omap4-cpu-thermal.dtsi index 801b4f10350c..d484ec1e4fd8 100644 --- a/arch/arm/boot/dts/omap4-cpu-thermal.dtsi +++ b/arch/arm/boot/dts/omap4-cpu-thermal.dtsi @@ -12,7 +12,10 @@ cpu_thermal: cpu_thermal { polling-delay-passive = <250>; /* milliseconds */ polling-delay = <1000>; /* milliseconds */ - /* sensor ID */ + /* + * See 44xx files for single sensor addressing, omap5 and dra7 need + * also sensor ID for addressing. + */ thermal-sensors = <&bandgap 0>; cpu_trips: trips { diff --git a/arch/arm/boot/dts/omap443x.dtsi b/arch/arm/boot/dts/omap443x.dtsi index 238aceb799f8..2104170fe2cd 100644 --- a/arch/arm/boot/dts/omap443x.dtsi +++ b/arch/arm/boot/dts/omap443x.dtsi @@ -69,6 +69,7 @@ abb_iva: regulator-abb-iva { }; &cpu_thermal { + thermal-sensors = <&bandgap>; coefficients = <0 20000>; }; diff --git a/arch/arm/boot/dts/omap4460.dtsi b/arch/arm/boot/dts/omap4460.dtsi index 1b27a862ae81..a6764750d447 100644 --- a/arch/arm/boot/dts/omap4460.dtsi +++ b/arch/arm/boot/dts/omap4460.dtsi @@ -79,6 +79,7 @@ abb_iva: regulator-abb-iva { }; &cpu_thermal { + thermal-sensors = <&bandgap>; coefficients = <348 (-9301)>; }; From 16455bed4f86c96d3802deb07ac900dd77bf4b05 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 18 Nov 2022 14:19:24 +0200 Subject: [PATCH 1762/2093] ARM: dts: Unify pwm-omap-dmtimer node names [ Upstream commit 4f15fc7c0f28ffcd6e9a56396db6edcdfa4c9925 ] There is no reg property for pwm-omap-dmtimer. Cc: Krzysztof Kozlowski Cc: Rob Herring Signed-off-by: Tony Lindgren Stable-dep-of: ac08bda1569b ("ARM: dts: ti: omap: motorola-mapphone: Fix abe_clkctrl warning on boot") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/am335x-guardian.dts | 3 ++- arch/arm/boot/dts/am3517-evm.dts | 2 +- arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi | 2 +- arch/arm/boot/dts/motorola-mapphone-common.dtsi | 4 ++-- arch/arm/boot/dts/omap3-gta04.dtsi | 2 +- arch/arm/boot/dts/omap3-n900.dts | 2 +- 6 files changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/arm/boot/dts/am335x-guardian.dts b/arch/arm/boot/dts/am335x-guardian.dts index f6356266564c..b357364e93f9 100644 --- a/arch/arm/boot/dts/am335x-guardian.dts +++ b/arch/arm/boot/dts/am335x-guardian.dts @@ -103,8 +103,9 @@ panel-info { }; - guardian_beeper: dmtimer-pwm@7 { + guardian_beeper: pwm-7 { compatible = "ti,omap-dmtimer-pwm"; + #pwm-cells = <3>; ti,timers = <&timer7>; pinctrl-names = "default"; pinctrl-0 = <&guardian_beeper_pins>; diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts index 35b653014f2b..7bab0a9dadb3 100644 --- a/arch/arm/boot/dts/am3517-evm.dts +++ b/arch/arm/boot/dts/am3517-evm.dts @@ -150,7 +150,7 @@ bl: backlight { enable-gpios = <&gpio6 22 GPIO_ACTIVE_HIGH>; /* gpio_182 */ }; - pwm11: dmtimer-pwm@11 { + pwm11: pwm-11 { compatible = "ti,omap-dmtimer-pwm"; pinctrl-names = "default"; pinctrl-0 = <&pwm_pins>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index d3da8b1b473b..e0cbac500e17 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -59,7 +59,7 @@ led2 { }; }; - pwm10: dmtimer-pwm { + pwm10: pwm-10 { compatible = "ti,omap-dmtimer-pwm"; pinctrl-names = "default"; pinctrl-0 = <&pwm_pins>; diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi index c7a1f3ffc48c..f7cc8fc678fa 100644 --- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi @@ -133,7 +133,7 @@ soundcard { dais = <&mcbsp2_port>, <&mcbsp3_port>; }; - pwm8: dmtimer-pwm-8 { + pwm8: pwm-8 { pinctrl-names = "default"; pinctrl-0 = <&vibrator_direction_pin>; @@ -143,7 +143,7 @@ pwm8: dmtimer-pwm-8 { ti,clock-source = <0x01>; }; - pwm9: dmtimer-pwm-9 { + pwm9: pwm-9 { pinctrl-names = "default"; pinctrl-0 = <&vibrator_enable_pin>; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index da578719ac5a..e0be0fb23f80 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -147,7 +147,7 @@ backlight: backlight { pinctrl-0 = <&backlight_pins>; }; - pwm11: dmtimer-pwm { + pwm11: pwm-11 { compatible = "ti,omap-dmtimer-pwm"; ti,timers = <&timer11>; #pwm-cells = <3>; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 98a67581bdd2..89ab08d83261 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -156,7 +156,7 @@ battery: n900-battery { io-channel-names = "temp", "bsi", "vbat"; }; - pwm9: dmtimer-pwm { + pwm9: pwm-9 { compatible = "ti,omap-dmtimer-pwm"; #pwm-cells = <3>; ti,timers = <&timer9>; From fe1379c0f61d369936c99b9e79787ddbe0b95222 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 17 May 2023 12:52:53 +0300 Subject: [PATCH 1763/2093] ARM: dts: Unify pinctrl-single pin group nodes for omap4 [ Upstream commit 7fff6f6d6e198ad619fea9dbbe9731999af56070 ] We want to unify the pinctrl-single pin group nodes to use naming "pins". Otherwise non-standad pin group names will add make dtbs checks errors when the pinctrl-single yaml binding gets merged. Cc: Conor Dooley Cc: Krzysztof Kozlowski Cc: Rob Herring Signed-off-by: Tony Lindgren Stable-dep-of: ac08bda1569b ("ARM: dts: ti: omap: motorola-mapphone: Fix abe_clkctrl warning on boot") Signed-off-by: Sasha Levin --- .../boot/dts/motorola-mapphone-common.dtsi | 40 +++++++++---------- arch/arm/boot/dts/omap4-duovero-parlor.dts | 12 +++--- arch/arm/boot/dts/omap4-duovero.dtsi | 18 ++++----- arch/arm/boot/dts/omap4-kc1.dts | 14 +++---- arch/arm/boot/dts/omap4-mcpdm.dtsi | 2 +- arch/arm/boot/dts/omap4-panda-common.dtsi | 30 +++++++------- arch/arm/boot/dts/omap4-panda-es.dts | 8 ++-- arch/arm/boot/dts/omap4-sdp.dts | 36 ++++++++--------- .../boot/dts/omap4-var-om44customboard.dtsi | 24 +++++------ .../arm/boot/dts/omap4-var-som-om44-wlan.dtsi | 6 +-- arch/arm/boot/dts/omap4-var-som-om44.dtsi | 22 +++++----- arch/arm/boot/dts/twl6030_omap4.dtsi | 4 +- 12 files changed, 108 insertions(+), 108 deletions(-) diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi index f7cc8fc678fa..091ba310053e 100644 --- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi @@ -352,13 +352,13 @@ isl29030@44 { &omap4_pmx_core { /* hdmi_hpd.gpio_63 */ - hdmi_hpd_gpio: pinmux_hdmi_hpd_pins { + hdmi_hpd_gpio: hdmi-hpd-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x098, PIN_INPUT | MUX_MODE3) >; }; - hdq_pins: pinmux_hdq_pins { + hdq_pins: hdq-pins { pinctrl-single,pins = < /* 0x4a100120 hdq_sio.hdq_sio aa27 */ OMAP4_IOPAD(0x120, PIN_INPUT | MUX_MODE0) @@ -366,7 +366,7 @@ OMAP4_IOPAD(0x120, PIN_INPUT | MUX_MODE0) }; /* hdmi_cec.hdmi_cec, hdmi_scl.hdmi_scl, hdmi_sda.hdmi_sda */ - dss_hdmi_pins: pinmux_dss_hdmi_pins { + dss_hdmi_pins: dss-hdmi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) OMAP4_IOPAD(0x09c, PIN_INPUT | MUX_MODE0) @@ -380,7 +380,7 @@ OMAP4_IOPAD(0x09e, PIN_INPUT | MUX_MODE0) * devices. Off mode value should be tested if we have off mode working * later on. */ - mmc3_pins: pinmux_mmc3_pins { + mmc3_pins: mmc3-pins { pinctrl-single,pins = < /* 0x4a10008e gpmc_wait2.gpio_100 d23 */ OMAP4_IOPAD(0x08e, PIN_INPUT | MUX_MODE3) @@ -406,40 +406,40 @@ OMAP4_IOPAD(0x11e, PIN_INPUT_PULLUP | MUX_MODE1) }; /* gpmc_ncs0.gpio_50 */ - poweroff_gpio: pinmux_poweroff_pins { + poweroff_gpio: poweroff-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x074, PIN_OUTPUT_PULLUP | MUX_MODE3) >; }; /* kpd_row0.gpio_178 */ - tmp105_irq: pinmux_tmp105_irq { + tmp105_irq: tmp105-irq-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x18e, PIN_INPUT_PULLUP | MUX_MODE3) >; }; - usb_gpio_mux_sel1: pinmux_usb_gpio_mux_sel1_pins { + usb_gpio_mux_sel1: usb-gpio-mux-sel1-pins { /* gpio_60 */ pinctrl-single,pins = < OMAP4_IOPAD(0x088, PIN_OUTPUT | MUX_MODE3) >; }; - touchscreen_pins: pinmux_touchscreen_pins { + touchscreen_pins: touchscreen-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x180, PIN_OUTPUT | MUX_MODE3) OMAP4_IOPAD(0x1a0, PIN_INPUT_PULLUP | MUX_MODE3) >; }; - als_proximity_pins: pinmux_als_proximity_pins { + als_proximity_pins: als-proximity-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x18c, PIN_INPUT_PULLUP | MUX_MODE3) >; }; - usb_mdm6600_pins: pinmux_usb_mdm6600_pins { + usb_mdm6600_pins: usb-mdm6600-pins { pinctrl-single,pins = < /* enable 0x4a1000d8 usbb1_ulpitll_dat7.gpio_95 ag16 */ OMAP4_IOPAD(0x0d8, PIN_INPUT | MUX_MODE3) @@ -476,7 +476,7 @@ OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE3) >; }; - usb_ulpi_pins: pinmux_usb_ulpi_pins { + usb_ulpi_pins: usb-ulpi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x196, MUX_MODE7) OMAP4_IOPAD(0x198, MUX_MODE7) @@ -496,7 +496,7 @@ OMAP4_IOPAD(0x1c8, PIN_INPUT_PULLUP | MUX_MODE0) }; /* usb0_otg_dp and usb0_otg_dm */ - usb_utmi_pins: pinmux_usb_utmi_pins { + usb_utmi_pins: usb-utmi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x196, PIN_INPUT | MUX_MODE0) OMAP4_IOPAD(0x198, PIN_INPUT | MUX_MODE0) @@ -521,7 +521,7 @@ OMAP4_IOPAD(0x1c8, PIN_INPUT_PULLUP | MUX_MODE7) * when not used. If needed, we can add rts pin remux later based * on power measurements. */ - uart1_pins: pinmux_uart1_pins { + uart1_pins: uart1-pins { pinctrl-single,pins = < /* 0x4a10013c mcspi1_cs2.uart1_cts ag23 */ OMAP4_IOPAD(0x13c, PIN_INPUT_PULLUP | MUX_MODE1) @@ -538,7 +538,7 @@ OMAP4_IOPAD(0x1ca, PIN_INPUT_PULLUP | MUX_MODE2) }; /* uart3_tx_irtx and uart3_rx_irrx */ - uart3_pins: pinmux_uart3_pins { + uart3_pins: uart3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x196, MUX_MODE7) OMAP4_IOPAD(0x198, MUX_MODE7) @@ -557,7 +557,7 @@ OMAP4_IOPAD(0x1c8, PIN_INPUT_PULLUP | MUX_MODE7) >; }; - uart4_pins: pinmux_uart4_pins { + uart4_pins: uart4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x15c, PIN_INPUT | MUX_MODE0) /* uart4_rx */ OMAP4_IOPAD(0x15e, PIN_OUTPUT | MUX_MODE0) /* uart4_tx */ @@ -566,7 +566,7 @@ OMAP4_IOPAD(0x112, PIN_OUTPUT_PULLUP | MUX_MODE5) /* uart4_rts */ >; }; - mcbsp2_pins: pinmux_mcbsp2_pins { + mcbsp2_pins: mcbsp2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0f6, PIN_INPUT | MUX_MODE0) /* abe_mcbsp2_clkx */ OMAP4_IOPAD(0x0f8, PIN_INPUT | MUX_MODE0) /* abe_mcbsp2_dr */ @@ -575,7 +575,7 @@ OMAP4_IOPAD(0x0fc, PIN_INPUT | MUX_MODE0) /* abe_mcbsp2_fsx */ >; }; - mcbsp3_pins: pinmux_mcbsp3_pins { + mcbsp3_pins: mcbsp3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x106, PIN_INPUT | MUX_MODE1) /* abe_mcbsp3_dr */ OMAP4_IOPAD(0x108, PIN_OUTPUT | MUX_MODE1) /* abe_mcbsp3_dx */ @@ -584,13 +584,13 @@ OMAP4_IOPAD(0x10c, PIN_INPUT | MUX_MODE1) /* abe_mcbsp3_fsx */ >; }; - vibrator_direction_pin: pinmux_vibrator_direction_pin { + vibrator_direction_pin: vibrator-direction-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x1ce, PIN_OUTPUT | MUX_MODE1) /* dmtimer8_pwm_evt (gpio_27) */ >; }; - vibrator_enable_pin: pinmux_vibrator_enable_pin { + vibrator_enable_pin: vibrator-enable-pins { pinctrl-single,pins = < OMAP4_IOPAD(0X1d0, PIN_OUTPUT | MUX_MODE1) /* dmtimer9_pwm_evt (gpio_28) */ >; @@ -598,7 +598,7 @@ OMAP4_IOPAD(0X1d0, PIN_OUTPUT | MUX_MODE1) /* dmtimer9_pwm_evt (gpio_28) */ }; &omap4_pmx_wkup { - usb_gpio_mux_sel2: pinmux_usb_gpio_mux_sel2_pins { + usb_gpio_mux_sel2: usb-gpio-mux-sel2-pins { /* gpio_wk0 */ pinctrl-single,pins = < OMAP4_IOPAD(0x040, PIN_OUTPUT_PULLDOWN | MUX_MODE3) diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index b294c22177cb..6d1beb453234 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -62,33 +62,33 @@ &button_pins &smsc_pins >; - led_pins: pinmux_led_pins { + led_pins: led-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x116, PIN_OUTPUT | MUX_MODE3) /* abe_dmic_din3.gpio_122 */ >; }; - button_pins: pinmux_button_pins { + button_pins: button-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x114, PIN_INPUT_PULLUP | MUX_MODE3) /* abe_dmic_din2.gpio_121 */ >; }; - i2c2_pins: pinmux_i2c2_pins { + i2c2_pins: i2c2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x126, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ OMAP4_IOPAD(0x128, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ >; }; - i2c3_pins: pinmux_i2c3_pins { + i2c3_pins: i2c3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12a, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ OMAP4_IOPAD(0x12c, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ >; }; - smsc_pins: pinmux_smsc_pins { + smsc_pins: smsc-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x068, PIN_INPUT | MUX_MODE3) /* gpmc_a20.gpio_44: IRQ */ OMAP4_IOPAD(0x06a, PIN_INPUT_PULLUP | MUX_MODE3) /* gpmc_a21.gpio_45: nReset */ @@ -96,7 +96,7 @@ OMAP4_IOPAD(0x070, PIN_INPUT_PULLUP | MUX_MODE3) /* gpmc_a24.gpio_48: amdix enab >; }; - dss_hdmi_pins: pinmux_dss_hdmi_pins { + dss_hdmi_pins: dss-hdmi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x098, PIN_INPUT | MUX_MODE3) /* hdmi_hpd.gpio_63 */ OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */ diff --git a/arch/arm/boot/dts/omap4-duovero.dtsi b/arch/arm/boot/dts/omap4-duovero.dtsi index 805dfd40030d..b8af455b411a 100644 --- a/arch/arm/boot/dts/omap4-duovero.dtsi +++ b/arch/arm/boot/dts/omap4-duovero.dtsi @@ -73,14 +73,14 @@ &twl6040_pins &hsusbb1_pins >; - twl6040_pins: pinmux_twl6040_pins { + twl6040_pins: twl6040-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x166, PIN_OUTPUT | MUX_MODE3) /* usbb2_ulpitll_nxt.gpio_160 */ OMAP4_IOPAD(0x1a0, PIN_INPUT | MUX_MODE0) /* sys_nirq2.sys_nirq2 */ >; }; - mcbsp1_pins: pinmux_mcbsp1_pins { + mcbsp1_pins: mcbsp1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0fe, PIN_INPUT | MUX_MODE0) /* abe_mcbsp1_clkx.abe_mcbsp1_clkx */ OMAP4_IOPAD(0x100, PIN_INPUT_PULLDOWN | MUX_MODE0) /* abe_mcbsp1_dr.abe_mcbsp1_dr */ @@ -89,7 +89,7 @@ OMAP4_IOPAD(0x104, PIN_INPUT | MUX_MODE0) /* abe_mcbsp1_fsx.abe_mcbsp1_fsx */ >; }; - hsusbb1_pins: pinmux_hsusbb1_pins { + hsusbb1_pins: hsusbb1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0c2, PIN_INPUT_PULLDOWN | MUX_MODE4) /* usbb1_ulpitll_clk.usbb1_ulpiphy_clk */ OMAP4_IOPAD(0x0c4, PIN_OUTPUT | MUX_MODE4) /* usbb1_ulpitll_stp.usbb1_ulpiphy_stp */ @@ -106,34 +106,34 @@ OMAP4_IOPAD(0x0d8, PIN_INPUT_PULLDOWN | MUX_MODE4) /* usbb1_ulpitll_dat7.usbb1_u >; }; - hsusb1phy_pins: pinmux_hsusb1phy_pins { + hsusb1phy_pins: hsusb1phy-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x08c, PIN_OUTPUT | MUX_MODE3) /* gpmc_wait1.gpio_62 */ >; }; - w2cbw0015_pins: pinmux_w2cbw0015_pins { + w2cbw0015_pins: w2cbw0015-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x066, PIN_OUTPUT | MUX_MODE3) /* gpmc_a19.gpio_43 */ OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3) /* gpmc_ncs3.gpio_53 */ >; }; - i2c1_pins: pinmux_i2c1_pins { + i2c1_pins: i2c1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x122, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ OMAP4_IOPAD(0x124, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ >; }; - i2c4_pins: pinmux_i2c4_pins { + i2c4_pins: i2c4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12e, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_scl */ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ >; }; - mmc1_pins: pinmux_mmc1_pins { + mmc1_pins: mmc1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0e2, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc1_clk */ OMAP4_IOPAD(0x0e4, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmcc1_cmd */ @@ -144,7 +144,7 @@ OMAP4_IOPAD(0x0ec, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc1_dat3 */ >; }; - mmc5_pins: pinmux_mmc5_pins { + mmc5_pins: mmc5-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x148, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc5_clk */ OMAP4_IOPAD(0x14a, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmcc5_cmd */ diff --git a/arch/arm/boot/dts/omap4-kc1.dts b/arch/arm/boot/dts/omap4-kc1.dts index e59d17b25a1d..c6b79ba8bbc9 100644 --- a/arch/arm/boot/dts/omap4-kc1.dts +++ b/arch/arm/boot/dts/omap4-kc1.dts @@ -35,42 +35,42 @@ led-2 { &omap4_pmx_core { pinctrl-names = "default"; - uart3_pins: pinmux_uart3_pins { + uart3_pins: uart3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x144, PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx */ OMAP4_IOPAD(0x146, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx */ >; }; - i2c1_pins: pinmux_i2c1_pins { + i2c1_pins: i2c1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x122, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ OMAP4_IOPAD(0x124, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ >; }; - i2c2_pins: pinmux_i2c2_pins { + i2c2_pins: i2c2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x126, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ OMAP4_IOPAD(0x128, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ >; }; - i2c3_pins: pinmux_i2c3_pins { + i2c3_pins: i2c3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12a, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ OMAP4_IOPAD(0x12c, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ >; }; - i2c4_pins: pinmux_i2c4_pins { + i2c4_pins: i2c4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12e, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_scl */ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ >; }; - mmc2_pins: pinmux_mmc2_pins { + mmc2_pins: mmc2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x040, PIN_INPUT_PULLUP | MUX_MODE1) /* sdmmc2_dat0 */ OMAP4_IOPAD(0x042, PIN_INPUT_PULLUP | MUX_MODE1) /* sdmmc2_dat1 */ @@ -85,7 +85,7 @@ OMAP4_IOPAD(0x084, PIN_INPUT_PULLUP | MUX_MODE1) /* sdmmc2_cmd */ >; }; - usb_otg_hs_pins: pinmux_usb_otg_hs_pins { + usb_otg_hs_pins: usb-otg-hs-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x194, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* usba0_otg_ce */ OMAP4_IOPAD(0x196, PIN_INPUT | MUX_MODE0) /* usba0_otg_dp */ diff --git a/arch/arm/boot/dts/omap4-mcpdm.dtsi b/arch/arm/boot/dts/omap4-mcpdm.dtsi index 915a9b31a33b..03ade47431fb 100644 --- a/arch/arm/boot/dts/omap4-mcpdm.dtsi +++ b/arch/arm/boot/dts/omap4-mcpdm.dtsi @@ -7,7 +7,7 @@ */ &omap4_pmx_core { - mcpdm_pins: pinmux_mcpdm_pins { + mcpdm_pins: mcpdm-pins { pinctrl-single,pins = < /* 0x4a100106 abe_pdm_ul_data.abe_pdm_ul_data ag25 */ OMAP4_IOPAD(0x106, PIN_INPUT_PULLDOWN | MUX_MODE0) diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi index 518652a599bd..53b99004b19c 100644 --- a/arch/arm/boot/dts/omap4-panda-common.dtsi +++ b/arch/arm/boot/dts/omap4-panda-common.dtsi @@ -237,14 +237,14 @@ &tpd12s015_pins &hsusbb1_pins >; - twl6040_pins: pinmux_twl6040_pins { + twl6040_pins: twl6040-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x120, PIN_OUTPUT | MUX_MODE3) /* hdq_sio.gpio_127 */ OMAP4_IOPAD(0x1a0, PIN_INPUT | MUX_MODE0) /* sys_nirq2.sys_nirq2 */ >; }; - mcbsp1_pins: pinmux_mcbsp1_pins { + mcbsp1_pins: mcbsp1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0fe, PIN_INPUT | MUX_MODE0) /* abe_mcbsp1_clkx.abe_mcbsp1_clkx */ OMAP4_IOPAD(0x100, PIN_INPUT_PULLDOWN | MUX_MODE0) /* abe_mcbsp1_dr.abe_mcbsp1_dr */ @@ -253,7 +253,7 @@ OMAP4_IOPAD(0x104, PIN_INPUT | MUX_MODE0) /* abe_mcbsp1_fsx.abe_mcbsp1_fsx */ >; }; - dss_dpi_pins: pinmux_dss_dpi_pins { + dss_dpi_pins: dss-dpi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x162, PIN_OUTPUT | MUX_MODE5) /* dispc2_data23 */ OMAP4_IOPAD(0x164, PIN_OUTPUT | MUX_MODE5) /* dispc2_data22 */ @@ -288,13 +288,13 @@ OMAP4_IOPAD(0x1d4, PIN_OUTPUT | MUX_MODE5) /* dispc2_data0 */ >; }; - tfp410_pins: pinmux_tfp410_pins { + tfp410_pins: tfp410-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x184, PIN_OUTPUT | MUX_MODE3) /* gpio_0 */ >; }; - dss_hdmi_pins: pinmux_dss_hdmi_pins { + dss_hdmi_pins: dss-hdmi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */ OMAP4_IOPAD(0x09c, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_scl.hdmi_scl */ @@ -302,7 +302,7 @@ OMAP4_IOPAD(0x09e, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_sda.hdmi_sda */ >; }; - tpd12s015_pins: pinmux_tpd12s015_pins { + tpd12s015_pins: tpd12s015-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x062, PIN_OUTPUT | MUX_MODE3) /* gpmc_a17.gpio_41 */ OMAP4_IOPAD(0x088, PIN_OUTPUT | MUX_MODE3) /* gpmc_nbe1.gpio_60 */ @@ -310,7 +310,7 @@ OMAP4_IOPAD(0x098, PIN_INPUT_PULLDOWN | MUX_MODE3) /* hdmi_hpd.gpio_63 */ >; }; - hsusbb1_pins: pinmux_hsusbb1_pins { + hsusbb1_pins: hsusbb1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0c2, PIN_INPUT_PULLDOWN | MUX_MODE4) /* usbb1_ulpitll_clk.usbb1_ulpiphy_clk */ OMAP4_IOPAD(0x0c4, PIN_OUTPUT | MUX_MODE4) /* usbb1_ulpitll_stp.usbb1_ulpiphy_stp */ @@ -327,28 +327,28 @@ OMAP4_IOPAD(0x0d8, PIN_INPUT_PULLDOWN | MUX_MODE4) /* usbb1_ulpitll_dat7.usbb1_u >; }; - i2c1_pins: pinmux_i2c1_pins { + i2c1_pins: i2c1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x122, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ OMAP4_IOPAD(0x124, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ >; }; - i2c2_pins: pinmux_i2c2_pins { + i2c2_pins: i2c2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x126, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ OMAP4_IOPAD(0x128, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ >; }; - i2c3_pins: pinmux_i2c3_pins { + i2c3_pins: i2c3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12a, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ OMAP4_IOPAD(0x12c, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ >; }; - i2c4_pins: pinmux_i2c4_pins { + i2c4_pins: i2c4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12e, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_scl */ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ @@ -359,7 +359,7 @@ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ * wl12xx GPIO outputs for WLAN_EN, BT_EN, FM_EN, BT_WAKEUP * REVISIT: Are the pull-ups needed for GPIO 48 and 49? */ - wl12xx_gpio: pinmux_wl12xx_gpio { + wl12xx_gpio: wl12xx-gpio-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x066, PIN_OUTPUT | MUX_MODE3) /* gpmc_a19.gpio_43 */ OMAP4_IOPAD(0x06c, PIN_OUTPUT | MUX_MODE3) /* gpmc_a22.gpio_46 */ @@ -369,7 +369,7 @@ OMAP4_IOPAD(0x072, PIN_OUTPUT_PULLUP | MUX_MODE3) /* gpmc_a25.gpio_49 */ }; /* wl12xx GPIO inputs and SDIO pins */ - wl12xx_pins: pinmux_wl12xx_pins { + wl12xx_pins: wl12xx-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x078, PIN_INPUT | MUX_MODE3) /* gpmc_ncs2.gpio_52 */ OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3) /* gpmc_ncs3.gpio_53 */ @@ -382,7 +382,7 @@ OMAP4_IOPAD(0x152, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc5_dat3.sdmmc5_dat3 */ >; }; - button_pins: pinmux_button_pins { + button_pins: button-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x114, PIN_INPUT_PULLUP | MUX_MODE3) /* gpio_121 */ >; @@ -390,7 +390,7 @@ OMAP4_IOPAD(0x114, PIN_INPUT_PULLUP | MUX_MODE3) /* gpio_121 */ }; &omap4_pmx_wkup { - led_wkgpio_pins: pinmux_leds_wkpins { + led_wkgpio_pins: leds-wkpins-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x05a, PIN_OUTPUT | MUX_MODE3) /* gpio_wk7 */ OMAP4_IOPAD(0x05c, PIN_OUTPUT | MUX_MODE3) /* gpio_wk8 */ diff --git a/arch/arm/boot/dts/omap4-panda-es.dts b/arch/arm/boot/dts/omap4-panda-es.dts index 7c6886cd738f..6c08dff58bea 100644 --- a/arch/arm/boot/dts/omap4-panda-es.dts +++ b/arch/arm/boot/dts/omap4-panda-es.dts @@ -38,26 +38,26 @@ OMAP4_IOPAD(0x09e, PIN_INPUT | MUX_MODE0) /* hdmi_sda.hdmi_sda */ }; &omap4_pmx_core { - led_gpio_pins: gpio_led_pmx { + led_gpio_pins: gpio-led-pmx-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0f6, PIN_OUTPUT | MUX_MODE3) /* gpio_110 */ >; }; - button_pins: pinmux_button_pins { + button_pins: button-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0fc, PIN_INPUT_PULLUP | MUX_MODE3) /* gpio_113 */ >; }; - bt_pins: pinmux_bt_pins { + bt_pins: bt-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x06c, PIN_OUTPUT | MUX_MODE3) /* gpmc_a22.gpio_46 - BTEN */ OMAP4_IOPAD(0x072, PIN_OUTPUT_PULLUP | MUX_MODE3) /* gpmc_a25.gpio_49 - BTWAKEUP */ >; }; - uart2_pins: pinmux_uart2_pins { + uart2_pins: uart2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x118, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts - HCI */ OMAP4_IOPAD(0x11a, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts index 9e976140f34a..b2cb93edbc3a 100644 --- a/arch/arm/boot/dts/omap4-sdp.dts +++ b/arch/arm/boot/dts/omap4-sdp.dts @@ -214,7 +214,7 @@ &dss_hdmi_pins &tpd12s015_pins >; - uart2_pins: pinmux_uart2_pins { + uart2_pins: uart2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x118, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */ OMAP4_IOPAD(0x11a, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ @@ -223,7 +223,7 @@ OMAP4_IOPAD(0x11e, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */ >; }; - uart3_pins: pinmux_uart3_pins { + uart3_pins: uart3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x140, PIN_INPUT_PULLUP | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */ OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */ @@ -232,21 +232,21 @@ OMAP4_IOPAD(0x146, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */ >; }; - uart4_pins: pinmux_uart4_pins { + uart4_pins: uart4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x15c, PIN_INPUT | MUX_MODE0) /* uart4_rx.uart4_rx */ OMAP4_IOPAD(0x15e, PIN_OUTPUT | MUX_MODE0) /* uart4_tx.uart4_tx */ >; }; - twl6040_pins: pinmux_twl6040_pins { + twl6040_pins: twl6040-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x120, PIN_OUTPUT | MUX_MODE3) /* hdq_sio.gpio_127 */ OMAP4_IOPAD(0x1a0, PIN_INPUT | MUX_MODE0) /* sys_nirq2.sys_nirq2 */ >; }; - dmic_pins: pinmux_dmic_pins { + dmic_pins: dmic-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x110, PIN_OUTPUT | MUX_MODE0) /* abe_dmic_clk1.abe_dmic_clk1 */ OMAP4_IOPAD(0x112, PIN_INPUT | MUX_MODE0) /* abe_dmic_din1.abe_dmic_din1 */ @@ -255,7 +255,7 @@ OMAP4_IOPAD(0x116, PIN_INPUT | MUX_MODE0) /* abe_dmic_din3.abe_dmic_din3 */ >; }; - mcbsp1_pins: pinmux_mcbsp1_pins { + mcbsp1_pins: mcbsp1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0fe, PIN_INPUT | MUX_MODE0) /* abe_mcbsp1_clkx.abe_mcbsp1_clkx */ OMAP4_IOPAD(0x100, PIN_INPUT_PULLDOWN | MUX_MODE0) /* abe_mcbsp1_dr.abe_mcbsp1_dr */ @@ -264,7 +264,7 @@ OMAP4_IOPAD(0x104, PIN_INPUT | MUX_MODE0) /* abe_mcbsp1_fsx.abe_mcbsp1_fsx */ >; }; - mcbsp2_pins: pinmux_mcbsp2_pins { + mcbsp2_pins: mcbsp2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0f6, PIN_INPUT | MUX_MODE0) /* abe_mcbsp2_clkx.abe_mcbsp2_clkx */ OMAP4_IOPAD(0x0f8, PIN_INPUT_PULLDOWN | MUX_MODE0) /* abe_mcbsp2_dr.abe_mcbsp2_dr */ @@ -273,7 +273,7 @@ OMAP4_IOPAD(0x0fc, PIN_INPUT | MUX_MODE0) /* abe_mcbsp2_fsx.abe_mcbsp2_fsx */ >; }; - mcspi1_pins: pinmux_mcspi1_pins { + mcspi1_pins: mcspi1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x132, PIN_INPUT | MUX_MODE0) /* mcspi1_clk.mcspi1_clk */ OMAP4_IOPAD(0x134, PIN_INPUT | MUX_MODE0) /* mcspi1_somi.mcspi1_somi */ @@ -282,7 +282,7 @@ OMAP4_IOPAD(0x138, PIN_INPUT | MUX_MODE0) /* mcspi1_cs0.mcspi1_cs0 */ >; }; - dss_hdmi_pins: pinmux_dss_hdmi_pins { + dss_hdmi_pins: dss-hdmi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */ OMAP4_IOPAD(0x09c, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_scl.hdmi_scl */ @@ -290,7 +290,7 @@ OMAP4_IOPAD(0x09e, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_sda.hdmi_sda */ >; }; - tpd12s015_pins: pinmux_tpd12s015_pins { + tpd12s015_pins: tpd12s015-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x062, PIN_OUTPUT | MUX_MODE3) /* gpmc_a17.gpio_41 */ OMAP4_IOPAD(0x088, PIN_OUTPUT | MUX_MODE3) /* gpmc_nbe1.gpio_60 */ @@ -298,28 +298,28 @@ OMAP4_IOPAD(0x098, PIN_INPUT_PULLDOWN | MUX_MODE3) /* hdmi_hpd.gpio_63 */ >; }; - i2c1_pins: pinmux_i2c1_pins { + i2c1_pins: i2c1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x122, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ OMAP4_IOPAD(0x124, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ >; }; - i2c2_pins: pinmux_i2c2_pins { + i2c2_pins: i2c2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x126, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ OMAP4_IOPAD(0x128, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ >; }; - i2c3_pins: pinmux_i2c3_pins { + i2c3_pins: i2c3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12a, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ OMAP4_IOPAD(0x12c, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ >; }; - i2c4_pins: pinmux_i2c4_pins { + i2c4_pins: i2c4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12e, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_scl */ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ @@ -327,14 +327,14 @@ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ }; /* wl12xx GPIO output for WLAN_EN */ - wl12xx_gpio: pinmux_wl12xx_gpio { + wl12xx_gpio: wl12xx-gpio-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x07c, PIN_OUTPUT | MUX_MODE3) /* gpmc_nwp.gpio_54 */ >; }; /* wl12xx GPIO inputs and SDIO pins */ - wl12xx_pins: pinmux_wl12xx_pins { + wl12xx_pins: wl12xx-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x07a, PIN_INPUT | MUX_MODE3) /* gpmc_ncs3.gpio_53 */ OMAP4_IOPAD(0x148, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc5_clk.sdmmc5_clk */ @@ -347,13 +347,13 @@ OMAP4_IOPAD(0x152, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc5_dat3.sdmmc5_dat3 */ }; /* gpio_48 for ENET_ENABLE */ - enet_enable_gpio: pinmux_enet_enable_gpio { + enet_enable_gpio: enet-enable-gpio-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x070, PIN_OUTPUT_PULLDOWN | MUX_MODE3) /* gpmc_a24.gpio_48 */ >; }; - ks8851_pins: pinmux_ks8851_pins { + ks8851_pins: ks8851-pins { pinctrl-single,pins = < /* ENET_INT */ OMAP4_IOPAD(0x054, PIN_INPUT_PULLUP | MUX_MODE3) /* gpmc_ad10.gpio_34 */ diff --git a/arch/arm/boot/dts/omap4-var-om44customboard.dtsi b/arch/arm/boot/dts/omap4-var-om44customboard.dtsi index 458cb53dd3d1..cadc7e02592b 100644 --- a/arch/arm/boot/dts/omap4-var-om44customboard.dtsi +++ b/arch/arm/boot/dts/omap4-var-om44customboard.dtsi @@ -60,7 +60,7 @@ hdmi_connector_in: endpoint { }; &omap4_pmx_core { - uart1_pins: pinmux_uart1_pins { + uart1_pins: uart1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x13c, PIN_INPUT_PULLUP | MUX_MODE1) /* mcspi1_cs2.uart1_cts */ OMAP4_IOPAD(0x13e, PIN_OUTPUT | MUX_MODE1) /* mcspi1_cs3.uart1_rts */ @@ -69,7 +69,7 @@ OMAP4_IOPAD(0x128, PIN_OUTPUT | MUX_MODE1) /* i2c2_sda.uart1_tx */ >; }; - mcspi1_pins: pinmux_mcspi1_pins { + mcspi1_pins: mcspi1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x132, PIN_INPUT | MUX_MODE0) /* mcspi1_clk.mcspi1_clk */ OMAP4_IOPAD(0x134, PIN_INPUT | MUX_MODE0) /* mcspi1_somi.mcspi1_somi */ @@ -78,13 +78,13 @@ OMAP4_IOPAD(0x138, PIN_INPUT | MUX_MODE0) /* mcspi1_cs0.mcspi1_cs0 */ >; }; - mcasp_pins: pinmux_mcsasp_pins { + mcasp_pins: mcsasp-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0f8, PIN_OUTPUT | MUX_MODE2) /* mcbsp2_dr.abe_mcasp_axr */ >; }; - dss_dpi_pins: pinmux_dss_dpi_pins { + dss_dpi_pins: dss-dpi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x162, PIN_OUTPUT | MUX_MODE5) /* dispc2_data23 */ OMAP4_IOPAD(0x164, PIN_OUTPUT | MUX_MODE5) /* dispc2_data22 */ @@ -117,7 +117,7 @@ OMAP4_IOPAD(0x1d4, PIN_OUTPUT | MUX_MODE5) /* dispc2_data0 */ >; }; - dss_hdmi_pins: pinmux_dss_hdmi_pins { + dss_hdmi_pins: dss-hdmi-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x09a, PIN_INPUT | MUX_MODE0) /* hdmi_cec.hdmi_cec */ OMAP4_IOPAD(0x09c, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_scl.hdmi_scl */ @@ -125,14 +125,14 @@ OMAP4_IOPAD(0x09e, PIN_INPUT_PULLUP | MUX_MODE0) /* hdmi_sda.hdmi_sda */ >; }; - i2c4_pins: pinmux_i2c4_pins { + i2c4_pins: i2c4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12e, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_scl */ OMAP4_IOPAD(0x130, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c4_sda */ >; }; - mmc5_pins: pinmux_mmc5_pins { + mmc5_pins: mmc5-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0f6, PIN_INPUT | MUX_MODE3) /* abe_mcbsp2_clkx.gpio_110 */ OMAP4_IOPAD(0x148, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc5_clk.sdmmc5_clk */ @@ -144,32 +144,32 @@ OMAP4_IOPAD(0x152, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc5_dat3.sdmmc5_dat3 */ >; }; - gpio_led_pins: pinmux_gpio_led_pins { + gpio_led_pins: gpio-led-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x17e, PIN_OUTPUT | MUX_MODE3) /* kpd_col4.gpio_172 */ OMAP4_IOPAD(0x180, PIN_OUTPUT | MUX_MODE3) /* kpd_col5.gpio_173 */ >; }; - gpio_key_pins: pinmux_gpio_key_pins { + gpio_key_pins: gpio-key-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x1a2, PIN_INPUT | MUX_MODE3) /* sys_boot0.gpio_184 */ >; }; - ks8851_irq_pins: pinmux_ks8851_irq_pins { + ks8851_irq_pins: ks8851-irq-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x17c, PIN_INPUT_PULLUP | MUX_MODE3) /* kpd_col3.gpio_171 */ >; }; - hdmi_hpd_pins: pinmux_hdmi_hpd_pins { + hdmi_hpd_pins: hdmi-hpd-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x098, PIN_INPUT_PULLDOWN | MUX_MODE3) /* hdmi_hpd.gpio_63 */ >; }; - backlight_pins: pinmux_backlight_pins { + backlight_pins: backlight-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x116, PIN_OUTPUT | MUX_MODE3) /* abe_dmic_din3.gpio_122 */ >; diff --git a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi index d0032213101e..de779d2d7c3e 100644 --- a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi +++ b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi @@ -19,7 +19,7 @@ wl12xx_vmmc: wl12xx_vmmc { }; &omap4_pmx_core { - uart2_pins: pinmux_uart2_pins { + uart2_pins: uart2-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x118, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */ OMAP4_IOPAD(0x11a, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ @@ -28,7 +28,7 @@ OMAP4_IOPAD(0x11e, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */ >; }; - wl12xx_ctrl_pins: pinmux_wl12xx_ctrl_pins { + wl12xx_ctrl_pins: wl12xx-ctrl-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x062, PIN_INPUT_PULLUP | MUX_MODE3) /* gpmc_a17.gpio_41 (WLAN_IRQ) */ OMAP4_IOPAD(0x064, PIN_OUTPUT | MUX_MODE3) /* gpmc_a18.gpio_42 (BT_EN) */ @@ -36,7 +36,7 @@ OMAP4_IOPAD(0x066, PIN_OUTPUT | MUX_MODE3) /* gpmc_a19.gpio_43 (WLAN_EN) */ >; }; - mmc4_pins: pinmux_mmc4_pins { + mmc4_pins: mmc4-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x154, PIN_INPUT_PULLUP | MUX_MODE1) /* mcspi4_clk.sdmmc4_clk */ OMAP4_IOPAD(0x156, PIN_INPUT_PULLUP | MUX_MODE1) /* mcspi4_simo.sdmmc4_cmd */ diff --git a/arch/arm/boot/dts/omap4-var-som-om44.dtsi b/arch/arm/boot/dts/omap4-var-som-om44.dtsi index 334cbbaa5b8b..37d56b3010cf 100644 --- a/arch/arm/boot/dts/omap4-var-som-om44.dtsi +++ b/arch/arm/boot/dts/omap4-var-som-om44.dtsi @@ -65,21 +65,21 @@ &omap4_pmx_core { &hsusbb1_pins >; - twl6040_pins: pinmux_twl6040_pins { + twl6040_pins: twl6040-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x19c, PIN_OUTPUT | MUX_MODE3) /* fref_clk2_out.gpio_182 */ OMAP4_IOPAD(0x1a0, PIN_INPUT | MUX_MODE0) /* sys_nirq2.sys_nirq2 */ >; }; - tsc2004_pins: pinmux_tsc2004_pins { + tsc2004_pins: tsc2004-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x090, PIN_INPUT | MUX_MODE3) /* gpmc_ncs4.gpio_101 (irq) */ OMAP4_IOPAD(0x092, PIN_OUTPUT | MUX_MODE3) /* gpmc_ncs5.gpio_102 (rst) */ >; }; - uart3_pins: pinmux_uart3_pins { + uart3_pins: uart3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x140, PIN_INPUT_PULLUP | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */ OMAP4_IOPAD(0x142, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */ @@ -88,7 +88,7 @@ OMAP4_IOPAD(0x146, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */ >; }; - hsusbb1_pins: pinmux_hsusbb1_pins { + hsusbb1_pins: hsusbb1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0c2, PIN_INPUT_PULLDOWN | MUX_MODE4) /* usbb1_ulpitll_clk.usbb1_ulpiphy_clk */ OMAP4_IOPAD(0x0c4, PIN_OUTPUT | MUX_MODE4) /* usbb1_ulpitll_stp.usbb1_ulpiphy_stp */ @@ -105,27 +105,27 @@ OMAP4_IOPAD(0x0d8, PIN_INPUT_PULLDOWN | MUX_MODE4) /* usbb1_ulpitll_dat7.usbb1_u >; }; - hsusbb1_phy_rst_pins: pinmux_hsusbb1_phy_rst_pins { + hsusbb1_phy_rst_pins: hsusbb1-phy-rst-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x18c, PIN_OUTPUT | MUX_MODE3) /* kpd_row2.gpio_177 */ >; }; - i2c1_pins: pinmux_i2c1_pins { + i2c1_pins: i2c1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x122, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ OMAP4_IOPAD(0x124, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ >; }; - i2c3_pins: pinmux_i2c3_pins { + i2c3_pins: i2c3-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x12a, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ OMAP4_IOPAD(0x12c, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ >; }; - mmc1_pins: pinmux_mmc1_pins { + mmc1_pins: mmc1-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x0e2, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc1_clk.sdmmc1_clk */ OMAP4_IOPAD(0x0e4, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc1_cmd.sdmmc1_cmd */ @@ -144,19 +144,19 @@ &hsusbb1_hub_rst_pins &lan7500_rst_pins >; - hsusbb1_phy_clk_pins: pinmux_hsusbb1_phy_clk_pins { + hsusbb1_phy_clk_pins: hsusbb1-phy-clk-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x058, PIN_OUTPUT | MUX_MODE0) /* fref_clk3_out */ >; }; - hsusbb1_hub_rst_pins: pinmux_hsusbb1_hub_rst_pins { + hsusbb1_hub_rst_pins: hsusbb1-hub-rst-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x042, PIN_OUTPUT | MUX_MODE3) /* gpio_wk1 */ >; }; - lan7500_rst_pins: pinmux_lan7500_rst_pins { + lan7500_rst_pins: lan7500-rst-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x040, PIN_OUTPUT | MUX_MODE3) /* gpio_wk0 */ >; diff --git a/arch/arm/boot/dts/twl6030_omap4.dtsi b/arch/arm/boot/dts/twl6030_omap4.dtsi index 5730e46b0067..64e38c7c8be7 100644 --- a/arch/arm/boot/dts/twl6030_omap4.dtsi +++ b/arch/arm/boot/dts/twl6030_omap4.dtsi @@ -19,7 +19,7 @@ &twl6030_wkup_pins }; &omap4_pmx_wkup { - twl6030_wkup_pins: pinmux_twl6030_wkup_pins { + twl6030_wkup_pins: twl6030-wkup-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x054, PIN_OUTPUT | MUX_MODE2) /* fref_clk0_out.sys_drm_msecure */ >; @@ -27,7 +27,7 @@ OMAP4_IOPAD(0x054, PIN_OUTPUT | MUX_MODE2) /* fref_clk0_out.sys_drm_msecure */ }; &omap4_pmx_core { - twl6030_pins: pinmux_twl6030_pins { + twl6030_pins: twl6030-pins { pinctrl-single,pins = < OMAP4_IOPAD(0x19e, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1.sys_nirq1 */ >; From dd19672aaac4d0dc01b3873f4df8b4537e5f6cc0 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 11 Sep 2023 07:07:38 +0300 Subject: [PATCH 1764/2093] ARM: dts: ti: omap: motorola-mapphone: Fix abe_clkctrl warning on boot [ Upstream commit ac08bda1569b06b7a62c7b4dd00d4c3b28ceaaec ] Commit 0840242e8875 ("ARM: dts: Configure clock parent for pwm vibra") attempted to fix the PWM settings but ended up causin an additional clock reparenting error: clk: failed to reparent abe-clkctrl:0060:24 to sys_clkin_ck: -22 Only timer9 is in the PER domain and can use the sys_clkin_ck clock source. For timer8, the there is no sys_clkin_ck available as it's in the ABE domain, instead it should use syc_clk_div_ck. However, for power management, we want to use the always on sys_32k_ck instead. Cc: Ivaylo Dimitrov Cc: Carl Philipp Klemm Cc: Merlijn Wajer Cc: Pavel Machek Reviewed-by: Sebastian Reichel Fixes: 0840242e8875 ("ARM: dts: Configure clock parent for pwm vibra") Depends-on: 61978617e905 ("ARM: dts: Add minimal support for Droid Bionic xt875") Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/boot/dts/motorola-mapphone-common.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi index 091ba310053e..d69f0f4b4990 100644 --- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi @@ -614,12 +614,12 @@ &rng_target { /* Configure pwm clock source for timers 8 & 9 */ &timer8 { assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>; - assigned-clock-parents = <&sys_clkin_ck>; + assigned-clock-parents = <&sys_32k_ck>; }; &timer9 { assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>; - assigned-clock-parents = <&sys_clkin_ck>; + assigned-clock-parents = <&sys_32k_ck>; }; /* From 1ec48a9fac7d07c70e12147949e4941b1c2db3d2 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 7 Sep 2023 08:53:28 +0300 Subject: [PATCH 1765/2093] bus: ti-sysc: Fix SYSC_QUIRK_SWSUP_SIDLE_ACT handling for uart wake-up [ Upstream commit e5deb8f76e64d94ccef715e75ebafffd0c312d80 ] The uarts should be tagged with SYSC_QUIRK_SWSUP_SIDLE instead of SYSC_QUIRK_SWSUP_SIDLE_ACT. The difference is that SYSC_QUIRK_SWSUP_SIDLE is used to force idle target modules rather than block idle during usage. The SYSC_QUIRK_SWSUP_SIDLE_ACT should disable autoidle and wake-up when a target module is active, and configure autoidle and wake-up when a target module is inactive. We are missing configuring the target module on sysc_disable_module(), and missing toggling of the wake-up bit. Let's fix the issue to allow uart wake-up to work. Fixes: fb685f1c190e ("bus: ti-sysc: Handle swsup idle mode quirks") Tested-by: Dhruva Gole Tested-by: Kevin Hilman Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index d56e7b61bb5a..59a2fe2448f1 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1120,6 +1120,11 @@ static int sysc_enable_module(struct device *dev) if (ddata->cfg.quirks & (SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_SIDLE_ACT)) { best_mode = SYSC_IDLE_NO; + + /* Clear WAKEUP */ + if (regbits->enwkup_shift >= 0 && + ddata->cfg.sysc_val & BIT(regbits->enwkup_shift)) + reg &= ~BIT(regbits->enwkup_shift); } else { best_mode = fls(ddata->cfg.sidlemodes) - 1; if (best_mode > SYSC_IDLE_MASK) { @@ -1247,6 +1252,13 @@ static int sysc_disable_module(struct device *dev) } } + if (ddata->cfg.quirks & SYSC_QUIRK_SWSUP_SIDLE_ACT) { + /* Set WAKEUP */ + if (regbits->enwkup_shift >= 0 && + ddata->cfg.sysc_val & BIT(regbits->enwkup_shift)) + reg |= BIT(regbits->enwkup_shift); + } + reg &= ~(SYSC_IDLE_MASK << regbits->sidle_shift); reg |= best_mode << regbits->sidle_shift; if (regbits->autoidle_shift >= 0 && @@ -1541,16 +1553,16 @@ struct sysc_revision_quirk { static const struct sysc_revision_quirk sysc_revision_quirks[] = { /* These drivers need to be fixed to not use pm_runtime_irq_safe() */ SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000046, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000052, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), /* Uarts on omap4 and later */ SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffff00ff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47424e03, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), /* Quirks that need to be set based on the module address */ SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff, From 33ed60d8b961fca23a96f3a2f0c7c142c6ec5455 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 19 Jun 2023 12:44:17 +0300 Subject: [PATCH 1766/2093] power: supply: ucs1002: fix error code in ucs1002_get_property() [ Upstream commit e35059949daa83f8dadf710d0f829ab3c3a72fe2 ] This function is supposed to return 0 for success instead of returning the val->intval. This makes it the same as the other case statements in this function. Fixes: 81196e2e57fc ("power: supply: ucs1002: fix some health status issues") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/687f64a4-4c6e-4536-8204-98ad1df934e5@moroto.mountain Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/ucs1002_power.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c index ef673ec3db56..332cb50d9fb4 100644 --- a/drivers/power/supply/ucs1002_power.c +++ b/drivers/power/supply/ucs1002_power.c @@ -384,7 +384,8 @@ static int ucs1002_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_USB_TYPE: return ucs1002_get_usb_type(info, val); case POWER_SUPPLY_PROP_HEALTH: - return val->intval = info->health; + val->intval = info->health; + return 0; case POWER_SUPPLY_PROP_PRESENT: val->intval = info->present; return 0; From 7cad56459964855a2e5b9ab3f4471e64a8de8dc4 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 15 Jan 2023 19:13:46 +0100 Subject: [PATCH 1767/2093] firmware: imx-dsp: Fix an error handling path in imx_dsp_setup_channels() [ Upstream commit e527adfb9b7d9d05a4577c116519e59a2bda4b05 ] If mbox_request_channel_byname() fails, the memory allocated a few lines above still need to be freed before going to the error handling path. Fixes: 046326989a18 ("firmware: imx: Save channel name for further use") Signed-off-by: Christophe JAILLET Reviewed-by: Daniel Baluta Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- drivers/firmware/imx/imx-dsp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/imx/imx-dsp.c b/drivers/firmware/imx/imx-dsp.c index a6c06d7476c3..1f410809d3ee 100644 --- a/drivers/firmware/imx/imx-dsp.c +++ b/drivers/firmware/imx/imx-dsp.c @@ -115,6 +115,7 @@ static int imx_dsp_setup_channels(struct imx_dsp_ipc *dsp_ipc) dsp_chan->idx = i % 2; dsp_chan->ch = mbox_request_channel_byname(cl, chan_name); if (IS_ERR(dsp_chan->ch)) { + kfree(dsp_chan->name); ret = PTR_ERR(dsp_chan->ch); if (ret != -EPROBE_DEFER) dev_err(dev, "Failed to request mbox chan %s ret %d\n", From b4e666fa38fd1e1b6f9600a860852c17ae691f14 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 20 Sep 2023 04:15:22 -0700 Subject: [PATCH 1768/2093] xtensa: add default definition for XCHAL_HAVE_DIV32 [ Upstream commit 494e87ffa0159b3f879694a9231089707792a44d ] When variant FSF is set, XCHAL_HAVE_DIV32 is not defined. Add default definition for that macro to prevent build warnings: arch/xtensa/lib/divsi3.S:9:5: warning: "XCHAL_HAVE_DIV32" is not defined, evaluates to 0 [-Wundef] 9 | #if XCHAL_HAVE_DIV32 arch/xtensa/lib/modsi3.S:9:5: warning: "XCHAL_HAVE_DIV32" is not defined, evaluates to 0 [-Wundef] 9 | #if XCHAL_HAVE_DIV32 Fixes: 173d6681380a ("xtensa: remove extra header files") Suggested-by: Randy Dunlap Signed-off-by: Max Filippov Reported-by: kernel test robot Closes: lore.kernel.org/r/202309150556.t0yCdv3g-lkp@intel.com Signed-off-by: Sasha Levin --- arch/xtensa/include/asm/core.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/xtensa/include/asm/core.h b/arch/xtensa/include/asm/core.h index 7cef85ad9741..25293269e1ed 100644 --- a/arch/xtensa/include/asm/core.h +++ b/arch/xtensa/include/asm/core.h @@ -6,6 +6,10 @@ #include +#ifndef XCHAL_HAVE_DIV32 +#define XCHAL_HAVE_DIV32 0 +#endif + #ifndef XCHAL_HAVE_EXCLUSIVE #define XCHAL_HAVE_EXCLUSIVE 0 #endif From fca1b09645e5d8334a17412cbf3f82235e6f4dcb Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 19 Sep 2023 22:21:36 -0700 Subject: [PATCH 1769/2093] xtensa: iss/network: make functions static [ Upstream commit 1b59efeb59851277266318f4e0132aa61ce3455e ] Make 2 functions static to prevent build warnings: arch/xtensa/platforms/iss/network.c:204:16: warning: no previous prototype for 'tuntap_protocol' [-Wmissing-prototypes] 204 | unsigned short tuntap_protocol(struct sk_buff *skb) arch/xtensa/platforms/iss/network.c:444:6: warning: no previous prototype for 'iss_net_user_timer_expire' [-Wmissing-prototypes] 444 | void iss_net_user_timer_expire(struct timer_list *unused) Fixes: 7282bee78798 ("xtensa: Architecture support for Tensilica Xtensa Part 8") Fixes: d8479a21a98b ("xtensa: Convert timers to use timer_setup()") Signed-off-by: Randy Dunlap Cc: Chris Zankel Cc: Max Filippov Message-Id: <20230920052139.10570-14-rdunlap@infradead.org> Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/platforms/iss/network.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 119345eeb04c..bea539f9039a 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -201,7 +201,7 @@ static int tuntap_write(struct iss_net_private *lp, struct sk_buff **skb) return simc_write(lp->tp.info.tuntap.fd, (*skb)->data, (*skb)->len); } -unsigned short tuntap_protocol(struct sk_buff *skb) +static unsigned short tuntap_protocol(struct sk_buff *skb) { return eth_type_trans(skb, skb->dev); } @@ -441,7 +441,7 @@ static int iss_net_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } -void iss_net_user_timer_expire(struct timer_list *unused) +static void iss_net_user_timer_expire(struct timer_list *unused) { } From 45661247d117093e3fbd55d190d981daacebba6b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 19 Sep 2023 22:21:37 -0700 Subject: [PATCH 1770/2093] xtensa: boot: don't add include-dirs [ Upstream commit 54d3d7d363823782c3444ddc41bb8cf1edc80514 ] Drop the -I options to prevent build warnings since there is not boot/include directory: cc1: warning: arch/xtensa/boot/include: No such file or directory [-Wmissing-include-dirs] Fixes: 437374e9a950 ("restore arch/{ppc/xtensa}/boot cflags") Fixes: 4bedea945451 ("xtensa: Architecture support for Tensilica Xtensa Part 2") Signed-off-by: Randy Dunlap Cc: Chris Zankel Cc: Max Filippov Message-Id: <20230920052139.10570-15-rdunlap@infradead.org> Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/boot/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile index a65b7a9ebff2..d8b0fadf429a 100644 --- a/arch/xtensa/boot/Makefile +++ b/arch/xtensa/boot/Makefile @@ -9,8 +9,7 @@ # KBUILD_CFLAGS used when building rest of boot (takes effect recursively) -KBUILD_CFLAGS += -fno-builtin -Iarch/$(ARCH)/boot/include -HOSTFLAGS += -Iarch/$(ARCH)/boot/include +KBUILD_CFLAGS += -fno-builtin subdir-y := lib targets += vmlinux.bin vmlinux.bin.gz From 6438653ad1f2d13b054a54a84f8f024d55765822 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 19 Sep 2023 22:21:38 -0700 Subject: [PATCH 1771/2093] xtensa: umulsidi3: fix conditional expression [ Upstream commit 9aecda97ec3deecbfa7670877c8ddfd3d0fc87c4 ] Even when a variant has one or more of these defines set to 1, the multiplier code paths are not used. Change the expression so that the correct code paths are used. arch/xtensa/lib/umulsidi3.S:44:38: warning: "XCHAL_NO_MUL" is not defined, evaluates to 0 [-Wundef] 44 | #if defined(__XTENSA_CALL0_ABI__) && XCHAL_NO_MUL arch/xtensa/lib/umulsidi3.S:145:38: warning: "XCHAL_NO_MUL" is not defined, evaluates to 0 [-Wundef] 145 | #if defined(__XTENSA_CALL0_ABI__) && XCHAL_NO_MUL arch/xtensa/lib/umulsidi3.S:159:5: warning: "XCHAL_NO_MUL" is not defined, evaluates to 0 [-Wundef] 159 | #if XCHAL_NO_MUL Fixes: 8939c58d68f9 ("xtensa: add __umulsidi3 helper") Signed-off-by: Randy Dunlap Cc: Chris Zankel Cc: Max Filippov Message-Id: <20230920052139.10570-16-rdunlap@infradead.org> Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/lib/umulsidi3.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/xtensa/lib/umulsidi3.S b/arch/xtensa/lib/umulsidi3.S index 136081647942..4d9ba2387de0 100644 --- a/arch/xtensa/lib/umulsidi3.S +++ b/arch/xtensa/lib/umulsidi3.S @@ -3,7 +3,9 @@ #include #include -#if !XCHAL_HAVE_MUL16 && !XCHAL_HAVE_MUL32 && !XCHAL_HAVE_MAC16 +#if XCHAL_HAVE_MUL16 || XCHAL_HAVE_MUL32 || XCHAL_HAVE_MAC16 +#define XCHAL_NO_MUL 0 +#else #define XCHAL_NO_MUL 1 #endif From 1005010b732beff4af17e447cb965ac2204f8ce8 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 20 Sep 2023 04:41:09 -0700 Subject: [PATCH 1772/2093] xtensa: boot/lib: fix function prototypes [ Upstream commit f54d02c8f2cc4b46ba2a3bd8252a6750453b6f2b ] Add function prototype for gunzip() to the boot library code and make exit() and zalloc() static. arch/xtensa/boot/lib/zmem.c:8:6: warning: no previous prototype for 'exit' [-Wmissing-prototypes] 8 | void exit (void) arch/xtensa/boot/lib/zmem.c:13:7: warning: no previous prototype for 'zalloc' [-Wmissing-prototypes] 13 | void *zalloc(unsigned size) arch/xtensa/boot/lib/zmem.c:35:6: warning: no previous prototype for 'gunzip' [-Wmissing-prototypes] 35 | void gunzip (void *dst, int dstlen, unsigned char *src, int *lenp) Fixes: 4bedea945451 ("xtensa: Architecture support for Tensilica Xtensa Part 2") Fixes: e7d163f76665 ("xtensa: Removed local copy of zlib and fixed O= support") Suggested-by: Randy Dunlap Signed-off-by: Max Filippov Signed-off-by: Sasha Levin --- arch/xtensa/boot/lib/zmem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/xtensa/boot/lib/zmem.c b/arch/xtensa/boot/lib/zmem.c index e3ecd743c515..b89189355122 100644 --- a/arch/xtensa/boot/lib/zmem.c +++ b/arch/xtensa/boot/lib/zmem.c @@ -4,13 +4,14 @@ /* bits taken from ppc */ extern void *avail_ram, *end_avail; +void gunzip(void *dst, int dstlen, unsigned char *src, int *lenp); -void exit (void) +static void exit(void) { for (;;); } -void *zalloc(unsigned size) +static void *zalloc(unsigned int size) { void *p = avail_ram; From fe6406238d5a24e9fb0286c71edd67b99d8db58d Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Wed, 20 Sep 2023 09:56:44 -0500 Subject: [PATCH 1773/2093] power: supply: rk817: Fix node refcount leak [ Upstream commit 488ef44c068e79752dba8eda0b75f524f111a695 ] Dan Carpenter reports that the Smatch static checker warning has found that there is another refcount leak in the probe function. While of_node_put() was added in one of the return paths, it should in fact be added for ALL return paths that return an error and at driver removal time. Fixes: 54c03bfd094f ("power: supply: Fix refcount leak in rk817_charger_probe") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-pm/dc0bb0f8-212d-4be7-be69-becd2a3f9a80@kili.mountain/ Signed-off-by: Chris Morgan Link: https://lore.kernel.org/r/20230920145644.57964-1-macroalpha82@gmail.com Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/rk817_charger.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index f1b431aa0e4f..e30ef601d91d 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -1058,6 +1058,13 @@ static void rk817_charging_monitor(struct work_struct *work) queue_delayed_work(system_wq, &charger->work, msecs_to_jiffies(8000)); } +static void rk817_cleanup_node(void *data) +{ + struct device_node *node = data; + + of_node_put(node); +} + static int rk817_charger_probe(struct platform_device *pdev) { struct rk808 *rk808 = dev_get_drvdata(pdev->dev.parent); @@ -1074,11 +1081,13 @@ static int rk817_charger_probe(struct platform_device *pdev) if (!node) return -ENODEV; + ret = devm_add_action_or_reset(&pdev->dev, rk817_cleanup_node, node); + if (ret) + return ret; + charger = devm_kzalloc(&pdev->dev, sizeof(*charger), GFP_KERNEL); - if (!charger) { - of_node_put(node); + if (!charger) return -ENOMEM; - } charger->rk808 = rk808; From b9dc3d6b761d857d6dbd97fdedb13c2f9d6b4a40 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 28 Feb 2023 11:07:07 +1100 Subject: [PATCH 1774/2093] selftests/powerpc: Use CLEAN macro to fix make warning [ Upstream commit 69608683a65be5322ef44091eaeb9890472b2eea ] The CLEAN macro was added in 337f1e36 to prevent the Makefile:50: warning: overriding recipe for target 'clean' ../../lib.mk:124: warning: ignoring old recipe for target 'clean' style warnings. Expand it's use to fix another case of redefining a target directly. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230228000709.124727-2-bgray@linux.ibm.com Stable-dep-of: 58b33e78a317 ("selftests/powerpc: Fix emit_tests to work with run_kselftest.sh") Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/pmu/Makefile | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 30803353bd7c..d2c1accc2e69 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -46,11 +46,14 @@ override define INSTALL_RULE TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef -clean: +DEFAULT_CLEAN := $(CLEAN) +override define CLEAN + $(DEFAULT_CLEAN) $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean +endef ebb: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all @@ -61,4 +64,4 @@ sampling_tests: event_code_tests: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests clean ebb sampling_tests event_code_tests +.PHONY: all run_tests ebb sampling_tests event_code_tests From 763f029f8c0f3f4662312709b34ab8240e50ef13 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 28 Feb 2023 11:07:08 +1100 Subject: [PATCH 1775/2093] selftests/powerpc: Pass make context to children [ Upstream commit 4ecd0868c5138238dec8a1549bb6ff8e5b48208b ] Make supports passing the 'jobserver' (parallel make support) to child invocations of make when either 1. The target command uses $(MAKE) directly 2. The command starts with '+' This context is not passed through expansions that result in $(MAKE), so the macros used in several places fail to pass on the jobserver context. Warnings are also raised by the child mentioning this. Prepend macros lines that invoke $(MAKE) with '+' to allow passing the jobserver context to these children. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230228000709.124727-3-bgray@linux.ibm.com Stable-dep-of: 58b33e78a317 ("selftests/powerpc: Fix emit_tests to work with run_kselftest.sh") Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/Makefile | 8 +++---- tools/testing/selftests/powerpc/pmu/Makefile | 24 ++++++++++---------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 6ba95cd19e42..ae2bfc0d822f 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -45,28 +45,28 @@ $(SUB_DIRS): include ../lib.mk override define RUN_TESTS - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; endef override define INSTALL_RULE - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\ done; endef override define EMIT_TESTS - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ done; endef override define CLEAN - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \ done; diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index d2c1accc2e69..2b95e44d20ff 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -25,34 +25,34 @@ $(OUTPUT)/per_event_excludes: ../utils.c DEFAULT_RUN_TESTS := $(RUN_TESTS) override define RUN_TESTS $(DEFAULT_RUN_TESTS) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef DEFAULT_EMIT_TESTS := $(EMIT_TESTS) override define EMIT_TESTS $(DEFAULT_EMIT_TESTS) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef DEFAULT_CLEAN := $(CLEAN) override define CLEAN $(DEFAULT_CLEAN) $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean endef ebb: From aab681bcb13a7b3390ed3075e6bc9426d0bf2245 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 21 Sep 2023 17:26:10 +1000 Subject: [PATCH 1776/2093] selftests/powerpc: Fix emit_tests to work with run_kselftest.sh [ Upstream commit 58b33e78a31782ffe25d404d5eba9a45fe636e27 ] In order to use run_kselftest.sh the list of tests must be emitted to populate kselftest-list.txt. The powerpc Makefile is written to use EMIT_TESTS. But support for EMIT_TESTS was dropped in commit d4e59a536f50 ("selftests: Use runner.sh for emit targets"). Although prior to that commit a548de0fe8e1 ("selftests: lib.mk: add test execute bit check to EMIT_TESTS") had already broken run_kselftest.sh for powerpc due to the executable check using the wrong path. It can be fixed by replacing the EMIT_TESTS definitions with actual emit_tests rules in the powerpc Makefiles. This makes run_kselftest.sh able to run powerpc tests: $ cd linux $ export ARCH=powerpc $ export CROSS_COMPILE=powerpc64le-linux-gnu- $ make headers $ make -j -C tools/testing/selftests install $ grep -c "^powerpc" tools/testing/selftests/kselftest_install/kselftest-list.txt 182 Fixes: d4e59a536f50 ("selftests: Use runner.sh for emit targets") Signed-off-by: Michael Ellerman Link: https://msgid.link/20230921072623.828772-1-mpe@ellerman.id.au Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/Makefile | 7 +++---- tools/testing/selftests/powerpc/pmu/Makefile | 11 ++++++----- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index ae2bfc0d822f..c8c085fa05b0 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -58,12 +58,11 @@ override define INSTALL_RULE done; endef -override define EMIT_TESTS +emit_tests: +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET $@;\ done; -endef override define CLEAN +@for TARGET in $(SUB_DIRS); do \ @@ -76,4 +75,4 @@ endef tags: find . -name '*.c' -o -name '*.h' | xargs ctags -.PHONY: tags $(SUB_DIRS) +.PHONY: tags $(SUB_DIRS) emit_tests diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 2b95e44d20ff..a284fa874a9f 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -30,13 +30,14 @@ override define RUN_TESTS +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef -DEFAULT_EMIT_TESTS := $(EMIT_TESTS) -override define EMIT_TESTS - $(DEFAULT_EMIT_TESTS) +emit_tests: + for TEST in $(TEST_GEN_PROGS); do \ + BASENAME_TEST=`basename $$TEST`; \ + echo "$(COLLECTION):$$BASENAME_TEST"; \ + done +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests -endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE @@ -64,4 +65,4 @@ sampling_tests: event_code_tests: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests ebb sampling_tests event_code_tests +.PHONY: all run_tests ebb sampling_tests event_code_tests emit_tests From 328efccc7847b55b0083a5b5a81e28a4f79b6fa0 Mon Sep 17 00:00:00 2001 From: Nathan Rossi Date: Mon, 14 Aug 2023 01:57:00 +0000 Subject: [PATCH 1777/2093] soc: imx8m: Enable OCOTP clock for imx8mm before reading registers [ Upstream commit 9d1e8275a28f51599d754ce661c91e0a689c0234 ] Commit 836fb30949d9 ("soc: imx8m: Enable OCOTP clock before reading the register") added configuration to enable the OCOTP clock before attempting to read from the associated registers. This same kexec issue is present with the imx8m SoCs that use the imx8mm_soc_uid function (e.g. imx8mp). This requires the imx8mm_soc_uid function to configure the OCOTP clock before accessing the associated registers. This change implements the same clock enable functionality that is present in the imx8mq_soc_revision function for the imx8mm_soc_uid function. Signed-off-by: Nathan Rossi Reviewed-by: Fabio Estevam Fixes: 836fb30949d9 ("soc: imx8m: Enable OCOTP clock before reading the register") Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- drivers/soc/imx/soc-imx8m.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c index 32ed9dc88e45..08197b03955d 100644 --- a/drivers/soc/imx/soc-imx8m.c +++ b/drivers/soc/imx/soc-imx8m.c @@ -100,6 +100,7 @@ static void __init imx8mm_soc_uid(void) { void __iomem *ocotp_base; struct device_node *np; + struct clk *clk; u32 offset = of_machine_is_compatible("fsl,imx8mp") ? IMX8MP_OCOTP_UID_OFFSET : 0; @@ -109,11 +110,20 @@ static void __init imx8mm_soc_uid(void) ocotp_base = of_iomap(np, 0); WARN_ON(!ocotp_base); + clk = of_clk_get_by_name(np, NULL); + if (IS_ERR(clk)) { + WARN_ON(IS_ERR(clk)); + return; + } + + clk_prepare_enable(clk); soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH + offset); soc_uid <<= 32; soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW + offset); + clk_disable_unprepare(clk); + clk_put(clk); iounmap(ocotp_base); of_node_put(np); } From 099cfc6e5d1bbf4639521b9f7be3d70ed6711ded Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 11 Sep 2023 16:45:37 -0500 Subject: [PATCH 1778/2093] arm64: dts: imx: Add imx8mm-prt8mm.dtb to build [ Upstream commit f09752eaf0e8f8befc26b44c4d3e15633e56d16a ] imx8mm-prt8mm.dts was not getting built. Add it to the build. Fixes: 58497d7a13ed ("arm64: dts: imx: add Protonic PRT8MM board") Signed-off-by: Rob Herring Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile index 3ea9edc87909..ac6f780dc191 100644 --- a/arch/arm64/boot/dts/freescale/Makefile +++ b/arch/arm64/boot/dts/freescale/Makefile @@ -62,6 +62,7 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-kontron-bl-osm-s.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-mx8menlo.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-nitrogen-r2.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-rdk.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mm-prt8mm.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-tqma8mqml-mba8mx.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-var-som-symphony.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-venice-gw71xx-0x.dtb From e578a26084eba5758972ede124169510f778cf45 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 19 Sep 2023 18:41:01 +0100 Subject: [PATCH 1779/2093] firmware: arm_ffa: Don't set the memory region attributes for MEM_LEND [ Upstream commit 9dda1178479aa0a73fe0eaabfe2d9a1c603cfeed ] As per the FF-A specification: section "Usage of other memory region attributes", in a transaction to donate memory or lend memory to a single borrower, if the receiver is a PE or Proxy endpoint, the owner must not specify the attributes and the relayer will return INVALID_PARAMETERS if the attributes are set. Let us not set the memory region attributes for MEM_LEND. Fixes: 82a8daaecfd9 ("firmware: arm_ffa: Add support for MEM_LEND") Reported-by: Joao Alves Reported-by: Olivier Deprez Link: https://lore.kernel.org/r/20230919-ffa_v1-1_notif-v2-13-6f3a3ca3923c@arm.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_ffa/driver.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index c37e82359005..21481fc05800 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -478,6 +478,19 @@ static u32 ffa_get_num_pages_sg(struct scatterlist *sg) return num_pages; } +static u8 ffa_memory_attributes_get(u32 func_id) +{ + /* + * For the memory lend or donate operation, if the receiver is a PE or + * a proxy endpoint, the owner/sender must not specify the attributes + */ + if (func_id == FFA_FN_NATIVE(MEM_LEND) || + func_id == FFA_MEM_LEND) + return 0; + + return FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | FFA_MEM_INNER_SHAREABLE; +} + static int ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, struct ffa_mem_ops_args *args) @@ -494,8 +507,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, mem_region->tag = args->tag; mem_region->flags = args->flags; mem_region->sender_id = drv_info->vm_id; - mem_region->attributes = FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | - FFA_MEM_INNER_SHAREABLE; + mem_region->attributes = ffa_memory_attributes_get(func_id); ep_mem_access = &mem_region->ep_mem_access[0]; for (idx = 0; idx < args->nattrs; idx++, ep_mem_access++) { From 0d6c2f0942c3e0bd826c24dc17d1c544f4ec82de Mon Sep 17 00:00:00 2001 From: Wenhua Lin Date: Thu, 21 Sep 2023 20:25:27 +0800 Subject: [PATCH 1780/2093] gpio: pmic-eic-sprd: Add can_sleep flag for PMIC EIC chip [ Upstream commit 26d9e5640d2130ee16df7b1fb6a908f460ab004c ] The drivers uses a mutex and I2C bus access in its PMIC EIC chip get implementation. This means these functions can sleep and the PMIC EIC chip should set the can_sleep property to true. This will ensure that a warning is printed when trying to get the value from a context that potentially can't sleep. Fixes: 348f3cde84ab ("gpio: Add Spreadtrum PMIC EIC driver support") Signed-off-by: Wenhua Lin Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-pmic-eic-sprd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-pmic-eic-sprd.c b/drivers/gpio/gpio-pmic-eic-sprd.c index e518490c4b68..ebbbcb54270d 100644 --- a/drivers/gpio/gpio-pmic-eic-sprd.c +++ b/drivers/gpio/gpio-pmic-eic-sprd.c @@ -337,6 +337,7 @@ static int sprd_pmic_eic_probe(struct platform_device *pdev) pmic_eic->chip.set_config = sprd_pmic_eic_set_config; pmic_eic->chip.set = sprd_pmic_eic_set; pmic_eic->chip.get = sprd_pmic_eic_get; + pmic_eic->chip.can_sleep = true; pmic_eic->intc.name = dev_name(&pdev->dev); pmic_eic->intc.irq_mask = sprd_pmic_eic_irq_mask; From 85fafa7ef0ac44959fd8ec156da6eaf4bb2a0345 Mon Sep 17 00:00:00 2001 From: "William A. Kennington III" Date: Sat, 23 Sep 2023 18:02:14 -0700 Subject: [PATCH 1781/2093] i2c: npcm7xx: Fix callback completion ordering [ Upstream commit 92e73d807b68b2214fcafca4e130b5300a9d4b3c ] Sometimes, our completions race with new master transfers and override the bus->operation and bus->master_or_slave variables. This causes transactions to timeout and kernel crashes less frequently. To remedy this, we re-order all completions to the very end of the function. Fixes: 56a1485b102e ("i2c: npcm7xx: Add Nuvoton NPCM I2C controller driver") Signed-off-by: William A. Kennington III Reviewed-by: Tali Perry Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-npcm7xx.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 83457359ec45..767dd15b3c88 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -696,6 +696,7 @@ static void npcm_i2c_callback(struct npcm_i2c *bus, { struct i2c_msg *msgs; int msgs_num; + bool do_complete = false; msgs = bus->msgs; msgs_num = bus->msgs_num; @@ -724,23 +725,17 @@ static void npcm_i2c_callback(struct npcm_i2c *bus, msgs[1].flags & I2C_M_RD) msgs[1].len = info; } - if (completion_done(&bus->cmd_complete) == false) - complete(&bus->cmd_complete); - break; - + do_complete = true; + break; case I2C_NACK_IND: /* MASTER transmit got a NACK before tx all bytes */ bus->cmd_err = -ENXIO; - if (bus->master_or_slave == I2C_MASTER) - complete(&bus->cmd_complete); - + do_complete = true; break; case I2C_BUS_ERR_IND: /* Bus error */ bus->cmd_err = -EAGAIN; - if (bus->master_or_slave == I2C_MASTER) - complete(&bus->cmd_complete); - + do_complete = true; break; case I2C_WAKE_UP_IND: /* I2C wake up */ @@ -754,6 +749,8 @@ static void npcm_i2c_callback(struct npcm_i2c *bus, if (bus->slave) bus->master_or_slave = I2C_SLAVE; #endif + if (do_complete) + complete(&bus->cmd_complete); } static u8 npcm_i2c_fifo_usage(struct npcm_i2c *bus) From 1375d9600c38c231163de584656b07aef9a27b0d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 21 Jul 2023 13:18:41 -0700 Subject: [PATCH 1782/2093] x86/reboot: VMCLEAR active VMCSes before emergency reboot [ Upstream commit b23c83ad2c638420ec0608a9de354507c41bec29 ] VMCLEAR active VMCSes before any emergency reboot, not just if the kernel may kexec into a new kernel after a crash. Per Intel's SDM, the VMX architecture doesn't require the CPU to flush the VMCS cache on INIT. If an emergency reboot doesn't RESET CPUs, cached VMCSes could theoretically be kept and only be written back to memory after the new kernel is booted, i.e. could effectively corrupt memory after reboot. Opportunistically remove the setting of the global pointer to NULL to make checkpatch happy. Cc: Andrew Cooper Link: https://lore.kernel.org/r/20230721201859.2307736-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Sasha Levin --- arch/x86/include/asm/kexec.h | 2 -- arch/x86/include/asm/reboot.h | 2 ++ arch/x86/kernel/crash.c | 31 ------------------------------- arch/x86/kernel/reboot.c | 22 ++++++++++++++++++++++ arch/x86/kvm/vmx/vmx.c | 10 +++------- 5 files changed, 27 insertions(+), 40 deletions(-) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index a3760ca796aa..256eee99afc8 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -208,8 +208,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image); #endif #endif -typedef void crash_vmclear_fn(void); -extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; extern void kdump_nmi_shootdown_cpus(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index bc5b4d788c08..2551baec927d 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 +typedef void crash_vmclear_fn(void); +extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; void cpu_emergency_disable_virtualization(void); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index cdd92ab43cda..54cd959cb316 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -48,38 +48,12 @@ struct crash_memmap_data { unsigned int type; }; -/* - * This is used to VMCLEAR all VMCSs loaded on the - * processor. And when loading kvm_intel module, the - * callback function pointer will be assigned. - * - * protected by rcu. - */ -crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL; -EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); - -static inline void cpu_crash_vmclear_loaded_vmcss(void) -{ - crash_vmclear_fn *do_vmclear_operation = NULL; - - rcu_read_lock(); - do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); - if (do_vmclear_operation) - do_vmclear_operation(); - rcu_read_unlock(); -} - #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { crash_save_cpu(regs, cpu); - /* - * VMCLEAR VMCSs loaded on all cpus if needed. - */ - cpu_crash_vmclear_loaded_vmcss(); - /* * Disable Intel PT to stop its logging */ @@ -133,11 +107,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs) crash_smp_send_stop(); - /* - * VMCLEAR VMCSs loaded on this cpu if needed. - */ - cpu_crash_vmclear_loaded_vmcss(); - cpu_emergency_disable_virtualization(); /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index d03c551defcc..299b970e5f82 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -787,6 +787,26 @@ void machine_crash_shutdown(struct pt_regs *regs) } #endif +/* + * This is used to VMCLEAR all VMCSs loaded on the + * processor. And when loading kvm_intel module, the + * callback function pointer will be assigned. + * + * protected by rcu. + */ +crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; +EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss); + +static inline void cpu_crash_vmclear_loaded_vmcss(void) +{ + crash_vmclear_fn *do_vmclear_operation = NULL; + + rcu_read_lock(); + do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss); + if (do_vmclear_operation) + do_vmclear_operation(); + rcu_read_unlock(); +} /* This is the CPU performing the emergency shutdown work. */ int crashing_cpu = -1; @@ -798,6 +818,8 @@ int crashing_cpu = -1; */ void cpu_emergency_disable_virtualization(void) { + cpu_crash_vmclear_loaded_vmcss(); + cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4e972b9b68e5..31a10d774df6 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -40,7 +40,7 @@ #include #include #include -#include +#include #include #include #include @@ -702,7 +702,6 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, return ret; } -#ifdef CONFIG_KEXEC_CORE static void crash_vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); @@ -712,7 +711,6 @@ static void crash_vmclear_local_loaded_vmcss(void) loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); } -#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -8522,10 +8520,9 @@ static void __vmx_exit(void) { allow_smaller_maxphyaddr = false; -#ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); -#endif + vmx_cleanup_l1d_flush(); } @@ -8598,10 +8595,9 @@ static int __init vmx_init(void) pi_init_cpu(cpu); } -#ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); -#endif + vmx_check_vmcs12_offsets(); /* From 89744b64914426cbabceb3d8a149176b5dafdfb5 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 21 Dec 2022 14:13:51 +0800 Subject: [PATCH 1783/2093] ceph: drop messages from MDS when unmounting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e3dfcab2080dc1f9a4b09cc1327361bc2845bfcd ] When unmounting all the dirty buffers will be flushed and after the last osd request is finished the last reference of the i_count will be released. Then it will flush the dirty cap/snap to MDSs, and the unmounting won't wait the possible acks, which will ihold the inodes when updating the metadata locally but makes no sense any more, of this. This will make the evict_inodes() to skip these inodes. If encrypt is enabled the kernel generate a warning when removing the encrypt keys when the skipped inodes still hold the keyring: WARNING: CPU: 4 PID: 168846 at fs/crypto/keyring.c:242 fscrypt_destroy_keyring+0x7e/0xd0 CPU: 4 PID: 168846 Comm: umount Tainted: G S 6.1.0-rc5-ceph-g72ead199864c #1 Hardware name: Supermicro SYS-5018R-WR/X10SRW-F, BIOS 2.0 12/17/2015 RIP: 0010:fscrypt_destroy_keyring+0x7e/0xd0 RSP: 0018:ffffc9000b277e28 EFLAGS: 00010202 RAX: 0000000000000002 RBX: ffff88810d52ac00 RCX: ffff88810b56aa00 RDX: 0000000080000000 RSI: ffffffff822f3a09 RDI: ffff888108f59000 RBP: ffff8881d394fb88 R08: 0000000000000028 R09: 0000000000000000 R10: 0000000000000001 R11: 11ff4fe6834fcd91 R12: ffff8881d394fc40 R13: ffff888108f59000 R14: ffff8881d394f800 R15: 0000000000000000 FS: 00007fd83f6f1080(0000) GS:ffff88885fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f918d417000 CR3: 000000017f89a005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: generic_shutdown_super+0x47/0x120 kill_anon_super+0x14/0x30 ceph_kill_sb+0x36/0x90 [ceph] deactivate_locked_super+0x29/0x60 cleanup_mnt+0xb8/0x140 task_work_run+0x67/0xb0 exit_to_user_mode_prepare+0x23d/0x240 syscall_exit_to_user_mode+0x25/0x60 do_syscall_64+0x40/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fd83dc39e9b Later the kernel will crash when iput() the inodes and dereferencing the "sb->s_master_keys", which has been released by the generic_shutdown_super(). Link: https://tracker.ceph.com/issues/59162 Signed-off-by: Xiubo Li Reviewed-and-tested-by: Luís Henriques Reviewed-by: Milind Changire Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/caps.c | 6 +++- fs/ceph/mds_client.c | 12 +++++-- fs/ceph/mds_client.h | 11 +++++-- fs/ceph/quota.c | 14 ++++----- fs/ceph/snap.c | 10 +++--- fs/ceph/super.c | 75 +++++++++++++++++++++++++++++++++++++++++--- fs/ceph/super.h | 3 ++ 7 files changed, 109 insertions(+), 22 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 4a9ad5ff726d..36052a362683 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4100,6 +4100,9 @@ void ceph_handle_caps(struct ceph_mds_session *session, dout("handle_caps from mds%d\n", session->s_mds); + if (!ceph_inc_mds_stopping_blocker(mdsc, session)) + return; + /* decode */ end = msg->front.iov_base + msg->front.iov_len; if (msg->front.iov_len < sizeof(*h)) @@ -4196,7 +4199,6 @@ void ceph_handle_caps(struct ceph_mds_session *session, vino.snap, inode); mutex_lock(&session->s_mutex); - inc_session_sequence(session); dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq, (unsigned)seq); @@ -4299,6 +4301,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, done_unlocked: iput(inode); out: + ceph_dec_mds_stopping_blocker(mdsc); + ceph_put_string(extra_info.pool_ns); /* Defer closing the sessions after s_mutex lock being released */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 5399a9ea5b4f..f6a7fd47efd7 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4546,6 +4546,9 @@ static void handle_lease(struct ceph_mds_client *mdsc, dout("handle_lease from mds%d\n", mds); + if (!ceph_inc_mds_stopping_blocker(mdsc, session)) + return; + /* decode */ if (msg->front.iov_len < sizeof(*h) + sizeof(u32)) goto bad; @@ -4564,8 +4567,6 @@ static void handle_lease(struct ceph_mds_client *mdsc, dname.len, dname.name); mutex_lock(&session->s_mutex); - inc_session_sequence(session); - if (!inode) { dout("handle_lease no inode %llx\n", vino.ino); goto release; @@ -4627,9 +4628,13 @@ static void handle_lease(struct ceph_mds_client *mdsc, out: mutex_unlock(&session->s_mutex); iput(inode); + + ceph_dec_mds_stopping_blocker(mdsc); return; bad: + ceph_dec_mds_stopping_blocker(mdsc); + pr_err("corrupt lease message\n"); ceph_msg_dump(msg); } @@ -4825,6 +4830,9 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) } init_completion(&mdsc->safe_umount_waiters); + spin_lock_init(&mdsc->stopping_lock); + atomic_set(&mdsc->stopping_blockers, 0); + init_completion(&mdsc->stopping_waiter); init_waitqueue_head(&mdsc->session_close_wq); INIT_LIST_HEAD(&mdsc->waiting_for_map); mdsc->quotarealms_inodes = RB_ROOT; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 9a80658f4167..0913959ccfa6 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -381,8 +381,9 @@ struct cap_wait { }; enum { - CEPH_MDSC_STOPPING_BEGIN = 1, - CEPH_MDSC_STOPPING_FLUSHED = 2, + CEPH_MDSC_STOPPING_BEGIN = 1, + CEPH_MDSC_STOPPING_FLUSHING = 2, + CEPH_MDSC_STOPPING_FLUSHED = 3, }; /* @@ -401,7 +402,11 @@ struct ceph_mds_client { struct ceph_mds_session **sessions; /* NULL for mds if no session */ atomic_t num_sessions; int max_sessions; /* len of sessions array */ - int stopping; /* true if shutting down */ + + spinlock_t stopping_lock; /* protect snap_empty */ + int stopping; /* the stage of shutting down */ + atomic_t stopping_blockers; + struct completion stopping_waiter; atomic64_t quotarealms_count; /* # realms with quota */ /* diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 64592adfe48f..f7fcf7f08ec6 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -47,25 +47,23 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, struct inode *inode; struct ceph_inode_info *ci; + if (!ceph_inc_mds_stopping_blocker(mdsc, session)) + return; + if (msg->front.iov_len < sizeof(*h)) { pr_err("%s corrupt message mds%d len %d\n", __func__, session->s_mds, (int)msg->front.iov_len); ceph_msg_dump(msg); - return; + goto out; } - /* increment msg sequence number */ - mutex_lock(&session->s_mutex); - inc_session_sequence(session); - mutex_unlock(&session->s_mutex); - /* lookup inode */ vino.ino = le64_to_cpu(h->ino); vino.snap = CEPH_NOSNAP; inode = ceph_find_inode(sb, vino); if (!inode) { pr_warn("Failed to find inode %llu\n", vino.ino); - return; + goto out; } ci = ceph_inode(inode); @@ -78,6 +76,8 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, spin_unlock(&ci->i_ceph_lock); iput(inode); +out: + ceph_dec_mds_stopping_blocker(mdsc); } static struct ceph_quotarealm_inode * diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 2e73ba62bd7a..82f7592e1747 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1012,6 +1012,9 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, int locked_rwsem = 0; bool close_sessions = false; + if (!ceph_inc_mds_stopping_blocker(mdsc, session)) + return; + /* decode */ if (msg->front.iov_len < sizeof(*h)) goto bad; @@ -1027,10 +1030,6 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, dout("%s from mds%d op %s split %llx tracelen %d\n", __func__, mds, ceph_snap_op_name(op), split, trace_len); - mutex_lock(&session->s_mutex); - inc_session_sequence(session); - mutex_unlock(&session->s_mutex); - down_write(&mdsc->snap_rwsem); locked_rwsem = 1; @@ -1148,6 +1147,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, up_write(&mdsc->snap_rwsem); flush_snaps(mdsc); + ceph_dec_mds_stopping_blocker(mdsc); return; bad: @@ -1157,6 +1157,8 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, if (locked_rwsem) up_write(&mdsc->snap_rwsem); + ceph_dec_mds_stopping_blocker(mdsc); + if (close_sessions) ceph_mdsc_close_sessions(mdsc); return; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index a5f52013314d..281b493fdac8 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1365,25 +1365,90 @@ static int ceph_init_fs_context(struct fs_context *fc) return -ENOMEM; } +/* + * Return true if it successfully increases the blocker counter, + * or false if the mdsc is in stopping and flushed state. + */ +static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc) +{ + spin_lock(&mdsc->stopping_lock); + if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) { + spin_unlock(&mdsc->stopping_lock); + return false; + } + atomic_inc(&mdsc->stopping_blockers); + spin_unlock(&mdsc->stopping_lock); + return true; +} + +static void __dec_stopping_blocker(struct ceph_mds_client *mdsc) +{ + spin_lock(&mdsc->stopping_lock); + if (!atomic_dec_return(&mdsc->stopping_blockers) && + mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) + complete_all(&mdsc->stopping_waiter); + spin_unlock(&mdsc->stopping_lock); +} + +/* For metadata IO requests */ +bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session) +{ + mutex_lock(&session->s_mutex); + inc_session_sequence(session); + mutex_unlock(&session->s_mutex); + + return __inc_stopping_blocker(mdsc); +} + +void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc) +{ + __dec_stopping_blocker(mdsc); +} + static void ceph_kill_sb(struct super_block *s) { struct ceph_fs_client *fsc = ceph_sb_to_client(s); + struct ceph_mds_client *mdsc = fsc->mdsc; + bool wait; dout("kill_sb %p\n", s); - ceph_mdsc_pre_umount(fsc->mdsc); + ceph_mdsc_pre_umount(mdsc); flush_fs_workqueues(fsc); /* * Though the kill_anon_super() will finally trigger the - * sync_filesystem() anyway, we still need to do it here - * and then bump the stage of shutdown to stop the work - * queue as earlier as possible. + * sync_filesystem() anyway, we still need to do it here and + * then bump the stage of shutdown. This will allow us to + * drop any further message, which will increase the inodes' + * i_count reference counters but makes no sense any more, + * from MDSs. + * + * Without this when evicting the inodes it may fail in the + * kill_anon_super(), which will trigger a warning when + * destroying the fscrypt keyring and then possibly trigger + * a further crash in ceph module when the iput() tries to + * evict the inodes later. */ sync_filesystem(s); - fsc->mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; + spin_lock(&mdsc->stopping_lock); + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING; + wait = !!atomic_read(&mdsc->stopping_blockers); + spin_unlock(&mdsc->stopping_lock); + if (wait && atomic_read(&mdsc->stopping_blockers)) { + long timeleft = wait_for_completion_killable_timeout( + &mdsc->stopping_waiter, + fsc->client->options->mount_timeout); + if (!timeleft) /* timed out */ + pr_warn("umount timed out, %ld\n", timeleft); + else if (timeleft < 0) /* killed */ + pr_warn("umount was killed, %ld\n", timeleft); + } + + mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 562f42f4a77d..7ca74f5f70be 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1374,4 +1374,7 @@ extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf); extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc); +bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session); +void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc); #endif /* _FS_CEPH_SUPER_H */ From be8f49029eca3efbad0d74dbff3cb9129994ffab Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 16 Aug 2023 11:32:21 +0900 Subject: [PATCH 1784/2093] dma-debug: don't call __dma_entry_alloc_check_leak() under free_entries_lock [ Upstream commit fb5a4315591dae307a65fc246ca80b5159d296e1 ] __dma_entry_alloc_check_leak() calls into printk -> serial console output (qcom geni) and grabs port->lock under free_entries_lock spin lock, which is a reverse locking dependency chain as qcom_geni IRQ handler can call into dma-debug code and grab free_entries_lock under port->lock. Move __dma_entry_alloc_check_leak() call out of free_entries_lock scope so that we don't acquire serial console's port->lock under it. Trimmed-down lockdep splat: The existing dependency chain (in reverse order) is: -> #2 (free_entries_lock){-.-.}-{2:2}: _raw_spin_lock_irqsave+0x60/0x80 dma_entry_alloc+0x38/0x110 debug_dma_map_page+0x60/0xf8 dma_map_page_attrs+0x1e0/0x230 dma_map_single_attrs.constprop.0+0x6c/0xc8 geni_se_rx_dma_prep+0x40/0xcc qcom_geni_serial_isr+0x310/0x510 __handle_irq_event_percpu+0x110/0x244 handle_irq_event_percpu+0x20/0x54 handle_irq_event+0x50/0x88 handle_fasteoi_irq+0xa4/0xcc handle_irq_desc+0x28/0x40 generic_handle_domain_irq+0x24/0x30 gic_handle_irq+0xc4/0x148 do_interrupt_handler+0xa4/0xb0 el1_interrupt+0x34/0x64 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x64/0x68 arch_local_irq_enable+0x4/0x8 ____do_softirq+0x18/0x24 ... -> #1 (&port_lock_key){-.-.}-{2:2}: _raw_spin_lock_irqsave+0x60/0x80 qcom_geni_serial_console_write+0x184/0x1dc console_flush_all+0x344/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 register_console+0x230/0x38c uart_add_one_port+0x338/0x494 qcom_geni_serial_probe+0x390/0x424 platform_probe+0x70/0xc0 really_probe+0x148/0x280 __driver_probe_device+0xfc/0x114 driver_probe_device+0x44/0x100 __device_attach_driver+0x64/0xdc bus_for_each_drv+0xb0/0xd8 __device_attach+0xe4/0x140 device_initial_probe+0x1c/0x28 bus_probe_device+0x44/0xb0 device_add+0x538/0x668 of_device_add+0x44/0x50 of_platform_device_create_pdata+0x94/0xc8 of_platform_bus_create+0x270/0x304 of_platform_populate+0xac/0xc4 devm_of_platform_populate+0x60/0xac geni_se_probe+0x154/0x160 platform_probe+0x70/0xc0 ... -> #0 (console_owner){-...}-{0:0}: __lock_acquire+0xdf8/0x109c lock_acquire+0x234/0x284 console_flush_all+0x330/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 dma_entry_alloc+0xb4/0x110 debug_dma_map_sg+0xdc/0x2f8 __dma_map_sg_attrs+0xac/0xe4 dma_map_sgtable+0x30/0x4c get_pages+0x1d4/0x1e4 [msm] msm_gem_pin_pages_locked+0x38/0xac [msm] msm_gem_pin_vma_locked+0x58/0x88 [msm] msm_ioctl_gem_submit+0xde4/0x13ac [msm] drm_ioctl_kernel+0xe0/0x15c drm_ioctl+0x2e8/0x3f4 vfs_ioctl+0x30/0x50 ... Chain exists of: console_owner --> &port_lock_key --> free_entries_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(free_entries_lock); lock(&port_lock_key); lock(free_entries_lock); lock(console_owner); *** DEADLOCK *** Call trace: dump_backtrace+0xb4/0xf0 show_stack+0x20/0x30 dump_stack_lvl+0x60/0x84 dump_stack+0x18/0x24 print_circular_bug+0x1cc/0x234 check_noncircular+0x78/0xac __lock_acquire+0xdf8/0x109c lock_acquire+0x234/0x284 console_flush_all+0x330/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 dma_entry_alloc+0xb4/0x110 debug_dma_map_sg+0xdc/0x2f8 __dma_map_sg_attrs+0xac/0xe4 dma_map_sgtable+0x30/0x4c get_pages+0x1d4/0x1e4 [msm] msm_gem_pin_pages_locked+0x38/0xac [msm] msm_gem_pin_vma_locked+0x58/0x88 [msm] msm_ioctl_gem_submit+0xde4/0x13ac [msm] drm_ioctl_kernel+0xe0/0x15c drm_ioctl+0x2e8/0x3f4 vfs_ioctl+0x30/0x50 ... Reported-by: Rob Clark Signed-off-by: Sergey Senozhatsky Acked-by: Robin Murphy Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- kernel/dma/debug.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 18c93c2276ca..3ff7089d11a9 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -603,15 +603,19 @@ static struct dma_debug_entry *__dma_entry_alloc(void) return entry; } -static void __dma_entry_alloc_check_leak(void) +/* + * This should be called outside of free_entries_lock scope to avoid potential + * deadlocks with serial consoles that use DMA. + */ +static void __dma_entry_alloc_check_leak(u32 nr_entries) { - u32 tmp = nr_total_entries % nr_prealloc_entries; + u32 tmp = nr_entries % nr_prealloc_entries; /* Shout each time we tick over some multiple of the initial pool */ if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) { pr_info("dma_debug_entry pool grown to %u (%u00%%)\n", - nr_total_entries, - (nr_total_entries / nr_prealloc_entries)); + nr_entries, + (nr_entries / nr_prealloc_entries)); } } @@ -622,8 +626,10 @@ static void __dma_entry_alloc_check_leak(void) */ static struct dma_debug_entry *dma_entry_alloc(void) { + bool alloc_check_leak = false; struct dma_debug_entry *entry; unsigned long flags; + u32 nr_entries; spin_lock_irqsave(&free_entries_lock, flags); if (num_free_entries == 0) { @@ -633,13 +639,17 @@ static struct dma_debug_entry *dma_entry_alloc(void) pr_err("debugging out of memory - disabling\n"); return NULL; } - __dma_entry_alloc_check_leak(); + alloc_check_leak = true; + nr_entries = nr_total_entries; } entry = __dma_entry_alloc(); spin_unlock_irqrestore(&free_entries_lock, flags); + if (alloc_check_leak) + __dma_entry_alloc_check_leak(nr_entries); + #ifdef CONFIG_STACKTRACE entry->stack_len = stack_trace_save(entry->stack_entries, ARRAY_SIZE(entry->stack_entries), From 5685f8a6fae1fbe480493b980a1fdbe67c86a094 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 29 Aug 2023 22:53:52 +0200 Subject: [PATCH 1785/2093] bpf: Annotate bpf_long_memcpy with data_race [ Upstream commit 6a86b5b5cd76d2734304a0173f5f01aa8aa2025e ] syzbot reported a data race splat between two processes trying to update the same BPF map value via syscall on different CPUs: BUG: KCSAN: data-race in bpf_percpu_array_update / bpf_percpu_array_update write to 0xffffe8fffe7425d8 of 8 bytes by task 8257 on cpu 1: bpf_long_memcpy include/linux/bpf.h:428 [inline] bpf_obj_memcpy include/linux/bpf.h:441 [inline] copy_map_value_long include/linux/bpf.h:464 [inline] bpf_percpu_array_update+0x3bb/0x500 kernel/bpf/arraymap.c:380 bpf_map_update_value+0x190/0x370 kernel/bpf/syscall.c:175 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1749 bpf_map_do_batch+0x2df/0x3d0 kernel/bpf/syscall.c:4648 __sys_bpf+0x28a/0x780 __do_sys_bpf kernel/bpf/syscall.c:5241 [inline] __se_sys_bpf kernel/bpf/syscall.c:5239 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5239 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffffe8fffe7425d8 of 8 bytes by task 8268 on cpu 0: bpf_long_memcpy include/linux/bpf.h:428 [inline] bpf_obj_memcpy include/linux/bpf.h:441 [inline] copy_map_value_long include/linux/bpf.h:464 [inline] bpf_percpu_array_update+0x3bb/0x500 kernel/bpf/arraymap.c:380 bpf_map_update_value+0x190/0x370 kernel/bpf/syscall.c:175 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1749 bpf_map_do_batch+0x2df/0x3d0 kernel/bpf/syscall.c:4648 __sys_bpf+0x28a/0x780 __do_sys_bpf kernel/bpf/syscall.c:5241 [inline] __se_sys_bpf kernel/bpf/syscall.c:5239 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5239 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x0000000000000000 -> 0xfffffff000002788 The bpf_long_memcpy is used with 8-byte aligned pointers, power-of-8 size and forced to use long read/writes to try to atomically copy long counters. It is best-effort only and no barriers are here since it _will_ race with concurrent updates from BPF programs. The bpf_long_memcpy() is called from bpf(2) syscall. Marco suggested that the best way to make this known to KCSAN would be to use data_race() annotation. Reported-by: syzbot+97522333291430dd277f@syzkaller.appspotmail.com Suggested-by: Marco Elver Signed-off-by: Daniel Borkmann Acked-by: Marco Elver Link: https://lore.kernel.org/bpf/000000000000d87a7f06040c970c@google.com Link: https://lore.kernel.org/bpf/57628f7a15e20d502247c3b55fceb1cb2b31f266.1693342186.git.daniel@iogearbox.net Signed-off-by: Sasha Levin --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b3d3aa8437dc..1ed2ec035e77 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -301,7 +301,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) size /= sizeof(long); while (size--) - *ldst++ = *lsrc++; + data_race(*ldst++ = *lsrc++); } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ From e15bb292b24630ee832bfc7fd616bd72c7682bbb Mon Sep 17 00:00:00 2001 From: Tobias Schramm Date: Sun, 27 Aug 2023 17:25:57 +0200 Subject: [PATCH 1786/2093] spi: sun6i: reduce DMA RX transfer width to single byte [ Upstream commit 171f8a49f212e87a8b04087568e1b3d132e36a18 ] Through empirical testing it has been determined that sometimes RX SPI transfers with DMA enabled return corrupted data. This is down to single or even multiple bytes lost during DMA transfer from SPI peripheral to memory. It seems the RX FIFO within the SPI peripheral can become confused when performing bus read accesses wider than a single byte to it during an active SPI transfer. This patch reduces the width of individual DMA read accesses to the RX FIFO to a single byte to mitigate that issue. Signed-off-by: Tobias Schramm Link: https://lore.kernel.org/r/20230827152558.5368-2-t.schramm@manjaro.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-sun6i.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c index 23ad052528db..2bfe87873edb 100644 --- a/drivers/spi/spi-sun6i.c +++ b/drivers/spi/spi-sun6i.c @@ -200,7 +200,7 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi, struct dma_slave_config rxconf = { .direction = DMA_DEV_TO_MEM, .src_addr = sspi->dma_addr_rx, - .src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES, + .src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE, .src_maxburst = 8, }; From 36b29974a7ad2ff604c24ad348f940506c7b1209 Mon Sep 17 00:00:00 2001 From: Tobias Schramm Date: Sun, 27 Aug 2023 17:25:58 +0200 Subject: [PATCH 1787/2093] spi: sun6i: fix race between DMA RX transfer completion and RX FIFO drain [ Upstream commit 1f11f4202caf5710204d334fe63392052783876d ] Previously the transfer complete IRQ immediately drained to RX FIFO to read any data remaining in FIFO to the RX buffer. This behaviour is correct when dealing with SPI in interrupt mode. However in DMA mode the transfer complete interrupt still fires as soon as all bytes to be transferred have been stored in the FIFO. At that point data in the FIFO still needs to be picked up by the DMA engine. Thus the drain procedure and DMA engine end up racing to read from RX FIFO, corrupting any data read. Additionally the RX buffer pointer is never adjusted according to DMA progress in DMA mode, thus calling the RX FIFO drain procedure in DMA mode is a bug. Fix corruptions in DMA RX mode by draining RX FIFO only in interrupt mode. Also wait for completion of RX DMA when in DMA mode before returning to ensure all data has been copied to the supplied memory buffer. Signed-off-by: Tobias Schramm Link: https://lore.kernel.org/r/20230827152558.5368-3-t.schramm@manjaro.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-sun6i.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c index 2bfe87873edb..d79853ba7792 100644 --- a/drivers/spi/spi-sun6i.c +++ b/drivers/spi/spi-sun6i.c @@ -95,6 +95,7 @@ struct sun6i_spi { struct reset_control *rstc; struct completion done; + struct completion dma_rx_done; const u8 *tx_buf; u8 *rx_buf; @@ -189,6 +190,13 @@ static size_t sun6i_spi_max_transfer_size(struct spi_device *spi) return SUN6I_MAX_XFER_SIZE - 1; } +static void sun6i_spi_dma_rx_cb(void *param) +{ + struct sun6i_spi *sspi = param; + + complete(&sspi->dma_rx_done); +} + static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi, struct spi_transfer *tfr) { @@ -213,6 +221,8 @@ static int sun6i_spi_prepare_dma(struct sun6i_spi *sspi, DMA_PREP_INTERRUPT); if (!rxdesc) return -EINVAL; + rxdesc->callback_param = sspi; + rxdesc->callback = sun6i_spi_dma_rx_cb; } txdesc = NULL; @@ -268,6 +278,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master, return -EINVAL; reinit_completion(&sspi->done); + reinit_completion(&sspi->dma_rx_done); sspi->tx_buf = tfr->tx_buf; sspi->rx_buf = tfr->rx_buf; sspi->len = tfr->len; @@ -426,6 +437,22 @@ static int sun6i_spi_transfer_one(struct spi_master *master, start = jiffies; timeout = wait_for_completion_timeout(&sspi->done, msecs_to_jiffies(tx_time)); + + if (!use_dma) { + sun6i_spi_drain_fifo(sspi); + } else { + if (timeout && rx_len) { + /* + * Even though RX on the peripheral side has finished + * RX DMA might still be in flight + */ + timeout = wait_for_completion_timeout(&sspi->dma_rx_done, + timeout); + if (!timeout) + dev_warn(&master->dev, "RX DMA timeout\n"); + } + } + end = jiffies; if (!timeout) { dev_warn(&master->dev, @@ -453,7 +480,6 @@ static irqreturn_t sun6i_spi_handler(int irq, void *dev_id) /* Transfer complete */ if (status & SUN6I_INT_CTL_TC) { sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_TC); - sun6i_spi_drain_fifo(sspi); complete(&sspi->done); return IRQ_HANDLED; } @@ -611,6 +637,7 @@ static int sun6i_spi_probe(struct platform_device *pdev) } init_completion(&sspi->done); + init_completion(&sspi->dma_rx_done); sspi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); if (IS_ERR(sspi->rstc)) { From be90c9e29dd59b7d19a73297a1590ff3ec1d22ea Mon Sep 17 00:00:00 2001 From: Nigel Kirkland Date: Thu, 17 Aug 2023 12:43:01 -0700 Subject: [PATCH 1788/2093] nvme-fc: Prevent null pointer dereference in nvme_fc_io_getuuid() [ Upstream commit 8ae5b3a685dc59a8cf7ccfe0e850999ba9727a3c ] The nvme_fc_fcp_op structure describing an AEN operation is initialized with a null request structure pointer. An FC LLDD may make a call to nvme_fc_io_getuuid passing a pointer to an nvmefc_fcp_req for an AEN operation. Add validation of the request structure pointer before dereference. Signed-off-by: Nigel Kirkland Reviewed-by: James Smart Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/fc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 6c3d469eed7e..177a365b8ec5 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1911,7 +1911,7 @@ char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req) struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req); struct request *rq = op->rq; - if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !rq->bio) + if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !rq || !rq->bio) return NULL; return blkcg_get_fc_appid(rq->bio); } From 632e0fcf409b421a0625d8b1bb5b6b1b876186b2 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 30 Aug 2023 08:10:01 +0200 Subject: [PATCH 1789/2093] parisc: sba: Fix compile warning wrt list of SBA devices [ Upstream commit eb3255ee8f6f4691471a28fbf22db5e8901116cd ] Fix this makecheck warning: drivers/parisc/sba_iommu.c:98:19: warning: symbol 'sba_list' was not declared. Should it be static? Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- arch/parisc/include/asm/ropes.h | 3 +++ drivers/char/agp/parisc-agp.c | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/parisc/include/asm/ropes.h b/arch/parisc/include/asm/ropes.h index 8e51c775c80a..62399c7ea94a 100644 --- a/arch/parisc/include/asm/ropes.h +++ b/arch/parisc/include/asm/ropes.h @@ -86,6 +86,9 @@ struct sba_device { struct ioc ioc[MAX_IOC]; }; +/* list of SBA's in system, see drivers/parisc/sba_iommu.c */ +extern struct sba_device *sba_list; + #define ASTRO_RUNWAY_PORT 0x582 #define IKE_MERCED_PORT 0x803 #define REO_MERCED_PORT 0x804 diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index 514f9f287a78..c6f181702b9a 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -394,8 +394,6 @@ find_quicksilver(struct device *dev, void *data) static int __init parisc_agp_init(void) { - extern struct sba_device *sba_list; - int err = -1; struct parisc_device *sba = NULL, *lba = NULL; struct lba_device *lbadev = NULL; From 60caeaf090d5b8e445b85a80ee7a3dfdbb5edc1d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 30 Aug 2023 11:59:55 +0200 Subject: [PATCH 1790/2093] parisc: iosapic.c: Fix sparse warnings [ Upstream commit 927c6c8aa27c284a799b8c18784e37d3373af908 ] Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/parisc/iosapic.c | 4 ++-- drivers/parisc/iosapic_private.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index bcc1dae00780..890c3c0f3d14 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -202,9 +202,9 @@ static inline void iosapic_write(void __iomem *iosapic, unsigned int reg, u32 va static DEFINE_SPINLOCK(iosapic_lock); -static inline void iosapic_eoi(void __iomem *addr, unsigned int data) +static inline void iosapic_eoi(__le32 __iomem *addr, __le32 data) { - __raw_writel(data, addr); + __raw_writel((__force u32)data, addr); } /* diff --git a/drivers/parisc/iosapic_private.h b/drivers/parisc/iosapic_private.h index 73ecc657ad95..bd8ff40162b4 100644 --- a/drivers/parisc/iosapic_private.h +++ b/drivers/parisc/iosapic_private.h @@ -118,8 +118,8 @@ struct iosapic_irt { struct vector_info { struct iosapic_info *iosapic; /* I/O SAPIC this vector is on */ struct irt_entry *irte; /* IRT entry */ - u32 __iomem *eoi_addr; /* precalculate EOI reg address */ - u32 eoi_data; /* IA64: ? PA: swapped txn_data */ + __le32 __iomem *eoi_addr; /* precalculate EOI reg address */ + __le32 eoi_data; /* IA64: ? PA: swapped txn_data */ int txn_irq; /* virtual IRQ number for processor */ ulong txn_addr; /* IA64: id_eid PA: partial HPA */ u32 txn_data; /* CPU interrupt bit */ From 8a2c2630e18dc43ceb6de1137bb7042d250b1bfd Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 31 Aug 2023 22:08:32 +0200 Subject: [PATCH 1791/2093] parisc: drivers: Fix sparse warning [ Upstream commit b137b9d60b8add5620a06c687a71ce18776730b0 ] Fix "warning: directive in macro's argument list" warning. Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- arch/parisc/kernel/drivers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index e7ee0c0c91d3..8f12b9f318ae 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -924,9 +924,9 @@ static __init void qemu_header(void) pr_info("#define PARISC_MODEL \"%s\"\n\n", boot_cpu_data.pdc.sys_model_name); + #define p ((unsigned long *)&boot_cpu_data.pdc.model) pr_info("#define PARISC_PDC_MODEL 0x%lx, 0x%lx, 0x%lx, " "0x%lx, 0x%lx, 0x%lx, 0x%lx, 0x%lx, 0x%lx\n\n", - #define p ((unsigned long *)&boot_cpu_data.pdc.model) p[0], p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8]); #undef p From 655e9d209c0604d9559697c3cb8014e3ca7c0d9e Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 31 Aug 2023 22:36:12 +0200 Subject: [PATCH 1792/2093] parisc: irq: Make irq_stack_union static to avoid sparse warning [ Upstream commit b1bef1388c427cdad7331a9c8eb4ebbbe5b954b0 ] Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- arch/parisc/kernel/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index b05055f3ba4b..9ddb2e397058 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -368,7 +368,7 @@ union irq_stack_union { volatile unsigned int lock[1]; }; -DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = { +static DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = { .slock = { 1,1,1,1 }, }; #endif From 843348f9e4aab5802b27db8d89634a40c88854c1 Mon Sep 17 00:00:00 2001 From: Javed Hasan Date: Fri, 1 Sep 2023 11:36:46 +0530 Subject: [PATCH 1793/2093] scsi: qedf: Add synchronization between I/O completions and abort [ Upstream commit 7df0b2605489bef3f4223ad66f1f9bb8d50d4cd2 ] Avoid race condition between I/O completion and abort processing by protecting the cmd_type with the rport lock. Signed-off-by: Javed Hasan Signed-off-by: Saurav Kashyap Link: https://lore.kernel.org/r/20230901060646.27885-1-skashyap@marvell.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedf/qedf_io.c | 10 ++++++++-- drivers/scsi/qedf/qedf_main.c | 7 ++++++- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index 4750ec5789a8..10fe3383855c 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -1904,6 +1904,7 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts) goto drop_rdata_kref; } + spin_lock_irqsave(&fcport->rport_lock, flags); if (!test_bit(QEDF_CMD_OUTSTANDING, &io_req->flags) || test_bit(QEDF_CMD_IN_CLEANUP, &io_req->flags) || test_bit(QEDF_CMD_IN_ABORT, &io_req->flags)) { @@ -1911,17 +1912,20 @@ int qedf_initiate_abts(struct qedf_ioreq *io_req, bool return_scsi_cmd_on_abts) "io_req xid=0x%x sc_cmd=%p already in cleanup or abort processing or already completed.\n", io_req->xid, io_req->sc_cmd); rc = 1; + spin_unlock_irqrestore(&fcport->rport_lock, flags); goto drop_rdata_kref; } + /* Set the command type to abort */ + io_req->cmd_type = QEDF_ABTS; + spin_unlock_irqrestore(&fcport->rport_lock, flags); + kref_get(&io_req->refcount); xid = io_req->xid; qedf->control_requests++; qedf->packet_aborts++; - /* Set the command type to abort */ - io_req->cmd_type = QEDF_ABTS; io_req->return_scsi_cmd_on_abts = return_scsi_cmd_on_abts; set_bit(QEDF_CMD_IN_ABORT, &io_req->flags); @@ -2210,7 +2214,9 @@ int qedf_initiate_cleanup(struct qedf_ioreq *io_req, refcount, fcport, fcport->rdata->ids.port_id); /* Cleanup cmds re-use the same TID as the original I/O */ + spin_lock_irqsave(&fcport->rport_lock, flags); io_req->cmd_type = QEDF_CLEANUP; + spin_unlock_irqrestore(&fcport->rport_lock, flags); io_req->return_scsi_cmd_on_abts = return_scsi_cmd_on_abts; init_completion(&io_req->cleanup_done); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index c4f293d39f22..d969b0dc9732 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -2807,6 +2807,8 @@ void qedf_process_cqe(struct qedf_ctx *qedf, struct fcoe_cqe *cqe) struct qedf_ioreq *io_req; struct qedf_rport *fcport; u32 comp_type; + u8 io_comp_type; + unsigned long flags; comp_type = (cqe->cqe_data >> FCOE_CQE_CQE_TYPE_SHIFT) & FCOE_CQE_CQE_TYPE_MASK; @@ -2840,11 +2842,14 @@ void qedf_process_cqe(struct qedf_ctx *qedf, struct fcoe_cqe *cqe) return; } + spin_lock_irqsave(&fcport->rport_lock, flags); + io_comp_type = io_req->cmd_type; + spin_unlock_irqrestore(&fcport->rport_lock, flags); switch (comp_type) { case FCOE_GOOD_COMPLETION_CQE_TYPE: atomic_inc(&fcport->free_sqes); - switch (io_req->cmd_type) { + switch (io_comp_type) { case QEDF_SCSI_CMD: qedf_scsi_completion(qedf, cqe, io_req); break; From 81a6cdfcfd233adf0be7952e91ffda4b9a04e959 Mon Sep 17 00:00:00 2001 From: Kiwoong Kim Date: Mon, 4 Sep 2023 10:30:44 +0900 Subject: [PATCH 1794/2093] scsi: ufs: core: Move __ufshcd_send_uic_cmd() outside host_lock [ Upstream commit 2d3f59cf868b4a2dd678a96cd49bdd91411bd59f ] __ufshcd_send_uic_cmd() is wrapped by uic_cmd_mutex and its related contexts are accessed within the section wrapped by uic_cmd_mutex. Thus, wrapping with host_lock is redundant. Signed-off-by: Kiwoong Kim Link: https://lore.kernel.org/r/782ba5f26f0a96e58d85dff50751787d2d2a6b2b.1693790060.git.kwmad.kim@samsung.com Reviewed-by: Bart Van Assche Reviewed-by: Chanwoo Lee Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/ufs/core/ufshcd.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 36437d39b93c..135be6dd0252 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2346,7 +2346,6 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd, bool completion) { lockdep_assert_held(&hba->uic_cmd_mutex); - lockdep_assert_held(hba->host->host_lock); if (!ufshcd_ready_for_uic_cmd(hba)) { dev_err(hba->dev, @@ -2373,7 +2372,6 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd, int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) { int ret; - unsigned long flags; if (hba->quirks & UFSHCD_QUIRK_BROKEN_UIC_CMD) return 0; @@ -2382,9 +2380,7 @@ int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) mutex_lock(&hba->uic_cmd_mutex); ufshcd_add_delay_before_dme_cmd(hba); - spin_lock_irqsave(hba->host->host_lock, flags); ret = __ufshcd_send_uic_cmd(hba, uic_cmd, true); - spin_unlock_irqrestore(hba->host->host_lock, flags); if (!ret) ret = ufshcd_wait_for_uic_cmd(hba, uic_cmd); @@ -4076,8 +4072,8 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd) wmb(); reenable_intr = true; } - ret = __ufshcd_send_uic_cmd(hba, cmd, false); spin_unlock_irqrestore(hba->host->host_lock, flags); + ret = __ufshcd_send_uic_cmd(hba, cmd, false); if (ret) { dev_err(hba->dev, "pwr ctrl cmd 0x%x with mode 0x%x uic error %d\n", From 5fb322df090e5419ebfb3dbac6401f8c46fd13d5 Mon Sep 17 00:00:00 2001 From: Kiwoong Kim Date: Mon, 4 Sep 2023 10:30:45 +0900 Subject: [PATCH 1795/2093] scsi: ufs: core: Poll HCS.UCRDY before issuing a UIC command [ Upstream commit d32533d30e2119b0c0aa17596734f1f842f750df ] With auto hibern8 enabled, UIC could be busy processing a hibern8 operation and the HCI would reports UIC not ready for a short while through HCS.UCRDY. The UFS driver doesn't currently handle this situation. The UFSHCI spec specifies UCRDY like this: whether the host controller is ready to process UIC COMMAND The 'ready' could be seen as many different meanings. If the meaning includes not processing any request from HCI, processing a hibern8 operation can be 'not ready'. In this situation, the driver needs to wait until the operations is completed. Signed-off-by: Kiwoong Kim Link: https://lore.kernel.org/r/550484ffb66300bdcec63d3e304dfd55cb432f1f.1693790060.git.kwmad.kim@samsung.com Reviewed-by: Adrian Hunter Reviewed-by: Chanwoo Lee Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/ufs/core/ufshcd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 135be6dd0252..b4e3f14b9a3d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -2254,7 +2255,11 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba) */ static inline bool ufshcd_ready_for_uic_cmd(struct ufs_hba *hba) { - return ufshcd_readl(hba, REG_CONTROLLER_STATUS) & UIC_COMMAND_READY; + u32 val; + int ret = read_poll_timeout(ufshcd_readl, val, val & UIC_COMMAND_READY, + 500, UIC_CMD_TIMEOUT * 1000, false, hba, + REG_CONTROLLER_STATUS); + return ret == 0 ? true : false; } /** From a687e817d814a161dc47c72430404a2a8a6c5f69 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Mon, 26 Jun 2023 08:11:44 +0800 Subject: [PATCH 1796/2093] selftests/ftrace: Correctly enable event in instance-event.tc [ Upstream commit f4e4ada586995b17f828c6d147d1800eb1471450 ] Function instance_set() expects to enable event 'sched_switch', so we should set 1 to its 'enable' file. Testcase passed after this patch: # ./ftracetest test.d/instances/instance-event.tc === Ftrace unit tests === [1] Test creation and deletion of trace instances while setting an event [PASS] # of passed: 1 # of failed: 0 # of unresolved: 0 # of untested: 0 # of unsupported: 0 # of xfailed: 0 # of undefined(test bug): 0 Signed-off-by: Zheng Yejian Acked-by: Masami Hiramatsu (Google) Acked-by: Steven Rostedt (Google) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../testing/selftests/ftrace/test.d/instances/instance-event.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc index 0eb47fbb3f44..42422e425107 100644 --- a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc +++ b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc @@ -39,7 +39,7 @@ instance_read() { instance_set() { while :; do - echo 1 > foo/events/sched/sched_switch + echo 1 > foo/events/sched/sched_switch/enable done 2> /dev/null } From 11054f0b889fbc5636c55361cb93a900633d8374 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Wed, 6 Sep 2023 16:19:30 +0800 Subject: [PATCH 1797/2093] ring-buffer: Avoid softlockup in ring_buffer_resize() [ Upstream commit f6bd2c92488c30ef53b5bd80c52f0a7eee9d545a ] When user resize all trace ring buffer through file 'buffer_size_kb', then in ring_buffer_resize(), kernel allocates buffer pages for each cpu in a loop. If the kernel preemption model is PREEMPT_NONE and there are many cpus and there are many buffer pages to be allocated, it may not give up cpu for a long time and finally cause a softlockup. To avoid it, call cond_resched() after each cpu buffer allocation. Link: https://lore.kernel.org/linux-trace-kernel/20230906081930.3939106-1-zhengyejian1@huawei.com Cc: Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index de55107aef5d..42ad59a00236 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2212,6 +2212,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, err = -ENOMEM; goto out_err; } + + cond_resched(); } cpus_read_lock(); From 45ad79c9cb5059b2fcd8b37debf18cf7e6693485 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 28 Aug 2023 09:06:44 +0100 Subject: [PATCH 1798/2093] btrfs: assert delayed node locked when removing delayed item [ Upstream commit a57c2d4e46f519b24558ae0752c17eec416ac72a ] When removing a delayed item, or releasing which will remove it as well, we will modify one of the delayed node's rbtrees and item counter if the delayed item is in one of the rbtrees. This require having the delayed node's mutex locked, otherwise we will race with other tasks modifying the rbtrees and the counter. This is motivated by a previous version of another patch actually calling btrfs_release_delayed_item() after unlocking the delayed node's mutex and against a delayed item that is in a rbtree. So assert at __btrfs_remove_delayed_item() that the delayed node's mutex is locked. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/delayed-inode.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 9dacf72a75d0..1331e56e8e84 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -407,6 +407,7 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root) static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) { + struct btrfs_delayed_node *delayed_node = delayed_item->delayed_node; struct rb_root_cached *root; struct btrfs_delayed_root *delayed_root; @@ -414,18 +415,21 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) if (RB_EMPTY_NODE(&delayed_item->rb_node)) return; - delayed_root = delayed_item->delayed_node->root->fs_info->delayed_root; + /* If it's in a rbtree, then we need to have delayed node locked. */ + lockdep_assert_held(&delayed_node->mutex); + + delayed_root = delayed_node->root->fs_info->delayed_root; BUG_ON(!delayed_root); if (delayed_item->type == BTRFS_DELAYED_INSERTION_ITEM) - root = &delayed_item->delayed_node->ins_root; + root = &delayed_node->ins_root; else - root = &delayed_item->delayed_node->del_root; + root = &delayed_node->del_root; rb_erase_cached(&delayed_item->rb_node, root); RB_CLEAR_NODE(&delayed_item->rb_node); - delayed_item->delayed_node->count--; + delayed_node->count--; finish_one_item(delayed_root); } From baa1634bc936e605bf3f4143ecf17e5e3249330e Mon Sep 17 00:00:00 2001 From: "Ricardo B. Marliere" Date: Tue, 22 Aug 2023 18:09:40 -0300 Subject: [PATCH 1799/2093] selftests: fix dependency checker script [ Upstream commit 5f9dd2e896a91bfca90f8463eb6808c03d535d8a ] This patch fixes inconsistencies in the parsing rules of the levels 1 and 2 of the kselftest_deps.sh. It was added the levels 4 and 5 to account for a few edge cases that are present in some tests, also some minor identation styling have been fixed (s/ /\t/g). Signed-off-by: Ricardo B. Marliere Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/kselftest_deps.sh | 77 +++++++++++++++++++---- 1 file changed, 65 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh index 708cb5429633..47a1281a3b70 100755 --- a/tools/testing/selftests/kselftest_deps.sh +++ b/tools/testing/selftests/kselftest_deps.sh @@ -46,11 +46,11 @@ fi print_targets=0 while getopts "p" arg; do - case $arg in - p) + case $arg in + p) print_targets=1 shift;; - esac + esac done if [ $# -eq 0 ] @@ -92,6 +92,10 @@ pass_cnt=0 # Get all TARGETS from selftests Makefile targets=$(egrep "^TARGETS +|^TARGETS =" Makefile | cut -d "=" -f2) +# Initially, in LDLIBS related lines, the dep checker needs +# to ignore lines containing the following strings: +filter="\$(VAR_LDLIBS)\|pkg-config\|PKG_CONFIG\|IOURING_EXTRA_LIBS" + # Single test case if [ $# -eq 2 ] then @@ -100,6 +104,8 @@ then l1_test $test l2_test $test l3_test $test + l4_test $test + l5_test $test print_results $1 $2 exit $? @@ -113,7 +119,7 @@ fi # Append space at the end of the list to append more tests. l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ - grep -v "VAR_LDLIBS" | awk -F: '{print $1}') + grep -v "$filter" | awk -F: '{print $1}' | uniq) # Level 2: LDLIBS set dynamically. # @@ -126,7 +132,7 @@ l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ # Append space at the end of the list to append more tests. l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \ - grep -v "VAR_LDLIBS" | awk -F: '{print $1}') + grep -v "$filter" | awk -F: '{print $1}' | uniq) # Level 3 # memfd and others use pkg-config to find mount and fuse libs @@ -138,11 +144,32 @@ l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \ # VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null) l3_tests=$(grep -r --include=Makefile "^VAR_LDLIBS" | \ - grep -v "pkg-config" | awk -F: '{print $1}') + grep -v "pkg-config\|PKG_CONFIG" | awk -F: '{print $1}' | uniq) -#echo $l1_tests -#echo $l2_1_tests -#echo $l3_tests +# Level 4 +# some tests may fall back to default using `|| echo -l` +# if pkg-config doesn't find the libs, instead of using VAR_LDLIBS +# as per level 3 checks. +# e.g: +# netfilter/Makefile +# LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) +l4_tests=$(grep -r --include=Makefile "^LDLIBS" | \ + grep "pkg-config\|PKG_CONFIG" | awk -F: '{print $1}' | uniq) + +# Level 5 +# some tests may use IOURING_EXTRA_LIBS to add extra libs to LDLIBS, +# which in turn may be defined in a sub-Makefile +# e.g.: +# mm/Makefile +# $(OUTPUT)/gup_longterm: LDLIBS += $(IOURING_EXTRA_LIBS) +l5_tests=$(grep -r --include=Makefile "LDLIBS +=.*\$(IOURING_EXTRA_LIBS)" | \ + awk -F: '{print $1}' | uniq) + +#echo l1_tests $l1_tests +#echo l2_tests $l2_tests +#echo l3_tests $l3_tests +#echo l4_tests $l4_tests +#echo l5_tests $l5_tests all_tests print_results $1 $2 @@ -164,24 +191,32 @@ all_tests() for test in $l3_tests; do l3_test $test done + + for test in $l4_tests; do + l4_test $test + done + + for test in $l5_tests; do + l5_test $test + done } # Use same parsing used for l1_tests and pick libraries this time. l1_test() { test_libs=$(grep --include=Makefile "^LDLIBS" $test | \ - grep -v "VAR_LDLIBS" | \ + grep -v "$filter" | \ sed -e 's/\:/ /' | \ sed -e 's/+/ /' | cut -d "=" -f 2) check_libs $test $test_libs } -# Use same parsing used for l2__tests and pick libraries this time. +# Use same parsing used for l2_tests and pick libraries this time. l2_test() { test_libs=$(grep --include=Makefile ": LDLIBS" $test | \ - grep -v "VAR_LDLIBS" | \ + grep -v "$filter" | \ sed -e 's/\:/ /' | sed -e 's/+/ /' | \ cut -d "=" -f 2) @@ -197,6 +232,24 @@ l3_test() check_libs $test $test_libs } +l4_test() +{ + test_libs=$(grep --include=Makefile "^VAR_LDLIBS\|^LDLIBS" $test | \ + grep "\(pkg-config\|PKG_CONFIG\).*|| echo " | \ + sed -e 's/.*|| echo //' | sed -e 's/)$//') + + check_libs $test $test_libs +} + +l5_test() +{ + tests=$(find $(dirname "$test") -type f -name "*.mk") + test_libs=$(grep "^IOURING_EXTRA_LIBS +\?=" $tests | \ + cut -d "=" -f 2) + + check_libs $test $test_libs +} + check_libs() { From b08a4938229dbb530a35c41b83002a1457c6ff49 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 7 Sep 2023 12:28:20 -0400 Subject: [PATCH 1800/2093] ring-buffer: Do not attempt to read past "commit" [ Upstream commit 95a404bd60af6c4d9d8db01ad14fe8957ece31ca ] When iterating over the ring buffer while the ring buffer is active, the writer can corrupt the reader. There's barriers to help detect this and handle it, but that code missed the case where the last event was at the very end of the page and has only 4 bytes left. The checks to detect the corruption by the writer to reads needs to see the length of the event. If the length in the first 4 bytes is zero then the length is stored in the second 4 bytes. But if the writer is in the process of updating that code, there's a small window where the length in the first 4 bytes could be zero even though the length is only 4 bytes. That will cause rb_event_length() to read the next 4 bytes which could happen to be off the allocated page. To protect against this, fail immediately if the next event pointer is less than 8 bytes from the end of the commit (last byte of data), as all events must be a minimum of 8 bytes anyway. Link: https://lore.kernel.org/all/20230905141245.26470-1-Tze-nan.Wu@mediatek.com/ Link: https://lore.kernel.org/linux-trace-kernel/20230907122820.0899019c@gandalf.local.home Cc: Masami Hiramatsu Cc: Mark Rutland Reported-by: Tze-nan Wu Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 42ad59a00236..c0b708b55c3b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2388,6 +2388,11 @@ rb_iter_head_event(struct ring_buffer_iter *iter) */ commit = rb_page_commit(iter_head_page); smp_rmb(); + + /* An event needs to be at least 8 bytes in size */ + if (iter->head > commit - 8) + goto reset; + event = __rb_page_index(iter_head_page, iter->head); length = rb_event_length(event); From 797d75bd575cbc5263b870adad900ce0ae69cf06 Mon Sep 17 00:00:00 2001 From: Guangguan Wang Date: Fri, 8 Sep 2023 11:31:42 +0800 Subject: [PATCH 1801/2093] net/smc: bugfix for smcr v2 server connect success statistic [ Upstream commit 6912e724832c47bb381eb1bd1e483ec8df0d0f0f ] In the macro SMC_STAT_SERV_SUCC_INC, the smcd_version is used to determin whether to increase the v1 statistic or the v2 statistic. It is correct for SMCD. But for SMCR, smcr_version should be used. Signed-off-by: Guangguan Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/smc_stats.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index 84b7ecd8c05c..4dbc237b7c19 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -244,8 +244,9 @@ while (0) #define SMC_STAT_SERV_SUCC_INC(net, _ini) \ do { \ typeof(_ini) i = (_ini); \ - bool is_v2 = (i->smcd_version & SMC_V2); \ bool is_smcd = (i->is_smcd); \ + u8 version = is_smcd ? i->smcd_version : i->smcr_version; \ + bool is_v2 = (version & SMC_V2); \ typeof(net->smc.smc_stats) smc_stats = (net)->smc.smc_stats; \ if (is_v2 && is_smcd) \ this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v2_succ_cnt); \ From dfbcef80dda96f6433eb6db6d146e68c46cf314c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 4 Sep 2023 21:54:36 +0200 Subject: [PATCH 1802/2093] ata: sata_mv: Fix incorrect string length computation in mv_dump_mem() [ Upstream commit e97eb65dd464e7f118a16a26337322d07eb653e2 ] snprintf() returns the "number of characters which *would* be generated for the given input", not the size *really* generated. In order to avoid too large values for 'o' (and potential negative values for "sizeof(linebuf) o") use scnprintf() instead of snprintf(). Note that given the "w < 4" in the for loop, the buffer can NOT overflow, but using the *right* function is always better. Signed-off-by: Christophe JAILLET Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- drivers/ata/sata_mv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index e3cff01201b8..17f9062b0eaa 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -1255,8 +1255,8 @@ static void mv_dump_mem(struct device *dev, void __iomem *start, unsigned bytes) for (b = 0; b < bytes; ) { for (w = 0, o = 0; b < bytes && w < 4; w++) { - o += snprintf(linebuf + o, sizeof(linebuf) - o, - "%08x ", readl(start + b)); + o += scnprintf(linebuf + o, sizeof(linebuf) - o, + "%08x ", readl(start + b)); b += sizeof(u32); } dev_dbg(dev, "%s: %p: %s\n", From d1f916c6eb0c98dbab5a1392163a29cae482add8 Mon Sep 17 00:00:00 2001 From: David Thompson Date: Tue, 5 Sep 2023 09:32:43 -0400 Subject: [PATCH 1803/2093] platform/mellanox: mlxbf-bootctl: add NET dependency into Kconfig [ Upstream commit c2dffda1d8f7511505bbbf16ba282f2079b30089 ] The latest version of the mlxbf_bootctl driver utilizes "sysfs_format_mac", and this API is only available if NET is defined in the kernel configuration. This patch changes the mlxbf_bootctl Kconfig to depend on NET. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202309031058.JvwNDBKt-lkp@intel.com/ Reported-by: Randy Dunlap Signed-off-by: David Thompson Link: https://lore.kernel.org/r/20230905133243.31550-1-davthompson@nvidia.com Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/mellanox/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/mellanox/Kconfig b/drivers/platform/mellanox/Kconfig index 30b50920b278..f7dfa0e785fd 100644 --- a/drivers/platform/mellanox/Kconfig +++ b/drivers/platform/mellanox/Kconfig @@ -60,6 +60,7 @@ config MLXBF_BOOTCTL tristate "Mellanox BlueField Firmware Boot Control driver" depends on ARM64 depends on ACPI + depends on NET help The Mellanox BlueField firmware implements functionality to request swapping the primary and alternate eMMC boot partition, From d6a68f16324681749397d1697e0914f80d7b0892 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Tue, 5 Sep 2023 20:28:13 +1200 Subject: [PATCH 1804/2093] platform/x86: asus-wmi: Support 2023 ROG X16 tablet mode [ Upstream commit 4106a70ddad57ee6d8f98b81d6f036740c72762b ] Add quirk for ASUS ROG X16 (GV601V, 2023 versions) Flow 2-in-1 to enable tablet mode with lid flip (all screen rotations). Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20230905082813.13470-1-luke@ljones.dev Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/asus-nb-wmi.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index fdf7da06af30..d85d895fee89 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -478,6 +478,15 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_tablet_mode, }, + { + .callback = dmi_matched, + .ident = "ASUS ROG FLOW X16", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GV601V"), + }, + .driver_data = &quirk_asus_tablet_mode, + }, { .callback = dmi_matched, .ident = "ASUS VivoBook E410MA", From 49bdfc83c74a26d418734007eed187b01ba48aa2 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Thu, 7 Sep 2023 11:55:18 +0200 Subject: [PATCH 1805/2093] thermal/of: add missing of_node_put() [ Upstream commit 8a81cf96f5510aaf9a65d103f7405079a7b0fcc5 ] for_each_child_of_node performs an of_node_get on each iteration, so a break out of the loop requires an of_node_put. This was done using the Coccinelle semantic patch iterators/for_each_child.cocci Signed-off-by: Julia Lawall Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/thermal_of.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 762d1990180b..4104743dbc17 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -149,8 +149,10 @@ static int of_find_trip_id(struct device_node *np, struct device_node *trip) */ for_each_child_of_node(trips, t) { - if (t == trip) + if (t == trip) { + of_node_put(t); goto out; + } i++; } @@ -519,8 +521,10 @@ static int thermal_of_for_each_cooling_maps(struct thermal_zone_device *tz, for_each_child_of_node(cm_np, child) { ret = thermal_of_for_each_cooling_device(tz_np, child, tz, cdev, action); - if (ret) + if (ret) { + of_node_put(child); break; + } } of_node_put(cm_np); From b9971393d4c9be5eec3c6b30d9e312ba88c865ac Mon Sep 17 00:00:00 2001 From: Swapnil Patel Date: Thu, 17 Aug 2023 14:04:26 -0400 Subject: [PATCH 1806/2093] drm/amd/display: Don't check registers, if using AUX BL control [ Upstream commit f5b2c10b57615828b531bb0ae56bd6325a41167e ] [Why] Currently the driver looks DCN registers to access if BL is on or not. This check is not valid if we are using AUX based brightness control. This causes driver to not send out "backlight off" command during power off sequence as it already thinks it is off. [How] Only check DCN registers if we aren't using AUX based brightness control. Reviewed-by: Wenjing Liu Acked-by: Stylon Wang Signed-off-by: Swapnil Patel Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 9378c98d02cf..508f5fe26848 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -973,7 +973,9 @@ void dce110_edp_backlight_control( return; } - if (link->panel_cntl) { + if (link->panel_cntl && !(link->dpcd_sink_ext_caps.bits.oled || + link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 || + link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) { bool is_backlight_on = link->panel_cntl->funcs->is_panel_backlight_on(link->panel_cntl); if ((enable && is_backlight_on) || (!enable && !is_backlight_on)) { From cca15a82790772c0303ae295f7153c4af0536ad1 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 6 Sep 2023 11:35:04 -0400 Subject: [PATCH 1807/2093] drm/amdgpu/soc21: don't remap HDP registers for SR-IOV MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1832403cd41ca6b19b24e9d64f79cb08d920ca44 ] This matches the behavior for soc15 and nv. Acked-by: Christian König Reviewed-by: Timmy Tsai Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/soc21.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index d150a90daa40..56af7b5abac1 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -755,7 +755,7 @@ static int soc21_common_hw_init(void *handle) * for the purpose of expose those registers * to process space */ - if (adev->nbio.funcs->remap_hdp_registers) + if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev)) adev->nbio.funcs->remap_hdp_registers(adev); /* enable the doorbell aperture */ soc21_enable_doorbell_aperture(adev, true); From ad3c37f90bae3675bc686562f7e63511d1033cc0 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 7 Sep 2023 15:44:54 -0400 Subject: [PATCH 1808/2093] drm/amdgpu/nbio4.3: set proper rmmio_remap.reg_offset for SR-IOV [ Upstream commit ab43213e7afd08ac68d4282060bacf309e70fd14 ] Needed for HDP flush to work correctly. Reviewed-by: Timmy Tsai Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c index 09fdcd20cb91..c52a378396af 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c @@ -344,6 +344,9 @@ static void nbio_v4_3_init_registers(struct amdgpu_device *adev) data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK; WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data); } + if (amdgpu_sriov_vf(adev)) + adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0, + regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2; } static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev) From 91b6845ef387ab9ae2c6f3f8d43655be955e444b Mon Sep 17 00:00:00 2001 From: David Francis Date: Tue, 5 Sep 2023 10:13:51 -0400 Subject: [PATCH 1809/2093] drm/amdgpu: Handle null atom context in VBIOS info ioctl [ Upstream commit 5e7e82254270c8cf8b107451c5de01cee2f135ae ] On some APU systems, there is no atom context and so the atom_context struct is null. Add a check to the VBIOS_INFO branch of amdgpu_info_ioctl to handle this case, returning all zeroes. Reviewed-by: Alex Deucher Signed-off-by: David Francis Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 9e3313dd956a..24b4bd6bb277 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -896,12 +896,17 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) struct atom_context *atom_context; atom_context = adev->mode_info.atom_context; - memcpy(vbios_info.name, atom_context->name, sizeof(atom_context->name)); - memcpy(vbios_info.vbios_pn, atom_context->vbios_pn, sizeof(atom_context->vbios_pn)); - vbios_info.version = atom_context->version; - memcpy(vbios_info.vbios_ver_str, atom_context->vbios_ver_str, - sizeof(atom_context->vbios_ver_str)); - memcpy(vbios_info.date, atom_context->date, sizeof(atom_context->date)); + if (atom_context) { + memcpy(vbios_info.name, atom_context->name, + sizeof(atom_context->name)); + memcpy(vbios_info.vbios_pn, atom_context->vbios_pn, + sizeof(atom_context->vbios_pn)); + vbios_info.version = atom_context->version; + memcpy(vbios_info.vbios_ver_str, atom_context->vbios_ver_str, + sizeof(atom_context->vbios_ver_str)); + memcpy(vbios_info.date, atom_context->date, + sizeof(atom_context->date)); + } return copy_to_user(out, &vbios_info, min((size_t)size, sizeof(vbios_info))) ? -EFAULT : 0; From 6e392ff884768a151a375cc1ad1dea32dc1dc9c5 Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Tue, 12 Sep 2023 15:24:10 +0800 Subject: [PATCH 1810/2093] riscv: errata: fix T-Head dcache.cva encoding [ Upstream commit 8eb8fe67e2c84324398f5983c41b4f831d0705b3 ] The dcache.cva encoding shown in the comments are wrong, it's for dcache.cval1 (which is restricted to L1) instead. Fix this in the comment and in the hardcoded instruction. Signed-off-by: Icenowy Zheng Tested-by: Sergey Matyukevich Reviewed-by: Heiko Stuebner Reviewed-by: Guo Ren Tested-by: Drew Fustini Link: https://lore.kernel.org/r/20230912072410.2481-1-jszhang@kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/include/asm/errata_list.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 19a771085781..7d2675bb7161 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -100,7 +100,7 @@ asm volatile(ALTERNATIVE( \ * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | * 0000001 01001 rs1 000 00000 0001011 * dcache.cva rs1 (clean, virtual address) - * 0000001 00100 rs1 000 00000 0001011 + * 0000001 00101 rs1 000 00000 0001011 * * dcache.cipa rs1 (clean then invalidate, physical address) * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | @@ -113,7 +113,7 @@ asm volatile(ALTERNATIVE( \ * 0000000 11001 00000 000 00000 0001011 */ #define THEAD_inval_A0 ".long 0x0265000b" -#define THEAD_clean_A0 ".long 0x0245000b" +#define THEAD_clean_A0 ".long 0x0255000b" #define THEAD_flush_A0 ".long 0x0275000b" #define THEAD_SYNC_S ".long 0x0190000b" From 82f575a7e81192588a02eafc5837820a0f661e6b Mon Sep 17 00:00:00 2001 From: Michal Grzedzicki Date: Wed, 13 Sep 2023 08:56:10 -0700 Subject: [PATCH 1811/2093] scsi: pm80xx: Use phy-specific SAS address when sending PHY_START command [ Upstream commit 71996bb835aed58c7ec4967be1d05190a27339ec ] Some cards have more than one SAS address. Using an incorrect address causes communication issues with some devices like expanders. Closes: https://lore.kernel.org/linux-kernel/A57AEA84-5CA0-403E-8053-106033C73C70@fb.com/ Signed-off-by: Michal Grzedzicki Link: https://lore.kernel.org/r/20230913155611.3183612-1-mge@meta.com Acked-by: Jack Wang Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/pm8001/pm8001_hwi.c | 2 +- drivers/scsi/pm8001/pm80xx_hwi.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 628b08ba6770..e2c52c2d00b3 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -4313,7 +4313,7 @@ pm8001_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id) payload.sas_identify.dev_type = SAS_END_DEVICE; payload.sas_identify.initiator_bits = SAS_PROTOCOL_ALL; memcpy(payload.sas_identify.sas_addr, - pm8001_ha->sas_addr, SAS_ADDR_SIZE); + &pm8001_ha->phy[phy_id].dev_sas_addr, SAS_ADDR_SIZE); payload.sas_identify.phy_id = phy_id; return pm8001_mpi_build_cmd(pm8001_ha, 0, opcode, &payload, diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index f8b8624458f7..bcccea7c1244 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -4803,7 +4803,7 @@ pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id) payload.sas_identify.dev_type = SAS_END_DEVICE; payload.sas_identify.initiator_bits = SAS_PROTOCOL_ALL; memcpy(payload.sas_identify.sas_addr, - &pm8001_ha->sas_addr, SAS_ADDR_SIZE); + &pm8001_ha->phy[phy_id].dev_sas_addr, SAS_ADDR_SIZE); payload.sas_identify.phy_id = phy_id; return pm8001_mpi_build_cmd(pm8001_ha, 0, opcode, &payload, From 2259e1901b2d8c0e8538fc99e77de443b939e749 Mon Sep 17 00:00:00 2001 From: Michal Grzedzicki Date: Mon, 11 Sep 2023 10:03:40 -0700 Subject: [PATCH 1812/2093] scsi: pm80xx: Avoid leaking tags when processing OPC_INB_SET_CONTROLLER_CONFIG command [ Upstream commit c13e7331745852d0dd7c35eabbe181cbd5b01172 ] Tags allocated for OPC_INB_SET_CONTROLLER_CONFIG command need to be freed when we receive the response. Signed-off-by: Michal Grzedzicki Link: https://lore.kernel.org/r/20230911170340.699533-2-mge@meta.com Acked-by: Jack Wang Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/pm8001/pm80xx_hwi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index bcccea7c1244..2bf293e8f747 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -3750,10 +3750,12 @@ static int mpi_set_controller_config_resp(struct pm8001_hba_info *pm8001_ha, (struct set_ctrl_cfg_resp *)(piomb + 4); u32 status = le32_to_cpu(pPayload->status); u32 err_qlfr_pgcd = le32_to_cpu(pPayload->err_qlfr_pgcd); + u32 tag = le32_to_cpu(pPayload->tag); pm8001_dbg(pm8001_ha, MSG, "SET CONTROLLER RESP: status 0x%x qlfr_pgcd 0x%x\n", status, err_qlfr_pgcd); + pm8001_tag_free(pm8001_ha, tag); return 0; } From 2132ea3f9f5a682863bb408a0182ea9d283d6b18 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 15 Sep 2023 01:10:40 -0500 Subject: [PATCH 1813/2093] smb3: correct places where ENOTSUPP is used instead of preferred EOPNOTSUPP [ Upstream commit ebc3d4e44a7e05457825e03d0560153687265523 ] checkpatch flagged a few places with: WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP Also fixed minor typo Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/smb/client/inode.c | 2 +- fs/smb/client/smb2ops.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 92c1ed9304be..9531ea243089 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2605,7 +2605,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, } cifsFileInfo_put(cfile); - return -ENOTSUPP; + return -EOPNOTSUPP; } int cifs_truncate_page(struct address_space *mapping, loff_t from) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1387d5126f53..efff7137412b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -292,7 +292,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server, cifs_server_dbg(VFS, "request has less credits (%d) than required (%d)", credits->value, new_val); - return -ENOTSUPP; + return -EOPNOTSUPP; } spin_lock(&server->req_lock); @@ -1155,7 +1155,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, /* Use a fudge factor of 256 bytes in case we collide * with a different set_EAs command. */ - if(CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - + if (CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE - 256 < used_len + ea_name_len + ea_value_len + 1) { rc = -ENOSPC; @@ -4721,7 +4721,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (shdr->Command != SMB2_READ) { cifs_server_dbg(VFS, "only big read responses are supported\n"); - return -ENOTSUPP; + return -EOPNOTSUPP; } if (server->ops->is_session_expired && From d5ae9d9f0c4132d68add52054e471be15b1d433b Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 Sep 2023 00:19:16 +0200 Subject: [PATCH 1814/2093] ata: libata-eh: do not clear ATA_PFLAG_EH_PENDING in ata_eh_reset() [ Upstream commit 80cc944eca4f0baa9c381d0706f3160e491437f2 ] ata_scsi_port_error_handler() starts off by clearing ATA_PFLAG_EH_PENDING, before calling ap->ops->error_handler() (without holding the ap->lock). If an error IRQ is received while ap->ops->error_handler() is running, the irq handler will set ATA_PFLAG_EH_PENDING. Once ap->ops->error_handler() returns, ata_scsi_port_error_handler() checks if ATA_PFLAG_EH_PENDING is set, and if it is, another iteration of ATA EH is performed. The problem is that ATA_PFLAG_EH_PENDING is not only cleared by ata_scsi_port_error_handler(), it is also cleared by ata_eh_reset(). ata_eh_reset() is called by ap->ops->error_handler(). This additional clearing done by ata_eh_reset() breaks the whole retry logic in ata_scsi_port_error_handler(). Thus, if an error IRQ is received while ap->ops->error_handler() is running, the port will currently remain frozen and will never get re-enabled. The additional clearing in ata_eh_reset() was introduced in commit 1e641060c4b5 ("libata: clear eh_info on reset completion"). Looking at the original error report: https://marc.info/?l=linux-ide&m=124765325828495&w=2 We can see the following happening: [ 1.074659] ata3: XXX port freeze [ 1.074700] ata3: XXX hardresetting link, stopping engine [ 1.074746] ata3: XXX flipping SControl [ 1.411471] ata3: XXX irq_stat=400040 CONN|PHY [ 1.411475] ata3: XXX port freeze [ 1.420049] ata3: XXX starting engine [ 1.420096] ata3: XXX rc=0, class=1 [ 1.420142] ata3: XXX clearing IRQs for thawing [ 1.420188] ata3: XXX port thawed [ 1.420234] ata3: SATA link up 3.0 Gbps (SStatus 123 SControl 300) We are not supposed to be able to receive an error IRQ while the port is frozen (PxIE is set to 0, i.e. all IRQs for the port are disabled). AHCI 1.3.1 section 10.7.1.1 First Tier (IS Register) states: "Each bit location can be thought of as reporting a '1' if the virtual "interrupt line" for that port is indicating it wishes to generate an interrupt. That is, if a port has one or more interrupt status bit set, and the enables for those status bits are set, then this bit shall be set." Additionally, AHCI state P:ComInit clearly shows that the state machine will only jump to P:ComInitSetIS (which sets IS.IPS(x) to '1'), if PxIE.PCE is set to '1'. In our case, PxIE is set to 0, so IS.IPS(x) won't get set. So IS.IPS(x) only gets set if PxIS and PxIE is set. AHCI 1.3.1 section 10.7.1.1 First Tier (IS Register) also states: "The bits in this register are read/write clear. It is set by the level of the virtual interrupt line being a set, and cleared by a write of '1' from the software." So if IS.IPS(x) is set, you need to explicitly clear it by writing a 1 to IS.IPS(x) for that port. Since PxIE is cleared, the only way to get an interrupt while the port is frozen, is if IS.IPS(x) is set, and the only way IS.IPS(x) can be set when the port is frozen, is if it was set before the port was frozen. However, since commit 737dd811a3db ("ata: libahci: clear pending interrupt status"), we clear both PxIS and IS.IPS(x) after freezing the port, but before the COMRESET, so the problem that commit 1e641060c4b5 ("libata: clear eh_info on reset completion") fixed can no longer happen. Thus, revert commit 1e641060c4b5 ("libata: clear eh_info on reset completion"), so that the retry logic in ata_scsi_port_error_handler() works once again. (The retry logic is still needed, since we can still get an error IRQ _after_ the port has been thawed, but before ata_scsi_port_error_handler() takes the ap->lock in order to check if ATA_PFLAG_EH_PENDING is set.) Signed-off-by: Niklas Cassel Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- drivers/ata/libata-eh.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index a3ae5fc2a42f..6d4c80b6daae 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2704,18 +2704,11 @@ int ata_eh_reset(struct ata_link *link, int classify, } } - /* - * Some controllers can't be frozen very well and may set spurious - * error conditions during reset. Clear accumulated error - * information and re-thaw the port if frozen. As reset is the - * final recovery action and we cross check link onlineness against - * device classification later, no hotplug event is lost by this. - */ + /* clear cached SError */ spin_lock_irqsave(link->ap->lock, flags); - memset(&link->eh_info, 0, sizeof(link->eh_info)); + link->eh_info.serror = 0; if (slave) - memset(&slave->eh_info, 0, sizeof(link->eh_info)); - ap->pflags &= ~ATA_PFLAG_EH_PENDING; + slave->eh_info.serror = 0; spin_unlock_irqrestore(link->ap->lock, flags); if (ap->pflags & ATA_PFLAG_FROZEN) From 84592ec591be7d6b03180c389d5a81dea09fabb5 Mon Sep 17 00:00:00 2001 From: Han Xu Date: Wed, 6 Sep 2023 13:32:54 -0500 Subject: [PATCH 1815/2093] spi: nxp-fspi: reset the FLSHxCR1 registers [ Upstream commit 18495676f7886e105133f1dc06c1d5e8d5436f32 ] Reset the FLSHxCR1 registers to default value. ROM may set the register value and it affects the SPI NAND normal functions. Signed-off-by: Han Xu Link: https://lore.kernel.org/r/20230906183254.235847-1-han.xu@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-nxp-fspi.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index d6a65a989ef8..c7a4a3606547 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -1029,6 +1029,13 @@ static int nxp_fspi_default_setup(struct nxp_fspi *f) fspi_writel(f, FSPI_AHBCR_PREF_EN | FSPI_AHBCR_RDADDROPT, base + FSPI_AHBCR); + /* Reset the FLSHxCR1 registers. */ + reg = FSPI_FLSHXCR1_TCSH(0x3) | FSPI_FLSHXCR1_TCSS(0x3); + fspi_writel(f, reg, base + FSPI_FLSHA1CR1); + fspi_writel(f, reg, base + FSPI_FLSHA2CR1); + fspi_writel(f, reg, base + FSPI_FLSHB1CR1); + fspi_writel(f, reg, base + FSPI_FLSHB2CR1); + /* AHB Read - Set lut sequence ID for all CS. */ fspi_writel(f, SEQID_LUT, base + FSPI_FLSHA1CR2); fspi_writel(f, SEQID_LUT, base + FSPI_FLSHA2CR2); From 85ca138f922cd99370c56f884631f91cab661ac8 Mon Sep 17 00:00:00 2001 From: Valentin Caron Date: Wed, 6 Sep 2023 15:27:35 +0200 Subject: [PATCH 1816/2093] spi: stm32: add a delay before SPI disable [ Upstream commit 6de8a70c84ee0586fdde4e671626b9caca6aed74 ] As explained in errata sheet, in section "2.14.5 Truncation of SPI output signals after EOT event": On STM32MP1x, EOT interrupt can be thrown before the true end of communication. So we add a delay of a half period to wait the real end of the transmission. Link: https://www.st.com/resource/en/errata_sheet/es0539-stm32mp131x3x5x-device-errata-stmicroelectronics.pdf Signed-off-by: Valentin Caron Link: https://lore.kernel.org/r/20230906132735.748174-1-valentin.caron@foss.st.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-stm32.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index def09cf0dc14..12241815510d 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -268,6 +268,7 @@ struct stm32_spi_cfg { * @fifo_size: size of the embedded fifo in bytes * @cur_midi: master inter-data idleness in ns * @cur_speed: speed configured in Hz + * @cur_half_period: time of a half bit in us * @cur_bpw: number of bits in a single SPI data frame * @cur_fthlv: fifo threshold level (data frames in a single data packet) * @cur_comm: SPI communication mode @@ -294,6 +295,7 @@ struct stm32_spi { unsigned int cur_midi; unsigned int cur_speed; + unsigned int cur_half_period; unsigned int cur_bpw; unsigned int cur_fthlv; unsigned int cur_comm; @@ -454,6 +456,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, spi->cur_speed = spi->clk_rate / (1 << mbrdiv); + spi->cur_half_period = DIV_ROUND_CLOSEST(USEC_PER_SEC, 2 * spi->cur_speed); + return mbrdiv - 1; } @@ -695,6 +699,10 @@ static void stm32h7_spi_disable(struct stm32_spi *spi) return; } + /* Add a delay to make sure that transmission is ended. */ + if (spi->cur_half_period) + udelay(spi->cur_half_period); + if (spi->cur_usedma && spi->dma_tx) dmaengine_terminate_all(spi->dma_tx); if (spi->cur_usedma && spi->dma_rx) From 12716449289e687f7ca4f21074ec0c31b3cc95b2 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Mon, 11 Sep 2023 14:38:07 +0800 Subject: [PATCH 1817/2093] ASoC: fsl: imx-pcm-rpmsg: Add SNDRV_PCM_INFO_BATCH flag [ Upstream commit 2f9426905a63be7ccf8cd10109caf1848aa0993a ] The rpmsg pcm device is a device which should support double buffering. Found this issue with pipewire. When there is no SNDRV_PCM_INFO_BATCH flag in driver, the pipewire will set headroom to be zero, and because rpmsg pcm device don't support residue report, when the latency setting is small, the "delay" always larger than "target" in alsa-pcm.c, that reading next period data is not scheduled on time. With SNDRV_PCM_INFO_BATCH flag in driver, the pipewire will select a smaller period size for device, then the task of reading next period data will be scheduled on time. Signed-off-by: Shengjiu Wang Link: https://lore.kernel.org/r/1694414287-13291-1-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/imx-pcm-rpmsg.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/fsl/imx-pcm-rpmsg.c b/sound/soc/fsl/imx-pcm-rpmsg.c index 35049043e532..933bac7ea186 100644 --- a/sound/soc/fsl/imx-pcm-rpmsg.c +++ b/sound/soc/fsl/imx-pcm-rpmsg.c @@ -19,6 +19,7 @@ static struct snd_pcm_hardware imx_rpmsg_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER | + SNDRV_PCM_INFO_BATCH | SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_NO_PERIOD_WAKEUP | From 60446b5e74865acff1af5f2d89d99551c8e6e2c1 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 11 Sep 2023 10:46:16 +0300 Subject: [PATCH 1818/2093] spi: intel-pci: Add support for Granite Rapids SPI serial flash [ Upstream commit 9855d60cfc720ff32355484c119acafd3c4dc806 ] Intel Granite Rapids has a flash controller that is compatible with the other Cannon Lake derivatives. Add Granite Rapids PCI ID to the driver list of supported devices. Signed-off-by: Mika Westerberg Link: https://lore.kernel.org/r/20230911074616.3473347-1-mika.westerberg@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-intel-pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index f0d532ea40e8..b718a74fa3ed 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -72,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x5794), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7e23), (unsigned long)&cnl_info }, From 92f24f98d5ff65c59a2b3c6fa30d38e8cc941d4d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 11 Sep 2023 12:47:30 -0700 Subject: [PATCH 1819/2093] bpf: Clarify error expectations from bpf_clone_redirect [ Upstream commit 7cb779a6867fea00b4209bcf6de2f178a743247d ] Commit 151e887d8ff9 ("veth: Fixing transmit return status for dropped packets") exposed the fact that bpf_clone_redirect is capable of returning raw NET_XMIT_XXX return codes. This is in the conflict with its UAPI doc which says the following: "0 on success, or a negative error in case of failure." Update the UAPI to reflect the fact that bpf_clone_redirect can return positive error numbers, but don't explicitly define their meaning. Reported-by: Daniel Borkmann Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230911194731.286342-1-sdf@google.com Signed-off-by: Sasha Levin --- include/uapi/linux/bpf.h | 4 +++- tools/include/uapi/linux/bpf.h | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 51b9aa640ad2..53bc48794719 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1837,7 +1837,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 51b9aa640ad2..53bc48794719 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1837,7 +1837,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description From 019f01f81887ab9c5cac4576bbce8b4502583b57 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 12 Sep 2023 19:26:17 +0300 Subject: [PATCH 1820/2093] ALSA: hda: intel-sdw-acpi: Use u8 type for link index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 485ddd519fbd89a9d9ac4b02be489e03cbbeebba ] Use consistently u8 for sdw link index. The id is limited to 4, u8 is adequate in size to store it. This change will also fixes the following compiler warning/error (W=1): sound/hda/intel-sdw-acpi.c: In function ‘sdw_intel_acpi_scan’: sound/hda/intel-sdw-acpi.c:34:35: error: ‘-subproperties’ directive output may be truncated writing 14 bytes into a region of size between 7 and 17 [-Werror=format-truncation=] 34 | "mipi-sdw-link-%d-subproperties", i); | ^~~~~~~~~~~~~~ In function ‘is_link_enabled’, inlined from ‘sdw_intel_scan_controller’ at sound/hda/intel-sdw-acpi.c:106:8, inlined from ‘sdw_intel_acpi_scan’ at sound/hda/intel-sdw-acpi.c:180:9: sound/hda/intel-sdw-acpi.c:33:9: note: ‘snprintf’ output between 30 and 40 bytes into a destination of size 32 33 | snprintf(name, sizeof(name), | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ 34 | "mipi-sdw-link-%d-subproperties", i); | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors The warnings got brought to light by a recent patch upstream: commit 6d4ab2e97dcf ("extrawarn: enable format and stringop overflow warnings in W=1") Signed-off-by: Peter Ujfalusi Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230912162617.29178-1-peter.ujfalusi@linux.intel.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/hda/intel-sdw-acpi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index 5cb92f7ccbca..b57d72ea4503 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -23,7 +23,7 @@ static int ctrl_link_mask; module_param_named(sdw_link_mask, ctrl_link_mask, int, 0444); MODULE_PARM_DESC(sdw_link_mask, "Intel link mask (one bit per link)"); -static bool is_link_enabled(struct fwnode_handle *fw_node, int i) +static bool is_link_enabled(struct fwnode_handle *fw_node, u8 idx) { struct fwnode_handle *link; char name[32]; @@ -31,7 +31,7 @@ static bool is_link_enabled(struct fwnode_handle *fw_node, int i) /* Find master handle */ snprintf(name, sizeof(name), - "mipi-sdw-link-%d-subproperties", i); + "mipi-sdw-link-%hhu-subproperties", idx); link = fwnode_get_named_child_node(fw_node, name); if (!link) @@ -51,8 +51,8 @@ static int sdw_intel_scan_controller(struct sdw_intel_acpi_info *info) { struct acpi_device *adev = acpi_fetch_acpi_dev(info->handle); - int ret, i; - u8 count; + u8 count, i; + int ret; if (!adev) return -EINVAL; From cbc43ddd5ce278d44a3e45b9831a7b2f9f7f1787 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 13 Sep 2023 16:00:10 +0100 Subject: [PATCH 1821/2093] ASoC: cs42l42: Ensure a reset pulse meets minimum pulse width. [ Upstream commit 41dac81b56c82c51a6d00fda5f3af7691ffee2d7 ] The CS42L42 can accept very short reset pulses of a few microseconds but there's no reason to force a very short pulse. Allow a wide range for the usleep_range() so it can be relaxed about the choice of timing source. Signed-off-by: Richard Fitzgerald Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20230913150012.604775-2-sbinding@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/cs42l42.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 2fefbcf7bd13..914cdd737fa3 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -2280,6 +2280,10 @@ int cs42l42_common_probe(struct cs42l42_private *cs42l42, if (cs42l42->reset_gpio) { dev_dbg(cs42l42->dev, "Found reset GPIO\n"); + + /* Ensure minimum reset pulse width */ + usleep_range(10, 500); + gpiod_set_value_cansleep(cs42l42->reset_gpio, 1); } usleep_range(CS42L42_BOOT_TIME_US, CS42L42_BOOT_TIME_US * 2); From 110e6f5750287397714074ef0c3eae39289e771a Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 13 Sep 2023 16:00:11 +0100 Subject: [PATCH 1822/2093] ASoC: cs42l42: Don't rely on GPIOD_OUT_LOW to set RESET initially low [ Upstream commit a479b44ac0a0ac25cd48e5356200078924d78022 ] The ACPI setting for a GPIO default state has higher priority than the flag passed to devm_gpiod_get_optional() so ACPI can override the GPIOD_OUT_LOW. Explicitly set the GPIO low when hard resetting. Although GPIOD_OUT_LOW can't be relied on this doesn't seem like a reason to stop passing it to devm_gpiod_get_optional(). So we still pass it to state our intent, but can deal with it having no effect. Signed-off-by: Richard Fitzgerald Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20230913150012.604775-3-sbinding@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/cs42l42.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 914cdd737fa3..735061690ded 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -2281,6 +2281,12 @@ int cs42l42_common_probe(struct cs42l42_private *cs42l42, if (cs42l42->reset_gpio) { dev_dbg(cs42l42->dev, "Found reset GPIO\n"); + /* + * ACPI can override the default GPIO state we requested + * so ensure that we start with RESET low. + */ + gpiod_set_value_cansleep(cs42l42->reset_gpio, 0); + /* Ensure minimum reset pulse width */ usleep_range(10, 500); From 53618d56bfe4c7fefbfcdd562e963f56b9fdac37 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 13 Sep 2023 17:05:23 +0100 Subject: [PATCH 1823/2093] firmware: cirrus: cs_dsp: Only log list of algorithms in debug build [ Upstream commit 69343ce91435f222052015c5af86b550391bac85 ] Change the logging of each algorithm from info level to debug level. On the original devices supported by this code there were typically only one or two algorithms in a firmware and one or two DSPs so this logging only used a small number of log lines. However, for the latest devices there could be 30-40 algorithms in a firmware and 8 DSPs being loaded in parallel, so using 300+ lines of log for information that isn't particularly important to have logged. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20230913160523.3701189-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/firmware/cirrus/cs_dsp.c | 34 ++++++++++++++++---------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 81c5f94b1be1..64ed9d3f5d5d 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1821,15 +1821,15 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) return PTR_ERR(adsp2_alg); for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, - "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n", - i, be32_to_cpu(adsp2_alg[i].alg.id), - (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff, - be32_to_cpu(adsp2_alg[i].xm), - be32_to_cpu(adsp2_alg[i].ym), - be32_to_cpu(adsp2_alg[i].zm)); + cs_dsp_dbg(dsp, + "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n", + i, be32_to_cpu(adsp2_alg[i].alg.id), + (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff, + be32_to_cpu(adsp2_alg[i].xm), + be32_to_cpu(adsp2_alg[i].ym), + be32_to_cpu(adsp2_alg[i].zm)); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, adsp2_alg[i].alg.id, @@ -1954,14 +1954,14 @@ static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) return PTR_ERR(halo_alg); for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, - "%d: ID %x v%d.%d.%d XM@%x YM@%x\n", - i, be32_to_cpu(halo_alg[i].alg.id), - (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(halo_alg[i].alg.ver) & 0xff, - be32_to_cpu(halo_alg[i].xm_base), - be32_to_cpu(halo_alg[i].ym_base)); + cs_dsp_dbg(dsp, + "%d: ID %x v%d.%d.%d XM@%x YM@%x\n", + i, be32_to_cpu(halo_alg[i].alg.id), + (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(halo_alg[i].alg.ver) & 0xff, + be32_to_cpu(halo_alg[i].xm_base), + be32_to_cpu(halo_alg[i].ym_base)); ret = cs_dsp_halo_create_regions(dsp, halo_alg[i].alg.id, halo_alg[i].alg.ver, From 729757fe9718bcddae890b5f24949204fd61d2f7 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Thu, 14 Sep 2023 09:24:51 +0300 Subject: [PATCH 1824/2093] memblock tests: fix warning: "__ALIGN_KERNEL" redefined [ Upstream commit 5e1bffbdb63baf89f3bf0b6bafb50903432a7434 ] Building memblock tests produces the following warning: cc -I. -I../../include -Wall -O2 -fsanitize=address -fsanitize=undefined -D CONFIG_PHYS_ADDR_T_64BIT -c -o main.o main.c In file included from ../../include/linux/pfn.h:5, from ./linux/memory_hotplug.h:6, from ./linux/init.h:7, from ./linux/memblock.h:11, from tests/common.h:8, from tests/basic_api.h:5, from main.c:2: ../../include/linux/mm.h:14: warning: "__ALIGN_KERNEL" redefined 14 | #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) | In file included from ../../include/linux/mm.h:6, from ../../include/linux/pfn.h:5, from ./linux/memory_hotplug.h:6, from ./linux/init.h:7, from ./linux/memblock.h:11, from tests/common.h:8, from tests/basic_api.h:5, from main.c:2: ../../include/uapi/linux/const.h:31: note: this is the location of the previous definition 31 | #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) | Remove definitions of __ALIGN_KERNEL and __ALIGN_KERNEL_MASK from tools/include/linux/mm.h to fix it. Signed-off-by: Mike Rapoport (IBM) Signed-off-by: Sasha Levin --- tools/include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index a03d9bba5151..43be27bcc897 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -11,8 +11,6 @@ #define PHYS_ADDR_MAX (~(phys_addr_t)0) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) -#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) #define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) From 1c88886587d306387abd2edcf12d9a0724461ce9 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Thu, 14 Sep 2023 10:45:40 +0300 Subject: [PATCH 1825/2093] =?UTF-8?q?memblock=20tests:=20fix=20warning=20?= =?UTF-8?q?=E2=80=98struct=20seq=5Ffile=E2=80=99=20declared=20inside=20par?= =?UTF-8?q?ameter=20list?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 55122e0130e51eb71f5ec62d10525db0468f28e8 ] Building memblock tests produces the following warning: cc -I. -I../../include -Wall -O2 -fsanitize=address -fsanitize=undefined -D CONFIG_PHYS_ADDR_T_64BIT -c -o main.o main.c In file included from tests/common.h:9, from tests/basic_api.h:5, from main.c:2: ./linux/memblock.h:601:50: warning: ‘struct seq_file’ declared inside parameter list will not be visible outside of this definition or declaration 601 | static inline void memtest_report_meminfo(struct seq_file *m) { } | ^~~~~~~~ Add declaration of 'struct seq_file' to tools/include/linux/seq_file.h to fix it. Signed-off-by: Mike Rapoport (IBM) Signed-off-by: Sasha Levin --- tools/include/linux/seq_file.h | 2 ++ tools/testing/memblock/tests/basic_api.c | 2 +- tools/testing/memblock/tests/common.h | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/include/linux/seq_file.h b/tools/include/linux/seq_file.h index 102fd9217f1f..f6bc226af0c1 100644 --- a/tools/include/linux/seq_file.h +++ b/tools/include/linux/seq_file.h @@ -1,4 +1,6 @@ #ifndef _TOOLS_INCLUDE_LINUX_SEQ_FILE_H #define _TOOLS_INCLUDE_LINUX_SEQ_FILE_H +struct seq_file; + #endif /* _TOOLS_INCLUDE_LINUX_SEQ_FILE_H */ diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c index a13a57ba0815..7ce628e31a43 100644 --- a/tools/testing/memblock/tests/basic_api.c +++ b/tools/testing/memblock/tests/basic_api.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include "basic_api.h" #include #include -#include "basic_api.h" #define EXPECTED_MEMBLOCK_REGIONS 128 #define FUNC_ADD "memblock_add" diff --git a/tools/testing/memblock/tests/common.h b/tools/testing/memblock/tests/common.h index d6bbbe63bfc3..4c33ce04c064 100644 --- a/tools/testing/memblock/tests/common.h +++ b/tools/testing/memblock/tests/common.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include From 28c36932492295eae9ce1ae4fe177cb344fc1e1c Mon Sep 17 00:00:00 2001 From: Chancel Liu Date: Wed, 13 Sep 2023 18:26:56 +0800 Subject: [PATCH 1826/2093] ASoC: imx-rpmsg: Set ignore_pmdown_time for dai_link [ Upstream commit fac58baf8fcfcd7481e8f6d60206ce2a47c1476c ] i.MX rpmsg sound cards work on codec slave mode. MCLK will be disabled by CPU DAI driver in hw_free(). Some codec requires MCLK present at power up/down sequence. So need to set ignore_pmdown_time to power down codec immediately before MCLK is turned off. Take WM8962 as an example, if MCLK is disabled before DAPM power down playback stream, FIFO error will arise in WM8962 which will have bad impact on playback next. Signed-off-by: Chancel Liu Acked-by: Shengjiu Wang Link: https://lore.kernel.org/r/20230913102656.2966757-1-chancel.liu@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/imx-rpmsg.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/soc/fsl/imx-rpmsg.c b/sound/soc/fsl/imx-rpmsg.c index 4d99f4858a14..76c6febf2499 100644 --- a/sound/soc/fsl/imx-rpmsg.c +++ b/sound/soc/fsl/imx-rpmsg.c @@ -88,6 +88,14 @@ static int imx_rpmsg_probe(struct platform_device *pdev) SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBC_CFC; + /* + * i.MX rpmsg sound cards work on codec slave mode. MCLK will be + * disabled by CPU DAI driver in hw_free(). Some codec requires MCLK + * present at power up/down sequence. So need to set ignore_pmdown_time + * to power down codec immediately before MCLK is turned off. + */ + data->dai.ignore_pmdown_time = 1; + /* Optional codec node */ ret = of_parse_phandle_with_fixed_args(np, "audio-codec", 0, 0, &args); if (ret) { From e9f05ae6f63624fa95afdd7797610ec22d788d99 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 17 Aug 2023 12:41:32 +0200 Subject: [PATCH 1827/2093] media: vb2: frame_vector.c: replace WARN_ONCE with a comment [ Upstream commit 735de5caf79e06cc9fb96b1b4f4974674ae3e917 ] The WARN_ONCE was issued also in cases that had nothing to do with VM_IO (e.g. if the start address was just a random value and uaccess fails with -EFAULT). There are no reports of WARN_ONCE being issued for actual VM_IO cases, so just drop it and instead add a note to the comment before the function. Signed-off-by: Hans Verkuil Reviewed-by: David Hildenbrand Reported-by: Yikebaer Aizezi Signed-off-by: Sasha Levin --- drivers/media/common/videobuf2/frame_vector.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/common/videobuf2/frame_vector.c b/drivers/media/common/videobuf2/frame_vector.c index 144027035892..07ebe4424df3 100644 --- a/drivers/media/common/videobuf2/frame_vector.c +++ b/drivers/media/common/videobuf2/frame_vector.c @@ -30,6 +30,10 @@ * different type underlying the specified range of virtual addresses. * When the function isn't able to map a single page, it returns error. * + * Note that get_vaddr_frames() cannot follow VM_IO mappings. It used + * to be able to do that, but that could (racily) return non-refcounted + * pfns. + * * This function takes care of grabbing mmap_lock as necessary. */ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, @@ -55,8 +59,6 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, if (likely(ret > 0)) return ret; - /* This used to (racily) return non-refcounted pfns. Let people know */ - WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping"); vec->nr_frames = 0; return ret ? ret : -EFAULT; } From 3608be186ae5197bb5b65c92e6eac88a0d37ddce Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Thu, 13 Jul 2023 15:54:16 -0400 Subject: [PATCH 1828/2093] NFSv4.1: fix zero value filehandle in post open getattr [ Upstream commit 4506f23e117161a20104c8fa04f33e1ca63c26af ] Currently, if the OPEN compound experiencing an error and needs to get the file attributes separately, it will send a stand alone GETATTR but it would use the filehandle from the results of the OPEN compound. In case of the CLAIM_FH OPEN, nfs_openres's fh is zero value. That generate a GETATTR that's sent with a zero value filehandle, and results in the server returning an error. Instead, for the CLAIM_FH OPEN, take the filehandle that was used in the PUTFH of the OPEN compound. Signed-off-by: Olga Kornievskaia Reviewed-by: Benjamin Coddington Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index acb1346da13e..be570c65ae15 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2708,8 +2708,12 @@ static int _nfs4_proc_open(struct nfs4_opendata *data, return status; } if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) { + struct nfs_fh *fh = &o_res->fh; + nfs4_sequence_free_slot(&o_res->seq_res); - nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, NULL); + if (o_arg->claim == NFS4_OPEN_CLAIM_FH) + fh = NFS_FH(d_inode(data->dentry)); + nfs4_proc_getattr(server, fh, o_res->f_attr, NULL); } return 0; } From ee8bbb2a31d33c48eac4a8cdae846d699e6b5d02 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Fri, 15 Sep 2023 16:41:53 +0300 Subject: [PATCH 1829/2093] ASoC: SOF: Intel: MTL: Reduce the DSP init timeout MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e0f96246c4402514acda040be19ee24c1619e01a ] 20s seems unnecessarily large for the DSP init timeout. This coupled with multiple FW boot attempts causes an excessive delay in the error path when booting in recovery mode. Reduce it to 0.5s and use the existing HDA_DSP_INIT_TIMEOUT_US. Link: https://github.com/thesofproject/linux/issues/4565 Signed-off-by: Ranjani Sridharan Reviewed-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20230915134153.9688-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/intel/mtl.c | 2 +- sound/soc/sof/intel/mtl.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/sof/intel/mtl.c b/sound/soc/sof/intel/mtl.c index 10298532816f..d7048f1d6a04 100644 --- a/sound/soc/sof/intel/mtl.c +++ b/sound/soc/sof/intel/mtl.c @@ -453,7 +453,7 @@ static int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_bo /* step 3: wait for IPC DONE bit from ROM */ ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR, chip->ipc_ack, status, ((status & chip->ipc_ack_mask) == chip->ipc_ack_mask), - HDA_DSP_REG_POLL_INTERVAL_US, MTL_DSP_PURGE_TIMEOUT_US); + HDA_DSP_REG_POLL_INTERVAL_US, HDA_DSP_INIT_TIMEOUT_US); if (ret < 0) { if (hda->boot_iteration == HDA_FW_BOOT_ATTEMPTS) dev_err(sdev->dev, "timeout waiting for purge IPC done\n"); diff --git a/sound/soc/sof/intel/mtl.h b/sound/soc/sof/intel/mtl.h index 788bf0e3ea87..00e3526889d3 100644 --- a/sound/soc/sof/intel/mtl.h +++ b/sound/soc/sof/intel/mtl.h @@ -54,7 +54,6 @@ #define MTL_DSP_IRQSTS_IPC BIT(0) #define MTL_DSP_IRQSTS_SDW BIT(6) -#define MTL_DSP_PURGE_TIMEOUT_US 20000000 /* 20s */ #define MTL_DSP_REG_POLL_INTERVAL_US 10 /* 10 us */ /* Memory windows */ From 16722418cbe31400a4ab2ebab05ca2cb305c68e4 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 29 Aug 2023 16:34:55 +1000 Subject: [PATCH 1830/2093] powerpc/watchpoints: Disable preemption in thread_change_pc() [ Upstream commit cc879ab3ce39bc39f9b1d238b283f43a5f6f957d ] thread_change_pc() uses CPU local data, so must be protected from swapping CPUs while it is reading the breakpoint struct. The error is more noticeable after 1e60f3564bad ("powerpc/watchpoints: Track perf single step directly on the breakpoint"), which added an unconditional __this_cpu_read() call in thread_change_pc(). However the existing __this_cpu_read() that runs if a breakpoint does need to be re-inserted has the same issue. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230829063457.54157-2-bgray@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/hw_breakpoint.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 8db1a15d7acb..a72f86c13048 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -505,11 +505,13 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) struct arch_hw_breakpoint *info; int i; + preempt_disable(); + for (i = 0; i < nr_wp_slots(); i++) { if (unlikely(tsk->thread.last_hit_ubp[i])) goto reset; } - return; + goto out; reset: regs_set_return_msr(regs, regs->msr & ~MSR_SE); @@ -518,6 +520,9 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) __set_breakpoint(i, info); tsk->thread.last_hit_ubp[i] = NULL; } + +out: + preempt_enable(); } static bool is_larx_stcx_instr(int type) From 3632e9fd82d030491c8643cb61d36a2371e83a02 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 29 Aug 2023 16:34:56 +1000 Subject: [PATCH 1831/2093] powerpc/watchpoint: Disable pagefaults when getting user instruction [ Upstream commit 3241f260eb830d27d09cc604690ec24533fdb433 ] This is called in an atomic context, so is not allowed to sleep if a user page needs to be faulted in and has nowhere it can be deferred to. The pagefault_disabled() function is documented as preventing user access methods from sleeping. In practice the page will be mapped in nearly always because we are reading the instruction that just triggered the watchpoint trap. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230829063457.54157-3-bgray@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/hw_breakpoint_constraints.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c index a74623025f3a..9e51801c4915 100644 --- a/arch/powerpc/kernel/hw_breakpoint_constraints.c +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr, int *type, int *size, unsigned long *ea) { struct instruction_op op; + int err; - if (__get_user_instr(*instr, (void __user *)regs->nip)) + pagefault_disable(); + err = __get_user_instr(*instr, (void __user *)regs->nip); + pagefault_enable(); + + if (err) return; analyse_instr(&op, regs, *instr); From c93aa8cfaec493e21aed78438f7cfb341fdaec12 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 29 Aug 2023 16:34:57 +1000 Subject: [PATCH 1832/2093] powerpc/watchpoints: Annotate atomic context in more places [ Upstream commit 27646b2e02b096a6936b3e3b6ba334ae20763eab ] It can be easy to miss that the notifier mechanism invokes the callbacks in an atomic context, so add some comments to that effect on the two handlers we register here. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230829063457.54157-4-bgray@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/hw_breakpoint.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index a72f86c13048..02436f80e60e 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -637,6 +637,11 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info, } } +/* + * Handle a DABR or DAWR exception. + * + * Called in atomic context. + */ int hw_breakpoint_handler(struct die_args *args) { bool err = false; @@ -763,6 +768,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler); /* * Handle single-step exceptions following a DABR hit. + * + * Called in atomic context. */ static int single_step_dabr_instruction(struct die_args *args) { @@ -820,6 +827,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction); /* * Handle debug exception notifications. + * + * Called in atomic context. */ int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) From 97788f0757bd028f4f3eece5b113966de6f60a17 Mon Sep 17 00:00:00 2001 From: Johnathan Mantey Date: Fri, 15 Sep 2023 09:12:35 -0700 Subject: [PATCH 1833/2093] ncsi: Propagate carrier gain/loss events to the NCSI controller [ Upstream commit 3780bb29311eccb7a1c9641032a112eed237f7e3 ] Report the carrier/no-carrier state for the network interface shared between the BMC and the passthrough channel. Without this functionality the BMC is unable to reconfigure the NIC in the event of a re-cabling to a different subnet. Signed-off-by: Johnathan Mantey Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ncsi/ncsi-aen.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..f8854bff286c 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -89,6 +89,11 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, if ((had_link == has_link) || chained) return 0; + if (had_link) + netif_carrier_off(ndp->ndev.dev); + else + netif_carrier_on(ndp->ndev.dev); + if (!ndp->multi_package && !nc->package->multi_channel) { if (had_link) { ndp->flags |= NCSI_DEV_RESHUFFLE; From b09c1359e4f08bc8369357cf4ec4a08150b47888 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 15 Sep 2023 20:10:03 +0200 Subject: [PATCH 1834/2093] net: hsr: Add __packed to struct hsr_sup_tlv. [ Upstream commit fbd825fcd7dd4c11d4c48c3d0adc248a4a0ce90b ] Struct hsr_sup_tlv describes HW layout and therefore it needs a __packed attribute to ensure the compiler does not add any padding. Due to the size and __packed attribute of the structs that use hsr_sup_tlv it has no functional impact. Add __packed to struct hsr_sup_tlv. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/hsr/hsr_main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 16ae9fb09ccd..58a5a8b3891f 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -83,7 +83,7 @@ struct hsr_vlan_ethhdr { struct hsr_sup_tlv { u8 HSR_TLV_type; u8 HSR_TLV_length; -}; +} __packed; /* HSR/PRP Supervision Frame data types. * Field names as defined in the IEC:2010 standard for HSR. From 78ac1e7dec24683045b3a1790f3ec2248893f0d0 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 15 Sep 2023 23:01:24 +0200 Subject: [PATCH 1835/2093] tsnep: Fix NAPI scheduling [ Upstream commit ea852c17f5382a0a52041cfbd9a4451ae0fa1a38 ] According to the NAPI documentation networking/napi.rst, drivers which have to mask interrupts explicitly should use the napi_schedule_prep() and __napi_schedule() calls. No problem seen so far with current implementation. Nevertheless, let's align the implementation with documentation. Signed-off-by: Gerhard Engleder Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/engleder/tsnep_main.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 6bf3cc11d212..00436a6f785e 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -65,8 +65,11 @@ static irqreturn_t tsnep_irq(int irq, void *arg) /* handle TX/RX queue 0 interrupt */ if ((active & adapter->queue[0].irq_mask) != 0) { - tsnep_disable_irq(adapter, adapter->queue[0].irq_mask); - napi_schedule(&adapter->queue[0].napi); + if (napi_schedule_prep(&adapter->queue[0].napi)) { + tsnep_disable_irq(adapter, adapter->queue[0].irq_mask); + /* schedule after masking to avoid races */ + __napi_schedule(&adapter->queue[0].napi); + } } return IRQ_HANDLED; @@ -77,8 +80,11 @@ static irqreturn_t tsnep_irq_txrx(int irq, void *arg) struct tsnep_queue *queue = arg; /* handle TX/RX queue interrupt */ - tsnep_disable_irq(queue->adapter, queue->irq_mask); - napi_schedule(&queue->napi); + if (napi_schedule_prep(&queue->napi)) { + tsnep_disable_irq(queue->adapter, queue->irq_mask); + /* schedule after masking to avoid races */ + __napi_schedule(&queue->napi); + } return IRQ_HANDLED; } From 146ba159f5a6bd6756539af4c0d7dbb7dea32ada Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 15 Sep 2023 23:01:26 +0200 Subject: [PATCH 1836/2093] tsnep: Fix NAPI polling with budget 0 [ Upstream commit 46589db3817bd8b523701274885984b5a5dda7d1 ] According to the NAPI documentation networking/napi.rst, Rx specific APIs like page pool and XDP cannot be used at all when budget is 0. skb Tx processing should happen regardless of the budget. Stop NAPI polling after Tx processing and skip Rx processing if budget is 0. Signed-off-by: Gerhard Engleder Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/engleder/tsnep_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 00436a6f785e..2be518db0427 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -930,6 +930,10 @@ static int tsnep_poll(struct napi_struct *napi, int budget) if (queue->tx) complete = tsnep_tx_poll(queue->tx, budget); + /* handle case where we are called by netpoll with a budget of 0 */ + if (unlikely(budget <= 0)) + return budget; + if (queue->rx) { done = tsnep_rx_poll(queue->rx, napi, budget); if (done >= budget) From f105e893a8edd48bdf4bef9fef845a9ff402f737 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Sep 2023 14:26:29 +0800 Subject: [PATCH 1837/2093] LoongArch: Set all reserved memblocks on Node#0 at initialization [ Upstream commit b795fb9f5861ee256070d59e33130980a01fadd7 ] After commit 61167ad5fecdea ("mm: pass nid to reserve_bootmem_region()") we get a panic if DEFERRED_STRUCT_PAGE_INIT is enabled: [ 0.000000] CPU 0 Unable to handle kernel paging request at virtual address 0000000000002b82, era == 90000000040e3f28, ra == 90000000040e3f18 [ 0.000000] Oops[#1]: [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.5.0+ #733 [ 0.000000] pc 90000000040e3f28 ra 90000000040e3f18 tp 90000000046f4000 sp 90000000046f7c90 [ 0.000000] a0 0000000000000001 a1 0000000000200000 a2 0000000000000040 a3 90000000046f7ca0 [ 0.000000] a4 90000000046f7ca4 a5 0000000000000000 a6 90000000046f7c38 a7 0000000000000000 [ 0.000000] t0 0000000000000002 t1 9000000004b00ac8 t2 90000000040e3f18 t3 90000000040f0800 [ 0.000000] t4 00000000000f0000 t5 80000000ffffe07e t6 0000000000000003 t7 900000047fff5e20 [ 0.000000] t8 aaaaaaaaaaaaaaab u0 0000000000000018 s9 0000000000000000 s0 fffffefffe000000 [ 0.000000] s1 0000000000000000 s2 0000000000000080 s3 0000000000000040 s4 0000000000000000 [ 0.000000] s5 0000000000000000 s6 fffffefffe000000 s7 900000000470b740 s8 9000000004ad4000 [ 0.000000] ra: 90000000040e3f18 reserve_bootmem_region+0xec/0x21c [ 0.000000] ERA: 90000000040e3f28 reserve_bootmem_region+0xfc/0x21c [ 0.000000] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 0.000000] PRMD: 00000000 (PPLV0 -PIE -PWE) [ 0.000000] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 0.000000] ECFG: 00070800 (LIE=11 VS=7) [ 0.000000] ESTAT: 00010800 [PIL] (IS=11 ECode=1 EsubCode=0) [ 0.000000] BADV: 0000000000002b82 [ 0.000000] PRID: 0014d000 (Loongson-64bit, Loongson-3A6000) [ 0.000000] Modules linked in: [ 0.000000] Process swapper (pid: 0, threadinfo=(____ptrval____), task=(____ptrval____)) [ 0.000000] Stack : 0000000000000000 9000000002eb5430 0000003a00000020 90000000045ccd00 [ 0.000000] 900000000470e000 90000000002c1918 0000000000000000 9000000004110780 [ 0.000000] 00000000fe6c0000 0000000480000000 9000000004b4e368 9000000004110748 [ 0.000000] 0000000000000000 900000000421ca84 9000000004620000 9000000004564970 [ 0.000000] 90000000046f7d78 9000000002cc9f70 90000000002c1918 900000000470e000 [ 0.000000] 9000000004564970 90000000040bc0e0 90000000046f7d78 0000000000000000 [ 0.000000] 0000000000004000 90000000045ccd00 0000000000000000 90000000002c1918 [ 0.000000] 90000000002c1900 900000000470b700 9000000004b4df78 9000000004620000 [ 0.000000] 90000000046200a8 90000000046200a8 0000000000000000 9000000004218b2c [ 0.000000] 9000000004270008 0000000000000001 0000000000000000 90000000045ccd00 [ 0.000000] ... [ 0.000000] Call Trace: [ 0.000000] [<90000000040e3f28>] reserve_bootmem_region+0xfc/0x21c [ 0.000000] [<900000000421ca84>] memblock_free_all+0x114/0x350 [ 0.000000] [<9000000004218b2c>] mm_core_init+0x138/0x3cc [ 0.000000] [<9000000004200e38>] start_kernel+0x488/0x7a4 [ 0.000000] [<90000000040df0d8>] kernel_entry+0xd8/0xdc [ 0.000000] [ 0.000000] Code: 02eb21ad 00410f4c 380c31ac <262b818d> 6800b70d 02c1c196 0015001c 57fe4bb1 260002cd The reason is early memblock_reserve() in memblock_init() set node id to MAX_NUMNODES, making NODE_DATA(nid) a NULL dereference in the call chain reserve_bootmem_region() -> init_reserved_page(). After memblock_init(), those late calls of memblock_reserve() operate on subregions of memblock .memory regions. As a result, these reserved regions will be set to the correct node at the first iteration of memmap_init_reserved_pages(). So set all reserved memblocks on Node#0 at initialization can avoid this panic. Reported-by: WANG Xuerui Tested-by: WANG Xuerui Reviewed-by: WANG Xuerui # with nits addressed Signed-off-by: Huacai Chen Signed-off-by: Sasha Levin --- arch/loongarch/kernel/mem.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c index 4a4107a6a965..aed901c57fb4 100644 --- a/arch/loongarch/kernel/mem.c +++ b/arch/loongarch/kernel/mem.c @@ -50,7 +50,6 @@ void __init memblock_init(void) } memblock_set_current_limit(PFN_PHYS(max_low_pfn)); - memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); /* Reserve the first 2MB */ memblock_reserve(PHYS_OFFSET, 0x200000); @@ -58,4 +57,7 @@ void __init memblock_init(void) /* Reserve the kernel text/data/bss */ memblock_reserve(__pa_symbol(&_text), __pa_symbol(&_end) - __pa_symbol(&_text)); + + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.reserved, 0); } From 8e85af2c682e19219044aed99166ab8600275578 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 18 Sep 2023 11:03:49 +0200 Subject: [PATCH 1838/2093] fbdev/sh7760fb: Depend on FB=y [ Upstream commit f75f71b2c418a27a7c05139bb27a0c83adf88d19 ] Fix linker error if FB=m about missing fb_io_read and fb_io_write. The linker's error message suggests that this config setting has already been broken for other symbols. All errors (new ones prefixed by >>): sh4-linux-ld: drivers/video/fbdev/sh7760fb.o: in function `sh7760fb_probe': sh7760fb.c:(.text+0x374): undefined reference to `framebuffer_alloc' sh4-linux-ld: sh7760fb.c:(.text+0x394): undefined reference to `fb_videomode_to_var' sh4-linux-ld: sh7760fb.c:(.text+0x39c): undefined reference to `fb_alloc_cmap' sh4-linux-ld: sh7760fb.c:(.text+0x3a4): undefined reference to `register_framebuffer' sh4-linux-ld: sh7760fb.c:(.text+0x3ac): undefined reference to `fb_dealloc_cmap' sh4-linux-ld: sh7760fb.c:(.text+0x434): undefined reference to `framebuffer_release' sh4-linux-ld: drivers/video/fbdev/sh7760fb.o: in function `sh7760fb_remove': sh7760fb.c:(.text+0x800): undefined reference to `unregister_framebuffer' sh4-linux-ld: sh7760fb.c:(.text+0x804): undefined reference to `fb_dealloc_cmap' sh4-linux-ld: sh7760fb.c:(.text+0x814): undefined reference to `framebuffer_release' >> sh4-linux-ld: drivers/video/fbdev/sh7760fb.o:(.rodata+0xc): undefined reference to `fb_io_read' >> sh4-linux-ld: drivers/video/fbdev/sh7760fb.o:(.rodata+0x10): undefined reference to `fb_io_write' sh4-linux-ld: drivers/video/fbdev/sh7760fb.o:(.rodata+0x2c): undefined reference to `cfb_fillrect' sh4-linux-ld: drivers/video/fbdev/sh7760fb.o:(.rodata+0x30): undefined reference to `cfb_copyarea' sh4-linux-ld: drivers/video/fbdev/sh7760fb.o:(.rodata+0x34): undefined reference to `cfb_imageblit' Suggested-by: Randy Dunlap Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202309130632.LS04CPWu-lkp@intel.com/ Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Acked-by: John Paul Adrian Glaubitz Link: https://patchwork.freedesktop.org/patch/msgid/20230918090400.13264-1-tzimmermann@suse.de Signed-off-by: Sasha Levin --- drivers/video/fbdev/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 974e862cd20d..ff95f1922490 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -2015,7 +2015,7 @@ config FB_COBALT config FB_SH7760 bool "SH7760/SH7763/SH7720/SH7721 LCDC support" - depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ + depends on FB=y && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ || CPU_SUBTYPE_SH7720 || CPU_SUBTYPE_SH7721) select FB_CFB_FILLRECT select FB_CFB_COPYAREA From 9ebee88a891156fbca33b3642a3c6929f7b3cf63 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 28 Jul 2023 17:26:54 -0300 Subject: [PATCH 1839/2093] perf build: Define YYNOMEM as YYNOABORT for bison < 3.81 [ Upstream commit 88cc47e24597971b05b6e94c28a2fc81d2a8d61a ] YYNOMEM was introduced in bison 3.81, so define it as YYABORT for older versions, which should provide the previous perf behaviour. Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/Build | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index e315ecaec323..2c364a9087a2 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -276,6 +276,12 @@ ifeq ($(BISON_GE_35),1) else bison_flags += -w endif + +BISON_LT_381 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 381) +ifeq ($(BISON_LT_381),1) + bison_flags += -DYYNOMEM=YYABORT +endif + CFLAGS_parse-events-bison.o += $(bison_flags) CFLAGS_pmu-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) CFLAGS_expr-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) From 69bc295d0e0b75f2fc449840e511385b37393b49 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2022 09:41:41 +0100 Subject: [PATCH 1840/2093] nvme-pci: factor the iod mempool creation into a helper [ Upstream commit 081a7d958ce4b65f9aab6e70e65b0b2e0b92297c ] Add a helper to create the iod mempool. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Tested-by Gerd Bayer Stable-dep-of: dad651b2a44e ("nvme-pci: do not set the NUMA node of device if it has none") Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 41 ++++++++++++++++++----------------------- 1 file changed, 18 insertions(+), 23 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b30269f5e68f..6ab532ca7722 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -392,14 +392,6 @@ static int nvme_pci_npages_sgl(void) NVME_CTRL_PAGE_SIZE); } -static size_t nvme_pci_iod_alloc_size(void) -{ - size_t npages = max(nvme_pci_npages_prp(), nvme_pci_npages_sgl()); - - return sizeof(__le64 *) * npages + - sizeof(struct scatterlist) * NVME_MAX_SEGS; -} - static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -2775,6 +2767,22 @@ static void nvme_release_prp_pools(struct nvme_dev *dev) dma_pool_destroy(dev->prp_small_pool); } +static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev) +{ + size_t npages = max(nvme_pci_npages_prp(), nvme_pci_npages_sgl()); + size_t alloc_size = sizeof(__le64 *) * npages + + sizeof(struct scatterlist) * NVME_MAX_SEGS; + + WARN_ON_ONCE(alloc_size > PAGE_SIZE); + dev->iod_mempool = mempool_create_node(1, + mempool_kmalloc, mempool_kfree, + (void *)alloc_size, GFP_KERNEL, + dev_to_node(dev->dev)); + if (!dev->iod_mempool) + return -ENOMEM; + return 0; +} + static void nvme_free_tagset(struct nvme_dev *dev) { if (dev->tagset.tags) @@ -3103,7 +3111,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) int node, result = -ENOMEM; struct nvme_dev *dev; unsigned long quirks = id->driver_data; - size_t alloc_size; node = dev_to_node(&pdev->dev); if (node == NUMA_NO_NODE) @@ -3148,21 +3155,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) quirks |= NVME_QUIRK_SIMPLE_SUSPEND; } - /* - * Double check that our mempool alloc size will cover the biggest - * command we support. - */ - alloc_size = nvme_pci_iod_alloc_size(); - WARN_ON_ONCE(alloc_size > PAGE_SIZE); - - dev->iod_mempool = mempool_create_node(1, mempool_kmalloc, - mempool_kfree, - (void *) alloc_size, - GFP_KERNEL, node); - if (!dev->iod_mempool) { - result = -ENOMEM; + result = nvme_pci_alloc_iod_mempool(dev); + if (result) goto release_pools; - } result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, quirks); From 6b2165cae40353e313056269289cb894c0103c1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Nov 2022 09:44:00 +0100 Subject: [PATCH 1841/2093] nvme-pci: factor out a nvme_pci_alloc_dev helper [ Upstream commit 2e87570be9d2746e7c4e7ab1cc18fd3ca7de2768 ] Add a helper that allocates the nvme_dev structure up to the point where we can call nvme_init_ctrl. This pairs with the free_ctrl method and can thus be used to cleanup the teardown path and make it more symmetric. Note that this now calls nvme_init_ctrl a lot earlier during probing, which also means the per-controller character device shows up earlier. Due to the controller state no commnds can be send on it, but it might make sense to delay the cdev registration until nvme_init_ctrl_finish. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Tested-by Gerd Bayer Stable-dep-of: dad651b2a44e ("nvme-pci: do not set the NUMA node of device if it has none") Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 83 +++++++++++++++++++++++------------------ 1 file changed, 47 insertions(+), 36 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 6ab532ca7722..42e85b1bf659 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2790,6 +2790,7 @@ static void nvme_free_tagset(struct nvme_dev *dev) dev->ctrl.tagset = NULL; } +/* pairs with nvme_pci_alloc_dev */ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) { struct nvme_dev *dev = to_nvme_dev(ctrl); @@ -3106,19 +3107,23 @@ static void nvme_async_probe(void *data, async_cookie_t cookie) nvme_put_ctrl(&dev->ctrl); } -static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, + const struct pci_device_id *id) { - int node, result = -ENOMEM; - struct nvme_dev *dev; unsigned long quirks = id->driver_data; + int node = dev_to_node(&pdev->dev); + struct nvme_dev *dev; + int ret = -ENOMEM; - node = dev_to_node(&pdev->dev); if (node == NUMA_NO_NODE) set_dev_node(&pdev->dev, first_memory_node); dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node); if (!dev) - return -ENOMEM; + return NULL; + INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); + INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work); + mutex_init(&dev->shutdown_lock); dev->nr_write_queues = write_queues; dev->nr_poll_queues = poll_queues; @@ -3126,25 +3131,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev->queues = kcalloc_node(dev->nr_allocated_queues, sizeof(struct nvme_queue), GFP_KERNEL, node); if (!dev->queues) - goto free; + goto out_free_dev; dev->dev = get_device(&pdev->dev); - pci_set_drvdata(pdev, dev); - - result = nvme_dev_map(dev); - if (result) - goto put_pci; - - INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); - INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work); - mutex_init(&dev->shutdown_lock); - - result = nvme_setup_prp_pools(dev); - if (result) - goto unmap; quirks |= check_vendor_combination_bug(pdev); - if (!noacpi && acpi_storage_d3(&pdev->dev)) { /* * Some systems use a bios work around to ask for D3 on @@ -3154,34 +3145,54 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) "platform quirk: setting simple suspend\n"); quirks |= NVME_QUIRK_SIMPLE_SUSPEND; } + ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, + quirks); + if (ret) + goto out_put_device; + return dev; + +out_put_device: + put_device(dev->dev); + kfree(dev->queues); +out_free_dev: + kfree(dev); + return ERR_PTR(ret); +} + +static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct nvme_dev *dev; + int result = -ENOMEM; + + dev = nvme_pci_alloc_dev(pdev, id); + if (!dev) + return -ENOMEM; + + result = nvme_dev_map(dev); + if (result) + goto out_uninit_ctrl; + + result = nvme_setup_prp_pools(dev); + if (result) + goto out_dev_unmap; result = nvme_pci_alloc_iod_mempool(dev); if (result) - goto release_pools; - - result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, - quirks); - if (result) - goto release_mempool; + goto out_release_prp_pools; dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); + pci_set_drvdata(pdev, dev); nvme_reset_ctrl(&dev->ctrl); async_schedule(nvme_async_probe, dev); - return 0; - release_mempool: - mempool_destroy(dev->iod_mempool); - release_pools: +out_release_prp_pools: nvme_release_prp_pools(dev); - unmap: +out_dev_unmap: nvme_dev_unmap(dev); - put_pci: - put_device(dev->dev); - free: - kfree(dev->queues); - kfree(dev); +out_uninit_ctrl: + nvme_uninit_ctrl(&dev->ctrl); return result; } From a60768c05b586d79ad32ec0dfac3f2ede75395ac Mon Sep 17 00:00:00 2001 From: Pratyush Yadav Date: Tue, 12 Sep 2023 17:52:49 +0200 Subject: [PATCH 1842/2093] nvme-pci: do not set the NUMA node of device if it has none [ Upstream commit dad651b2a44eb6b201738f810254279dca29d30d ] If a device has no NUMA node information associated with it, the driver puts the device in node first_memory_node (say node 0). Not having a NUMA node and being associated with node 0 are completely different things and it makes little sense to mix the two. Signed-off-by: Pratyush Yadav Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 42e85b1bf659..f28f50ea273a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3115,9 +3115,6 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, struct nvme_dev *dev; int ret = -ENOMEM; - if (node == NUMA_NO_NODE) - set_dev_node(&pdev->dev, first_memory_node); - dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node); if (!dev) return NULL; From 1a51d35ba72915b81c38b4b89fc433435767844a Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 22 Aug 2023 16:42:24 +0300 Subject: [PATCH 1843/2093] wifi: ath11k: Don't drop tx_status when peer cannot be found [ Upstream commit 400ece6c7f346b0a30867bd00b03b5b2563d4357 ] When a station idles for a long time, hostapd will try to send a QoS Null frame to the station as "poll". NL80211_CMD_PROBE_CLIENT is used for this purpose. And the skb will be added to ack_status_frame - waiting for a completion via ieee80211_report_ack_skb(). But when the peer was already removed before the tx_complete arrives, the peer will be missing. And when using dev_kfree_skb_any (instead of going through mac80211), the entry will stay inside ack_status_frames. This IDR will therefore run full after 8K request were generated for such clients. At this point, the access point will then just stall and not allow any new clients because idr_alloc() for ack_status_frame will fail. ieee80211_free_txskb() on the other hand will (when required) call ieee80211_report_ack_skb() and make sure that (when required) remove the entry from the ack_status_frame. Tested-on: IPQ6018 hw1.0 WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1 Fixes: 6257c702264c ("wifi: ath11k: fix tx status reporting in encap offload mode") Fixes: 94739d45c388 ("ath11k: switch to using ieee80211_tx_status_ext()") Cc: stable@vger.kernel.org Signed-off-by: Sven Eckelmann Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230802-ath11k-ack_status_leak-v2-1-c0af729d6229@narfation.org Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp_tx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c index 64c8ccac22d2..cd2448861245 100644 --- a/drivers/net/wireless/ath/ath11k/dp_tx.c +++ b/drivers/net/wireless/ath/ath11k/dp_tx.c @@ -369,7 +369,7 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab, "dp_tx: failed to find the peer with peer_id %d\n", ts->peer_id); spin_unlock_bh(&ab->base_lock); - dev_kfree_skb_any(msdu); + ieee80211_free_txskb(ar->hw, msdu); return; } spin_unlock_bh(&ab->base_lock); @@ -624,7 +624,7 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar, "dp_tx: failed to find the peer with peer_id %d\n", ts->peer_id); spin_unlock_bh(&ab->base_lock); - dev_kfree_skb_any(msdu); + ieee80211_free_txskb(ar->hw, msdu); return; } arsta = (struct ath11k_sta *)peer->sta->drv_priv; From 1d7bc76b58497a9ff3f1be1b1900541ecaa6d479 Mon Sep 17 00:00:00 2001 From: Gleb Chesnokov Date: Wed, 17 May 2023 11:22:35 +0300 Subject: [PATCH 1844/2093] scsi: qla2xxx: Fix NULL pointer dereference in target mode [ Upstream commit d54820b22e404b06b2b65877ff802cc7b31688bc ] When target mode is enabled, the pci_irq_get_affinity() function may return a NULL value in qla_mapq_init_qp_cpu_map() due to the qla24xx_enable_msix() code that handles IRQ settings for target mode. This leads to a crash due to a NULL pointer dereference. This patch fixes the issue by adding a check for the NULL value returned by pci_irq_get_affinity() and introducing a 'cpu_mapped' boolean flag to the qla_qpair structure, ensuring that the qpair's CPU affinity is updated when it has not been mapped to a CPU. Fixes: 1d201c81d4cc ("scsi: qla2xxx: Select qpair depending on which CPU post_cmd() gets called") Signed-off-by: Gleb Chesnokov Link: https://lore.kernel.org/r/56b416f2-4e0f-b6cf-d6d5-b7c372e3c6a2@scst.dev Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_def.h | 1 + drivers/scsi/qla2xxx/qla_init.c | 3 +++ drivers/scsi/qla2xxx/qla_inline.h | 3 +++ drivers/scsi/qla2xxx/qla_isr.c | 3 +++ 4 files changed, 10 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 817efdd32ad6..1713588f671f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3805,6 +3805,7 @@ struct qla_qpair { uint64_t retry_term_jiff; struct qla_tgt_counters tgt_counters; uint16_t cpuid; + bool cpu_mapped; struct qla_fw_resources fwres ____cacheline_aligned; u32 cmd_cnt; u32 cmd_completion_cnt; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 79de31e7e8b2..884ed77259f8 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -9759,6 +9759,9 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, qpair->rsp->req = qpair->req; qpair->rsp->qpair = qpair; + if (!qpair->cpu_mapped) + qla_cpu_update(qpair, raw_smp_processor_id()); + if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif) { if (ha->fw_attributes & BIT_4) qpair->difdix_supported = 1; diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index e66441355f7a..a4a56ab0ba74 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -597,11 +597,14 @@ qla_mapq_init_qp_cpu_map(struct qla_hw_data *ha, if (!ha->qp_cpu_map) return; mask = pci_irq_get_affinity(ha->pdev, msix->vector_base0); + if (!mask) + return; qpair->cpuid = cpumask_first(mask); for_each_cpu(cpu, mask) { ha->qp_cpu_map[cpu] = qpair; } msix->cpuid = qpair->cpuid; + qpair->cpu_mapped = true; } static inline void diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index cf1025c91726..db65dbab3a9f 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3819,6 +3819,9 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, if (rsp->qpair->cpuid != raw_smp_processor_id() || !rsp->qpair->rcv_intr) { rsp->qpair->rcv_intr = 1; + + if (!rsp->qpair->cpu_mapped) + qla_cpu_update(rsp->qpair, raw_smp_processor_id()); } #define __update_rsp_in(_is_shadow_hba, _rsp, _rsp_in) \ From 4b8ef68e39d2c86ba88c78aa34c6b067166e8adc Mon Sep 17 00:00:00 2001 From: Irvin Cote Date: Thu, 9 Feb 2023 17:43:57 -0300 Subject: [PATCH 1845/2093] nvme-pci: always return an ERR_PTR from nvme_pci_alloc_dev [ Upstream commit dc785d69d753a3894c93afc23b91404652382ead ] Don't mix NULL and ERR_PTR returns. Fixes: 2e87570be9d2 ("nvme-pci: factor out a nvme_pci_alloc_dev helper") Signed-off-by: Irvin Cote Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index f28f50ea273a..64990a2cfd0a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3117,7 +3117,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node); if (!dev) - return NULL; + return ERR_PTR(-ENOMEM); INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); INIT_WORK(&dev->remove_work, nvme_remove_dead_ctrl_work); mutex_init(&dev->shutdown_lock); @@ -3162,8 +3162,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) int result = -ENOMEM; dev = nvme_pci_alloc_dev(pdev, id); - if (!dev) - return -ENOMEM; + if (IS_ERR(dev)) + return PTR_ERR(dev); result = nvme_dev_map(dev); if (result) From cbb16d0f4996a9b697de824b94a2a7287148e9d3 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 8 May 2023 19:02:34 +0200 Subject: [PATCH 1846/2093] smack: Record transmuting in smk_transmuted [ Upstream commit 2c085f3a8f23c9b444e8b99d93c15d7ce870fc4e ] smack_dentry_create_files_as() determines whether transmuting should occur based on the label of the parent directory the new inode will be added to, and not the label of the directory where it is created. This helps for example to do transmuting on overlayfs, since the latter first creates the inode in the working directory, and then moves it to the correct destination. However, despite smack_dentry_create_files_as() provides the correct label, smack_inode_init_security() does not know from passed information whether or not transmuting occurred. Without this information, smack_inode_init_security() cannot set SMK_INODE_CHANGED in smk_flags, which will result in the SMACK64TRANSMUTE xattr not being set in smack_d_instantiate(). Thus, add the smk_transmuted field to the task_smack structure, and set it in smack_dentry_create_files_as() to smk_task if transmuting occurred. If smk_task is equal to smk_transmuted in smack_inode_init_security(), act as if transmuting was successful but without taking the label from the parent directory (the inode label was already set correctly from the current credentials in smack_inode_alloc_security()). Signed-off-by: Roberto Sassu Signed-off-by: Casey Schaufler Signed-off-by: Sasha Levin --- security/smack/smack.h | 1 + security/smack/smack_lsm.c | 41 +++++++++++++++++++++++++++----------- 2 files changed, 30 insertions(+), 12 deletions(-) diff --git a/security/smack/smack.h b/security/smack/smack.h index e2239be7bd60..aa15ff56ed6e 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -120,6 +120,7 @@ struct inode_smack { struct task_smack { struct smack_known *smk_task; /* label for access control */ struct smack_known *smk_forked; /* label when forked */ + struct smack_known *smk_transmuted;/* label when transmuted */ struct list_head smk_rules; /* per task access rules */ struct mutex smk_rules_lock; /* lock for the rules */ struct list_head smk_relabel; /* transit allowed labels */ diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 67dcd31cd3f3..1232c1d71d9f 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -999,8 +999,9 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) { + struct task_smack *tsp = smack_cred(current_cred()); struct inode_smack *issp = smack_inode(inode); - struct smack_known *skp = smk_of_current(); + struct smack_known *skp = smk_of_task(tsp); struct smack_known *isp = smk_of_inode(inode); struct smack_known *dsp = smk_of_inode(dir); int may; @@ -1009,20 +1010,34 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir, *name = XATTR_SMACK_SUFFIX; if (value && len) { - rcu_read_lock(); - may = smk_access_entry(skp->smk_known, dsp->smk_known, - &skp->smk_rules); - rcu_read_unlock(); + /* + * If equal, transmuting already occurred in + * smack_dentry_create_files_as(). No need to check again. + */ + if (tsp->smk_task != tsp->smk_transmuted) { + rcu_read_lock(); + may = smk_access_entry(skp->smk_known, dsp->smk_known, + &skp->smk_rules); + rcu_read_unlock(); + } /* - * If the access rule allows transmutation and - * the directory requests transmutation then - * by all means transmute. + * In addition to having smk_task equal to smk_transmuted, + * if the access rule allows transmutation and the directory + * requests transmutation then by all means transmute. * Mark the inode as changed. */ - if (may > 0 && ((may & MAY_TRANSMUTE) != 0) && - smk_inode_transmutable(dir)) { - isp = dsp; + if ((tsp->smk_task == tsp->smk_transmuted) || + (may > 0 && ((may & MAY_TRANSMUTE) != 0) && + smk_inode_transmutable(dir))) { + /* + * The caller of smack_dentry_create_files_as() + * should have overridden the current cred, so the + * inode label was already set correctly in + * smack_inode_alloc_security(). + */ + if (tsp->smk_task != tsp->smk_transmuted) + isp = dsp; issp->smk_flags |= SMK_INODE_CHANGED; } @@ -4750,8 +4765,10 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode, * providing access is transmuting use the containing * directory label instead of the process label. */ - if (may > 0 && (may & MAY_TRANSMUTE)) + if (may > 0 && (may & MAY_TRANSMUTE)) { ntsp->smk_task = isp->smk_inode; + ntsp->smk_transmuted = ntsp->smk_task; + } } return 0; } From a09446ac0414801bf2b3945b9bdf3ef59389710e Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 8 May 2023 19:02:33 +0200 Subject: [PATCH 1847/2093] smack: Retrieve transmuting information in smack_inode_getsecurity() [ Upstream commit 3a3d8fce31a49363cc31880dce5e3b0617c9c38b ] Enhance smack_inode_getsecurity() to retrieve the value for SMACK64TRANSMUTE from the inode security blob, similarly to SMACK64. This helps to display accurate values in the situation where the security labels come from mount options and not from xattrs. Signed-off-by: Roberto Sassu Signed-off-by: Casey Schaufler Signed-off-by: Sasha Levin --- security/smack/smack_lsm.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 1232c1d71d9f..cd6a03e945eb 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1476,10 +1476,19 @@ static int smack_inode_getsecurity(struct user_namespace *mnt_userns, struct super_block *sbp; struct inode *ip = (struct inode *)inode; struct smack_known *isp; + struct inode_smack *ispp; + size_t label_len; + char *label = NULL; - if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) + if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) { isp = smk_of_inode(inode); - else { + } else if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) { + ispp = smack_inode(inode); + if (ispp->smk_flags & SMK_INODE_TRANSMUTE) + label = TRANS_TRUE; + else + label = ""; + } else { /* * The rest of the Smack xattrs are only on sockets. */ @@ -1501,13 +1510,18 @@ static int smack_inode_getsecurity(struct user_namespace *mnt_userns, return -EOPNOTSUPP; } + if (!label) + label = isp->smk_known; + + label_len = strlen(label); + if (alloc) { - *buffer = kstrdup(isp->smk_known, GFP_KERNEL); + *buffer = kstrdup(label, GFP_KERNEL); if (*buffer == NULL) return -ENOMEM; } - return strlen(isp->smk_known); + return label_len; } From f90f4c562003ac3d3b135c5a40a5383313f27264 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 3 Oct 2023 16:35:49 -0700 Subject: [PATCH 1848/2093] iommu/arm-smmu-v3: Fix soft lockup triggered by arm_smmu_mm_invalidate_range commit d5afb4b47e13161b3f33904d45110f9e6463bad6 upstream. When running an SVA case, the following soft lockup is triggered: -------------------------------------------------------------------- watchdog: BUG: soft lockup - CPU#244 stuck for 26s! pstate: 83400009 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : arm_smmu_cmdq_issue_cmdlist+0x178/0xa50 lr : arm_smmu_cmdq_issue_cmdlist+0x150/0xa50 sp : ffff8000d83ef290 x29: ffff8000d83ef290 x28: 000000003b9aca00 x27: 0000000000000000 x26: ffff8000d83ef3c0 x25: da86c0812194a0e8 x24: 0000000000000000 x23: 0000000000000040 x22: ffff8000d83ef340 x21: ffff0000c63980c0 x20: 0000000000000001 x19: ffff0000c6398080 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: ffff3000b4a3bbb0 x14: ffff3000b4a30888 x13: ffff3000b4a3cf60 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : ffffc08120e4d6bc x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000048cfa x5 : 0000000000000000 x4 : 0000000000000001 x3 : 000000000000000a x2 : 0000000080000000 x1 : 0000000000000000 x0 : 0000000000000001 Call trace: arm_smmu_cmdq_issue_cmdlist+0x178/0xa50 __arm_smmu_tlb_inv_range+0x118/0x254 arm_smmu_tlb_inv_range_asid+0x6c/0x130 arm_smmu_mm_invalidate_range+0xa0/0xa4 __mmu_notifier_invalidate_range_end+0x88/0x120 unmap_vmas+0x194/0x1e0 unmap_region+0xb4/0x144 do_mas_align_munmap+0x290/0x490 do_mas_munmap+0xbc/0x124 __vm_munmap+0xa8/0x19c __arm64_sys_munmap+0x28/0x50 invoke_syscall+0x78/0x11c el0_svc_common.constprop.0+0x58/0x1c0 do_el0_svc+0x34/0x60 el0_svc+0x2c/0xd4 el0t_64_sync_handler+0x114/0x140 el0t_64_sync+0x1a4/0x1a8 -------------------------------------------------------------------- The commit 06ff87bae8d3 ("arm64: mm: remove unused functions and variable protoypes") fixed a similar lockup on the CPU MMU side. Yet, it can occur to SMMU too since arm_smmu_mm_invalidate_range() is typically called next to MMU tlb flush function, e.g. tlb_flush_mmu_tlbonly { tlb_flush { __flush_tlb_range { // check MAX_TLBI_OPS } } mmu_notifier_invalidate_range { arm_smmu_mm_invalidate_range { // does not check MAX_TLBI_OPS } } } Clone a CMDQ_MAX_TLBI_OPS from the MAX_TLBI_OPS in tlbflush.h, since in an SVA case SMMU uses the CPU page table, so it makes sense to align with the tlbflush code. Then, replace per-page TLBI commands with a single per-asid TLBI command, if the request size hits this threshold. Signed-off-by: Nicolin Chen Link: https://lore.kernel.org/r/20230920052257.8615-1-nicolinc@nvidia.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 27 ++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 5968a568aae2..ffba8ce93ff8 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -186,6 +186,15 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd) } } +/* + * Cloned from the MAX_TLBI_OPS in arch/arm64/include/asm/tlbflush.h, this + * is used as a threshold to replace per-page TLBI commands to issue in the + * command queue with an address-space TLBI command, when SMMU w/o a range + * invalidation feature handles too many per-page TLBI commands, which will + * otherwise result in a soft lockup. + */ +#define CMDQ_MAX_TLBI_OPS (1 << (PAGE_SHIFT - 3)) + static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) @@ -200,10 +209,22 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn, * range. So do a simple translation here by calculating size correctly. */ size = end - start; + if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_RANGE_INV)) { + if (size >= CMDQ_MAX_TLBI_OPS * PAGE_SIZE) + size = 0; + } + + if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) { + if (!size) + arm_smmu_tlb_inv_asid(smmu_domain->smmu, + smmu_mn->cd->asid); + else + arm_smmu_tlb_inv_range_asid(start, size, + smmu_mn->cd->asid, + PAGE_SIZE, false, + smmu_domain); + } - if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) - arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid, - PAGE_SIZE, false, smmu_domain); arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size); } From 811ba2ef0cb6402672e64ba1419d6ef95aa3405d Mon Sep 17 00:00:00 2001 From: Haitao Huang Date: Thu, 27 Jul 2023 22:10:24 -0700 Subject: [PATCH 1849/2093] x86/sgx: Resolves SECS reclaim vs. page fault for EAUG race commit c6c2adcba50c2622ed25ba5d5e7f05f584711358 upstream. The SGX EPC reclaimer (ksgxd) may reclaim the SECS EPC page for an enclave and set secs.epc_page to NULL. The SECS page is used for EAUG and ELDU in the SGX page fault handler. However, the NULL check for secs.epc_page is only done for ELDU, not EAUG before being used. Fix this by doing the same NULL check and reloading of the SECS page as needed for both EAUG and ELDU. The SECS page holds global enclave metadata. It can only be reclaimed when there are no other enclave pages remaining. At that point, virtually nothing can be done with the enclave until the SECS page is paged back in. An enclave can not run nor generate page faults without a resident SECS page. But it is still possible for a #PF for a non-SECS page to race with paging out the SECS page: when the last resident non-SECS page A triggers a #PF in a non-resident page B, and then page A and the SECS both are paged out before the #PF on B is handled. Hitting this bug requires that race triggered with a #PF for EAUG. Following is a trace when it happens. BUG: kernel NULL pointer dereference, address: 0000000000000000 RIP: 0010:sgx_encl_eaug_page+0xc7/0x210 Call Trace: ? __kmem_cache_alloc_node+0x16a/0x440 ? xa_load+0x6e/0xa0 sgx_vma_fault+0x119/0x230 __do_fault+0x36/0x140 do_fault+0x12f/0x400 __handle_mm_fault+0x728/0x1110 handle_mm_fault+0x105/0x310 do_user_addr_fault+0x1ee/0x750 ? __this_cpu_preempt_check+0x13/0x20 exc_page_fault+0x76/0x180 asm_exc_page_fault+0x27/0x30 Fixes: 5a90d2c3f5ef ("x86/sgx: Support adding of pages to an initialized enclave") Signed-off-by: Haitao Huang Signed-off-by: Dave Hansen Reviewed-by: Jarkko Sakkinen Reviewed-by: Kai Huang Acked-by: Reinette Chatre Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20230728051024.33063-1-haitao.huang%40linux.intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/sgx/encl.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 2c258255a629..d5f76b996795 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -235,6 +235,21 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page, return epc_page; } +/* + * Ensure the SECS page is not swapped out. Must be called with encl->lock + * to protect the enclave states including SECS and ensure the SECS page is + * not swapped out again while being used. + */ +static struct sgx_epc_page *sgx_encl_load_secs(struct sgx_encl *encl) +{ + struct sgx_epc_page *epc_page = encl->secs.epc_page; + + if (!epc_page) + epc_page = sgx_encl_eldu(&encl->secs, NULL); + + return epc_page; +} + static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, struct sgx_encl_page *entry) { @@ -248,11 +263,9 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, return entry; } - if (!(encl->secs.epc_page)) { - epc_page = sgx_encl_eldu(&encl->secs, NULL); - if (IS_ERR(epc_page)) - return ERR_CAST(epc_page); - } + epc_page = sgx_encl_load_secs(encl); + if (IS_ERR(epc_page)) + return ERR_CAST(epc_page); epc_page = sgx_encl_eldu(entry, encl->secs.epc_page); if (IS_ERR(epc_page)) @@ -339,6 +352,13 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, mutex_lock(&encl->lock); + epc_page = sgx_encl_load_secs(encl); + if (IS_ERR(epc_page)) { + if (PTR_ERR(epc_page) == -EBUSY) + vmret = VM_FAULT_NOPAGE; + goto err_out_unlock; + } + epc_page = sgx_alloc_epc_page(encl_page, false); if (IS_ERR(epc_page)) { if (PTR_ERR(epc_page) == -EBUSY) From 6ce2f297a7168274547d0b5aea6c7c16268b8a96 Mon Sep 17 00:00:00 2001 From: Pu Wen Date: Thu, 28 Sep 2023 14:59:16 +0800 Subject: [PATCH 1850/2093] x86/srso: Add SRSO mitigation for Hygon processors commit a5ef7d68cea1344cf524f04981c2b3f80bedbb0d upstream. Add mitigation for the speculative return stack overflow vulnerability which exists on Hygon processors too. Signed-off-by: Pu Wen Signed-off-by: Ingo Molnar Acked-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/tencent_4A14812842F104E93AA722EC939483CEFF05@qq.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b723368dbc64..454cdf341862 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1282,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), - VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), VULNBL_AMD(0x19, SRSO), {} }; From e86a3a6226339367b24afacc8b0d530a1e7b2070 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 22 Sep 2023 17:06:34 -0400 Subject: [PATCH 1851/2093] KVM: SVM: INTERCEPT_RDTSCP is never intercepted anyway commit e8d93d5d93f85949e7299be289c6e7e1154b2f78 upstream. svm_recalc_instruction_intercepts() is always called at least once before the vCPU is started, so the setting or clearing of the RDTSCP intercept can be dropped from the TSC_AUX virtualization support. Extracted from a patch by Tom Lendacky. Cc: stable@vger.kernel.org Fixes: 296d5a17e793 ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts") Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/sev.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index d08d5e085649..e0d14f964fe7 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2990,11 +2990,8 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) { + guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); - if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP)) - svm_clr_intercept(svm, INTERCEPT_RDTSCP); - } } void sev_init_vmcb(struct vcpu_svm *svm) From 733d7a5451fc648e3383162e1f7ae00d80ccd6d5 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 15 Sep 2023 15:54:30 -0500 Subject: [PATCH 1852/2093] KVM: SVM: Fix TSC_AUX virtualization setup commit e0096d01c4fcb8c96c05643cfc2c20ab78eae4da upstream. The checks for virtualizing TSC_AUX occur during the vCPU reset processing path. However, at the time of initial vCPU reset processing, when the vCPU is first created, not all of the guest CPUID information has been set. In this case the RDTSCP and RDPID feature support for the guest is not in place and so TSC_AUX virtualization is not established. This continues for each vCPU created for the guest. On the first boot of an AP, vCPU reset processing is executed as a result of an APIC INIT event, this time with all of the guest CPUID information set, resulting in TSC_AUX virtualization being enabled, but only for the APs. The BSP always sees a TSC_AUX value of 0 which probably went unnoticed because, at least for Linux, the BSP TSC_AUX value is 0. Move the TSC_AUX virtualization enablement out of the init_vmcb() path and into the vcpu_after_set_cpuid() path to allow for proper initialization of the support after the guest CPUID information has been set. With the TSC_AUX virtualization support now in the vcpu_set_after_cpuid() path, the intercepts must be either cleared or set based on the guest CPUID input. Fixes: 296d5a17e793 ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts") Signed-off-by: Tom Lendacky Message-Id: <4137fbcb9008951ab5f0befa74a0399d2cce809a.1694811272.git.thomas.lendacky@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/svm/sev.c | 31 ++++++++++++++++++++++++++----- arch/x86/kvm/svm/svm.c | 9 ++------- arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 29 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index e0d14f964fe7..3060fe4e9731 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2941,6 +2941,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } +} + +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_cpuid_entry2 *best; + + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); + if (best) + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_vcpu_after_set_cpuid(svm); +} + static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; @@ -2987,11 +3013,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); - - if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && - (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) - set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7e4d66be18ef..c871a6d6364c 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4173,7 +4173,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_cpuid_entry2 *best; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -4198,12 +4197,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm_recalc_instruction_intercepts(vcpu, svm); - /* For sev guests, the memory encryption bit is not reserved in CR3. */ - if (sev_guest(vcpu->kvm)) { - best = kvm_find_cpuid_entry(vcpu, 0x8000001F); - if (best) - vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); - } + if (sev_guest(vcpu->kvm)) + sev_vcpu_after_set_cpuid(svm); init_vmcb_after_set_cpuid(vcpu); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 62f87492763e..4cb1425900c6 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -677,6 +677,7 @@ void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); From cd41db6cb2851478db60689e2133cfc41b555fc4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 15 Sep 2023 17:39:14 -0700 Subject: [PATCH 1853/2093] KVM: x86/mmu: Open code leaf invalidation from mmu_notifier commit 50107e8b2a8a59d8cec7e8454e27c1f8e365acdb upstream. The mmu_notifier path is a bit of a special snowflake, e.g. it zaps only a single address space (because it's per-slot), and can't always yield. Because of this, it calls kvm_tdp_mmu_zap_leafs() in ways that no one else does. Iterate manually over the leafs in response to an mmu_notifier invalidation, instead of invoking kvm_tdp_mmu_zap_leafs(). Drop the @can_yield param from kvm_tdp_mmu_zap_leafs() as its sole remaining caller unconditionally passes "true". Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20230916003916.2545000-2-seanjc@google.com> Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/mmu/tdp_mmu.c | 13 +++++++++---- arch/x86/kvm/mmu/tdp_mmu.h | 4 ++-- 3 files changed, 12 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7a6df4b62c1b..e232ddaed3e4 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6093,7 +6093,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (is_tdp_mmu_enabled(kvm)) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, true, flush); + gfn_end, flush); } if (flush) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 70945f00ec41..2bd4e186a9b5 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -956,12 +956,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * more SPTEs were zapped since the MMU lock was last acquired. */ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool can_yield, bool flush) + bool flush) { struct kvm_mmu_page *root; for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); + flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; } @@ -1221,8 +1221,13 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + struct kvm_mmu_page *root; + + for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id) + flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, + range->may_block, flush); + + return flush; } typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index c163f7cc23ca..1fb4d4e9cde5 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -15,8 +15,8 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, + bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); From 00c27bffdba6a9c7ecab241ee74e04656060c8d5 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 21 Sep 2023 05:44:56 -0400 Subject: [PATCH 1854/2093] KVM: x86/mmu: Do not filter address spaces in for_each_tdp_mmu_root_yield_safe() commit 441a5dfcd96854cbcb625709e2694a9c60adfaab upstream. All callers except the MMU notifier want to process all address spaces. Remove the address space ID argument of for_each_tdp_mmu_root_yield_safe() and switch the MMU notifier to use __for_each_tdp_mmu_root_yield_safe(). Extracted out of a patch by Sean Christopherson Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/mmu/mmu.c | 8 ++------ arch/x86/kvm/mmu/tdp_mmu.c | 22 +++++++++++----------- arch/x86/kvm/mmu/tdp_mmu.h | 3 +-- 3 files changed, 14 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e232ddaed3e4..2a6fec4e2d19 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6079,7 +6079,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; - int i; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; @@ -6090,11 +6089,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (is_tdp_mmu_enabled(kvm)) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, flush); - } + if (is_tdp_mmu_enabled(kvm)) + flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_with_address(kvm, gfn_start, diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 2bd4e186a9b5..9b9fc4e834d0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -222,8 +222,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false) +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, false, false); \ + _root; \ + _root = tdp_mmu_next_root(_kvm, _root, false, false)) \ + if (!kvm_lockdep_assert_mmu_lock_held(_kvm, false)) { \ + } else /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -955,12 +959,11 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or * more SPTEs were zapped since the MMU lock was last acquired. */ -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool flush) +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) + for_each_tdp_mmu_root_yield_safe(kvm, root) flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; @@ -969,7 +972,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *root; - int i; /* * Zap all roots, including invalid roots, as all SPTEs must be dropped @@ -983,10 +985,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - for_each_tdp_mmu_root_yield_safe(kvm, root, i) - tdp_mmu_zap_root(kvm, root, false); - } + for_each_tdp_mmu_root_yield_safe(kvm, root) + tdp_mmu_zap_root(kvm, root, false); } /* @@ -1223,7 +1223,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id) + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 1fb4d4e9cde5..d0a9fe0770fd 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -15,8 +15,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); From 5d6613ed2b7dca6c5ed6dee8f9fd1dff5966e85f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:45 +0200 Subject: [PATCH 1855/2093] mptcp: fix bogus receive window shrinkage with multiple subflows commit 6bec041147a2a64a490d1f813e8a004443061b38 upstream. In case multiple subflows race to update the mptcp-level receive window, the subflow losing the race should use the window value provided by the "winning" subflow to update it's own tcp-level rcv_wnd. To such goal, the current code bogusly uses the mptcp-level rcv_wnd value as observed before the update attempt. On unlucky circumstances that may lead to TCP-level window shrinkage, and stall the other end. Address the issue feeding to the rcv wnd update the correct value. Fixes: f3589be0c420 ("mptcp: never shrink offered window") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/427 Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/mptcp/options.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 6b2ef3bb53a3..0c786ceda5ee 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1248,12 +1248,13 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd == rcv_wnd_old) break; - if (before64(rcv_wnd_new, rcv_wnd)) { + + rcv_wnd_old = rcv_wnd; + if (before64(rcv_wnd_new, rcv_wnd_old)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE); goto raise_win; } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); - rcv_wnd_old = rcv_wnd; } return; } From 37435ddfadc6ece211415970af44866e2f695ee2 Mon Sep 17 00:00:00 2001 From: Ricky WU Date: Wed, 20 Sep 2023 09:11:19 +0000 Subject: [PATCH 1856/2093] misc: rtsx: Fix some platforms can not boot and move the l1ss judgment to probe commit 0e4cac557531a4c93de108d9ff11329fcad482ff upstream. commit 101bd907b424 ("misc: rtsx: judge ASPM Mode to set PETXCFG Reg") some readers no longer force #CLKREQ to low when the system need to enter ASPM. But some platform maybe not implement complete ASPM? it causes some platforms can not boot Like in the past only the platform support L1ss we release the #CLKREQ. Move the judgment (L1ss) to probe, we think read config space one time when the driver start is enough Fixes: 101bd907b424 ("misc: rtsx: judge ASPM Mode to set PETXCFG Reg") Cc: stable Reported-by: Paul Grandperrin Signed-off-by: Ricky Wu Tested-By: Jade Lovelace Link: https://lore.kernel.org/r/37b1afb997f14946a8784c73d1f9a4f5@realtek.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/rts5227.c | 55 ++++------------------------ drivers/misc/cardreader/rts5228.c | 57 +++++++++--------------------- drivers/misc/cardreader/rts5249.c | 56 ++++------------------------- drivers/misc/cardreader/rts5260.c | 43 +++++++--------------- drivers/misc/cardreader/rts5261.c | 52 +++++++-------------------- drivers/misc/cardreader/rtsx_pcr.c | 51 +++++++++++++++++++++++--- 6 files changed, 102 insertions(+), 212 deletions(-) diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index 3dae5e3a1697..cd512284bfb3 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -83,63 +83,20 @@ static void rts5227_fetch_vendor_settings(struct rtsx_pcr *pcr) static void rts5227_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; - u32 lval; struct rtsx_cr_option *option = &pcr->option; - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - if (CHK_PCI_PID(pcr, 0x522A)) { - if (0 == (lval & 0x0F)) - rtsx_pci_enable_oobs_polling(pcr); - else + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) rtsx_pci_disable_oobs_polling(pcr); + else + rtsx_pci_enable_oobs_polling(pcr); } - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_2_EN); - if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; - } static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) @@ -195,7 +152,7 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) } } - if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) + if (option->force_clkreq_0) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index f4ab09439da7..0c7f10bcf6f1 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -386,59 +386,25 @@ static void rts5228_process_ocp(struct rtsx_pcr *pcr) static void rts5228_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; - u32 lval; struct rtsx_cr_option *option = &pcr->option; - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - - if (0 == (lval & 0x0F)) - rtsx_pci_enable_oobs_polling(pcr); - else + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) rtsx_pci_disable_oobs_polling(pcr); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); else - rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_2_EN); + rtsx_pci_enable_oobs_polling(pcr); rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0); - if (option->ltr_en) { - u16 val; - pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_en) { + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) { + struct rtsx_cr_option *option = &pcr->option; rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1, CD_RESUME_EN_MASK, CD_RESUME_EN_MASK); @@ -469,6 +435,17 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index 47ab72a43256..6c81040e18be 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -86,64 +86,22 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr) static void rts5249_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; struct rtsx_cr_option *option = &(pcr->option); - u32 lval; - - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A)) { - if (0 == (lval & 0x0F)) - rtsx_pci_enable_oobs_polling(pcr); - else + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) rtsx_pci_disable_oobs_polling(pcr); + else + rtsx_pci_enable_oobs_polling(pcr); } - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } -static int rts5249_init_from_hw(struct rtsx_pcr *pcr) -{ - struct rtsx_cr_option *option = &(pcr->option); - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; - - return 0; -} - static void rts52xa_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime) { /* Set relink_time to 0 */ @@ -276,7 +234,6 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) struct rtsx_cr_option *option = &(pcr->option); rts5249_init_from_cfg(pcr); - rts5249_init_from_hw(pcr); rtsx_pci_init_cmd(pcr); @@ -327,11 +284,12 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) } } + /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced * to drive low, and we forcibly request clock. */ - if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) + if (option->force_clkreq_0) rtsx_pci_write_register(pcr, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 79b18f6f73a8..d2d3a6ccb8f7 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -480,47 +480,19 @@ static void rts5260_pwr_saving_setting(struct rtsx_pcr *pcr) static void rts5260_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; struct rtsx_cr_option *option = &pcr->option; - u32 lval; - - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); rts5260_pwr_saving_setting(pcr); if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) { + struct rtsx_cr_option *option = &pcr->option; /* Set mcu_cnt to 7 to ensure data can be sampled properly */ rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07); @@ -539,6 +511,17 @@ static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) rts5260_init_hw(pcr); + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00); return 0; diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index 94af6bf8a25a..67252512a132 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -454,54 +454,17 @@ static void rts5261_init_from_hw(struct rtsx_pcr *pcr) static void rts5261_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; - u32 lval; struct rtsx_cr_option *option = &pcr->option; - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_2_EN); - - rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0); if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) { + struct rtsx_cr_option *option = &pcr->option; u32 val; rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1, @@ -547,6 +510,17 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index a3f4b52bb159..a30751ad3733 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1326,11 +1326,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) return err; } - if (pcr->aspm_mode == ASPM_MODE_REG) { + if (pcr->aspm_mode == ASPM_MODE_REG) rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - } /* No CD interrupt if probing driver with card inserted. * So we need to initialize pcr->card_exist here. @@ -1345,7 +1342,9 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) { - int err; + struct rtsx_cr_option *option = &(pcr->option); + int err, l1ss; + u32 lval; u16 cfg_val; u8 val; @@ -1430,6 +1429,48 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) pcr->aspm_enabled = true; } + l1ss = pci_find_ext_capability(pcr->pci, PCI_EXT_CAP_ID_L1SS); + if (l1ss) { + pci_read_config_dword(pcr->pci, l1ss + PCI_L1SS_CTL1, &lval); + + if (lval & PCI_L1SS_CTL1_ASPM_L1_1) + rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); + else + rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); + + if (lval & PCI_L1SS_CTL1_ASPM_L1_2) + rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); + else + rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); + + if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) + rtsx_set_dev_flag(pcr, PM_L1_1_EN); + else + rtsx_clear_dev_flag(pcr, PM_L1_1_EN); + + if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) + rtsx_set_dev_flag(pcr, PM_L1_2_EN); + else + rtsx_clear_dev_flag(pcr, PM_L1_2_EN); + + pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &cfg_val); + if (cfg_val & PCI_EXP_DEVCTL2_LTR_EN) { + option->ltr_enabled = true; + option->ltr_active = true; + } else { + option->ltr_enabled = false; + } + + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) + option->force_clkreq_0 = false; + else + option->force_clkreq_0 = true; + } else { + option->ltr_enabled = false; + option->force_clkreq_0 = true; + } + if (pcr->ops->fetch_vendor_settings) pcr->ops->fetch_vendor_settings(pcr); From c61d0b87a7028c2c10faffc524d748334c7b9827 Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Thu, 14 Sep 2023 07:15:07 +0200 Subject: [PATCH 1857/2093] Revert "tty: n_gsm: fix UAF in gsm_cleanup_mux" commit 29346e217b8ab8a52889b88f00b268278d6b7668 upstream. This reverts commit 9b9c8195f3f0d74a826077fc1c01b9ee74907239. The commit above is reverted as it did not solve the original issue. gsm_cleanup_mux() tries to free up the virtual ttys by calling gsm_dlci_release() for each available DLCI. There, dlci_put() is called to decrease the reference counter for the DLCI via tty_port_put() which finally calls gsm_dlci_free(). This already clears the pointer which is being checked in gsm_cleanup_mux() before calling gsm_dlci_release(). Therefore, it is not necessary to clear this pointer in gsm_cleanup_mux() as done in the reverted commit. The commit introduces a null pointer dereference: ? __die+0x1f/0x70 ? page_fault_oops+0x156/0x420 ? search_exception_tables+0x37/0x50 ? fixup_exception+0x21/0x310 ? exc_page_fault+0x69/0x150 ? asm_exc_page_fault+0x26/0x30 ? tty_port_put+0x19/0xa0 gsmtty_cleanup+0x29/0x80 [n_gsm] release_one_tty+0x37/0xe0 process_one_work+0x1e6/0x3e0 worker_thread+0x4c/0x3d0 ? __pfx_worker_thread+0x10/0x10 kthread+0xe1/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2f/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 The actual issue is that nothing guards dlci_put() from being called multiple times while the tty driver was triggered but did not yet finished calling gsm_dlci_free(). Fixes: 9b9c8195f3f0 ("tty: n_gsm: fix UAF in gsm_cleanup_mux") Cc: stable Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230914051507.3240-1-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_gsm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index c1fa20a4e342..4b4358930470 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2509,10 +2509,8 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) gsm->has_devices = false; } for (i = NUM_DLCI - 1; i >= 0; i--) - if (gsm->dlci[i]) { + if (gsm->dlci[i]) gsm_dlci_release(gsm->dlci[i]); - gsm->dlci[i] = NULL; - } mutex_unlock(&gsm->mutex); /* Now wipe the queues */ tty_ldisc_flush(gsm->tty); From e14f68a48fd445a083ac0750fafcb064df5f18f7 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Sep 2023 01:25:55 +0300 Subject: [PATCH 1858/2093] serial: 8250_port: Check IRQ data before use commit cce7fc8b29961b64fadb1ce398dc5ff32a79643b upstream. In case the leaf driver wants to use IRQ polling (irq = 0) and IIR register shows that an interrupt happened in the 8250 hardware the IRQ data can be NULL. In such a case we need to skip the wake event as we came to this path from the timer interrupt and quite likely system is already awake. Without this fix we have got an Oops: serial8250: ttyS0 at I/O 0x3f8 (irq = 0, base_baud = 115200) is a 16550A ... BUG: kernel NULL pointer dereference, address: 0000000000000010 RIP: 0010:serial8250_handle_irq+0x7c/0x240 Call Trace: ? serial8250_handle_irq+0x7c/0x240 ? __pfx_serial8250_timeout+0x10/0x10 Fixes: 0ba9e3a13c6a ("serial: 8250: Add missing wakeup event reporting") Cc: stable Signed-off-by: Andy Shevchenko Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230831222555.614426-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 38760bd6e0c2..8efe31448df3 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1953,7 +1953,10 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { - if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) + struct irq_data *d; + + d = irq_get_irq_data(port->irq); + if (d && irqd_is_wakeup_set(d)) pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); From 980663f1d189eedafd18d80053d9cf3e2ceb5c8c Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Thu, 21 Sep 2023 23:17:31 +0900 Subject: [PATCH 1859/2093] nilfs2: fix potential use after free in nilfs_gccache_submit_read_data() commit 7ee29facd8a9c5a26079148e36bcf07141b3a6bc upstream. In nilfs_gccache_submit_read_data(), brelse(bh) is called to drop the reference count of bh when the call to nilfs_dat_translate() fails. If the reference count hits 0 and its owner page gets unlocked, bh may be freed. However, bh->b_page is dereferenced to put the page after that, which may result in a use-after-free bug. This patch moves the release operation after unlocking and putting the page. NOTE: The function in question is only called in GC, and in combination with current userland tools, address translation using DAT does not occur in that function, so the code path that causes this issue will not be executed. However, it is possible to run that code path by intentionally modifying the userland GC library or by calling the GC ioctl directly. [konishi.ryusuke@gmail.com: NOTE added to the commit log] Link: https://lkml.kernel.org/r/1543201709-53191-1-git-send-email-bianpan2016@163.com Link: https://lkml.kernel.org/r/20230921141731.10073-1-konishi.ryusuke@gmail.com Fixes: a3d93f709e89 ("nilfs2: block cache for garbage collection") Signed-off-by: Pan Bian Reported-by: Ferry Meng Closes: https://lkml.kernel.org/r/20230818092022.111054-1-mengferry@linux.alibaba.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/gcinode.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index b0d22ff24b67..fcd13da5d012 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, struct the_nilfs *nilfs = inode->i_sb->s_fs_info; err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn); - if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */ - brelse(bh); + if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */ goto failed; - } } lock_buffer(bh); @@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, failed: unlock_page(bh->b_page); put_page(bh->b_page); + if (unlikely(err)) + brelse(bh); return err; } From 9af8bb2afea3705b58fe930f97a39322f46e5b8b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 7 Sep 2023 08:22:33 +0200 Subject: [PATCH 1860/2093] netfilter: nf_tables: disallow rule removal from chain binding [ Upstream commit f15f29fd4779be8a418b66e9d52979bb6d6c2325 ] Chain binding only requires the rule addition/insertion command within the same transaction. Removal of rules from chain bindings within the same transaction makes no sense, userspace does not utilize this feature. Replace nft_chain_is_bound() check to nft_chain_binding() in rule deletion commands. Replace command implies a rule deletion, reject this command too. Rule flush command can also safely rely on this nft_chain_binding() check because unbound chains are not allowed since 62e1e94b246e ("netfilter: nf_tables: reject unbound chain set before commit phase"). Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1d6a37430ff6..52b81dc1fcf5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1427,7 +1427,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1471,7 +1471,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2792,6 +2792,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + if (info->nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; @@ -3771,6 +3774,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err_destroy_flow_rule; + } + err = nft_delrule(&ctx, old_rule); if (err < 0) goto err_destroy_flow_rule; @@ -3874,7 +3882,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -3904,7 +3912,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -10664,7 +10672,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; From f04ded9ae26876de7948485e1e7c8e0ef754e462 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Thu, 7 Sep 2023 15:24:34 +0800 Subject: [PATCH 1861/2093] ALSA: hda: Disable power save for solving pop issue on Lenovo ThinkCentre M70q commit 057a28ef93bdbe84326d34cdb5543afdaab49fe1 upstream. Lenovo ThinkCentre M70q had boot up pop noise. Disable power save will solve pop issue. Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/315900e2efef42fd9855eacfeb443abd@realtek.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_intel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3226691ac923..54f4b593a115 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2208,6 +2208,7 @@ static const struct snd_pci_quirk power_save_denylist[] = { SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), + SND_PCI_QUIRK(0x17aa, 0x316e, "Lenovo ThinkCentre M70q", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1689623 */ SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */ From 7bc8585aa0719dd1996be804dd4fba601d48f3d6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Wed, 27 Sep 2023 16:19:13 +0800 Subject: [PATCH 1862/2093] LoongArch: Define relocation types for ABI v2.10 commit 2761498876adebff77a43574639005b29e912c43 upstream. The relocation types from 101 to 109 are used by GNU binutils >= 2.41, add their definitions to use them in later patches. Link: https://sourceware.org/git/?p=binutils-gdb.git;a=blob;f=include/elf/loongarch.h#l230 Cc: Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/include/asm/elf.h | 9 +++++++++ arch/loongarch/kernel/module.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index 7af0cebf28d7..b9a4ab54285c 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -111,6 +111,15 @@ #define R_LARCH_TLS_GD_HI20 98 #define R_LARCH_32_PCREL 99 #define R_LARCH_RELAX 100 +#define R_LARCH_DELETE 101 +#define R_LARCH_ALIGN 102 +#define R_LARCH_PCREL20_S2 103 +#define R_LARCH_CFA 104 +#define R_LARCH_ADD6 105 +#define R_LARCH_SUB6 106 +#define R_LARCH_ADD_ULEB128 107 +#define R_LARCH_SUB_ULEB128 108 +#define R_LARCH_64_PCREL 109 #ifndef ELF_ARCH diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c index 097595b2fc14..4f1e6e55dc02 100644 --- a/arch/loongarch/kernel/module.c +++ b/arch/loongarch/kernel/module.c @@ -376,7 +376,7 @@ typedef int (*reloc_rela_handler)(struct module *mod, u32 *location, Elf_Addr v, /* The handlers for known reloc types */ static reloc_rela_handler reloc_rela_handlers[] = { - [R_LARCH_NONE ... R_LARCH_RELAX] = apply_r_larch_error, + [R_LARCH_NONE ... R_LARCH_64_PCREL] = apply_r_larch_error, [R_LARCH_NONE] = apply_r_larch_none, [R_LARCH_32] = apply_r_larch_32, From 490f3b805ee3639e8b69c91d63e1ea76189950ae Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 27 Sep 2023 16:19:13 +0800 Subject: [PATCH 1863/2093] LoongArch: numa: Fix high_memory calculation commit 1943feecf80e73ecc03ce40271f29c6cea142bac upstream. For 64bit kernel without HIGHMEM, high_memory is the virtual address of the highest physical address in the system. But __va(get_num_physpages() << PAGE_SHIFT) is not what we want for high_memory because there may be holes in the physical address space. On the other hand, max_low_pfn is calculated from memblock_end_of_DRAM(), which is exactly corresponding to the highest physical address, so use it for high_memory calculation. Cc: Fixes: d4b6f1562a3c3284adce ("LoongArch: Add Non-Uniform Memory Access (NUMA) support") Signed-off-by: Chong Qiao Signed-off-by: Huacai Chen Signed-off-by: Greg Kroah-Hartman --- arch/loongarch/kernel/numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index a13f92593cfd..f7ffce170213 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -453,7 +453,7 @@ void __init paging_init(void) void __init mem_init(void) { - high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); + high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); setup_zero_pages(); /* This comes from node 0 */ } From 476fd029e7008722da9e2326af30f69cd187417a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 25 Aug 2023 15:41:14 +0900 Subject: [PATCH 1864/2093] ata: libata-scsi: link ata port and scsi device commit fb99ef17865035a6657786d4b2af11a27ba23f9b upstream. There is no direct device ancestry defined between an ata_device and its scsi device which prevents the power management code from correctly ordering suspend and resume operations. Create such ancestry with the ata device as the parent to ensure that the scsi device (child) is suspended before the ata device and that resume handles the ata device before the scsi device. The parent-child (supplier-consumer) relationship is established between the ata_port (parent) and the scsi device (child) with the function device_add_link(). The parent used is not the ata_device as the PM operations are defined per port and the status of all devices connected through that port is controlled from the port operations. The device link is established with the new function ata_scsi_slave_alloc(), and this function is used to define the ->slave_alloc callback of the scsi host template of all ata drivers. Fixes: a19a93e4c6a9 ("scsi: core: pm: Rely on the device driver core for async power management") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Niklas Cassel Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Reviewed-by: John Garry Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-scsi.c | 45 ++++++++++++++++++++++++++++++++++----- include/linux/libata.h | 2 ++ 2 files changed, 42 insertions(+), 5 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 9c0052d28078..82f3e977f61e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1113,6 +1113,42 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) return 0; } +/** + * ata_scsi_slave_alloc - Early setup of SCSI device + * @sdev: SCSI device to examine + * + * This is called from scsi_alloc_sdev() when the scsi device + * associated with an ATA device is scanned on a port. + * + * LOCKING: + * Defined by SCSI layer. We don't really care. + */ + +int ata_scsi_slave_alloc(struct scsi_device *sdev) +{ + struct ata_port *ap = ata_shost_to_port(sdev->host); + struct device_link *link; + + ata_scsi_sdev_config(sdev); + + /* + * Create a link from the ata_port device to the scsi device to ensure + * that PM does suspend/resume in the correct order: the scsi device is + * consumer (child) and the ata port the supplier (parent). + */ + link = device_link_add(&sdev->sdev_gendev, &ap->tdev, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); + if (!link) { + ata_port_err(ap, "Failed to create link to scsi device %s\n", + dev_name(&sdev->sdev_gendev)); + return -ENODEV; + } + + return 0; +} +EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc); + /** * ata_scsi_slave_config - Set SCSI device attributes * @sdev: SCSI device to examine @@ -1129,14 +1165,11 @@ int ata_scsi_slave_config(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = __ata_scsi_find_dev(ap, sdev); - int rc = 0; - - ata_scsi_sdev_config(sdev); if (dev) - rc = ata_scsi_dev_config(sdev, dev); + return ata_scsi_dev_config(sdev, dev); - return rc; + return 0; } EXPORT_SYMBOL_GPL(ata_scsi_slave_config); @@ -1163,6 +1196,8 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev) if (!ap->ops->error_handler) return; + device_link_remove(&sdev->sdev_gendev, &ap->tdev); + spin_lock_irqsave(ap->lock, flags); dev = __ata_scsi_find_dev(ap, sdev); if (dev && dev->sdev) { diff --git a/include/linux/libata.h b/include/linux/libata.h index 4c9b322bb3d8..c3c50218f6eb 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1136,6 +1136,7 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); +extern int ata_scsi_slave_alloc(struct scsi_device *sdev); extern int ata_scsi_slave_config(struct scsi_device *sdev); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, @@ -1384,6 +1385,7 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ + .slave_alloc = ata_scsi_slave_alloc, \ .slave_destroy = ata_scsi_slave_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ From 06fba8a8dea22c2260785cafd74e6d42ac38711a Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Mon, 18 Sep 2023 22:24:50 +0200 Subject: [PATCH 1865/2093] ata: libata-scsi: ignore reserved bits for REPORT SUPPORTED OPERATION CODES commit 3ef600923521616ebe192c893468ad0424de2afb upstream. For REPORT SUPPORTED OPERATION CODES command, the service action field is defined as bits 0-4 in the second byte in the CDB. Bits 5-7 in the second byte are reserved. Only look at the service action field in the second byte when determining if the MAINTENANCE IN opcode is a REPORT SUPPORTED OPERATION CODES command. This matches how we only look at the service action field in the second byte when determining if the SERVICE ACTION IN(16) opcode is a READ CAPACITY(16) command (reserved bits 5-7 in the second byte are ignored). Fixes: 7b2030942859 ("libata: Add support for SCT Write Same") Cc: stable@vger.kernel.org Signed-off-by: Niklas Cassel Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-scsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 82f3e977f61e..d28628b964e2 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4227,7 +4227,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) break; case MAINTENANCE_IN: - if (scsicmd[1] == MI_REPORT_SUPPORTED_OPERATION_CODES) + if ((scsicmd[1] & 0x1f) == MI_REPORT_SUPPORTED_OPERATION_CODES) ata_scsi_rbuf_fill(&args, ata_scsiop_maint_in); else ata_scsi_set_invalid_field(dev, cmd, 1, 0xff); From 75c307d9f2fbb949cb8713b8f659fec5f21f2c34 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Sep 2023 09:23:27 -0600 Subject: [PATCH 1866/2093] io_uring/fs: remove sqe->rw_flags checking from LINKAT commit a52d4f657568d6458e873f74a9602e022afe666f upstream. This is unionized with the actual link flags, so they can of course be set and they will be evaluated further down. If not we fail any LINKAT that has to set option flags. Fixes: cf30da90bc3a ("io_uring: add support for IORING_OP_LINKAT") Cc: stable@vger.kernel.org Reported-by: Thomas Leonard Link: https://github.com/axboe/liburing/issues/955 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/fs.c b/io_uring/fs.c index 7100c293c13a..27676e015004 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -243,7 +243,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); const char __user *oldf, *newf; - if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; From 829ff08be5663bb70aa8b21c47e514f0f53df5e1 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 14 Sep 2023 23:08:44 +0200 Subject: [PATCH 1867/2093] i2c: i801: unregister tco_pdev in i801_probe() error path commit 3914784553f68c931fc666dbe7e86fe881aada38 upstream. We have to unregister tco_pdev also if i2c_add_adapter() fails. Fixes: 9424693035a5 ("i2c: i801: Create iTCO device on newer Intel PCHs") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Mika Westerberg Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-i801.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 1fda1eaa6d6a..da1f6b60f9c9 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1754,6 +1754,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) "SMBus I801 adapter at %04lx", priv->smba); err = i2c_add_adapter(&priv->adapter); if (err) { + platform_device_unregister(priv->tco_pdev); i801_acpi_remove(priv); return err; } From afa2bbd682c7704b78104ec9fea8dd71fd7dbd1c Mon Sep 17 00:00:00 2001 From: August Wikerfors Date: Mon, 11 Sep 2023 23:34:09 +0200 Subject: [PATCH 1868/2093] ASoC: amd: yc: Fix non-functional mic on Lenovo 82QF and 82UG commit 1263cc0f414d212129c0f1289b49b7df77f92084 upstream. Like the Lenovo 82TL and 82V2, the Lenovo 82QF (Yoga 7 14ARB7) and 82UG (Legion S7 16ARHA7) both need a quirk entry for the internal microphone to function. Commit c008323fe361 ("ASoC: amd: yc: Fix a non-functional mic on Lenovo 82SJ") restricted the quirk that previously matched "82" to "82V2", breaking microphone functionality on these devices. Fix this by adding specific quirks for these models, as was done for the Lenovo 82TL. Fixes: c008323fe361 ("ASoC: amd: yc: Fix a non-functional mic on Lenovo 82SJ") Closes: https://github.com/tomsom/yoga-linux/issues/51 Link: https://bugzilla.kernel.org/show_bug.cgi?id=208555#c780 Cc: stable@vger.kernel.org Signed-off-by: August Wikerfors Link: https://lore.kernel.org/r/20230911213409.6106-1-git@augustwikerfors.se Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/amd/yc/acp6x-mach.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 9a9571c3f08c..2ee741ac25f4 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -213,6 +213,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "21J6"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -220,6 +227,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82V2"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82UG"), + } + }, { .driver_data = &acp6x_card, .matches = { From 787256ec9b443f2a77d9ee06a8385f1bd1aedada Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Fri, 15 Sep 2023 13:44:44 -0400 Subject: [PATCH 1869/2093] kernel/sched: Modify initial boot task idle setup commit cff9b2332ab762b7e0586c793c431a8f2ea4db04 upstream. Initial booting is setting the task flag to idle (PF_IDLE) by the call path sched_init() -> init_idle(). Having the task idle and calling call_rcu() in kernel/rcu/tiny.c means that TIF_NEED_RESCHED will be set. Subsequent calls to any cond_resched() will enable IRQs, potentially earlier than the IRQ setup has completed. Recent changes have caused just this scenario and IRQs have been enabled early. This causes a warning later in start_kernel() as interrupts are enabled before they are fully set up. Fix this issue by setting the PF_IDLE flag later in the boot sequence. Although the boot task was marked as idle since (at least) d80e4fda576d, I am not sure that it is wrong to do so. The forced context-switch on idle task was introduced in the tiny_rcu update, so I'm going to claim this fixes 5f6130fa52ee. Fixes: 5f6130fa52ee ("tiny_rcu: Directly force QS when call_rcu_[bh|sched]() on idle_task") Signed-off-by: Liam R. Howlett Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-mm/CAMuHMdWpvpWoDa=Ox-do92czYRvkok6_x6pYUH+ZouMcJbXy+Q@mail.gmail.com/ Signed-off-by: Greg Kroah-Hartman --- kernel/sched/core.c | 2 +- kernel/sched/idle.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0f6a92737c91..55d13980e29f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9019,7 +9019,7 @@ void __init init_idle(struct task_struct *idle, int cpu) * PF_KTHREAD should already be set at this point; regardless, make it * look like a proper per-CPU kthread. */ - idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; + idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); #ifdef CONFIG_SMP diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index f26ab2675f7d..200a0fac03b8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -394,6 +394,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise); void cpu_startup_entry(enum cpuhp_state state) { + current->flags |= PF_IDLE; arch_cpu_idle_prepare(); cpuhp_online_idle(state); while (1) From 49903f70d728ee516bcaf620354553d0788103ab Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Sat, 23 Sep 2023 01:14:08 +0000 Subject: [PATCH 1870/2093] sched/rt: Fix live lock between select_fallback_rq() and RT push commit fc09027786c900368de98d03d40af058bcb01ad9 upstream. During RCU-boost testing with the TREE03 rcutorture config, I found that after a few hours, the machine locks up. On tracing, I found that there is a live lock happening between 2 CPUs. One CPU has an RT task running, while another CPU is being offlined which also has an RT task running. During this offlining, all threads are migrated. The migration thread is repeatedly scheduled to migrate actively running tasks on the CPU being offlined. This results in a live lock because select_fallback_rq() keeps picking the CPU that an RT task is already running on only to get pushed back to the CPU being offlined. It is anyway pointless to pick CPUs for pushing tasks to if they are being offlined only to get migrated away to somewhere else. This could also add unwanted latency to this task. Fix these issues by not selecting CPUs in RT if they are not 'active' for scheduling, using the cpu_active_mask. Other parts in core.c already use cpu_active_mask to prevent tasks from being put on CPUs going offline. With this fix I ran the tests for days and could not reproduce the hang. Without the patch, I hit it in a few hours. Signed-off-by: Joel Fernandes (Google) Signed-off-by: Ingo Molnar Tested-by: Paul E. McKenney Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230923011409.3522762-1-joel@joelfernandes.org Signed-off-by: Greg Kroah-Hartman --- kernel/sched/cpupri.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index a286e726eb4b..42c40cfdf836 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -101,6 +101,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p, if (lowest_mask) { cpumask_and(lowest_mask, &p->cpus_mask, vec->mask); + cpumask_and(lowest_mask, lowest_mask, cpu_active_mask); /* * We have to ensure that we have at least one bit From 1e4c03d530d8368799a6cd3473c4e44ff2e36451 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 10 Aug 2023 23:59:03 +0200 Subject: [PATCH 1871/2093] netfilter: nf_tables: fix kdoc warnings after gc rework commit 08713cb006b6f07434f276c5ee214fb20c7fd965 upstream. Jakub Kicinski says: We've got some new kdoc warnings here: net/netfilter/nft_set_pipapo.c:1557: warning: Function parameter or member '_set' not described in 'pipapo_gc' net/netfilter/nft_set_pipapo.c:1557: warning: Excess function parameter 'set' description in 'pipapo_gc' include/net/netfilter/nf_tables.h:577: warning: Function parameter or member 'dead' not described in 'nft_set' Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Reported-by: Jakub Kicinski Closes: https://lore.kernel.org/netdev/20230810104638.746e46f1@kernel.org/ Signed-off-by: Florian Westphal Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 1 + net/netfilter/nft_set_pipapo.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 05d7a60a0e1f..d1f81a6d7773 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -529,6 +529,7 @@ struct nft_set_elem_expr { * @expr: stateful expression * @ops: set ops * @flags: set flags + * @dead: set will be freed, never cleared * @genmask: generation mask * @klen: key length * @dlen: data length diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 83f5f276c3bf..deea6196d992 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1550,7 +1550,7 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements - * @set: nftables API set representation + * @_set: nftables API set representation * @m: Matching data */ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) From f32340c70eb96372321b9084840e76dcdc1a455a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Sep 2023 19:26:46 -0400 Subject: [PATCH 1872/2093] Revert "SUNRPC dont update timeout value on connection reset" commit a275ab62606bcd894ddff09460f7d253828313dc upstream. This reverts commit 88428cc4ae7abcc879295fbb19373dd76aad2bdd. The problem this commit is intended to fix was comprehensively fixed in commit 7de62bc09fe6 ("SUNRPC dont update timeout value on connection reset"). Since then, this commit has been preventing the correct timeout of soft mounted requests. Cc: stable@vger.kernel.org # 5.9.x: 09252177d5f9: SUNRPC: Handle major timeout in xprt_adjust_timeout() Cc: stable@vger.kernel.org # 5.9.x: 7de62bc09fe6: SUNRPC dont update timeout value on connection reset Cc: stable@vger.kernel.org # 5.9.x Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/clnt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b3f6f67ed252..2b803383c7b3 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2462,8 +2462,7 @@ call_status(struct rpc_task *task) goto out_exit; } task->tk_action = call_encode; - if (status != -ECONNRESET && status != -ECONNABORTED) - rpc_check_timeout(task); + rpc_check_timeout(task); return; out_exit: rpc_call_rpcerror(task, status); From a90eafbf165f71e2b51a2a85be6d2f8cc895a028 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 12 Sep 2023 12:44:06 +0200 Subject: [PATCH 1873/2093] timers: Tag (hr)timer softirq as hotplug safe commit 1a6a464774947920dcedcf7409be62495c7cedd0 upstream. Specific stress involving frequent CPU-hotplug operations, such as running rcutorture for example, may trigger the following message: NOHZ tick-stop error: local softirq work is pending, handler #02!!!" This happens in the CPU-down hotplug process, after CPUHP_AP_SMPBOOT_THREADS whose teardown callback parks ksoftirqd, and before the target CPU shuts down through CPUHP_AP_IDLE_DEAD. In this fragile intermediate state, softirqs waiting for threaded handling may be forever ignored and eventually reported by the idle task as in the above example. However some vectors are known to be safe as long as the corresponding subsystems have teardown callbacks handling the migration of their events. The above error message reports pending timers softirq although this vector can be considered as hotplug safe because the CPUHP_TIMERS_PREPARE teardown callback performs the necessary migration of timers after the death of the CPU. Hrtimers also have a similar hotplug handling. Therefore this error message, as far as (hr-)timers are concerned, can be considered spurious and the relevant softirq vectors can be marked as hotplug safe. Fixes: 0345691b24c0 ("tick/rcu: Stop allowing RCU_SOFTIRQ in idle") Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Reviewed-by: Joel Fernandes (Google) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230912104406.312185-6-frederic@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/interrupt.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a92bce40b04b..4a1dc88ddbff 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,8 +569,12 @@ enum * 2) rcu_report_dead() reports the final quiescent states. * * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue + * + * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue */ -#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\ + BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ)) + /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. From b29756aefe03ac0439147f48a2a11d0a0dccee83 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 11 Sep 2023 15:03:24 +0200 Subject: [PATCH 1874/2093] drm/tests: Fix incorrect argument in drm_test_mm_insert_range MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2ba157983974ae1b6aaef7d4953812020d6f1eb5 upstream. While drm_mm test was converted form igt selftest to kunit, unexpected value of "end" argument equal "start" was introduced to one of calls to a function that executes the drm_test_mm_insert_range for specific start/end pair of arguments. As a consequence, DRM_MM_BUG_ON(end <= start) is triggered. Fix it by restoring the original value. Fixes: fc8d29e298cf ("drm: selftest: convert drm_mm selftest to KUnit") Signed-off-by: Janusz Krzysztofik Cc: "Maíra Canal" Cc: Arthur Grillo Cc: Javier Martinez Canillas Cc: Daniel Latypov Cc: stable@vger.kernel.org # v6.1+ Reviewed-by: Maíra Canal Signed-off-by: Maíra Canal Link: https://patchwork.freedesktop.org/patch/msgid/20230911130323.7037-2-janusz.krzysztofik@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/tests/drm_mm_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index c4b66eeae203..13fa4a18a11b 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -939,7 +939,7 @@ static void drm_test_mm_insert_range(struct kunit *test) KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, 0, max - 1)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, 0, max / 2)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, - max / 2, max / 2)); + max / 2, max)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, max / 4 + 1, 3 * max / 4 - 1)); From 68a63a077e02dba22ba62b53e6db1241bbffb116 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 21 Sep 2023 17:57:22 +0300 Subject: [PATCH 1875/2093] arm64: defconfig: remove CONFIG_COMMON_CLK_NPCM8XX=y commit 7d3e4e9d3bde9c8bd8914d47ddaa90e0d0ffbcab upstream. There is no code for this config option and enabling it in defconfig causes warnings from tools which are detecting unused and obsolete kernel config flags since the flag will be completely missing from effective build config after "make olddefconfig". Fixes yocto kernel recipe build time warning: WARNING: [kernel config]: This BSP contains fragments with warnings: ... [INFO]: the following symbols were not found in the active configuration: - CONFIG_COMMON_CLK_NPCM8XX The flag was added with commit 45472f1e5348c7b755b4912f2f529ec81cea044b v5.19-rc4-15-g45472f1e5348 so 6.1 and 6.4 stable kernel trees are affected. Fixes: 45472f1e5348c7b755b4912f2f529ec81cea044b ("arm64: defconfig: Add Nuvoton NPCM family support") Cc: stable@kernel.org Cc: Catalin Marinas Cc: Will Deacon Cc: Bjorn Andersson Cc: Krzysztof Kozlowski Cc: Konrad Dybcio Cc: Neil Armstrong Cc: Tomer Maimon Cc: Bruce Ashfield Cc: Jon Mason Cc: Jon Mason Cc: Ross Burton Cc: Arnd Bergmann Signed-off-by: Mikko Rapeli Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- arch/arm64/configs/defconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0b6af3348e79..623e9f308f38 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1050,7 +1050,6 @@ CONFIG_COMMON_CLK_FSL_SAI=y CONFIG_COMMON_CLK_S2MPS11=y CONFIG_COMMON_CLK_PWM=y CONFIG_COMMON_CLK_VC5=y -CONFIG_COMMON_CLK_NPCM8XX=y CONFIG_COMMON_CLK_BD718XX=m CONFIG_CLK_RASPBERRYPI=m CONFIG_CLK_IMX8MM=y From 9a4fe81a8644b717d57d81ce5849e16583b13fe8 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Mon, 25 Sep 2023 15:20:59 +0800 Subject: [PATCH 1876/2093] mm/damon/vaddr-test: fix memory leak in damon_do_test_apply_three_regions() commit 45120b15743fa7c0aa53d5db6dfb4c8f87be4abd upstream. When CONFIG_DAMON_VADDR_KUNIT_TEST=y and making CONFIG_DEBUG_KMEMLEAK=y and CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y, the below memory leak is detected. Since commit 9f86d624292c ("mm/damon/vaddr-test: remove unnecessary variables"), the damon_destroy_ctx() is removed, but still call damon_new_target() and damon_new_region(), the damon_region which is allocated by kmem_cache_alloc() in damon_new_region() and the damon_target which is allocated by kmalloc in damon_new_target() are not freed. And the damon_region which is allocated in damon_new_region() in damon_set_regions() is also not freed. So use damon_destroy_target to free all the damon_regions and damon_target. unreferenced object 0xffff888107c9a940 (size 64): comm "kunit_try_catch", pid 1069, jiffies 4294670592 (age 732.761s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 06 00 00 00 6b 6b 6b 6b ............kkkk 60 c7 9c 07 81 88 ff ff f8 cb 9c 07 81 88 ff ff `............... backtrace: [] kmalloc_trace+0x27/0xa0 [] damon_new_target+0x3f/0x1b0 [] damon_do_test_apply_three_regions.constprop.0+0x95/0x3e0 [] damon_test_apply_three_regions1+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff8881079cc740 (size 56): comm "kunit_try_catch", pid 1069, jiffies 4294670592 (age 732.761s) hex dump (first 32 bytes): 05 00 00 00 00 00 00 00 14 00 00 00 00 00 00 00 ................ 6b 6b 6b 6b 6b 6b 6b 6b 00 00 00 00 6b 6b 6b 6b kkkkkkkk....kkkk backtrace: [] damon_new_region+0x22/0x1c0 [] damon_do_test_apply_three_regions.constprop.0+0xd1/0x3e0 [] damon_test_apply_three_regions1+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888107c9ac40 (size 64): comm "kunit_try_catch", pid 1071, jiffies 4294670595 (age 732.843s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 06 00 00 00 6b 6b 6b 6b ............kkkk a0 cc 9c 07 81 88 ff ff 78 a1 76 07 81 88 ff ff ........x.v..... backtrace: [] kmalloc_trace+0x27/0xa0 [] damon_new_target+0x3f/0x1b0 [] damon_do_test_apply_three_regions.constprop.0+0x95/0x3e0 [] damon_test_apply_three_regions2+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff8881079ccc80 (size 56): comm "kunit_try_catch", pid 1071, jiffies 4294670595 (age 732.843s) hex dump (first 32 bytes): 05 00 00 00 00 00 00 00 14 00 00 00 00 00 00 00 ................ 6b 6b 6b 6b 6b 6b 6b 6b 00 00 00 00 6b 6b 6b 6b kkkkkkkk....kkkk backtrace: [] damon_new_region+0x22/0x1c0 [] damon_do_test_apply_three_regions.constprop.0+0xd1/0x3e0 [] damon_test_apply_three_regions2+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888107c9af40 (size 64): comm "kunit_try_catch", pid 1073, jiffies 4294670597 (age 733.011s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 06 00 00 00 6b 6b 6b 6b ............kkkk 20 a2 76 07 81 88 ff ff b8 a6 76 07 81 88 ff ff .v.......v..... backtrace: [] kmalloc_trace+0x27/0xa0 [] damon_new_target+0x3f/0x1b0 [] damon_do_test_apply_three_regions.constprop.0+0x95/0x3e0 [] damon_test_apply_three_regions3+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810776a200 (size 56): comm "kunit_try_catch", pid 1073, jiffies 4294670597 (age 733.011s) hex dump (first 32 bytes): 05 00 00 00 00 00 00 00 14 00 00 00 00 00 00 00 ................ 6b 6b 6b 6b 6b 6b 6b 6b 00 00 00 00 6b 6b 6b 6b kkkkkkkk....kkkk backtrace: [] damon_new_region+0x22/0x1c0 [] damon_do_test_apply_three_regions.constprop.0+0xd1/0x3e0 [] damon_test_apply_three_regions3+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810776a740 (size 56): comm "kunit_try_catch", pid 1073, jiffies 4294670597 (age 733.025s) hex dump (first 32 bytes): 3d 00 00 00 00 00 00 00 3f 00 00 00 00 00 00 00 =.......?....... 6b 6b 6b 6b 6b 6b 6b 6b 00 00 00 00 6b 6b 6b 6b kkkkkkkk....kkkk backtrace: [] damon_new_region+0x22/0x1c0 [] damon_set_regions+0x4c2/0x8e0 [] damon_do_test_apply_three_regions.constprop.0+0xfb/0x3e0 [] damon_test_apply_three_regions3+0x21e/0x260 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888108038240 (size 64): comm "kunit_try_catch", pid 1075, jiffies 4294670600 (age 733.022s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 03 00 00 00 6b 6b 6b 6b ............kkkk 48 ad 76 07 81 88 ff ff 98 ae 76 07 81 88 ff ff H.v.......v..... backtrace: [] kmalloc_trace+0x27/0xa0 [] damon_new_target+0x3f/0x1b0 [] damon_do_test_apply_three_regions.constprop.0+0x95/0x3e0 [] damon_test_apply_three_regions4+0x1cd/0x210 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810776ad28 (size 56): comm "kunit_try_catch", pid 1075, jiffies 4294670600 (age 733.022s) hex dump (first 32 bytes): 05 00 00 00 00 00 00 00 07 00 00 00 00 00 00 00 ................ 6b 6b 6b 6b 6b 6b 6b 6b 00 00 00 00 6b 6b 6b 6b kkkkkkkk....kkkk backtrace: [] damon_new_region+0x22/0x1c0 [] damon_set_regions+0x4c2/0x8e0 [] damon_do_test_apply_three_regions.constprop.0+0xfb/0x3e0 [] damon_test_apply_three_regions4+0x1cd/0x210 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 Link: https://lkml.kernel.org/r/20230925072100.3725620-1-ruanjinjie@huawei.com Fixes: 9f86d624292c ("mm/damon/vaddr-test: remove unnecessary variables") Signed-off-by: Jinjie Ruan Reviewed-by: SeongJae Park Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/damon/vaddr-test.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index bce37c487540..e939598aff94 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -140,6 +140,8 @@ static void damon_do_test_apply_three_regions(struct kunit *test, KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]); KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]); } + + damon_destroy_target(t); } /* From a5569bb187521432f509b69dda7d29f78b2d38b0 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Fri, 8 Sep 2023 19:06:49 -0400 Subject: [PATCH 1877/2093] mm/slab_common: fix slab_caches list corruption after kmem_cache_destroy() commit 46a9ea6681907a3be6b6b0d43776dccc62cad6cf upstream. After the commit in Fixes:, if a module that created a slab cache does not release all of its allocated objects before destroying the cache (at rmmod time), we might end up releasing the kmem_cache object without removing it from the slab_caches list thus corrupting the list as kmem_cache_destroy() ignores the return value from shutdown_cache(), which in turn never removes the kmem_cache object from slabs_list in case __kmem_cache_shutdown() fails to release all of the cache's slabs. This is easily observable on a kernel built with CONFIG_DEBUG_LIST=y as after that ill release the system will immediately trip on list_add, or list_del, assertions similar to the one shown below as soon as another kmem_cache gets created, or destroyed: [ 1041.213632] list_del corruption. next->prev should be ffff89f596fb5768, but was 52f1e5016aeee75d. (next=ffff89f595a1b268) [ 1041.219165] ------------[ cut here ]------------ [ 1041.221517] kernel BUG at lib/list_debug.c:62! [ 1041.223452] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 1041.225408] CPU: 2 PID: 1852 Comm: rmmod Kdump: loaded Tainted: G B W OE 6.5.0 #15 [ 1041.228244] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230524-3.fc37 05/24/2023 [ 1041.231212] RIP: 0010:__list_del_entry_valid+0xae/0xb0 Another quick way to trigger this issue, in a kernel with CONFIG_SLUB=y, is to set slub_debug to poison the released objects and then just run cat /proc/slabinfo after removing the module that leaks slab objects, in which case the kernel will panic: [ 50.954843] general protection fault, probably for non-canonical address 0xa56b6b6b6b6b6b8b: 0000 [#1] PREEMPT SMP PTI [ 50.961545] CPU: 2 PID: 1495 Comm: cat Kdump: loaded Tainted: G B W OE 6.5.0 #15 [ 50.966808] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230524-3.fc37 05/24/2023 [ 50.972663] RIP: 0010:get_slabinfo+0x42/0xf0 This patch fixes this issue by properly checking shutdown_cache()'s return value before taking the kmem_cache_release() branch. Fixes: 0495e337b703 ("mm/slab_common: Deleting kobject in kmem_cache_destroy() without holding slab_mutex/cpu_hotplug_lock") Signed-off-by: Rafael Aquini Cc: stable@vger.kernel.org Reviewed-by: Waiman Long Signed-off-by: Vlastimil Babka Signed-off-by: Greg Kroah-Hartman --- mm/slab_common.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/slab_common.c b/mm/slab_common.c index 0042fb2730d1..4736c0e6093f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -474,7 +474,7 @@ void slab_kmem_cache_release(struct kmem_cache *s) void kmem_cache_destroy(struct kmem_cache *s) { - int refcnt; + int err = -EBUSY; bool rcu_set; if (unlikely(!s) || !kasan_check_byte(s)) @@ -485,17 +485,17 @@ void kmem_cache_destroy(struct kmem_cache *s) rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU; - refcnt = --s->refcount; - if (refcnt) + s->refcount--; + if (s->refcount) goto out_unlock; - WARN(shutdown_cache(s), - "%s %s: Slab cache still has objects when called from %pS", + err = shutdown_cache(s); + WARN(err, "%s %s: Slab cache still has objects when called from %pS", __func__, s->name, (void *)_RET_IP_); out_unlock: mutex_unlock(&slab_mutex); cpus_read_unlock(); - if (!refcnt && !rcu_set) + if (!err && !rcu_set) kmem_cache_release(s); } EXPORT_SYMBOL(kmem_cache_destroy); From 6bacdb914a99183d270a422fcfb16f46679e3a84 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Sep 2023 11:21:39 -0400 Subject: [PATCH 1878/2093] mm: memcontrol: fix GFP_NOFS recursion in memory.high enforcement commit 9ea9cb00a82b53ec39630eac718776d37e41b35a upstream. Breno and Josef report a deadlock scenario from cgroup reclaim re-entering the filesystem: [ 361.546690] ====================================================== [ 361.559210] WARNING: possible circular locking dependency detected [ 361.571703] 6.5.0-0_fbk700_debug_rc0_kbuilder_13159_gbf787a128001 #1 Tainted: G S E [ 361.589704] ------------------------------------------------------ [ 361.602277] find/9315 is trying to acquire lock: [ 361.611625] ffff88837ba140c0 (&delayed_node->mutex){+.+.}-{4:4}, at: __btrfs_release_delayed_node+0x68/0x4f0 [ 361.631437] [ 361.631437] but task is already holding lock: [ 361.643243] ffff8881765b8678 (btrfs-tree-01){++++}-{4:4}, at: btrfs_tree_read_lock+0x1e/0x40 [ 362.904457] mutex_lock_nested+0x1c/0x30 [ 362.912414] __btrfs_release_delayed_node+0x68/0x4f0 [ 362.922460] btrfs_evict_inode+0x301/0x770 [ 362.982726] evict+0x17c/0x380 [ 362.988944] prune_icache_sb+0x100/0x1d0 [ 363.005559] super_cache_scan+0x1f8/0x260 [ 363.013695] do_shrink_slab+0x2a2/0x540 [ 363.021489] shrink_slab_memcg+0x237/0x3d0 [ 363.050606] shrink_slab+0xa7/0x240 [ 363.083382] shrink_node_memcgs+0x262/0x3b0 [ 363.091870] shrink_node+0x1a4/0x720 [ 363.099150] shrink_zones+0x1f6/0x5d0 [ 363.148798] do_try_to_free_pages+0x19b/0x5e0 [ 363.157633] try_to_free_mem_cgroup_pages+0x266/0x370 [ 363.190575] reclaim_high+0x16f/0x1f0 [ 363.208409] mem_cgroup_handle_over_high+0x10b/0x270 [ 363.246678] try_charge_memcg+0xaf2/0xc70 [ 363.304151] charge_memcg+0xf0/0x350 [ 363.320070] __mem_cgroup_charge+0x28/0x40 [ 363.328371] __filemap_add_folio+0x870/0xd50 [ 363.371303] filemap_add_folio+0xdd/0x310 [ 363.399696] __filemap_get_folio+0x2fc/0x7d0 [ 363.419086] pagecache_get_page+0xe/0x30 [ 363.427048] alloc_extent_buffer+0x1cd/0x6a0 [ 363.435704] read_tree_block+0x43/0xc0 [ 363.443316] read_block_for_search+0x361/0x510 [ 363.466690] btrfs_search_slot+0xc8c/0x1520 This is caused by the mem_cgroup_handle_over_high() not respecting the gfp_mask of the allocation context. We used to only call this function on resume to userspace, where no locks were held. But c9afe31ec443 ("memcg: synchronously enforce memory.high for large overcharges") added a call from the allocation context without considering the gfp. Link: https://lkml.kernel.org/r/20230914152139.100822-1-hannes@cmpxchg.org Fixes: c9afe31ec443 ("memcg: synchronously enforce memory.high for large overcharges") Signed-off-by: Johannes Weiner Reported-by: Breno Leitao Reported-by: Josef Bacik Acked-by: Shakeel Butt Acked-by: Michal Hocko Cc: Roman Gushchin Cc: Muchun Song Cc: [5.17+] Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/memcontrol.h | 4 ++-- include/linux/resume_user_mode.h | 2 +- mm/memcontrol.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 099521835cd1..50a078a31734 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -902,7 +902,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(void); +void mem_cgroup_handle_over_high(gfp_t gfp_mask); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); @@ -1437,7 +1437,7 @@ static inline void mem_cgroup_unlock_pages(void) rcu_read_unlock(); } -static inline void mem_cgroup_handle_over_high(void) +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index 285189454449..f8f3e958e9cf 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -55,7 +55,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) } #endif - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 67b6d8238b3e..9ffcf80cf252 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2545,7 +2545,7 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg, * Scheduled by try_charge() to be executed from the userland return path * and reclaims memory over the high limit. */ -void mem_cgroup_handle_over_high(void) +void mem_cgroup_handle_over_high(gfp_t gfp_mask) { unsigned long penalty_jiffies; unsigned long pflags; @@ -2573,7 +2573,7 @@ void mem_cgroup_handle_over_high(void) */ nr_reclaimed = reclaim_high(memcg, in_retry ? SWAP_CLUSTER_MAX : nr_pages, - GFP_KERNEL); + gfp_mask); /* * memory.high is breached and reclaim is unable to keep up. Throttle @@ -2809,7 +2809,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH && !(current->flags & PF_MEMALLOC) && gfpflags_allow_blocking(gfp_mask)) { - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(gfp_mask); } return 0; } From f3ad8874541d671d4ec21581196bd3f38973805b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 29 Sep 2023 18:01:13 -0400 Subject: [PATCH 1879/2093] ring-buffer: Update "shortest_full" in polling commit 1e0cb399c7653462d9dadf8ab9425337c355d358 upstream. It was discovered that the ring buffer polling was incorrectly stating that read would not block, but that's because polling did not take into account that reads will block if the "buffer-percent" was set. Instead, the ring buffer polling would say reads would not block if there was any data in the ring buffer. This was incorrect behavior from a user space point of view. This was fixed by commit 42fb0a1e84ff by having the polling code check if the ring buffer had more data than what the user specified "buffer percent" had. The problem now is that the polling code did not register itself to the writer that it wanted to wait for a specific "full" value of the ring buffer. The result was that the writer would wake the polling waiter whenever there was a new event. The polling waiter would then wake up, see that there's not enough data in the ring buffer to notify user space and then go back to sleep. The next event would wake it up again. Before the polling fix was added, the code would wake up around 100 times for a hackbench 30 benchmark. After the "fix", due to the constant waking of the writer, it would wake up over 11,0000 times! It would never leave the kernel, so the user space behavior was still "correct", but this definitely is not the desired effect. To fix this, have the polling code add what it's waiting for to the "shortest_full" variable, to tell the writer not to wake it up if the buffer is not as full as it expects to be. Note, after this fix, it appears that the waiter is now woken up around 2x the times it was before (~200). This is a tremendous improvement from the 11,000 times, but I will need to spend some time to see why polling is more aggressive in its wakeups than the read blocking code. Link: https://lore.kernel.org/linux-trace-kernel/20230929180113.01c2cae3@rorschach.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Fixes: 42fb0a1e84ff ("tracing/ring-buffer: Have polling block on watermark") Reported-by: Julia Lawall Tested-by: Julia Lawall Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ring_buffer.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c0b708b55c3b..2f562cf961e0 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1142,6 +1142,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, if (full) { poll_wait(filp, &work->full_waiters, poll_table); work->full_waiters_pending = true; + if (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full) + cpu_buffer->shortest_full = full; } else { poll_wait(filp, &work->waiters, poll_table); work->waiters_pending = true; From d6a749e4cab2bb51950baf0dac87822db8833bc9 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 18 Sep 2023 10:34:51 -0400 Subject: [PATCH 1880/2093] btrfs: properly report 0 avail for very full file systems commit 58bfe2ccec5f9f137b41dd38f335290dcc13cd5c upstream. A user reported some issues with smaller file systems that get very full. While investigating this issue I noticed that df wasn't showing 100% full, despite having 0 chunk space and having < 1MiB of available metadata space. This turns out to be an overflow issue, we're doing: total_available_metadata_space - SZ_4M < global_block_rsv_size to determine if there's not enough space to make metadata allocations, which overflows if total_available_metadata_space is < 4M. Fix this by checking to see if our available space is greater than the 4M threshold. This makes df properly report 100% usage on the file system. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6438300fa246..582b71b7fa77 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2418,7 +2418,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * calculated f_bavail. */ if (!mixed && block_rsv->space_info->full && - total_free_meta - thresh < block_rsv->size) + (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size)) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; From 09635bf4cdd4adf2160198a6041bcc7ca46c0558 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Thu, 20 Jul 2023 17:46:54 +0000 Subject: [PATCH 1881/2093] media: uvcvideo: Fix OOB read commit 41ebaa5e0eebea4c3bac96b72f9f8ae0d77c0bdb upstream. If the index provided by the user is bigger than the mask size, we might do an out of bound read. CC: stable@kernel.org Fixes: 40140eda661e ("media: uvcvideo: Implement mask for V4L2_CTRL_TYPE_MENU") Reported-by: Zubin Mithra Signed-off-by: Ricardo Ribalda Reviewed-by: Sergey Senozhatsky Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_ctrl.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 067b43a1cb3e..6d7535efc09d 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1347,6 +1347,9 @@ int uvc_query_v4l2_menu(struct uvc_video_chain *chain, query_menu->id = id; query_menu->index = index; + if (index >= BITS_PER_TYPE(mapping->menu_mask)) + return -EINVAL; + ret = mutex_lock_interruptible(&chain->ctrl_mutex); if (ret < 0) return -ERESTARTSYS; From b1041cab47260374f389de1e81dc9a4a3b2e4859 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Sep 2023 22:06:51 +0200 Subject: [PATCH 1882/2093] bpf: Add override check to kprobe multi link attach commit 41bc46c12a8053a1b3279a379bd6b5e87b045b85 upstream. Currently the multi_kprobe link attach does not check error injection list for programs with bpf_override_return helper and allows them to attach anywhere. Adding the missing check. Fixes: 0dcac2725406 ("bpf: Add multi kprobe link") Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Reviewed-by: Alan Maguire Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20230907200652.926951-1-jolsa@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/trace/bpf_trace.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9fc5db194027..8c77c54e6348 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2684,6 +2684,17 @@ static void symbols_swap_r(void *a, void *b, int size, const void *priv) } } +static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + if (!within_error_injection_list(addrs[i])) + return -EINVAL; + } + return 0; +} + int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_kprobe_multi_link *link = NULL; @@ -2761,6 +2772,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error; } + if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) { + err = -EINVAL; + goto error; + } + link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { err = -ENOMEM; From 4f1e3e02777b2ccc915da4db681133eb585a7a3b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 15 Sep 2023 10:34:27 -0700 Subject: [PATCH 1883/2093] bpf: Fix BTF_ID symbol generation collision commit 8f908db77782630c45ba29dac35c434b5ce0b730 upstream. Marcus and Satya reported an issue where BTF_ID macro generates same symbol in separate objects and that breaks final vmlinux link. ld.lld: error: ld-temp.o :14577:1: symbol '__BTF_ID__struct__cgroup__624' is already defined This can be triggered under specific configs when __COUNTER__ happens to be the same for the same symbol in two different translation units, which is already quite unlikely to happen. Add __LINE__ number suffix to make BTF_ID symbol more unique, which is not a complete fix, but it would help for now and meanwhile we can work on better solution as suggested by Andrii. Cc: stable@vger.kernel.org Reported-by: Satya Durga Srinivasu Prabhala Reported-by: Marcus Seyfarth Closes: https://github.com/ClangBuiltLinux/linux/issues/1913 Debugged-by: Nathan Chancellor Link: https://lore.kernel.org/bpf/CAEf4Bzb5KQ2_LmhN769ifMeSJaWfebccUasQOfQKaOd0nQ51tw@mail.gmail.com/ Signed-off-by: Jiri Olsa Signed-off-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230915-bpf_collision-v3-1-263fc519c21f@google.com Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- include/linux/btf_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 2b9872008428..0f02bbb20573 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -49,7 +49,7 @@ word \ ____BTF_ID(symbol, word) #define __ID(prefix) \ - __PASTE(prefix, __COUNTER__) + __PASTE(__PASTE(prefix, __COUNTER__), __LINE__) /* * The BTF_ID defines unique symbol for each ID pointing From 4fb56e82d939eb949bfa6b142cf54b394b7514a6 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 15 Sep 2023 10:34:28 -0700 Subject: [PATCH 1884/2093] bpf: Fix BTF_ID symbol generation collision in tools/ commit c0bb9fb0e52a64601d38b3739b729d9138d4c8a1 upstream. Marcus and Satya reported an issue where BTF_ID macro generates same symbol in separate objects and that breaks final vmlinux link. ld.lld: error: ld-temp.o :14577:1: symbol '__BTF_ID__struct__cgroup__624' is already defined This can be triggered under specific configs when __COUNTER__ happens to be the same for the same symbol in two different translation units, which is already quite unlikely to happen. Add __LINE__ number suffix to make BTF_ID symbol more unique, which is not a complete fix, but it would help for now and meanwhile we can work on better solution as suggested by Andrii. Cc: stable@vger.kernel.org Reported-by: Satya Durga Srinivasu Prabhala Reported-by: Marcus Seyfarth Closes: https://github.com/ClangBuiltLinux/linux/issues/1913 Debugged-by: Nathan Chancellor Co-developed-by: Jiri Olsa Link: https://lore.kernel.org/bpf/CAEf4Bzb5KQ2_LmhN769ifMeSJaWfebccUasQOfQKaOd0nQ51tw@mail.gmail.com/ Signed-off-by: Nick Desaulniers Link: https://lore.kernel.org/r/20230915-bpf_collision-v3-2-263fc519c21f@google.com Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- tools/include/linux/btf_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 71e54b1e3796..2f882d5cb30f 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -38,7 +38,7 @@ asm( \ ____BTF_ID(symbol) #define __ID(prefix) \ - __PASTE(prefix, __COUNTER__) + __PASTE(__PASTE(prefix, __COUNTER__), __LINE__) /* * The BTF_ID defines unique symbol for each ID pointing From 1983fd78701a04664951ca5d0852b587ad495626 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 13 Sep 2023 08:26:47 +0300 Subject: [PATCH 1885/2093] net: thunderbolt: Fix TCPv6 GSO checksum calculation commit e0b65f9b81fef180cf5f103adecbe5505c961153 upstream. Alex reported that running ssh over IPv6 does not work with Thunderbolt/USB4 networking driver. The reason for that is that driver should call skb_is_gso() before calling skb_is_gso_v6(), and it should not return false after calculates the checksum successfully. This probably was a copy paste error from the original driver where it was done properly. Reported-by: Alex Balcanquall Fixes: e69b6c02b4c3 ("net: Add support for networking over Thunderbolt cable") Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg Reviewed-by: Eric Dumazet Reviewed-by: Jiri Pirko Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/thunderbolt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index 6312f67f260e..5966e36875de 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -1005,12 +1005,11 @@ static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb, *tucso = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, 0, ip_hdr(skb)->protocol, 0); - } else if (skb_is_gso_v6(skb)) { + } else if (skb_is_gso(skb) && skb_is_gso_v6(skb)) { tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data); *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); - return false; } else if (protocol == htons(ETH_P_IPV6)) { tucso = dest + skb_checksum_start_offset(skb) + skb->csum_offset; *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, From f555a508087ab8210b4658120ac6413d6fe2b4c7 Mon Sep 17 00:00:00 2001 From: Quang Le Date: Fri, 29 Sep 2023 00:44:13 +0700 Subject: [PATCH 1886/2093] fs/smb/client: Reset password pointer to NULL commit e6e43b8aa7cd3c3af686caf0c2e11819a886d705 upstream. Forget to reset ctx->password to NULL will lead to bug like double free Cc: stable@vger.kernel.org Cc: Willy Tarreau Reviewed-by: Namjae Jeon Signed-off-by: Quang Le Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/fs_context.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index e2e2ef0fa9a0..f4818599c00a 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1487,6 +1487,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_parse_mount_err: kfree_sensitive(ctx->password); + ctx->password = NULL; return -EINVAL; } From 0b7aaf2058baf3aa1d5c82fd2016ef53b45f2553 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 4 Sep 2023 20:38:13 +0900 Subject: [PATCH 1887/2093] ata: libata-core: Fix ata_port_request_pm() locking commit 3b8e0af4a7a331d1510e963b8fd77e2fca0a77f1 upstream. The function ata_port_request_pm() checks the port flag ATA_PFLAG_PM_PENDING and calls ata_port_wait_eh() if this flag is set to ensure that power management operations for a port are not scheduled simultaneously. However, this flag check is done without holding the port lock. Fix this by taking the port lock on entry to the function and checking the flag under this lock. The lock is released and re-taken if ata_port_wait_eh() needs to be called. The two WARN_ON() macros checking that the ATA_PFLAG_PM_PENDING flag was cleared are removed as the first call is racy and the second one done without holding the port lock. Fixes: 5ef41082912b ("ata: add ata port system PM callbacks") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Tested-by: Chia-Lin Kao (AceLan) Reviewed-by: Niklas Cassel Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Reviewed-by: Bart Van Assche Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-core.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 0ba0c3d1613f..a95809272b22 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4981,17 +4981,19 @@ static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg, struct ata_link *link; unsigned long flags; - /* Previous resume operation might still be in - * progress. Wait for PM_PENDING to clear. - */ - if (ap->pflags & ATA_PFLAG_PM_PENDING) { - ata_port_wait_eh(ap); - WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); - } - - /* request PM ops to EH */ spin_lock_irqsave(ap->lock, flags); + /* + * A previous PM operation might still be in progress. Wait for + * ATA_PFLAG_PM_PENDING to clear. + */ + if (ap->pflags & ATA_PFLAG_PM_PENDING) { + spin_unlock_irqrestore(ap->lock, flags); + ata_port_wait_eh(ap); + spin_lock_irqsave(ap->lock, flags); + } + + /* Request PM operation to EH */ ap->pm_mesg = mesg; ap->pflags |= ATA_PFLAG_PM_PENDING; ata_for_each_link(link, ap, HOST_FIRST) { @@ -5003,10 +5005,8 @@ static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg, spin_unlock_irqrestore(ap->lock, flags); - if (!async) { + if (!async) ata_port_wait_eh(ap); - WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); - } } /* From 5cfbe6da83541bb262f4e9c9881283479439409e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 26 Aug 2023 13:07:36 +0900 Subject: [PATCH 1888/2093] ata: libata-core: Fix port and device removal commit 84d76529c650f887f1e18caee72d6f0589e1baf9 upstream. Whenever an ATA adapter driver is removed (e.g. rmmod), ata_port_detach() is called repeatedly for all the adapter ports to remove (unload) the devices attached to the port and delete the port device itself. Removing of devices is done using libata EH with the ATA_PFLAG_UNLOADING port flag set. This causes libata EH to execute ata_eh_unload() which disables all devices attached to the port. ata_port_detach() finishes by calling scsi_remove_host() to remove the scsi host associated with the port. This function will trigger the removal of all scsi devices attached to the host and in the case of disks, calls to sd_shutdown() which will flush the device write cache and stop the device. However, given that the devices were already disabled by ata_eh_unload(), the synchronize write cache command and start stop unit commands fail. E.g. running "rmmod ahci" with first removing sd_mod results in error messages like: ata13.00: disable device sd 0:0:0:0: [sda] Synchronizing SCSI cache sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK sd 0:0:0:0: [sda] Stopping disk sd 0:0:0:0: [sda] Start/Stop Unit failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK Fix this by removing all scsi devices of the ata devices connected to the port before scheduling libata EH to disable the ATA devices. Fixes: 720ba12620ee ("[PATCH] libata-hp: update unload-unplug") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Niklas Cassel Tested-by: Chia-Lin Kao (AceLan) Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-core.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index a95809272b22..39dc4b94a317 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5906,11 +5906,30 @@ static void ata_port_detach(struct ata_port *ap) if (!ap->ops->error_handler) goto skip_eh; - /* tell EH we're leaving & flush EH */ + /* Wait for any ongoing EH */ + ata_port_wait_eh(ap); + + mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); + + /* Remove scsi devices */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ALL) { + if (dev->sdev) { + spin_unlock_irqrestore(ap->lock, flags); + scsi_remove_device(dev->sdev); + spin_lock_irqsave(ap->lock, flags); + dev->sdev = NULL; + } + } + } + + /* Tell EH to disable all devices */ ap->pflags |= ATA_PFLAG_UNLOADING; ata_port_schedule_eh(ap); + spin_unlock_irqrestore(ap->lock, flags); + mutex_unlock(&ap->scsi_scan_mutex); /* wait till EH commits suicide */ ata_port_wait_eh(ap); From 886f387db1e6ce38a478672e2c2cc2582401004d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 8 Sep 2023 20:04:52 +0900 Subject: [PATCH 1889/2093] ata: libata-core: Do not register PM operations for SAS ports commit 75e2bd5f1ede42a2bc88aa34b431e1ace8e0bea0 upstream. libsas does its own domain based power management of ports. For such ports, libata should not use a device type defining power management operations as executing these operations for suspend/resume in addition to libsas calls to ata_sas_port_suspend() and ata_sas_port_resume() is not necessary (and likely dangerous to do, even though problems are not seen currently). Introduce the new ata_port_sas_type device_type for ports managed by libsas. This new device type is used in ata_tport_add() and is defined without power management operations. Fixes: 2fcbdcb4c802 ("[SCSI] libata: export ata_port suspend/resume infrastructure for sas") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Tested-by: Chia-Lin Kao (AceLan) Tested-by: Geert Uytterhoeven Reviewed-by: John Garry Reviewed-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-core.c | 2 +- drivers/ata/libata-transport.c | 9 ++++++++- drivers/ata/libata.h | 2 ++ 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 39dc4b94a317..25b9bdf2fc38 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5173,7 +5173,7 @@ EXPORT_SYMBOL_GPL(ata_host_resume); #endif const struct device_type ata_port_type = { - .name = "ata_port", + .name = ATA_PORT_TYPE_NAME, #ifdef CONFIG_PM .pm = &ata_port_pm_ops, #endif diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index e4fb9d1b9b39..3e49a877500e 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -266,6 +266,10 @@ void ata_tport_delete(struct ata_port *ap) put_device(dev); } +static const struct device_type ata_port_sas_type = { + .name = ATA_PORT_TYPE_NAME, +}; + /** ata_tport_add - initialize a transport ATA port structure * * @parent: parent device @@ -283,7 +287,10 @@ int ata_tport_add(struct device *parent, struct device *dev = &ap->tdev; device_initialize(dev); - dev->type = &ata_port_type; + if (ap->flags & ATA_FLAG_SAS_HOST) + dev->type = &ata_port_sas_type; + else + dev->type = &ata_port_type; dev->parent = parent; ata_host_get(ap->host); diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 2c5c8273af01..e5ec197aed30 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -30,6 +30,8 @@ enum { ATA_DNXFER_QUIET = (1 << 31), }; +#define ATA_PORT_TYPE_NAME "ata_port" + extern atomic_t ata_print_id; extern int atapi_passthru16; extern int libata_fua; From 60d2e06ad6e3bf4d630420be730ad014234b64f1 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 22 Sep 2023 22:55:16 +0200 Subject: [PATCH 1890/2093] ata: libata-sata: increase PMP SRST timeout to 10s commit 753a4d531bc518633ea88ac0ed02b25a16823d51 upstream. On certain SATA controllers, softreset fails after wakeup from S2RAM with the message "softreset failed (1st FIS failed)", sometimes resulting in drives not being detected again. With the increased timeout, this issue is avoided. Instead, "softreset failed (device not ready)" is now logged 1-2 times; this later failure seems to cause fewer problems however, and the drives are detected reliably once they've spun up and the probe is retried. The issue was observed with the primary SATA controller of the QNAP TS-453B, which is an "Intel Corporation Celeron/Pentium Silver Processor SATA Controller [8086:31e3] (rev 06)" integrated in the Celeron J4125 CPU, and the following drives: - Seagate IronWolf ST12000VN0008 - Seagate IronWolf ST8000NE0004 The SATA controller seems to be more relevant to this issue than the drives, as the same drives are always detected reliably on the secondary SATA controller on the same board (an ASMedia 106x) without any "softreset failed" errors even without the increased timeout. Fixes: e7d3ef13d52a ("libata: change drive ready wait after hard reset to 5s") Cc: stable@vger.kernel.org Signed-off-by: Matthias Schiffer Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/libata.h b/include/linux/libata.h index c3c50218f6eb..a9ec8d97a715 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -253,7 +253,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 5000, + ATA_TMOUT_PMP_SRST_WAIT = 10000, /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might * be a spurious PHY event, so ignore the first PHY event that From 69dd84470b4deed45658f2717aef533ec4ceb43d Mon Sep 17 00:00:00 2001 From: Javier Pello Date: Sat, 2 Sep 2023 17:10:39 +0200 Subject: [PATCH 1891/2093] drm/i915/gt: Fix reservation address in ggtt_reserve_guc_top commit b7599d241778d0b10cdf7a5c755aa7db9b83250c upstream. There is an assertion in ggtt_reserve_guc_top that the global GTT is of size at least GUC_GGTT_TOP, which is not the case on a 32-bit platform; see commit 562d55d991b39ce376c492df2f7890fd6a541ffc ("drm/i915/bdw: Only use 2g GGTT for 32b platforms"). If GEM_BUG_ON is enabled, this triggers a BUG(); if GEM_BUG_ON is disabled, the subsequent reservation fails and the driver fails to initialise the device: i915 0000:00:02.0: [drm:i915_init_ggtt [i915]] Failed to reserve top of GGTT for GuC i915 0000:00:02.0: Device initialization failed (-28) i915 0000:00:02.0: Please file a bug on drm/i915; see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details. i915: probe of 0000:00:02.0 failed with error -28 Make the reservation at the top of the available space, whatever that is, instead of assuming that the top will be GUC_GGTT_TOP. Fixes: 911800765ef6 ("drm/i915/uc: Reserve upper range of GGTT") Link: https://gitlab.freedesktop.org/drm/intel/-/issues/9080 Signed-off-by: Javier Pello Reviewed-by: Daniele Ceraolo Spurio Cc: Fernando Pacheco Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Cc: intel-gfx@lists.freedesktop.org Cc: stable@vger.kernel.org # v5.3+ Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20230902171039.2229126186d697dbcf62d6d8@otheo.eu (cherry picked from commit 0f3fa942d91165c2702577e9274d2ee1c7212afc) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/intel_ggtt.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 2049a00417af..a6d0463b18d9 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -500,20 +500,31 @@ void intel_ggtt_unbind_vma(struct i915_address_space *vm, vm->clear_range(vm, vma_res->start, vma_res->vma_size); } +/* + * Reserve the top of the GuC address space for firmware images. Addresses + * beyond GUC_GGTT_TOP in the GuC address space are inaccessible by GuC, + * which makes for a suitable range to hold GuC/HuC firmware images if the + * size of the GGTT is 4G. However, on a 32-bit platform the size of the GGTT + * is limited to 2G, which is less than GUC_GGTT_TOP, but we reserve a chunk + * of the same size anyway, which is far more than needed, to keep the logic + * in uc_fw_ggtt_offset() simple. + */ +#define GUC_TOP_RESERVE_SIZE (SZ_4G - GUC_GGTT_TOP) + static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt) { - u64 size; + u64 offset; int ret; if (!intel_uc_uses_guc(&ggtt->vm.gt->uc)) return 0; - GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP); - size = ggtt->vm.total - GUC_GGTT_TOP; + GEM_BUG_ON(ggtt->vm.total <= GUC_TOP_RESERVE_SIZE); + offset = ggtt->vm.total - GUC_TOP_RESERVE_SIZE; - ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, size, - GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE, - PIN_NOEVICT); + ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, + GUC_TOP_RESERVE_SIZE, offset, + I915_COLOR_UNEVICTABLE, PIN_NOEVICT); if (ret) drm_dbg(&ggtt->vm.i915->drm, "Failed to reserve top of GGTT for GuC\n"); From c038ebffbb4811ee7d13c208e685ced5da98f2f4 Mon Sep 17 00:00:00 2001 From: Nicolas Frattaroli Date: Mon, 12 Jun 2023 16:36:52 +0200 Subject: [PATCH 1892/2093] power: supply: rk817: Add missing module alias commit cbcdfbf5a6cd66e47e5ee5d49c4c5a27a07ba082 upstream. Similar to the rk817 codec alias that was missing, the rk817 charger driver is missing a module alias as well. This absence prevents the driver from autoprobing on OF systems when it is built as a module. Add the right MODULE_ALIAS to fix this. Fixes: 11cb8da0189b ("power: supply: Add charger driver for Rockchip RK817") Cc: stable@vger.kernel.org Signed-off-by: Nicolas Frattaroli Reviewed-by: Chris Morgan Link: https://lore.kernel.org/r/20230612143651.959646-2-frattaroli.nicolas@gmail.com Signed-off-by: Sebastian Reichel Signed-off-by: Greg Kroah-Hartman --- drivers/power/supply/rk817_charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index e30ef601d91d..c04b96edcf59 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -1233,3 +1233,4 @@ MODULE_DESCRIPTION("Battery power supply driver for RK817 PMIC"); MODULE_AUTHOR("Maya Matuszczyk "); MODULE_AUTHOR("Chris Morgan "); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:rk817-charger"); From 69e61ee8ea8abd573e4b58df80a7f5249e18299c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 13 Jun 2023 23:31:50 +0200 Subject: [PATCH 1893/2093] power: supply: ab8500: Set typing and props commit dc77721ea4aa1e8937e2436f230b5a69065cc508 upstream. I had the following weird phenomena on a mobile phone: while the capacity in /sys/class/power_supply/ab8500_fg/capacity would reflect the actual charge and capacity of the battery, only 1/3 of the value was shown on the battery status indicator and warnings for low battery appeared. It turns out that UPower, the Freedesktop power daemon, will average all the power supplies of type "battery" in /sys/class/power_supply/* if there is more than one battery. For the AB8500, there was "battery" ab8500_fg, ab8500_btemp and ab8500_chargalg. The latter two don't know anything about the battery, and should not be considered. They were however averaged and with the capacity of 0. Flag ab8500_btemp and ab8500_chargalg with type "unknown" so they are not averaged as batteries. Remove the technology prop from ab8500_btemp as well, all it does is snoop in on knowledge from another supply. After this the battery indicator shows the right value. Cc: Stefan Hansson Cc: stable@vger.kernel.org Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel Signed-off-by: Greg Kroah-Hartman --- drivers/power/supply/ab8500_btemp.c | 9 +-------- drivers/power/supply/ab8500_chargalg.c | 2 +- 2 files changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 6f83e99d2eb7..ce36d6ca3422 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -115,7 +115,6 @@ struct ab8500_btemp { static enum power_supply_property ab8500_btemp_props[] = { POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_ONLINE, - POWER_SUPPLY_PROP_TECHNOLOGY, POWER_SUPPLY_PROP_TEMP, }; @@ -532,12 +531,6 @@ static int ab8500_btemp_get_property(struct power_supply *psy, else val->intval = 1; break; - case POWER_SUPPLY_PROP_TECHNOLOGY: - if (di->bm->bi) - val->intval = di->bm->bi->technology; - else - val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN; - break; case POWER_SUPPLY_PROP_TEMP: val->intval = ab8500_btemp_get_temp(di); break; @@ -662,7 +655,7 @@ static char *supply_interface[] = { static const struct power_supply_desc ab8500_btemp_desc = { .name = "ab8500_btemp", - .type = POWER_SUPPLY_TYPE_BATTERY, + .type = POWER_SUPPLY_TYPE_UNKNOWN, .properties = ab8500_btemp_props, .num_properties = ARRAY_SIZE(ab8500_btemp_props), .get_property = ab8500_btemp_get_property, diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c index ea4ad61d4c7e..2205ea0834a6 100644 --- a/drivers/power/supply/ab8500_chargalg.c +++ b/drivers/power/supply/ab8500_chargalg.c @@ -1720,7 +1720,7 @@ static char *supply_interface[] = { static const struct power_supply_desc ab8500_chargalg_desc = { .name = "ab8500_chargalg", - .type = POWER_SUPPLY_TYPE_BATTERY, + .type = POWER_SUPPLY_TYPE_UNKNOWN, .properties = ab8500_chargalg_props, .num_properties = ARRAY_SIZE(ab8500_chargalg_props), .get_property = ab8500_chargalg_get_property, From 48a22f13fb1b16dd56280f6fe8dccc8b68600af9 Mon Sep 17 00:00:00 2001 From: Greg Ungerer Date: Thu, 7 Sep 2023 11:18:08 +1000 Subject: [PATCH 1894/2093] fs: binfmt_elf_efpic: fix personality for ELF-FDPIC commit 7c3151585730b7095287be8162b846d31e6eee61 upstream. The elf-fdpic loader hard sets the process personality to either PER_LINUX_FDPIC for true elf-fdpic binaries or to PER_LINUX for normal ELF binaries (in this case they would be constant displacement compiled with -pie for example). The problem with that is that it will lose any other bits that may be in the ELF header personality (such as the "bug emulation" bits). On the ARM architecture the ADDR_LIMIT_32BIT flag is used to signify a normal 32bit binary - as opposed to a legacy 26bit address binary. This matters since start_thread() will set the ARM CPSR register as required based on this flag. If the elf-fdpic loader loses this bit the process will be mis-configured and crash out pretty quickly. Modify elf-fdpic loader personality setting so that it preserves the upper three bytes by using the SET_PERSONALITY macro to set it. This macro in the generic case sets PER_LINUX and preserves the upper bytes. Architectures can override this for their specific use case, and ARM does exactly this. The problem shows up quite easily running under qemu using the ARM architecture, but not necessarily on all types of real ARM hardware. If the underlying ARM processor does not support the legacy 26-bit addressing mode then everything will work as expected. Link: https://lkml.kernel.org/r/20230907011808.2985083-1-gerg@kernel.org Fixes: 1bde925d23547 ("fs/binfmt_elf_fdpic.c: provide NOMMU loader for regular ELF binaries") Signed-off-by: Greg Ungerer Cc: Al Viro Cc: Christian Brauner Cc: Eric W. Biederman Cc: Greg Ungerer Cc: Kees Cook Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/binfmt_elf_fdpic.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 069f12cc7634..2aecd4ffb13b 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -345,10 +345,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ + SET_PERSONALITY(exec_params.hdr); if (elf_check_fdpic(&exec_params.hdr)) - set_personality(PER_LINUX_FDPIC); - else - set_personality(PER_LINUX); + current->personality |= PER_LINUX_FDPIC; if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; From b60028c81e463b0930191a4fa2ba770ff6d40e3a Mon Sep 17 00:00:00 2001 From: YuBiao Wang Date: Fri, 15 Sep 2023 10:47:50 +0800 Subject: [PATCH 1895/2093] drm/amdkfd: Use gpu_offset for user queue's wptr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit cc39f9ccb82426e576734b493e1777ea01b144a8 upstream. Directly use tbo's start address will miss the domain start offset. Need to use gpu_offset instead. Signed-off-by: YuBiao Wang Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index c06ada0844ba..0b87034d9dd5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -201,7 +201,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (q->wptr_bo) { wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1); - queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off; + queue_input.wptr_mc_addr = amdgpu_bo_gpu_offset(q->wptr_bo) + wptr_addr_off; } queue_input.is_kfd_process = 1; From ee335e0094add7fc2c7034e0534e1920d61d2078 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 14 Sep 2023 16:10:15 +0300 Subject: [PATCH 1896/2093] drm/meson: fix memory leak on ->hpd_notify callback commit 099f0af9d98231bb74956ce92508e87cbcb896be upstream. The EDID returned by drm_bridge_get_edid() needs to be freed. Fixes: 0af5e0b41110 ("drm/meson: encoder_hdmi: switch to bridge DRM_BRIDGE_ATTACH_NO_CONNECTOR") Cc: Neil Armstrong Cc: Sam Ravnborg Cc: Martin Blumenstingl Cc: Neil Armstrong Cc: Kevin Hilman Cc: Jerome Brunet Cc: dri-devel@lists.freedesktop.org Cc: linux-amlogic@lists.infradead.org Cc: linux-arm-kernel@lists.infradead.org Cc: stable@vger.kernel.org # v5.17+ Signed-off-by: Jani Nikula Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230914131015.2472029-1-jani.nikula@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/meson/meson_encoder_hdmi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 53231bfdf7e2..b14e6e507c61 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -332,6 +332,8 @@ static void meson_encoder_hdmi_hpd_notify(struct drm_bridge *bridge, return; cec_notifier_set_phys_addr_from_edid(encoder_hdmi->cec_notifier, edid); + + kfree(edid); } else cec_notifier_phys_addr_invalidate(encoder_hdmi->cec_notifier); } From b8901b6c2e9bf7f9c18af447942468a51ba6bf5f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 4 Jul 2023 13:52:40 +0200 Subject: [PATCH 1897/2093] memcg: drop kmem.limit_in_bytes commit 86327e8eb94c52eca4f93cfece2e29d1bf52acbf upstream. kmem.limit_in_bytes (v1 way to limit kernel memory usage) has been deprecated since 58056f77502f ("memcg, kmem: further deprecate kmem.limit_in_bytes") merged in 5.16. We haven't heard about any serious users since then but it seems that the mere presence of the file is causing more harm thatn good. We (SUSE) have had several bug reports from customers where Docker based containers started to fail because a write to kmem.limit_in_bytes has failed. This was unexpected because runc code only expects ENOENT (kmem disabled) or EBUSY (tasks already running within cgroup). So a new error code was unexpected and the whole container startup failed. This has been later addressed by https://github.com/opencontainers/runc/commit/52390d68040637dfc77f9fda6bbe70952423d380 so current Docker runtimes do not suffer from the problem anymore. There are still older version of Docker in use and likely hard to get rid of completely. Address this by wiping out the file completely and effectively get back to pre 4.5 era and CONFIG_MEMCG_KMEM=n configuration. I would recommend backporting to stable trees which have picked up 58056f77502f ("memcg, kmem: further deprecate kmem.limit_in_bytes"). [mhocko@suse.com: restore _KMEM switch case] Link: https://lkml.kernel.org/r/ZKe5wxdbvPi5Cwd7@dhcp22.suse.cz Link: https://lkml.kernel.org/r/20230704115240.14672-1-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Roman Gushchin Cc: Muchun Song Cc: Tejun Heo Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cgroup-v1/memory.rst | 2 -- mm/memcontrol.c | 10 ---------- 2 files changed, 12 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 2524061836ac..34911ce5e4b5 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -91,8 +91,6 @@ Brief summary of control files. memory.oom_control set/show oom controls. memory.numa_stat show the number of memory usage per numa node - memory.kmem.limit_in_bytes This knob is deprecated and writing to - it will return -ENOTSUPP. memory.kmem.usage_in_bytes show current kernel memory allocation memory.kmem.failcnt show the number of kernel memory usage hits limits diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9ffcf80cf252..15f44cf4f939 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3841,10 +3841,6 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, case _MEMSWAP: ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; - case _KMEM: - /* kmem.limit_in_bytes is deprecated. */ - ret = -EOPNOTSUPP; - break; case _TCP: ret = memcg_update_tcp_max(memcg, nr_pages); break; @@ -5055,12 +5051,6 @@ static struct cftype mem_cgroup_legacy_files[] = { .seq_show = memcg_numa_stat_show, }, #endif - { - .name = "kmem.limit_in_bytes", - .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), From a3c1da44835357f67f2d4d2c2e11f4c8e7618ad4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 21 Sep 2023 09:38:29 +0200 Subject: [PATCH 1898/2093] mm, memcg: reconsider kmem.limit_in_bytes deprecation commit 4597648fddeadef5877610d693af11906aa666ac upstream. This reverts commits 86327e8eb94c ("memcg: drop kmem.limit_in_bytes") and partially reverts 58056f77502f ("memcg, kmem: further deprecate kmem.limit_in_bytes") which have incrementally removed support for the kernel memory accounting hard limit. Unfortunately it has turned out that there is still userspace depending on the existence of memory.kmem.limit_in_bytes [1]. The underlying functionality is not really required but the non-existent file just confuses the userspace which fails in the result. The patch to fix this on the userspace side has been submitted but it is hard to predict how it will propagate through the maze of 3rd party consumers of the software. Now, reverting alone 86327e8eb94c is not an option because there is another set of userspace which cannot cope with ENOTSUPP returned when writing to the file. Therefore we have to go and revisit 58056f77502f as well. There are two ways to go ahead. Either we give up on the deprecation and fully revert 58056f77502f as well or we can keep kmem.limit_in_bytes but make the write a noop and warn about the fact. This should work for both known breaking workloads which depend on the existence but do not depend on the hard limit enforcement. Note to backporters to stable trees. a8c49af3be5f ("memcg: add per-memcg total kernel memory stat") introduced in 4.18 has added memcg_account_kmem so the accounting is not done by obj_cgroup_charge_pages directly for v1 anymore. Prior kernels need to add it explicitly (thanks to Johannes for pointing this out). [akpm@linux-foundation.org: fix build - remove unused local] Link: http://lkml.kernel.org/r/20230920081101.GA12096@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net [1] Link: https://lkml.kernel.org/r/ZRE5VJozPZt9bRPy@dhcp22.suse.cz Fixes: 86327e8eb94c ("memcg: drop kmem.limit_in_bytes") Fixes: 58056f77502f ("memcg, kmem: further deprecate kmem.limit_in_bytes") Signed-off-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Greg Kroah-Hartman Cc: Jeremi Piotrowski Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun heo Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cgroup-v1/memory.rst | 7 +++++++ mm/memcontrol.c | 13 +++++++++++++ 2 files changed, 20 insertions(+) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 34911ce5e4b5..40164f2881e1 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -91,6 +91,13 @@ Brief summary of control files. memory.oom_control set/show oom controls. memory.numa_stat show the number of memory usage per numa node + memory.kmem.limit_in_bytes Deprecated knob to set and read the kernel + memory hard limit. Kernel hard limit is not + supported since 5.16. Writing any value to + do file will not have any effect same as if + nokmem kernel parameter was specified. + Kernel memory is still charged and reported + by memory.kmem.usage_in_bytes. memory.kmem.usage_in_bytes show current kernel memory allocation memory.kmem.failcnt show the number of kernel memory usage hits limits diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 15f44cf4f939..dacbaf4f7b2c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3841,6 +3841,13 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, case _MEMSWAP: ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; + case _KMEM: + pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. " + "Writing any value to this file has no effect. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + ret = 0; + break; case _TCP: ret = memcg_update_tcp_max(memcg, nr_pages); break; @@ -5051,6 +5058,12 @@ static struct cftype mem_cgroup_legacy_files[] = { .seq_show = memcg_numa_stat_show, }, #endif + { + .name = "kmem.limit_in_bytes", + .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), From 8c515d4f2d668c1a3ba43b2d219be237087b7380 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 6 Sep 2023 13:22:57 -0500 Subject: [PATCH 1899/2093] ASoC: amd: yc: Fix a non-functional mic on Lenovo 82TL commit cfff2a7794d23b03a3ddedd318bf1df1876c598f upstream. Lenovo 82TL has DMIC connected like 82V2 does. Also match 82TL. Reported-by: wildjim@kiwinet.org Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217063 Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230906182257.45736-1-mario.limonciello@amd.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/amd/yc/acp6x-mach.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 2ee741ac25f4..533250efcbd8 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -213,6 +213,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "21J6"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82TL"), + } + }, { .driver_data = &acp6x_card, .matches = { From ecda77b46871007ab0e6c671fe9df5795dd8154a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 6 Oct 2023 14:57:07 +0200 Subject: [PATCH 1900/2093] Linux 6.1.56 Link: https://lore.kernel.org/r/20231004175217.404851126@linuxfoundation.org Tested-by: Salvatore Bonaccorso Tested-by: Shuah Khan Tested-by: SeongJae Park Tested-by: Bagas Sanjaya Tested-by: Pavel Machek (CIP) Tested-by: Takeshi Ogasawara Tested-by: Allen Pais Tested-by: Ron Economos Tested-by: Jon Hunter Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3d839824a722..9ceda3dad5eb 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 55 +SUBLEVEL = 56 EXTRAVERSION = NAME = Curry Ramen From 1031f68108ea612bb6bafb948b8228339ce73547 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 22 Jun 2023 10:24:35 +0200 Subject: [PATCH 1901/2093] spi: zynqmp-gqspi: fix clock imbalance on probe failure [ Upstream commit 1527b076ae2cb6a9c590a02725ed39399fcad1cf ] Make sure that the device is not runtime suspended before explicitly disabling the clocks on probe failure and on driver unbind to avoid a clock enable-count imbalance. Fixes: 9e3a000362ae ("spi: zynqmp: Add pm runtime support") Cc: stable@vger.kernel.org # 4.19 Cc: Naga Sureshkumar Relli Cc: Shubhrajyoti Datta Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/Message-Id: <20230622082435.7873-1-johan+linaro@kernel.org> Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-zynqmp-gqspi.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c index c760aac070e5..3b56d5e7080e 100644 --- a/drivers/spi/spi-zynqmp-gqspi.c +++ b/drivers/spi/spi-zynqmp-gqspi.c @@ -1218,9 +1218,9 @@ static int zynqmp_qspi_probe(struct platform_device *pdev) return 0; clk_dis_all: - pm_runtime_put_sync(&pdev->dev); - pm_runtime_set_suspended(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); clk_disable_unprepare(xqspi->refclk); clk_dis_pclk: clk_disable_unprepare(xqspi->pclk); @@ -1244,11 +1244,15 @@ static int zynqmp_qspi_remove(struct platform_device *pdev) { struct zynqmp_qspi *xqspi = platform_get_drvdata(pdev); + pm_runtime_get_sync(&pdev->dev); + zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, 0x0); + + pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); clk_disable_unprepare(xqspi->refclk); clk_disable_unprepare(xqspi->pclk); - pm_runtime_set_suspended(&pdev->dev); - pm_runtime_disable(&pdev->dev); return 0; } From 5f9d73761553364654080bfa76244abb6b682bfe Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Thu, 7 Sep 2023 20:32:24 +0530 Subject: [PATCH 1902/2093] ASoC: soc-utils: Export snd_soc_dai_is_dummy() symbol [ Upstream commit f101583fa9f8c3f372d4feb61d67da0ccbf4d9a5 ] Export symbol snd_soc_dai_is_dummy() for usage outside core driver modules. This is required by Tegra ASoC machine driver. Signed-off-by: Sameer Pujar Link: https://lore.kernel.org/r/1694098945-32760-2-git-send-email-spujar@nvidia.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/soc-utils.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c index a4dba0b751e7..1bbd1d077dfd 100644 --- a/sound/soc/soc-utils.c +++ b/sound/soc/soc-utils.c @@ -217,6 +217,7 @@ int snd_soc_dai_is_dummy(struct snd_soc_dai *dai) return 1; return 0; } +EXPORT_SYMBOL_GPL(snd_soc_dai_is_dummy); int snd_soc_component_is_dummy(struct snd_soc_component *component) { From bbdfef76096d592a9474fdbcda8903df467e4b7c Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Thu, 7 Sep 2023 20:32:25 +0530 Subject: [PATCH 1903/2093] ASoC: tegra: Fix redundant PLLA and PLLA_OUT0 updates [ Upstream commit e765886249c533e1bb5cbc3cd741bad677417312 ] Tegra audio graph card has many DAI links which connects internal AHUB modules and external audio codecs. Since these are DPCM links, hw_params() call in the machine driver happens for each connected BE link and PLLA is updated every time. This is not really needed for all links as only I/O link DAIs derive respective clocks from PLLA_OUT0 and thus from PLLA. Hence add checks to limit the clock updates to DAIs over I/O links. This found to be fixing a DMIC clock discrepancy which is suspected to happen because of back to back quick PLLA and PLLA_OUT0 rate updates. This was observed on Jetson TX2 platform where DMIC clock ended up with unexpected value. Fixes: 202e2f774543 ("ASoC: tegra: Add audio graph based card driver") Cc: stable@vger.kernel.org Signed-off-by: Sameer Pujar Link: https://lore.kernel.org/r/1694098945-32760-3-git-send-email-spujar@nvidia.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/tegra/tegra_audio_graph_card.c | 30 ++++++++++++++---------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c index 1f2c5018bf5a..4737e776d383 100644 --- a/sound/soc/tegra/tegra_audio_graph_card.c +++ b/sound/soc/tegra/tegra_audio_graph_card.c @@ -10,6 +10,7 @@ #include #include #include +#include #define MAX_PLLA_OUT0_DIV 128 @@ -44,6 +45,21 @@ struct tegra_audio_cdata { unsigned int plla_out0_rates[NUM_RATE_TYPE]; }; +static bool need_clk_update(struct snd_soc_dai *dai) +{ + if (snd_soc_dai_is_dummy(dai) || + !dai->driver->ops || + !dai->driver->name) + return false; + + if (strstr(dai->driver->name, "I2S") || + strstr(dai->driver->name, "DMIC") || + strstr(dai->driver->name, "DSPK")) + return true; + + return false; +} + /* Setup PLL clock as per the given sample rate */ static int tegra_audio_graph_update_pll(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) @@ -140,19 +156,7 @@ static int tegra_audio_graph_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); int err; - /* - * This gets called for each DAI link (FE or BE) when DPCM is used. - * We may not want to update PLLA rate for each call. So PLLA update - * must be restricted to external I/O links (I2S, DMIC or DSPK) since - * they actually depend on it. I/O modules update their clocks in - * hw_param() of their respective component driver and PLLA rate - * update here helps them to derive appropriate rates. - * - * TODO: When more HW accelerators get added (like sample rate - * converter, volume gain controller etc., which don't really - * depend on PLLA) we need a better way to filter here. - */ - if (cpu_dai->driver->ops && rtd->dai_link->no_pcm) { + if (need_clk_update(cpu_dai)) { err = tegra_audio_graph_update_pll(substream, params); if (err) return err; From 7544918e48e6776d2590f5bf829bcbb1786f347b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:48 +0200 Subject: [PATCH 1904/2093] mptcp: rename timer related helper to less confusing names [ Upstream commit f6909dc1c1f4452879278128012da6c76bc186a5 ] The msk socket uses to different timeout to track close related events and retransmissions. The existing helpers do not indicate clearly which timer they actually touch, making the related code quite confusing. Change the existing helpers name to avoid such confusion. No functional change intended. This patch is linked to the next one ("mptcp: fix dangling connection hang-up"). The two patches are supposed to be backported together. Cc: stable@vger.kernel.org # v5.11+ Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller Stable-dep-of: 27e5ccc2d5a5 ("mptcp: fix dangling connection hang-up") Signed-off-by: Sasha Levin --- net/mptcp/protocol.c | 42 +++++++++++++++++++++--------------------- net/mptcp/protocol.h | 2 +- net/mptcp/subflow.c | 2 +- 3 files changed, 23 insertions(+), 23 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 6dd880d6b051..93b60b049be2 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -401,7 +401,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, return false; } -static void mptcp_stop_timer(struct sock *sk) +static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -865,12 +865,12 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list } } -static bool mptcp_timer_pending(struct sock *sk) +static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } -static void mptcp_reset_timer(struct sock *sk) +static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; @@ -1054,10 +1054,10 @@ static void __mptcp_clean_una(struct sock *sk) out: if (snd_una == READ_ONCE(msk->snd_nxt) && snd_una == READ_ONCE(msk->write_seq)) { - if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) - mptcp_stop_timer(sk); + if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) + mptcp_stop_rtx_timer(sk); } else { - mptcp_reset_timer(sk); + mptcp_reset_rtx_timer(sk); } } @@ -1606,8 +1606,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) out: /* ensure the rtx timer is running */ - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } @@ -1665,8 +1665,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) @@ -2227,7 +2227,7 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static void mptcp_timeout_timer(struct timer_list *t) +static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2597,14 +2597,14 @@ static void __mptcp_retrans(struct sock *sk) reset_timer: mptcp_check_and_set_pending(sk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; @@ -2637,7 +2637,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - mptcp_reset_timeout(msk, 0); + mptcp_reset_tout_timer(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2728,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk) /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); - timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); + timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); return 0; } @@ -2820,8 +2820,8 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } break; } @@ -2904,7 +2904,7 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; @@ -3021,7 +3021,7 @@ bool __mptcp_close(struct sock *sk, long timeout) __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_timeout(msk, 0); + mptcp_reset_tout_timer(msk, 0); } return do_cancel_work; @@ -3084,7 +3084,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); if (mptcp_sk(sk)->token) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d77b25636125..b73160c5e2cf 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -681,7 +681,7 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 52a747a80e88..6c8148c6e771 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1161,7 +1161,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) WRITE_ONCE(subflow->fail_tout, fail_tout); tcp_send_ack(ssk); - mptcp_reset_timeout(msk, subflow->fail_tout); + mptcp_reset_tout_timer(msk, subflow->fail_tout); } static bool subflow_check_data_avail(struct sock *ssk) From 09b6fdf7a12e535dc39207b45b42b9bc9b578c75 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:49 +0200 Subject: [PATCH 1905/2093] mptcp: fix dangling connection hang-up [ Upstream commit 27e5ccc2d5a50ed61bb73153edb1066104b108b3 ] According to RFC 8684 section 3.3: A connection is not closed unless [...] or an implementation-specific connection-level send timeout. Currently the MPTCP protocol does not implement such timeout, and connection timing-out at the TCP-level never move to close state. Introduces a catch-up condition at subflow close time to move the MPTCP socket to close, too. That additionally allows removing similar existing inside the worker. Finally, allow some additional timeout for plain ESTABLISHED mptcp sockets, as the protocol allows creating new subflows even at that point and making the connection functional again. This issue is actually present since the beginning, but it is basically impossible to solve without a long chain of functional pre-requisites topped by commit bbd49d114d57 ("mptcp: consolidate transition to TCP_CLOSE in mptcp_do_fastclose()"). When backporting this current patch, please also backport this other commit as well. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/430 Fixes: e16163b6e2b7 ("mptcp: refactor shutdown and close") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/mptcp/protocol.c | 90 ++++++++++++++++++++++---------------------- net/mptcp/protocol.h | 22 +++++++++++ net/mptcp/subflow.c | 1 + 3 files changed, 67 insertions(+), 46 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 93b60b049be2..60e65f6325c3 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -846,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); + mptcp_stop_tout_timer(sk); return true; } @@ -2349,18 +2350,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, bool dispose_it, need_push = false; /* If the first subflow moved to a close state before accept, e.g. due - * to an incoming reset, mptcp either: - * - if either the subflow or the msk are dead, destroy the context - * (the subflow socket is deleted by inet_child_forget) and the msk - * - otherwise do nothing at the moment and take action at accept and/or - * listener shutdown - user-space must be able to accept() the closed - * socket. + * to an incoming reset or listener shutdown, the subflow socket is + * already deleted by inet_child_forget() and the mptcp socket can't + * survive too. */ - if (msk->in_accept_queue && msk->first == ssk) { - if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) - return; - + if (msk->in_accept_queue && msk->first == ssk && + (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ + mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); @@ -2426,6 +2423,22 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (need_push) __mptcp_push_pending(sk, 0); + + /* Catch every 'all subflows closed' scenario, including peers silently + * closing them, e.g. due to timeout. + * For established sockets, allow an additional timeout before closing, + * as the protocol can still create more subflows. + */ + if (list_is_singular(&msk->conn_list) && msk->first && + inet_sk_state_load(msk->first) == TCP_CLOSE) { + if (sk->sk_state != TCP_ESTABLISHED || + msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_close_wake_up(sk); + } else { + mptcp_start_tout_timer(sk); + } + } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2469,23 +2482,14 @@ static void __mptcp_close_subflow(struct sock *sk) } -static bool mptcp_should_close(const struct sock *sk) +static bool mptcp_close_tout_expired(const struct sock *sk) { - s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; - struct mptcp_subflow_context *subflow; + if (!inet_csk(sk)->icsk_mtup.probe_timestamp || + sk->sk_state == TCP_CLOSE) + return false; - if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) - return true; - - /* if all subflows are in closed status don't bother with additional - * timeout - */ - mptcp_for_each_subflow(mptcp_sk(sk), subflow) { - if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) != - TCP_CLOSE) - return false; - } - return true; + return time_after32(tcp_jiffies32, + inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2609,15 +2613,16 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; - if (!fail_tout && !sock_flag(sk, SOCK_DEAD)) + if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; - close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN; + close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + + TCP_TIMEWAIT_LEN; /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ - timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout; + timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &sk->sk_timer, timeout); } @@ -2636,8 +2641,6 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - - mptcp_reset_tout_timer(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2676,19 +2679,15 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); - /* There is no point in keeping around an orphaned sk timedout or - * closed, but we need the msk around to reply to incoming DATA_FIN, - * even if it is orphaned and in FIN_WAIT2 state - */ - if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_should_close(sk)) { - inet_sk_state_store(sk, TCP_CLOSE); - mptcp_do_fastclose(sk); - } - if (sk->sk_state == TCP_CLOSE) { - __mptcp_destroy_sock(sk); - goto unlock; - } + if (mptcp_close_tout_expired(sk)) { + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + mptcp_close_wake_up(sk); + } + + if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { + __mptcp_destroy_sock(sk); + goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) @@ -2984,7 +2983,6 @@ bool __mptcp_close(struct sock *sk, long timeout) cleanup: /* orphan all the subflows */ - inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); @@ -3021,7 +3019,7 @@ bool __mptcp_close(struct sock *sk, long timeout) __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_tout_timer(msk, 0); + mptcp_start_tout_timer(sk); } return do_cancel_work; @@ -3085,7 +3083,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) inet_sk_state_store(sk, TCP_CLOSE); mptcp_stop_rtx_timer(sk); - sk_stop_timer(sk, &sk->sk_timer); + mptcp_stop_tout_timer(sk); if (mptcp_sk(sk)->token) mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b73160c5e2cf..91d89a0aeb58 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -682,6 +682,28 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); + +static inline void mptcp_stop_tout_timer(struct sock *sk) +{ + if (!inet_csk(sk)->icsk_mtup.probe_timestamp) + return; + + sk_stop_timer(sk, &sk->sk_timer); + inet_csk(sk)->icsk_mtup.probe_timestamp = 0; +} + +static inline void mptcp_set_close_tout(struct sock *sk, unsigned long tout) +{ + /* avoid 0 timestamp, as that means no close timeout */ + inet_csk(sk)->icsk_mtup.probe_timestamp = tout ? : 1; +} + +static inline void mptcp_start_tout_timer(struct sock *sk) +{ + mptcp_set_close_tout(sk, tcp_jiffies32); + mptcp_reset_tout_timer(mptcp_sk(sk), 0); +} + static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6c8148c6e771..168dced2434b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1527,6 +1527,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_stop_tout_timer(sk); return 0; failed_unlink: From c1432ece79e682cea66112dfb010e2a1ca3be9d5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 15 Mar 2023 20:57:45 +0000 Subject: [PATCH 1906/2093] mptcp: annotate lockless accesses to sk->sk_err [ Upstream commit 9ae8e5ad99b8ebcd3d3dd46075f3825e6f08f063 ] mptcp_poll() reads sk->sk_err without socket lock held/owned. Add READ_ONCE() and WRITE_ONCE() to avoid load/store tearing. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: d5fbeff1ab81 ("mptcp: move __mptcp_error_report in protocol.c") Signed-off-by: Sasha Levin --- net/mptcp/pm_netlink.c | 2 +- net/mptcp/protocol.c | 8 ++++---- net/mptcp/subflow.c | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9127a7fd5269..5d845fcf3d09 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -2047,7 +2047,7 @@ static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if)) return -EMSGSIZE; - sk_err = ssk->sk_err; + sk_err = READ_ONCE(ssk->sk_err); if (sk_err && sk->sk_state == TCP_ESTABLISHED && nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err)) return -EMSGSIZE; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 60e65f6325c3..84f107854eac 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2517,15 +2517,15 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) /* Mirror the tcp_reset() error propagation */ switch (sk->sk_state) { case TCP_SYN_SENT: - sk->sk_err = ECONNREFUSED; + WRITE_ONCE(sk->sk_err, ECONNREFUSED); break; case TCP_CLOSE_WAIT: - sk->sk_err = EPIPE; + WRITE_ONCE(sk->sk_err, EPIPE); break; case TCP_CLOSE: return; default: - sk->sk_err = ECONNRESET; + WRITE_ONCE(sk->sk_err, ECONNRESET); } inet_sk_state_store(sk, TCP_CLOSE); @@ -3893,7 +3893,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; return mask; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 168dced2434b..032661c8273f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1248,7 +1248,7 @@ static bool subflow_check_data_avail(struct sock *ssk) subflow->reset_reason = MPTCP_RST_EMPTCP; reset: - ssk->sk_err = EBADMSG; + WRITE_ONCE(ssk->sk_err, EBADMSG); tcp_set_state(ssk, TCP_CLOSE); while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); @@ -1332,7 +1332,7 @@ void __mptcp_error_report(struct sock *sk) ssk_state = inet_sk_state_load(ssk); if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) inet_sk_state_store(sk, ssk_state); - sk->sk_err = -err; + WRITE_ONCE(sk->sk_err, -err); /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); From fc8917b79069710bd6943d7f35e31e1d52f49944 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:46 +0200 Subject: [PATCH 1907/2093] mptcp: move __mptcp_error_report in protocol.c [ Upstream commit d5fbeff1ab812b6c473b6924bee8748469462e2c ] This will simplify the next patch ("mptcp: process pending subflow error on close"). No functional change intended. Cc: stable@vger.kernel.org # v5.12+ Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/mptcp/protocol.c | 36 ++++++++++++++++++++++++++++++++++++ net/mptcp/subflow.c | 36 ------------------------------------ 2 files changed, 36 insertions(+), 36 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 84f107854eac..193f2bdc8fe1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -765,6 +765,42 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } +void __mptcp_error_report(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err = sock_error(ssk); + int ssk_state; + + if (!err) + continue; + + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) + continue; + + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); + + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + break; + } +} + /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 032661c8273f..b93b08a75017 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1305,42 +1305,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); } -void __mptcp_error_report(struct sock *sk) -{ - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; - - if (!err) - continue; - - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; - - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } -} - static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; From 078651647064b4f5b04e8ea2d16ce6b018a346d1 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:47 +0200 Subject: [PATCH 1908/2093] mptcp: process pending subflow error on close [ Upstream commit 9f1a98813b4b686482e5ef3c9d998581cace0ba6 ] On incoming TCP reset, subflow closing could happen before error propagation. That in turn could cause the socket error being ignored, and a missing socket state transition, as reported by Daire-Byrne. Address the issues explicitly checking for subflow socket error at close time. To avoid code duplication, factor-out of __mptcp_error_report() a new helper implementing the relevant bits. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/429 Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/mptcp/protocol.c | 63 ++++++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 29 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 193f2bdc8fe1..b6e0579e7264 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -765,40 +765,44 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } +static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) +{ + int err = sock_error(ssk); + int ssk_state; + + if (!err) + return false; + + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) + return false; + + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); + + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + return true; +} + void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; - - if (!err) - continue; - - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; - - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } + mptcp_for_each_subflow(msk, subflow) + if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) + break; } /* In most cases we will be able to lock the mptcp socket. If its already @@ -2446,6 +2450,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } out_release: + __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); From dc3354c961badffc24117390ed2d4d12988d171b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 24 Jul 2023 13:23:14 +0900 Subject: [PATCH 1909/2093] ata,scsi: do not issue START STOP UNIT on resume [ Upstream commit 0a8589055936d8feb56477123a8373ac634018fa ] During system resume, ata_port_pm_resume() triggers ata EH to 1) Resume the controller 2) Reset and rescan the ports 3) Revalidate devices This EH execution is started asynchronously from ata_port_pm_resume(), which means that when sd_resume() is executed, none or only part of the above processing may have been executed. However, sd_resume() issues a START STOP UNIT to wake up the drive from sleep mode. This command is translated to ATA with ata_scsi_start_stop_xlat() and issued to the device. However, depending on the state of execution of the EH process and revalidation triggerred by ata_port_pm_resume(), two things may happen: 1) The START STOP UNIT fails if it is received before the controller has been reenabled at the beginning of the EH execution. This is visible with error messages like: ata10.00: device reported invalid CHS sector 0 sd 9:0:0:0: [sdc] Start/Stop Unit failed: Result: hostbyte=DID_OK driverbyte=DRIVER_OK sd 9:0:0:0: [sdc] Sense Key : Illegal Request [current] sd 9:0:0:0: [sdc] Add. Sense: Unaligned write command sd 9:0:0:0: PM: dpm_run_callback(): scsi_bus_resume+0x0/0x90 returns -5 sd 9:0:0:0: PM: failed to resume async: error -5 2) The START STOP UNIT command is received while the EH process is on-going, which mean that it is stopped and must wait for its completion, at which point the command is rather useless as the drive is already fully spun up already. This case results also in a significant delay in sd_resume() which is observable by users as the entire system resume completion is delayed. Given that ATA devices will be woken up by libata activity on resume, sd_resume() has no need to issue a START STOP UNIT command, which solves the above mentioned problems. Do not issue this command by introducing the new scsi_device flag no_start_on_resume and setting this flag to 1 in ata_scsi_dev_config(). sd_resume() is modified to issue a START STOP UNIT command only if this flag is not set. Reported-by: Paul Ausbeck Closes: https://bugzilla.kernel.org/show_bug.cgi?id=215880 Fixes: a19a93e4c6a9 ("scsi: core: pm: Rely on the device driver core for async power management") Signed-off-by: Damien Le Moal Tested-by: Tanner Watkins Tested-by: Paul Ausbeck Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Stable-dep-of: 99398d2070ab ("scsi: sd: Do not issue commands to suspended disks on shutdown") Signed-off-by: Sasha Levin --- drivers/ata/libata-scsi.c | 7 +++++++ drivers/scsi/sd.c | 9 ++++++--- include/scsi/scsi_device.h | 1 + 3 files changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d28628b964e2..9c8dd9f86cbb 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1081,7 +1081,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) } } else { sdev->sector_size = ata_id_logical_sector_size(dev->id); + /* + * Stop the drive on suspend but do not issue START STOP UNIT + * on resume as this is not necessary and may fail: the device + * will be woken up by ata_port_pm_resume() with a port reset + * and device revalidation. + */ sdev->manage_start_stop = 1; + sdev->no_start_on_resume = 1; } /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e934779bf05c..5bfca4941511 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3718,7 +3718,7 @@ static int sd_suspend_runtime(struct device *dev) static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret; + int ret = 0; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; @@ -3726,8 +3726,11 @@ static int sd_resume(struct device *dev) if (!sdkp->device->manage_start_stop) return 0; - sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); - ret = sd_start_stop_device(sdkp, 1); + if (!sdkp->device->no_start_on_resume) { + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + ret = sd_start_stop_device(sdkp, 1); + } + if (!ret) opal_unlock_from_suspend(sdkp->opal_dev); return ret; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 006858ed04e8..9fdc77db3a2a 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -193,6 +193,7 @@ struct scsi_device { unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */ + unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */ unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */ unsigned no_uld_attach:1; /* disable connecting to upper level drivers */ unsigned select_no_atn:1; From 8de6d8449ae959cfea0b20bd7a1cae1041d15a0d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 15 Sep 2023 10:02:41 +0900 Subject: [PATCH 1910/2093] scsi: sd: Differentiate system and runtime start/stop management [ Upstream commit 3cc2ffe5c16dc65dfac354bc5b5bc98d3b397567 ] The underlying device and driver of a SCSI disk may have different system and runtime power mode control requirements. This is because runtime power management affects only the SCSI disk, while system level power management affects all devices, including the controller for the SCSI disk. For instance, issuing a START STOP UNIT command when a SCSI disk is runtime suspended and resumed is fine: the command is translated to a STANDBY IMMEDIATE command to spin down the ATA disk and to a VERIFY command to wake it up. The SCSI disk runtime operations have no effect on the ata port device used to connect the ATA disk. However, for system suspend/resume operations, the ATA port used to connect the device will also be suspended and resumed, with the resume operation requiring re-validating the device link and the device itself. In this case, issuing a VERIFY command to spinup the disk must be done before starting to revalidate the device, when the ata port is being resumed. In such case, we must not allow the SCSI disk driver to issue START STOP UNIT commands. Allow a low level driver to refine the SCSI disk start/stop management by differentiating system and runtime cases with two new SCSI device flags: manage_system_start_stop and manage_runtime_start_stop. These new flags replace the current manage_start_stop flag. Drivers setting the manage_start_stop are modifed to set both new flags, thus preserving the existing start/stop management behavior. For backward compatibility, the old manage_start_stop sysfs device attribute is kept as a read-only attribute showing a value of 1 for devices enabling both new flags and 0 otherwise. Fixes: 0a8589055936 ("ata,scsi: do not issue START STOP UNIT on resume") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Stable-dep-of: 99398d2070ab ("scsi: sd: Do not issue commands to suspended disks on shutdown") Signed-off-by: Sasha Levin --- drivers/ata/libata-scsi.c | 3 +- drivers/firewire/sbp2.c | 9 ++-- drivers/scsi/sd.c | 90 ++++++++++++++++++++++++++++++-------- include/scsi/scsi_device.h | 5 ++- 4 files changed, 84 insertions(+), 23 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 9c8dd9f86cbb..8cc8268327f0 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1087,7 +1087,8 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) * will be woken up by ata_port_pm_resume() with a port reset * and device revalidation. */ - sdev->manage_start_stop = 1; + sdev->manage_system_start_stop = true; + sdev->manage_runtime_start_stop = true; sdev->no_start_on_resume = 1; } diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 60051c0cabea..e322a326546b 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -81,7 +81,8 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device " * * - power condition * Set the power condition field in the START STOP UNIT commands sent by - * sd_mod on suspend, resume, and shutdown (if manage_start_stop is on). + * sd_mod on suspend, resume, and shutdown (if manage_system_start_stop or + * manage_runtime_start_stop is on). * Some disks need this to spin down or to resume properly. * * - override internal blacklist @@ -1517,8 +1518,10 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->use_10_for_rw = 1; - if (sbp2_param_exclusive_login) - sdev->manage_start_stop = 1; + if (sbp2_param_exclusive_login) { + sdev->manage_system_start_stop = true; + sdev->manage_runtime_start_stop = true; + } if (sdev->type == TYPE_ROM) sdev->use_10_for_ms = 1; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 5bfca4941511..2ed57dfaf9ee 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -213,18 +213,32 @@ cache_type_store(struct device *dev, struct device_attribute *attr, } static ssize_t -manage_start_stop_show(struct device *dev, struct device_attribute *attr, - char *buf) +manage_start_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; - return sprintf(buf, "%u\n", sdp->manage_start_stop); + return sysfs_emit(buf, "%u\n", + sdp->manage_system_start_stop && + sdp->manage_runtime_start_stop); +} +static DEVICE_ATTR_RO(manage_start_stop); + +static ssize_t +manage_system_start_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + return sysfs_emit(buf, "%u\n", sdp->manage_system_start_stop); } static ssize_t -manage_start_stop_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +manage_system_start_stop_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; @@ -236,11 +250,42 @@ manage_start_stop_store(struct device *dev, struct device_attribute *attr, if (kstrtobool(buf, &v)) return -EINVAL; - sdp->manage_start_stop = v; + sdp->manage_system_start_stop = v; return count; } -static DEVICE_ATTR_RW(manage_start_stop); +static DEVICE_ATTR_RW(manage_system_start_stop); + +static ssize_t +manage_runtime_start_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + return sysfs_emit(buf, "%u\n", sdp->manage_runtime_start_stop); +} + +static ssize_t +manage_runtime_start_stop_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + bool v; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->manage_runtime_start_stop = v; + + return count; +} +static DEVICE_ATTR_RW(manage_runtime_start_stop); static ssize_t allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -572,6 +617,8 @@ static struct attribute *sd_disk_attrs[] = { &dev_attr_FUA.attr, &dev_attr_allow_restart.attr, &dev_attr_manage_start_stop.attr, + &dev_attr_manage_system_start_stop.attr, + &dev_attr_manage_runtime_start_stop.attr, &dev_attr_protection_type.attr, &dev_attr_protection_mode.attr, &dev_attr_app_tag_own.attr, @@ -3652,13 +3699,20 @@ static void sd_shutdown(struct device *dev) sd_sync_cache(sdkp, NULL); } - if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) { + if (system_state != SYSTEM_RESTART && + sdkp->device->manage_system_start_stop) { sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } } -static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) +static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime) +{ + return (sdev->manage_system_start_stop && !runtime) || + (sdev->manage_runtime_start_stop && runtime); +} + +static int sd_suspend_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); struct scsi_sense_hdr sshdr; @@ -3690,12 +3744,12 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) } } - if (sdkp->device->manage_start_stop) { + if (sd_do_start_stop(sdkp->device, runtime)) { if (!sdkp->device->silence_suspend) sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); /* an error is not worth aborting a system sleep */ ret = sd_start_stop_device(sdkp, 0); - if (ignore_stop_errors) + if (!runtime) ret = 0; } @@ -3707,23 +3761,23 @@ static int sd_suspend_system(struct device *dev) if (pm_runtime_suspended(dev)) return 0; - return sd_suspend_common(dev, true); + return sd_suspend_common(dev, false); } static int sd_suspend_runtime(struct device *dev) { - return sd_suspend_common(dev, false); + return sd_suspend_common(dev, true); } -static int sd_resume(struct device *dev) +static int sd_resume(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret = 0; + int ret; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; - if (!sdkp->device->manage_start_stop) + if (!sd_do_start_stop(sdkp->device, runtime)) return 0; if (!sdkp->device->no_start_on_resume) { @@ -3741,7 +3795,7 @@ static int sd_resume_system(struct device *dev) if (pm_runtime_suspended(dev)) return 0; - return sd_resume(dev); + return sd_resume(dev, false); } static int sd_resume_runtime(struct device *dev) @@ -3765,7 +3819,7 @@ static int sd_resume_runtime(struct device *dev) "Failed to clear sense data\n"); } - return sd_resume(dev); + return sd_resume(dev, true); } /** diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 9fdc77db3a2a..dc2cff18b68b 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -161,6 +161,10 @@ struct scsi_device { * pass settings from slave_alloc to scsi * core. */ unsigned int eh_timeout; /* Error handling timeout */ + + bool manage_system_start_stop; /* Let HLD (sd) manage system start/stop */ + bool manage_runtime_start_stop; /* Let HLD (sd) manage runtime start/stop */ + unsigned removable:1; unsigned changed:1; /* Data invalid due to media change */ unsigned busy:1; /* Used to prevent races */ @@ -192,7 +196,6 @@ struct scsi_device { unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */ unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ - unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */ unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */ unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */ unsigned no_uld_attach:1; /* disable connecting to upper level drivers */ From deacabef6834e7311e901b1924230af502244e02 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 8 Sep 2023 17:03:15 +0900 Subject: [PATCH 1911/2093] scsi: sd: Do not issue commands to suspended disks on shutdown [ Upstream commit 99398d2070ab03d13f90b758ad397e19a65fffb0 ] If an error occurs when resuming a host adapter before the devices attached to the adapter are resumed, the adapter low level driver may remove the scsi host, resulting in a call to sd_remove() for the disks of the host. This in turn results in a call to sd_shutdown() which will issue a synchronize cache command and a start stop unit command to spindown the disk. sd_shutdown() issues the commands only if the device is not already runtime suspended but does not check the power state for system-wide suspend/resume. That is, the commands may be issued with the device in a suspended state, which causes PM resume to hang, forcing a reset of the machine to recover. Fix this by tracking the suspended state of a disk by introducing the suspended boolean field in the scsi_disk structure. This flag is set to true when the disk is suspended is sd_suspend_common() and resumed with sd_resume(). When suspended is true, sd_shutdown() is not executed from sd_remove(). Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Reviewed-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/sd.c | 17 +++++++++++++---- drivers/scsi/sd.h | 1 + 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 2ed57dfaf9ee..30184f7b762c 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3626,7 +3626,8 @@ static int sd_remove(struct device *dev) device_del(&sdkp->disk_dev); del_gendisk(sdkp->disk); - sd_shutdown(dev); + if (!sdkp->suspended) + sd_shutdown(dev); put_disk(sdkp->disk); return 0; @@ -3753,6 +3754,9 @@ static int sd_suspend_common(struct device *dev, bool runtime) ret = 0; } + if (!ret) + sdkp->suspended = true; + return ret; } @@ -3772,21 +3776,26 @@ static int sd_suspend_runtime(struct device *dev) static int sd_resume(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret; + int ret = 0; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; - if (!sd_do_start_stop(sdkp->device, runtime)) + if (!sd_do_start_stop(sdkp->device, runtime)) { + sdkp->suspended = false; return 0; + } if (!sdkp->device->no_start_on_resume) { sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); } - if (!ret) + if (!ret) { opal_unlock_from_suspend(sdkp->opal_dev); + sdkp->suspended = false; + } + return ret; } diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 5eea762f84d1..409dda5350d1 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -131,6 +131,7 @@ struct scsi_disk { u8 provisioning_mode; u8 zeroing_mode; u8 nr_actuators; /* Number of actuators */ + bool suspended; /* Disk is suspended (stopped) */ unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ From 5d3b0fcb3ca61916616c7290d541a0f8f738ac8e Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 22 Aug 2023 08:30:41 -0700 Subject: [PATCH 1912/2093] scsi: core: Improve type safety of scsi_rescan_device() [ Upstream commit 79519528a180c64a90863db2ce70887de6c49d16 ] Most callers of scsi_rescan_device() have the scsi_device pointer readily available. Pass a struct scsi_device pointer to scsi_rescan_device() instead of a struct device pointer. This change prevents that a pointer to another struct device would be passed accidentally to scsi_rescan_device(). Remove the scsi_rescan_device() declaration from the scsi_priv.h header file since it duplicates the declaration in . Reviewed-by: Hannes Reinecke Reviewed-by: Damien Le Moal Reviewed-by: John Garry Cc: Mike Christie Cc: Ming Lei Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230822153043.4046244-1-bvanassche@acm.org Signed-off-by: Martin K. Petersen Stable-dep-of: 8b4d9469d0b0 ("ata: libata-scsi: Fix delayed scsi_rescan_device() execution") Signed-off-by: Sasha Levin --- drivers/ata/libata-scsi.c | 2 +- drivers/scsi/aacraid/commsup.c | 2 +- drivers/scsi/mvumi.c | 2 +- drivers/scsi/scsi_lib.c | 2 +- drivers/scsi/scsi_priv.h | 1 - drivers/scsi/scsi_scan.c | 4 ++-- drivers/scsi/scsi_sysfs.c | 4 ++-- drivers/scsi/smartpqi/smartpqi_init.c | 2 +- drivers/scsi/storvsc_drv.c | 2 +- drivers/scsi/virtio_scsi.c | 2 +- include/scsi/scsi_host.h | 2 +- 11 files changed, 12 insertions(+), 13 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 8cc8268327f0..b348f77b9123 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4678,7 +4678,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) } spin_unlock_irqrestore(ap->lock, flags); - scsi_rescan_device(&(sdev->sdev_gendev)); + scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); } diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 3f062e4013ab..013a9a334972 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -1451,7 +1451,7 @@ static void aac_handle_aif(struct aac_dev * dev, struct fib * fibptr) #endif break; } - scsi_rescan_device(&device->sdev_gendev); + scsi_rescan_device(device); break; default: diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c index 05d3ce9b72db..c4acf65379d2 100644 --- a/drivers/scsi/mvumi.c +++ b/drivers/scsi/mvumi.c @@ -1500,7 +1500,7 @@ static void mvumi_rescan_devices(struct mvumi_hba *mhba, int id) sdev = scsi_device_lookup(mhba->shost, 0, id, 0); if (sdev) { - scsi_rescan_device(&sdev->sdev_gendev); + scsi_rescan_device(sdev); scsi_device_put(sdev); } } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index fb6e9a7a7f58..d25e1c247253 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2445,7 +2445,7 @@ static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt) envp[idx++] = "SDEV_MEDIA_CHANGE=1"; break; case SDEV_EVT_INQUIRY_CHANGE_REPORTED: - scsi_rescan_device(&sdev->sdev_gendev); + scsi_rescan_device(sdev); envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED"; break; case SDEV_EVT_CAPACITY_CHANGE_REPORTED: diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index c52de9a973e4..b14545acb40f 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -132,7 +132,6 @@ extern int scsi_complete_async_scans(void); extern int scsi_scan_host_selected(struct Scsi_Host *, unsigned int, unsigned int, u64, enum scsi_scan_mode); extern void scsi_forget_host(struct Scsi_Host *); -extern void scsi_rescan_device(struct device *); /* scsi_sysctl.c */ #ifdef CONFIG_SYSCTL diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index d12f2dcb4040..445989f44d3f 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1611,9 +1611,9 @@ int scsi_add_device(struct Scsi_Host *host, uint channel, } EXPORT_SYMBOL(scsi_add_device); -void scsi_rescan_device(struct device *dev) +void scsi_rescan_device(struct scsi_device *sdev) { - struct scsi_device *sdev = to_scsi_device(dev); + struct device *dev = &sdev->sdev_gendev; device_lock(dev); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index cac7c902cf70..1f531063d633 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -762,7 +762,7 @@ static ssize_t store_rescan_field (struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - scsi_rescan_device(dev); + scsi_rescan_device(to_scsi_device(dev)); return count; } static DEVICE_ATTR(rescan, S_IWUSR, NULL, store_rescan_field); @@ -855,7 +855,7 @@ store_state_field(struct device *dev, struct device_attribute *attr, * waiting for pending I/O to finish. */ blk_mq_run_hw_queues(sdev->request_queue, true); - scsi_rescan_device(dev); + scsi_rescan_device(sdev); } return ret == 0 ? count : -EINVAL; diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 9f0f69c1ed66..47d487729635 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -2278,7 +2278,7 @@ static void pqi_update_device_list(struct pqi_ctrl_info *ctrl_info, device->advertised_queue_depth = device->queue_depth; scsi_change_queue_depth(device->sdev, device->advertised_queue_depth); if (device->rescan) { - scsi_rescan_device(&device->sdev->sdev_gendev); + scsi_rescan_device(device->sdev); device->rescan = false; } } diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 7a1dc5c7c49e..c2d981d5a2dd 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -471,7 +471,7 @@ static void storvsc_device_scan(struct work_struct *work) sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun); if (!sdev) goto done; - scsi_rescan_device(&sdev->sdev_gendev); + scsi_rescan_device(sdev); scsi_device_put(sdev); done: diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 2a79ab16134b..3f8c553f3d91 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -325,7 +325,7 @@ static void virtscsi_handle_param_change(struct virtio_scsi *vscsi, /* Handle "Parameters changed", "Mode parameters changed", and "Capacity data has changed". */ if (asc == 0x2a && (ascq == 0x00 || ascq == 0x01 || ascq == 0x09)) - scsi_rescan_device(&sdev->sdev_gendev); + scsi_rescan_device(sdev); scsi_device_put(sdev); } diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index d27d9fb7174c..16848def47a1 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -752,7 +752,7 @@ extern int __must_check scsi_add_host_with_dma(struct Scsi_Host *, struct device *, struct device *); extern void scsi_scan_host(struct Scsi_Host *); -extern void scsi_rescan_device(struct device *); +extern void scsi_rescan_device(struct scsi_device *); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); extern int scsi_host_busy(struct Scsi_Host *shost); From f2b359e3a4f3ef405840446c7a82cd5d1c3dfd19 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 15 Sep 2023 15:00:13 +0900 Subject: [PATCH 1913/2093] scsi: Do not attempt to rescan suspended devices [ Upstream commit ff48b37802e5c134e2dfc4d091f10b2eb5065a72 ] scsi_rescan_device() takes a scsi device lock before executing a device handler and device driver rescan methods. Waiting for the completion of any command issued to the device by these methods will thus be done with the device lock held. As a result, there is a risk of deadlocking within the power management code if scsi_rescan_device() is called to handle a device resume with the associated scsi device not yet resumed. Avoid such situation by checking that the target scsi device is in the running state, that is, fully capable of executing commands, before proceeding with the rescan and bailout returning -EWOULDBLOCK otherwise. With this error return, the caller can retry rescaning the device after a delay. The state check is done with the device lock held and is thus safe against incoming suspend power management operations. Fixes: 6aa0365a3c85 ("ata: libata-scsi: Avoid deadlock on rescan after device resume") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Niklas Cassel Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Reviewed-by: Bart Van Assche Stable-dep-of: 8b4d9469d0b0 ("ata: libata-scsi: Fix delayed scsi_rescan_device() execution") Signed-off-by: Sasha Levin --- drivers/scsi/scsi_scan.c | 18 +++++++++++++++++- include/scsi/scsi_host.h | 2 +- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 445989f44d3f..ed26c52ed847 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1611,12 +1611,24 @@ int scsi_add_device(struct Scsi_Host *host, uint channel, } EXPORT_SYMBOL(scsi_add_device); -void scsi_rescan_device(struct scsi_device *sdev) +int scsi_rescan_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; + int ret = 0; device_lock(dev); + /* + * Bail out if the device is not running. Otherwise, the rescan may + * block waiting for commands to be executed, with us holding the + * device lock. This can result in a potential deadlock in the power + * management core code when system resume is on-going. + */ + if (sdev->sdev_state != SDEV_RUNNING) { + ret = -EWOULDBLOCK; + goto unlock; + } + scsi_attach_vpd(sdev); if (sdev->handler && sdev->handler->rescan) @@ -1629,7 +1641,11 @@ void scsi_rescan_device(struct scsi_device *sdev) drv->rescan(dev); module_put(dev->driver->owner); } + +unlock: device_unlock(dev); + + return ret; } EXPORT_SYMBOL(scsi_rescan_device); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 16848def47a1..71def41b1ad7 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -752,7 +752,7 @@ extern int __must_check scsi_add_host_with_dma(struct Scsi_Host *, struct device *, struct device *); extern void scsi_scan_host(struct Scsi_Host *); -extern void scsi_rescan_device(struct scsi_device *); +extern int scsi_rescan_device(struct scsi_device *sdev); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); extern int scsi_host_busy(struct Scsi_Host *shost); From 2f09a09d73cb65533de7fbea7685f36a78c59d29 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 5 Sep 2023 09:06:23 +0900 Subject: [PATCH 1914/2093] ata: libata-scsi: Fix delayed scsi_rescan_device() execution [ Upstream commit 8b4d9469d0b0e553208ee6f62f2807111fde18b9 ] Commit 6aa0365a3c85 ("ata: libata-scsi: Avoid deadlock on rescan after device resume") modified ata_scsi_dev_rescan() to check the scsi device "is_suspended" power field to ensure that the scsi device associated with an ATA device is fully resumed when scsi_rescan_device() is executed. However, this fix is problematic as: 1) It relies on a PM internal field that should not be used without PM device locking protection. 2) The check for is_suspended and the call to scsi_rescan_device() are not atomic and a suspend PM event may be triggered between them, casuing scsi_rescan_device() to be called on a suspended device and in that function blocking while holding the scsi device lock. This would deadlock a following resume operation. These problems can trigger PM deadlocks on resume, especially with resume operations triggered quickly after or during suspend operations. E.g., a simple bash script like: for (( i=0; i<10; i++ )); do echo "+2 > /sys/class/rtc/rtc0/wakealarm echo mem > /sys/power/state done that triggers a resume 2 seconds after starting suspending a system can quickly lead to a PM deadlock preventing the system from correctly resuming. Fix this by replacing the check on is_suspended with a check on the return value given by scsi_rescan_device() as that function will fail if called against a suspended device. Also make sure rescan tasks already scheduled are first cancelled before suspending an ata port. Fixes: 6aa0365a3c85 ("ata: libata-scsi: Avoid deadlock on rescan after device resume") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Niklas Cassel Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/ata/libata-core.c | 16 ++++++++++++++++ drivers/ata/libata-scsi.c | 33 +++++++++++++++------------------ 2 files changed, 31 insertions(+), 18 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 25b9bdf2fc38..6a053cd0cf41 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5022,11 +5022,27 @@ static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg) { + /* + * We are about to suspend the port, so we do not care about + * scsi_rescan_device() calls scheduled by previous resume operations. + * The next resume will schedule the rescan again. So cancel any rescan + * that is not done yet. + */ + cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false); } static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg) { + /* + * We are about to suspend the port, so we do not care about + * scsi_rescan_device() calls scheduled by previous resume operations. + * The next resume will schedule the rescan again. So cancel any rescan + * that is not done yet. + */ + cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true); } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index b348f77b9123..7b9c9264b9a7 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4648,7 +4648,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) struct ata_link *link; struct ata_device *dev; unsigned long flags; - bool delay_rescan = false; + int ret = 0; mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); @@ -4657,37 +4657,34 @@ void ata_scsi_dev_rescan(struct work_struct *work) ata_for_each_dev(dev, link, ENABLED) { struct scsi_device *sdev = dev->sdev; + /* + * If the port was suspended before this was scheduled, + * bail out. + */ + if (ap->pflags & ATA_PFLAG_SUSPENDED) + goto unlock; + if (!sdev) continue; if (scsi_device_get(sdev)) continue; - /* - * If the rescan work was scheduled because of a resume - * event, the port is already fully resumed, but the - * SCSI device may not yet be fully resumed. In such - * case, executing scsi_rescan_device() may cause a - * deadlock with the PM code on device_lock(). Prevent - * this by giving up and retrying rescan after a short - * delay. - */ - delay_rescan = sdev->sdev_gendev.power.is_suspended; - if (delay_rescan) { - scsi_device_put(sdev); - break; - } - spin_unlock_irqrestore(ap->lock, flags); - scsi_rescan_device(sdev); + ret = scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); + + if (ret) + goto unlock; } } +unlock: spin_unlock_irqrestore(ap->lock, flags); mutex_unlock(&ap->scsi_scan_mutex); - if (delay_rescan) + /* Reschedule with a delay if scsi_rescan_device() returned an error */ + if (ret) schedule_delayed_work(&ap->scsi_rescan_task, msecs_to_jiffies(5)); } From 15ff5870236199c60e5a3853352cb06972273cfe Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Thu, 20 Apr 2023 12:17:35 -0400 Subject: [PATCH 1915/2093] NFS: Cleanup unused rpc_clnt variable [ Upstream commit e025f0a73f6acb920d86549b2177a5883535421d ] The root rpc_clnt is not used here, clean it up. Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Signed-off-by: Benjamin Coddington Reviewed-by: NeilBrown Signed-off-by: Anna Schumaker Stable-dep-of: 956fd46f97d2 ("NFSv4: Fix a state manager thread deadlock regression") Signed-off-by: Sasha Levin --- fs/nfs/nfs4state.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5b49e5365bb3..1b707573fbf8 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,10 +1209,6 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; - struct rpc_clnt *cl = clp->cl_rpcclient; - - while (cl != cl->cl_parent) - cl = cl->cl_parent; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { From 80ba4fd1ac33190381b17221fbe2ebcabf4777b2 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Thu, 15 Jun 2023 14:07:22 -0400 Subject: [PATCH 1916/2093] NFS: rename nfs_client_kset to nfs_kset [ Upstream commit 8b18a2edecc0741b0eecf8b18fdb356a0f8682de ] Be brief and match the subsystem name. There's no need to distinguish this kset variable from the server. Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust Stable-dep-of: 956fd46f97d2 ("NFSv4: Fix a state manager thread deadlock regression") Signed-off-by: Sasha Levin --- fs/nfs/sysfs.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index a6f740366963..edb535a0ff97 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -18,7 +18,7 @@ #include "sysfs.h" struct kobject *nfs_client_kobj; -static struct kset *nfs_client_kset; +static struct kset *nfs_kset; static void nfs_netns_object_release(struct kobject *kobj) { @@ -55,13 +55,13 @@ static struct kobject *nfs_netns_object_alloc(const char *name, int nfs_sysfs_init(void) { - nfs_client_kset = kset_create_and_add("nfs", NULL, fs_kobj); - if (!nfs_client_kset) + nfs_kset = kset_create_and_add("nfs", NULL, fs_kobj); + if (!nfs_kset) return -ENOMEM; - nfs_client_kobj = nfs_netns_object_alloc("net", nfs_client_kset, NULL); + nfs_client_kobj = nfs_netns_object_alloc("net", nfs_kset, NULL); if (!nfs_client_kobj) { - kset_unregister(nfs_client_kset); - nfs_client_kset = NULL; + kset_unregister(nfs_kset); + nfs_kset = NULL; return -ENOMEM; } return 0; @@ -70,7 +70,7 @@ int nfs_sysfs_init(void) void nfs_sysfs_exit(void) { kobject_put(nfs_client_kobj); - kset_unregister(nfs_client_kset); + kset_unregister(nfs_kset); } static ssize_t nfs_netns_identifier_show(struct kobject *kobj, @@ -159,7 +159,7 @@ static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent, p = kzalloc(sizeof(*p), GFP_KERNEL); if (p) { p->net = net; - p->kobject.kset = nfs_client_kset; + p->kobject.kset = nfs_kset; if (kobject_init_and_add(&p->kobject, &nfs_netns_client_type, parent, "nfs_client") == 0) return p; From 89f2ace6d016d2aac29af621069a41c1583382ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 24 Sep 2023 13:14:15 -0400 Subject: [PATCH 1917/2093] NFSv4: Fix a state manager thread deadlock regression [ Upstream commit 956fd46f97d238032cb5fa4771cdaccc6e760f9a ] Commit 4dc73c679114 reintroduces the deadlock that was fixed by commit aeabb3c96186 ("NFSv4: Fix a NFSv4 state manager deadlock") because it prevents the setup of new threads to handle reboot recovery, while the older recovery thread is stuck returning delegations. Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 4 +++- fs/nfs/nfs4state.c | 36 +++++++++++++++++++++++++----------- 2 files changed, 28 insertions(+), 12 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index be570c65ae15..b927a7d1b46d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10629,7 +10629,9 @@ static void nfs4_disable_swap(struct inode *inode) */ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + wake_up_var(&clp->cl_state); } static const struct inode_operations nfs4_dir_inode_operations = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 1b707573fbf8..ed789e0cb943 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,13 +1209,23 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *clnt = clp->cl_rpcclient; + bool swapon = false; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { - wake_up_var(&clp->cl_state); - return; + + if (atomic_read(&clnt->cl_swapper)) { + swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, + &clp->cl_state); + if (!swapon) { + wake_up_var(&clp->cl_state); + return; + } } - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1232,8 +1242,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) __func__, PTR_ERR(task)); if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); + if (swapon) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs4_clear_state_manager_bit(clp); - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2737,22 +2748,25 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); again: - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); - if (atomic_read(&cl->cl_swapper)) { + + if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) && + !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) { wait_var_event_interruptible(&clp->cl_state, test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)); - if (atomic_read(&cl->cl_swapper) && - test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + if (!atomic_read(&cl->cl_swapper)) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; /* Either no longer a swapper, or were signalled */ + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); } - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); if (refcount_read(&clp->cl_count) > 1 && !signalled() && test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && - !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; nfs_put_client(clp); From 6d6635749d4c9fd67aa74e8b3fcdbdecd97d8567 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Wed, 21 Dec 2022 10:08:45 -0800 Subject: [PATCH 1918/2093] mm/memory: add vm_normal_folio() [ Upstream commit 318e9342fbbb6888d903d86e83865609901a1c65 ] Patch series "Convert deactivate_page() to folio_deactivate()", v4. Deactivate_page() has already been converted to use folios. This patch series modifies the callers of deactivate_page() to use folios. It also introduces vm_normal_folio() to assist with folio conversions, and converts deactivate_page() to folio_deactivate() which takes in a folio. This patch (of 4): Introduce a wrapper function called vm_normal_folio(). This function calls vm_normal_page() and returns the folio of the page found, or null if no page is found. This function allows callers to get a folio from a pte, which will eventually allow them to completely replace their struct page variables with struct folio instead. Link: https://lkml.kernel.org/r/20221221180848.20774-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221221180848.20774-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Matthew Wilcox (Oracle) Cc: SeongJae Park Signed-off-by: Andrew Morton Stable-dep-of: 24526268f4e3 ("mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified") Signed-off-by: Sasha Levin --- include/linux/mm.h | 2 ++ mm/memory.c | 10 ++++++++++ 2 files changed, 12 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 104ec00823da..eefb0948110a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1906,6 +1906,8 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); +struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, diff --git a/mm/memory.c b/mm/memory.c index 2083078cd061..0d1b3ee8fcd7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -672,6 +672,16 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, return pfn_to_page(pfn); } +struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + struct page *page = vm_normal_page(vma, addr, pte); + + if (page) + return page_folio(page); + return NULL; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) From 6c2c728d299f8207214c8f3b90253cf913a90333 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Mon, 30 Jan 2023 12:18:29 -0800 Subject: [PATCH 1919/2093] mm/mempolicy: convert queue_pages_pmd() to queue_folios_pmd() [ Upstream commit de1f5055523e9a035b38533f25a56df03d45034a ] The function now operates on a folio instead of the page associated with a pmd. This change is in preparation for the conversion of queue_pages_required() to queue_folio_required() and migrate_page_add() to migrate_folio_add(). Link: https://lkml.kernel.org/r/20230130201833.27042-3-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Cc: David Hildenbrand Cc: Jane Chu Cc: "Yin, Fengwei" Signed-off-by: Andrew Morton Stable-dep-of: 24526268f4e3 ("mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified") Signed-off-by: Sasha Levin --- mm/mempolicy.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7d36dd95d1ff..3a291026e189 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -442,21 +442,21 @@ static inline bool queue_pages_required(struct page *page, } /* - * queue_pages_pmd() has three possible return values: - * 0 - pages are placed on the right node or queued successfully, or + * queue_folios_pmd() has three possible return values: + * 0 - folios are placed on the right node or queued successfully, or * special page is met, i.e. huge zero page. - * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an - * existing page was already on a node that does not follow the + * existing folio was already on a node that does not follow the * policy. */ -static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, +static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) __releases(ptl) { int ret = 0; - struct page *page; + struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags; @@ -464,19 +464,19 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = -EIO; goto unlock; } - page = pmd_page(*pmd); - if (is_huge_zero_page(page)) { + folio = pfn_folio(pmd_pfn(*pmd)); + if (is_huge_zero_page(&folio->page)) { walk->action = ACTION_CONTINUE; goto unlock; } - if (!queue_pages_required(page, qp)) + if (!queue_pages_required(&folio->page, qp)) goto unlock; flags = qp->flags; - /* go to thp migration */ + /* go to folio migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || - migrate_page_add(page, qp->pagelist, flags)) { + migrate_page_add(&folio->page, qp->pagelist, flags)) { ret = 1; goto unlock; } @@ -512,7 +512,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) - return queue_pages_pmd(pmd, ptl, addr, end, walk); + return queue_folios_pmd(pmd, ptl, addr, end, walk); if (pmd_trans_unstable(pmd)) return 0; From dc0a8466cd118202cf3ea5cddb738e7a49c3be9b Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Mon, 30 Jan 2023 12:18:30 -0800 Subject: [PATCH 1920/2093] mm/mempolicy: convert queue_pages_pte_range() to queue_folios_pte_range() [ Upstream commit 3dae02bbd07f40e37bbfec2d77119628db461eaa ] This function now operates on folios associated with ptes instead of pages. This change is in preparation for the conversion of queue_pages_required() to queue_folio_required() and migrate_page_add() to migrate_folio_add(). Link: https://lkml.kernel.org/r/20230130201833.27042-4-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Cc: David Hildenbrand Cc: Jane Chu Cc: "Yin, Fengwei" Signed-off-by: Andrew Morton Stable-dep-of: 24526268f4e3 ("mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified") Signed-off-by: Sasha Levin --- mm/mempolicy.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3a291026e189..2ae6c8f18aba 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -491,19 +491,19 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. * - * queue_pages_pte_range() has three possible return values: - * 0 - pages are placed on the right node or queued successfully, or + * queue_folios_pte_range() has three possible return values: + * 0 - folios are placed on the right node or queued successfully, or * special page is met, i.e. zero page. - * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. - * -EIO - only MPOL_MF_STRICT was specified and an existing page was already + * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ -static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, +static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; - struct page *page; + struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; bool has_unmovable = false; @@ -521,16 +521,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; - page = vm_normal_page(vma, addr, *pte); - if (!page || is_zone_device_page(page)) + folio = vm_normal_folio(vma, addr, *pte); + if (!folio || folio_is_zone_device(folio)) continue; /* - * vm_normal_page() filters out zero pages, but there might - * still be PageReserved pages to skip, perhaps in a VDSO. + * vm_normal_folio() filters out zero pages, but there might + * still be reserved folios to skip, perhaps in a VDSO. */ - if (PageReserved(page)) + if (folio_test_reserved(folio)) continue; - if (!queue_pages_required(page, qp)) + if (!queue_pages_required(&folio->page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { /* MPOL_MF_STRICT must be specified if we get here */ @@ -544,7 +544,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, * temporary off LRU pages in the range. Still * need migrate other LRU pages. */ - if (migrate_page_add(page, qp->pagelist, flags)) + if (migrate_page_add(&folio->page, qp->pagelist, flags)) has_unmovable = true; } else break; @@ -705,7 +705,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_pages_hugetlb, - .pmd_entry = queue_pages_pte_range, + .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, }; From ce9f3441fc6a7cb6a4df55caa11791afa54aae56 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Mon, 30 Jan 2023 12:18:33 -0800 Subject: [PATCH 1921/2093] mm/mempolicy: convert migrate_page_add() to migrate_folio_add() [ Upstream commit 4a64981dfee9119aa2c1f243b48f34cbbd67779c ] Replace migrate_page_add() with migrate_folio_add(). migrate_folio_add() does the same a migrate_page_add() but takes in a folio instead of a page. This removes a couple of calls to compound_head(). Link: https://lkml.kernel.org/r/20230130201833.27042-7-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Yin Fengwei Cc: David Hildenbrand Cc: Jane Chu Signed-off-by: Andrew Morton Stable-dep-of: 24526268f4e3 ("mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified") Signed-off-by: Sasha Levin --- mm/mempolicy.c | 39 ++++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 19 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2ae6c8f18aba..158b0bcd12fd 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -414,7 +414,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { }, }; -static int migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); struct queue_pages { @@ -476,7 +476,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, /* go to folio migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || - migrate_page_add(&folio->page, qp->pagelist, flags)) { + migrate_folio_add(folio, qp->pagelist, flags)) { ret = 1; goto unlock; } @@ -544,7 +544,7 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * temporary off LRU pages in the range. Still * need migrate other LRU pages. */ - if (migrate_page_add(&folio->page, qp->pagelist, flags)) + if (migrate_folio_add(folio, qp->pagelist, flags)) has_unmovable = true; } else break; @@ -1012,27 +1012,28 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } #ifdef CONFIG_MIGRATION -/* - * page migration, thp tail pages can be passed. - */ -static int migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { - struct page *head = compound_head(page); /* - * Avoid migrating a page that is shared with others. + * We try to migrate only unshared folios. If it is shared it + * is likely not worth migrating. + * + * To check if the folio is shared, ideally we want to make sure + * every page is mapped to the same process. Doing that is very + * expensive, so check the estimated mapcount of the folio instead. */ - if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) { - if (!isolate_lru_page(head)) { - list_add_tail(&head->lru, pagelist); - mod_node_page_state(page_pgdat(head), - NR_ISOLATED_ANON + page_is_file_lru(head), - thp_nr_pages(head)); + if ((flags & MPOL_MF_MOVE_ALL) || folio_estimated_sharers(folio) == 1) { + if (!folio_isolate_lru(folio)) { + list_add_tail(&folio->lru, foliolist); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); } else if (flags & MPOL_MF_STRICT) { /* - * Non-movable page may reach here. And, there may be - * temporary off LRU pages or non-LRU movable pages. - * Treat them as unmovable pages since they can't be + * Non-movable folio may reach here. And, there may be + * temporary off LRU folios or non-LRU movable folios. + * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. It * should return -EIO for this case too. */ @@ -1224,7 +1225,7 @@ static struct page *new_page(struct page *page, unsigned long start) } #else -static int migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return -EIO; From 939189aedfac6b7b8dfd6eb02f70b251c51a8163 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH 1922/2093] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified [ Upstream commit 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 ] When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.com Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi Cc: Hugh Dickins Cc: Suren Baghdasaryan Cc: Matthew Wilcox Cc: Michal Hocko Cc: Vlastimil Babka Cc: Oscar Salvador Cc: Rafael Aquini Cc: Kirill A. Shutemov Cc: David Rientjes Cc: [4.9+] Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- mm/mempolicy.c | 39 +++++++++++++++++++-------------------- 1 file changed, 19 insertions(+), 20 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 158b0bcd12fd..bfe2d1d50fbe 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -424,6 +424,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -444,9 +445,8 @@ static inline bool queue_pages_required(struct page *page, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -477,7 +477,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -493,9 +493,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -506,7 +505,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; spinlock_t *ptl; @@ -533,11 +531,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_pages_required(&folio->page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -545,16 +544,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -594,7 +590,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced page but allow migrating pages which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -608,7 +604,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate page but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -737,10 +733,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1338,7 +1337,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out: From 570786ac6f04b6958b2224254a5138f619f334a8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 18 Nov 2022 10:17:13 +0000 Subject: [PATCH 1923/2093] mm/page_alloc: always remove pages from temporary list [ Upstream commit c3e58a70425ac6ddaae1529c8146e88b4f7252bb ] Patch series "Leave IRQs enabled for per-cpu page allocations", v3. This patch (of 2): free_unref_page_list() has neglected to remove pages properly from the list of pages to free since forever. It works by coincidence because list_add happened to do the right thing adding the pages to just the PCP lists. However, a later patch added pages to either the PCP list or the zone list but only properly deleted the page from the list in one path leading to list corruption and a subsequent failure. As a preparation patch, always delete the pages from one list properly before adding to another. On its own, this fixes nothing although it adds a fractional amount of overhead but is critical to the next patch. Link: https://lkml.kernel.org/r/20221118101714.19590-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20221118101714.19590-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Reported-by: Hugh Dickins Reviewed-by: Vlastimil Babka Cc: Marcelo Tosatti Cc: Marek Szyprowski Cc: Michal Hocko Cc: Yu Zhao Signed-off-by: Andrew Morton Stable-dep-of: 7b086755fb8c ("mm: page_alloc: fix CMA and HIGHATOMIC landing on the wrong buddy list") Signed-off-by: Sasha Levin --- mm/page_alloc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 69668817fed3..d94ac6d87bc9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3547,6 +3547,8 @@ void free_unref_page_list(struct list_head *list) list_for_each_entry_safe(page, next, list, lru) { struct zone *zone = page_zone(page); + list_del(&page->lru); + /* Different zone, different pcp lock. */ if (zone != locked_zone) { if (pcp) From d1da921452b3ee7e07383c12955ab1c6f3b08752 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 18 Nov 2022 10:17:14 +0000 Subject: [PATCH 1924/2093] mm/page_alloc: leave IRQs enabled for per-cpu page allocations [ Upstream commit 5749077415994eb02d660b2559b9d8278521e73d ] The pcp_spin_lock_irqsave protecting the PCP lists is IRQ-safe as a task allocating from the PCP must not re-enter the allocator from IRQ context. In each instance where IRQ-reentrancy is possible, the lock is acquired using pcp_spin_trylock_irqsave() even though IRQs are disabled and re-entrancy is impossible. Demote the lock to pcp_spin_lock avoids an IRQ disable/enable in the common case at the cost of some IRQ allocations taking a slower path. If the PCP lists need to be refilled, the zone lock still needs to disable IRQs but that will only happen on PCP refill and drain. If an IRQ is raised when a PCP allocation is in progress, the trylock will fail and fallback to using the buddy lists directly. Note that this may not be a universal win if an interrupt-intensive workload also allocates heavily from interrupt context and contends heavily on the zone->lock as a result. [mgorman@techsingularity.net: migratetype might be wrong if a PCP was locked] Link: https://lkml.kernel.org/r/20221122131229.5263-2-mgorman@techsingularity.net [yuzhao@google.com: reported lockdep issue on IO completion from softirq] [hughd@google.com: fix list corruption, lock improvements, micro-optimsations] Link: https://lkml.kernel.org/r/20221118101714.19590-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Reviewed-by: Vlastimil Babka Cc: Marcelo Tosatti Cc: Marek Szyprowski Cc: Michal Hocko Signed-off-by: Andrew Morton Stable-dep-of: 7b086755fb8c ("mm: page_alloc: fix CMA and HIGHATOMIC landing on the wrong buddy list") Signed-off-by: Sasha Levin --- mm/page_alloc.c | 124 +++++++++++++++++++++--------------------------- 1 file changed, 54 insertions(+), 70 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d94ac6d87bc9..90082f75660f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -170,21 +170,12 @@ static DEFINE_MUTEX(pcp_batch_high_lock); _ret; \ }) -#define pcpu_spin_lock_irqsave(type, member, ptr, flags) \ +#define pcpu_spin_trylock(type, member, ptr) \ ({ \ type *_ret; \ pcpu_task_pin(); \ _ret = this_cpu_ptr(ptr); \ - spin_lock_irqsave(&_ret->member, flags); \ - _ret; \ -}) - -#define pcpu_spin_trylock_irqsave(type, member, ptr, flags) \ -({ \ - type *_ret; \ - pcpu_task_pin(); \ - _ret = this_cpu_ptr(ptr); \ - if (!spin_trylock_irqsave(&_ret->member, flags)) { \ + if (!spin_trylock(&_ret->member)) { \ pcpu_task_unpin(); \ _ret = NULL; \ } \ @@ -197,27 +188,16 @@ static DEFINE_MUTEX(pcp_batch_high_lock); pcpu_task_unpin(); \ }) -#define pcpu_spin_unlock_irqrestore(member, ptr, flags) \ -({ \ - spin_unlock_irqrestore(&ptr->member, flags); \ - pcpu_task_unpin(); \ -}) - /* struct per_cpu_pages specific helpers. */ #define pcp_spin_lock(ptr) \ pcpu_spin_lock(struct per_cpu_pages, lock, ptr) -#define pcp_spin_lock_irqsave(ptr, flags) \ - pcpu_spin_lock_irqsave(struct per_cpu_pages, lock, ptr, flags) - -#define pcp_spin_trylock_irqsave(ptr, flags) \ - pcpu_spin_trylock_irqsave(struct per_cpu_pages, lock, ptr, flags) +#define pcp_spin_trylock(ptr) \ + pcpu_spin_trylock(struct per_cpu_pages, lock, ptr) #define pcp_spin_unlock(ptr) \ pcpu_spin_unlock(lock, ptr) -#define pcp_spin_unlock_irqrestore(ptr, flags) \ - pcpu_spin_unlock_irqrestore(lock, ptr, flags) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -1548,6 +1528,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, struct per_cpu_pages *pcp, int pindex) { + unsigned long flags; int min_pindex = 0; int max_pindex = NR_PCP_LISTS - 1; unsigned int order; @@ -1563,8 +1544,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* Ensure requested pindex is drained first. */ pindex = pindex - 1; - /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ - spin_lock(&zone->lock); + spin_lock_irqsave(&zone->lock, flags); isolated_pageblocks = has_isolate_pageblock(zone); while (count > 0) { @@ -1612,7 +1592,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, } while (count > 0 && !list_empty(list)); } - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); } static void free_one_page(struct zone *zone, @@ -3126,10 +3106,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, unsigned int alloc_flags) { + unsigned long flags; int i, allocated = 0; - /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ - spin_lock(&zone->lock); + spin_lock_irqsave(&zone->lock, flags); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, alloc_flags); @@ -3163,7 +3143,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages added to the pcp list. */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); return allocated; } @@ -3180,16 +3160,9 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { - unsigned long flags; - - /* - * free_pcppages_bulk expects IRQs disabled for zone->lock - * so even though pcp->lock is not intended to be IRQ-safe, - * it's needed in this context. - */ - spin_lock_irqsave(&pcp->lock, flags); + spin_lock(&pcp->lock); free_pcppages_bulk(zone, to_drain, pcp, 0); - spin_unlock_irqrestore(&pcp->lock, flags); + spin_unlock(&pcp->lock); } } #endif @@ -3203,12 +3176,9 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); if (pcp->count) { - unsigned long flags; - - /* See drain_zone_pages on why this is disabling IRQs */ - spin_lock_irqsave(&pcp->lock, flags); + spin_lock(&pcp->lock); free_pcppages_bulk(zone, pcp->count, pcp, 0); - spin_unlock_irqrestore(&pcp->lock, flags); + spin_unlock(&pcp->lock); } } @@ -3474,7 +3444,6 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, */ void free_unref_page(struct page *page, unsigned int order) { - unsigned long flags; unsigned long __maybe_unused UP_flags; struct per_cpu_pages *pcp; struct zone *zone; @@ -3502,10 +3471,10 @@ void free_unref_page(struct page *page, unsigned int order) zone = page_zone(page); pcp_trylock_prepare(UP_flags); - pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { free_unref_page_commit(zone, pcp, page, migratetype, order); - pcp_spin_unlock_irqrestore(pcp, flags); + pcp_spin_unlock(pcp); } else { free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); } @@ -3517,10 +3486,10 @@ void free_unref_page(struct page *page, unsigned int order) */ void free_unref_page_list(struct list_head *list) { + unsigned long __maybe_unused UP_flags; struct page *page, *next; struct per_cpu_pages *pcp = NULL; struct zone *locked_zone = NULL; - unsigned long flags; int batch_count = 0; int migratetype; @@ -3548,21 +3517,36 @@ void free_unref_page_list(struct list_head *list) struct zone *zone = page_zone(page); list_del(&page->lru); + migratetype = get_pcppage_migratetype(page); /* Different zone, different pcp lock. */ if (zone != locked_zone) { - if (pcp) - pcp_spin_unlock_irqrestore(pcp, flags); + if (pcp) { + pcp_spin_unlock(pcp); + pcp_trylock_finish(UP_flags); + } + /* + * trylock is necessary as pages may be getting freed + * from IRQ or SoftIRQ context after an IO completion. + */ + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock(zone->per_cpu_pageset); + if (unlikely(!pcp)) { + pcp_trylock_finish(UP_flags); + free_one_page(zone, page, page_to_pfn(page), + 0, migratetype, FPI_NONE); + locked_zone = NULL; + continue; + } locked_zone = zone; - pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); + batch_count = 0; } /* * Non-isolated types over MIGRATE_PCPTYPES get added * to the MIGRATE_MOVABLE pcp list. */ - migratetype = get_pcppage_migratetype(page); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) migratetype = MIGRATE_MOVABLE; @@ -3570,18 +3554,23 @@ void free_unref_page_list(struct list_head *list) free_unref_page_commit(zone, pcp, page, migratetype, 0); /* - * Guard against excessive IRQ disabled times when we get - * a large list of pages to free. + * Guard against excessive lock hold times when freeing + * a large list of pages. Lock will be reacquired if + * necessary on the next iteration. */ if (++batch_count == SWAP_CLUSTER_MAX) { - pcp_spin_unlock_irqrestore(pcp, flags); + pcp_spin_unlock(pcp); + pcp_trylock_finish(UP_flags); batch_count = 0; - pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); + pcp = NULL; + locked_zone = NULL; } } - if (pcp) - pcp_spin_unlock_irqrestore(pcp, flags); + if (pcp) { + pcp_spin_unlock(pcp); + pcp_trylock_finish(UP_flags); + } } /* @@ -3782,15 +3771,11 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct per_cpu_pages *pcp; struct list_head *list; struct page *page; - unsigned long flags; unsigned long __maybe_unused UP_flags; - /* - * spin_trylock may fail due to a parallel drain. In the future, the - * trylock will also protect against IRQ reentrancy. - */ + /* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */ pcp_trylock_prepare(UP_flags); - pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (!pcp) { pcp_trylock_finish(UP_flags); return NULL; @@ -3804,7 +3789,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, pcp->free_factor >>= 1; list = &pcp->lists[order_to_pindex(migratetype, order)]; page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); - pcp_spin_unlock_irqrestore(pcp, flags); + pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); @@ -5375,7 +5360,6 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct page **page_array) { struct page *page; - unsigned long flags; unsigned long __maybe_unused UP_flags; struct zone *zone; struct zoneref *z; @@ -5457,9 +5441,9 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (unlikely(!zone)) goto failed; - /* Is a parallel drain in progress? */ + /* spin_trylock may fail due to a parallel drain or IRQ reentrancy. */ pcp_trylock_prepare(UP_flags); - pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (!pcp) goto failed_irq; @@ -5478,7 +5462,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (unlikely(!page)) { /* Try and allocate at least one page */ if (!nr_account) { - pcp_spin_unlock_irqrestore(pcp, flags); + pcp_spin_unlock(pcp); goto failed_irq; } break; @@ -5493,7 +5477,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_populated++; } - pcp_spin_unlock_irqrestore(pcp, flags); + pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); From 836adaddc60c3ac635682ae48b89e6c4fd45c6ab Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 11 Sep 2023 14:11:08 -0400 Subject: [PATCH 1925/2093] mm: page_alloc: fix CMA and HIGHATOMIC landing on the wrong buddy list [ Upstream commit 7b086755fb8cdbb6b3e45a1bbddc00e7f9b1dc03 ] Commit 4b23a68f9536 ("mm/page_alloc: protect PCP lists with a spinlock") bypasses the pcplist on lock contention and returns the page directly to the buddy list of the page's migratetype. For pages that don't have their own pcplist, such as CMA and HIGHATOMIC, the migratetype is temporarily updated such that the page can hitch a ride on the MOVABLE pcplist. Their true type is later reassessed when flushing in free_pcppages_bulk(). However, when lock contention is detected after the type was already overridden, the bypass will then put the page on the wrong buddy list. Once on the MOVABLE buddy list, the page becomes eligible for fallbacks and even stealing. In the case of HIGHATOMIC, otherwise ineligible allocations can dip into the highatomic reserves. In the case of CMA, the page can be lost from the CMA region permanently. Use a separate pcpmigratetype variable for the pcplist override. Use the original migratetype when going directly to the buddy. This fixes the bug and should make the intentions more obvious in the code. Originally sent here to address the HIGHATOMIC case: https://lore.kernel.org/lkml/20230821183733.106619-4-hannes@cmpxchg.org/ Changelog updated in response to the CMA-specific bug report. [mgorman@techsingularity.net: updated changelog] Link: https://lkml.kernel.org/r/20230911181108.GA104295@cmpxchg.org Fixes: 4b23a68f9536 ("mm/page_alloc: protect PCP lists with a spinlock") Signed-off-by: Johannes Weiner Reported-by: Joe Liu Reviewed-by: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- mm/page_alloc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 90082f75660f..ca017c6008b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3448,7 +3448,7 @@ void free_unref_page(struct page *page, unsigned int order) struct per_cpu_pages *pcp; struct zone *zone; unsigned long pfn = page_to_pfn(page); - int migratetype; + int migratetype, pcpmigratetype; if (!free_unref_page_prepare(page, pfn, order)) return; @@ -3456,24 +3456,24 @@ void free_unref_page(struct page *page, unsigned int order) /* * We only track unmovable, reclaimable and movable on pcp lists. * Place ISOLATE pages on the isolated list because they are being - * offlined but treat HIGHATOMIC as movable pages so we can get those - * areas back if necessary. Otherwise, we may have to free + * offlined but treat HIGHATOMIC and CMA as movable pages so we can + * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - migratetype = get_pcppage_migratetype(page); + migratetype = pcpmigratetype = get_pcppage_migratetype(page); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); return; } - migratetype = MIGRATE_MOVABLE; + pcpmigratetype = MIGRATE_MOVABLE; } zone = page_zone(page); pcp_trylock_prepare(UP_flags); pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { - free_unref_page_commit(zone, pcp, page, migratetype, order); + free_unref_page_commit(zone, pcp, page, pcpmigratetype, order); pcp_spin_unlock(pcp); } else { free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); From 62eed43e03902cee236b09f795ad068361746eaa Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 15 Mar 2023 15:24:46 +0100 Subject: [PATCH 1926/2093] ring-buffer: remove obsolete comment for free_buffer_page() [ Upstream commit a98151ad53b53f010ee364ec2fd06445b328578b ] The comment refers to mm/slob.c which is being removed. It comes from commit ed56829cb319 ("ring_buffer: reset buffer page when freeing") and according to Steven the borrowed code was a page mapcount and mapping reset, which was later removed by commit e4c2ce82ca27 ("ring_buffer: allocate buffer page pointer"). Thus the comment is not accurate anyway, remove it. Link: https://lore.kernel.org/linux-trace-kernel/20230315142446.27040-1-vbabka@suse.cz Cc: Masami Hiramatsu Cc: Ingo Molnar Reported-by: Mike Rapoport Suggested-by: Steven Rostedt (Google) Fixes: e4c2ce82ca27 ("ring_buffer: allocate buffer page pointer") Signed-off-by: Vlastimil Babka Reviewed-by: Mukesh Ojha Signed-off-by: Steven Rostedt (Google) Stable-dep-of: 45d99ea451d0 ("ring-buffer: Fix bytes info in per_cpu buffer stats") Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2f562cf961e0..51737b3d54b3 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,10 +354,6 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } -/* - * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing - * this issue out. - */ static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); From 87efd87d3624e0be64b9b11a109a6e21a5bdbc1c Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Thu, 21 Sep 2023 20:54:25 +0800 Subject: [PATCH 1927/2093] ring-buffer: Fix bytes info in per_cpu buffer stats [ Upstream commit 45d99ea451d0c30bfd4864f0fe485d7dac014902 ] The 'bytes' info in file 'per_cpu/cpu/stats' means the number of bytes in cpu buffer that have not been consumed. However, currently after consuming data by reading file 'trace_pipe', the 'bytes' info was not changed as expected. # cat per_cpu/cpu0/stats entries: 0 overrun: 0 commit overrun: 0 bytes: 568 <--- 'bytes' is problematical !!! oldest event ts: 8651.371479 now ts: 8653.912224 dropped events: 0 read events: 8 The root cause is incorrect stat on cpu_buffer->read_bytes. To fix it: 1. When stat 'read_bytes', account consumed event in rb_advance_reader(); 2. When stat 'entries_bytes', exclude the discarded padding event which is smaller than minimum size because it is invisible to reader. Then use rb_page_commit() instead of BUF_PAGE_SIZE at where accounting for page-based read/remove/overrun. Also correct the comments of ring_buffer_bytes_cpu() in this patch. Link: https://lore.kernel.org/linux-trace-kernel/20230921125425.1708423-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Fixes: c64e148a3be3 ("trace: Add ring buffer stats to measure rate of events") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 51737b3d54b3..b7383358c4ea 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2020,7 +2025,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2364,11 +2369,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2514,7 +2514,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2657,9 +2657,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2673,7 +2670,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2698,6 +2696,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4725,6 +4726,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5820,7 +5822,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage); From 1cf474cd474bc5d3ef63086ffd009a87a5b7bb2e Mon Sep 17 00:00:00 2001 From: Sweet Tea Dorminy Date: Thu, 20 Oct 2022 12:58:25 -0400 Subject: [PATCH 1928/2093] btrfs: use struct qstr instead of name and namelen pairs [ Upstream commit e43eec81c5167b655b72c781b0e75e62a05e415e ] Many functions throughout btrfs take name buffer and name length arguments. Most of these functions at the highest level are usually called with these arguments extracted from a supplied dentry's name. But the entire name can be passed instead, making each function a little more elegant. Each function whose arguments are currently the name and length extracted from a dentry is herein converted to instead take a pointer to the name in the dentry. The couple of calls to these calls without a struct dentry are converted to create an appropriate qstr to pass in. Additionally, every function which is only called with a name/len extracted directly from a qstr is also converted. This change has positive effect on stack consumption, frame of many functions is reduced but this will be used in the future for fscrypt related structures. Signed-off-by: Sweet Tea Dorminy Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 9af86694fd5d ("btrfs: file_remove_privs needs an exclusive lock in direct io write") Signed-off-by: Sasha Levin --- fs/btrfs/ctree.h | 26 ++-- fs/btrfs/dir-item.c | 50 ++++---- fs/btrfs/inode-item.c | 73 ++++++----- fs/btrfs/inode-item.h | 20 ++- fs/btrfs/inode.c | 130 +++++++++----------- fs/btrfs/ioctl.c | 7 +- fs/btrfs/root-tree.c | 19 ++- fs/btrfs/send.c | 12 +- fs/btrfs/super.c | 3 +- fs/btrfs/transaction.c | 11 +- fs/btrfs/tree-log.c | 267 +++++++++++++++++++---------------------- fs/btrfs/tree-log.h | 4 +- 12 files changed, 287 insertions(+), 335 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3bcef0c4d6fc..6718cee57a94 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3238,11 +3238,11 @@ static inline void btrfs_clear_sb_rdonly(struct super_block *sb) /* root-item.c */ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, - u64 ref_id, u64 dirid, u64 sequence, const char *name, - int name_len); + u64 ref_id, u64 dirid, u64 sequence, + const struct qstr *name); int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, - u64 ref_id, u64 dirid, u64 *sequence, const char *name, - int name_len); + u64 ref_id, u64 dirid, u64 *sequence, + const struct qstr *name); int btrfs_del_root(struct btrfs_trans_handle *trans, const struct btrfs_key *key); int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3271,25 +3271,23 @@ int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info); /* dir-item.c */ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, - const char *name, int name_len); -int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, - int name_len, struct btrfs_inode *dir, + const struct qstr *name); +int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, + const struct qstr *name, struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index); struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - const char *name, int name_len, - int mod); + const struct qstr *name, int mod); struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 index, const char *name, int name_len, - int mod); + u64 index, const struct qstr *name, int mod); struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, - const char *name, int name_len); + const struct qstr *name); int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, @@ -3370,10 +3368,10 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const char *name, int name_len); + const struct qstr *name); int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, - const char *name, int name_len, int add_backref, u64 index); + const struct qstr *name, int add_backref, u64 index); int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry); int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len, int front); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 72fb2c518a2b..8c60f37eb13f 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -103,8 +103,8 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, * to use for the second index (if one is created). * Will return 0 or -ENOMEM */ -int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, - int name_len, struct btrfs_inode *dir, +int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, + const struct qstr *name, struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index) { int ret = 0; @@ -120,7 +120,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, key.objectid = btrfs_ino(dir); key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); + key.offset = btrfs_name_hash(name->name, name->len); path = btrfs_alloc_path(); if (!path) @@ -128,9 +128,9 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, btrfs_cpu_key_to_disk(&disk_key, location); - data_size = sizeof(*dir_item) + name_len; + data_size = sizeof(*dir_item) + name->len; dir_item = insert_with_overflow(trans, root, path, &key, data_size, - name, name_len); + name->name, name->len); if (IS_ERR(dir_item)) { ret = PTR_ERR(dir_item); if (ret == -EEXIST) @@ -142,11 +142,11 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, btrfs_set_dir_item_key(leaf, dir_item, &disk_key); btrfs_set_dir_type(leaf, dir_item, type); btrfs_set_dir_data_len(leaf, dir_item, 0); - btrfs_set_dir_name_len(leaf, dir_item, name_len); + btrfs_set_dir_name_len(leaf, dir_item, name->len); btrfs_set_dir_transid(leaf, dir_item, trans->transid); name_ptr = (unsigned long)(dir_item + 1); - write_extent_buffer(leaf, name, name_ptr, name_len); + write_extent_buffer(leaf, name->name, name_ptr, name->len); btrfs_mark_buffer_dirty(leaf); second_insert: @@ -157,7 +157,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, } btrfs_release_path(path); - ret2 = btrfs_insert_delayed_dir_index(trans, name, name_len, dir, + ret2 = btrfs_insert_delayed_dir_index(trans, name->name, name->len, dir, &disk_key, type, index); out_free: btrfs_free_path(path); @@ -206,7 +206,7 @@ static struct btrfs_dir_item *btrfs_lookup_match_dir( struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - const char *name, int name_len, + const struct qstr *name, int mod) { struct btrfs_key key; @@ -214,9 +214,10 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, key.objectid = dir; key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); + key.offset = btrfs_name_hash(name->name, name->len); - di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + di = btrfs_lookup_match_dir(trans, root, path, &key, name->name, + name->len, mod); if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; @@ -224,7 +225,7 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, } int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, - const char *name, int name_len) + const struct qstr *name) { int ret; struct btrfs_key key; @@ -240,9 +241,10 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, key.objectid = dir; key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); + key.offset = btrfs_name_hash(name->name, name->len); - di = btrfs_lookup_match_dir(NULL, root, path, &key, name, name_len, 0); + di = btrfs_lookup_match_dir(NULL, root, path, &key, name->name, + name->len, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); /* Nothing found, we're safe */ @@ -262,11 +264,8 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, goto out; } - /* - * see if there is room in the item to insert this - * name - */ - data_size = sizeof(*di) + name_len; + /* See if there is room in the item to insert this name. */ + data_size = sizeof(*di) + name->len; leaf = path->nodes[0]; slot = path->slots[0]; if (data_size + btrfs_item_size(leaf, slot) + @@ -303,8 +302,7 @@ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 index, const char *name, int name_len, - int mod) + u64 index, const struct qstr *name, int mod) { struct btrfs_dir_item *di; struct btrfs_key key; @@ -313,7 +311,8 @@ btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, key.type = BTRFS_DIR_INDEX_KEY; key.offset = index; - di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + di = btrfs_lookup_match_dir(trans, root, path, &key, name->name, + name->len, mod); if (di == ERR_PTR(-ENOENT)) return NULL; @@ -321,9 +320,8 @@ btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, } struct btrfs_dir_item * -btrfs_search_dir_index_item(struct btrfs_root *root, - struct btrfs_path *path, u64 dirid, - const char *name, int name_len) +btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path, + u64 dirid, const struct qstr *name) { struct btrfs_dir_item *di; struct btrfs_key key; @@ -338,7 +336,7 @@ btrfs_search_dir_index_item(struct btrfs_root *root, break; di = btrfs_match_dir_item_name(root->fs_info, path, - name, name_len); + name->name, name->len); if (di) return di; } diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 0eeb5ea87894..61b323517a40 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -10,8 +10,8 @@ #include "print-tree.h" struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, - int slot, const char *name, - int name_len) + int slot, + const struct qstr *name) { struct btrfs_inode_ref *ref; unsigned long ptr; @@ -27,9 +27,10 @@ struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, len = btrfs_inode_ref_name_len(leaf, ref); name_ptr = (unsigned long)(ref + 1); cur_offset += len + sizeof(*ref); - if (len != name_len) + if (len != name->len) continue; - if (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) + if (memcmp_extent_buffer(leaf, name->name, name_ptr, + name->len) == 0) return ref; } return NULL; @@ -37,7 +38,7 @@ struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( struct extent_buffer *leaf, int slot, u64 ref_objectid, - const char *name, int name_len) + const struct qstr *name) { struct btrfs_inode_extref *extref; unsigned long ptr; @@ -60,9 +61,10 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( name_ptr = (unsigned long)(&extref->name); ref_name_len = btrfs_inode_extref_name_len(leaf, extref); - if (ref_name_len == name_len && + if (ref_name_len == name->len && btrfs_inode_extref_parent(leaf, extref) == ref_objectid && - (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0)) + (memcmp_extent_buffer(leaf, name->name, name_ptr, + name->len) == 0)) return extref; cur_offset += ref_name_len + sizeof(*extref); @@ -75,7 +77,7 @@ struct btrfs_inode_extref * btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - const char *name, int name_len, + const struct qstr *name, u64 inode_objectid, u64 ref_objectid, int ins_len, int cow) { @@ -84,7 +86,7 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, key.objectid = inode_objectid; key.type = BTRFS_INODE_EXTREF_KEY; - key.offset = btrfs_extref_hash(ref_objectid, name, name_len); + key.offset = btrfs_extref_hash(ref_objectid, name->name, name->len); ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); if (ret < 0) @@ -92,13 +94,13 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, if (ret > 0) return NULL; return btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], - ref_objectid, name, name_len); + ref_objectid, name); } static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const char *name, int name_len, + const struct qstr *name, u64 inode_objectid, u64 ref_objectid, u64 *index) { @@ -107,14 +109,14 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_inode_extref *extref; struct extent_buffer *leaf; int ret; - int del_len = name_len + sizeof(*extref); + int del_len = name->len + sizeof(*extref); unsigned long ptr; unsigned long item_start; u32 item_size; key.objectid = inode_objectid; key.type = BTRFS_INODE_EXTREF_KEY; - key.offset = btrfs_extref_hash(ref_objectid, name, name_len); + key.offset = btrfs_extref_hash(ref_objectid, name->name, name->len); path = btrfs_alloc_path(); if (!path) @@ -132,7 +134,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, * readonly. */ extref = btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], - ref_objectid, name, name_len); + ref_objectid, name); if (!extref) { btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL); ret = -EROFS; @@ -168,8 +170,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, } int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - const char *name, int name_len, + struct btrfs_root *root, const struct qstr *name, u64 inode_objectid, u64 ref_objectid, u64 *index) { struct btrfs_path *path; @@ -182,7 +183,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, u32 sub_item_len; int ret; int search_ext_refs = 0; - int del_len = name_len + sizeof(*ref); + int del_len = name->len + sizeof(*ref); key.objectid = inode_objectid; key.offset = ref_objectid; @@ -201,8 +202,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, goto out; } - ref = btrfs_find_name_in_backref(path->nodes[0], path->slots[0], name, - name_len); + ref = btrfs_find_name_in_backref(path->nodes[0], path->slots[0], name); if (!ref) { ret = -ENOENT; search_ext_refs = 1; @@ -219,7 +219,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, goto out; } ptr = (unsigned long)ref; - sub_item_len = name_len + sizeof(*ref); + sub_item_len = name->len + sizeof(*ref); item_start = btrfs_item_ptr_offset(leaf, path->slots[0]); memmove_extent_buffer(leaf, ptr, ptr + sub_item_len, item_size - (ptr + sub_item_len - item_start)); @@ -233,7 +233,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, * name in our ref array. Find and remove the extended * inode ref then. */ - return btrfs_del_inode_extref(trans, root, name, name_len, + return btrfs_del_inode_extref(trans, root, name, inode_objectid, ref_objectid, index); } @@ -247,12 +247,13 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, */ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const char *name, int name_len, - u64 inode_objectid, u64 ref_objectid, u64 index) + const struct qstr *name, + u64 inode_objectid, u64 ref_objectid, + u64 index) { struct btrfs_inode_extref *extref; int ret; - int ins_len = name_len + sizeof(*extref); + int ins_len = name->len + sizeof(*extref); unsigned long ptr; struct btrfs_path *path; struct btrfs_key key; @@ -260,7 +261,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, key.objectid = inode_objectid; key.type = BTRFS_INODE_EXTREF_KEY; - key.offset = btrfs_extref_hash(ref_objectid, name, name_len); + key.offset = btrfs_extref_hash(ref_objectid, name->name, name->len); path = btrfs_alloc_path(); if (!path) @@ -272,7 +273,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, if (btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], ref_objectid, - name, name_len)) + name)) goto out; btrfs_extend_item(path, ins_len); @@ -286,12 +287,12 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, ptr += btrfs_item_size(leaf, path->slots[0]) - ins_len; extref = (struct btrfs_inode_extref *)ptr; - btrfs_set_inode_extref_name_len(path->nodes[0], extref, name_len); + btrfs_set_inode_extref_name_len(path->nodes[0], extref, name->len); btrfs_set_inode_extref_index(path->nodes[0], extref, index); btrfs_set_inode_extref_parent(path->nodes[0], extref, ref_objectid); ptr = (unsigned long)&extref->name; - write_extent_buffer(path->nodes[0], name, ptr, name_len); + write_extent_buffer(path->nodes[0], name->name, ptr, name->len); btrfs_mark_buffer_dirty(path->nodes[0]); out: @@ -301,8 +302,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, /* Will return 0, -ENOMEM, -EMLINK, or -EEXIST or anything from the CoW path */ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - const char *name, int name_len, + struct btrfs_root *root, const struct qstr *name, u64 inode_objectid, u64 ref_objectid, u64 index) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -311,7 +311,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_inode_ref *ref; unsigned long ptr; int ret; - int ins_len = name_len + sizeof(*ref); + int ins_len = name->len + sizeof(*ref); key.objectid = inode_objectid; key.offset = ref_objectid; @@ -327,7 +327,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, if (ret == -EEXIST) { u32 old_size; ref = btrfs_find_name_in_backref(path->nodes[0], path->slots[0], - name, name_len); + name); if (ref) goto out; @@ -336,7 +336,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ref = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_ref); ref = (struct btrfs_inode_ref *)((unsigned long)ref + old_size); - btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len); + btrfs_set_inode_ref_name_len(path->nodes[0], ref, name->len); btrfs_set_inode_ref_index(path->nodes[0], ref, index); ptr = (unsigned long)(ref + 1); ret = 0; @@ -344,7 +344,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, if (ret == -EOVERFLOW) { if (btrfs_find_name_in_backref(path->nodes[0], path->slots[0], - name, name_len)) + name)) ret = -EEXIST; else ret = -EMLINK; @@ -353,11 +353,11 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, } else { ref = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_ref); - btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len); + btrfs_set_inode_ref_name_len(path->nodes[0], ref, name->len); btrfs_set_inode_ref_index(path->nodes[0], ref, index); ptr = (unsigned long)(ref + 1); } - write_extent_buffer(path->nodes[0], name, ptr, name_len); + write_extent_buffer(path->nodes[0], name->name, ptr, name->len); btrfs_mark_buffer_dirty(path->nodes[0]); out: @@ -370,7 +370,6 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, if (btrfs_super_incompat_flags(disk_super) & BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) ret = btrfs_insert_inode_extref(trans, root, name, - name_len, inode_objectid, ref_objectid, index); } diff --git a/fs/btrfs/inode-item.h b/fs/btrfs/inode-item.h index a8fc16d0147f..3c657c670cfd 100644 --- a/fs/btrfs/inode-item.h +++ b/fs/btrfs/inode-item.h @@ -64,33 +64,31 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_truncate_control *control); int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - const char *name, int name_len, + struct btrfs_root *root, const struct qstr *name, u64 inode_objectid, u64 ref_objectid, u64 index); int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - const char *name, int name_len, - u64 inode_objectid, u64 ref_objectid, u64 *index); + struct btrfs_root *root, const struct qstr *name, + u64 inode_objectid, u64 ref_objectid, u64 *index); int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 objectid); -int btrfs_lookup_inode(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_path *path, +int btrfs_lookup_inode(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *location, int mod); struct btrfs_inode_extref *btrfs_lookup_inode_extref( struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - const char *name, int name_len, + const struct qstr *name, u64 inode_objectid, u64 ref_objectid, int ins_len, int cow); struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, - int slot, const char *name, - int name_len); + int slot, + const struct qstr *name); struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( struct extent_buffer *leaf, int slot, u64 ref_objectid, - const char *name, int name_len); + const struct qstr *name); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 222068bf8003..a5e61ad2ba69 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3627,7 +3627,7 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->delayed_iput_lock); } -/** +/* * Wait for flushing all delayed iputs * * @fs_info: the filesystem @@ -4272,7 +4272,7 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const char *name, int name_len, + const struct qstr *name, struct btrfs_rename_ctx *rename_ctx) { struct btrfs_root *root = dir->root; @@ -4290,8 +4290,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, goto out; } - di = btrfs_lookup_dir_item(trans, root, path, dir_ino, - name, name_len, -1); + di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, -1); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto err; @@ -4319,12 +4318,11 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, } } - ret = btrfs_del_inode_ref(trans, root, name, name_len, ino, - dir_ino, &index); + ret = btrfs_del_inode_ref(trans, root, name, ino, dir_ino, &index); if (ret) { btrfs_info(fs_info, "failed to delete reference to %.*s, inode %llu parent %llu", - name_len, name, ino, dir_ino); + name->len, name->name, ino, dir_ino); btrfs_abort_transaction(trans, ret); goto err; } @@ -4345,10 +4343,8 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, * operations on the log tree, increasing latency for applications. */ if (!rename_ctx) { - btrfs_del_inode_ref_in_log(trans, root, name, name_len, inode, - dir_ino); - btrfs_del_dir_entries_in_log(trans, root, name, name_len, dir, - index); + btrfs_del_inode_ref_in_log(trans, root, name, inode, dir_ino); + btrfs_del_dir_entries_in_log(trans, root, name, dir, index); } /* @@ -4366,7 +4362,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, if (ret) goto out; - btrfs_i_size_write(dir, dir->vfs_inode.i_size - name_len * 2); + btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2); inode_inc_iversion(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode); @@ -4379,10 +4375,11 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const char *name, int name_len) + const struct qstr *name) { int ret; - ret = __btrfs_unlink_inode(trans, dir, inode, name, name_len, NULL); + + ret = __btrfs_unlink_inode(trans, dir, inode, name, NULL); if (!ret) { drop_nlink(&inode->vfs_inode); ret = btrfs_update_inode(trans, inode->root, inode); @@ -4426,9 +4423,8 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), 0); - ret = btrfs_unlink_inode(trans, BTRFS_I(dir), - BTRFS_I(d_inode(dentry)), dentry->d_name.name, - dentry->d_name.len); + ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), + &dentry->d_name); if (ret) goto out; @@ -4453,8 +4449,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key key; - const char *name = dentry->d_name.name; - int name_len = dentry->d_name.len; + const struct qstr *name = &dentry->d_name; u64 index; int ret; u64 objectid; @@ -4473,8 +4468,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - di = btrfs_lookup_dir_item(trans, root, path, dir_ino, - name, name_len, -1); + di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, -1); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; @@ -4500,8 +4494,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, * call btrfs_del_root_ref, and it _shouldn't_ fail. */ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) { - di = btrfs_search_dir_index_item(root, path, dir_ino, - name, name_len); + di = btrfs_search_dir_index_item(root, path, dir_ino, name); if (IS_ERR_OR_NULL(di)) { if (!di) ret = -ENOENT; @@ -4518,7 +4511,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, } else { ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid, dir_ino, - &index, name, name_len); + &index, name); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -4531,7 +4524,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, goto out; } - btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name->len * 2); inode_inc_iversion(dir); dir->i_mtime = current_time(dir); dir->i_ctime = dir->i_mtime; @@ -4553,6 +4546,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root) struct btrfs_path *path; struct btrfs_dir_item *di; struct btrfs_key key; + struct qstr name = QSTR_INIT("default", 7); u64 dir_id; int ret; @@ -4563,7 +4557,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root) /* Make sure this root isn't set as the default subvol */ dir_id = btrfs_super_root_dir(fs_info->super_copy); di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path, - dir_id, "default", 7, 0); + dir_id, &name, 0); if (di && !IS_ERR(di)) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); if (key.objectid == root->root_key.objectid) { @@ -4830,9 +4824,8 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) last_unlink_trans = BTRFS_I(inode)->last_unlink_trans; /* now the directory is empty */ - err = btrfs_unlink_inode(trans, BTRFS_I(dir), - BTRFS_I(d_inode(dentry)), dentry->d_name.name, - dentry->d_name.len); + err = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), + &dentry->d_name); if (!err) { btrfs_i_size_write(BTRFS_I(inode), 0); /* @@ -5532,8 +5525,7 @@ void btrfs_evict_inode(struct inode *inode) static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, struct btrfs_key *location, u8 *type) { - const char *name = dentry->d_name.name; - int namelen = dentry->d_name.len; + const struct qstr *name = &dentry->d_name; struct btrfs_dir_item *di; struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(dir)->root; @@ -5544,7 +5536,7 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, return -ENOMEM; di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)), - name, namelen, 0); + name, 0); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; @@ -5556,7 +5548,7 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, ret = -EUCLEAN; btrfs_warn(root->fs_info, "%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))", - __func__, name, btrfs_ino(BTRFS_I(dir)), + __func__, name->name, btrfs_ino(BTRFS_I(dir)), location->objectid, location->type, location->offset); } if (!ret) @@ -6315,8 +6307,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, { struct inode *dir = args->dir; struct inode *inode = args->inode; - const char *name = args->orphan ? NULL : args->dentry->d_name.name; - int name_len = args->orphan ? 0 : args->dentry->d_name.len; + const struct qstr *name = args->orphan ? NULL : &args->dentry->d_name; struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_root *root; struct btrfs_inode_item *inode_item; @@ -6417,7 +6408,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, sizes[1] = 2 + sizeof(*ref); } else { key[1].offset = btrfs_ino(BTRFS_I(dir)); - sizes[1] = name_len + sizeof(*ref); + sizes[1] = name->len + sizeof(*ref); } } @@ -6456,10 +6447,12 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_ref_index(path->nodes[0], ref, 0); write_extent_buffer(path->nodes[0], "..", ptr, 2); } else { - btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len); + btrfs_set_inode_ref_name_len(path->nodes[0], ref, + name->len); btrfs_set_inode_ref_index(path->nodes[0], ref, BTRFS_I(inode)->dir_index); - write_extent_buffer(path->nodes[0], name, ptr, name_len); + write_extent_buffer(path->nodes[0], name->name, ptr, + name->len); } } @@ -6520,7 +6513,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, ret = btrfs_orphan_add(trans, BTRFS_I(inode)); } else { ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, - name_len, 0, BTRFS_I(inode)->dir_index); + 0, BTRFS_I(inode)->dir_index); } if (ret) { btrfs_abort_transaction(trans, ret); @@ -6549,7 +6542,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, */ int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, - const char *name, int name_len, int add_backref, u64 index) + const struct qstr *name, int add_backref, u64 index) { int ret = 0; struct btrfs_key key; @@ -6568,17 +6561,17 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_add_root_ref(trans, key.objectid, root->root_key.objectid, parent_ino, - index, name, name_len); + index, name); } else if (add_backref) { - ret = btrfs_insert_inode_ref(trans, root, name, name_len, ino, - parent_ino, index); + ret = btrfs_insert_inode_ref(trans, root, name, + ino, parent_ino, index); } /* Nothing to clean up yet */ if (ret) return ret; - ret = btrfs_insert_dir_item(trans, name, name_len, parent_inode, &key, + ret = btrfs_insert_dir_item(trans, name, parent_inode, &key, btrfs_inode_type(&inode->vfs_inode), index); if (ret == -EEXIST || ret == -EOVERFLOW) goto fail_dir_item; @@ -6588,7 +6581,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, } btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size + - name_len * 2); + name->len * 2); inode_inc_iversion(&parent_inode->vfs_inode); /* * If we are replaying a log tree, we do not want to update the mtime @@ -6613,15 +6606,15 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, int err; err = btrfs_del_root_ref(trans, key.objectid, root->root_key.objectid, parent_ino, - &local_index, name, name_len); + &local_index, name); if (err) btrfs_abort_transaction(trans, err); } else if (add_backref) { u64 local_index; int err; - err = btrfs_del_inode_ref(trans, root, name, name_len, - ino, parent_ino, &local_index); + err = btrfs_del_inode_ref(trans, root, name, ino, parent_ino, + &local_index); if (err) btrfs_abort_transaction(trans, err); } @@ -6741,7 +6734,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), - dentry->d_name.name, dentry->d_name.len, 1, index); + &dentry->d_name, 1, index); if (err) { drop_inode = 1; @@ -9115,9 +9108,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, dest, - new_dentry->d_name.name, - new_dentry->d_name.len, + ret = btrfs_insert_inode_ref(trans, dest, &new_dentry->d_name, old_ino, btrfs_ino(BTRFS_I(new_dir)), old_idx); @@ -9131,9 +9122,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, root, - old_dentry->d_name.name, - old_dentry->d_name.len, + ret = btrfs_insert_inode_ref(trans, root, &old_dentry->d_name, new_ino, btrfs_ino(BTRFS_I(old_dir)), new_idx); @@ -9169,8 +9158,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, } else { /* src is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(old_dentry->d_inode), - old_dentry->d_name.name, - old_dentry->d_name.len, + &old_dentry->d_name, &old_rename_ctx); if (!ret) ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); @@ -9186,8 +9174,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, } else { /* dest is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(new_dentry->d_inode), - new_dentry->d_name.name, - new_dentry->d_name.len, + &new_dentry->d_name, &new_rename_ctx); if (!ret) ret = btrfs_update_inode(trans, dest, BTRFS_I(new_inode)); @@ -9198,16 +9185,14 @@ static int btrfs_rename_exchange(struct inode *old_dir, } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), - new_dentry->d_name.name, - new_dentry->d_name.len, 0, old_idx); + &new_dentry->d_name, 0, old_idx); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; } ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode), - old_dentry->d_name.name, - old_dentry->d_name.len, 0, new_idx); + &old_dentry->d_name, 0, new_idx); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; @@ -9308,8 +9293,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, /* check for collisions, even if the name isn't there */ ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, - new_dentry->d_name.name, - new_dentry->d_name.len); + &new_dentry->d_name); if (ret) { if (ret == -EEXIST) { @@ -9403,9 +9387,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, dest, - new_dentry->d_name.name, - new_dentry->d_name.len, + ret = btrfs_insert_inode_ref(trans, dest, &new_dentry->d_name, old_ino, btrfs_ino(BTRFS_I(new_dir)), index); if (ret) @@ -9429,10 +9411,8 @@ static int btrfs_rename(struct user_namespace *mnt_userns, ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); } else { ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), - BTRFS_I(d_inode(old_dentry)), - old_dentry->d_name.name, - old_dentry->d_name.len, - &rename_ctx); + BTRFS_I(d_inode(old_dentry)), + &old_dentry->d_name, &rename_ctx); if (!ret) ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } @@ -9451,8 +9431,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } else { ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(d_inode(new_dentry)), - new_dentry->d_name.name, - new_dentry->d_name.len); + &new_dentry->d_name); } if (!ret && new_inode->i_nlink == 0) ret = btrfs_orphan_add(trans, @@ -9464,8 +9443,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), - new_dentry->d_name.name, - new_dentry->d_name.len, 0, index); + &new_dentry->d_name, 0, index); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2e29fafe0e7d..5305d98905ce 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -951,6 +951,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, struct inode *dir = d_inode(parent->dentry); struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct dentry *dentry; + struct qstr name_str = QSTR_INIT(name, namelen); int error; error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); @@ -971,8 +972,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, * check for them now when we can safely fail */ error = btrfs_check_dir_item_collision(BTRFS_I(dir)->root, - dir->i_ino, name, - namelen); + dir->i_ino, &name_str); if (error) goto out_dput; @@ -3782,6 +3782,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) struct btrfs_trans_handle *trans; struct btrfs_path *path = NULL; struct btrfs_disk_key disk_key; + struct qstr name = QSTR_INIT("default", 7); u64 objectid = 0; u64 dir_id; int ret; @@ -3825,7 +3826,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) dir_id = btrfs_super_root_dir(fs_info->super_copy); di = btrfs_lookup_dir_item(trans, fs_info->tree_root, path, - dir_id, "default", 7, 1); + dir_id, &name, 1); if (IS_ERR_OR_NULL(di)) { btrfs_release_path(path); btrfs_end_transaction(trans); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index e1f599d7a916..cf29241b9b31 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -327,9 +327,8 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, } int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, - u64 ref_id, u64 dirid, u64 *sequence, const char *name, - int name_len) - + u64 ref_id, u64 dirid, u64 *sequence, + const struct qstr *name) { struct btrfs_root *tree_root = trans->fs_info->tree_root; struct btrfs_path *path; @@ -356,8 +355,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, struct btrfs_root_ref); ptr = (unsigned long)(ref + 1); if ((btrfs_root_ref_dirid(leaf, ref) != dirid) || - (btrfs_root_ref_name_len(leaf, ref) != name_len) || - memcmp_extent_buffer(leaf, name, ptr, name_len)) { + (btrfs_root_ref_name_len(leaf, ref) != name->len) || + memcmp_extent_buffer(leaf, name->name, ptr, name->len)) { ret = -ENOENT; goto out; } @@ -400,8 +399,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, * Will return 0, -ENOMEM, or anything from the CoW path */ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, - u64 ref_id, u64 dirid, u64 sequence, const char *name, - int name_len) + u64 ref_id, u64 dirid, u64 sequence, + const struct qstr *name) { struct btrfs_root *tree_root = trans->fs_info->tree_root; struct btrfs_key key; @@ -420,7 +419,7 @@ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_insert_empty_item(trans, tree_root, path, &key, - sizeof(*ref) + name_len); + sizeof(*ref) + name->len); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_free_path(path); @@ -431,9 +430,9 @@ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); btrfs_set_root_ref_dirid(leaf, ref, dirid); btrfs_set_root_ref_sequence(leaf, ref, sequence); - btrfs_set_root_ref_name_len(leaf, ref, name_len); + btrfs_set_root_ref_name_len(leaf, ref, name->len); ptr = (unsigned long)(ref + 1); - write_extent_buffer(leaf, name, ptr, name_len); + write_extent_buffer(leaf, name->name, ptr, name->len); btrfs_mark_buffer_dirty(leaf); if (key.type == BTRFS_ROOT_BACKREF_KEY) { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 35e889fe2a95..833364527554 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1596,13 +1596,17 @@ static int gen_unique_name(struct send_ctx *sctx, return -ENOMEM; while (1) { + struct qstr tmp_name; + len = snprintf(tmp, sizeof(tmp), "o%llu-%llu-%llu", ino, gen, idx); ASSERT(len < sizeof(tmp)); + tmp_name.name = tmp; + tmp_name.len = strlen(tmp); di = btrfs_lookup_dir_item(NULL, sctx->send_root, path, BTRFS_FIRST_FREE_OBJECTID, - tmp, strlen(tmp), 0); + &tmp_name, 0); btrfs_release_path(path); if (IS_ERR(di)) { ret = PTR_ERR(di); @@ -1622,7 +1626,7 @@ static int gen_unique_name(struct send_ctx *sctx, di = btrfs_lookup_dir_item(NULL, sctx->parent_root, path, BTRFS_FIRST_FREE_OBJECTID, - tmp, strlen(tmp), 0); + &tmp_name, 0); btrfs_release_path(path); if (IS_ERR(di)) { ret = PTR_ERR(di); @@ -1752,13 +1756,13 @@ static int lookup_dir_item_inode(struct btrfs_root *root, struct btrfs_dir_item *di; struct btrfs_key key; struct btrfs_path *path; + struct qstr name_str = QSTR_INIT(name, name_len); path = alloc_path_for_send(); if (!path) return -ENOMEM; - di = btrfs_lookup_dir_item(NULL, root, path, - dir, name, name_len, 0); + di = btrfs_lookup_dir_item(NULL, root, path, dir, &name_str, 0); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 582b71b7fa77..bf56e4d6b9f4 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1398,6 +1398,7 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec struct btrfs_dir_item *di; struct btrfs_path *path; struct btrfs_key location; + struct qstr name = QSTR_INIT("default", 7); u64 dir_id; path = btrfs_alloc_path(); @@ -1410,7 +1411,7 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec * to mount. */ dir_id = btrfs_super_root_dir(fs_info->super_copy); - di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0); + di = btrfs_lookup_dir_item(NULL, root, path, dir_id, &name, 0); if (IS_ERR(di)) { btrfs_free_path(path); return PTR_ERR(di); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index a55556759441..b0fe054c9f40 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1694,8 +1694,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, /* check if there is a file/dir which has the same name. */ dir_item = btrfs_lookup_dir_item(NULL, parent_root, path, btrfs_ino(BTRFS_I(parent_inode)), - dentry->d_name.name, - dentry->d_name.len, 0); + &dentry->d_name, 0); if (dir_item != NULL && !IS_ERR(dir_item)) { pending->error = -EEXIST; goto dir_item_existed; @@ -1790,7 +1789,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_add_root_ref(trans, objectid, parent_root->root_key.objectid, btrfs_ino(BTRFS_I(parent_inode)), index, - dentry->d_name.name, dentry->d_name.len); + &dentry->d_name); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; @@ -1822,9 +1821,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, if (ret < 0) goto fail; - ret = btrfs_insert_dir_item(trans, dentry->d_name.name, - dentry->d_name.len, BTRFS_I(parent_inode), - &key, BTRFS_FT_DIR, index); + ret = btrfs_insert_dir_item(trans, &dentry->d_name, + BTRFS_I(parent_inode), &key, BTRFS_FT_DIR, + index); /* We have check then name at the beginning, so it is impossible. */ BUG_ON(ret == -EEXIST || ret == -EOVERFLOW); if (ret) { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 00be69ce7b90..9f55e81acc0e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -595,6 +595,21 @@ static int overwrite_item(struct btrfs_trans_handle *trans, return do_overwrite_item(trans, root, path, eb, slot, key); } +static int read_alloc_one_name(struct extent_buffer *eb, void *start, int len, + struct qstr *name) +{ + char *buf; + + buf = kmalloc(len, GFP_NOFS); + if (!buf) + return -ENOMEM; + + read_extent_buffer(eb, buf, (unsigned long)start, len); + name->name = buf; + name->len = len; + return 0; +} + /* * simple helper to read an inode off the disk from a given root * This can only be called for subvolume roots and not for the log @@ -901,12 +916,11 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, static int unlink_inode_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const char *name, - int name_len) + const struct qstr *name) { int ret; - ret = btrfs_unlink_inode(trans, dir, inode, name, name_len); + ret = btrfs_unlink_inode(trans, dir, inode, name); if (ret) return ret; /* @@ -933,8 +947,7 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, { struct btrfs_root *root = dir->root; struct inode *inode; - char *name; - int name_len; + struct qstr name; struct extent_buffer *leaf; struct btrfs_key location; int ret; @@ -942,12 +955,10 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, leaf = path->nodes[0]; btrfs_dir_item_key_to_cpu(leaf, di, &location); - name_len = btrfs_dir_name_len(leaf, di); - name = kmalloc(name_len, GFP_NOFS); - if (!name) + ret = read_alloc_one_name(leaf, di + 1, btrfs_dir_name_len(leaf, di), &name); + if (ret) return -ENOMEM; - read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len); btrfs_release_path(path); inode = read_one_inode(root, location.objectid); @@ -960,10 +971,9 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, if (ret) goto out; - ret = unlink_inode_for_log_replay(trans, dir, BTRFS_I(inode), name, - name_len); + ret = unlink_inode_for_log_replay(trans, dir, BTRFS_I(inode), &name); out: - kfree(name); + kfree(name.name); iput(inode); return ret; } @@ -978,14 +988,14 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 objectid, u64 index, - const char *name, int name_len) + struct qstr *name) { struct btrfs_dir_item *di; struct btrfs_key location; int ret = 0; di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, - index, name, name_len, 0); + index, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; @@ -998,7 +1008,7 @@ static noinline int inode_in_dir(struct btrfs_root *root, } btrfs_release_path(path); - di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0); + di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; @@ -1025,7 +1035,7 @@ static noinline int inode_in_dir(struct btrfs_root *root, static noinline int backref_in_log(struct btrfs_root *log, struct btrfs_key *key, u64 ref_objectid, - const char *name, int namelen) + const struct qstr *name) { struct btrfs_path *path; int ret; @@ -1045,12 +1055,10 @@ static noinline int backref_in_log(struct btrfs_root *log, if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], - ref_objectid, - name, namelen); + ref_objectid, name); else ret = !!btrfs_find_name_in_backref(path->nodes[0], - path->slots[0], - name, namelen); + path->slots[0], name); out: btrfs_free_path(path); return ret; @@ -1063,11 +1071,9 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, u64 inode_objectid, u64 parent_objectid, - u64 ref_index, char *name, int namelen) + u64 ref_index, struct qstr *name) { int ret; - char *victim_name; - int victim_name_len; struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key search_key; @@ -1099,43 +1105,40 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); ptr_end = ptr + btrfs_item_size(leaf, path->slots[0]); while (ptr < ptr_end) { - victim_ref = (struct btrfs_inode_ref *)ptr; - victim_name_len = btrfs_inode_ref_name_len(leaf, - victim_ref); - victim_name = kmalloc(victim_name_len, GFP_NOFS); - if (!victim_name) - return -ENOMEM; + struct qstr victim_name; - read_extent_buffer(leaf, victim_name, - (unsigned long)(victim_ref + 1), - victim_name_len); + victim_ref = (struct btrfs_inode_ref *)ptr; + ret = read_alloc_one_name(leaf, (victim_ref + 1), + btrfs_inode_ref_name_len(leaf, victim_ref), + &victim_name); + if (ret) + return ret; ret = backref_in_log(log_root, &search_key, - parent_objectid, victim_name, - victim_name_len); + parent_objectid, &victim_name); if (ret < 0) { - kfree(victim_name); + kfree(victim_name.name); return ret; } else if (!ret) { inc_nlink(&inode->vfs_inode); btrfs_release_path(path); ret = unlink_inode_for_log_replay(trans, dir, inode, - victim_name, victim_name_len); - kfree(victim_name); + &victim_name); + kfree(victim_name.name); if (ret) return ret; goto again; } - kfree(victim_name); + kfree(victim_name.name); - ptr = (unsigned long)(victim_ref + 1) + victim_name_len; + ptr = (unsigned long)(victim_ref + 1) + victim_name.len; } } btrfs_release_path(path); /* Same search but for extended refs */ - extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen, + extref = btrfs_lookup_inode_extref(NULL, root, path, name, inode_objectid, parent_objectid, 0, 0); if (IS_ERR(extref)) { @@ -1152,29 +1155,28 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { - extref = (struct btrfs_inode_extref *)(base + cur_offset); + struct qstr victim_name; - victim_name_len = btrfs_inode_extref_name_len(leaf, extref); + extref = (struct btrfs_inode_extref *)(base + cur_offset); if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid) goto next; - victim_name = kmalloc(victim_name_len, GFP_NOFS); - if (!victim_name) - return -ENOMEM; - read_extent_buffer(leaf, victim_name, (unsigned long)&extref->name, - victim_name_len); + ret = read_alloc_one_name(leaf, &extref->name, + btrfs_inode_extref_name_len(leaf, extref), + &victim_name); + if (ret) + return ret; search_key.objectid = inode_objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = btrfs_extref_hash(parent_objectid, - victim_name, - victim_name_len); + victim_name.name, + victim_name.len); ret = backref_in_log(log_root, &search_key, - parent_objectid, victim_name, - victim_name_len); + parent_objectid, &victim_name); if (ret < 0) { - kfree(victim_name); + kfree(victim_name.name); return ret; } else if (!ret) { ret = -ENOENT; @@ -1186,26 +1188,24 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, ret = unlink_inode_for_log_replay(trans, BTRFS_I(victim_parent), - inode, - victim_name, - victim_name_len); + inode, &victim_name); } iput(victim_parent); - kfree(victim_name); + kfree(victim_name.name); if (ret) return ret; goto again; } - kfree(victim_name); + kfree(victim_name.name); next: - cur_offset += victim_name_len + sizeof(*extref); + cur_offset += victim_name.len + sizeof(*extref); } } btrfs_release_path(path); /* look for a conflicting sequence number */ di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), - ref_index, name, namelen, 0); + ref_index, name, 0); if (IS_ERR(di)) { return PTR_ERR(di); } else if (di) { @@ -1216,8 +1216,7 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, btrfs_release_path(path); /* look for a conflicting name */ - di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), - name, namelen, 0); + di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), name, 0); if (IS_ERR(di)) { return PTR_ERR(di); } else if (di) { @@ -1231,20 +1230,18 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, } static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - u32 *namelen, char **name, u64 *index, + struct qstr *name, u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; + int ret; extref = (struct btrfs_inode_extref *)ref_ptr; - *namelen = btrfs_inode_extref_name_len(eb, extref); - *name = kmalloc(*namelen, GFP_NOFS); - if (*name == NULL) - return -ENOMEM; - - read_extent_buffer(eb, *name, (unsigned long)&extref->name, - *namelen); + ret = read_alloc_one_name(eb, &extref->name, + btrfs_inode_extref_name_len(eb, extref), name); + if (ret) + return ret; if (index) *index = btrfs_inode_extref_index(eb, extref); @@ -1255,18 +1252,17 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, } static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - u32 *namelen, char **name, u64 *index) + struct qstr *name, u64 *index) { struct btrfs_inode_ref *ref; + int ret; ref = (struct btrfs_inode_ref *)ref_ptr; - *namelen = btrfs_inode_ref_name_len(eb, ref); - *name = kmalloc(*namelen, GFP_NOFS); - if (*name == NULL) - return -ENOMEM; - - read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen); + ret = read_alloc_one_name(eb, ref + 1, btrfs_inode_ref_name_len(eb, ref), + name); + if (ret) + return ret; if (index) *index = btrfs_inode_ref_index(eb, ref); @@ -1308,28 +1304,24 @@ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]); ref_end = ref_ptr + btrfs_item_size(eb, path->slots[0]); while (ref_ptr < ref_end) { - char *name = NULL; - int namelen; + struct qstr name; u64 parent_id; if (key->type == BTRFS_INODE_EXTREF_KEY) { - ret = extref_get_fields(eb, ref_ptr, &namelen, &name, + ret = extref_get_fields(eb, ref_ptr, &name, NULL, &parent_id); } else { parent_id = key->offset; - ret = ref_get_fields(eb, ref_ptr, &namelen, &name, - NULL); + ret = ref_get_fields(eb, ref_ptr, &name, NULL); } if (ret) goto out; if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(log_eb, log_slot, - parent_id, name, - namelen); + parent_id, &name); else - ret = !!btrfs_find_name_in_backref(log_eb, log_slot, - name, namelen); + ret = !!btrfs_find_name_in_backref(log_eb, log_slot, &name); if (!ret) { struct inode *dir; @@ -1338,20 +1330,20 @@ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, dir = read_one_inode(root, parent_id); if (!dir) { ret = -ENOENT; - kfree(name); + kfree(name.name); goto out; } ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), - inode, name, namelen); - kfree(name); + inode, &name); + kfree(name.name); iput(dir); if (ret) goto out; goto again; } - kfree(name); - ref_ptr += namelen; + kfree(name.name); + ref_ptr += name.len; if (key->type == BTRFS_INODE_EXTREF_KEY) ref_ptr += sizeof(struct btrfs_inode_extref); else @@ -1380,8 +1372,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, struct inode *inode = NULL; unsigned long ref_ptr; unsigned long ref_end; - char *name = NULL; - int namelen; + struct qstr name; int ret; int log_ref_ver = 0; u64 parent_objectid; @@ -1425,7 +1416,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, while (ref_ptr < ref_end) { if (log_ref_ver) { - ret = extref_get_fields(eb, ref_ptr, &namelen, &name, + ret = extref_get_fields(eb, ref_ptr, &name, &ref_index, &parent_objectid); /* * parent object can change from one array @@ -1438,15 +1429,13 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, goto out; } } else { - ret = ref_get_fields(eb, ref_ptr, &namelen, &name, - &ref_index); + ret = ref_get_fields(eb, ref_ptr, &name, &ref_index); } if (ret) goto out; ret = inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), - btrfs_ino(BTRFS_I(inode)), ref_index, - name, namelen); + btrfs_ino(BTRFS_I(inode)), ref_index, &name); if (ret < 0) { goto out; } else if (ret == 0) { @@ -1460,7 +1449,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, ret = __add_inode_ref(trans, root, path, log, BTRFS_I(dir), BTRFS_I(inode), inode_objectid, parent_objectid, - ref_index, name, namelen); + ref_index, &name); if (ret) { if (ret == 1) ret = 0; @@ -1469,7 +1458,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, /* insert our name */ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), - name, namelen, 0, ref_index); + &name, 0, ref_index); if (ret) goto out; @@ -1479,9 +1468,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } /* Else, ret == 1, we already have a perfect match, we're done. */ - ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen; - kfree(name); - name = NULL; + ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + name.len; + kfree(name.name); + name.name = NULL; if (log_ref_ver) { iput(dir); dir = NULL; @@ -1505,7 +1494,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, ret = overwrite_item(trans, root, path, eb, slot, key); out: btrfs_release_path(path); - kfree(name); + kfree(name.name); iput(dir); iput(inode); return ret; @@ -1777,7 +1766,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, static noinline int insert_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 dirid, u64 index, - char *name, int name_len, + const struct qstr *name, struct btrfs_key *location) { struct inode *inode; @@ -1795,7 +1784,7 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, } ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, - name_len, 1, index); + 1, index); /* FIXME, put inode into FIXUP list */ @@ -1855,8 +1844,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_dir_item *di, struct btrfs_key *key) { - char *name; - int name_len; + struct qstr name; struct btrfs_dir_item *dir_dst_di; struct btrfs_dir_item *index_dst_di; bool dir_dst_matches = false; @@ -1874,17 +1862,11 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, if (!dir) return -EIO; - name_len = btrfs_dir_name_len(eb, di); - name = kmalloc(name_len, GFP_NOFS); - if (!name) { - ret = -ENOMEM; + ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); + if (ret) goto out; - } log_type = btrfs_dir_type(eb, di); - read_extent_buffer(eb, name, (unsigned long)(di + 1), - name_len); - btrfs_dir_item_key_to_cpu(eb, di, &log_key); ret = btrfs_lookup_inode(trans, root, path, &log_key, 0); btrfs_release_path(path); @@ -1894,7 +1876,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, ret = 0; dir_dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid, - name, name_len, 1); + &name, 1); if (IS_ERR(dir_dst_di)) { ret = PTR_ERR(dir_dst_di); goto out; @@ -1911,7 +1893,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, index_dst_di = btrfs_lookup_dir_index_item(trans, root, path, key->objectid, key->offset, - name, name_len, 1); + &name, 1); if (IS_ERR(index_dst_di)) { ret = PTR_ERR(index_dst_di); goto out; @@ -1939,7 +1921,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = key->objectid; - ret = backref_in_log(root->log_root, &search_key, 0, name, name_len); + ret = backref_in_log(root->log_root, &search_key, 0, &name); if (ret < 0) { goto out; } else if (ret) { @@ -1952,8 +1934,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = key->objectid; - ret = backref_in_log(root->log_root, &search_key, key->objectid, name, - name_len); + ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; } else if (ret) { @@ -1964,7 +1945,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, } btrfs_release_path(path); ret = insert_one_name(trans, root, key->objectid, key->offset, - name, name_len, &log_key); + &name, &log_key); if (ret && ret != -ENOENT && ret != -EEXIST) goto out; if (!ret) @@ -1974,10 +1955,10 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, out: if (!ret && update_size) { - btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name.len * 2); ret = btrfs_update_inode(trans, root, BTRFS_I(dir)); } - kfree(name); + kfree(name.name); iput(dir); if (!ret && name_added) ret = 1; @@ -2143,8 +2124,7 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, struct extent_buffer *eb; int slot; struct btrfs_dir_item *di; - int name_len; - char *name; + struct qstr name; struct inode *inode = NULL; struct btrfs_key location; @@ -2159,22 +2139,16 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, eb = path->nodes[0]; slot = path->slots[0]; di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); - name_len = btrfs_dir_name_len(eb, di); - name = kmalloc(name_len, GFP_NOFS); - if (!name) { - ret = -ENOMEM; + ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); + if (ret) goto out; - } - - read_extent_buffer(eb, name, (unsigned long)(di + 1), name_len); if (log) { struct btrfs_dir_item *log_di; log_di = btrfs_lookup_dir_index_item(trans, log, log_path, dir_key->objectid, - dir_key->offset, - name, name_len, 0); + dir_key->offset, &name, 0); if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); goto out; @@ -2200,7 +2174,7 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, inc_nlink(inode); ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), BTRFS_I(inode), - name, name_len); + &name); /* * Unlike dir item keys, dir index keys can only have one name (entry) in * them, as there are no key collisions since each key has a unique offset @@ -2209,7 +2183,7 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, out: btrfs_release_path(path); btrfs_release_path(log_path); - kfree(name); + kfree(name.name); iput(inode); return ret; } @@ -3443,7 +3417,7 @@ static int del_logged_dentry(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dir_ino, - const char *name, int name_len, + const struct qstr *name, u64 index) { struct btrfs_dir_item *di; @@ -3453,7 +3427,7 @@ static int del_logged_dentry(struct btrfs_trans_handle *trans, * for dir item keys. */ di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino, - index, name, name_len, -1); + index, name, -1); if (IS_ERR(di)) return PTR_ERR(di); else if (!di) @@ -3490,7 +3464,7 @@ static int del_logged_dentry(struct btrfs_trans_handle *trans, */ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const char *name, int name_len, + const struct qstr *name, struct btrfs_inode *dir, u64 index) { struct btrfs_path *path; @@ -3517,7 +3491,7 @@ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } ret = del_logged_dentry(trans, root->log_root, path, btrfs_ino(dir), - name, name_len, index); + name, index); btrfs_free_path(path); out_unlock: mutex_unlock(&dir->log_mutex); @@ -3529,7 +3503,7 @@ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, /* see comments for btrfs_del_dir_entries_in_log */ void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const char *name, int name_len, + const struct qstr *name, struct btrfs_inode *inode, u64 dirid) { struct btrfs_root *log; @@ -3550,7 +3524,7 @@ void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, log = root->log_root; mutex_lock(&inode->log_mutex); - ret = btrfs_del_inode_ref(trans, log, name, name_len, btrfs_ino(inode), + ret = btrfs_del_inode_ref(trans, log, name, btrfs_ino(inode), dirid, &index); mutex_unlock(&inode->log_mutex); if (ret < 0 && ret != -ENOENT) @@ -5293,6 +5267,7 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, u32 this_len; unsigned long name_ptr; struct btrfs_dir_item *di; + struct qstr name_str; if (key->type == BTRFS_INODE_REF_KEY) { struct btrfs_inode_ref *iref; @@ -5326,8 +5301,11 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, } read_extent_buffer(eb, name, name_ptr, this_name_len); + + name_str.name = name; + name_str.len = this_name_len; di = btrfs_lookup_dir_item(NULL, inode->root, search_path, - parent, name, this_name_len, 0); + parent, &name_str, 0); if (di && !IS_ERR(di)) { struct btrfs_key di_key; @@ -7530,8 +7508,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), - old_dentry->d_name.name, - old_dentry->d_name.len, old_dir_index); + &old_dentry->d_name, old_dir_index); if (ret > 0) { /* * The dentry does not exist in the log, so record its diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index bcca74128c3b..6c0dc79787f0 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -84,11 +84,11 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct btrfs_log_ctx *ctx); void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const char *name, int name_len, + const struct qstr *name, struct btrfs_inode *dir, u64 index); void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const char *name, int name_len, + const struct qstr *name, struct btrfs_inode *inode, u64 dirid); void btrfs_end_log_trans(struct btrfs_root *root); void btrfs_pin_log_trans(struct btrfs_root *root); From 68ad364ec8dd43f977dd58b28b4eb26f1826ddea Mon Sep 17 00:00:00 2001 From: Sweet Tea Dorminy Date: Thu, 20 Oct 2022 12:58:26 -0400 Subject: [PATCH 1929/2093] btrfs: setup qstr from dentrys using fscrypt helper [ Upstream commit ab3c5c18e8fa3f8ea116016095d25adab466cd39 ] Most places where we get a struct qstr, we are doing so from a dentry. With fscrypt, the dentry's name may be encrypted on-disk, so fscrypt provides a helper to convert a dentry name to the appropriate disk name if necessary. Convert each of the dentry name accesses to use fscrypt_setup_filename(), then convert the resulting fscrypt_name back to an unencrypted qstr. This does not work for nokey names, but the specific locations that could spawn nokey names are noted. At present, since there are no encrypted directories, nothing goes down the filename encryption paths. Signed-off-by: Sweet Tea Dorminy Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 9af86694fd5d ("btrfs: file_remove_privs needs an exclusive lock in direct io write") Signed-off-by: Sasha Levin --- fs/btrfs/ctree.h | 3 + fs/btrfs/inode.c | 192 +++++++++++++++++++++++++++++++---------- fs/btrfs/transaction.c | 40 ++++++--- fs/btrfs/tree-log.c | 11 ++- 4 files changed, 189 insertions(+), 57 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 6718cee57a94..5120cea15b09 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -28,6 +28,7 @@ #include #include #include +#include #include "extent-io-tree.h" #include "extent_io.h" #include "extent_map.h" @@ -3396,6 +3397,8 @@ struct btrfs_new_inode_args { */ struct posix_acl *default_acl; struct posix_acl *acl; + struct fscrypt_name fname; + struct qstr name; }; int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, unsigned int *trans_num_items); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a5e61ad2ba69..b5224dbaa416 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4415,28 +4415,41 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) struct btrfs_trans_handle *trans; struct inode *inode = d_inode(dentry); int ret; + struct fscrypt_name fname; + struct qstr name; + + ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); + if (ret) + return ret; + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); + + /* This needs to handle no-key deletions later on */ trans = __unlink_start_trans(dir); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto fscrypt_free; + } btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), 0); ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), - &dentry->d_name); + &name); if (ret) - goto out; + goto end_trans; if (inode->i_nlink == 0) { ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) - goto out; + goto end_trans; } -out: +end_trans: btrfs_end_transaction(trans); btrfs_btree_balance_dirty(BTRFS_I(dir)->root->fs_info); +fscrypt_free: + fscrypt_free_filename(&fname); return ret; } @@ -4449,11 +4462,19 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key key; - const struct qstr *name = &dentry->d_name; + struct qstr name; u64 index; int ret; u64 objectid; u64 dir_ino = btrfs_ino(BTRFS_I(dir)); + struct fscrypt_name fname; + + ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); + if (ret) + return ret; + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); + + /* This needs to handle no-key deletions later on */ if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) { objectid = inode->root->root_key.objectid; @@ -4461,14 +4482,17 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, objectid = inode->location.objectid; } else { WARN_ON(1); + fscrypt_free_filename(&fname); return -EINVAL; } path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } - di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, -1); + di = btrfs_lookup_dir_item(trans, root, path, dir_ino, &name, -1); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; @@ -4494,7 +4518,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, * call btrfs_del_root_ref, and it _shouldn't_ fail. */ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) { - di = btrfs_search_dir_index_item(root, path, dir_ino, name); + di = btrfs_search_dir_index_item(root, path, dir_ino, &name); if (IS_ERR_OR_NULL(di)) { if (!di) ret = -ENOENT; @@ -4511,7 +4535,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, } else { ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid, dir_ino, - &index, name); + &index, &name); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -4524,7 +4548,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, goto out; } - btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name->len * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name.len * 2); inode_inc_iversion(dir); dir->i_mtime = current_time(dir); dir->i_ctime = dir->i_mtime; @@ -4533,6 +4557,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, btrfs_abort_transaction(trans, ret); out: btrfs_free_path(path); + fscrypt_free_filename(&fname); return ret; } @@ -4796,6 +4821,8 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) int err = 0; struct btrfs_trans_handle *trans; u64 last_unlink_trans; + struct fscrypt_name fname; + struct qstr name; if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; @@ -4808,9 +4835,18 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) return btrfs_delete_subvolume(dir, dentry); } + err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); + if (err) + return err; + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); + + /* This needs to handle no-key deletions later on */ + trans = __unlink_start_trans(dir); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto out_notrans; + } if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { err = btrfs_unlink_subvol(trans, dir, dentry); @@ -4825,7 +4861,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) /* now the directory is empty */ err = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), - &dentry->d_name); + &name); if (!err) { btrfs_i_size_write(BTRFS_I(inode), 0); /* @@ -4844,7 +4880,9 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) } out: btrfs_end_transaction(trans); +out_notrans: btrfs_btree_balance_dirty(fs_info); + fscrypt_free_filename(&fname); return err; } @@ -5525,18 +5563,27 @@ void btrfs_evict_inode(struct inode *inode) static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, struct btrfs_key *location, u8 *type) { - const struct qstr *name = &dentry->d_name; + struct qstr name; struct btrfs_dir_item *di; struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(dir)->root; int ret = 0; + struct fscrypt_name fname; path = btrfs_alloc_path(); if (!path) return -ENOMEM; + ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); + if (ret) + goto out; + + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); + + /* This needs to handle no-key deletions later on */ + di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)), - name, 0); + &name, 0); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; @@ -5548,12 +5595,13 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, ret = -EUCLEAN; btrfs_warn(root->fs_info, "%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))", - __func__, name->name, btrfs_ino(BTRFS_I(dir)), + __func__, name.name, btrfs_ino(BTRFS_I(dir)), location->objectid, location->type, location->offset); } if (!ret) *type = btrfs_dir_type(path->nodes[0], di); out: + fscrypt_free_filename(&fname); btrfs_free_path(path); return ret; } @@ -5576,6 +5624,14 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info, struct btrfs_key key; int ret; int err = 0; + struct fscrypt_name fname; + struct qstr name; + + ret = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname); + if (ret) + return ret; + + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); path = btrfs_alloc_path(); if (!path) { @@ -5598,12 +5654,11 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(BTRFS_I(dir)) || - btrfs_root_ref_name_len(leaf, ref) != dentry->d_name.len) + btrfs_root_ref_name_len(leaf, ref) != name.len) goto out; - ret = memcmp_extent_buffer(leaf, dentry->d_name.name, - (unsigned long)(ref + 1), - dentry->d_name.len); + ret = memcmp_extent_buffer(leaf, name.name, (unsigned long)(ref + 1), + name.len); if (ret) goto out; @@ -5622,6 +5677,7 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info, err = 0; out: btrfs_free_path(path); + fscrypt_free_filename(&fname); return err; } @@ -6230,9 +6286,19 @@ int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, struct inode *inode = args->inode; int ret; + if (!args->orphan) { + ret = fscrypt_setup_filename(dir, &args->dentry->d_name, 0, + &args->fname); + if (ret) + return ret; + args->name = (struct qstr)FSTR_TO_QSTR(&args->fname.disk_name); + } + ret = posix_acl_create(dir, &inode->i_mode, &args->default_acl, &args->acl); - if (ret) + if (ret) { + fscrypt_free_filename(&args->fname); return ret; + } /* 1 to add inode item */ *trans_num_items = 1; @@ -6272,6 +6338,7 @@ void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args) { posix_acl_release(args->acl); posix_acl_release(args->default_acl); + fscrypt_free_filename(&args->fname); } /* @@ -6697,6 +6764,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct btrfs_root *root = BTRFS_I(dir)->root; struct inode *inode = d_inode(old_dentry); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct fscrypt_name fname; + struct qstr name; u64 index; int err; int drop_inode = 0; @@ -6708,6 +6777,12 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, if (inode->i_nlink >= BTRFS_LINK_MAX) return -EMLINK; + err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname); + if (err) + goto fail; + + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); + err = btrfs_set_inode_index(BTRFS_I(dir), &index); if (err) goto fail; @@ -6734,7 +6809,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), - &dentry->d_name, 1, index); + &name, 1, index); if (err) { drop_inode = 1; @@ -6758,6 +6833,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, } fail: + fscrypt_free_filename(&fname); if (trans) btrfs_end_transaction(trans); if (drop_inode) { @@ -9030,6 +9106,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, int ret; int ret2; bool need_abort = false; + struct fscrypt_name old_fname, new_fname; + struct qstr old_name, new_name; /* * For non-subvolumes allow exchange only within one subvolume, in the @@ -9041,6 +9119,19 @@ static int btrfs_rename_exchange(struct inode *old_dir, new_ino != BTRFS_FIRST_FREE_OBJECTID)) return -EXDEV; + ret = fscrypt_setup_filename(old_dir, &old_dentry->d_name, 0, &old_fname); + if (ret) + return ret; + + ret = fscrypt_setup_filename(new_dir, &new_dentry->d_name, 0, &new_fname); + if (ret) { + fscrypt_free_filename(&old_fname); + return ret; + } + + old_name = (struct qstr)FSTR_TO_QSTR(&old_fname.disk_name); + new_name = (struct qstr)FSTR_TO_QSTR(&new_fname.disk_name); + /* close the race window with snapshot create/destroy ioctl */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID || new_ino == BTRFS_FIRST_FREE_OBJECTID) @@ -9108,8 +9199,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, dest, &new_dentry->d_name, - old_ino, + ret = btrfs_insert_inode_ref(trans, dest, &new_name, old_ino, btrfs_ino(BTRFS_I(new_dir)), old_idx); if (ret) @@ -9122,8 +9212,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, root, &old_dentry->d_name, - new_ino, + ret = btrfs_insert_inode_ref(trans, root, &old_name, new_ino, btrfs_ino(BTRFS_I(old_dir)), new_idx); if (ret) { @@ -9158,8 +9247,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, } else { /* src is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(old_dentry->d_inode), - &old_dentry->d_name, - &old_rename_ctx); + &old_name, &old_rename_ctx); if (!ret) ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } @@ -9174,8 +9262,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, } else { /* dest is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(new_dentry->d_inode), - &new_dentry->d_name, - &new_rename_ctx); + &new_name, &new_rename_ctx); if (!ret) ret = btrfs_update_inode(trans, dest, BTRFS_I(new_inode)); } @@ -9185,14 +9272,14 @@ static int btrfs_rename_exchange(struct inode *old_dir, } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), - &new_dentry->d_name, 0, old_idx); + &new_name, 0, old_idx); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; } ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode), - &old_dentry->d_name, 0, new_idx); + &old_name, 0, new_idx); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; @@ -9235,6 +9322,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); + fscrypt_free_filename(&new_fname); + fscrypt_free_filename(&old_fname); return ret; } @@ -9274,6 +9363,8 @@ static int btrfs_rename(struct user_namespace *mnt_userns, int ret; int ret2; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); + struct fscrypt_name old_fname, new_fname; + struct qstr old_name, new_name; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9290,21 +9381,32 @@ static int btrfs_rename(struct user_namespace *mnt_userns, new_inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; + ret = fscrypt_setup_filename(old_dir, &old_dentry->d_name, 0, &old_fname); + if (ret) + return ret; + + ret = fscrypt_setup_filename(new_dir, &new_dentry->d_name, 0, &new_fname); + if (ret) { + fscrypt_free_filename(&old_fname); + return ret; + } + + old_name = (struct qstr)FSTR_TO_QSTR(&old_fname.disk_name); + new_name = (struct qstr)FSTR_TO_QSTR(&new_fname.disk_name); /* check for collisions, even if the name isn't there */ - ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, - &new_dentry->d_name); + ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, &new_name); if (ret) { if (ret == -EEXIST) { /* we shouldn't get * eexist without a new_inode */ if (WARN_ON(!new_inode)) { - return ret; + goto out_fscrypt_names; } } else { /* maybe -EOVERFLOW */ - return ret; + goto out_fscrypt_names; } } ret = 0; @@ -9387,8 +9489,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, dest, &new_dentry->d_name, - old_ino, + ret = btrfs_insert_inode_ref(trans, dest, &new_name, old_ino, btrfs_ino(BTRFS_I(new_dir)), index); if (ret) goto out_fail; @@ -9412,7 +9513,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } else { ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), - &old_dentry->d_name, &rename_ctx); + &old_name, &rename_ctx); if (!ret) ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } @@ -9431,7 +9532,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } else { ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(d_inode(new_dentry)), - &new_dentry->d_name); + &new_name); } if (!ret && new_inode->i_nlink == 0) ret = btrfs_orphan_add(trans, @@ -9443,7 +9544,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), - &new_dentry->d_name, 0, index); + &new_name, 0, index); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; @@ -9478,6 +9579,9 @@ static int btrfs_rename(struct user_namespace *mnt_userns, out_whiteout_inode: if (flags & RENAME_WHITEOUT) iput(whiteout_args.inode); +out_fscrypt_names: + fscrypt_free_filename(&old_fname); + fscrypt_free_filename(&new_fname); return ret; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b0fe054c9f40..c8918bdf15cc 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -1627,10 +1628,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root *root = pending->root; struct btrfs_root *parent_root; struct btrfs_block_rsv *rsv; - struct inode *parent_inode; + struct inode *parent_inode = pending->dir; struct btrfs_path *path; struct btrfs_dir_item *dir_item; - struct dentry *dentry; struct extent_buffer *tmp; struct extent_buffer *old; struct timespec64 cur_time; @@ -1639,6 +1639,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, u64 index = 0; u64 objectid; u64 root_flags; + unsigned int nofs_flags; + struct fscrypt_name fname; + struct qstr name; ASSERT(pending->path); path = pending->path; @@ -1646,9 +1649,23 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ASSERT(pending->root_item); new_root_item = pending->root_item; + /* + * We're inside a transaction and must make sure that any potential + * allocations with GFP_KERNEL in fscrypt won't recurse back to + * filesystem. + */ + nofs_flags = memalloc_nofs_save(); + pending->error = fscrypt_setup_filename(parent_inode, + &pending->dentry->d_name, 0, + &fname); + memalloc_nofs_restore(nofs_flags); + if (pending->error) + goto free_pending; + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); + pending->error = btrfs_get_free_objectid(tree_root, &objectid); if (pending->error) - goto no_free_objectid; + goto free_fname; /* * Make qgroup to skip current new snapshot's qgroupid, as it is @@ -1677,8 +1694,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, trace_btrfs_space_reservation(fs_info, "transaction", trans->transid, trans->bytes_reserved, 1); - dentry = pending->dentry; - parent_inode = pending->dir; parent_root = BTRFS_I(parent_inode)->root; ret = record_root_in_trans(trans, parent_root, 0); if (ret) @@ -1694,7 +1709,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, /* check if there is a file/dir which has the same name. */ dir_item = btrfs_lookup_dir_item(NULL, parent_root, path, btrfs_ino(BTRFS_I(parent_inode)), - &dentry->d_name, 0); + &name, 0); if (dir_item != NULL && !IS_ERR(dir_item)) { pending->error = -EEXIST; goto dir_item_existed; @@ -1789,7 +1804,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_add_root_ref(trans, objectid, parent_root->root_key.objectid, btrfs_ino(BTRFS_I(parent_inode)), index, - &dentry->d_name); + &name); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; @@ -1821,9 +1836,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, if (ret < 0) goto fail; - ret = btrfs_insert_dir_item(trans, &dentry->d_name, - BTRFS_I(parent_inode), &key, BTRFS_FT_DIR, - index); + ret = btrfs_insert_dir_item(trans, &name, BTRFS_I(parent_inode), &key, + BTRFS_FT_DIR, index); /* We have check then name at the beginning, so it is impossible. */ BUG_ON(ret == -EEXIST || ret == -EOVERFLOW); if (ret) { @@ -1832,7 +1846,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size + - dentry->d_name.len * 2); + name.len * 2); parent_inode->i_mtime = current_time(parent_inode); parent_inode->i_ctime = parent_inode->i_mtime; ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode)); @@ -1864,7 +1878,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, trans->bytes_reserved = 0; clear_skip_qgroup: btrfs_clear_skip_qgroup(trans); -no_free_objectid: +free_fname: + fscrypt_free_filename(&fname); +free_pending: kfree(new_root_item); pending->root_item = NULL; btrfs_free_path(path); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9f55e81acc0e..25fd3f34b8f2 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7471,9 +7471,16 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, if (old_dir && old_dir->logged_trans == trans->transid) { struct btrfs_root *log = old_dir->root->log_root; struct btrfs_path *path; + struct fscrypt_name fname; + struct qstr name; ASSERT(old_dir_index >= BTRFS_DIR_START_INDEX); + ret = fscrypt_setup_filename(&old_dir->vfs_inode, + &old_dentry->d_name, 0, &fname); + if (ret) + goto out; + name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); /* * We have two inodes to update in the log, the old directory and * the inode that got renamed, so we must pin the log to prevent @@ -7493,6 +7500,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; + fscrypt_free_filename(&fname); goto out; } @@ -7508,7 +7516,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), - &old_dentry->d_name, old_dir_index); + &name, old_dir_index); if (ret > 0) { /* * The dentry does not exist in the log, so record its @@ -7522,6 +7530,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, mutex_unlock(&old_dir->log_mutex); btrfs_free_path(path); + fscrypt_free_filename(&fname); if (ret < 0) goto out; } From ef54db5b5df70f40b7bee8498cb308b1f419e5bb Mon Sep 17 00:00:00 2001 From: Sweet Tea Dorminy Date: Thu, 20 Oct 2022 12:58:27 -0400 Subject: [PATCH 1930/2093] btrfs: use struct fscrypt_str instead of struct qstr [ Upstream commit 6db75318823a169e836a478ca57d6a7c0a156b77 ] While struct qstr is more natural without fscrypt, since it's provided by dentries, struct fscrypt_str is provided by the fscrypt handlers processing dentries, and is thus more natural in the fscrypt world. Replace all of the struct qstr uses with struct fscrypt_str. Signed-off-by: Sweet Tea Dorminy Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 9af86694fd5d ("btrfs: file_remove_privs needs an exclusive lock in direct io write") Signed-off-by: Sasha Levin --- fs/btrfs/ctree.h | 19 +++++---- fs/btrfs/dir-item.c | 10 ++--- fs/btrfs/inode-item.c | 14 +++---- fs/btrfs/inode-item.h | 10 ++--- fs/btrfs/inode.c | 87 +++++++++++++++++------------------------- fs/btrfs/ioctl.c | 4 +- fs/btrfs/root-tree.c | 4 +- fs/btrfs/send.c | 4 +- fs/btrfs/super.c | 2 +- fs/btrfs/transaction.c | 13 +++---- fs/btrfs/tree-log.c | 42 ++++++++++---------- fs/btrfs/tree-log.h | 4 +- 12 files changed, 95 insertions(+), 118 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5120cea15b09..27d06bb5e5c0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3240,10 +3240,10 @@ static inline void btrfs_clear_sb_rdonly(struct super_block *sb) /* root-item.c */ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 sequence, - const struct qstr *name); + const struct fscrypt_str *name); int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 *sequence, - const struct qstr *name); + const struct fscrypt_str *name); int btrfs_del_root(struct btrfs_trans_handle *trans, const struct btrfs_key *key); int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3272,23 +3272,23 @@ int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info); /* dir-item.c */ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, - const struct qstr *name); + const struct fscrypt_str *name); int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, - const struct qstr *name, struct btrfs_inode *dir, + const struct fscrypt_str *name, struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index); struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - const struct qstr *name, int mod); + const struct fscrypt_str *name, int mod); struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 index, const struct qstr *name, int mod); + u64 index, const struct fscrypt_str *name, int mod); struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, - const struct qstr *name); + const struct fscrypt_str *name); int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, @@ -3369,10 +3369,10 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const struct qstr *name); + const struct fscrypt_str *name); int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, - const struct qstr *name, int add_backref, u64 index); + const struct fscrypt_str *name, int add_backref, u64 index); int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry); int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len, int front); @@ -3398,7 +3398,6 @@ struct btrfs_new_inode_args { struct posix_acl *default_acl; struct posix_acl *acl; struct fscrypt_name fname; - struct qstr name; }; int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, unsigned int *trans_num_items); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 8c60f37eb13f..fdab48c1abb8 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -104,7 +104,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, * Will return 0 or -ENOMEM */ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, - const struct qstr *name, struct btrfs_inode *dir, + const struct fscrypt_str *name, struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index) { int ret = 0; @@ -206,7 +206,7 @@ static struct btrfs_dir_item *btrfs_lookup_match_dir( struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - const struct qstr *name, + const struct fscrypt_str *name, int mod) { struct btrfs_key key; @@ -225,7 +225,7 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, } int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, - const struct qstr *name) + const struct fscrypt_str *name) { int ret; struct btrfs_key key; @@ -302,7 +302,7 @@ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 index, const struct qstr *name, int mod) + u64 index, const struct fscrypt_str *name, int mod) { struct btrfs_dir_item *di; struct btrfs_key key; @@ -321,7 +321,7 @@ btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, struct btrfs_path *path, - u64 dirid, const struct qstr *name) + u64 dirid, const struct fscrypt_str *name) { struct btrfs_dir_item *di; struct btrfs_key key; diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 61b323517a40..5add022d3534 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -11,7 +11,7 @@ struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot, - const struct qstr *name) + const struct fscrypt_str *name) { struct btrfs_inode_ref *ref; unsigned long ptr; @@ -38,7 +38,7 @@ struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( struct extent_buffer *leaf, int slot, u64 ref_objectid, - const struct qstr *name) + const struct fscrypt_str *name) { struct btrfs_inode_extref *extref; unsigned long ptr; @@ -77,7 +77,7 @@ struct btrfs_inode_extref * btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - const struct qstr *name, + const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, int ins_len, int cow) { @@ -100,7 +100,7 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct qstr *name, + const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, u64 *index) { @@ -170,7 +170,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, } int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, const struct qstr *name, + struct btrfs_root *root, const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, u64 *index) { struct btrfs_path *path; @@ -247,7 +247,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, */ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct qstr *name, + const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, u64 index) { @@ -302,7 +302,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, /* Will return 0, -ENOMEM, -EMLINK, or -EEXIST or anything from the CoW path */ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, const struct qstr *name, + struct btrfs_root *root, const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, u64 index) { struct btrfs_fs_info *fs_info = root->fs_info; diff --git a/fs/btrfs/inode-item.h b/fs/btrfs/inode-item.h index 3c657c670cfd..b80aeb715701 100644 --- a/fs/btrfs/inode-item.h +++ b/fs/btrfs/inode-item.h @@ -64,10 +64,10 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_truncate_control *control); int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, const struct qstr *name, + struct btrfs_root *root, const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, u64 index); int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, const struct qstr *name, + struct btrfs_root *root, const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, u64 *index); int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -80,15 +80,15 @@ struct btrfs_inode_extref *btrfs_lookup_inode_extref( struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - const struct qstr *name, + const struct fscrypt_str *name, u64 inode_objectid, u64 ref_objectid, int ins_len, int cow); struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot, - const struct qstr *name); + const struct fscrypt_str *name); struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( struct extent_buffer *leaf, int slot, u64 ref_objectid, - const struct qstr *name); + const struct fscrypt_str *name); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b5224dbaa416..47c5be597368 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4272,7 +4272,7 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const struct qstr *name, + const struct fscrypt_str *name, struct btrfs_rename_ctx *rename_ctx) { struct btrfs_root *root = dir->root; @@ -4375,7 +4375,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const struct qstr *name) + const struct fscrypt_str *name) { int ret; @@ -4416,12 +4416,10 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); int ret; struct fscrypt_name fname; - struct qstr name; ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); if (ret) return ret; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); /* This needs to handle no-key deletions later on */ @@ -4435,7 +4433,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) 0); ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), - &name); + &fname.disk_name); if (ret) goto end_trans; @@ -4462,7 +4460,6 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key key; - struct qstr name; u64 index; int ret; u64 objectid; @@ -4472,7 +4469,6 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); if (ret) return ret; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); /* This needs to handle no-key deletions later on */ @@ -4492,7 +4488,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, goto out; } - di = btrfs_lookup_dir_item(trans, root, path, dir_ino, &name, -1); + di = btrfs_lookup_dir_item(trans, root, path, dir_ino, + &fname.disk_name, -1); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; @@ -4518,7 +4515,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, * call btrfs_del_root_ref, and it _shouldn't_ fail. */ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) { - di = btrfs_search_dir_index_item(root, path, dir_ino, &name); + di = btrfs_search_dir_index_item(root, path, dir_ino, &fname.disk_name); if (IS_ERR_OR_NULL(di)) { if (!di) ret = -ENOENT; @@ -4535,7 +4532,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, } else { ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid, dir_ino, - &index, &name); + &index, &fname.disk_name); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -4548,7 +4545,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, goto out; } - btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name.len * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size - fname.disk_name.len * 2); inode_inc_iversion(dir); dir->i_mtime = current_time(dir); dir->i_ctime = dir->i_mtime; @@ -4571,7 +4568,7 @@ static noinline int may_destroy_subvol(struct btrfs_root *root) struct btrfs_path *path; struct btrfs_dir_item *di; struct btrfs_key key; - struct qstr name = QSTR_INIT("default", 7); + struct fscrypt_str name = FSTR_INIT("default", 7); u64 dir_id; int ret; @@ -4822,7 +4819,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) struct btrfs_trans_handle *trans; u64 last_unlink_trans; struct fscrypt_name fname; - struct qstr name; if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; @@ -4838,7 +4834,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname); if (err) return err; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); /* This needs to handle no-key deletions later on */ @@ -4861,7 +4856,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) /* now the directory is empty */ err = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), - &name); + &fname.disk_name); if (!err) { btrfs_i_size_write(BTRFS_I(inode), 0); /* @@ -5563,7 +5558,6 @@ void btrfs_evict_inode(struct inode *inode) static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, struct btrfs_key *location, u8 *type) { - struct qstr name; struct btrfs_dir_item *di; struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(dir)->root; @@ -5578,12 +5572,10 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, if (ret) goto out; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); - /* This needs to handle no-key deletions later on */ di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)), - &name, 0); + &fname.disk_name, 0); if (IS_ERR_OR_NULL(di)) { ret = di ? PTR_ERR(di) : -ENOENT; goto out; @@ -5595,7 +5587,7 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, ret = -EUCLEAN; btrfs_warn(root->fs_info, "%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))", - __func__, name.name, btrfs_ino(BTRFS_I(dir)), + __func__, fname.disk_name.name, btrfs_ino(BTRFS_I(dir)), location->objectid, location->type, location->offset); } if (!ret) @@ -5625,14 +5617,11 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info, int ret; int err = 0; struct fscrypt_name fname; - struct qstr name; ret = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname); if (ret) return ret; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); - path = btrfs_alloc_path(); if (!path) { err = -ENOMEM; @@ -5654,11 +5643,11 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(BTRFS_I(dir)) || - btrfs_root_ref_name_len(leaf, ref) != name.len) + btrfs_root_ref_name_len(leaf, ref) != fname.disk_name.len) goto out; - ret = memcmp_extent_buffer(leaf, name.name, (unsigned long)(ref + 1), - name.len); + ret = memcmp_extent_buffer(leaf, fname.disk_name.name, + (unsigned long)(ref + 1), fname.disk_name.len); if (ret) goto out; @@ -6291,7 +6280,6 @@ int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args, &args->fname); if (ret) return ret; - args->name = (struct qstr)FSTR_TO_QSTR(&args->fname.disk_name); } ret = posix_acl_create(dir, &inode->i_mode, &args->default_acl, &args->acl); @@ -6374,7 +6362,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, { struct inode *dir = args->dir; struct inode *inode = args->inode; - const struct qstr *name = args->orphan ? NULL : &args->dentry->d_name; + const struct fscrypt_str *name = args->orphan ? NULL : &args->fname.disk_name; struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_root *root; struct btrfs_inode_item *inode_item; @@ -6609,7 +6597,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, */ int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, - const struct qstr *name, int add_backref, u64 index) + const struct fscrypt_str *name, int add_backref, u64 index) { int ret = 0; struct btrfs_key key; @@ -6765,7 +6753,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct inode *inode = d_inode(old_dentry); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct fscrypt_name fname; - struct qstr name; u64 index; int err; int drop_inode = 0; @@ -6781,8 +6768,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, if (err) goto fail; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); - err = btrfs_set_inode_index(BTRFS_I(dir), &index); if (err) goto fail; @@ -6809,7 +6794,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), - &name, 1, index); + &fname.disk_name, 1, index); if (err) { drop_inode = 1; @@ -9107,7 +9092,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, int ret2; bool need_abort = false; struct fscrypt_name old_fname, new_fname; - struct qstr old_name, new_name; + struct fscrypt_str *old_name, *new_name; /* * For non-subvolumes allow exchange only within one subvolume, in the @@ -9129,8 +9114,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, return ret; } - old_name = (struct qstr)FSTR_TO_QSTR(&old_fname.disk_name); - new_name = (struct qstr)FSTR_TO_QSTR(&new_fname.disk_name); + old_name = &old_fname.disk_name; + new_name = &new_fname.disk_name; /* close the race window with snapshot create/destroy ioctl */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID || @@ -9199,7 +9184,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, dest, &new_name, old_ino, + ret = btrfs_insert_inode_ref(trans, dest, new_name, old_ino, btrfs_ino(BTRFS_I(new_dir)), old_idx); if (ret) @@ -9212,7 +9197,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, root, &old_name, new_ino, + ret = btrfs_insert_inode_ref(trans, root, old_name, new_ino, btrfs_ino(BTRFS_I(old_dir)), new_idx); if (ret) { @@ -9247,7 +9232,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, } else { /* src is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(old_dentry->d_inode), - &old_name, &old_rename_ctx); + old_name, &old_rename_ctx); if (!ret) ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } @@ -9262,7 +9247,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, } else { /* dest is an inode */ ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(new_dentry->d_inode), - &new_name, &new_rename_ctx); + new_name, &new_rename_ctx); if (!ret) ret = btrfs_update_inode(trans, dest, BTRFS_I(new_inode)); } @@ -9272,14 +9257,14 @@ static int btrfs_rename_exchange(struct inode *old_dir, } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), - &new_name, 0, old_idx); + new_name, 0, old_idx); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; } ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode), - &old_name, 0, new_idx); + old_name, 0, new_idx); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; @@ -9364,7 +9349,6 @@ static int btrfs_rename(struct user_namespace *mnt_userns, int ret2; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); struct fscrypt_name old_fname, new_fname; - struct qstr old_name, new_name; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9391,12 +9375,8 @@ static int btrfs_rename(struct user_namespace *mnt_userns, return ret; } - old_name = (struct qstr)FSTR_TO_QSTR(&old_fname.disk_name); - new_name = (struct qstr)FSTR_TO_QSTR(&new_fname.disk_name); - /* check for collisions, even if the name isn't there */ - ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, &new_name); - + ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, &new_fname.disk_name); if (ret) { if (ret == -EEXIST) { /* we shouldn't get @@ -9489,8 +9469,9 @@ static int btrfs_rename(struct user_namespace *mnt_userns, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - ret = btrfs_insert_inode_ref(trans, dest, &new_name, old_ino, - btrfs_ino(BTRFS_I(new_dir)), index); + ret = btrfs_insert_inode_ref(trans, dest, &new_fname.disk_name, + old_ino, btrfs_ino(BTRFS_I(new_dir)), + index); if (ret) goto out_fail; } @@ -9513,7 +9494,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } else { ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), - &old_name, &rename_ctx); + &old_fname.disk_name, &rename_ctx); if (!ret) ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } @@ -9532,7 +9513,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } else { ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir), BTRFS_I(d_inode(new_dentry)), - &new_name); + &new_fname.disk_name); } if (!ret && new_inode->i_nlink == 0) ret = btrfs_orphan_add(trans, @@ -9544,7 +9525,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), - &new_name, 0, index); + &new_fname.disk_name, 0, index); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5305d98905ce..9e323420c96d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -951,7 +951,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, struct inode *dir = d_inode(parent->dentry); struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct dentry *dentry; - struct qstr name_str = QSTR_INIT(name, namelen); + struct fscrypt_str name_str = FSTR_INIT((char *)name, namelen); int error; error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); @@ -3782,7 +3782,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) struct btrfs_trans_handle *trans; struct btrfs_path *path = NULL; struct btrfs_disk_key disk_key; - struct qstr name = QSTR_INIT("default", 7); + struct fscrypt_str name = FSTR_INIT("default", 7); u64 objectid = 0; u64 dir_id; int ret; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index cf29241b9b31..7d783f094306 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -328,7 +328,7 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 *sequence, - const struct qstr *name) + const struct fscrypt_str *name) { struct btrfs_root *tree_root = trans->fs_info->tree_root; struct btrfs_path *path; @@ -400,7 +400,7 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, */ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 sequence, - const struct qstr *name) + const struct fscrypt_str *name) { struct btrfs_root *tree_root = trans->fs_info->tree_root; struct btrfs_key key; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 833364527554..547b5c229218 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1596,7 +1596,7 @@ static int gen_unique_name(struct send_ctx *sctx, return -ENOMEM; while (1) { - struct qstr tmp_name; + struct fscrypt_str tmp_name; len = snprintf(tmp, sizeof(tmp), "o%llu-%llu-%llu", ino, gen, idx); @@ -1756,7 +1756,7 @@ static int lookup_dir_item_inode(struct btrfs_root *root, struct btrfs_dir_item *di; struct btrfs_key key; struct btrfs_path *path; - struct qstr name_str = QSTR_INIT(name, name_len); + struct fscrypt_str name_str = FSTR_INIT((char *)name, name_len); path = alloc_path_for_send(); if (!path) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index bf56e4d6b9f4..2c562febd801 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1398,7 +1398,7 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec struct btrfs_dir_item *di; struct btrfs_path *path; struct btrfs_key location; - struct qstr name = QSTR_INIT("default", 7); + struct fscrypt_str name = FSTR_INIT("default", 7); u64 dir_id; path = btrfs_alloc_path(); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c8918bdf15cc..1193214ba8c1 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1641,7 +1641,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, u64 root_flags; unsigned int nofs_flags; struct fscrypt_name fname; - struct qstr name; ASSERT(pending->path); path = pending->path; @@ -1661,7 +1660,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, memalloc_nofs_restore(nofs_flags); if (pending->error) goto free_pending; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); pending->error = btrfs_get_free_objectid(tree_root, &objectid); if (pending->error) @@ -1709,7 +1707,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, /* check if there is a file/dir which has the same name. */ dir_item = btrfs_lookup_dir_item(NULL, parent_root, path, btrfs_ino(BTRFS_I(parent_inode)), - &name, 0); + &fname.disk_name, 0); if (dir_item != NULL && !IS_ERR(dir_item)) { pending->error = -EEXIST; goto dir_item_existed; @@ -1804,7 +1802,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_add_root_ref(trans, objectid, parent_root->root_key.objectid, btrfs_ino(BTRFS_I(parent_inode)), index, - &name); + &fname.disk_name); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; @@ -1836,8 +1834,9 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, if (ret < 0) goto fail; - ret = btrfs_insert_dir_item(trans, &name, BTRFS_I(parent_inode), &key, - BTRFS_FT_DIR, index); + ret = btrfs_insert_dir_item(trans, &fname.disk_name, + BTRFS_I(parent_inode), &key, BTRFS_FT_DIR, + index); /* We have check then name at the beginning, so it is impossible. */ BUG_ON(ret == -EEXIST || ret == -EOVERFLOW); if (ret) { @@ -1846,7 +1845,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size + - name.len * 2); + fname.disk_name.len * 2); parent_inode->i_mtime = current_time(parent_inode); parent_inode->i_ctime = parent_inode->i_mtime; ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode)); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 25fd3f34b8f2..ab7893debf07 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -596,7 +596,7 @@ static int overwrite_item(struct btrfs_trans_handle *trans, } static int read_alloc_one_name(struct extent_buffer *eb, void *start, int len, - struct qstr *name) + struct fscrypt_str *name) { char *buf; @@ -916,7 +916,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, static int unlink_inode_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - const struct qstr *name) + const struct fscrypt_str *name) { int ret; @@ -947,7 +947,7 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, { struct btrfs_root *root = dir->root; struct inode *inode; - struct qstr name; + struct fscrypt_str name; struct extent_buffer *leaf; struct btrfs_key location; int ret; @@ -988,7 +988,7 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 objectid, u64 index, - struct qstr *name) + struct fscrypt_str *name) { struct btrfs_dir_item *di; struct btrfs_key location; @@ -1035,7 +1035,7 @@ static noinline int inode_in_dir(struct btrfs_root *root, static noinline int backref_in_log(struct btrfs_root *log, struct btrfs_key *key, u64 ref_objectid, - const struct qstr *name) + const struct fscrypt_str *name) { struct btrfs_path *path; int ret; @@ -1071,7 +1071,7 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, u64 inode_objectid, u64 parent_objectid, - u64 ref_index, struct qstr *name) + u64 ref_index, struct fscrypt_str *name) { int ret; struct extent_buffer *leaf; @@ -1105,7 +1105,7 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); ptr_end = ptr + btrfs_item_size(leaf, path->slots[0]); while (ptr < ptr_end) { - struct qstr victim_name; + struct fscrypt_str victim_name; victim_ref = (struct btrfs_inode_ref *)ptr; ret = read_alloc_one_name(leaf, (victim_ref + 1), @@ -1155,7 +1155,7 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { - struct qstr victim_name; + struct fscrypt_str victim_name; extref = (struct btrfs_inode_extref *)(base + cur_offset); @@ -1230,7 +1230,7 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, } static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - struct qstr *name, u64 *index, + struct fscrypt_str *name, u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; @@ -1252,7 +1252,7 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, } static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - struct qstr *name, u64 *index) + struct fscrypt_str *name, u64 *index) { struct btrfs_inode_ref *ref; int ret; @@ -1304,7 +1304,7 @@ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]); ref_end = ref_ptr + btrfs_item_size(eb, path->slots[0]); while (ref_ptr < ref_end) { - struct qstr name; + struct fscrypt_str name; u64 parent_id; if (key->type == BTRFS_INODE_EXTREF_KEY) { @@ -1372,7 +1372,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, struct inode *inode = NULL; unsigned long ref_ptr; unsigned long ref_end; - struct qstr name; + struct fscrypt_str name; int ret; int log_ref_ver = 0; u64 parent_objectid; @@ -1766,7 +1766,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, static noinline int insert_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 dirid, u64 index, - const struct qstr *name, + const struct fscrypt_str *name, struct btrfs_key *location) { struct inode *inode; @@ -1844,7 +1844,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_dir_item *di, struct btrfs_key *key) { - struct qstr name; + struct fscrypt_str name; struct btrfs_dir_item *dir_dst_di; struct btrfs_dir_item *index_dst_di; bool dir_dst_matches = false; @@ -2124,7 +2124,7 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, struct extent_buffer *eb; int slot; struct btrfs_dir_item *di; - struct qstr name; + struct fscrypt_str name; struct inode *inode = NULL; struct btrfs_key location; @@ -3417,7 +3417,7 @@ static int del_logged_dentry(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dir_ino, - const struct qstr *name, + const struct fscrypt_str *name, u64 index) { struct btrfs_dir_item *di; @@ -3464,7 +3464,7 @@ static int del_logged_dentry(struct btrfs_trans_handle *trans, */ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct qstr *name, + const struct fscrypt_str *name, struct btrfs_inode *dir, u64 index) { struct btrfs_path *path; @@ -3503,7 +3503,7 @@ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, /* see comments for btrfs_del_dir_entries_in_log */ void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct qstr *name, + const struct fscrypt_str *name, struct btrfs_inode *inode, u64 dirid) { struct btrfs_root *log; @@ -5267,7 +5267,7 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, u32 this_len; unsigned long name_ptr; struct btrfs_dir_item *di; - struct qstr name_str; + struct fscrypt_str name_str; if (key->type == BTRFS_INODE_REF_KEY) { struct btrfs_inode_ref *iref; @@ -7472,7 +7472,6 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_root *log = old_dir->root->log_root; struct btrfs_path *path; struct fscrypt_name fname; - struct qstr name; ASSERT(old_dir_index >= BTRFS_DIR_START_INDEX); @@ -7480,7 +7479,6 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, &old_dentry->d_name, 0, &fname); if (ret) goto out; - name = (struct qstr)FSTR_TO_QSTR(&fname.disk_name); /* * We have two inodes to update in the log, the old directory and * the inode that got renamed, so we must pin the log to prevent @@ -7516,7 +7514,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), - &name, old_dir_index); + &fname.disk_name, old_dir_index); if (ret > 0) { /* * The dentry does not exist in the log, so record its diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 6c0dc79787f0..8adebf4c9ada 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -84,11 +84,11 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct btrfs_log_ctx *ctx); void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct qstr *name, + const struct fscrypt_str *name, struct btrfs_inode *dir, u64 index); void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct qstr *name, + const struct fscrypt_str *name, struct btrfs_inode *inode, u64 dirid); void btrfs_end_log_trans(struct btrfs_root *root); void btrfs_pin_log_trans(struct btrfs_root *root); From dd8c8369305deee68f2fe1a27173b23dc3a2729a Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 27 Jun 2023 14:31:49 -0400 Subject: [PATCH 1931/2093] Revert "NFSv4: Retry LOCK on OLD_STATEID during delegation return" [ Upstream commit 5b4a82a0724af1dfd1320826e0266117b6a57fbd ] Olga Kornievskaia reports that this patch breaks NFSv4.0 state recovery. It also introduces additional complexity in the error paths for cases not related to the original problem. Let's revert it for now, and address the original problem in another manner. This reverts commit f5ea16137a3fa2858620dc9084466491c128535f. Fixes: f5ea16137a3f ("NFSv4: Retry LOCK on OLD_STATEID during delegation return") Reported-by: Kornievskaia, Olga Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b927a7d1b46d..e1297c6bcfbe 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7157,7 +7157,6 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) { struct nfs4_lockdata *data = calldata; struct nfs4_lock_state *lsp = data->lsp; - struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry)); if (!nfs4_sequence_done(task, &data->res.seq_res)) return; @@ -7165,7 +7164,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) data->rpc_status = task->tk_status; switch (task->tk_status) { case 0: - renew_lease(server, data->timestamp); + renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)), + data->timestamp); if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) @@ -7193,8 +7193,6 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) goto out_restart; - else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN) - goto out_restart; } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) goto out_restart; From 9d91134c165f88967944113821c81362ceec24a7 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 9 Jan 2023 12:19:55 -0300 Subject: [PATCH 1932/2093] arm64: Avoid repeated AA64MMFR1_EL1 register read on pagefault path [ Upstream commit a89c6bcdac22bec1bfbe6e64060b4cf5838d4f47 ] Accessing AA64MMFR1_EL1 is expensive in KVM guests, since it is emulated in the hypervisor. In fact, ARM documentation mentions some feature registers are not supposed to be accessed frequently by the OS, and therefore should be emulated for guests [1]. Commit 0388f9c74330 ("arm64: mm: Implement arch_wants_old_prefaulted_pte()") introduced a read of this register in the page fault path. But, even when the feature of setting faultaround pages with the old flag is disabled for a given cpu, we are still paying the cost of checking the register on every pagefault. This results in an explosion of vmexit events in KVM guests, which directly impacts the performance of virtualized workloads. For instance, running kernbench yields a 15% increase in system time solely due to the increased vmexit cycles. This patch avoids the extra cost by using the sanitized cached value. It should be safe to do so, since this register mustn't change for a given cpu. [1] https://developer.arm.com/-/media/Arm%20Developer%20Community/PDF/Learn%20the%20Architecture/Armv8-A%20virtualization.pdf?revision=a765a7df-1a00-434d-b241-357bfda2dd31 Signed-off-by: Gabriel Krisman Bertazi Acked-by: Will Deacon Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20230109151955.8292-1-krisman@suse.de Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/include/asm/cpufeature.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index f73f11b55042..5bf0f9aa4626 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -863,7 +863,11 @@ static inline bool cpu_has_hw_af(void) if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) return false; - mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + /* + * Use cached version to avoid emulated msr operation on KVM + * guests. + */ + mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_HAFDBS_SHIFT); } From ec4162bb70189648ac39dd5a13d4f16e78b15544 Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Wed, 19 Jul 2023 07:52:13 -0700 Subject: [PATCH 1933/2093] net: add sysctl accept_ra_min_rtr_lft MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1671bcfd76fdc0b9e65153cf759153083755fe4c upstream. This change adds a new sysctl accept_ra_min_rtr_lft to specify the minimum acceptable router lifetime in an RA. If the received RA router lifetime is less than the configured value (and not 0), the RA is ignored. This is useful for mobile devices, whose battery life can be impacted by networks that configure RAs with a short lifetime. On such networks, the device should never gain IPv6 provisioning and should attempt to drop RAs via hardware offload, if available. Signed-off-by: Patrick Rohr Cc: Maciej Żenczykowski Cc: Lorenzo Colitti Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- Documentation/networking/ip-sysctl.rst | 8 ++++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 10 ++++++++++ net/ipv6/ndisc.c | 18 ++++++++++++++++-- 5 files changed, 36 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 3301288a7c69..b0e9210f7a28 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2148,6 +2148,14 @@ accept_ra_min_hop_limit - INTEGER Default: 1 +accept_ra_min_rtr_lft - INTEGER + Minimum acceptable router lifetime in Router Advertisement. + + RAs with a router lifetime less than this value shall be + ignored. RAs with a router lifetime of 0 are unaffected. + + Default: 0 + accept_ra_pinfo - BOOLEAN Learn Prefix Information in Router Advertisement. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 15d7529ac953..a4b35f4c89d7 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -33,6 +33,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; + __s32 accept_ra_min_rtr_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 53326dfc59ec..2038eff9b63f 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -198,6 +198,7 @@ enum { DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, + DEVCONF_ACCEPT_RA_MIN_RTR_LFT, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 83be84219824..c7e939c619c9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -202,6 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, + .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -262,6 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, + .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -5601,6 +5603,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; + array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft; } static inline size_t inet6_ifla6_size(void) @@ -6794,6 +6797,13 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "accept_ra_min_rtr_lft", + .data = &ipv6_devconf.accept_ra_min_rtr_lft, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a4d43eb45a9d..c2a6cda4be28 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1284,6 +1284,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", @@ -1291,6 +1293,13 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_linkparms; } + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto skip_linkparms; + } + #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { @@ -1343,8 +1352,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_defrtr; } - lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ @@ -1495,6 +1502,13 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto out; } + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto out; + } + #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, From bad004c384b7f15fa84a6613868c85e3efcf016e Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Wed, 26 Jul 2023 16:07:01 -0700 Subject: [PATCH 1934/2093] net: change accept_ra_min_rtr_lft to affect all RA lifetimes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 5027d54a9c30bc7ec808360378e2b4753f053f25 upstream. accept_ra_min_rtr_lft only considered the lifetime of the default route and discarded entire RAs accordingly. This change renames accept_ra_min_rtr_lft to accept_ra_min_lft, and applies the value to individual RA sections; in particular, router lifetime, PIO preferred lifetime, and RIO lifetime. If any of those lifetimes are lower than the configured value, the specific RA section is ignored. In order for the sysctl to be useful to Android, it should really apply to all lifetimes in the RA, since that is what determines the minimum frequency at which RAs must be processed by the kernel. Android uses hardware offloads to drop RAs for a fraction of the minimum of all lifetimes present in the RA (some networks have very frequent RAs (5s) with high lifetimes (2h)). Despite this, we have encountered networks that set the router lifetime to 30s which results in very frequent CPU wakeups. Instead of disabling IPv6 (and dropping IPv6 ethertype in the WiFi firmware) entirely on such networks, it seems better to ignore the misconfigured routers while still processing RAs from other IPv6 routers on the same network (i.e. to support IoT applications). The previous implementation dropped the entire RA based on router lifetime. This turned out to be hard to expand to the other lifetimes present in the RA in a consistent manner; dropping the entire RA based on RIO/PIO lifetimes would essentially require parsing the whole thing twice. Fixes: 1671bcfd76fd ("net: add sysctl accept_ra_min_rtr_lft") Cc: Lorenzo Colitti Signed-off-by: Patrick Rohr Reviewed-by: Maciej Żenczykowski Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230726230701.919212-1-prohr@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- Documentation/networking/ip-sysctl.rst | 8 ++++---- include/linux/ipv6.h | 2 +- include/uapi/linux/ipv6.h | 2 +- net/ipv6/addrconf.c | 13 ++++++++----- net/ipv6/ndisc.c | 27 +++++++++++--------------- 5 files changed, 25 insertions(+), 27 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b0e9210f7a28..f5f7a464605f 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2148,11 +2148,11 @@ accept_ra_min_hop_limit - INTEGER Default: 1 -accept_ra_min_rtr_lft - INTEGER - Minimum acceptable router lifetime in Router Advertisement. +accept_ra_min_lft - INTEGER + Minimum acceptable lifetime value in Router Advertisement. - RAs with a router lifetime less than this value shall be - ignored. RAs with a router lifetime of 0 are unaffected. + RA sections with a lifetime less than this value shall be + ignored. Zero lifetimes stay unaffected. Default: 0 diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a4b35f4c89d7..9a44de45cc1f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -33,7 +33,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; - __s32 accept_ra_min_rtr_lft; + __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 2038eff9b63f..4fa8511b1e35 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -198,7 +198,7 @@ enum { DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, - DEVCONF_ACCEPT_RA_MIN_RTR_LFT, + DEVCONF_ACCEPT_RA_MIN_LFT, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c7e939c619c9..53db8daa7385 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -202,7 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_rtr_lft = 0, + .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -263,7 +263,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_rtr_lft = 0, + .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -2733,6 +2733,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) return; } + if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) + return; + /* * Two things going on here: * 1) Add routes for on-link prefixes @@ -5603,7 +5606,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; - array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft; + array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft; } static inline size_t inet6_ifla6_size(void) @@ -6798,8 +6801,8 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { - .procname = "accept_ra_min_rtr_lft", - .data = &ipv6_devconf.accept_ra_min_rtr_lft, + .procname = "accept_ra_min_lft", + .data = &ipv6_devconf.accept_ra_min_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index c2a6cda4be28..6cb2d6a536a8 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1284,8 +1284,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", @@ -1293,13 +1291,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_linkparms; } - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto skip_linkparms; - } - #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { @@ -1340,6 +1331,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_defrtr; } + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto skip_defrtr; + } + /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ @@ -1502,13 +1501,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto out; } - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto out; - } - #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, @@ -1533,6 +1525,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (ri->prefix_len == 0 && !in6_dev->cnf.accept_ra_defrtr) continue; + if (ri->lifetime != 0 && + ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft) + continue; if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) From b6912642746d2c48b80c205b26145839a3a412ed Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Fri, 18 Aug 2023 11:22:49 -0700 Subject: [PATCH 1935/2093] net: release reference to inet6_dev pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 5cb249686e67dbef3ffe53887fa725eefc5a7144 upstream. addrconf_prefix_rcv returned early without releasing the inet6_dev pointer when the PIO lifetime is less than accept_ra_min_lft. Fixes: 5027d54a9c30 ("net: change accept_ra_min_rtr_lft to affect all RA lifetimes") Cc: Maciej Żenczykowski Cc: Lorenzo Colitti Cc: David Ahern Cc: Simon Horman Reviewed-by: Simon Horman Reviewed-by: Maciej Żenczykowski Signed-off-by: Patrick Rohr Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/addrconf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 53db8daa7385..96f4351b55a6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2734,7 +2734,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) } if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) - return; + goto put; /* * Two things going on here: From b0fe3786745592fccd9af4e3f6c7d0f76f5b7950 Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Tue, 12 Sep 2023 14:34:29 +0100 Subject: [PATCH 1936/2093] arm64: cpufeature: Fix CLRBHB and BC detection commit 479965a2b7ec481737df0cadf553331063b9c343 upstream. ClearBHB support is indicated by the CLRBHB field in ID_AA64ISAR2_EL1. Following some refactoring the kernel incorrectly checks the BC field instead. Fix the detection to use the right field. (Note: The original ClearBHB support had it as FTR_HIGHER_SAFE, but this patch uses FTR_LOWER_SAFE, which seems more correct.) Also fix the detection of BC (hinted conditional branches) to use FTR_LOWER_SAFE, so that it is not reported on mismatched systems. Fixes: 356137e68a9f ("arm64/sysreg: Make BHB clear feature defines match the architecture") Fixes: 8fcc8285c0e3 ("arm64/sysreg: Convert ID_AA64ISAR2_EL1 to automatic generation") Cc: stable@vger.kernel.org Signed-off-by: Kristina Martsenko Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20230912133429.2606875-1-kristina.martsenko@arm.com Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/cpufeature.h | 2 +- arch/arm64/kernel/cpufeature.c | 3 ++- arch/arm64/tools/sysreg | 6 +++++- 3 files changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 5bf0f9aa4626..a0badda3a8d1 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -670,7 +670,7 @@ static inline bool supports_clearbhb(int scope) isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); return cpuid_feature_extract_unsigned_field(isar2, - ID_AA64ISAR2_EL1_BC_SHIFT); + ID_AA64ISAR2_EL1_CLRBHB_SHIFT); } const struct cpumask *system_32bit_el0_cpumask(void); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index b3eb53847c96..770a31c6ed81 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -212,7 +212,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 384757a7eda9..11c3f7a7cec7 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -484,7 +484,11 @@ EndEnum EndSysreg Sysreg ID_AA64ISAR2_EL1 3 0 0 6 2 -Res0 63:28 +Res0 63:32 +Enum 31:28 CLRBHB + 0b0000 NI + 0b0001 IMP +EndEnum Enum 27:24 PAC_frac 0b0000 NI 0b0001 IMP From 71472872932b11ca2591104eb73255fecaae9d33 Mon Sep 17 00:00:00 2001 From: Wayne Lin Date: Tue, 22 Aug 2023 16:03:17 +0800 Subject: [PATCH 1937/2093] drm/amd/display: Adjust the MST resume flow commit ec5fa9fcdeca69edf7dab5ca3b2e0ceb1c08fe9a upstream. [Why] In drm_dp_mst_topology_mgr_resume() today, it will resume the mst branch to be ready handling mst mode and also consecutively do the mst topology probing. Which will cause the dirver have chance to fire hotplug event before restoring the old state. Then Userspace will react to the hotplug event based on a wrong state. [How] Adjust the mst resume flow as: 1. set dpcd to resume mst branch status 2. restore source old state 3. Do mst resume topology probing For drm_dp_mst_topology_mgr_resume(), it's better to adjust it to pull out topology probing work into a 2nd part procedure of the mst resume. Will have a follow up patch in drm. Reviewed-by: Chao-kai Wang Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Acked-by: Stylon Wang Signed-off-by: Wayne Lin Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher [ Adjust for missing variable rename in f0127cb11299 ("drm/amdgpu/display/mst: adjust the naming of mst_port and port of aconnector") ] Signed-off-by: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 93 ++++++++++++++++--- 1 file changed, 80 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 18274ff5082a..339f1f5a0833 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2344,14 +2344,62 @@ static int dm_late_init(void *handle) return detect_mst_link_for_all_connectors(adev_to_drm(adev)); } +static void resume_mst_branch_status(struct drm_dp_mst_topology_mgr *mgr) +{ + int ret; + u8 guid[16]; + u64 tmp64; + + mutex_lock(&mgr->lock); + if (!mgr->mst_primary) + goto out_fail; + + if (drm_dp_read_dpcd_caps(mgr->aux, mgr->dpcd) < 0) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, + DP_MST_EN | + DP_UP_REQ_EN | + DP_UPSTREAM_IS_SRC); + if (ret < 0) { + drm_dbg_kms(mgr->dev, "mst write failed - undocked during suspend?\n"); + goto out_fail; + } + + /* Some hubs forget their guids after they resume */ + ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (ret != 16) { + drm_dbg_kms(mgr->dev, "dpcd read failed - undocked during suspend?\n"); + goto out_fail; + } + + if (memchr_inv(guid, 0, 16) == NULL) { + tmp64 = get_jiffies_64(); + memcpy(&guid[0], &tmp64, sizeof(u64)); + memcpy(&guid[8], &tmp64, sizeof(u64)); + + ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, guid, 16); + + if (ret != 16) { + drm_dbg_kms(mgr->dev, "check mstb guid failed - undocked during suspend?\n"); + goto out_fail; + } + } + + memcpy(mgr->mst_primary->guid, guid, 16); + +out_fail: + mutex_unlock(&mgr->lock); +} + static void s3_handle_mst(struct drm_device *dev, bool suspend) { struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; struct drm_connector_list_iter iter; struct drm_dp_mst_topology_mgr *mgr; - int ret; - bool need_hotplug = false; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -2373,18 +2421,15 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) if (!dp_is_lttpr_present(aconnector->dc_link)) dc_link_aux_try_to_configure_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); - ret = drm_dp_mst_topology_mgr_resume(mgr, true); - if (ret < 0) { - dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, - aconnector->dc_link); - need_hotplug = true; - } + /* TODO: move resume_mst_branch_status() into drm mst resume again + * once topology probing work is pulled out from mst resume into mst + * resume 2nd step. mst resume 2nd step should be called after old + * state getting restored (i.e. drm_atomic_helper_resume()). + */ + resume_mst_branch_status(mgr); } } drm_connector_list_iter_end(&iter); - - if (need_hotplug) - drm_kms_helper_hotplug_event(dev); } static int amdgpu_dm_smu_write_watermarks_table(struct amdgpu_device *adev) @@ -2773,7 +2818,8 @@ static int dm_resume(void *handle) struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state); enum dc_connection_type new_connection_type = dc_connection_none; struct dc_state *dc_state; - int i, r, j; + int i, r, j, ret; + bool need_hotplug = false; if (amdgpu_in_reset(adev)) { dc_state = dm->cached_dc_state; @@ -2871,7 +2917,7 @@ static int dm_resume(void *handle) continue; /* - * this is the case when traversing through already created + * this is the case when traversing through already created end sink * MST connectors, should be skipped */ if (aconnector && aconnector->mst_port) @@ -2931,6 +2977,27 @@ static int dm_resume(void *handle) dm->cached_state = NULL; + /* Do mst topology probing after resuming cached state*/ + drm_connector_list_iter_begin(ddev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (aconnector->dc_link->type != dc_connection_mst_branch || + aconnector->mst_port) + continue; + + ret = drm_dp_mst_topology_mgr_resume(&aconnector->mst_mgr, true); + + if (ret < 0) { + dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, + aconnector->dc_link); + need_hotplug = true; + } + } + drm_connector_list_iter_end(&iter); + + if (need_hotplug) + drm_kms_helper_hotplug_event(ddev); + amdgpu_dm_irq_resume_late(adev); amdgpu_dm_smu_write_watermarks_table(adev); From 357ba59b9d3bd803a43e9e8e2461a4d0b4907562 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 1 Jun 2023 17:43:33 +0100 Subject: [PATCH 1938/2093] iommu/arm-smmu-v3: Set TTL invalidation hint better [ Upstream commit 6833b8f2e19945a41e4d5efd8c6d9f4cae9a5b7d ] When io-pgtable unmaps a whole table, rather than waste time walking it to find the leaf entries to invalidate exactly, it simply expects .tlb_flush_walk with nominal last-level granularity to invalidate any leaf entries at higher intermediate levels as well. This works fine with page-based invalidation, but with range commands we need to be careful with the TTL hint - unconditionally setting it based on the given level 3 granule means that an invalidation for a level 1 table would strictly not be required to affect level 2 block entries. It's easy to comply with the expected behaviour by simply not setting the TTL hint for non-leaf invalidations, so let's do that. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b409d9a17c52dc0db51faee91d92737bb7975f5b.1685637456.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index db33dc87f69e..becf37c08877 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1889,8 +1889,13 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd, /* Convert page size of 12,14,16 (log2) to 1,2,3 */ cmd->tlbi.tg = (tg - 10) / 2; - /* Determine what level the granule is at */ - cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); + /* + * Determine what level the granule is at. For non-leaf, io-pgtable + * assumes .tlb_flush_walk can invalidate multiple levels at once, + * so ignore the nominal last-level granule and leave TTL=0. + */ + if (cmd->tlbi.leaf) + cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); num_pages = size >> tg; } From ff09fa5f23aa59b43bd58d747930944118a48f3d Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 11 Sep 2023 12:57:04 +0100 Subject: [PATCH 1939/2093] iommu/arm-smmu-v3: Avoid constructing invalid range commands [ Upstream commit eb6c97647be227822c7ce23655482b05e348fba5 ] Although io-pgtable's non-leaf invalidations are always for full tables, I missed that SVA also uses non-leaf invalidations, while being at the mercy of whatever range the MMU notifier throws at it. This means it definitely wants the previous TTL fix as well, since it also doesn't know exactly which leaf level(s) may need invalidating, but it can also give us less-aligned ranges wherein certain corners may lead to building an invalid command where TTL, Num and Scale are all 0. It should be fine to handle this by over-invalidating an extra page, since falling back to a non-range command opens up a whole can of errata-flavoured worms. Fixes: 6833b8f2e199 ("iommu/arm-smmu-v3: Set TTL invalidation hint better") Reported-by: Rui Zhu Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b99cfe71af2bd93a8a2930f20967fb2a4f7748dd.1694432734.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index becf37c08877..8966f7d5aab6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1886,18 +1886,23 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd, /* Get the leaf page size */ tg = __ffs(smmu_domain->domain.pgsize_bitmap); + num_pages = size >> tg; + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ cmd->tlbi.tg = (tg - 10) / 2; /* - * Determine what level the granule is at. For non-leaf, io-pgtable - * assumes .tlb_flush_walk can invalidate multiple levels at once, - * so ignore the nominal last-level granule and leave TTL=0. + * Determine what level the granule is at. For non-leaf, both + * io-pgtable and SVA pass a nominal last-level granule because + * they don't know what level(s) actually apply, so ignore that + * and leave TTL=0. However for various errata reasons we still + * want to use a range command, so avoid the SVA corner case + * where both scale and num could be 0 as well. */ if (cmd->tlbi.leaf) cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); - - num_pages = size >> tg; + else if ((num_pages & CMDQ_TLBI_RANGE_NUM_MAX) == 1) + num_pages++; } cmds.num = 0; From 33ecf5f5a8762b4fb33fe6b4e14338ad62999c76 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 5 Oct 2023 11:59:32 +0200 Subject: [PATCH 1940/2093] rbd: move rbd_dev_refresh() definition commit 0b035401c57021fc6c300272cbb1c5a889d4fe45 upstream. Move rbd_dev_refresh() definition further down to avoid having to move struct parent_image_info definition in the next commit. This spares some forward declarations too. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang [idryomov@gmail.com: backport to 5.10-6.1: context] Signed-off-by: Sasha Levin --- drivers/block/rbd.c | 68 ++++++++++++++++++++++----------------------- 1 file changed, 33 insertions(+), 35 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 74ef3da54536..762795430b4d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -633,8 +633,6 @@ static void rbd_dev_remove_parent(struct rbd_device *rbd_dev); static int rbd_dev_refresh(struct rbd_device *rbd_dev); static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev); -static int rbd_dev_header_info(struct rbd_device *rbd_dev); -static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev); static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev, u64 snap_id); static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, @@ -4932,39 +4930,6 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev) } } -static int rbd_dev_refresh(struct rbd_device *rbd_dev) -{ - u64 mapping_size; - int ret; - - down_write(&rbd_dev->header_rwsem); - mapping_size = rbd_dev->mapping.size; - - ret = rbd_dev_header_info(rbd_dev); - if (ret) - goto out; - - /* - * If there is a parent, see if it has disappeared due to the - * mapped image getting flattened. - */ - if (rbd_dev->parent) { - ret = rbd_dev_v2_parent_info(rbd_dev); - if (ret) - goto out; - } - - rbd_assert(!rbd_is_snap(rbd_dev)); - rbd_dev->mapping.size = rbd_dev->header.image_size; - -out: - up_write(&rbd_dev->header_rwsem); - if (!ret && mapping_size != rbd_dev->mapping.size) - rbd_dev_update_size(rbd_dev); - - return ret; -} - static const struct blk_mq_ops rbd_mq_ops = { .queue_rq = rbd_queue_rq, }; @@ -7044,6 +7009,39 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) return ret; } +static int rbd_dev_refresh(struct rbd_device *rbd_dev) +{ + u64 mapping_size; + int ret; + + down_write(&rbd_dev->header_rwsem); + mapping_size = rbd_dev->mapping.size; + + ret = rbd_dev_header_info(rbd_dev); + if (ret) + goto out; + + /* + * If there is a parent, see if it has disappeared due to the + * mapped image getting flattened. + */ + if (rbd_dev->parent) { + ret = rbd_dev_v2_parent_info(rbd_dev); + if (ret) + goto out; + } + + rbd_assert(!rbd_is_snap(rbd_dev)); + rbd_dev->mapping.size = rbd_dev->header.image_size; + +out: + up_write(&rbd_dev->header_rwsem); + if (!ret && mapping_size != rbd_dev->mapping.size) + rbd_dev_update_size(rbd_dev); + + return ret; +} + static ssize_t do_rbd_add(struct bus_type *bus, const char *buf, size_t count) From 377d26174e1d5412284ce33854d8adcff2129240 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 5 Oct 2023 11:59:33 +0200 Subject: [PATCH 1941/2093] rbd: decouple header read-in from updating rbd_dev->header commit 510a7330c82a7754d5df0117a8589e8a539067c7 upstream. Make rbd_dev_header_info() populate a passed struct rbd_image_header instead of rbd_dev->header and introduce rbd_dev_update_header() for updating mutable fields in rbd_dev->header upon refresh. The initial read-in of both mutable and immutable fields in rbd_dev_image_probe() passes in rbd_dev->header so no update step is required there. rbd_init_layout() is now called directly from rbd_dev_image_probe() instead of individually in format 1 and format 2 implementations. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Sasha Levin --- drivers/block/rbd.c | 210 ++++++++++++++++++++++++-------------------- 1 file changed, 116 insertions(+), 94 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 762795430b4d..b1c44c633857 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -632,7 +632,8 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...) static void rbd_dev_remove_parent(struct rbd_device *rbd_dev); static int rbd_dev_refresh(struct rbd_device *rbd_dev); -static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev); +static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev, + struct rbd_image_header *header); static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev, u64 snap_id); static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, @@ -993,15 +994,24 @@ static void rbd_init_layout(struct rbd_device *rbd_dev) RCU_INIT_POINTER(rbd_dev->layout.pool_ns, NULL); } +static void rbd_image_header_cleanup(struct rbd_image_header *header) +{ + kfree(header->object_prefix); + ceph_put_snap_context(header->snapc); + kfree(header->snap_sizes); + kfree(header->snap_names); + + memset(header, 0, sizeof(*header)); +} + /* * Fill an rbd image header with information from the given format 1 * on-disk header. */ -static int rbd_header_from_disk(struct rbd_device *rbd_dev, - struct rbd_image_header_ondisk *ondisk) +static int rbd_header_from_disk(struct rbd_image_header *header, + struct rbd_image_header_ondisk *ondisk, + bool first_time) { - struct rbd_image_header *header = &rbd_dev->header; - bool first_time = header->object_prefix == NULL; struct ceph_snap_context *snapc; char *object_prefix = NULL; char *snap_names = NULL; @@ -1068,11 +1078,6 @@ static int rbd_header_from_disk(struct rbd_device *rbd_dev, if (first_time) { header->object_prefix = object_prefix; header->obj_order = ondisk->options.order; - rbd_init_layout(rbd_dev); - } else { - ceph_put_snap_context(header->snapc); - kfree(header->snap_names); - kfree(header->snap_sizes); } /* The remaining fields always get updated (when we refresh) */ @@ -4858,7 +4863,9 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev, * return, the rbd_dev->header field will contain up-to-date * information about the image. */ -static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev) +static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev, + struct rbd_image_header *header, + bool first_time) { struct rbd_image_header_ondisk *ondisk = NULL; u32 snap_count = 0; @@ -4906,7 +4913,7 @@ static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev) snap_count = le32_to_cpu(ondisk->snap_count); } while (snap_count != want_count); - ret = rbd_header_from_disk(rbd_dev, ondisk); + ret = rbd_header_from_disk(header, ondisk, first_time); out: kfree(ondisk); @@ -5469,17 +5476,12 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, return 0; } -static int rbd_dev_v2_image_size(struct rbd_device *rbd_dev) -{ - return _rbd_dev_v2_snap_size(rbd_dev, CEPH_NOSNAP, - &rbd_dev->header.obj_order, - &rbd_dev->header.image_size); -} - -static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev) +static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev, + char **pobject_prefix) { size_t size; void *reply_buf; + char *object_prefix; int ret; void *p; @@ -5497,16 +5499,16 @@ static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev) goto out; p = reply_buf; - rbd_dev->header.object_prefix = ceph_extract_encoded_string(&p, - p + ret, NULL, GFP_NOIO); + object_prefix = ceph_extract_encoded_string(&p, p + ret, NULL, + GFP_NOIO); + if (IS_ERR(object_prefix)) { + ret = PTR_ERR(object_prefix); + goto out; + } ret = 0; - if (IS_ERR(rbd_dev->header.object_prefix)) { - ret = PTR_ERR(rbd_dev->header.object_prefix); - rbd_dev->header.object_prefix = NULL; - } else { - dout(" object_prefix = %s\n", rbd_dev->header.object_prefix); - } + *pobject_prefix = object_prefix; + dout(" object_prefix = %s\n", object_prefix); out: kfree(reply_buf); @@ -5557,13 +5559,6 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, return 0; } -static int rbd_dev_v2_features(struct rbd_device *rbd_dev) -{ - return _rbd_dev_v2_snap_features(rbd_dev, CEPH_NOSNAP, - rbd_is_ro(rbd_dev), - &rbd_dev->header.features); -} - /* * These are generic image flags, but since they are used only for * object map, store them in rbd_dev->object_map_flags. @@ -5838,14 +5833,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) return ret; } -static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev) +static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev, + u64 *stripe_unit, u64 *stripe_count) { struct { __le64 stripe_unit; __le64 stripe_count; } __attribute__ ((packed)) striping_info_buf = { 0 }; size_t size = sizeof (striping_info_buf); - void *p; int ret; ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, @@ -5857,27 +5852,33 @@ static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev) if (ret < size) return -ERANGE; - p = &striping_info_buf; - rbd_dev->header.stripe_unit = ceph_decode_64(&p); - rbd_dev->header.stripe_count = ceph_decode_64(&p); + *stripe_unit = le64_to_cpu(striping_info_buf.stripe_unit); + *stripe_count = le64_to_cpu(striping_info_buf.stripe_count); + dout(" stripe_unit = %llu stripe_count = %llu\n", *stripe_unit, + *stripe_count); + return 0; } -static int rbd_dev_v2_data_pool(struct rbd_device *rbd_dev) +static int rbd_dev_v2_data_pool(struct rbd_device *rbd_dev, s64 *data_pool_id) { - __le64 data_pool_id; + __le64 data_pool_buf; int ret; ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, &rbd_dev->header_oloc, "get_data_pool", - NULL, 0, &data_pool_id, sizeof(data_pool_id)); + NULL, 0, &data_pool_buf, + sizeof(data_pool_buf)); + dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret); if (ret < 0) return ret; - if (ret < sizeof(data_pool_id)) + if (ret < sizeof(data_pool_buf)) return -EBADMSG; - rbd_dev->header.data_pool_id = le64_to_cpu(data_pool_id); - WARN_ON(rbd_dev->header.data_pool_id == CEPH_NOPOOL); + *data_pool_id = le64_to_cpu(data_pool_buf); + dout(" data_pool_id = %lld\n", *data_pool_id); + WARN_ON(*data_pool_id == CEPH_NOPOOL); + return 0; } @@ -6069,7 +6070,8 @@ static int rbd_spec_fill_names(struct rbd_device *rbd_dev) return ret; } -static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev) +static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev, + struct ceph_snap_context **psnapc) { size_t size; int ret; @@ -6130,9 +6132,7 @@ static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev) for (i = 0; i < snap_count; i++) snapc->snaps[i] = ceph_decode_64(&p); - ceph_put_snap_context(rbd_dev->header.snapc); - rbd_dev->header.snapc = snapc; - + *psnapc = snapc; dout(" snap context seq = %llu, snap_count = %u\n", (unsigned long long)seq, (unsigned int)snap_count); out: @@ -6181,38 +6181,42 @@ static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev, return snap_name; } -static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev) +static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev, + struct rbd_image_header *header, + bool first_time) { - bool first_time = rbd_dev->header.object_prefix == NULL; int ret; - ret = rbd_dev_v2_image_size(rbd_dev); + ret = _rbd_dev_v2_snap_size(rbd_dev, CEPH_NOSNAP, + first_time ? &header->obj_order : NULL, + &header->image_size); if (ret) return ret; if (first_time) { - ret = rbd_dev_v2_header_onetime(rbd_dev); + ret = rbd_dev_v2_header_onetime(rbd_dev, header); if (ret) return ret; } - ret = rbd_dev_v2_snap_context(rbd_dev); - if (ret && first_time) { - kfree(rbd_dev->header.object_prefix); - rbd_dev->header.object_prefix = NULL; - } + ret = rbd_dev_v2_snap_context(rbd_dev, &header->snapc); + if (ret) + return ret; - return ret; + return 0; } -static int rbd_dev_header_info(struct rbd_device *rbd_dev) +static int rbd_dev_header_info(struct rbd_device *rbd_dev, + struct rbd_image_header *header, + bool first_time) { rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); + rbd_assert(!header->object_prefix && !header->snapc); if (rbd_dev->image_format == 1) - return rbd_dev_v1_header_info(rbd_dev); + return rbd_dev_v1_header_info(rbd_dev, header, first_time); - return rbd_dev_v2_header_info(rbd_dev); + return rbd_dev_v2_header_info(rbd_dev, header, first_time); } /* @@ -6700,60 +6704,49 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev) */ static void rbd_dev_unprobe(struct rbd_device *rbd_dev) { - struct rbd_image_header *header; - rbd_dev_parent_put(rbd_dev); rbd_object_map_free(rbd_dev); rbd_dev_mapping_clear(rbd_dev); /* Free dynamic fields from the header, then zero it out */ - header = &rbd_dev->header; - ceph_put_snap_context(header->snapc); - kfree(header->snap_sizes); - kfree(header->snap_names); - kfree(header->object_prefix); - memset(header, 0, sizeof (*header)); + rbd_image_header_cleanup(&rbd_dev->header); } -static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev) +static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev, + struct rbd_image_header *header) { int ret; - ret = rbd_dev_v2_object_prefix(rbd_dev); + ret = rbd_dev_v2_object_prefix(rbd_dev, &header->object_prefix); if (ret) - goto out_err; + return ret; /* * Get the and check features for the image. Currently the * features are assumed to never change. */ - ret = rbd_dev_v2_features(rbd_dev); + ret = _rbd_dev_v2_snap_features(rbd_dev, CEPH_NOSNAP, + rbd_is_ro(rbd_dev), &header->features); if (ret) - goto out_err; + return ret; /* If the image supports fancy striping, get its parameters */ - if (rbd_dev->header.features & RBD_FEATURE_STRIPINGV2) { - ret = rbd_dev_v2_striping_info(rbd_dev); - if (ret < 0) - goto out_err; - } - - if (rbd_dev->header.features & RBD_FEATURE_DATA_POOL) { - ret = rbd_dev_v2_data_pool(rbd_dev); + if (header->features & RBD_FEATURE_STRIPINGV2) { + ret = rbd_dev_v2_striping_info(rbd_dev, &header->stripe_unit, + &header->stripe_count); if (ret) - goto out_err; + return ret; } - rbd_init_layout(rbd_dev); - return 0; + if (header->features & RBD_FEATURE_DATA_POOL) { + ret = rbd_dev_v2_data_pool(rbd_dev, &header->data_pool_id); + if (ret) + return ret; + } -out_err: - rbd_dev->header.features = 0; - kfree(rbd_dev->header.object_prefix); - rbd_dev->header.object_prefix = NULL; - return ret; + return 0; } /* @@ -6948,13 +6941,15 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) if (!depth) down_write(&rbd_dev->header_rwsem); - ret = rbd_dev_header_info(rbd_dev); + ret = rbd_dev_header_info(rbd_dev, &rbd_dev->header, true); if (ret) { if (ret == -ENOENT && !need_watch) rbd_print_dne(rbd_dev, false); goto err_out_probe; } + rbd_init_layout(rbd_dev); + /* * If this image is the one being mapped, we have pool name and * id, image name and id, and snap name - need to fill snap id. @@ -7009,15 +7004,39 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) return ret; } +static void rbd_dev_update_header(struct rbd_device *rbd_dev, + struct rbd_image_header *header) +{ + rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); + rbd_assert(rbd_dev->header.object_prefix); /* !first_time */ + + rbd_dev->header.image_size = header->image_size; + + ceph_put_snap_context(rbd_dev->header.snapc); + rbd_dev->header.snapc = header->snapc; + header->snapc = NULL; + + if (rbd_dev->image_format == 1) { + kfree(rbd_dev->header.snap_names); + rbd_dev->header.snap_names = header->snap_names; + header->snap_names = NULL; + + kfree(rbd_dev->header.snap_sizes); + rbd_dev->header.snap_sizes = header->snap_sizes; + header->snap_sizes = NULL; + } +} + static int rbd_dev_refresh(struct rbd_device *rbd_dev) { + struct rbd_image_header header = { 0 }; u64 mapping_size; int ret; down_write(&rbd_dev->header_rwsem); mapping_size = rbd_dev->mapping.size; - ret = rbd_dev_header_info(rbd_dev); + ret = rbd_dev_header_info(rbd_dev, &header, false); if (ret) goto out; @@ -7031,6 +7050,8 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev) goto out; } + rbd_dev_update_header(rbd_dev, &header); + rbd_assert(!rbd_is_snap(rbd_dev)); rbd_dev->mapping.size = rbd_dev->header.image_size; @@ -7039,6 +7060,7 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev) if (!ret && mapping_size != rbd_dev->mapping.size) rbd_dev_update_size(rbd_dev); + rbd_image_header_cleanup(&header); return ret; } From 698039a461a357894f8964c67970c53b459705c5 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 5 Oct 2023 11:59:34 +0200 Subject: [PATCH 1942/2093] rbd: decouple parent info read-in from updating rbd_dev commit c10311776f0a8ddea2276df96e255625b07045a8 upstream. Unlike header read-in, parent info read-in is already decoupled in get_parent_info(), but it's buried in rbd_dev_v2_parent_info() along with the processing logic. Separate the initial read-in and update read-in logic into rbd_dev_setup_parent() and rbd_dev_update_parent() respectively and have rbd_dev_v2_parent_info() just populate struct parent_image_info (i.e. what get_parent_info() did). Some existing QoI issues, like flatten of a standalone clone being disregarded on refresh, remain. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Sasha Levin --- drivers/block/rbd.c | 142 +++++++++++++++++++++++++------------------- 1 file changed, 80 insertions(+), 62 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b1c44c633857..38c92b1b0346 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -5595,6 +5595,14 @@ struct parent_image_info { u64 overlap; }; +static void rbd_parent_info_cleanup(struct parent_image_info *pii) +{ + kfree(pii->pool_ns); + kfree(pii->image_id); + + memset(pii, 0, sizeof(*pii)); +} + /* * The caller is responsible for @pii. */ @@ -5664,6 +5672,9 @@ static int __get_parent_info(struct rbd_device *rbd_dev, if (pii->has_overlap) ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii->pool_id, pii->pool_ns, pii->image_id, pii->snap_id, + pii->has_overlap, pii->overlap); return 0; e_inval: @@ -5702,14 +5713,17 @@ static int __get_parent_info_legacy(struct rbd_device *rbd_dev, pii->has_overlap = true; ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii->pool_id, pii->pool_ns, pii->image_id, pii->snap_id, + pii->has_overlap, pii->overlap); return 0; e_inval: return -EINVAL; } -static int get_parent_info(struct rbd_device *rbd_dev, - struct parent_image_info *pii) +static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev, + struct parent_image_info *pii) { struct page *req_page, *reply_page; void *p; @@ -5737,7 +5751,7 @@ static int get_parent_info(struct rbd_device *rbd_dev, return ret; } -static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) +static int rbd_dev_setup_parent(struct rbd_device *rbd_dev) { struct rbd_spec *parent_spec; struct parent_image_info pii = { 0 }; @@ -5747,37 +5761,12 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) if (!parent_spec) return -ENOMEM; - ret = get_parent_info(rbd_dev, &pii); + ret = rbd_dev_v2_parent_info(rbd_dev, &pii); if (ret) goto out_err; - dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", - __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id, - pii.has_overlap, pii.overlap); - - if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) { - /* - * Either the parent never existed, or we have - * record of it but the image got flattened so it no - * longer has a parent. When the parent of a - * layered image disappears we immediately set the - * overlap to 0. The effect of this is that all new - * requests will be treated as if the image had no - * parent. - * - * If !pii.has_overlap, the parent image spec is not - * applicable. It's there to avoid duplication in each - * snapshot record. - */ - if (rbd_dev->parent_overlap) { - rbd_dev->parent_overlap = 0; - rbd_dev_parent_put(rbd_dev); - pr_info("%s: clone image has been flattened\n", - rbd_dev->disk->disk_name); - } - + if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) goto out; /* No parent? No problem. */ - } /* The ceph file layout needs to fit pool id in 32 bits */ @@ -5789,46 +5778,34 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) } /* - * The parent won't change (except when the clone is - * flattened, already handled that). So we only need to - * record the parent spec we have not already done so. + * The parent won't change except when the clone is flattened, + * so we only need to record the parent image spec once. */ - if (!rbd_dev->parent_spec) { - parent_spec->pool_id = pii.pool_id; - if (pii.pool_ns && *pii.pool_ns) { - parent_spec->pool_ns = pii.pool_ns; - pii.pool_ns = NULL; - } - parent_spec->image_id = pii.image_id; - pii.image_id = NULL; - parent_spec->snap_id = pii.snap_id; - - rbd_dev->parent_spec = parent_spec; - parent_spec = NULL; /* rbd_dev now owns this */ + parent_spec->pool_id = pii.pool_id; + if (pii.pool_ns && *pii.pool_ns) { + parent_spec->pool_ns = pii.pool_ns; + pii.pool_ns = NULL; } + parent_spec->image_id = pii.image_id; + pii.image_id = NULL; + parent_spec->snap_id = pii.snap_id; + + rbd_assert(!rbd_dev->parent_spec); + rbd_dev->parent_spec = parent_spec; + parent_spec = NULL; /* rbd_dev now owns this */ /* - * We always update the parent overlap. If it's zero we issue - * a warning, as we will proceed as if there was no parent. + * Record the parent overlap. If it's zero, issue a warning as + * we will proceed as if there is no parent. */ - if (!pii.overlap) { - if (parent_spec) { - /* refresh, careful to warn just once */ - if (rbd_dev->parent_overlap) - rbd_warn(rbd_dev, - "clone now standalone (overlap became 0)"); - } else { - /* initial probe */ - rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); - } - } + if (!pii.overlap) + rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); rbd_dev->parent_overlap = pii.overlap; out: ret = 0; out_err: - kfree(pii.pool_ns); - kfree(pii.image_id); + rbd_parent_info_cleanup(&pii); rbd_spec_put(parent_spec); return ret; } @@ -6978,7 +6955,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) } if (rbd_dev->header.features & RBD_FEATURE_LAYERING) { - ret = rbd_dev_v2_parent_info(rbd_dev); + ret = rbd_dev_setup_parent(rbd_dev); if (ret) goto err_out_probe; } @@ -7027,9 +7004,47 @@ static void rbd_dev_update_header(struct rbd_device *rbd_dev, } } +static void rbd_dev_update_parent(struct rbd_device *rbd_dev, + struct parent_image_info *pii) +{ + if (pii->pool_id == CEPH_NOPOOL || !pii->has_overlap) { + /* + * Either the parent never existed, or we have + * record of it but the image got flattened so it no + * longer has a parent. When the parent of a + * layered image disappears we immediately set the + * overlap to 0. The effect of this is that all new + * requests will be treated as if the image had no + * parent. + * + * If !pii.has_overlap, the parent image spec is not + * applicable. It's there to avoid duplication in each + * snapshot record. + */ + if (rbd_dev->parent_overlap) { + rbd_dev->parent_overlap = 0; + rbd_dev_parent_put(rbd_dev); + pr_info("%s: clone has been flattened\n", + rbd_dev->disk->disk_name); + } + } else { + rbd_assert(rbd_dev->parent_spec); + + /* + * Update the parent overlap. If it became zero, issue + * a warning as we will proceed as if there is no parent. + */ + if (!pii->overlap && rbd_dev->parent_overlap) + rbd_warn(rbd_dev, + "clone has become standalone (overlap 0)"); + rbd_dev->parent_overlap = pii->overlap; + } +} + static int rbd_dev_refresh(struct rbd_device *rbd_dev) { struct rbd_image_header header = { 0 }; + struct parent_image_info pii = { 0 }; u64 mapping_size; int ret; @@ -7045,12 +7060,14 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev) * mapped image getting flattened. */ if (rbd_dev->parent) { - ret = rbd_dev_v2_parent_info(rbd_dev); + ret = rbd_dev_v2_parent_info(rbd_dev, &pii); if (ret) goto out; } rbd_dev_update_header(rbd_dev, &header); + if (rbd_dev->parent) + rbd_dev_update_parent(rbd_dev, &pii); rbd_assert(!rbd_is_snap(rbd_dev)); rbd_dev->mapping.size = rbd_dev->header.image_size; @@ -7060,6 +7077,7 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev) if (!ret && mapping_size != rbd_dev->mapping.size) rbd_dev_update_size(rbd_dev); + rbd_parent_info_cleanup(&pii); rbd_image_header_cleanup(&header); return ret; } From 77d0e7e8e58273c09efb6095661af010843c0048 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 5 Oct 2023 11:59:35 +0200 Subject: [PATCH 1943/2093] rbd: take header_rwsem in rbd_dev_refresh() only when updating commit 0b207d02bd9ab8dcc31b262ca9f60dbc1822500d upstream. rbd_dev_refresh() has been holding header_rwsem across header and parent info read-in unnecessarily for ages. With commit 870611e4877e ("rbd: get snapshot context after exclusive lock is ensured to be held"), the potential for deadlocks became much more real owning to a) header_rwsem now nesting inside lock_rwsem and b) rw_semaphores not allowing new readers after a writer is registered. For example, assuming that I/O request 1, I/O request 2 and header read-in request all target the same OSD: 1. I/O request 1 comes in and gets submitted 2. watch error occurs 3. rbd_watch_errcb() takes lock_rwsem for write, clears owner_cid and releases lock_rwsem 4. after reestablishing the watch, rbd_reregister_watch() calls rbd_dev_refresh() which takes header_rwsem for write and submits a header read-in request 5. I/O request 2 comes in: after taking lock_rwsem for read in __rbd_img_handle_request(), it blocks trying to take header_rwsem for read in rbd_img_object_requests() 6. another watch error occurs 7. rbd_watch_errcb() blocks trying to take lock_rwsem for write 8. I/O request 1 completion is received by the messenger but can't be processed because lock_rwsem won't be granted anymore 9. header read-in request completion can't be received, let alone processed, because the messenger is stranded Change rbd_dev_refresh() to take header_rwsem only for actually updating rbd_dev->header. Header and parent info read-in don't need any locking. Cc: stable@vger.kernel.org # 0b035401c570: rbd: move rbd_dev_refresh() definition Cc: stable@vger.kernel.org # 510a7330c82a: rbd: decouple header read-in from updating rbd_dev->header Cc: stable@vger.kernel.org # c10311776f0a: rbd: decouple parent info read-in from updating rbd_dev Cc: stable@vger.kernel.org Fixes: 870611e4877e ("rbd: get snapshot context after exclusive lock is ensured to be held") Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Sasha Levin --- drivers/block/rbd.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 38c92b1b0346..afc92869cba4 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -6987,7 +6987,14 @@ static void rbd_dev_update_header(struct rbd_device *rbd_dev, rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); rbd_assert(rbd_dev->header.object_prefix); /* !first_time */ - rbd_dev->header.image_size = header->image_size; + if (rbd_dev->header.image_size != header->image_size) { + rbd_dev->header.image_size = header->image_size; + + if (!rbd_is_snap(rbd_dev)) { + rbd_dev->mapping.size = header->image_size; + rbd_dev_update_size(rbd_dev); + } + } ceph_put_snap_context(rbd_dev->header.snapc); rbd_dev->header.snapc = header->snapc; @@ -7045,11 +7052,9 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev) { struct rbd_image_header header = { 0 }; struct parent_image_info pii = { 0 }; - u64 mapping_size; int ret; - down_write(&rbd_dev->header_rwsem); - mapping_size = rbd_dev->mapping.size; + dout("%s rbd_dev %p\n", __func__, rbd_dev); ret = rbd_dev_header_info(rbd_dev, &header, false); if (ret) @@ -7065,18 +7070,13 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev) goto out; } + down_write(&rbd_dev->header_rwsem); rbd_dev_update_header(rbd_dev, &header); if (rbd_dev->parent) rbd_dev_update_parent(rbd_dev, &pii); - - rbd_assert(!rbd_is_snap(rbd_dev)); - rbd_dev->mapping.size = rbd_dev->header.image_size; + up_write(&rbd_dev->header_rwsem); out: - up_write(&rbd_dev->header_rwsem); - if (!ret && mapping_size != rbd_dev->mapping.size) - rbd_dev_update_size(rbd_dev); - rbd_parent_info_cleanup(&pii); rbd_image_header_cleanup(&header); return ret; From 752ec2d93e75ee5a473086f6f6859ea5ba9fb114 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 15 Dec 2022 10:16:29 +0800 Subject: [PATCH 1944/2093] block: fix use-after-free of q->q_usage_counter commit d36a9ea5e7766961e753ee38d4c331bbe6ef659b upstream. For blk-mq, queue release handler is usually called after blk_mq_freeze_queue_wait() returns. However, the q_usage_counter->release() handler may not be run yet at that time, so this can cause a use-after-free. Fix the issue by moving percpu_ref_exit() into blk_free_queue_rcu(). Since ->release() is called with rcu read lock held, it is agreed that the race should be covered in caller per discussion from the two links. Reported-by: Zhang Wensheng Reported-by: Zhong Jinghua Link: https://lore.kernel.org/linux-block/Y5prfOjyyjQKUrtH@T590/T/#u Link: https://lore.kernel.org/lkml/Y4%2FmzMd4evRg9yDi@fedora/ Cc: Hillf Danton Cc: Yu Kuai Cc: Dennis Zhou Fixes: 2b0d3d3e4fcf ("percpu_ref: reduce memory footprint of percpu_ref in fast path") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20221215021629.74870-1-ming.lei@redhat.com Signed-off-by: Jens Axboe Signed-off-by: Saranya Muruganandam Signed-off-by: Greg Kroah-Hartman --- block/blk-sysfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index a582ea0da74f..a82bdec923b2 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -737,6 +737,7 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head) struct request_queue *q = container_of(rcu_head, struct request_queue, rcu_head); + percpu_ref_exit(&q->q_usage_counter); kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q); } @@ -762,8 +763,6 @@ static void blk_release_queue(struct kobject *kobj) might_sleep(); - percpu_ref_exit(&q->q_usage_counter); - if (q->poll_stat) blk_stat_remove_callback(q, q->poll_cb); blk_stat_free_callback(q->poll_cb); From 6ddb9e6b9b6adfee90e0bf2485d16e6ac9c56ab0 Mon Sep 17 00:00:00 2001 From: Herman Fries Date: Wed, 14 Dec 2022 20:46:28 +0100 Subject: [PATCH 1945/2093] hwmon: (nzxt-smart2) Add device id commit e247510e1baad04e9b7b8ed7190dbb00989387b9 upstream. Adding support for new device id 1e71:2019 NZXT NZXT RGB & Fan Controller Signed-off-by: Herman Fries Link: https://lore.kernel.org/r/20221214194627.135692-1-baracoder@googlemail.com Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/nzxt-smart2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c index 533f38b0b4e9..2b93ba89610a 100644 --- a/drivers/hwmon/nzxt-smart2.c +++ b/drivers/hwmon/nzxt-smart2.c @@ -791,6 +791,7 @@ static const struct hid_device_id nzxt_smart2_hid_id_table[] = { { HID_USB_DEVICE(0x1e71, 0x2009) }, /* NZXT RGB & Fan Controller */ { HID_USB_DEVICE(0x1e71, 0x200e) }, /* NZXT RGB & Fan Controller */ { HID_USB_DEVICE(0x1e71, 0x2010) }, /* NZXT RGB & Fan Controller */ + { HID_USB_DEVICE(0x1e71, 0x2019) }, /* NZXT RGB & Fan Controller */ {}, }; From a0829d9cf22e5a8447a1a342204e072763702c15 Mon Sep 17 00:00:00 2001 From: Aleksandr Mezin Date: Sun, 19 Feb 2023 12:59:19 +0200 Subject: [PATCH 1946/2093] hwmon: (nzxt-smart2) add another USB ID commit 4a148e9b1ee04e608263fa9536a96214d5561220 upstream. This seems to be a new revision of the device. RGB controls have changed, but this driver doesn't touch them anyway. Fan speed control reported to be working with existing userspace (hidraw) software, so I assume it's compatible. Fan channel count is the same. Recently added (0x1e71, 0x2019) seems to be the same device. Discovered in liquidctl project: https://github.com/liquidctl/liquidctl/issues/541 Signed-off-by: Aleksandr Mezin Link: https://lore.kernel.org/r/20230219105924.333007-1-mezin.alexander@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/nzxt-smart2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c index 2b93ba89610a..a8e72d8fd060 100644 --- a/drivers/hwmon/nzxt-smart2.c +++ b/drivers/hwmon/nzxt-smart2.c @@ -791,7 +791,8 @@ static const struct hid_device_id nzxt_smart2_hid_id_table[] = { { HID_USB_DEVICE(0x1e71, 0x2009) }, /* NZXT RGB & Fan Controller */ { HID_USB_DEVICE(0x1e71, 0x200e) }, /* NZXT RGB & Fan Controller */ { HID_USB_DEVICE(0x1e71, 0x2010) }, /* NZXT RGB & Fan Controller */ - { HID_USB_DEVICE(0x1e71, 0x2019) }, /* NZXT RGB & Fan Controller */ + { HID_USB_DEVICE(0x1e71, 0x2011) }, /* NZXT RGB & Fan Controller (6 RGB) */ + { HID_USB_DEVICE(0x1e71, 0x2019) }, /* NZXT RGB & Fan Controller (6 RGB) */ {}, }; From ef167cc1882fbbef2fde332d92d22231c6148f4e Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Tue, 26 Sep 2023 15:10:59 +0800 Subject: [PATCH 1947/2093] i40e: fix the wrong PTP frequency calculation The new adjustment should be based on the base frequency, not the I40E_PTP_40GB_INCVAL in i40e_ptp_adjfine(). This issue was introduced in commit 3626a690b717 ("i40e: use mul_u64_u64_div_u64 for PTP frequency calculation"), frequency is left just as base I40E_PTP_40GB_INCVAL before the commit. After the commit, frequency is the I40E_PTP_40GB_INCVAL times the ptp_adj_mult value. But then the diff is applied on the wrong value, and no multiplication is done afterwards. It was accidentally fixed in commit 1060707e3809 ("ptp: introduce helpers to adjust by scaled parts per million"). It uses adjust_by_scaled_ppm correctly performs the calculation and uses the base adjustment, so there's no error here. But it is a new feature and doesn't need to backported to the stable releases. This issue affects both v6.0 and v6.1, and the v6.1 version is an LTS release. Therefore, the patch only needs to be applied to v6.1 stable. Fixes: 3626a690b717 ("i40e: use mul_u64_u64_div_u64 for PTP frequency calculation") Cc: # 6.1 Cc: Tony Nguyen Signed-off-by: Yajun Deng Reviewed-by: Jacob Keller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/i40e/i40e_ptp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index ffea0c9c82f1..97a9efe7b713 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -361,9 +361,9 @@ static int i40e_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) 1000000ULL << 16); if (neg_adj) - adj = I40E_PTP_40GB_INCVAL - diff; + adj = freq - diff; else - adj = I40E_PTP_40GB_INCVAL + diff; + adj = freq + diff; wr32(hw, I40E_PRTTSYN_INC_L, adj & 0xFFFFFFFF); wr32(hw, I40E_PRTTSYN_INC_H, adj >> 32); From cdf18e75850f4359bc36fbe41873723629ff2b74 Mon Sep 17 00:00:00 2001 From: Dinghao Liu Date: Sat, 23 Sep 2023 18:37:23 +0800 Subject: [PATCH 1948/2093] scsi: zfcp: Fix a double put in zfcp_port_enqueue() commit b481f644d9174670b385c3a699617052cd2a79d3 upstream. When device_register() fails, zfcp_port_release() will be called after put_device(). As a result, zfcp_ccw_adapter_put() will be called twice: one in zfcp_port_release() and one in the error path after device_register(). So the reference on the adapter object is doubly put, which may lead to a premature free. Fix this by adjusting the error tag after device_register(). Fixes: f3450c7b9172 ("[SCSI] zfcp: Replace local reference counting with common kref") Signed-off-by: Dinghao Liu Link: https://lore.kernel.org/r/20230923103723.10320-1-dinghao.liu@zju.edu.cn Acked-by: Benjamin Block Cc: stable@vger.kernel.org # v2.6.33+ Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/s390/scsi/zfcp_aux.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index df782646e856..ab2f35bc294d 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -518,12 +518,12 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, if (port) { put_device(&port->dev); retval = -EEXIST; - goto err_out; + goto err_put; } port = kzalloc(sizeof(struct zfcp_port), GFP_KERNEL); if (!port) - goto err_out; + goto err_put; rwlock_init(&port->unit_list_lock); INIT_LIST_HEAD(&port->unit_list); @@ -546,7 +546,7 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, if (dev_set_name(&port->dev, "0x%016llx", (unsigned long long)wwpn)) { kfree(port); - goto err_out; + goto err_put; } retval = -EINVAL; @@ -563,7 +563,8 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, return port; -err_out: +err_put: zfcp_ccw_adapter_put(adapter); +err_out: return ERR_PTR(retval); } From c12ef025add77ca3a0902e8719d552b6d47b4282 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Mon, 25 Sep 2023 20:04:17 +0800 Subject: [PATCH 1949/2093] iommu/vt-d: Avoid memory allocation in iommu_suspend() commit 59df44bfb0ca4c3ee1f1c3c5d0ee8e314844799e upstream. The iommu_suspend() syscore suspend callback is invoked with IRQ disabled. Allocating memory with the GFP_KERNEL flag may re-enable IRQs during the suspend callback, which can cause intermittent suspend/hibernation problems with the following kernel traces: Calling iommu_suspend+0x0/0x1d0 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 15 at kernel/time/timekeeping.c:868 ktime_get+0x9b/0xb0 ... CPU: 0 PID: 15 Comm: rcu_preempt Tainted: G U E 6.3-intel #r1 RIP: 0010:ktime_get+0x9b/0xb0 ... Call Trace: tick_sched_timer+0x22/0x90 ? __pfx_tick_sched_timer+0x10/0x10 __hrtimer_run_queues+0x111/0x2b0 hrtimer_interrupt+0xfa/0x230 __sysvec_apic_timer_interrupt+0x63/0x140 sysvec_apic_timer_interrupt+0x7b/0xa0 asm_sysvec_apic_timer_interrupt+0x1f/0x30 ... ------------[ cut here ]------------ Interrupts enabled after iommu_suspend+0x0/0x1d0 WARNING: CPU: 0 PID: 27420 at drivers/base/syscore.c:68 syscore_suspend+0x147/0x270 CPU: 0 PID: 27420 Comm: rtcwake Tainted: G U W E 6.3-intel #r1 RIP: 0010:syscore_suspend+0x147/0x270 ... Call Trace: hibernation_snapshot+0x25b/0x670 hibernate+0xcd/0x390 state_store+0xcf/0xe0 kobj_attr_store+0x13/0x30 sysfs_kf_write+0x3f/0x50 kernfs_fop_write_iter+0x128/0x200 vfs_write+0x1fd/0x3c0 ksys_write+0x6f/0xf0 __x64_sys_write+0x1d/0x30 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Given that only 4 words memory is needed, avoid the memory allocation in iommu_suspend(). CC: stable@kernel.org Fixes: 33e07157105e ("iommu/vt-d: Avoid GFP_ATOMIC where it is not needed") Signed-off-by: Zhang Rui Tested-by: Ooi, Chin Hao Link: https://lore.kernel.org/r/20230921093956.234692-1-rui.zhang@intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230925120417.55977-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel/iommu.c | 16 ---------------- drivers/iommu/intel/iommu.h | 2 +- 2 files changed, 1 insertion(+), 17 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index d4b5d20bd6dd..5c4f5aa8e87e 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3163,13 +3163,6 @@ static int iommu_suspend(void) struct intel_iommu *iommu = NULL; unsigned long flag; - for_each_active_iommu(iommu, drhd) { - iommu->iommu_state = kcalloc(MAX_SR_DMAR_REGS, sizeof(u32), - GFP_KERNEL); - if (!iommu->iommu_state) - goto nomem; - } - iommu_flush_all(); for_each_active_iommu(iommu, drhd) { @@ -3189,12 +3182,6 @@ static int iommu_suspend(void) raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } return 0; - -nomem: - for_each_active_iommu(iommu, drhd) - kfree(iommu->iommu_state); - - return -ENOMEM; } static void iommu_resume(void) @@ -3226,9 +3213,6 @@ static void iommu_resume(void) raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } - - for_each_active_iommu(iommu, drhd) - kfree(iommu->iommu_state); } static struct syscore_ops iommu_syscore_ops = { diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index db9df7c3790c..c99cb715bd9a 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -595,7 +595,7 @@ struct intel_iommu { struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; struct q_inval *qi; /* Queued invalidation info */ - u32 *iommu_state; /* Store iommu states between suspend and resume.*/ + u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/ #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ From 3a72decd6b49ff11a894aabd4d9b3025f046fe61 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Mon, 25 Sep 2023 12:30:57 +0200 Subject: [PATCH 1950/2093] vringh: don't use vringh_kiov_advance() in vringh_iov_xfer() commit 7aed44babc7f97e82b38e9a68515e699692cc100 upstream. In the while loop of vringh_iov_xfer(), `partlen` could be 0 if one of the `iov` has 0 lenght. In this case, we should skip the iov and go to the next one. But calling vringh_kiov_advance() with 0 lenght does not cause the advancement, since it returns immediately if asked to advance by 0 bytes. Let's restore the code that was there before commit b8c06ad4d67d ("vringh: implement vringh_kiov_advance()"), avoiding using vringh_kiov_advance(). Fixes: b8c06ad4d67d ("vringh: implement vringh_kiov_advance()") Cc: stable@vger.kernel.org Reported-by: Jason Wang Signed-off-by: Stefano Garzarella Acked-by: Jason Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/vhost/vringh.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 33eb941fcf15..10bfc5f1c50d 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -123,8 +123,18 @@ static inline ssize_t vringh_iov_xfer(struct vringh *vrh, done += partlen; len -= partlen; ptr += partlen; + iov->consumed += partlen; + iov->iov[iov->i].iov_len -= partlen; + iov->iov[iov->i].iov_base += partlen; - vringh_kiov_advance(iov, partlen); + if (!iov->iov[iov->i].iov_len) { + /* Fix up old iov element then increment. */ + iov->iov[iov->i].iov_len = iov->consumed; + iov->iov[iov->i].iov_base -= iov->consumed; + + iov->consumed = 0; + iov->i++; + } } return done; } From 4674e9626beb366de76b87378121d52c778b070f Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 2 Oct 2023 16:08:05 +0200 Subject: [PATCH 1951/2093] net: ethernet: mediatek: disable irq before schedule napi commit fcdfc462881d8acf9db77f483b2c821e286ca97b upstream. While searching for possible refactor of napi_schedule_prep and __napi_schedule it was notice that the mtk eth driver disable the interrupt for rx and tx AFTER napi is scheduled. While this is a very hard to repro case it might happen to have situation where the interrupt is disabled and never enabled again as the napi completes and the interrupt is enabled before. This is caused by the fact that a napi driven by interrupt expect a logic with: 1. interrupt received. napi prepared -> interrupt disabled -> napi scheduled 2. napi triggered. ring cleared -> interrupt enabled -> wait for new interrupt To prevent this case, disable the interrupt BEFORE the napi is scheduled. Fixes: 656e705243fd ("net-next: mediatek: add support for MT7623 ethernet") Cc: stable@vger.kernel.org Signed-off-by: Christian Marangi Link: https://lore.kernel.org/r/20231002140805.568-1-ansuelsmth@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 0ac5ae16308f..17e6ac4445af 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2862,8 +2862,8 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth) eth->rx_events++; if (likely(napi_schedule_prep(ð->rx_napi))) { - __napi_schedule(ð->rx_napi); mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + __napi_schedule(ð->rx_napi); } return IRQ_HANDLED; @@ -2875,8 +2875,8 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth) eth->tx_events++; if (likely(napi_schedule_prep(ð->tx_napi))) { - __napi_schedule(ð->tx_napi); mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); + __napi_schedule(ð->tx_napi); } return IRQ_HANDLED; From 454bb54b8fe86486f8e137d34951ffb80467f734 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 4 Oct 2023 13:38:12 -0700 Subject: [PATCH 1952/2093] mptcp: userspace pm allow creating id 0 subflow commit e5ed101a602873d65d2d64edaba93e8c73ec1b0f upstream. This patch drops id 0 limitation in mptcp_nl_cmd_sf_create() to allow creating additional subflows with the local addr ID 0. There is no reason not to allow additional subflows from this local address: we should be able to create new subflows from the initial endpoint. This limitation was breaking fullmesh support from userspace. Fixes: 702c2f646d42 ("mptcp: netlink: allow userspace-driven subflow establishment") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/391 Cc: stable@vger.kernel.org Suggested-by: Matthieu Baerts Reviewed-by: Matthieu Baerts Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20231004-send-net-20231004-v1-2-28de4ac663ae@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/pm_userspace.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 8a2aa63caa51..38cbdc66d8bf 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -309,12 +309,6 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } - if (addr_l.id == 0) { - NL_SET_ERR_MSG_ATTR(info->extack, laddr, "missing local addr id"); - err = -EINVAL; - goto create_err; - } - err = mptcp_pm_parse_addr(raddr, info, &addr_r); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr"); From 01afbfb39585b8f74398b435c05767204d960b6c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sat, 23 Sep 2023 19:15:59 -0600 Subject: [PATCH 1953/2093] qed/red_ll2: Fix undefined behavior bug in struct qed_ll2_info commit eea03d18af9c44235865a4bc9bec4d780ef6cf21 upstream. The flexible structure (a structure that contains a flexible-array member at the end) `qed_ll2_tx_packet` is nested within the second layer of `struct qed_ll2_info`: struct qed_ll2_tx_packet { ... /* Flexible Array of bds_set determined by max_bds_per_packet */ struct { struct core_tx_bd *txq_bd; dma_addr_t tx_frag; u16 frag_len; } bds_set[]; }; struct qed_ll2_tx_queue { ... struct qed_ll2_tx_packet cur_completing_packet; }; struct qed_ll2_info { ... struct qed_ll2_tx_queue tx_queue; struct qed_ll2_cbs cbs; }; The problem is that member `cbs` in `struct qed_ll2_info` is placed just after an object of type `struct qed_ll2_tx_queue`, which is in itself an implicit flexible structure, which by definition ends in a flexible array member, in this case `bds_set`. This causes an undefined behavior bug at run-time when dynamic memory is allocated for `bds_set`, which could lead to a serious issue if `cbs` in `struct qed_ll2_info` is overwritten by the contents of `bds_set`. Notice that the type of `cbs` is a structure full of function pointers (and a cookie :) ): include/linux/qed/qed_ll2_if.h: 107 typedef 108 void (*qed_ll2_complete_rx_packet_cb)(void *cxt, 109 struct qed_ll2_comp_rx_data *data); 110 111 typedef 112 void (*qed_ll2_release_rx_packet_cb)(void *cxt, 113 u8 connection_handle, 114 void *cookie, 115 dma_addr_t rx_buf_addr, 116 bool b_last_packet); 117 118 typedef 119 void (*qed_ll2_complete_tx_packet_cb)(void *cxt, 120 u8 connection_handle, 121 void *cookie, 122 dma_addr_t first_frag_addr, 123 bool b_last_fragment, 124 bool b_last_packet); 125 126 typedef 127 void (*qed_ll2_release_tx_packet_cb)(void *cxt, 128 u8 connection_handle, 129 void *cookie, 130 dma_addr_t first_frag_addr, 131 bool b_last_fragment, bool b_last_packet); 132 133 typedef 134 void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle, 135 u32 opaque_data_0, u32 opaque_data_1); 136 137 struct qed_ll2_cbs { 138 qed_ll2_complete_rx_packet_cb rx_comp_cb; 139 qed_ll2_release_rx_packet_cb rx_release_cb; 140 qed_ll2_complete_tx_packet_cb tx_comp_cb; 141 qed_ll2_release_tx_packet_cb tx_release_cb; 142 qed_ll2_slowpath_cb slowpath_cb; 143 void *cookie; 144 }; Fix this by moving the declaration of `cbs` to the middle of its containing structure `qed_ll2_info`, preventing it from being overwritten by the contents of `bds_set` at run-time. This bug was introduced in 2017, when `bds_set` was converted to a one-element array, and started to be used as a Variable Length Object (VLO) at run-time. Fixes: f5823fe6897c ("qed: Add ll2 option to limit the number of bds per packet") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/ZQ+Nz8DfPg56pIzr@work Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/qlogic/qed/qed_ll2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index 0bfc375161ed..a174c6fc626a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -110,9 +110,9 @@ struct qed_ll2_info { enum core_tx_dest tx_dest; u8 tx_stats_en; bool main_func_queue; + struct qed_ll2_cbs cbs; struct qed_ll2_rx_queue rx_queue; struct qed_ll2_tx_queue tx_queue; - struct qed_ll2_cbs cbs; }; extern const struct qed_ll2_ops qed_ll2_ops_pass; From 626535077ba9dc110787540d1fe24881094c15a1 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 15 Sep 2023 13:24:47 -0700 Subject: [PATCH 1954/2093] Bluetooth: hci_codec: Fix leaking content of local_codecs commit b938790e70540bf4f2e653dcd74b232494d06c8f upstream. The following memory leak can be observed when the controller supports codecs which are stored in local_codecs list but the elements are never freed: unreferenced object 0xffff88800221d840 (size 32): comm "kworker/u3:0", pid 36, jiffies 4294898739 (age 127.060s) hex dump (first 32 bytes): f8 d3 02 03 80 88 ff ff 80 d8 21 02 80 88 ff ff ..........!..... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] __kmalloc+0x47/0x120 [] hci_codec_list_add.isra.0+0x2d/0x160 [] hci_read_codec_capabilities+0x183/0x270 [] hci_read_supported_codecs+0x1bb/0x2d0 [] hci_read_local_codecs_sync+0x3e/0x60 [] hci_dev_open_sync+0x943/0x11e0 [] hci_power_on+0x10d/0x3f0 [] process_one_work+0x404/0x800 [] worker_thread+0x374/0x670 [] kthread+0x188/0x1c0 [] ret_from_fork+0x2b/0x50 [] ret_from_fork_asm+0x1a/0x30 Cc: stable@vger.kernel.org Fixes: 8961987f3f5f ("Bluetooth: Enumerate local supported codec and cache details") Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_core.c | 1 + net/bluetooth/hci_event.c | 1 + net/bluetooth/hci_sync.c | 1 + 3 files changed, 3 insertions(+) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index fa4dd5fab0d4..d13b498f148c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2783,6 +2783,7 @@ void hci_release_dev(struct hci_dev *hdev) hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); + hci_codec_list_clear(&hdev->local_codecs); hci_dev_unlock(hdev); ida_simple_remove(&hci_index_ida, hdev->id); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 83eaf25ece46..e4d8857716eb 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -32,6 +32,7 @@ #include "hci_request.h" #include "hci_debugfs.h" +#include "hci_codec.h" #include "a2mp.h" #include "amp.h" #include "smp.h" diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 2ae038dfc39f..48dd1924991b 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -5033,6 +5033,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); bacpy(&hdev->random_addr, BDADDR_ANY); + hci_codec_list_clear(&hdev->local_codecs); hci_dev_put(hdev); return err; From 794ae3a9f8feb696e9436fe07eb61d2abc548135 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Tue, 29 Aug 2023 13:50:06 -0700 Subject: [PATCH 1955/2093] Bluetooth: hci_sync: Fix handling of HCI_QUIRK_STRICT_DUPLICATE_FILTER commit 941c998b42f5c90384f49da89a6e11233de567cf upstream. When HCI_QUIRK_STRICT_DUPLICATE_FILTER is set LE scanning requires periodic restarts of the scanning procedure as the controller would consider device previously found as duplicated despite of RSSI changes, but in order to set the scan timeout properly set le_scan_restart needs to be synchronous so it shall not use hci_cmd_sync_queue which defers the command processing to cmd_sync_work. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-bluetooth/578e6d7afd676129decafba846a933f5@agner.ch/#t Fixes: 27d54b778ad1 ("Bluetooth: Rework le_scan_restart for hci_sync") Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_sync.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 48dd1924991b..5218c4dfe0a8 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -412,11 +412,6 @@ static int hci_le_scan_restart_sync(struct hci_dev *hdev) LE_SCAN_FILTER_DUP_ENABLE); } -static int le_scan_restart_sync(struct hci_dev *hdev, void *data) -{ - return hci_le_scan_restart_sync(hdev); -} - static void le_scan_restart(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -426,15 +421,15 @@ static void le_scan_restart(struct work_struct *work) bt_dev_dbg(hdev, ""); - hci_dev_lock(hdev); - - status = hci_cmd_sync_queue(hdev, le_scan_restart_sync, NULL, NULL); + status = hci_le_scan_restart_sync(hdev); if (status) { bt_dev_err(hdev, "failed to restart LE scan: status %d", status); - goto unlock; + return; } + hci_dev_lock(hdev); + if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) || !hdev->discovery.scan_start) goto unlock; From c404d39e7749c16173dea3156f5a46800e7e3f08 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 24 Aug 2023 21:06:51 -0600 Subject: [PATCH 1956/2093] wifi: mwifiex: Fix tlv_buf_left calculation commit eec679e4ac5f47507774956fb3479c206e761af7 upstream. In a TLV encoding scheme, the Length part represents the length after the header containing the values for type and length. In this case, `tlv_len` should be: tlv_len == (sizeof(*tlv_rxba) - 1) - sizeof(tlv_rxba->header) + tlv_bitmap_len Notice that the `- 1` accounts for the one-element array `bitmap`, which 1-byte size is already included in `sizeof(*tlv_rxba)`. So, if the above is correct, there is a double-counting of some members in `struct mwifiex_ie_types_rxba_sync`, when `tlv_buf_left` and `tmp` are calculated: 968 tlv_buf_left -= (sizeof(*tlv_rxba) + tlv_len); 969 tmp = (u8 *)tlv_rxba + tlv_len + sizeof(*tlv_rxba); in specific, members: drivers/net/wireless/marvell/mwifiex/fw.h:777 777 u8 mac[ETH_ALEN]; 778 u8 tid; 779 u8 reserved; 780 __le16 seq_num; 781 __le16 bitmap_len; This is clearly wrong, and affects the subsequent decoding of data in `event_buf` through `tlv_rxba`: 970 tlv_rxba = (struct mwifiex_ie_types_rxba_sync *)tmp; Fix this by using `sizeof(tlv_rxba->header)` instead of `sizeof(*tlv_rxba)` in the calculation of `tlv_buf_left` and `tmp`. This results in the following binary differences before/after changes: | drivers/net/wireless/marvell/mwifiex/11n_rxreorder.o | @@ -4698,11 +4698,11 @@ | drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c:968 | tlv_buf_left -= (sizeof(tlv_rxba->header) + tlv_len); | - 1da7: lea -0x11(%rbx),%edx | + 1da7: lea -0x4(%rbx),%edx | 1daa: movzwl %bp,%eax | drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c:969 | tmp = (u8 *)tlv_rxba + sizeof(tlv_rxba->header) + tlv_len; | - 1dad: lea 0x11(%r15,%rbp,1),%r15 | + 1dad: lea 0x4(%r15,%rbp,1),%r15 The above reflects the desired change: avoid counting 13 too many bytes; which is the total size of the double-counted members in `struct mwifiex_ie_types_rxba_sync`: $ pahole -C mwifiex_ie_types_rxba_sync drivers/net/wireless/marvell/mwifiex/11n_rxreorder.o struct mwifiex_ie_types_rxba_sync { struct mwifiex_ie_types_header header; /* 0 4 */ |----------------------------------------------------------------------- | u8 mac[6]; /* 4 6 */ | | u8 tid; /* 10 1 */ | | u8 reserved; /* 11 1 */ | | __le16 seq_num; /* 12 2 */ | | __le16 bitmap_len; /* 14 2 */ | | u8 bitmap[1]; /* 16 1 */ | |----------------------------------------------------------------------| | 13 bytes| ----------- /* size: 17, cachelines: 1, members: 7 */ /* last cacheline: 17 bytes */ } __attribute__((__packed__)); Fixes: 99ffe72cdae4 ("mwifiex: process rxba_sync event") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/06668edd68e7a26bbfeebd1201ae077a2a7a8bce.1692931954.git.gustavoars@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index a04b66284af4..7351acac6932 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -965,8 +965,8 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv, } } - tlv_buf_left -= (sizeof(*tlv_rxba) + tlv_len); - tmp = (u8 *)tlv_rxba + tlv_len + sizeof(*tlv_rxba); + tlv_buf_left -= (sizeof(tlv_rxba->header) + tlv_len); + tmp = (u8 *)tlv_rxba + sizeof(tlv_rxba->header) + tlv_len; tlv_rxba = (struct mwifiex_ie_types_rxba_sync *)tmp; } } From ebf2d9a7822beb5618b970afb628fcc1f0c41650 Mon Sep 17 00:00:00 2001 From: David Jeffery Date: Mon, 2 Oct 2023 14:32:29 -0400 Subject: [PATCH 1957/2093] md/raid5: release batch_last before waiting for another stripe_head commit 2fd7b0f6d5ad655b1d947d3acdd82f687c31465e upstream. When raid5_get_active_stripe is called with a ctx containing a stripe_head in its batch_last pointer, it can cause a deadlock if the task sleeps waiting on another stripe_head to become available. The stripe_head held by batch_last can be blocking the advancement of other stripe_heads, leading to no stripe_heads being released so raid5_get_active_stripe waits forever. Like with the quiesce state handling earlier in the function, batch_last needs to be released by raid5_get_active_stripe before it waits for another stripe_head. Fixes: 3312e6c887fe ("md/raid5: Keep a reference to last stripe_head for batch") Cc: stable@vger.kernel.org # v6.0+ Signed-off-by: David Jeffery Reviewed-by: Logan Gunthorpe Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20231002183422.13047-1-djeffery@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid5.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index fbef3c9badb6..98d4e93efa31 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -854,6 +854,13 @@ struct stripe_head *raid5_get_active_stripe(struct r5conf *conf, set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); r5l_wake_reclaim(conf->log, 0); + + /* release batch_last before wait to avoid risk of deadlock */ + if (ctx && ctx->batch_last) { + raid5_release_stripe(ctx->batch_last); + ctx->batch_last = NULL; + } + wait_event_lock_irq(conf->wait_for_stripe, is_inactive_blocked(conf, hash), *(conf->hash_locks + hash)); From 2dfb5f324d799f4545e17631415aba6d302a8e2b Mon Sep 17 00:00:00 2001 From: Sricharan Ramabadhran Date: Tue, 19 Sep 2023 15:59:48 +0530 Subject: [PATCH 1958/2093] PCI: qcom: Fix IPQ8074 enumeration commit 6a878a54d0053ef21f3b829dc267487c2302b012 upstream. PARF_SLV_ADDR_SPACE_SIZE_2_3_3 is used by qcom_pcie_post_init_2_3_3(). This PCIe slave address space size register offset is 0x358 but was incorrectly changed to 0x16c by 39171b33f652 ("PCI: qcom: Remove PCIE20_ prefix from register definitions"). This prevented access to slave address space registers like iATU, etc., so the IPQ8074 PCIe controller was not enumerated. Revert back to the correct 0x358 offset and remove the unused PARF_SLV_ADDR_SPACE_SIZE_2_3_3. Fixes: 39171b33f652 ("PCI: qcom: Remove PCIE20_ prefix from register definitions") Link: https://lore.kernel.org/r/20230919102948.1844909-1-quic_srichara@quicinc.com Tested-by: Robert Marko Signed-off-by: Sricharan Ramabadhran [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Reviewed-by: Konrad Dybcio Cc: stable@vger.kernel.org # v6.4+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/dwc/pcie-qcom.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index d24712a76ba7..0ccd92faf078 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -40,7 +40,6 @@ #define PARF_PHY_REFCLK 0x4c #define PARF_CONFIG_BITS 0x50 #define PARF_DBI_BASE_ADDR 0x168 -#define PARF_SLV_ADDR_SPACE_SIZE_2_3_3 0x16c /* Register offset specific to IP ver 2.3.3 */ #define PARF_MHI_CLOCK_RESET_CTRL 0x174 #define PARF_AXI_MSTR_WR_ADDR_HALT 0x178 #define PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1a8 @@ -1148,8 +1147,7 @@ static int qcom_pcie_post_init_2_3_3(struct qcom_pcie *pcie) u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); u32 val; - writel(SLV_ADDR_SPACE_SZ, - pcie->parf + PARF_SLV_ADDR_SPACE_SIZE_2_3_3); + writel(SLV_ADDR_SPACE_SZ, pcie->parf + PARF_SLV_ADDR_SPACE_SIZE); val = readl(pcie->parf + PARF_PHY_CTRL); val &= ~BIT(0); From 34f9370ae4449b7e76ff99a7484f4b98e1f9c17c Mon Sep 17 00:00:00 2001 From: Jordan Rife Date: Thu, 21 Sep 2023 18:46:40 -0500 Subject: [PATCH 1959/2093] net: replace calls to sock->ops->connect() with kernel_connect() commit 26297b4ce1ce4ea40bc9a48ec99f45da3f64d2e2 upstream. commit 0bdf399342c5 ("net: Avoid address overwrite in kernel_connect") ensured that kernel_connect() will not overwrite the address parameter in cases where BPF connect hooks perform an address rewrite. This change replaces direct calls to sock->ops->connect() in net with kernel_connect() to make these call safe. Link: https://lore.kernel.org/netdev/20230912013332.2048422-1-jrife@google.com/ Fixes: d74bad4e74ee ("bpf: Hooks for sys_connect") Cc: stable@vger.kernel.org Reviewed-by: Willem de Bruijn Signed-off-by: Jordan Rife Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/netfilter/ipvs/ip_vs_sync.c | 4 ++-- net/rds/tcp_connect.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d4fe7bb4f853..6574f4e651b1 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1507,8 +1507,8 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id, } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); - result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr, - salen, 0); + result = kernel_connect(sock, (struct sockaddr *)&mcast_addr, + salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index f0c477c5d1db..d788c6d28986 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -173,7 +173,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) * own the socket */ rds_tcp_set_callbacks(sock, cp); - ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK); + ret = kernel_connect(sock, addr, addrlen, O_NONBLOCK); rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) From fc8d9630c80b1dd7f6e8dd8e90aff11090f1b2a8 Mon Sep 17 00:00:00 2001 From: Jordan Rife Date: Thu, 21 Sep 2023 18:46:41 -0500 Subject: [PATCH 1960/2093] net: prevent rewrite of msg_name in sock_sendmsg() commit 86a7e0b69bd5b812e48a20c66c2161744f3caa16 upstream. Callers of sock_sendmsg(), and similarly kernel_sendmsg(), in kernel space may observe their value of msg_name change in cases where BPF sendmsg hooks rewrite the send address. This has been confirmed to break NFS mounts running in UDP mode and has the potential to break other systems. This patch: 1) Creates a new function called __sock_sendmsg() with same logic as the old sock_sendmsg() function. 2) Replaces calls to sock_sendmsg() made by __sys_sendto() and __sys_sendmsg() with __sock_sendmsg() to avoid an unnecessary copy, as these system calls are already protected. 3) Modifies sock_sendmsg() so that it makes a copy of msg_name if present before passing it down the stack to insulate callers from changes to the send address. Link: https://lore.kernel.org/netdev/20230912013332.2048422-1-jrife@google.com/ Fixes: 1cedee13d25a ("bpf: Hooks for sys_sendmsg") Cc: stable@vger.kernel.org Reviewed-by: Willem de Bruijn Signed-off-by: Jordan Rife Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/socket.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/net/socket.c b/net/socket.c index d281a7ef4b1d..b0169168e3f4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -720,6 +720,14 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) return ret; } +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + int err = security_socket_sendmsg(sock, msg, + msg_data_left(msg)); + + return err ?: sock_sendmsg_nosec(sock, msg); +} + /** * sock_sendmsg - send a message through @sock * @sock: socket @@ -730,10 +738,19 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { - int err = security_socket_sendmsg(sock, msg, - msg_data_left(msg)); + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int ret; - return err ?: sock_sendmsg_nosec(sock, msg); + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + + return ret; } EXPORT_SYMBOL(sock_sendmsg); @@ -1110,7 +1127,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -2114,7 +2131,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2479,7 +2496,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. From c8bd3e12b3291e632ae189619169914743ba77d1 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 26 Sep 2023 17:59:53 -0500 Subject: [PATCH 1961/2093] drm/amd: Fix detection of _PR3 on the PCIe root port commit 134b8c5d8674e7cde380f82e9aedfd46dcdd16f7 upstream. On some systems with Navi3x dGPU will attempt to use BACO for runtime PM but fails to resume properly. This is because on these systems the root port goes into D3cold which is incompatible with BACO. This happens because in this case dGPU is connected to a bridge between root port which causes BOCO detection logic to fail. Fix the intent of the logic by looking at root port, not the immediate upstream bridge for _PR3. Cc: stable@vger.kernel.org Suggested-by: Jun Ma Tested-by: David Perry Fixes: b10c1c5b3a4e ("drm/amdgpu: add check for ACPI power resources") Signed-off-by: Mario Limonciello Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5f5999cea7d2..92fa2faf63e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2179,7 +2179,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) adev->flags |= AMD_IS_PX; if (!(adev->flags & AMD_IS_APU)) { - parent = pci_upstream_bridge(adev->pdev); + parent = pcie_find_root_port(adev->pdev); adev->has_pr3 = parent ? pci_pr3_present(parent) : false; } From d2894c4f473ab71cd68ef0f9b086148bb2c02132 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 26 Sep 2023 21:07:43 -0500 Subject: [PATCH 1962/2093] drm/amd: Fix logic error in sienna_cichlid_update_pcie_parameters() commit 2a1fe39a5be785e962e387146aed34fa9a829f3f upstream. While aligning SMU11 with SMU13 implementation an assumption was made that `dpm_context->dpm_tables.pcie_table` was populated in dpm table initialization like in SMU13 but it isn't. So restore some of the original logic and instead just check for amdgpu_device_pcie_dynamic_switching_supported() to decide whether to hardcode values; erring on the side of performance. Cc: stable@vger.kernel.org # 6.1+ Reported-and-tested-by: Umio Yasuno Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1447#note_2101382 Fixes: e701156ccc6c ("drm/amd: Align SMU11 SMU_MSG_OverridePcieParameters implementation with SMU13") Signed-off-by: Mario Limonciello Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- .../amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 43 +++++++++++-------- 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 839a812e0da3..fbc4d706748b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2081,36 +2081,41 @@ static int sienna_cichlid_display_disable_memory_clock_switch(struct smu_context return ret; } +#define MAX(a, b) ((a) > (b) ? (a) : (b)) + static int sienna_cichlid_update_pcie_parameters(struct smu_context *smu, uint32_t pcie_gen_cap, uint32_t pcie_width_cap) { struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_11_0_pcie_table *pcie_table = &dpm_context->dpm_tables.pcie_table; - u32 smu_pcie_arg; + uint8_t *table_member1, *table_member2; + uint32_t min_gen_speed, max_gen_speed; + uint32_t min_lane_width, max_lane_width; + uint32_t smu_pcie_arg; int ret, i; - /* PCIE gen speed and lane width override */ + GET_PPTABLE_MEMBER(PcieGenSpeed, &table_member1); + GET_PPTABLE_MEMBER(PcieLaneCount, &table_member2); + + min_gen_speed = MAX(0, table_member1[0]); + max_gen_speed = MIN(pcie_gen_cap, table_member1[1]); + min_gen_speed = min_gen_speed > max_gen_speed ? + max_gen_speed : min_gen_speed; + min_lane_width = MAX(1, table_member2[0]); + max_lane_width = MIN(pcie_width_cap, table_member2[1]); + min_lane_width = min_lane_width > max_lane_width ? + max_lane_width : min_lane_width; + if (!amdgpu_device_pcie_dynamic_switching_supported()) { - if (pcie_table->pcie_gen[NUM_LINK_LEVELS - 1] < pcie_gen_cap) - pcie_gen_cap = pcie_table->pcie_gen[NUM_LINK_LEVELS - 1]; - - if (pcie_table->pcie_lane[NUM_LINK_LEVELS - 1] < pcie_width_cap) - pcie_width_cap = pcie_table->pcie_lane[NUM_LINK_LEVELS - 1]; - - /* Force all levels to use the same settings */ - for (i = 0; i < NUM_LINK_LEVELS; i++) { - pcie_table->pcie_gen[i] = pcie_gen_cap; - pcie_table->pcie_lane[i] = pcie_width_cap; - } + pcie_table->pcie_gen[0] = max_gen_speed; + pcie_table->pcie_lane[0] = max_lane_width; } else { - for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (pcie_table->pcie_gen[i] > pcie_gen_cap) - pcie_table->pcie_gen[i] = pcie_gen_cap; - if (pcie_table->pcie_lane[i] > pcie_width_cap) - pcie_table->pcie_lane[i] = pcie_width_cap; - } + pcie_table->pcie_gen[0] = min_gen_speed; + pcie_table->pcie_lane[0] = min_lane_width; } + pcie_table->pcie_gen[1] = max_gen_speed; + pcie_table->pcie_lane[1] = max_lane_width; for (i = 0; i < NUM_LINK_LEVELS; i++) { smu_pcie_arg = (i << 16 | From 0a4ae263480130140536b8948dc76b9b2b07d311 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 21 Sep 2023 14:41:51 -0500 Subject: [PATCH 1963/2093] arm64: Add Cortex-A520 CPU part definition commit a654a69b9f9c06b2e56387d0b99f0e3e6b0ff4ef upstream. Add the CPU Part number for the new Arm design. Cc: stable@vger.kernel.org Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230921194156.1050055-1-robh@kernel.org Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 65e53ef5a396..357932938b5a 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -79,6 +79,7 @@ #define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 +#define ARM_CPU_PART_CORTEX_A520 0xD80 #define ARM_CPU_PART_CORTEX_A710 0xD47 #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 @@ -141,6 +142,7 @@ #define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) +#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) From 6e3ae2927b432a3b7c8374f14dbc1bd9ebe4372c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 21 Sep 2023 14:41:52 -0500 Subject: [PATCH 1964/2093] arm64: errata: Add Cortex-A520 speculative unprivileged load workaround commit 471470bc7052d28ce125901877dd10e4c048e513 upstream. Implement the workaround for ARM Cortex-A520 erratum 2966298. On an affected Cortex-A520 core, a speculatively executed unprivileged load might leak data from a privileged load via a cache side channel. The issue only exists for loads within a translation regime with the same translation (e.g. same ASID and VMID). Therefore, the issue only affects the return to EL0. The workaround is to execute a TLBI before returning to EL0 after all loads of privileged data. A non-shareable TLBI to any address is sufficient. The workaround isn't necessary if page table isolation (KPTI) is enabled, but for simplicity it will be. Page table isolation should normally be disabled for Cortex-A520 as it supports the CSV3 feature and the E0PD feature (used when KASLR is enabled). Cc: stable@vger.kernel.org Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230921194156.1050055-2-robh@kernel.org Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- Documentation/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 13 +++++++++++++ arch/arm64/kernel/cpu_errata.c | 8 ++++++++ arch/arm64/kernel/entry.S | 4 ++++ arch/arm64/tools/cpucaps | 1 + 5 files changed, 28 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 9000640f7f7a..d9fce65b2f04 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -63,6 +63,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #1902691 | ARM64_ERRATUM_1902691 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A520 | #2966298 | ARM64_ERRATUM_2966298 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index d5eb2fbab473..9ee9e17eb2ca 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -983,6 +983,19 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_ERRATUM_2966298 + bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load" + default y + help + This option adds the workaround for ARM Cortex-A520 erratum 2966298. + + On an affected Cortex-A520 core, a speculatively executed unprivileged + load might leak data from a privileged level via a cache side channel. + + Work around this problem by executing a TLBI before returning to EL0. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 8dbf3c21ea22..3f917124684c 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -723,6 +723,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .cpu_enable = cpu_clear_bf16_from_user_emulation, }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2966298 + { + .desc = "ARM erratum 2966298", + .capability = ARM64_WORKAROUND_2966298, + /* Cortex-A520 r0p0 - r0p1 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), + }, +#endif #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38 { .desc = "AmpereOne erratum AC03_CPU_38", diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index beb4db21c89c..de16fa917e1b 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -419,6 +419,10 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] .if \el == 0 +alternative_if ARM64_WORKAROUND_2966298 + tlbi vale1, xzr + dsb nsh +alternative_else_nop_endif alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 ldr lr, [sp, #S_LR] add sp, sp, #PT_REGS_SIZE // restore sp diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 14d31d1b2ff0..e73830d9f136 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -71,6 +71,7 @@ WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 WORKAROUND_2658417 +WORKAROUND_2966298 WORKAROUND_AMPERE_AC03_CPU_38 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE From f237b17611fa3501f43f12d1cb64323e10fdcb4f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 3 Sep 2023 18:04:00 +0200 Subject: [PATCH 1965/2093] HID: sony: Fix a potential memory leak in sony_probe() [ Upstream commit e1cd4004cde7c9b694bbdd8def0e02288ee58c74 ] If an error occurs after a successful usb_alloc_urb() call, usb_free_urb() should be called. Fixes: fb1a79a6b6e1 ("HID: sony: fix freeze when inserting ghlive ps3/wii dongles") Signed-off-by: Christophe JAILLET Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-sony.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 03691cdcfb8e..5b3f58e06880 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -3074,6 +3074,9 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; err: + if (sc->ghl_urb) + usb_free_urb(sc->ghl_urb); + hid_hw_stop(hdev); return ret; } From 91aeb418b9175d09fc858f0fdf01988cbf990c5d Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Sun, 23 Apr 2023 19:10:41 +0800 Subject: [PATCH 1966/2093] ubi: Refuse attaching if mtd's erasesize is 0 [ Upstream commit 017c73a34a661a861712f7cc1393a123e5b2208c ] There exists mtd devices with zero erasesize, which will trigger a divide-by-zero exception while attaching ubi device. Fix it by refusing attaching if mtd's erasesize is 0. Fixes: 801c135ce73d ("UBI: Unsorted Block Images") Reported-by: Yu Hao Link: https://lore.kernel.org/lkml/977347543.226888.1682011999468.JavaMail.zimbra@nod.at/T/ Signed-off-by: Zhihao Cheng Reviewed-by: Miquel Raynal Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/build.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 1662c12e24ad..6fbd77dc1d18 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -893,6 +893,13 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, return -EINVAL; } + /* UBI cannot work on flashes with zero erasesize. */ + if (!mtd->erasesize) { + pr_err("ubi: refuse attaching mtd%d - zero erasesize flash is not supported\n", + mtd->index); + return -EINVAL; + } + if (ubi_num == UBI_DEV_NUM_AUTO) { /* Search for an empty slot in the @ubi_devices array */ for (ubi_num = 0; ubi_num < UBI_MAX_DEVICES; ubi_num++) From 6a5a8f0a9740f865693d5aa97a42cc4504538e18 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Thu, 7 Sep 2023 13:05:42 +0800 Subject: [PATCH 1967/2093] erofs: fix memory leak of LZMA global compressed deduplication [ Upstream commit 75a5221630fe5aa3fedba7a06be618db0f79ba1e ] When stressing microLZMA EROFS images with the new global compressed deduplication feature enabled (`-Ededupe`), I found some short-lived temporary pages weren't properly released, which could slowly cause unexpected OOMs hours later. Let's fix it now (LZ4 and DEFLATE don't have this issue.) Fixes: 5c2a64252c5d ("erofs: introduce partial-referenced pclusters") Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20230907050542.97152-1-hsiangkao@linux.alibaba.com Signed-off-by: Sasha Levin --- fs/erofs/decompressor_lzma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 5cd612a8f858..49addc345aeb 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -217,9 +217,12 @@ int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, strm->buf.out_size = min_t(u32, outlen, PAGE_SIZE - pageofs); outlen -= strm->buf.out_size; - if (!rq->out[no] && rq->fillgaps) /* deduped */ + if (!rq->out[no] && rq->fillgaps) { /* deduped */ rq->out[no] = erofs_allocpage(pagepool, GFP_KERNEL | __GFP_NOFAIL); + set_page_private(rq->out[no], + Z_EROFS_SHORTLIVED_PAGE); + } if (rq->out[no]) strm->buf.out = kmap(rq->out[no]) + pageofs; pageofs = 0; From 78b5c62edeea9f05059a33a1307cf07aa26b224d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 16 Jun 2023 11:03:34 +0200 Subject: [PATCH 1968/2093] wifi: iwlwifi: dbg_ini: fix structure packing [ Upstream commit 424c82e8ad56756bb98b08268ffcf68d12d183eb ] The iwl_fw_ini_error_dump_range structure has conflicting alignment requirements for the inner union and the outer struct: In file included from drivers/net/wireless/intel/iwlwifi/fw/dbg.c:9: drivers/net/wireless/intel/iwlwifi/fw/error-dump.h:312:2: error: field within 'struct iwl_fw_ini_error_dump_range' is less aligned than 'union iwl_fw_ini_error_dump_range::(anonymous at drivers/net/wireless/intel/iwlwifi/fw/error-dump.h:312:2)' and is usually due to 'struct iwl_fw_ini_error_dump_range' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] union { As the original intention was apparently to make the entire structure unaligned, mark the innermost members the same way so the union becomes packed as well. Fixes: 973193554cae6 ("iwlwifi: dbg_ini: dump headers cleanup") Signed-off-by: Arnd Bergmann Acked-by: Gregory Greenman Link: https://lore.kernel.org/r/20230616090343.2454061-1-arnd@kernel.org Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/fw/error-dump.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h index c62576e442bd..2d481849a9c2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h @@ -295,9 +295,9 @@ struct iwl_fw_ini_fifo_hdr { struct iwl_fw_ini_error_dump_range { __le32 range_data_size; union { - __le32 internal_base_addr; - __le64 dram_base_addr; - __le32 page_num; + __le32 internal_base_addr __packed; + __le64 dram_base_addr __packed; + __le32 page_num __packed; struct iwl_fw_ini_fifo_hdr fifo_hdr; struct iwl_cmd_header fw_pkt_hdr; }; From 6b3223449c959a8be94a1f042288059e40fcccb0 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 23 Jul 2023 22:24:59 +0200 Subject: [PATCH 1969/2093] wifi: iwlwifi: mvm: Fix a memory corruption issue [ Upstream commit 8ba438ef3cacc4808a63ed0ce24d4f0942cfe55d ] A few lines above, space is kzalloc()'ed for: sizeof(struct iwl_nvm_data) + sizeof(struct ieee80211_channel) + sizeof(struct ieee80211_rate) 'mvm->nvm_data' is a 'struct iwl_nvm_data', so it is fine. At the end of this structure, there is the 'channels' flex array. Each element is of type 'struct ieee80211_channel'. So only 1 element is allocated in this array. When doing: mvm->nvm_data->bands[0].channels = mvm->nvm_data->channels; We point at the first element of the 'channels' flex array. So this is fine. However, when doing: mvm->nvm_data->bands[0].bitrates = (void *)((u8 *)mvm->nvm_data->channels + 1); because of the "(u8 *)" cast, we add only 1 to the address of the beginning of the flex array. It is likely that we want point at the 'struct ieee80211_rate' allocated just after. Remove the spurious casting so that the pointer arithmetic works as expected. Fixes: 8ca151b568b6 ("iwlwifi: add the MVM driver") Signed-off-by: Christophe JAILLET Acked-by: Gregory Greenman Link: https://lore.kernel.org/r/23f0ec986ef1529055f4f93dcb3940a6cf8d9a94.1690143750.git.christophe.jaillet@wanadoo.fr Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 887d0789c96c..2e3c98eaa400 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -796,7 +796,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm) mvm->nvm_data->bands[0].n_channels = 1; mvm->nvm_data->bands[0].n_bitrates = 1; mvm->nvm_data->bands[0].bitrates = - (void *)((u8 *)mvm->nvm_data->channels + 1); + (void *)(mvm->nvm_data->channels + 1); mvm->nvm_data->bands[0].bitrates->hw_value = 10; } From fb195ff4183a415f58fcfb2f2ceadbe040df6acc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Jun 2023 14:49:20 +0200 Subject: [PATCH 1970/2093] wifi: cfg80211: hold wiphy lock in auto-disconnect [ Upstream commit e9da6df7492a981b071bafd169fb4c35b45f5ebf ] Most code paths in cfg80211 already hold the wiphy lock, mostly by virtue of being called from nl80211, so make the auto-disconnect worker also hold it, aligning the locking promises between different parts of cfg80211. Signed-off-by: Johannes Berg Stable-dep-of: 37c20b2effe9 ("wifi: cfg80211: fix cqm_config access race") Signed-off-by: Sasha Levin --- net/wireless/core.c | 6 ++---- net/wireless/sme.c | 4 +++- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/wireless/core.c b/net/wireless/core.c index 609b79fe4a74..9ac7c54379cf 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1162,10 +1162,6 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, kfree_sensitive(wdev->wext.keys); wdev->wext.keys = NULL; #endif - /* only initialized if we have a netdev */ - if (wdev->netdev) - flush_work(&wdev->disconnect_wk); - cfg80211_cqm_config_free(wdev); /* @@ -1439,6 +1435,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, cfg80211_leave(rdev, wdev); cfg80211_remove_links(wdev); wiphy_unlock(&rdev->wiphy); + /* since we just did cfg80211_leave() nothing to do there */ + cancel_work_sync(&wdev->disconnect_wk); break; case NETDEV_DOWN: wiphy_lock(&rdev->wiphy); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 6e87d2cd8345..b97834284bae 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -5,7 +5,7 @@ * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg - * Copyright (C) 2009, 2020, 2022 Intel Corporation. All rights reserved. + * Copyright (C) 2009, 2020, 2022-2023 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ @@ -1555,6 +1555,7 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) container_of(work, struct wireless_dev, disconnect_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + wiphy_lock(wdev->wiphy); wdev_lock(wdev); if (wdev->conn_owner_nlportid) { @@ -1593,4 +1594,5 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) } wdev_unlock(wdev); + wiphy_unlock(wdev->wiphy); } From 2ae4585f740af2123d71a3ab0048d70a20911362 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Jun 2023 14:49:22 +0200 Subject: [PATCH 1971/2093] wifi: cfg80211: move wowlan disable under locks [ Upstream commit a993df0f9143e63eca38c96a30daf08db99a98a3 ] This is a driver callback, and the driver should be able to assume that it's called with the wiphy lock held. Move the call up so that's true, it has no other effect since the device is already unregistering and we cannot reach this function through other paths. Signed-off-by: Johannes Berg Stable-dep-of: 37c20b2effe9 ("wifi: cfg80211: fix cqm_config access race") Signed-off-by: Sasha Levin --- net/wireless/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/wireless/core.c b/net/wireless/core.c index 9ac7c54379cf..28ae86c62f80 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1049,6 +1049,10 @@ void wiphy_unregister(struct wiphy *wiphy) cfg80211_rdev_list_generation++; device_del(&rdev->wiphy.dev); +#ifdef CONFIG_PM + if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) + rdev_set_wakeup(rdev, false); +#endif wiphy_unlock(&rdev->wiphy); rtnl_unlock(); @@ -1064,10 +1068,6 @@ void wiphy_unregister(struct wiphy *wiphy) flush_work(&rdev->mgmt_registrations_update_wk); flush_work(&rdev->background_cac_abort_wk); -#ifdef CONFIG_PM - if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) - rdev_set_wakeup(rdev, false); -#endif cfg80211_rdev_free_wowlan(rdev); cfg80211_rdev_free_coalesce(rdev); } From 3fcc6d7d5f40dad56dee7bde787b7e23edd4b93c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Jun 2023 14:49:25 +0200 Subject: [PATCH 1972/2093] wifi: cfg80211: add a work abstraction with special semantics [ Upstream commit a3ee4dc84c4e9d14cb34dad095fd678127aca5b6 ] Add a work abstraction at the cfg80211 level that will always hold the wiphy_lock() for any work executed and therefore also can be canceled safely (without waiting) while holding that. This improves on what we do now as with the new wiphy works we don't have to worry about locking while cancelling them safely. Also, don't let such works run while the device is suspended, since they'll likely need to interact with the device. Flush them before suspend though. Signed-off-by: Johannes Berg Stable-dep-of: 37c20b2effe9 ("wifi: cfg80211: fix cqm_config access race") Signed-off-by: Sasha Levin --- include/net/cfg80211.h | 95 ++++++++++++++++++++++++++++++-- net/wireless/core.c | 122 +++++++++++++++++++++++++++++++++++++++++ net/wireless/core.h | 7 +++ net/wireless/sysfs.c | 8 ++- 4 files changed, 227 insertions(+), 5 deletions(-) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5976545aa26b..f2144db89183 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5621,12 +5621,17 @@ struct cfg80211_cqm_config; * wiphy_lock - lock the wiphy * @wiphy: the wiphy to lock * - * This is mostly exposed so it can be done around registering and - * unregistering netdevs that aren't created through cfg80211 calls, - * since that requires locking in cfg80211 when the notifiers is - * called, but that cannot differentiate which way it's called. + * This is needed around registering and unregistering netdevs that + * aren't created through cfg80211 calls, since that requires locking + * in cfg80211 when the notifiers is called, but that cannot + * differentiate which way it's called. + * + * It can also be used by drivers for their own purposes. * * When cfg80211 ops are called, the wiphy is already locked. + * + * Note that this makes sure that no workers that have been queued + * with wiphy_queue_work() are running. */ static inline void wiphy_lock(struct wiphy *wiphy) __acquires(&wiphy->mtx) @@ -5646,6 +5651,88 @@ static inline void wiphy_unlock(struct wiphy *wiphy) mutex_unlock(&wiphy->mtx); } +struct wiphy_work; +typedef void (*wiphy_work_func_t)(struct wiphy *, struct wiphy_work *); + +struct wiphy_work { + struct list_head entry; + wiphy_work_func_t func; +}; + +static inline void wiphy_work_init(struct wiphy_work *work, + wiphy_work_func_t func) +{ + INIT_LIST_HEAD(&work->entry); + work->func = func; +} + +/** + * wiphy_work_queue - queue work for the wiphy + * @wiphy: the wiphy to queue for + * @work: the work item + * + * This is useful for work that must be done asynchronously, and work + * queued here has the special property that the wiphy mutex will be + * held as if wiphy_lock() was called, and that it cannot be running + * after wiphy_lock() was called. Therefore, wiphy_cancel_work() can + * use just cancel_work() instead of cancel_work_sync(), it requires + * being in a section protected by wiphy_lock(). + */ +void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work); + +/** + * wiphy_work_cancel - cancel previously queued work + * @wiphy: the wiphy, for debug purposes + * @work: the work to cancel + * + * Cancel the work *without* waiting for it, this assumes being + * called under the wiphy mutex acquired by wiphy_lock(). + */ +void wiphy_work_cancel(struct wiphy *wiphy, struct wiphy_work *work); + +struct wiphy_delayed_work { + struct wiphy_work work; + struct wiphy *wiphy; + struct timer_list timer; +}; + +void wiphy_delayed_work_timer(struct timer_list *t); + +static inline void wiphy_delayed_work_init(struct wiphy_delayed_work *dwork, + wiphy_work_func_t func) +{ + timer_setup(&dwork->timer, wiphy_delayed_work_timer, 0); + wiphy_work_init(&dwork->work, func); +} + +/** + * wiphy_delayed_work_queue - queue delayed work for the wiphy + * @wiphy: the wiphy to queue for + * @dwork: the delayable worker + * @delay: number of jiffies to wait before queueing + * + * This is useful for work that must be done asynchronously, and work + * queued here has the special property that the wiphy mutex will be + * held as if wiphy_lock() was called, and that it cannot be running + * after wiphy_lock() was called. Therefore, wiphy_cancel_work() can + * use just cancel_work() instead of cancel_work_sync(), it requires + * being in a section protected by wiphy_lock(). + */ +void wiphy_delayed_work_queue(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork, + unsigned long delay); + +/** + * wiphy_delayed_work_cancel - cancel previously queued delayed work + * @wiphy: the wiphy, for debug purposes + * @dwork: the delayed work to cancel + * + * Cancel the work *without* waiting for it, this assumes being + * called under the wiphy mutex acquired by wiphy_lock(). + */ +void wiphy_delayed_work_cancel(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork); + /** * struct wireless_dev - wireless device state * diff --git a/net/wireless/core.c b/net/wireless/core.c index 28ae86c62f80..8a1f34e95c4f 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -408,6 +408,34 @@ static void cfg80211_propagate_cac_done_wk(struct work_struct *work) rtnl_unlock(); } +static void cfg80211_wiphy_work(struct work_struct *work) +{ + struct cfg80211_registered_device *rdev; + struct wiphy_work *wk; + + rdev = container_of(work, struct cfg80211_registered_device, wiphy_work); + + wiphy_lock(&rdev->wiphy); + if (rdev->suspended) + goto out; + + spin_lock_irq(&rdev->wiphy_work_lock); + wk = list_first_entry_or_null(&rdev->wiphy_work_list, + struct wiphy_work, entry); + if (wk) { + list_del_init(&wk->entry); + if (!list_empty(&rdev->wiphy_work_list)) + schedule_work(work); + spin_unlock_irq(&rdev->wiphy_work_lock); + + wk->func(&rdev->wiphy, wk); + } else { + spin_unlock_irq(&rdev->wiphy_work_lock); + } +out: + wiphy_unlock(&rdev->wiphy); +} + /* exported functions */ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv, @@ -533,6 +561,9 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv, return NULL; } + INIT_WORK(&rdev->wiphy_work, cfg80211_wiphy_work); + INIT_LIST_HEAD(&rdev->wiphy_work_list); + spin_lock_init(&rdev->wiphy_work_lock); INIT_WORK(&rdev->rfkill_block, cfg80211_rfkill_block_work); INIT_WORK(&rdev->conn_work, cfg80211_conn_work); INIT_WORK(&rdev->event_work, cfg80211_event_work); @@ -1011,6 +1042,31 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy) } EXPORT_SYMBOL(wiphy_rfkill_start_polling); +void cfg80211_process_wiphy_works(struct cfg80211_registered_device *rdev) +{ + unsigned int runaway_limit = 100; + unsigned long flags; + + lockdep_assert_held(&rdev->wiphy.mtx); + + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); + while (!list_empty(&rdev->wiphy_work_list)) { + struct wiphy_work *wk; + + wk = list_first_entry(&rdev->wiphy_work_list, + struct wiphy_work, entry); + list_del_init(&wk->entry); + spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); + + wk->func(&rdev->wiphy, wk); + + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); + if (WARN_ON(--runaway_limit == 0)) + INIT_LIST_HEAD(&rdev->wiphy_work_list); + } + spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); +} + void wiphy_unregister(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -1053,9 +1109,15 @@ void wiphy_unregister(struct wiphy *wiphy) if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) rdev_set_wakeup(rdev, false); #endif + + /* surely nothing is reachable now, clean up work */ + cfg80211_process_wiphy_works(rdev); wiphy_unlock(&rdev->wiphy); rtnl_unlock(); + /* this has nothing to do now but make sure it's gone */ + cancel_work_sync(&rdev->wiphy_work); + flush_work(&rdev->scan_done_wk); cancel_work_sync(&rdev->conn_work); flush_work(&rdev->event_work); @@ -1546,6 +1608,66 @@ static struct pernet_operations cfg80211_pernet_ops = { .exit = cfg80211_pernet_exit, }; +void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + unsigned long flags; + + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); + if (list_empty(&work->entry)) + list_add_tail(&work->entry, &rdev->wiphy_work_list); + spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); + + schedule_work(&rdev->wiphy_work); +} +EXPORT_SYMBOL_GPL(wiphy_work_queue); + +void wiphy_work_cancel(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + unsigned long flags; + + lockdep_assert_held(&wiphy->mtx); + + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); + if (!list_empty(&work->entry)) + list_del_init(&work->entry); + spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); +} +EXPORT_SYMBOL_GPL(wiphy_work_cancel); + +void wiphy_delayed_work_timer(struct timer_list *t) +{ + struct wiphy_delayed_work *dwork = from_timer(dwork, t, timer); + + wiphy_work_queue(dwork->wiphy, &dwork->work); +} +EXPORT_SYMBOL(wiphy_delayed_work_timer); + +void wiphy_delayed_work_queue(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork, + unsigned long delay) +{ + if (!delay) { + wiphy_work_queue(wiphy, &dwork->work); + return; + } + + dwork->wiphy = wiphy; + mod_timer(&dwork->timer, jiffies + delay); +} +EXPORT_SYMBOL_GPL(wiphy_delayed_work_queue); + +void wiphy_delayed_work_cancel(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork) +{ + lockdep_assert_held(&wiphy->mtx); + + del_timer_sync(&dwork->timer); + wiphy_work_cancel(wiphy, &dwork->work); +} +EXPORT_SYMBOL_GPL(wiphy_delayed_work_cancel); + static int __init cfg80211_init(void) { int err; diff --git a/net/wireless/core.h b/net/wireless/core.h index 775e16cb99ed..0481a8a539d5 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -108,6 +108,12 @@ struct cfg80211_registered_device { /* lock for all wdev lists */ spinlock_t mgmt_registrations_lock; + struct work_struct wiphy_work; + struct list_head wiphy_work_list; + /* protects the list above */ + spinlock_t wiphy_work_lock; + bool suspended; + /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wiphy wiphy __aligned(NETDEV_ALIGN); @@ -450,6 +456,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype ntype, struct vif_params *params); void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev); +void cfg80211_process_wiphy_works(struct cfg80211_registered_device *rdev); void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 0c3f05c9be27..4d3b65803010 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -5,7 +5,7 @@ * * Copyright 2005-2006 Jiri Benc * Copyright 2006 Johannes Berg - * Copyright (C) 2020-2021 Intel Corporation + * Copyright (C) 2020-2021, 2023 Intel Corporation */ #include @@ -105,14 +105,18 @@ static int wiphy_suspend(struct device *dev) cfg80211_leave_all(rdev); cfg80211_process_rdev_events(rdev); } + cfg80211_process_wiphy_works(rdev); if (rdev->ops->suspend) ret = rdev_suspend(rdev, rdev->wiphy.wowlan_config); if (ret == 1) { /* Driver refuse to configure wowlan */ cfg80211_leave_all(rdev); cfg80211_process_rdev_events(rdev); + cfg80211_process_wiphy_works(rdev); ret = rdev_suspend(rdev, NULL); } + if (ret == 0) + rdev->suspended = true; } wiphy_unlock(&rdev->wiphy); rtnl_unlock(); @@ -132,6 +136,8 @@ static int wiphy_resume(struct device *dev) wiphy_lock(&rdev->wiphy); if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); + rdev->suspended = false; + schedule_work(&rdev->wiphy_work); wiphy_unlock(&rdev->wiphy); if (ret) From c797498e860e9a435a651bbf0789433684ce6dd8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 16 Aug 2023 15:38:04 +0200 Subject: [PATCH 1973/2093] wifi: cfg80211: fix cqm_config access race [ Upstream commit 37c20b2effe987b806c8de6d12978e4ffeff026f ] Max Schulze reports crashes with brcmfmac. The reason seems to be a race between userspace removing the CQM config and the driver calling cfg80211_cqm_rssi_notify(), where if the data is freed while cfg80211_cqm_rssi_notify() runs it will crash since it assumes wdev->cqm_config is set. This can't be fixed with a simple non-NULL check since there's nothing we can do for locking easily, so use RCU instead to protect the pointer, but that requires pulling the updates out into an asynchronous worker so they can sleep and call back into the driver. Since we need to change the free anyway, also change it to go back to the old settings if changing the settings fails. Reported-and-tested-by: Max Schulze Closes: https://lore.kernel.org/r/ac96309a-8d8d-4435-36e6-6d152eb31876@online.de Fixes: 4a4b8169501b ("cfg80211: Accept multiple RSSI thresholds for CQM") Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- include/net/cfg80211.h | 3 +- net/wireless/core.c | 14 +++---- net/wireless/core.h | 7 +++- net/wireless/nl80211.c | 95 +++++++++++++++++++++++++++--------------- 4 files changed, 76 insertions(+), 43 deletions(-) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f2144db89183..ab64bb94c92f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5877,7 +5877,8 @@ struct wireless_dev { } wext; #endif - struct cfg80211_cqm_config *cqm_config; + struct wiphy_work cqm_rssi_work; + struct cfg80211_cqm_config __rcu *cqm_config; struct list_head pmsr_list; spinlock_t pmsr_lock; diff --git a/net/wireless/core.c b/net/wireless/core.c index 8a1f34e95c4f..2c7960467206 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1176,16 +1176,11 @@ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state_reason); -void cfg80211_cqm_config_free(struct wireless_dev *wdev) -{ - kfree(wdev->cqm_config); - wdev->cqm_config = NULL; -} - static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, bool unregister_netdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_cqm_config *cqm_config; unsigned int link_id; ASSERT_RTNL(); @@ -1224,7 +1219,10 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, kfree_sensitive(wdev->wext.keys); wdev->wext.keys = NULL; #endif - cfg80211_cqm_config_free(wdev); + wiphy_work_cancel(wdev->wiphy, &wdev->cqm_rssi_work); + /* deleted from the list, so can't be found from nl80211 any more */ + cqm_config = rcu_access_pointer(wdev->cqm_config); + kfree_rcu(cqm_config, rcu_head); /* * Ensure that all events have been processed and @@ -1376,6 +1374,8 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; #endif + wiphy_work_init(&wdev->cqm_rssi_work, cfg80211_cqm_rssi_notify_work); + if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) wdev->ps = true; else diff --git a/net/wireless/core.h b/net/wireless/core.h index 0481a8a539d5..86fd79912254 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -293,12 +293,17 @@ struct cfg80211_beacon_registration { }; struct cfg80211_cqm_config { + struct rcu_head rcu_head; u32 rssi_hyst; s32 last_rssi_event_value; + enum nl80211_cqm_rssi_threshold_event last_rssi_event_type; int n_rssi_thresholds; s32 rssi_thresholds[]; }; +void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, + struct wiphy_work *work); + void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev); /* free object */ @@ -563,8 +568,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, #define CFG80211_DEV_WARN_ON(cond) ({bool __r = (cond); __r; }) #endif -void cfg80211_cqm_config_free(struct wireless_dev *wdev); - void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid); void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev); void cfg80211_pmsr_free_wk(struct work_struct *work); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 12c7c89d5be1..1d993a490ac4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12565,7 +12565,8 @@ static int nl80211_set_cqm_txe(struct genl_info *info, } static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, + struct cfg80211_cqm_config *cqm_config) { struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; @@ -12574,7 +12575,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, int err; /* RSSI reporting disabled? */ - if (!wdev->cqm_config) + if (!cqm_config) return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); /* @@ -12583,7 +12584,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, * connection is established and enough beacons received to calculate * the average. */ - if (!wdev->cqm_config->last_rssi_event_value && + if (!cqm_config->last_rssi_event_value && wdev->links[0].client.current_bss && rdev->ops->get_station) { struct station_info sinfo = {}; @@ -12597,30 +12598,30 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, cfg80211_sinfo_release_content(&sinfo); if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) - wdev->cqm_config->last_rssi_event_value = + cqm_config->last_rssi_event_value = (s8) sinfo.rx_beacon_signal_avg; } - last = wdev->cqm_config->last_rssi_event_value; - hyst = wdev->cqm_config->rssi_hyst; - n = wdev->cqm_config->n_rssi_thresholds; + last = cqm_config->last_rssi_event_value; + hyst = cqm_config->rssi_hyst; + n = cqm_config->n_rssi_thresholds; for (i = 0; i < n; i++) { i = array_index_nospec(i, n); - if (last < wdev->cqm_config->rssi_thresholds[i]) + if (last < cqm_config->rssi_thresholds[i]) break; } low_index = i - 1; if (low_index >= 0) { low_index = array_index_nospec(low_index, n); - low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; + low = cqm_config->rssi_thresholds[low_index] - hyst; } else { low = S32_MIN; } if (i < n) { i = array_index_nospec(i, n); - high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; + high = cqm_config->rssi_thresholds[i] + hyst - 1; } else { high = S32_MAX; } @@ -12633,6 +12634,7 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, u32 hysteresis) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_cqm_config *cqm_config = NULL, *old; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; int i, err; @@ -12650,10 +12652,6 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - wdev_lock(wdev); - cfg80211_cqm_config_free(wdev); - wdev_unlock(wdev); - if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) { if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */ return rdev_set_cqm_rssi_config(rdev, dev, 0, 0); @@ -12670,9 +12668,10 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, n_thresholds = 0; wdev_lock(wdev); - if (n_thresholds) { - struct cfg80211_cqm_config *cqm_config; + old = rcu_dereference_protected(wdev->cqm_config, + lockdep_is_held(&wdev->mtx)); + if (n_thresholds) { cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, n_thresholds), GFP_KERNEL); @@ -12687,11 +12686,18 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, flex_array_size(cqm_config, rssi_thresholds, n_thresholds)); - wdev->cqm_config = cqm_config; + rcu_assign_pointer(wdev->cqm_config, cqm_config); + } else { + RCU_INIT_POINTER(wdev->cqm_config, NULL); } - err = cfg80211_cqm_rssi_update(rdev, dev); - + err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); + if (err) { + rcu_assign_pointer(wdev->cqm_config, old); + kfree_rcu(cqm_config, rcu_head); + } else { + kfree_rcu(old, rcu_head); + } unlock: wdev_unlock(wdev); @@ -18719,9 +18725,8 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, s32 rssi_level, gfp_t gfp) { - struct sk_buff *msg; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_cqm_config *cqm_config; trace_cfg80211_cqm_rssi_notify(dev, rssi_event, rssi_level); @@ -18729,18 +18734,41 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH)) return; - if (wdev->cqm_config) { - wdev->cqm_config->last_rssi_event_value = rssi_level; - - cfg80211_cqm_rssi_update(rdev, dev); - - if (rssi_level == 0) - rssi_level = wdev->cqm_config->last_rssi_event_value; + rcu_read_lock(); + cqm_config = rcu_dereference(wdev->cqm_config); + if (cqm_config) { + cqm_config->last_rssi_event_value = rssi_level; + cqm_config->last_rssi_event_type = rssi_event; + wiphy_work_queue(wdev->wiphy, &wdev->cqm_rssi_work); } + rcu_read_unlock(); +} +EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); - msg = cfg80211_prepare_cqm(dev, NULL, gfp); +void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + cqm_rssi_work); + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + enum nl80211_cqm_rssi_threshold_event rssi_event; + struct cfg80211_cqm_config *cqm_config; + struct sk_buff *msg; + s32 rssi_level; + + wdev_lock(wdev); + cqm_config = rcu_dereference_protected(wdev->cqm_config, + lockdep_is_held(&wdev->mtx)); + if (!wdev->cqm_config) + goto unlock; + + cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); + + rssi_level = cqm_config->last_rssi_event_value; + rssi_event = cqm_config->last_rssi_event_type; + + msg = cfg80211_prepare_cqm(wdev->netdev, NULL, GFP_KERNEL); if (!msg) - return; + goto unlock; if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, rssi_event)) @@ -18750,14 +18778,15 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_level)) goto nla_put_failure; - cfg80211_send_cqm(msg, gfp); + cfg80211_send_cqm(msg, GFP_KERNEL); - return; + goto unlock; nla_put_failure: nlmsg_free(msg); + unlock: + wdev_unlock(wdev); } -EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, u32 num_packets, From 42970d32fe1e5a68f7dd0e487ef3881c1cc95882 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Sep 2023 09:36:57 +0200 Subject: [PATCH 1974/2093] wifi: cfg80211: add missing kernel-doc for cqm_rssi_work [ Upstream commit d1383077c225ceb87ac7a3b56b2c505193f77ed7 ] As reported by Stephen, I neglected to add the kernel-doc for the new struct member. Fix that. Reported-by: Stephen Rothwell Fixes: 37c20b2effe9 ("wifi: cfg80211: fix cqm_config access race") Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- include/net/cfg80211.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ab64bb94c92f..7a6c3059d50b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5805,6 +5805,7 @@ void wiphy_delayed_work_cancel(struct wiphy *wiphy, * @event_lock: (private) lock for event list * @owner_nlportid: (private) owner socket port ID * @nl_owner_dead: (private) owner socket went away + * @cqm_rssi_work: (private) CQM RSSI reporting work * @cqm_config: (private) nl80211 RSSI monitor state * @pmsr_list: (private) peer measurement requests * @pmsr_lock: (private) peer measurements requests/results lock From 6b706286473db4fd54b5f869faa67f4a8cb18e99 Mon Sep 17 00:00:00 2001 From: Pin-yen Lin Date: Fri, 8 Sep 2023 18:41:12 +0800 Subject: [PATCH 1975/2093] wifi: mwifiex: Fix oob check condition in mwifiex_process_rx_packet [ Upstream commit aef7a0300047e7b4707ea0411dc9597cba108fc8 ] Only skip the code path trying to access the rfc1042 headers when the buffer is too small, so the driver can still process packets without rfc1042 headers. Fixes: 119585281617 ("wifi: mwifiex: Fix OOB and integer underflow when rx packets") Signed-off-by: Pin-yen Lin Acked-by: Brian Norris Reviewed-by: Matthew Wang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230908104308.1546501-1-treapking@chromium.org Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/sta_rx.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c index 65420ad67416..257737137cd7 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c @@ -86,7 +86,8 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv, rx_pkt_len = le16_to_cpu(local_rx_pd->rx_pkt_length); rx_pkt_hdr = (void *)local_rx_pd + rx_pkt_off; - if (sizeof(*rx_pkt_hdr) + rx_pkt_off > skb->len) { + if (sizeof(rx_pkt_hdr->eth803_hdr) + sizeof(rfc1042_header) + + rx_pkt_off > skb->len) { mwifiex_dbg(priv->adapter, ERROR, "wrong rx packet offset: len=%d, rx_pkt_off=%d\n", skb->len, rx_pkt_off); @@ -95,12 +96,13 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv, return -1; } - if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, - sizeof(bridge_tunnel_header))) || - (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header, - sizeof(rfc1042_header)) && - ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_AARP && - ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_IPX)) { + if (sizeof(*rx_pkt_hdr) + rx_pkt_off <= skb->len && + ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, + sizeof(bridge_tunnel_header))) || + (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header, + sizeof(rfc1042_header)) && + ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_AARP && + ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_IPX))) { /* * Replace the 803 header and rfc1042 header (llc/snap) with an * EthernetII header, keep the src/dst and snap_type From c14c7214fc68ec003c7ec7b36598da2d89d47421 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Mon, 18 Sep 2023 16:07:24 +0200 Subject: [PATCH 1976/2093] leds: Drop BUG_ON check for LED_COLOR_ID_MULTI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9dc1664fab2246bc2c3e9bf2cf21518a857f9b5b ] Commit c3f853184bed ("leds: Fix BUG_ON check for LED_COLOR_ID_MULTI that is always false") fixed a no-op BUG_ON. This turned out to cause a regression, since some in-tree device-tree files already use LED_COLOR_ID_MULTI. Drop the BUG_ON altogether. Fixes: c3f853184bed ("leds: Fix BUG_ON check for LED_COLOR_ID_MULTI that is always false") Reported-by: Da Xue Closes: https://lore.kernel.org/linux-leds/ZQLelWcNjjp2xndY@duo.ucw.cz/T/ Signed-off-by: Marek Behún Link: https://lore.kernel.org/r/20230918140724.18634-1-kabel@kernel.org Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/leds/led-core.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index aad8bc44459f..d94d60b52646 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -424,10 +424,6 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data, led_parse_fwnode_props(dev, fwnode, &props); - /* We want to label LEDs that can produce full range of colors - * as RGB, not multicolor */ - BUG_ON(props.color == LED_COLOR_ID_MULTI); - if (props.label) { /* * If init_data.devicename is NULL, then it indicates that From 163042a01544b72fab9ebec77ac3969437d53158 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Sun, 17 Sep 2023 23:38:46 +0800 Subject: [PATCH 1977/2093] bpf: Fix tr dereferencing [ Upstream commit b724a6418f1f853bcb39c8923bf14a50c7bdbd07 ] Fix 'tr' dereferencing bug when CONFIG_BPF_JIT is turned off. When CONFIG_BPF_JIT is turned off, 'bpf_trampoline_get()' returns NULL, which is same as the cases when CONFIG_BPF_JIT is turned on. Closes: https://lore.kernel.org/r/202309131936.5Nc8eUD0-lkp@intel.com/ Fixes: f7b12b6fea00 ("bpf: verifier: refactor check_attach_btf_id()") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Leon Hwang Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230917153846.88732-1-hffilwlqm@gmail.com Signed-off-by: Sasha Levin --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1ed2ec035e77..1fba826f0ace 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1065,7 +1065,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { - return ERR_PTR(-EOPNOTSUPP); + return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) From c6ac402567e4218960b25e35bc7d48c68d5e633b Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 9 Jun 2023 16:30:01 +0800 Subject: [PATCH 1978/2093] regulator: mt6358: Drop *_SSHUB regulators [ Upstream commit 04ba665248ed91576d326041108e5fc2ec2254eb ] The *_SSHUB regulators are actually alternate configuration interfaces for their non *_SSHUB counterparts. They are not separate regulator outputs. These registers are intended for the companion processor to use to configure the power rails while the main processor is sleeping. They are not intended for the main operating system to use. Since they are not real outputs they shouldn't be modeled separately. Remove them. Luckily no device tree actually uses them. Signed-off-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20230609083009.2822259-5-wenst@chromium.org Signed-off-by: Mark Brown Stable-dep-of: 7e37c851374e ("regulator: mt6358: split ops for buck and linear range LDO regulators") Signed-off-by: Sasha Levin --- drivers/regulator/mt6358-regulator.c | 14 -------------- include/linux/regulator/mt6358-regulator.h | 4 ---- 2 files changed, 18 deletions(-) diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c index 8a5ce990f1bf..153c1fd5fb0b 100644 --- a/drivers/regulator/mt6358-regulator.c +++ b/drivers/regulator/mt6358-regulator.c @@ -505,9 +505,6 @@ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250, buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 1), - MT6358_BUCK("buck_vcore_sshub", VCORE_SSHUB, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_SSHUB_ELR0, 0x7f, - MT6358_VCORE_VGPU_ANA_CON0, 1), MT6358_BUCK("buck_vpa", VPA, 500000, 3650000, 50000, buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, MT6358_VPA_ANA_CON0, 3), @@ -587,10 +584,6 @@ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250, buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON2, 0x7f), - MT6358_LDO1("ldo_vsram_others_sshub", VSRAM_OTHERS_SSHUB, 500000, - 1293750, 6250, buck_volt_range1, - MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f, - MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f), MT6358_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250, buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON3, 0x7f), @@ -607,9 +600,6 @@ static struct mt6358_regulator_info mt6366_regulators[] = { MT6366_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250, buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 1), - MT6366_BUCK("buck_vcore_sshub", VCORE_SSHUB, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_SSHUB_ELR0, 0x7f, - MT6358_VCORE_VGPU_ANA_CON0, 1), MT6366_BUCK("buck_vpa", VPA, 500000, 3650000, 50000, buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, MT6358_VPA_ANA_CON0, 3), @@ -678,10 +668,6 @@ static struct mt6358_regulator_info mt6366_regulators[] = { MT6366_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250, buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON2, 0x7f), - MT6366_LDO1("ldo_vsram_others_sshub", VSRAM_OTHERS_SSHUB, 500000, - 1293750, 6250, buck_volt_range1, - MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f, - MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1, 0x7f), MT6366_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250, buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON3, 0x7f), diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h index bdcf83cd719e..be9f61e3e8e6 100644 --- a/include/linux/regulator/mt6358-regulator.h +++ b/include/linux/regulator/mt6358-regulator.h @@ -48,8 +48,6 @@ enum { MT6358_ID_VLDO28, MT6358_ID_VAUD28, MT6358_ID_VSIM2, - MT6358_ID_VCORE_SSHUB, - MT6358_ID_VSRAM_OTHERS_SSHUB, MT6358_ID_RG_MAX, }; @@ -90,8 +88,6 @@ enum { MT6366_ID_VMC, MT6366_ID_VAUD28, MT6366_ID_VSIM2, - MT6366_ID_VCORE_SSHUB, - MT6366_ID_VSRAM_OTHERS_SSHUB, MT6366_ID_RG_MAX, }; From a01576f58b1953752d125664df4ae08daa2e5e3e Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 9 Jun 2023 16:30:03 +0800 Subject: [PATCH 1979/2093] regulator: mt6358: Use linear voltage helpers for single range regulators [ Upstream commit ea861df772fd8cca715d43f62fe13c09c975f7a2 ] Some of the regulators on the MT6358/MT6366 PMICs have just one linear voltage range. These are the bulk regulators and VSRAM_* LDOs. Currently they are modeled with one linear range, but also have their minimum, maximum, and step voltage described. Convert them to the linear voltage helpers. These helpers are a bit simpler, and we can also drop the linear range definitions. Also reflow the touched lines now that they are shorter. Signed-off-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230609083009.2822259-7-wenst@chromium.org Signed-off-by: Mark Brown Stable-dep-of: 7e37c851374e ("regulator: mt6358: split ops for buck and linear range LDO regulators") Signed-off-by: Sasha Levin --- drivers/regulator/mt6358-regulator.c | 121 +++++++++------------------ 1 file changed, 40 insertions(+), 81 deletions(-) diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c index 153c1fd5fb0b..56b5fc9f62c9 100644 --- a/drivers/regulator/mt6358-regulator.c +++ b/drivers/regulator/mt6358-regulator.c @@ -35,7 +35,7 @@ struct mt6358_regulator_info { }; #define MT6358_BUCK(match, vreg, min, max, step, \ - volt_ranges, vosel_mask, _da_vsel_reg, _da_vsel_mask, \ + vosel_mask, _da_vsel_reg, _da_vsel_mask, \ _modeset_reg, _modeset_shift) \ [MT6358_ID_##vreg] = { \ .desc = { \ @@ -46,8 +46,8 @@ struct mt6358_regulator_info { .id = MT6358_ID_##vreg, \ .owner = THIS_MODULE, \ .n_voltages = ((max) - (min)) / (step) + 1, \ - .linear_ranges = volt_ranges, \ - .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .min_uV = (min), \ + .uV_step = (step), \ .vsel_reg = MT6358_BUCK_##vreg##_ELR0, \ .vsel_mask = vosel_mask, \ .enable_reg = MT6358_BUCK_##vreg##_CON0, \ @@ -87,7 +87,7 @@ struct mt6358_regulator_info { } #define MT6358_LDO1(match, vreg, min, max, step, \ - volt_ranges, _da_vsel_reg, _da_vsel_mask, \ + _da_vsel_reg, _da_vsel_mask, \ vosel, vosel_mask) \ [MT6358_ID_##vreg] = { \ .desc = { \ @@ -98,8 +98,8 @@ struct mt6358_regulator_info { .id = MT6358_ID_##vreg, \ .owner = THIS_MODULE, \ .n_voltages = ((max) - (min)) / (step) + 1, \ - .linear_ranges = volt_ranges, \ - .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .min_uV = (min), \ + .uV_step = (step), \ .vsel_reg = vosel, \ .vsel_mask = vosel_mask, \ .enable_reg = MT6358_LDO_##vreg##_CON0, \ @@ -131,7 +131,7 @@ struct mt6358_regulator_info { } #define MT6366_BUCK(match, vreg, min, max, step, \ - volt_ranges, vosel_mask, _da_vsel_reg, _da_vsel_mask, \ + vosel_mask, _da_vsel_reg, _da_vsel_mask, \ _modeset_reg, _modeset_shift) \ [MT6366_ID_##vreg] = { \ .desc = { \ @@ -142,8 +142,8 @@ struct mt6358_regulator_info { .id = MT6366_ID_##vreg, \ .owner = THIS_MODULE, \ .n_voltages = ((max) - (min)) / (step) + 1, \ - .linear_ranges = volt_ranges, \ - .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .min_uV = (min), \ + .uV_step = (step), \ .vsel_reg = MT6358_BUCK_##vreg##_ELR0, \ .vsel_mask = vosel_mask, \ .enable_reg = MT6358_BUCK_##vreg##_CON0, \ @@ -183,7 +183,7 @@ struct mt6358_regulator_info { } #define MT6366_LDO1(match, vreg, min, max, step, \ - volt_ranges, _da_vsel_reg, _da_vsel_mask, \ + _da_vsel_reg, _da_vsel_mask, \ vosel, vosel_mask) \ [MT6366_ID_##vreg] = { \ .desc = { \ @@ -194,8 +194,8 @@ struct mt6358_regulator_info { .id = MT6366_ID_##vreg, \ .owner = THIS_MODULE, \ .n_voltages = ((max) - (min)) / (step) + 1, \ - .linear_ranges = volt_ranges, \ - .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .min_uV = (min), \ + .uV_step = (step), \ .vsel_reg = vosel, \ .vsel_mask = vosel_mask, \ .enable_reg = MT6358_LDO_##vreg##_CON0, \ @@ -226,21 +226,6 @@ struct mt6358_regulator_info { .qi = BIT(15), \ } -static const struct linear_range buck_volt_range1[] = { - REGULATOR_LINEAR_RANGE(500000, 0, 0x7f, 6250), -}; - -static const struct linear_range buck_volt_range2[] = { - REGULATOR_LINEAR_RANGE(500000, 0, 0x7f, 12500), -}; - -static const struct linear_range buck_volt_range3[] = { - REGULATOR_LINEAR_RANGE(500000, 0, 0x3f, 50000), -}; - -static const struct linear_range buck_volt_range4[] = { - REGULATOR_LINEAR_RANGE(1000000, 0, 0x7f, 12500), -}; static const unsigned int vdram2_voltages[] = { 600000, 1800000, @@ -464,8 +449,8 @@ static unsigned int mt6358_regulator_get_mode(struct regulator_dev *rdev) } static const struct regulator_ops mt6358_volt_range_ops = { - .list_voltage = regulator_list_voltage_linear_range, - .map_voltage = regulator_map_voltage_linear_range, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = mt6358_get_buck_voltage_sel, .set_voltage_time_sel = regulator_set_voltage_time_sel, @@ -500,32 +485,23 @@ static const struct regulator_ops mt6358_volt_fixed_ops = { /* The array is indexed by id(MT6358_ID_XXX) */ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_BUCK("buck_vdram1", VDRAM1, 500000, 2087500, 12500, - buck_volt_range2, 0x7f, MT6358_BUCK_VDRAM1_DBG0, 0x7f, - MT6358_VDRAM1_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VDRAM1_DBG0, 0x7f, MT6358_VDRAM1_ANA_CON0, 8), MT6358_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, - MT6358_VCORE_VGPU_ANA_CON0, 1), + 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 1), MT6358_BUCK("buck_vpa", VPA, 500000, 3650000, 50000, - buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, - MT6358_VPA_ANA_CON0, 3), + 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, MT6358_VPA_ANA_CON0, 3), MT6358_BUCK("buck_vproc11", VPROC11, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VPROC11_DBG0, 0x7f, - MT6358_VPROC_ANA_CON0, 1), + 0x7f, MT6358_BUCK_VPROC11_DBG0, 0x7f, MT6358_VPROC_ANA_CON0, 1), MT6358_BUCK("buck_vproc12", VPROC12, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VPROC12_DBG0, 0x7f, - MT6358_VPROC_ANA_CON0, 2), + 0x7f, MT6358_BUCK_VPROC12_DBG0, 0x7f, MT6358_VPROC_ANA_CON0, 2), MT6358_BUCK("buck_vgpu", VGPU, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VGPU_ELR0, 0x7f, - MT6358_VCORE_VGPU_ANA_CON0, 2), + 0x7f, MT6358_BUCK_VGPU_ELR0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 2), MT6358_BUCK("buck_vs2", VS2, 500000, 2087500, 12500, - buck_volt_range2, 0x7f, MT6358_BUCK_VS2_DBG0, 0x7f, - MT6358_VS2_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VS2_DBG0, 0x7f, MT6358_VS2_ANA_CON0, 8), MT6358_BUCK("buck_vmodem", VMODEM, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VMODEM_DBG0, 0x7f, - MT6358_VMODEM_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VMODEM_DBG0, 0x7f, MT6358_VMODEM_ANA_CON0, 8), MT6358_BUCK("buck_vs1", VS1, 1000000, 2587500, 12500, - buck_volt_range4, 0x7f, MT6358_BUCK_VS1_DBG0, 0x7f, - MT6358_VS1_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VS1_DBG0, 0x7f, MT6358_VS1_ANA_CON0, 8), MT6358_REG_FIXED("ldo_vrf12", VRF12, MT6358_LDO_VRF12_CON0, 0, 1200000), MT6358_REG_FIXED("ldo_vio18", VIO18, @@ -579,48 +555,35 @@ static struct mt6358_regulator_info mt6358_regulators[] = { MT6358_LDO("ldo_vsim2", VSIM2, vsim_voltages, vsim_idx, MT6358_LDO_VSIM2_CON0, 0, MT6358_VSIM2_ANA_CON0, 0xf00), MT6358_LDO1("ldo_vsram_proc11", VSRAM_PROC11, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_PROC11_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON0, 0x7f), + MT6358_LDO_VSRAM_PROC11_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON0, 0x7f), MT6358_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON2, 0x7f), + MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON2, 0x7f), MT6358_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON3, 0x7f), + MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON3, 0x7f), MT6358_LDO1("ldo_vsram_proc12", VSRAM_PROC12, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_PROC12_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON1, 0x7f), + MT6358_LDO_VSRAM_PROC12_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON1, 0x7f), }; /* The array is indexed by id(MT6366_ID_XXX) */ static struct mt6358_regulator_info mt6366_regulators[] = { MT6366_BUCK("buck_vdram1", VDRAM1, 500000, 2087500, 12500, - buck_volt_range2, 0x7f, MT6358_BUCK_VDRAM1_DBG0, 0x7f, - MT6358_VDRAM1_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VDRAM1_DBG0, 0x7f, MT6358_VDRAM1_ANA_CON0, 8), MT6366_BUCK("buck_vcore", VCORE, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, - MT6358_VCORE_VGPU_ANA_CON0, 1), + 0x7f, MT6358_BUCK_VCORE_DBG0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 1), MT6366_BUCK("buck_vpa", VPA, 500000, 3650000, 50000, - buck_volt_range3, 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, - MT6358_VPA_ANA_CON0, 3), + 0x3f, MT6358_BUCK_VPA_DBG0, 0x3f, MT6358_VPA_ANA_CON0, 3), MT6366_BUCK("buck_vproc11", VPROC11, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VPROC11_DBG0, 0x7f, - MT6358_VPROC_ANA_CON0, 1), + 0x7f, MT6358_BUCK_VPROC11_DBG0, 0x7f, MT6358_VPROC_ANA_CON0, 1), MT6366_BUCK("buck_vproc12", VPROC12, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VPROC12_DBG0, 0x7f, - MT6358_VPROC_ANA_CON0, 2), + 0x7f, MT6358_BUCK_VPROC12_DBG0, 0x7f, MT6358_VPROC_ANA_CON0, 2), MT6366_BUCK("buck_vgpu", VGPU, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VGPU_ELR0, 0x7f, - MT6358_VCORE_VGPU_ANA_CON0, 2), + 0x7f, MT6358_BUCK_VGPU_ELR0, 0x7f, MT6358_VCORE_VGPU_ANA_CON0, 2), MT6366_BUCK("buck_vs2", VS2, 500000, 2087500, 12500, - buck_volt_range2, 0x7f, MT6358_BUCK_VS2_DBG0, 0x7f, - MT6358_VS2_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VS2_DBG0, 0x7f, MT6358_VS2_ANA_CON0, 8), MT6366_BUCK("buck_vmodem", VMODEM, 500000, 1293750, 6250, - buck_volt_range1, 0x7f, MT6358_BUCK_VMODEM_DBG0, 0x7f, - MT6358_VMODEM_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VMODEM_DBG0, 0x7f, MT6358_VMODEM_ANA_CON0, 8), MT6366_BUCK("buck_vs1", VS1, 1000000, 2587500, 12500, - buck_volt_range4, 0x7f, MT6358_BUCK_VS1_DBG0, 0x7f, - MT6358_VS1_ANA_CON0, 8), + 0x7f, MT6358_BUCK_VS1_DBG0, 0x7f, MT6358_VS1_ANA_CON0, 8), MT6366_REG_FIXED("ldo_vrf12", VRF12, MT6358_LDO_VRF12_CON0, 0, 1200000), MT6366_REG_FIXED("ldo_vio18", VIO18, @@ -663,17 +626,13 @@ static struct mt6358_regulator_info mt6366_regulators[] = { MT6366_LDO("ldo_vsim2", VSIM2, vsim_voltages, vsim_idx, MT6358_LDO_VSIM2_CON0, 0, MT6358_VSIM2_ANA_CON0, 0xf00), MT6366_LDO1("ldo_vsram_proc11", VSRAM_PROC11, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_PROC11_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON0, 0x7f), + MT6358_LDO_VSRAM_PROC11_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON0, 0x7f), MT6366_LDO1("ldo_vsram_others", VSRAM_OTHERS, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON2, 0x7f), + MT6358_LDO_VSRAM_OTHERS_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON2, 0x7f), MT6366_LDO1("ldo_vsram_gpu", VSRAM_GPU, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON3, 0x7f), + MT6358_LDO_VSRAM_GPU_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON3, 0x7f), MT6366_LDO1("ldo_vsram_proc12", VSRAM_PROC12, 500000, 1293750, 6250, - buck_volt_range1, MT6358_LDO_VSRAM_PROC12_DBG0, 0x7f00, - MT6358_LDO_VSRAM_CON1, 0x7f), + MT6358_LDO_VSRAM_PROC12_DBG0, 0x7f00, MT6358_LDO_VSRAM_CON1, 0x7f), }; static int mt6358_regulator_probe(struct platform_device *pdev) From b46384a681a861c8b47aaaf9862313afc29235f8 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Wed, 20 Sep 2023 16:53:34 +0800 Subject: [PATCH 1980/2093] regulator: mt6358: split ops for buck and linear range LDO regulators [ Upstream commit 7e37c851374eca2d1f6128de03195c9f7b4baaf2 ] The buck and linear range LDO (VSRAM_*) regulators share one set of ops. This set includes support for get/set mode. However this only makes sense for buck regulators, not LDOs. The callbacks were not checking whether the register offset and/or mask for mode setting was valid or not. This ends up making the kernel report "normal" mode operation for the LDOs. Create a new set of ops without the get/set mode callbacks for the linear range LDO regulators. Fixes: f67ff1bd58f0 ("regulator: mt6358: Add support for MT6358 regulator") Signed-off-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230920085336.136238-1-wenst@chromium.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/mt6358-regulator.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c index 56b5fc9f62c9..a0441b808671 100644 --- a/drivers/regulator/mt6358-regulator.c +++ b/drivers/regulator/mt6358-regulator.c @@ -41,7 +41,7 @@ struct mt6358_regulator_info { .desc = { \ .name = #vreg, \ .of_match = of_match_ptr(match), \ - .ops = &mt6358_volt_range_ops, \ + .ops = &mt6358_buck_ops, \ .type = REGULATOR_VOLTAGE, \ .id = MT6358_ID_##vreg, \ .owner = THIS_MODULE, \ @@ -137,7 +137,7 @@ struct mt6358_regulator_info { .desc = { \ .name = #vreg, \ .of_match = of_match_ptr(match), \ - .ops = &mt6358_volt_range_ops, \ + .ops = &mt6358_buck_ops, \ .type = REGULATOR_VOLTAGE, \ .id = MT6366_ID_##vreg, \ .owner = THIS_MODULE, \ @@ -448,7 +448,7 @@ static unsigned int mt6358_regulator_get_mode(struct regulator_dev *rdev) } } -static const struct regulator_ops mt6358_volt_range_ops = { +static const struct regulator_ops mt6358_buck_ops = { .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, .set_voltage_sel = regulator_set_voltage_sel_regmap, @@ -462,6 +462,18 @@ static const struct regulator_ops mt6358_volt_range_ops = { .get_mode = mt6358_regulator_get_mode, }; +static const struct regulator_ops mt6358_volt_range_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = mt6358_get_buck_voltage_sel, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6358_get_status, +}; + static const struct regulator_ops mt6358_volt_table_ops = { .list_voltage = regulator_list_voltage_table, .map_voltage = regulator_map_voltage_iterate, From c201d944bc38e056bbb4654d2c1060bf025a133e Mon Sep 17 00:00:00 2001 From: Yao Xiao Date: Sat, 26 Aug 2023 16:13:13 +0800 Subject: [PATCH 1981/2093] Bluetooth: Delete unused hci_req_prepare_suspend() declaration [ Upstream commit cbaabbcdcbd355f0a1ccc09a925575c51c270750 ] hci_req_prepare_suspend() has been deprecated in favor of hci_suspend_sync(). Fixes: 182ee45da083 ("Bluetooth: hci_sync: Rework hci_suspend_notifier") Signed-off-by: Yao Xiao Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/hci_request.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index b9c5a9823837..0be75cf0efed 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -71,7 +71,5 @@ struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn); void hci_req_add_le_passive_scan(struct hci_request *req); -void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next); - void hci_request_setup(struct hci_dev *hdev); void hci_request_cancel_all(struct hci_dev *hdev); From 6bfc4c7043c88557bec903f3f9ede4506998ec7f Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 28 Aug 2023 13:05:45 -0700 Subject: [PATCH 1982/2093] Bluetooth: ISO: Fix handling of listen for unicast [ Upstream commit e0275ea52169412b8faccb4e2f4fed8a057844c6 ] iso_listen_cis shall only return -EADDRINUSE if the listening socket has the destination set to BDADDR_ANY otherwise if the destination is set to a specific address it is for broadcast which shall be ignored. Fixes: f764a6c2c1e4 ("Bluetooth: ISO: Add broadcast support") Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/iso.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 5cd2e775915b..91e990accbf2 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -458,7 +458,7 @@ static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb) } /* -------- Socket interface ---------- */ -static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *ba) +static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *src, bdaddr_t *dst) { struct sock *sk; @@ -466,7 +466,10 @@ static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *ba) if (sk->sk_state != BT_LISTEN) continue; - if (!bacmp(&iso_pi(sk)->src, ba)) + if (bacmp(&iso_pi(sk)->dst, dst)) + continue; + + if (!bacmp(&iso_pi(sk)->src, src)) return sk; } @@ -910,7 +913,7 @@ static int iso_listen_cis(struct sock *sk) write_lock(&iso_sk_list.lock); - if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src)) + if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src, &iso_pi(sk)->dst)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); From b9eded289bea9c6f5a1226d033caa716e53f298f Mon Sep 17 00:00:00 2001 From: Alexandra Diupina Date: Tue, 19 Sep 2023 17:25:02 +0300 Subject: [PATCH 1983/2093] drivers/net: process the result of hdlc_open() and add call of hdlc_close() in uhdlc_close() [ Upstream commit a59addacf899b1b21a7b7449a1c52c98704c2472 ] Process the result of hdlc_open() and call uhdlc_close() in case of an error. It is necessary to pass the error code up the control flow, similar to a possible error in request_irq(). Also add a hdlc_close() call to the uhdlc_close() because the comment to hdlc_close() says it must be called by the hardware driver when the HDLC device is being closed Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: c19b6d246a35 ("drivers/net: support hdlc function for QE-UCC") Signed-off-by: Alexandra Diupina Reviewed-by: Christophe Leroy Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/wan/fsl_ucc_hdlc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 1c53b5546927..5fec8abe8e1d 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -34,6 +34,8 @@ #define TDM_PPPOHT_SLIC_MAXIN #define RX_BD_ERRORS (R_CD_S | R_OV_S | R_CR_S | R_AB_S | R_NO_S | R_LG_S) +static int uhdlc_close(struct net_device *dev); + static struct ucc_tdm_info utdm_primary_info = { .uf_info = { .tsa = 0, @@ -708,6 +710,7 @@ static int uhdlc_open(struct net_device *dev) hdlc_device *hdlc = dev_to_hdlc(dev); struct ucc_hdlc_private *priv = hdlc->priv; struct ucc_tdm *utdm = priv->utdm; + int rc = 0; if (priv->hdlc_busy != 1) { if (request_irq(priv->ut_info->uf_info.irq, @@ -731,10 +734,13 @@ static int uhdlc_open(struct net_device *dev) napi_enable(&priv->napi); netdev_reset_queue(dev); netif_start_queue(dev); - hdlc_open(dev); + + rc = hdlc_open(dev); + if (rc) + uhdlc_close(dev); } - return 0; + return rc; } static void uhdlc_memclean(struct ucc_hdlc_private *priv) @@ -824,6 +830,8 @@ static int uhdlc_close(struct net_device *dev) netdev_reset_queue(dev); priv->hdlc_busy = 0; + hdlc_close(dev); + return 0; } From 6150d4596861cc564f88f6dcea956f83b5d83ac9 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 19 Sep 2023 21:47:47 +0200 Subject: [PATCH 1984/2093] wifi: mt76: mt76x02: fix MT76x0 external LNA gain handling [ Upstream commit 684e45e120b82deccaf8b85633905304a3bbf56d ] On MT76x0, LNA gain should be applied for both external and internal LNA. On MT76x2, LNA gain should be treated as 0 for external LNA. Move the LNA type based logic to mt76x2 in order to fix mt76x0. Fixes: 2daa67588f34 ("mt76x0: unify lna_gain parsing") Reported-by: Shiji Yang Signed-off-by: Felix Fietkau Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230919194747.31647-1-nbd@nbd.name Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c | 7 ------- drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c | 13 +++++++++++-- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c index 0acabba2d1a5..5d402cf2951c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c @@ -131,15 +131,8 @@ u8 mt76x02_get_lna_gain(struct mt76x02_dev *dev, s8 *lna_2g, s8 *lna_5g, struct ieee80211_channel *chan) { - u16 val; u8 lna; - val = mt76x02_eeprom_get(dev, MT_EE_NIC_CONF_1); - if (val & MT_EE_NIC_CONF_1_LNA_EXT_2G) - *lna_2g = 0; - if (val & MT_EE_NIC_CONF_1_LNA_EXT_5G) - memset(lna_5g, 0, sizeof(s8) * 3); - if (chan->band == NL80211_BAND_2GHZ) lna = *lna_2g; else if (chan->hw_value <= 64) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c index c57e05a5c65e..91807bf662dd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c @@ -256,7 +256,8 @@ void mt76x2_read_rx_gain(struct mt76x02_dev *dev) struct ieee80211_channel *chan = dev->mphy.chandef.chan; int channel = chan->hw_value; s8 lna_5g[3], lna_2g; - u8 lna; + bool use_lna; + u8 lna = 0; u16 val; if (chan->band == NL80211_BAND_2GHZ) @@ -275,7 +276,15 @@ void mt76x2_read_rx_gain(struct mt76x02_dev *dev) dev->cal.rx.mcu_gain |= (lna_5g[1] & 0xff) << 16; dev->cal.rx.mcu_gain |= (lna_5g[2] & 0xff) << 24; - lna = mt76x02_get_lna_gain(dev, &lna_2g, lna_5g, chan); + val = mt76x02_eeprom_get(dev, MT_EE_NIC_CONF_1); + if (chan->band == NL80211_BAND_2GHZ) + use_lna = !(val & MT_EE_NIC_CONF_1_LNA_EXT_2G); + else + use_lna = !(val & MT_EE_NIC_CONF_1_LNA_EXT_5G); + + if (use_lna) + lna = mt76x02_get_lna_gain(dev, &lna_2g, lna_5g, chan); + dev->cal.rx.lna_gain = mt76x02_sign_extend(lna, 8); } EXPORT_SYMBOL_GPL(mt76x2_read_rx_gain); From e485a69d9b4433ad48673a1d31c705b09b3548c0 Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Thu, 14 Sep 2023 19:36:04 +0530 Subject: [PATCH 1985/2093] perf/x86/amd/core: Fix overflow reset on hotplug [ Upstream commit 23d2626b841c2adccdeb477665313c02dff02dc3 ] Kernels older than v5.19 do not support PerfMonV2 and the PMI handler does not clear the overflow bits of the PerfCntrGlobalStatus register. Because of this, loading a recent kernel using kexec from an older kernel can result in inconsistent register states on Zen 4 systems. The PMI handler of the new kernel gets confused and shows a warning when an overflow occurs because some of the overflow bits are set even if the corresponding counters are inactive. These are remnants from overflows that were handled by the older kernel. During CPU hotplug, the PerfCntrGlobalCtl and PerfCntrGlobalStatus registers should always be cleared for PerfMonV2-capable processors. However, a condition used for NB event constaints applicable only to older processors currently prevents this from happening. Move the reset sequence to an appropriate place and also clear the LBR Freeze bit. Fixes: 21d59e3e2c40 ("perf/x86/amd/core: Detect PerfMonV2 support") Signed-off-by: Sandipan Das Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/882a87511af40792ba69bb0e9026f19a2e71e8a3.1694696888.git.sandipan.das@amd.com Signed-off-by: Sasha Levin --- arch/x86/events/amd/core.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 6672a3f05fc6..bb9d99b45a45 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu) /* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */ wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0); - /* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */ - wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask); + /* + * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze + * and PerfCntrGLobalStatus.PerfCntrOvfl + */ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, + GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask); } static int amd_pmu_cpu_prepare(int cpu) @@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu) int i, nb_id; cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; + amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; - - amd_pmu_cpu_reset(cpu); } static void amd_pmu_cpu_dead(int cpu) @@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; + amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw->amd_nb = NULL; } - - amd_pmu_cpu_reset(cpu); } static inline void amd_pmu_set_global_ctl(u64 ctl) From 89192c6cbe0f91835eb9c0da6d0e8c4108d45ccc Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 22 Sep 2023 16:37:11 +0100 Subject: [PATCH 1986/2093] regmap: rbtree: Fix wrong register marked as in-cache when creating new node [ Upstream commit 7a795ac8d49e2433e1b97caf5e99129daf8e1b08 ] When regcache_rbtree_write() creates a new rbtree_node it was passing the wrong bit number to regcache_rbtree_set_register(). The bit number is the offset __in number of registers__, but in the case of creating a new block regcache_rbtree_write() was not dividing by the address stride to get the number of registers. Fix this by dividing by map->reg_stride. Compare with regcache_rbtree_read() where the bit is checked. This bug meant that the wrong register was marked as present. The register that was written to the cache could not be read from the cache because it was not marked as cached. But a nearby register could be marked as having a cached value even if it was never written to the cache. Signed-off-by: Richard Fitzgerald Fixes: 3f4ff561bc88 ("regmap: rbtree: Make cache_present bitmap per node") Link: https://lore.kernel.org/r/20230922153711.28103-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/base/regmap/regcache-rbtree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index ae6b8788d5f3..d65715b9e129 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -453,7 +453,8 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg, if (!rbnode) return -ENOMEM; regcache_rbtree_set_register(map, rbnode, - reg - rbnode->base_reg, value); + (reg - rbnode->base_reg) / map->reg_stride, + value); regcache_rbtree_insert(map, &rbtree_ctx->root, rbnode); rbtree_ctx->cached_rbnode = rbnode; } From 2f4e16e39e4f5e78248dd9e51276a83203950b36 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 19 Sep 2023 08:34:15 +0200 Subject: [PATCH 1987/2093] wifi: mac80211: fix potential key use-after-free [ Upstream commit 31db78a4923ef5e2008f2eed321811ca79e7f71b ] When ieee80211_key_link() is called by ieee80211_gtk_rekey_add() but returns 0 due to KRACK protection (identical key reinstall), ieee80211_gtk_rekey_add() will still return a pointer into the key, in a potential use-after-free. This normally doesn't happen since it's only called by iwlwifi in case of WoWLAN rekey offload which has its own KRACK protection, but still better to fix, do that by returning an error code and converting that to success on the cfg80211 boundary only, leaving the error for bad callers of ieee80211_gtk_rekey_add(). Reported-by: Dan Carpenter Fixes: fdf7cb4185b6 ("mac80211: accept key reinstall without changing anything") Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/cfg.c | 3 +++ net/mac80211/key.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index cf3453b532d6..0167413d5697 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -566,6 +566,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, } err = ieee80211_key_link(key, link, sta); + /* KRACK protection, shouldn't happen but just silently accept key */ + if (err == -EALREADY) + err = 0; out_unlock: mutex_unlock(&local->sta_mtx); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index e8f6c1e5eabf..23bb24243c6e 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -901,7 +901,7 @@ int ieee80211_key_link(struct ieee80211_key *key, */ if (ieee80211_key_identical(sdata, old_key, key)) { ieee80211_key_free_unused(key); - ret = 0; + ret = -EALREADY; goto out; } From 183e0f9da6aff45e1c5862ae14a46c0f32b5a6d0 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 14 Sep 2023 19:58:40 +0530 Subject: [PATCH 1988/2093] perf/x86/amd: Do not WARN() on every IRQ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 599522d9d2e19d6240e4312577f1c5f3ffca22f6 ] Zen 4 systems running buggy microcode can hit a WARN_ON() in the PMI handler, as shown below, several times while perf runs. A simple `perf top` run is enough to render the system unusable: WARNING: CPU: 18 PID: 20608 at arch/x86/events/amd/core.c:944 amd_pmu_v2_handle_irq+0x1be/0x2b0 This happens because the Performance Counter Global Status Register (PerfCntGlobalStatus) has one or more bits set which are considered reserved according to the "AMD64 Architecture Programmer’s Manual, Volume 2: System Programming, 24593": https://www.amd.com/system/files/TechDocs/24593.pdf To make this less intrusive, warn just once if any reserved bit is set and prompt the user to update the microcode. Also sanitize the value to what the code is handling, so that the overflow events continue to be handled for the number of counters that are known to be sane. Going forward, the following microcode patch levels are recommended for Zen 4 processors in order to avoid such issues with reserved bits: Family=0x19 Model=0x11 Stepping=0x01: Patch=0x0a10113e Family=0x19 Model=0x11 Stepping=0x02: Patch=0x0a10123e Family=0x19 Model=0xa0 Stepping=0x01: Patch=0x0aa00116 Family=0x19 Model=0xa0 Stepping=0x02: Patch=0x0aa00212 Commit f2eb058afc57 ("linux-firmware: Update AMD cpu microcode") from the linux-firmware tree has binaries that meet the minimum required patch levels. [ sandipan: - add message to prompt users to update microcode - rework commit message and call out required microcode levels ] Fixes: 7685665c390d ("perf/x86/amd/core: Add PerfMonV2 overflow handling") Reported-by: Jirka Hladky Signed-off-by: Breno Leitao Signed-off-by: Sandipan Das Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/all/3540f985652f41041e54ee82aa53e7dbd55739ae.1694696888.git.sandipan.das@amd.com/ Signed-off-by: Sasha Levin --- arch/x86/events/amd/core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index bb9d99b45a45..04f4b96dec6d 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -886,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) struct hw_perf_event *hwc; struct perf_event *event; int handled = 0, idx; - u64 status, mask; + u64 reserved, status, mask; bool pmu_enabled; /* @@ -911,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) status &= ~GLOBAL_STATUS_LBRS_FROZEN; } + reserved = status & ~amd_pmu_global_cntr_mask; + if (reserved) + pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n", + reserved); + + /* Clear any reserved bits set by buggy microcode */ + status &= amd_pmu_global_cntr_mask; + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; From fbac416e25efa7850e305dd3637e12b13f4f0c33 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Sat, 19 Aug 2023 16:14:43 +0800 Subject: [PATCH 1989/2093] iommu/mediatek: Fix share pgtable for iova over 4GB [ Upstream commit b07eba71a512eb196cbcc29765c29c8c29b11b59 ] In mt8192/mt8186, there is only one MM IOMMU that supports 16GB iova space, which is shared by display, vcodec and camera. These two SoC use one pgtable and have not the flag SHARE_PGTABLE, we should also keep share pgtable for this case. In mtk_iommu_domain_finalise, MM IOMMU always share pgtable, thus remove the flag SHARE_PGTABLE checking. Infra IOMMU always uses independent pgtable. Fixes: cf69ef46dbd9 ("iommu/mediatek: Fix two IOMMU share pagetable issue") Reported-by: Laura Nao Closes: https://lore.kernel.org/linux-iommu/20230818154156.314742-1-laura.nao@collabora.com/ Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Tested-by: Laura Nao Link: https://lore.kernel.org/r/20230819081443.8333-1-yong.wu@mediatek.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/mtk_iommu.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 9673cd60c84f..0ba2a63a9538 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -223,7 +223,7 @@ struct mtk_iommu_data { struct device *smicomm_dev; struct mtk_iommu_bank_data *bank; - struct mtk_iommu_domain *share_dom; /* For 2 HWs share pgtable */ + struct mtk_iommu_domain *share_dom; struct regmap *pericfg; struct mutex mutex; /* Protect m4u_group/m4u_dom above */ @@ -579,8 +579,8 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom, struct mtk_iommu_domain *share_dom = data->share_dom; const struct mtk_iommu_iova_region *region; - /* Always use share domain in sharing pgtable case */ - if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE) && share_dom) { + /* Share pgtable when 2 MM IOMMU share the pgtable or one IOMMU use multiple iova ranges */ + if (share_dom) { dom->iop = share_dom->iop; dom->cfg = share_dom->cfg; dom->domain.pgsize_bitmap = share_dom->cfg.pgsize_bitmap; @@ -613,8 +613,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom, /* Update our support page sizes bitmap */ dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap; - if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) - data->share_dom = dom; + data->share_dom = dom; update_iova_region: /* Update the iova region for this domain */ From 937ec4434e0a23e0c4d618d26cded802e15cde27 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Tue, 19 Sep 2023 00:50:26 +0200 Subject: [PATCH 1990/2093] regulator/core: regulator_register: set device->class earlier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8adb4e647a83cb5928c05dae95b010224aea0705 ] When fixing a memory leak in commit d3c731564e09 ("regulator: plug of_node leak in regulator_register()'s error path") it moved the device_initialize() call earlier, but did not move the `dev->class` initialization. The bug was spotted and fixed by reverting part of the commit (in commit 5f4b204b6b81 "regulator: core: fix kobject release warning and memory leak in regulator_register()") but introducing a different bug: now early error paths use `kfree(dev)` instead of `put_device()` for an already initialized `struct device`. Move the missing assignments to just after `device_initialize()`. Fixes: d3c731564e09 ("regulator: plug of_node leak in regulator_register()'s error path") Signed-off-by: Michał Mirosław Link: https://lore.kernel.org/r/b5b19cb458c40c9d02f3d5a7bd1ba7d97ba17279.1695077303.git.mirq-linux@rere.qmqm.pl Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 351f0fd225b1..f6a95f72af18 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5543,6 +5543,8 @@ regulator_register(struct device *dev, goto rinse; } device_initialize(&rdev->dev); + dev_set_drvdata(&rdev->dev, rdev); + rdev->dev.class = ®ulator_class; spin_lock_init(&rdev->err_lock); /* @@ -5604,11 +5606,9 @@ regulator_register(struct device *dev, rdev->supply_name = regulator_desc->supply_name; /* register with sysfs */ - rdev->dev.class = ®ulator_class; rdev->dev.parent = config->dev; dev_set_name(&rdev->dev, "regulator.%lu", (unsigned long) atomic_inc_return(®ulator_no)); - dev_set_drvdata(&rdev->dev, rdev); /* set regulator constraints */ if (init_data) From f23c35f0686c40078f6cd77b8899f9c87020775c Mon Sep 17 00:00:00 2001 From: Oleksandr Tymoshenko Date: Thu, 21 Sep 2023 06:45:05 +0000 Subject: [PATCH 1991/2093] ima: Finish deprecation of IMA_TRUSTED_KEYRING Kconfig [ Upstream commit be210c6d3597faf330cb9af33b9f1591d7b2a983 ] The removal of IMA_TRUSTED_KEYRING made IMA_LOAD_X509 and IMA_BLACKLIST_KEYRING unavailable because the latter two depend on the former. Since IMA_TRUSTED_KEYRING was deprecated in favor of INTEGRITY_TRUSTED_KEYRING use it as a dependency for the two Kconfigs affected by the deprecation. Fixes: 5087fd9e80e5 ("ima: Remove deprecated IMA_TRUSTED_KEYRING Kconfig") Signed-off-by: Oleksandr Tymoshenko Reviewed-by: Nayna Jain Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index c17660bf5f34..e6df7c930397 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -268,7 +268,7 @@ config IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY config IMA_BLACKLIST_KEYRING bool "Create IMA machine owner blacklist keyrings (EXPERIMENTAL)" depends on SYSTEM_TRUSTED_KEYRING - depends on IMA_TRUSTED_KEYRING + depends on INTEGRITY_TRUSTED_KEYRING default n help This option creates an IMA blacklist keyring, which contains all @@ -278,7 +278,7 @@ config IMA_BLACKLIST_KEYRING config IMA_LOAD_X509 bool "Load X509 certificate onto the '.ima' trusted keyring" - depends on IMA_TRUSTED_KEYRING + depends on INTEGRITY_TRUSTED_KEYRING default n help File signature verification is based on the public keys From 6c5d7f541693b894cf43e8ebae15aef77ac96993 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Mon, 18 Sep 2023 15:58:48 -0700 Subject: [PATCH 1992/2093] scsi: target: core: Fix deadlock due to recursive locking [ Upstream commit a154f5f643c6ecddd44847217a7a3845b4350003 ] The following call trace shows a deadlock issue due to recursive locking of mutex "device_mutex". First lock acquire is in target_for_each_device() and second in target_free_device(). PID: 148266 TASK: ffff8be21ffb5d00 CPU: 10 COMMAND: "iscsi_ttx" #0 [ffffa2bfc9ec3b18] __schedule at ffffffffa8060e7f #1 [ffffa2bfc9ec3ba0] schedule at ffffffffa8061224 #2 [ffffa2bfc9ec3bb8] schedule_preempt_disabled at ffffffffa80615ee #3 [ffffa2bfc9ec3bc8] __mutex_lock at ffffffffa8062fd7 #4 [ffffa2bfc9ec3c40] __mutex_lock_slowpath at ffffffffa80631d3 #5 [ffffa2bfc9ec3c50] mutex_lock at ffffffffa806320c #6 [ffffa2bfc9ec3c68] target_free_device at ffffffffc0935998 [target_core_mod] #7 [ffffa2bfc9ec3c90] target_core_dev_release at ffffffffc092f975 [target_core_mod] #8 [ffffa2bfc9ec3ca0] config_item_put at ffffffffa79d250f #9 [ffffa2bfc9ec3cd0] config_item_put at ffffffffa79d2583 #10 [ffffa2bfc9ec3ce0] target_devices_idr_iter at ffffffffc0933f3a [target_core_mod] #11 [ffffa2bfc9ec3d00] idr_for_each at ffffffffa803f6fc #12 [ffffa2bfc9ec3d60] target_for_each_device at ffffffffc0935670 [target_core_mod] #13 [ffffa2bfc9ec3d98] transport_deregister_session at ffffffffc0946408 [target_core_mod] #14 [ffffa2bfc9ec3dc8] iscsit_close_session at ffffffffc09a44a6 [iscsi_target_mod] #15 [ffffa2bfc9ec3df0] iscsit_close_connection at ffffffffc09a4a88 [iscsi_target_mod] #16 [ffffa2bfc9ec3df8] finish_task_switch at ffffffffa76e5d07 #17 [ffffa2bfc9ec3e78] iscsit_take_action_for_connection_exit at ffffffffc0991c23 [iscsi_target_mod] #18 [ffffa2bfc9ec3ea0] iscsi_target_tx_thread at ffffffffc09a403b [iscsi_target_mod] #19 [ffffa2bfc9ec3f08] kthread at ffffffffa76d8080 #20 [ffffa2bfc9ec3f50] ret_from_fork at ffffffffa8200364 Fixes: 36d4cb460bcb ("scsi: target: Avoid that EXTENDED COPY commands trigger lock inversion") Signed-off-by: Junxiao Bi Link: https://lore.kernel.org/r/20230918225848.66463-1-junxiao.bi@oracle.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/target_core_device.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index d21f88de197c..301fe376a120 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -883,7 +883,6 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb) EXPORT_SYMBOL(target_to_linux_sector); struct devices_idr_iter { - struct config_item *prev_item; int (*fn)(struct se_device *dev, void *data); void *data; }; @@ -893,11 +892,9 @@ static int target_devices_idr_iter(int id, void *p, void *data) { struct devices_idr_iter *iter = data; struct se_device *dev = p; + struct config_item *item; int ret; - config_item_put(iter->prev_item); - iter->prev_item = NULL; - /* * We add the device early to the idr, so it can be used * by backend modules during configuration. We do not want @@ -907,12 +904,13 @@ static int target_devices_idr_iter(int id, void *p, void *data) if (!target_dev_configured(dev)) return 0; - iter->prev_item = config_item_get_unless_zero(&dev->dev_group.cg_item); - if (!iter->prev_item) + item = config_item_get_unless_zero(&dev->dev_group.cg_item); + if (!item) return 0; mutex_unlock(&device_mutex); ret = iter->fn(dev, iter->data); + config_item_put(item); mutex_lock(&device_mutex); return ret; @@ -935,7 +933,6 @@ int target_for_each_device(int (*fn)(struct se_device *dev, void *data), mutex_lock(&device_mutex); ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter); mutex_unlock(&device_mutex); - config_item_put(iter.prev_item); return ret; } From 23acd1784eb5299e89c13616d42bb3090ddb0ccd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 27 Sep 2023 09:22:14 +0200 Subject: [PATCH 1993/2093] ima: rework CONFIG_IMA dependency block [ Upstream commit 91e326563ee34509c35267808a4b1b3ea3db62a8 ] Changing the direct dependencies of IMA_BLACKLIST_KEYRING and IMA_LOAD_X509 caused them to no longer depend on IMA, but a a configuration without IMA results in link failures: arm-linux-gnueabi-ld: security/integrity/iint.o: in function `integrity_load_keys': iint.c:(.init.text+0xd8): undefined reference to `ima_load_x509' aarch64-linux-ld: security/integrity/digsig_asymmetric.o: in function `asymmetric_verify': digsig_asymmetric.c:(.text+0x104): undefined reference to `ima_blacklist_keyring' Adding explicit dependencies on IMA would fix this, but a more reliable way to do this is to enclose the entire Kconfig file in an 'if IMA' block. This also allows removing the existing direct dependencies. Fixes: be210c6d3597f ("ima: Finish deprecation of IMA_TRUSTED_KEYRING Kconfig") Signed-off-by: Arnd Bergmann Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/Kconfig | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index e6df7c930397..6ef7bde55126 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -29,9 +29,11 @@ config IMA to learn more about IMA. If unsure, say N. +if IMA + config IMA_KEXEC bool "Enable carrying the IMA measurement list across a soft boot" - depends on IMA && TCG_TPM && HAVE_IMA_KEXEC + depends on TCG_TPM && HAVE_IMA_KEXEC default n help TPM PCRs are only reset on a hard reboot. In order to validate @@ -43,7 +45,6 @@ config IMA_KEXEC config IMA_MEASURE_PCR_IDX int - depends on IMA range 8 14 default 10 help @@ -53,7 +54,7 @@ config IMA_MEASURE_PCR_IDX config IMA_LSM_RULES bool - depends on IMA && AUDIT && (SECURITY_SELINUX || SECURITY_SMACK || SECURITY_APPARMOR) + depends on AUDIT && (SECURITY_SELINUX || SECURITY_SMACK || SECURITY_APPARMOR) default y help Disabling this option will disregard LSM based policy rules. @@ -61,7 +62,6 @@ config IMA_LSM_RULES choice prompt "Default template" default IMA_NG_TEMPLATE - depends on IMA help Select the default IMA measurement template. @@ -80,14 +80,12 @@ endchoice config IMA_DEFAULT_TEMPLATE string - depends on IMA default "ima-ng" if IMA_NG_TEMPLATE default "ima-sig" if IMA_SIG_TEMPLATE choice prompt "Default integrity hash algorithm" default IMA_DEFAULT_HASH_SHA1 - depends on IMA help Select the default hash algorithm used for the measurement list, integrity appraisal and audit log. The compiled default @@ -117,7 +115,6 @@ endchoice config IMA_DEFAULT_HASH string - depends on IMA default "sha1" if IMA_DEFAULT_HASH_SHA1 default "sha256" if IMA_DEFAULT_HASH_SHA256 default "sha512" if IMA_DEFAULT_HASH_SHA512 @@ -126,7 +123,6 @@ config IMA_DEFAULT_HASH config IMA_WRITE_POLICY bool "Enable multiple writes to the IMA policy" - depends on IMA default n help IMA policy can now be updated multiple times. The new rules get @@ -137,7 +133,6 @@ config IMA_WRITE_POLICY config IMA_READ_POLICY bool "Enable reading back the current IMA policy" - depends on IMA default y if IMA_WRITE_POLICY default n if !IMA_WRITE_POLICY help @@ -147,7 +142,6 @@ config IMA_READ_POLICY config IMA_APPRAISE bool "Appraise integrity measurements" - depends on IMA default n help This option enables local measurement integrity appraisal. @@ -303,7 +297,6 @@ config IMA_APPRAISE_SIGNED_INIT config IMA_MEASURE_ASYMMETRIC_KEYS bool - depends on IMA depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y default y @@ -322,7 +315,8 @@ config IMA_SECURE_AND_OR_TRUSTED_BOOT config IMA_DISABLE_HTABLE bool "Disable htable to allow measurement of duplicate records" - depends on IMA default n help This option disables htable to allow measurement of duplicate records. + +endif From 99fe9a12072956aaa1b1ab9aa93b3362c352664d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Sep 2023 19:05:50 -0400 Subject: [PATCH 1994/2093] NFSv4: Fix a nfs4_state_manager() race [ Upstream commit ed1cc05aa1f7fe8197d300e914afc28ab9818f89 ] If the NFS4CLNT_RUN_MANAGER flag got set just before we cleared NFS4CLNT_MANAGER_RUNNING, then we might have won the race against nfs4_schedule_state_manager(), and are responsible for handling the recovery situation. Fixes: aeabb3c96186 ("NFSv4: Fix a NFSv4 state manager deadlock") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4state.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ed789e0cb943..457b2b2f804a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2710,6 +2710,13 @@ static void nfs4_state_manager(struct nfs_client *clp) nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); + if (test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, + &clp->cl_state)) { + memflags = memalloc_nofs_save(); + continue; + } + if (!test_and_set_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state)) { if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) { nfs_client_return_marked_delegations(clp); From 46052a98854af5517384a53528c85943b0c983c7 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 25 Sep 2023 20:52:58 -0700 Subject: [PATCH 1995/2093] bpf: tcp_read_skb needs to pop skb regardless of seq [ Upstream commit 9b7177b1df64b8d7f85700027c324aadd6aded00 ] Before fix e5c6de5fa0258 tcp_read_skb() would increment the tp->copied-seq value. This (as described in the commit) would cause an error for apps because once that is incremented the application might believe there is no data to be read. Then some apps would stall or abort believing no data is available. However, the fix is incomplete because it introduces another issue in the skb dequeue. The loop does tcp_recv_skb() in a while loop to consume as many skbs as possible. The problem is the call is ... tcp_recv_skb(sk, seq, &offset) ... where 'seq' is: u32 seq = tp->copied_seq; Now we can hit a case where we've yet incremented copied_seq from BPF side, but then tcp_recv_skb() fails this test ... if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) ... so that instead of returning the skb we call tcp_eat_recv_skb() which frees the skb. This is because the routine believes the SKB has been collapsed per comment: /* This looks weird, but this can happen if TCP collapsing * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ This can't happen here we've unlinked the full SKB and orphaned it. Anyways it would confuse any BPF programs if the data were suddenly moved underneath it. To fix this situation do simpler operation and just skb_peek() the data of the queue followed by the unlink. It shouldn't need to check this condition and tcp_read_skb() reads entire skbs so there is no need to handle the 'offset!=0' case as we would see in tcp_read_sock(). Fixes: e5c6de5fa0258 ("bpf, sockmap: Incorrectly handling copied_seq") Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230926035300.135096-2-john.fastabend@gmail.com Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fab25d4f3a6f..96fdde6e42b1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1755,16 +1755,13 @@ EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; struct sk_buff *skb; int copied = 0; - u32 offset; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; @@ -1777,13 +1774,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) copied = used; break; } - seq += used; copied += used; - if (tcp_flags & TCPHDR_FIN) { - ++seq; + if (tcp_flags & TCPHDR_FIN) break; - } } return copied; } From c024db960301bff4c158f37d40c0d9d520e60c56 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 25 Sep 2023 20:52:59 -0700 Subject: [PATCH 1996/2093] bpf, sockmap: Do not inc copied_seq when PEEK flag set [ Upstream commit da9e915eaf5dadb1963b7738cdfa42ed55212445 ] When data is peek'd off the receive queue we shouldn't considered it copied from tcp_sock side. When we increment copied_seq this will confuse tcp_data_ready() because copied_seq can be arbitrarily increased. From application side it results in poll() operations not waking up when expected. Notice tcp stack without BPF recvmsg programs also does not increment copied_seq. We broke this when we moved copied_seq into recvmsg to only update when actual copy was happening. But, it wasn't working correctly either before because the tcp_data_ready() tried to use the copied_seq value to see if data was read by user yet. See fixes tags. Fixes: e5c6de5fa0258 ("bpf, sockmap: Incorrectly handling copied_seq") Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230926035300.135096-3-john.fastabend@gmail.com Signed-off-by: Sasha Levin --- net/ipv4/tcp_bpf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5f93918c063c..f53380fd89bc 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -217,6 +217,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int *addr_len) { struct tcp_sock *tcp = tcp_sk(sk); + int peek = flags & MSG_PEEK; u32 seq = tcp->copied_seq; struct sk_psock *psock; int copied = 0; @@ -306,7 +307,8 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, copied = -EAGAIN; } out: - WRITE_ONCE(tcp->copied_seq, seq); + if (!peek) + WRITE_ONCE(tcp->copied_seq, seq); tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); From b8f97e47b6fb84fcf2f5a22e725eefb6cf5070c2 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Wed, 20 Sep 2023 12:20:55 +0200 Subject: [PATCH 1997/2093] bpf, sockmap: Reject sk_msg egress redirects to non-TCP sockets [ Upstream commit b80e31baa43614e086a9d29dc1151932b1bd7fc5 ] With a SOCKMAP/SOCKHASH map and an sk_msg program user can steer messages sent from one TCP socket (s1) to actually egress from another TCP socket (s2): tcp_bpf_sendmsg(s1) // = sk_prot->sendmsg tcp_bpf_send_verdict(s1) // __SK_REDIRECT case tcp_bpf_sendmsg_redir(s2) tcp_bpf_push_locked(s2) tcp_bpf_push(s2) tcp_rate_check_app_limited(s2) // expects tcp_sock tcp_sendmsg_locked(s2) // ditto There is a hard-coded assumption in the call-chain, that the egress socket (s2) is a TCP socket. However in commit 122e6c79efe1 ("sock_map: Update sock type checks for UDP") we have enabled redirects to non-TCP sockets. This was done for the sake of BPF sk_skb programs. There was no indention to support sk_msg send-to-egress use case. As a result, attempts to send-to-egress through a non-TCP socket lead to a crash due to invalid downcast from sock to tcp_sock: BUG: kernel NULL pointer dereference, address: 000000000000002f ... Call Trace: ? show_regs+0x60/0x70 ? __die+0x1f/0x70 ? page_fault_oops+0x80/0x160 ? do_user_addr_fault+0x2d7/0x800 ? rcu_is_watching+0x11/0x50 ? exc_page_fault+0x70/0x1c0 ? asm_exc_page_fault+0x27/0x30 ? tcp_tso_segs+0x14/0xa0 tcp_write_xmit+0x67/0xce0 __tcp_push_pending_frames+0x32/0xf0 tcp_push+0x107/0x140 tcp_sendmsg_locked+0x99f/0xbb0 tcp_bpf_push+0x19d/0x3a0 tcp_bpf_sendmsg_redir+0x55/0xd0 tcp_bpf_send_verdict+0x407/0x550 tcp_bpf_sendmsg+0x1a1/0x390 inet_sendmsg+0x6a/0x70 sock_sendmsg+0x9d/0xc0 ? sockfd_lookup_light+0x12/0x80 __sys_sendto+0x10e/0x160 ? syscall_enter_from_user_mode+0x20/0x60 ? __this_cpu_preempt_check+0x13/0x20 ? lockdep_hardirqs_on+0x82/0x110 __x64_sys_sendto+0x1f/0x30 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reject selecting a non-TCP sockets as redirect target from a BPF sk_msg program to prevent the crash. When attempted, user will receive an EACCES error from send/sendto/sendmsg() syscall. Fixes: 122e6c79efe1 ("sock_map: Update sock type checks for UDP") Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20230920102055.42662-1-jakub@cloudflare.com Signed-off-by: Sasha Levin --- net/core/sock_map.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 96db7409baa1..38e01f82f2ef 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -670,6 +670,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; @@ -1262,6 +1264,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; From 8ef7f9acbe8e617992fa1942ac9405724b878972 Mon Sep 17 00:00:00 2001 From: Mauricio Faria de Oliveira Date: Thu, 28 Sep 2023 17:28:07 -0300 Subject: [PATCH 1998/2093] modpost: add missing else to the "of" check [ Upstream commit cbc3d00cf88fda95dbcafee3b38655b7a8f2650a ] Without this 'else' statement, an "usb" name goes into two handlers: the first/previous 'if' statement _AND_ the for-loop over 'devtable', but the latter is useless as it has no 'usb' device_id entry anyway. Tested with allmodconfig before/after patch; no changes to *.mod.c: git checkout v6.6-rc3 make -j$(nproc) allmodconfig make -j$(nproc) olddefconfig make -j$(nproc) find . -name '*.mod.c' | cpio -pd /tmp/before # apply patch make -j$(nproc) find . -name '*.mod.c' | cpio -pd /tmp/after diff -r /tmp/before/ /tmp/after/ # no difference Fixes: acbef7b76629 ("modpost: fix module autoloading for OF devices with generic compatible property") Signed-off-by: Mauricio Faria de Oliveira Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/mod/file2alias.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 80d973144fde..111d5464c12d 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1577,7 +1577,7 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, /* First handle the "special" cases */ if (sym_is(name, namelen, "usb")) do_usb_table(symval, sym->st_size, mod); - if (sym_is(name, namelen, "of")) + else if (sym_is(name, namelen, "of")) do_of_table(symval, sym->st_size, mod); else if (sym_is(name, namelen, "pnp")) do_pnp_device_entry(symval, sym->st_size, mod); From f82aac8162871e87027692b36af335a2375d4580 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Sep 2023 08:46:26 +0000 Subject: [PATCH 1999/2093] net: fix possible store tearing in neigh_periodic_work() [ Upstream commit 25563b581ba3a1f263a00e8c9a97f5e7363be6fd ] While looking at a related syzbot report involving neigh_periodic_work(), I found that I forgot to add an annotation when deleting an RCU protected item from a list. Readers use rcu_deference(*np), we need to use either rcu_assign_pointer() or WRITE_ONCE() on writer side to prevent store tearing. I use rcu_assign_pointer() to have lockdep support, this was the choice made in neigh_flush_dev(). Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/neighbour.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6c0f2149f2c7..8e726eb0548f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -988,7 +988,9 @@ static void neigh_periodic_work(struct work_struct *work) (state == NUD_FAILED || !time_in_range_open(jiffies, n->used, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); write_unlock(&n->lock); neigh_cleanup_and_release(n); From 8904d8848b31038b8ede40a0247a6682b0133f7a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 17 Feb 2023 12:55:14 -0800 Subject: [PATCH 2000/2093] bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup [ Upstream commit 31de4105f00d64570139bc5494a201b0bd57349f ] The bpf_fib_lookup() also looks up the neigh table. This was done before bpf_redirect_neigh() was added. In the use case that does not manage the neigh table and requires bpf_fib_lookup() to lookup a fib to decide if it needs to redirect or not, the bpf prog can depend only on using bpf_redirect_neigh() to lookup the neigh. It also keeps the neigh entries fresh and connected. This patch adds a bpf_fib_lookup flag, SKIP_NEIGH, to avoid the double neigh lookup when the bpf prog always call bpf_redirect_neigh() to do the neigh lookup. The params->smac output is skipped together when SKIP_NEIGH is set because bpf_redirect_neigh() will figure out the smac also. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230217205515.3583372-1-martin.lau@linux.dev Stable-dep-of: 5baa0433a15e ("neighbour: fix data-races around n->output") Signed-off-by: Sasha Levin --- include/uapi/linux/bpf.h | 6 ++++++ net/core/filter.c | 39 ++++++++++++++++++++++------------ tools/include/uapi/linux/bpf.h | 6 ++++++ 3 files changed, 38 insertions(+), 13 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 53bc48794719..92dbe89dafbf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3112,6 +3112,11 @@ union bpf_attr { * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6678,6 +6683,7 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), }; enum { diff --git a/net/core/filter.c b/net/core/filter.c index 9fd7c88b5db4..6ef62d84dcac 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5674,12 +5674,8 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) -static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, - const struct neighbour *neigh, - const struct net_device *dev, u32 mtu) +static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) { - memcpy(params->dmac, neigh->ha, ETH_ALEN); - memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; if (mtu) @@ -5790,21 +5786,29 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; - - neigh = __ipv4_neigh_lookup_noref(dev, - (__force u32)params->ipv4_dst); } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; - neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) + goto set_fwd_params; + + if (likely(nhc->nhc_gw_family != AF_INET6)) + neigh = __ipv4_neigh_lookup_noref(dev, + (__force u32)params->ipv4_dst); + else + neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst); + if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; + memcpy(params->dmac, neigh->ha, ETH_ALEN); + memcpy(params->smac, dev->dev_addr, ETH_ALEN); - return bpf_fib_set_fwd_params(params, neigh, dev, mtu); +set_fwd_params: + return bpf_fib_set_fwd_params(params, mtu); } #endif @@ -5912,24 +5916,33 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) + goto set_fwd_params; + /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; + memcpy(params->dmac, neigh->ha, ETH_ALEN); + memcpy(params->smac, dev->dev_addr, ETH_ALEN); - return bpf_fib_set_fwd_params(params, neigh, dev, mtu); +set_fwd_params: + return bpf_fib_set_fwd_params(params, mtu); } #endif +#define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ + BPF_FIB_LOOKUP_SKIP_NEIGH) + BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; - if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) + if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; switch (params->family) { @@ -5967,7 +5980,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, if (plen < sizeof(*params)) return -EINVAL; - if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) + if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; if (params->tot_len) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 53bc48794719..92dbe89dafbf 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3112,6 +3112,11 @@ union bpf_attr { * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6678,6 +6683,7 @@ struct bpf_raw_tracepoint_args { enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), }; enum { From 0526933c10058c69a5a85faaa3825116e68fd465 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Mar 2023 20:17:31 +0000 Subject: [PATCH 2001/2093] neighbour: annotate lockless accesses to n->nud_state [ Upstream commit b071af523579df7341cabf0f16fc661125e9a13f ] We have many lockless accesses to n->nud_state. Before adding another one in the following patch, add annotations to readers and writers. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Martin KaFai Lau Signed-off-by: Jakub Kicinski Stable-dep-of: 5baa0433a15e ("neighbour: fix data-races around n->output") Signed-off-by: Sasha Levin --- drivers/net/vxlan/vxlan_core.c | 4 ++-- include/net/neighbour.h | 2 +- net/bridge/br_arp_nd_proxy.c | 4 ++-- net/bridge/br_netfilter_hooks.c | 3 ++- net/core/filter.c | 4 ++-- net/core/neighbour.c | 28 ++++++++++++++-------------- net/ipv4/arp.c | 8 ++++---- net/ipv4/fib_semantics.c | 4 ++-- net/ipv4/nexthop.c | 4 ++-- net/ipv4/route.c | 2 +- net/ipv6/ip6_output.c | 2 +- net/ipv6/ndisc.c | 4 ++-- net/ipv6/route.c | 2 +- 13 files changed, 36 insertions(+), 35 deletions(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 0c3eb850fcb7..619dd71c9d75 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1910,7 +1910,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) struct vxlan_fdb *f; struct sk_buff *reply; - if (!(n->nud_state & NUD_CONNECTED)) { + if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } @@ -2074,7 +2074,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) struct vxlan_fdb *f; struct sk_buff *reply; - if (!(n->nud_state & NUD_CONNECTED)) { + if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 794e45981891..cd30aac9ec83 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -464,7 +464,7 @@ static __always_inline int neigh_event_send_probe(struct neighbour *neigh, if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); - if (!(neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) + if (!(READ_ONCE(neigh->nud_state) & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) return __neigh_event_send(neigh, skb, immediate_ok); return 0; } diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index e5e48c6e35d7..b45c00c01dea 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -192,7 +192,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, if (n) { struct net_bridge_fdb_entry *f; - if (!(n->nud_state & NUD_VALID)) { + if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_release(n); return; } @@ -452,7 +452,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, if (n) { struct net_bridge_fdb_entry *f; - if (!(n->nud_state & NUD_VALID)) { + if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_release(n); return; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 812bd7e1750b..442198cb8390 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -277,7 +277,8 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; - if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) { + if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && + READ_ONCE(neigh->hh.hh_len)) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; ret = br_handle_frame_finish(net, sk, skb); diff --git a/net/core/filter.c b/net/core/filter.c index 6ef62d84dcac..d32c6bd4d579 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5802,7 +5802,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, else neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst); - if (!neigh || !(neigh->nud_state & NUD_VALID)) + if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); @@ -5923,7 +5923,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); - if (!neigh || !(neigh->nud_state & NUD_VALID)) + if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e726eb0548f..51393079487a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1095,13 +1095,13 @@ static void neigh_timer_handler(struct timer_list *t) neigh->used + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is delayed\n", neigh); - neigh->nud_state = NUD_DELAY; + WRITE_ONCE(neigh->nud_state, NUD_DELAY); neigh->updated = jiffies; neigh_suspect(neigh); next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { neigh_dbg(2, "neigh %p is suspected\n", neigh); - neigh->nud_state = NUD_STALE; + WRITE_ONCE(neigh->nud_state, NUD_STALE); neigh->updated = jiffies; neigh_suspect(neigh); notify = 1; @@ -1111,14 +1111,14 @@ static void neigh_timer_handler(struct timer_list *t) neigh->confirmed + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is now reachable\n", neigh); - neigh->nud_state = NUD_REACHABLE; + WRITE_ONCE(neigh->nud_state, NUD_REACHABLE); neigh->updated = jiffies; neigh_connect(neigh); notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { neigh_dbg(2, "neigh %p is probed\n", neigh); - neigh->nud_state = NUD_PROBE; + WRITE_ONCE(neigh->nud_state, NUD_PROBE); neigh->updated = jiffies; atomic_set(&neigh->probes, 0); notify = 1; @@ -1132,7 +1132,7 @@ static void neigh_timer_handler(struct timer_list *t) if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { - neigh->nud_state = NUD_FAILED; + WRITE_ONCE(neigh->nud_state, NUD_FAILED); notify = 1; neigh_invalidate(neigh); goto out; @@ -1181,7 +1181,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh_del_timer(neigh); - neigh->nud_state = NUD_INCOMPLETE; + WRITE_ONCE(neigh->nud_state, NUD_INCOMPLETE); neigh->updated = now; if (!immediate_ok) { next = now + 1; @@ -1193,7 +1193,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, } neigh_add_timer(neigh, next); } else { - neigh->nud_state = NUD_FAILED; + WRITE_ONCE(neigh->nud_state, NUD_FAILED); neigh->updated = jiffies; write_unlock_bh(&neigh->lock); @@ -1203,7 +1203,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, } else if (neigh->nud_state & NUD_STALE) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh_del_timer(neigh); - neigh->nud_state = NUD_DELAY; + WRITE_ONCE(neigh->nud_state, NUD_DELAY); neigh->updated = jiffies; neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); @@ -1315,7 +1315,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, neigh_update_flags(neigh, flags, ¬ify, &gc_update, &managed_update); if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) { new = old & ~NUD_PERMANENT; - neigh->nud_state = new; + WRITE_ONCE(neigh->nud_state, new); err = 0; goto out; } @@ -1324,7 +1324,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, neigh_del_timer(neigh); if (old & NUD_CONNECTED) neigh_suspect(neigh); - neigh->nud_state = new; + WRITE_ONCE(neigh->nud_state, new); err = 0; notify = old & NUD_VALID; if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && @@ -1403,7 +1403,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, ((new & NUD_REACHABLE) ? neigh->parms->reachable_time : 0))); - neigh->nud_state = new; + WRITE_ONCE(neigh->nud_state, new); notify = 1; } @@ -1490,7 +1490,7 @@ void __neigh_set_probe_once(struct neighbour *neigh) neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; - neigh->nud_state = NUD_INCOMPLETE; + WRITE_ONCE(neigh->nud_state, NUD_INCOMPLETE); atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), @@ -3190,7 +3190,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) } if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) break; - if (n->nud_state & ~NUD_NOARP) + if (READ_ONCE(n->nud_state) & ~NUD_NOARP) break; next: n = rcu_dereference_bh(n->next); @@ -3232,7 +3232,7 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) break; - if (n->nud_state & ~NUD_NOARP) + if (READ_ONCE(n->nud_state) & ~NUD_NOARP) break; next: n = rcu_dereference_bh(n->next); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 4f7237661afb..9456f5bb35e5 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -375,7 +375,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { - if (!(neigh->nud_state & NUD_VALID)) + if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); neigh_ha_snapshot(dst_ha, neigh, dev); dst_hw = dst_ha; @@ -1123,7 +1123,7 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) neigh = neigh_lookup(&arp_tbl, &ip, dev); if (neigh) { - if (!(neigh->nud_state & NUD_NOARP)) { + if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { read_lock_bh(&neigh->lock); memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); r->arp_flags = arp_state_to_flags(neigh); @@ -1144,12 +1144,12 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force) struct neigh_table *tbl = &arp_tbl; if (neigh) { - if ((neigh->nud_state & NUD_VALID) && !force) { + if ((READ_ONCE(neigh->nud_state) & NUD_VALID) && !force) { neigh_release(neigh); return 0; } - if (neigh->nud_state & ~NUD_NOARP) + if (READ_ONCE(neigh->nud_state) & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3b6e6bc80dc1..158ad3c2662f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -564,7 +564,7 @@ static int fib_detect_death(struct fib_info *fi, int order, n = NULL; if (n) { - state = n->nud_state; + state = READ_ONCE(n->nud_state); neigh_release(n); } else { return 0; @@ -2205,7 +2205,7 @@ static bool fib_good_nh(const struct fib_nh *nh) else n = NULL; if (n) - state = n->nud_state; + state = READ_ONCE(n->nud_state); rcu_read_unlock_bh(); } diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 9cc287902454..d699a41c9d95 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1128,7 +1128,7 @@ static bool ipv6_good_nh(const struct fib6_nh *nh) n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); if (n) - state = n->nud_state; + state = READ_ONCE(n->nud_state); rcu_read_unlock_bh(); @@ -1145,7 +1145,7 @@ static bool ipv4_good_nh(const struct fib_nh *nh) n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); if (n) - state = n->nud_state; + state = READ_ONCE(n->nud_state); rcu_read_unlock_bh(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 84a0a71a6f4e..8d838b004690 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -784,7 +784,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { - if (!(n->nud_state & NUD_VALID)) { + if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 34192f7a166f..5bf15a530fe7 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1153,7 +1153,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); - err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; + err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); if (err) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 6cb2d6a536a8..8c5a99fe6803 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -746,7 +746,7 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { - if (!(neigh->nud_state & NUD_VALID)) { + if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) { ND_PRINTK(1, dbg, "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); @@ -1092,7 +1092,7 @@ static void ndisc_recv_na(struct sk_buff *skb) u8 old_flags = neigh->flags; struct net *net = dev_net(dev); - if (neigh->nud_state & NUD_FAILED) + if (READ_ONCE(neigh->nud_state) & NUD_FAILED) goto out; /* diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 93957b20fccc..4f103e7c4ea2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -641,7 +641,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) idev = __in6_dev_get(dev); neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { - if (neigh->nud_state & NUD_VALID) + if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; write_lock(&neigh->lock); From 2b76aad68b308b7ab50fe075a32b16195fb12f1c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Mar 2023 04:01:14 +0000 Subject: [PATCH 2002/2093] neighbour: switch to standard rcu, instead of rcu_bh [ Upstream commit 09eed1192cec1755967f2af8394207acdde579a1 ] rcu_bh is no longer a win, especially for objects freed with standard call_rcu(). Switch neighbour code to no longer disable BH when not necessary. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski Stable-dep-of: 5baa0433a15e ("neighbour: fix data-races around n->output") Signed-off-by: Sasha Levin --- include/net/arp.h | 8 ++--- include/net/ndisc.h | 12 ++++---- include/net/neighbour.h | 6 ++-- include/net/nexthop.h | 6 ++-- net/core/filter.c | 16 ++++++---- net/core/neighbour.c | 64 ++++++++++++++++++++-------------------- net/ipv4/fib_semantics.c | 4 +-- net/ipv4/ip_output.c | 6 ++-- net/ipv4/nexthop.c | 8 ++--- net/ipv4/route.c | 4 +-- net/ipv6/addrconf.c | 14 ++++----- net/ipv6/ip6_output.c | 10 +++---- net/ipv6/route.c | 12 ++++---- 13 files changed, 87 insertions(+), 83 deletions(-) diff --git a/include/net/arp.h b/include/net/arp.h index d7ef4ec71dfe..e8747e0713c7 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -38,11 +38,11 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 { struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; - rcu_read_unlock_bh(); + rcu_read_unlock(); return n; } @@ -51,10 +51,10 @@ static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) { struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv4_neigh_lookup_noref(dev, key); neigh_confirm(n); - rcu_read_unlock_bh(); + rcu_read_unlock(); } void arp_init(void); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index da7eec8669ec..325a6fb65c89 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -395,11 +395,11 @@ static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, cons { struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; - rcu_read_unlock_bh(); + rcu_read_unlock(); return n; } @@ -409,10 +409,10 @@ static inline void __ipv6_confirm_neigh(struct net_device *dev, { struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv6_neigh_lookup_noref(dev, pkey); neigh_confirm(n); - rcu_read_unlock_bh(); + rcu_read_unlock(); } static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, @@ -420,10 +420,10 @@ static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, { struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv6_neigh_lookup_noref_stub(dev, pkey); neigh_confirm(n); - rcu_read_unlock_bh(); + rcu_read_unlock(); } /* uses ipv6_stub and is meant for use outside of IPv6 core */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index cd30aac9ec83..f6a8ecc6b1fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -299,14 +299,14 @@ static inline struct neighbour *___neigh_lookup_noref( const void *pkey, struct net_device *dev) { - struct neigh_hash_table *nht = rcu_dereference_bh(tbl->nht); + struct neigh_hash_table *nht = rcu_dereference(tbl->nht); struct neighbour *n; u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + for (n = rcu_dereference(nht->hash_buckets[hash_val]); n != NULL; - n = rcu_dereference_bh(n->next)) { + n = rcu_dereference(n->next)) { if (n->dev == dev && key_eq(n, pkey)) return n; } diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 28085b995ddc..9fa291a04621 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -498,7 +498,7 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) } /* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock_bh(), or RTNL. + * Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) { @@ -507,13 +507,13 @@ static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) if (nh->is_group) { struct nh_group *nh_grp; - nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp); + nh_grp = rcu_dereference_rtnl(nh->nh_grp); nh = nexthop_mpath_select(nh_grp, 0); if (!nh) return NULL; } - nhi = rcu_dereference_bh_rtnl(nh->nh_info); + nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET6) return &nhi->fib6_nh; diff --git a/net/core/filter.c b/net/core/filter.c index d32c6bd4d579..adc327f4af1e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2197,7 +2197,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, return -ENOMEM; } - rcu_read_lock_bh(); + rcu_read_lock(); if (!nh) { dst = skb_dst(skb); nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst), @@ -2210,10 +2210,12 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, int ret; sock_confirm_neigh(skb, neigh); + local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, false); dev_xmit_recursion_dec(); - rcu_read_unlock_bh(); + local_bh_enable(); + rcu_read_unlock(); return ret; } rcu_read_unlock_bh(); @@ -2295,7 +2297,7 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, return -ENOMEM; } - rcu_read_lock_bh(); + rcu_read_lock(); if (!nh) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = container_of(dst, struct rtable, dst); @@ -2307,7 +2309,7 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, } else if (nh->nh_family == AF_INET) { neigh = ip_neigh_gw4(dev, nh->ipv4_nh); } else { - rcu_read_unlock_bh(); + rcu_read_unlock(); goto out_drop; } @@ -2315,13 +2317,15 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, int ret; sock_confirm_neigh(skb, neigh); + local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, is_v6gw); dev_xmit_recursion_dec(); - rcu_read_unlock_bh(); + local_bh_enable(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); out_drop: kfree_skb(skb); return -ENETDOWN; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 51393079487a..bafd72e5f588 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -614,7 +614,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, NEIGH_CACHE_STAT_INC(tbl, lookups); - rcu_read_lock_bh(); + rcu_read_lock(); n = __neigh_lookup_noref(tbl, pkey, dev); if (n) { if (!refcount_inc_not_zero(&n->refcnt)) @@ -622,7 +622,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, NEIGH_CACHE_STAT_INC(tbl, hits); } - rcu_read_unlock_bh(); + rcu_read_unlock(); return n; } EXPORT_SYMBOL(neigh_lookup); @@ -2176,11 +2176,11 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; - rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); + rcu_read_lock(); + nht = rcu_dereference(tbl->nht); ndc.ndtc_hash_rnd = nht->hash_rnd[0]; ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); - rcu_read_unlock_bh(); + rcu_read_unlock(); if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) goto nla_put_failure; @@ -2695,15 +2695,15 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; - rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); + rcu_read_lock(); + nht = rcu_dereference(tbl->nht); for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; - for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; + for (n = rcu_dereference(nht->hash_buckets[h]), idx = 0; n != NULL; - n = rcu_dereference_bh(n->next)) { + n = rcu_dereference(n->next)) { if (idx < s_idx || !net_eq(dev_net(n->dev), net)) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || @@ -2722,7 +2722,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, } rc = skb->len; out: - rcu_read_unlock_bh(); + rcu_read_unlock(); cb->args[1] = h; cb->args[2] = idx; return rc; @@ -3067,20 +3067,20 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void int chain; struct neigh_hash_table *nht; - rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); + rcu_read_lock(); + nht = rcu_dereference(tbl->nht); - read_lock(&tbl->lock); /* avoid resizes */ + read_lock_bh(&tbl->lock); /* avoid resizes */ for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; - for (n = rcu_dereference_bh(nht->hash_buckets[chain]); + for (n = rcu_dereference(nht->hash_buckets[chain]); n != NULL; - n = rcu_dereference_bh(n->next)) + n = rcu_dereference(n->next)) cb(n, cookie); } - read_unlock(&tbl->lock); - rcu_read_unlock_bh(); + read_unlock_bh(&tbl->lock); + rcu_read_unlock(); } EXPORT_SYMBOL(neigh_for_each); @@ -3130,7 +3130,7 @@ int neigh_xmit(int index, struct net_device *dev, tbl = neigh_tables[index]; if (!tbl) goto out; - rcu_read_lock_bh(); + rcu_read_lock(); if (index == NEIGH_ARP_TABLE) { u32 key = *((u32 *)addr); @@ -3142,11 +3142,11 @@ int neigh_xmit(int index, struct net_device *dev, neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); if (IS_ERR(neigh)) { - rcu_read_unlock_bh(); + rcu_read_unlock(); goto out_kfree_skb; } err = neigh->output(neigh, skb); - rcu_read_unlock_bh(); + rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { err = dev_hard_header(skb, dev, ntohs(skb->protocol), @@ -3175,7 +3175,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) state->flags &= ~NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { - n = rcu_dereference_bh(nht->hash_buckets[bucket]); + n = rcu_dereference(nht->hash_buckets[bucket]); while (n) { if (!net_eq(dev_net(n->dev), net)) @@ -3193,7 +3193,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) if (READ_ONCE(n->nud_state) & ~NUD_NOARP) break; next: - n = rcu_dereference_bh(n->next); + n = rcu_dereference(n->next); } if (n) @@ -3217,7 +3217,7 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (v) return n; } - n = rcu_dereference_bh(n->next); + n = rcu_dereference(n->next); while (1) { while (n) { @@ -3235,7 +3235,7 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (READ_ONCE(n->nud_state) & ~NUD_NOARP) break; next: - n = rcu_dereference_bh(n->next); + n = rcu_dereference(n->next); } if (n) @@ -3244,7 +3244,7 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (++state->bucket >= (1 << nht->hash_shift)) break; - n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); + n = rcu_dereference(nht->hash_buckets[state->bucket]); } if (n && pos) @@ -3346,7 +3346,7 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) __acquires(tbl->lock) - __acquires(rcu_bh) + __acquires(rcu) { struct neigh_seq_state *state = seq->private; @@ -3354,9 +3354,9 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl state->bucket = 0; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); - rcu_read_lock_bh(); - state->nht = rcu_dereference_bh(tbl->nht); - read_lock(&tbl->lock); + rcu_read_lock(); + state->nht = rcu_dereference(tbl->nht); + read_lock_bh(&tbl->lock); return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } @@ -3391,13 +3391,13 @@ EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) __releases(tbl->lock) - __releases(rcu_bh) + __releases(rcu) { struct neigh_seq_state *state = seq->private; struct neigh_table *tbl = state->tbl; - read_unlock(&tbl->lock); - rcu_read_unlock_bh(); + read_unlock_bh(&tbl->lock); + rcu_read_unlock(); } EXPORT_SYMBOL(neigh_seq_stop); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 158ad3c2662f..eafa4a033515 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2194,7 +2194,7 @@ static bool fib_good_nh(const struct fib_nh *nh) if (nh->fib_nh_scope == RT_SCOPE_LINK) { struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); if (likely(nh->fib_nh_gw_family == AF_INET)) n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, @@ -2207,7 +2207,7 @@ static bool fib_good_nh(const struct fib_nh *nh) if (n) state = READ_ONCE(n->nud_state); - rcu_read_unlock_bh(); + rcu_read_unlock(); } return !!(state & NUD_VALID); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 66908ce2dd11..493c679ea54f 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -218,7 +218,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s return res; } - rcu_read_lock_bh(); + rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; @@ -226,10 +226,10 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); - rcu_read_unlock_bh(); + rcu_read_unlock(); return res; } - rcu_read_unlock_bh(); + rcu_read_unlock(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d699a41c9d95..be5498f5dd31 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1124,13 +1124,13 @@ static bool ipv6_good_nh(const struct fib6_nh *nh) int state = NUD_REACHABLE; struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); if (n) state = READ_ONCE(n->nud_state); - rcu_read_unlock_bh(); + rcu_read_unlock(); return !!(state & NUD_VALID); } @@ -1140,14 +1140,14 @@ static bool ipv4_good_nh(const struct fib_nh *nh) int state = NUD_REACHABLE; struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); if (n) state = READ_ONCE(n->nud_state); - rcu_read_unlock_bh(); + rcu_read_unlock(); return !!(state & NUD_VALID); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8d838b004690..608bd9f8dbc8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -408,7 +408,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct net_device *dev = dst->dev; struct neighbour *n; - rcu_read_lock_bh(); + rcu_read_lock(); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); @@ -424,7 +424,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; - rcu_read_unlock_bh(); + rcu_read_unlock(); return n; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 96f4351b55a6..c63ccd39fc55 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1035,7 +1035,7 @@ static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) unsigned int hash = inet6_addr_hash(net, &ifa->addr); int err = 0; - spin_lock(&net->ipv6.addrconf_hash_lock); + spin_lock_bh(&net->ipv6.addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(net, &ifa->addr, dev, hash)) { @@ -1045,7 +1045,7 @@ static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) hlist_add_head_rcu(&ifa->addr_lst, &net->ipv6.inet6_addr_lst[hash]); } - spin_unlock(&net->ipv6.addrconf_hash_lock); + spin_unlock_bh(&net->ipv6.addrconf_hash_lock); return err; } @@ -1140,15 +1140,15 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, /* For caller */ refcount_set(&ifa->refcnt, 1); - rcu_read_lock_bh(); + rcu_read_lock(); err = ipv6_add_addr_hash(idev->dev, ifa); if (err < 0) { - rcu_read_unlock_bh(); + rcu_read_unlock(); goto out; } - write_lock(&idev->lock); + write_lock_bh(&idev->lock); /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); @@ -1159,9 +1159,9 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, } in6_ifa_hold(ifa); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); - rcu_read_unlock_bh(); + rcu_read_unlock(); inet6addr_notifier_call_chain(NETDEV_UP, ifa); out: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5bf15a530fe7..ce2c5e728745 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -116,7 +116,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * return res; } - rcu_read_lock_bh(); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); @@ -124,7 +124,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dev, false); if (IS_ERR(neigh)) { - rcu_read_unlock_bh(); + rcu_read_unlock(); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return -EINVAL; @@ -132,7 +132,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * } sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } @@ -1150,11 +1150,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * dst entry of the nexthop router */ rt = (struct rt6_info *) *dst; - rcu_read_lock_bh(); + rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0; - rcu_read_unlock_bh(); + rcu_read_unlock(); if (err) { struct inet6_ifaddr *ifp; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4f103e7c4ea2..0a9f854bfa50 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -636,7 +636,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; - rcu_read_lock_bh(); + rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); @@ -644,7 +644,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; - write_lock(&neigh->lock); + write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + idev->cnf.rtr_probe_interval)) { @@ -652,7 +652,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) if (work) __neigh_set_probe_once(neigh); } - write_unlock(&neigh->lock); + write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); @@ -670,7 +670,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) } out: - rcu_read_unlock_bh(); + rcu_read_unlock(); } #else static inline void rt6_probe(struct fib6_nh *fib6_nh) @@ -686,7 +686,7 @@ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; struct neighbour *neigh; - rcu_read_lock_bh(); + rcu_read_lock(); neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { @@ -704,7 +704,7 @@ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } From a8ed1b2e1674e2fb91d3197666fdcefc45993dce Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Sep 2023 09:27:13 +0000 Subject: [PATCH 2003/2093] neighbour: fix data-races around n->output [ Upstream commit 5baa0433a15eadd729625004c37463acb982eca7 ] n->output field can be read locklessly, while a writer might change the pointer concurrently. Add missing annotations to prevent load-store tearing. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/neighbour.h | 2 +- net/bridge/br_netfilter_hooks.c | 2 +- net/core/neighbour.c | 10 +++++----- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index f6a8ecc6b1fa..ccc4a0f8b4ad 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -541,7 +541,7 @@ static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); - return n->output(n, skb); + return READ_ONCE(n->output)(n, skb); } static inline struct neighbour * diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 442198cb8390..01d690d9fe5f 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -294,7 +294,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ /* tell br_dev_xmit to continue with forwarding */ nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ - ret = neigh->output(neigh, skb); + ret = READ_ONCE(neigh->output)(neigh, skb); } neigh_release(neigh); return ret; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index bafd72e5f588..b20c9768d9f3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -410,7 +410,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, */ __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; - n->output = neigh_blackhole; + WRITE_ONCE(n->output, neigh_blackhole); if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else @@ -920,7 +920,7 @@ static void neigh_suspect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is suspected\n", neigh); - neigh->output = neigh->ops->output; + WRITE_ONCE(neigh->output, neigh->ops->output); } /* Neighbour state is OK; @@ -932,7 +932,7 @@ static void neigh_connect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is connected\n", neigh); - neigh->output = neigh->ops->connected_output; + WRITE_ONCE(neigh->output, neigh->ops->connected_output); } static void neigh_periodic_work(struct work_struct *work) @@ -1449,7 +1449,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, if (n2) n1 = n2; } - n1->output(n1, skb); + READ_ONCE(n1->output)(n1, skb); if (n2) neigh_release(n2); rcu_read_unlock(); @@ -3145,7 +3145,7 @@ int neigh_xmit(int index, struct net_device *dev, rcu_read_unlock(); goto out_kfree_skb; } - err = neigh->output(neigh, skb); + err = READ_ONCE(neigh->output)(neigh, skb); rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { From f6a7182179c0ed788e3755ee2ed18c888ddcc33f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 21 Sep 2023 11:41:19 +0100 Subject: [PATCH 2004/2093] ipv4, ipv6: Fix handling of transhdrlen in __ip{,6}_append_data() [ Upstream commit 9d4c75800f61e5d75c1659ba201b6c0c7ead3070 ] Including the transhdrlen in length is a problem when the packet is partially filled (e.g. something like send(MSG_MORE) happened previously) when appending to an IPv4 or IPv6 packet as we don't want to repeat the transport header or account for it twice. This can happen under some circumstances, such as splicing into an L2TP socket. The symptom observed is a warning in __ip6_append_data(): WARNING: CPU: 1 PID: 5042 at net/ipv6/ip6_output.c:1800 __ip6_append_data.isra.0+0x1be8/0x47f0 net/ipv6/ip6_output.c:1800 that occurs when MSG_SPLICE_PAGES is used to append more data to an already partially occupied skbuff. The warning occurs when 'copy' is larger than the amount of data in the message iterator. This is because the requested length includes the transport header length when it shouldn't. This can be triggered by, for example: sfd = socket(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP); bind(sfd, ...); // ::1 connect(sfd, ...); // ::1 port 7 send(sfd, buffer, 4100, MSG_MORE); sendfile(sfd, dfd, NULL, 1024); Fix this by only adding transhdrlen into the length if the write queue is empty in l2tp_ip6_sendmsg(), analogously to how UDP does things. l2tp_ip_sendmsg() looks like it won't suffer from this problem as it builds the UDP packet itself. Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6") Reported-by: syzbot+62cbf263225ae13ff153@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/0000000000001c12b30605378ce8@google.com/ Suggested-by: Willem de Bruijn Signed-off-by: David Howells cc: Eric Dumazet cc: Willem de Bruijn cc: "David S. Miller" cc: David Ahern cc: Paolo Abeni cc: Jakub Kicinski cc: netdev@vger.kernel.org cc: bpf@vger.kernel.org cc: syzkaller-bugs@googlegroups.com Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/l2tp/l2tp_ip6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index bce4132b0a5c..314ec3a51e8d 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -510,7 +510,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ if (len > INT_MAX - transhdrlen) return -EMSGSIZE; - ulen = len + transhdrlen; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) @@ -631,6 +630,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); + ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, From 6a91ec7cfd0e242d7d7537206985541e58aa8bf4 Mon Sep 17 00:00:00 2001 From: Dinghao Liu Date: Fri, 22 Sep 2023 17:40:44 +0800 Subject: [PATCH 2005/2093] ptp: ocp: Fix error handling in ptp_ocp_device_init [ Upstream commit caa0578c1d487d39e4bb947a1b4965417053b409 ] When device_add() fails, ptp_ocp_dev_release() will be called after put_device(). Therefore, it seems that the ptp_ocp_dev_release() before put_device() is redundant. Fixes: 773bda964921 ("ptp: ocp: Expose various resources on the timecard.") Signed-off-by: Dinghao Liu Reviewed-by: Vadim Feodrenko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/ptp/ptp_ocp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index a48d9b7d2921..8fee9b330b61 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -3532,7 +3532,6 @@ ptp_ocp_device_init(struct ptp_ocp *bp, struct pci_dev *pdev) return 0; out: - ptp_ocp_dev_release(&bp->dev); put_device(&bp->dev); return err; } From a003d4994088fa20f18bd0f6e81083602744450e Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Fri, 22 Sep 2023 09:47:41 -0300 Subject: [PATCH 2006/2093] net: dsa: mv88e6xxx: Avoid EEPROM timeout when EEPROM is absent [ Upstream commit 6ccf50d4d4741e064ba35511a95402c63bbe21a8 ] Since commit 23d775f12dcd ("net: dsa: mv88e6xxx: Wait for EEPROM done before HW reset") the following error is seen on a imx8mn board with a 88E6320 switch: mv88e6085 30be0000.ethernet-1:00: Timeout waiting for EEPROM done This board does not have an EEPROM attached to the switch though. This problem is well explained by Andrew Lunn: "If there is an EEPROM, and the EEPROM contains a lot of data, it could be that when we perform a hardware reset towards the end of probe, it interrupts an I2C bus transaction, leaving the I2C bus in a bad state, and future reads of the EEPROM do not work. The work around for this was to poll the EEInt status and wait for it to go true before performing the hardware reset. However, we have discovered that for some boards which do not have an EEPROM, EEInt never indicates complete. As a result, mv88e6xxx_g1_wait_eeprom_done() spins for a second and then prints a warning. We probably need a different solution than calling mv88e6xxx_g1_wait_eeprom_done(). The datasheet for 6352 documents the EEPROM Command register: bit 15 is: EEPROM Unit Busy. This bit must be set to a one to start an EEPROM operation (see EEOp below). Only one EEPROM operation can be executing at one time so this bit must be zero before setting it to a one. When the requested EEPROM operation completes this bit will automatically be cleared to a zero. The transition of this bit from a one to a zero can be used to generate an interrupt (the EEInt in Global 1, offset 0x00). and more interesting is bit 11: Register Loader Running. This bit is set to one whenever the register loader is busy executing instructions contained in the EEPROM." Change to using mv88e6xxx_g2_eeprom_wait() to fix the timeout error when the EEPROM chip is not present. Fixes: 23d775f12dcd ("net: dsa: mv88e6xxx: Wait for EEPROM done before HW reset") Suggested-by: Andrew Lunn Signed-off-by: Fabio Estevam Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 6 ++++-- drivers/net/dsa/mv88e6xxx/global1.c | 31 ----------------------------- drivers/net/dsa/mv88e6xxx/global1.h | 1 - drivers/net/dsa/mv88e6xxx/global2.c | 2 +- drivers/net/dsa/mv88e6xxx/global2.h | 1 + 5 files changed, 6 insertions(+), 35 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index a73008b9e0b3..ba906dfab055 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3012,14 +3012,16 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) * from the wrong location resulting in the switch booting * to wrong mode and inoperable. */ - mv88e6xxx_g1_wait_eeprom_done(chip); + if (chip->info->ops->get_eeprom) + mv88e6xxx_g2_eeprom_wait(chip); gpiod_set_value_cansleep(gpiod, 1); usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); usleep_range(10000, 20000); - mv88e6xxx_g1_wait_eeprom_done(chip); + if (chip->info->ops->get_eeprom) + mv88e6xxx_g2_eeprom_wait(chip); } } diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 5848112036b0..964928285782 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -75,37 +75,6 @@ static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } -void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip) -{ - const unsigned long timeout = jiffies + 1 * HZ; - u16 val; - int err; - - /* Wait up to 1 second for the switch to finish reading the - * EEPROM. - */ - while (time_before(jiffies, timeout)) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); - if (err) { - dev_err(chip->dev, "Error reading status"); - return; - } - - /* If the switch is still resetting, it may not - * respond on the bus, and so MDIO read returns - * 0xffff. Differentiate between that, and waiting for - * the EEPROM to be done by bit 0 being set. - */ - if (val != 0xffff && - val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE)) - return; - - usleep_range(1000, 2000); - } - - dev_err(chip->dev, "Timeout waiting for EEPROM done"); -} - /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 * Offset 0x02: Switch MAC Address Register Bytes 2 & 3 * Offset 0x03: Switch MAC Address Register Bytes 4 & 5 diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 65958b2a0d3a..04b57a21f786 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -281,7 +281,6 @@ int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip); -void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index ec49939968fa..ac302a935ce6 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -340,7 +340,7 @@ int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) * Offset 0x15: EEPROM Addr (for 8-bit data access) */ -static int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) +int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) { int bit = __bf_shf(MV88E6XXX_G2_EEPROM_CMD_BUSY); int err; diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index c05fad5c9f19..751a6c988de4 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -359,6 +359,7 @@ int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip); int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, int port); +int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip); extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6250_watchdog_ops; From 7f042041360e6df0254d9ee0ec4b78b8f001a265 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Fri, 22 Sep 2023 23:04:58 +0200 Subject: [PATCH 2007/2093] ipv6: tcp: add a missing nf_reset_ct() in 3WHS handling [ Upstream commit 9593c7cb6cf670ef724d17f7f9affd7a8d2ad0c5 ] Commit b0e214d21203 ("netfilter: keep conntrack reference until IPsecv6 policy checks are done") is a direct copy of the old commit b59c270104f0 ("[NETFILTER]: Keep conntrack reference until IPsec policy checks are done") but for IPv6. However, it also copies a bug that this old commit had. That is: when the third packet of 3WHS connection establishment contains payload, it is added into socket receive queue without the XFRM check and the drop of connection tracking context. That leads to nf_conntrack module being impossible to unload as it waits for all the conntrack references to be dropped while the packet release is deferred in per-cpu cache indefinitely, if not consumed by the application. The issue for IPv4 was fixed in commit 6f0012e35160 ("tcp: add a missing nf_reset_ct() in 3WHS handling") by adding a missing XFRM check and correctly dropping the conntrack context. However, the issue was introduced to IPv6 code afterwards. Fixing it the same way for IPv6 now. Fixes: b0e214d21203 ("netfilter: keep conntrack reference until IPsecv6 policy checks are done") Link: https://lore.kernel.org/netdev/d589a999-d4dd-2768-b2d5-89dec64a4a42@ovn.org/ Signed-off-by: Ilya Maximets Acked-by: Florian Westphal Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230922210530.2045146-1-i.maximets@ovn.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv6/tcp_ipv6.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4bdd356bb5c4..7be89dcfd5fc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1644,9 +1644,12 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) struct sock *nsk; sk = req->rsk_listener; - drop_reason = tcp_inbound_md5_hash(sk, skb, - &hdr->saddr, &hdr->daddr, - AF_INET6, dif, sdif); + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + drop_reason = SKB_DROP_REASON_XFRM_POLICY; + else + drop_reason = tcp_inbound_md5_hash(sk, skb, + &hdr->saddr, &hdr->daddr, + AF_INET6, dif, sdif); if (drop_reason) { sk_drops_add(sk, skb); reqsk_put(req); @@ -1693,6 +1696,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) } goto discard_and_relse; } + nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); From 9ffc5018020fe646795a8dc1203224b8f776dc09 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Sun, 24 Sep 2023 02:35:49 +0900 Subject: [PATCH 2008/2093] net: usb: smsc75xx: Fix uninit-value access in __smsc75xx_read_reg [ Upstream commit e9c65989920f7c28775ec4e0c11b483910fb67b8 ] syzbot reported the following uninit-value access issue: ===================================================== BUG: KMSAN: uninit-value in smsc75xx_wait_ready drivers/net/usb/smsc75xx.c:975 [inline] BUG: KMSAN: uninit-value in smsc75xx_bind+0x5c9/0x11e0 drivers/net/usb/smsc75xx.c:1482 CPU: 0 PID: 8696 Comm: kworker/0:3 Not tainted 5.8.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: usb_hub_wq hub_event Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:121 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 smsc75xx_wait_ready drivers/net/usb/smsc75xx.c:975 [inline] smsc75xx_bind+0x5c9/0x11e0 drivers/net/usb/smsc75xx.c:1482 usbnet_probe+0x1152/0x3f90 drivers/net/usb/usbnet.c:1737 usb_probe_interface+0xece/0x1550 drivers/usb/core/driver.c:374 really_probe+0xf20/0x20b0 drivers/base/dd.c:529 driver_probe_device+0x293/0x390 drivers/base/dd.c:701 __device_attach_driver+0x63f/0x830 drivers/base/dd.c:807 bus_for_each_drv+0x2ca/0x3f0 drivers/base/bus.c:431 __device_attach+0x4e2/0x7f0 drivers/base/dd.c:873 device_initial_probe+0x4a/0x60 drivers/base/dd.c:920 bus_probe_device+0x177/0x3d0 drivers/base/bus.c:491 device_add+0x3b0e/0x40d0 drivers/base/core.c:2680 usb_set_configuration+0x380f/0x3f10 drivers/usb/core/message.c:2032 usb_generic_driver_probe+0x138/0x300 drivers/usb/core/generic.c:241 usb_probe_device+0x311/0x490 drivers/usb/core/driver.c:272 really_probe+0xf20/0x20b0 drivers/base/dd.c:529 driver_probe_device+0x293/0x390 drivers/base/dd.c:701 __device_attach_driver+0x63f/0x830 drivers/base/dd.c:807 bus_for_each_drv+0x2ca/0x3f0 drivers/base/bus.c:431 __device_attach+0x4e2/0x7f0 drivers/base/dd.c:873 device_initial_probe+0x4a/0x60 drivers/base/dd.c:920 bus_probe_device+0x177/0x3d0 drivers/base/bus.c:491 device_add+0x3b0e/0x40d0 drivers/base/core.c:2680 usb_new_device+0x1bd4/0x2a30 drivers/usb/core/hub.c:2554 hub_port_connect drivers/usb/core/hub.c:5208 [inline] hub_port_connect_change drivers/usb/core/hub.c:5348 [inline] port_event drivers/usb/core/hub.c:5494 [inline] hub_event+0x5e7b/0x8a70 drivers/usb/core/hub.c:5576 process_one_work+0x1688/0x2140 kernel/workqueue.c:2269 worker_thread+0x10bc/0x2730 kernel/workqueue.c:2415 kthread+0x551/0x590 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293 Local variable ----buf.i87@smsc75xx_bind created at: __smsc75xx_read_reg drivers/net/usb/smsc75xx.c:83 [inline] smsc75xx_wait_ready drivers/net/usb/smsc75xx.c:968 [inline] smsc75xx_bind+0x485/0x11e0 drivers/net/usb/smsc75xx.c:1482 __smsc75xx_read_reg drivers/net/usb/smsc75xx.c:83 [inline] smsc75xx_wait_ready drivers/net/usb/smsc75xx.c:968 [inline] smsc75xx_bind+0x485/0x11e0 drivers/net/usb/smsc75xx.c:1482 This issue is caused because usbnet_read_cmd() reads less bytes than requested (zero byte in the reproducer). In this case, 'buf' is not properly filled. This patch fixes the issue by returning -ENODATA if usbnet_read_cmd() reads less bytes than requested. Fixes: d0cad871703b ("smsc75xx: SMSC LAN75xx USB gigabit ethernet adapter driver") Reported-and-tested-by: syzbot+6966546b78d050bb0b5d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=6966546b78d050bb0b5d Signed-off-by: Shigeru Yoshida Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230923173549.3284502-1-syoshida@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/usb/smsc75xx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 5d6454fedb3f..78ad2da3ee29 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -90,7 +90,9 @@ static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index, ret = fn(dev, USB_VENDOR_REQUEST_READ_REGISTER, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, &buf, 4); - if (unlikely(ret < 0)) { + if (unlikely(ret < 4)) { + ret = ret < 0 ? ret : -ENODATA; + netdev_warn(dev->net, "Failed to read reg index 0x%08x: %d\n", index, ret); return ret; From 7562780e32b84196731d57dd24563546fcf6d082 Mon Sep 17 00:00:00 2001 From: Jeremy Cline Date: Fri, 8 Sep 2023 19:58:53 -0400 Subject: [PATCH 2009/2093] net: nfc: llcp: Add lock when modifying device list [ Upstream commit dfc7f7a988dad34c3bf4c053124fb26aa6c5f916 ] The device list needs its associated lock held when modifying it, or the list could become corrupted, as syzbot discovered. Reported-and-tested-by: syzbot+c1d0a03d305972dbbe14@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c1d0a03d305972dbbe14 Signed-off-by: Jeremy Cline Reviewed-by: Simon Horman Fixes: 6709d4b7bc2e ("net: nfc: Fix use-after-free caused by nfc_llcp_find_local") Link: https://lore.kernel.org/r/20230908235853.1319596-1-jeremy@jcline.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/nfc/llcp_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index f60e424e0607..6705bb895e23 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -1636,7 +1636,9 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) timer_setup(&local->sdreq_timer, nfc_llcp_sdreq_timer, 0); INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work); + spin_lock(&llcp_devices_lock); list_add(&local->list, &llcp_devices); + spin_unlock(&llcp_devices_lock); return 0; } From 2428c557cd628e104aa8fc3a82f9d98ac8a0cea7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 26 Sep 2023 17:04:43 +0300 Subject: [PATCH 2010/2093] net: ethernet: ti: am65-cpsw: Fix error code in am65_cpsw_nuss_init_tx_chns() [ Upstream commit 37d4f55567982e445f86dc0ff4ecfa72921abfe8 ] This accidentally returns success, but it should return a negative error code. Fixes: 93a76530316a ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver") Signed-off-by: Dan Carpenter Reviewed-by: Roger Quadros Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 25466cbdc16b..9f2553799895 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1614,6 +1614,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) if (tx_chn->irq <= 0) { dev_err(dev, "Failed to get tx dma irq %d\n", tx_chn->irq); + ret = tx_chn->irq ?: -ENXIO; goto err; } From 6e1dbbf29031e26cfd3892831128445f7ef0fcfe Mon Sep 17 00:00:00 2001 From: David Wilder Date: Tue, 26 Sep 2023 16:42:51 -0500 Subject: [PATCH 2011/2093] ibmveth: Remove condition to recompute TCP header checksum. [ Upstream commit 51e7a66666e0ca9642c59464ef8359f0ac604d41 ] In some OVS environments the TCP pseudo header checksum may need to be recomputed. Currently this is only done when the interface instance is configured for "Trunk Mode". We found the issue also occurs in some Kubernetes environments, these environments do not use "Trunk Mode", therefor the condition is removed. Performance tests with this change show only a fractional decrease in throughput (< 0.2%). Fixes: 7525de2516fb ("ibmveth: Set CHECKSUM_PARTIAL if NULL TCP CSUM.") Signed-off-by: David Wilder Reviewed-by: Nick Child Reviewed-by: Jacob Keller Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/ibm/ibmveth.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 0b4ec6e41eb4..1d21a281222d 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1308,24 +1308,23 @@ static void ibmveth_rx_csum_helper(struct sk_buff *skb, * the user space for finding a flow. During this process, OVS computes * checksum on the first packet when CHECKSUM_PARTIAL flag is set. * - * So, re-compute TCP pseudo header checksum when configured for - * trunk mode. + * So, re-compute TCP pseudo header checksum. */ + if (iph_proto == IPPROTO_TCP) { struct tcphdr *tcph = (struct tcphdr *)(skb->data + iphlen); + if (tcph->check == 0x0000) { /* Recompute TCP pseudo header checksum */ - if (adapter->is_active_trunk) { - tcphdrlen = skb->len - iphlen; - if (skb_proto == ETH_P_IP) - tcph->check = - ~csum_tcpudp_magic(iph->saddr, - iph->daddr, tcphdrlen, iph_proto, 0); - else if (skb_proto == ETH_P_IPV6) - tcph->check = - ~csum_ipv6_magic(&iph6->saddr, - &iph6->daddr, tcphdrlen, iph_proto, 0); - } + tcphdrlen = skb->len - iphlen; + if (skb_proto == ETH_P_IP) + tcph->check = + ~csum_tcpudp_magic(iph->saddr, + iph->daddr, tcphdrlen, iph_proto, 0); + else if (skb_proto == ETH_P_IPV6) + tcph->check = + ~csum_ipv6_magic(&iph6->saddr, + &iph6->daddr, tcphdrlen, iph_proto, 0); /* Setup SKB fields for checksum offload */ skb_partial_csum_set(skb, iphlen, offsetof(struct tcphdr, check)); From 00d35e6b1672b973a2bf8de1cb8167b287aa5797 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 3 Oct 2023 13:17:53 -0400 Subject: [PATCH 2012/2093] netfilter: handle the connecting collision properly in nf_conntrack_proto_sctp [ Upstream commit 8e56b063c86569e51eed1c5681ce6361fa97fc7a ] In Scenario A and B below, as the delayed INIT_ACK always changes the peer vtag, SCTP ct with the incorrect vtag may cause packet loss. Scenario A: INIT_ACK is delayed until the peer receives its own INIT_ACK 192.168.1.2 > 192.168.1.1: [INIT] [init tag: 1328086772] 192.168.1.1 > 192.168.1.2: [INIT] [init tag: 1414468151] 192.168.1.2 > 192.168.1.1: [INIT ACK] [init tag: 1328086772] 192.168.1.1 > 192.168.1.2: [INIT ACK] [init tag: 1650211246] * 192.168.1.2 > 192.168.1.1: [COOKIE ECHO] 192.168.1.1 > 192.168.1.2: [COOKIE ECHO] 192.168.1.2 > 192.168.1.1: [COOKIE ACK] Scenario B: INIT_ACK is delayed until the peer completes its own handshake 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885] 192.168.1.2 > 192.168.1.1: sctp (1) [INIT ACK] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [COOKIE ECHO] 192.168.1.2 > 192.168.1.1: sctp (1) [COOKIE ACK] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT ACK] [init tag: 3914796021] * This patch fixes it as below: In SCTP_CID_INIT processing: - clear ct->proto.sctp.init[!dir] if ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]. (Scenario E) - set ct->proto.sctp.init[dir]. In SCTP_CID_INIT_ACK processing: - drop it if !ct->proto.sctp.init[!dir] && ct->proto.sctp.vtag[!dir] && ct->proto.sctp.vtag[!dir] != ih->init_tag. (Scenario B, Scenario C) - drop it if ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && ct->proto.sctp.vtag[!dir] != ih->init_tag. (Scenario A) In SCTP_CID_COOKIE_ACK processing: - clear ct->proto.sctp.init[dir] and ct->proto.sctp.init[!dir]. (Scenario D) Also, it's important to allow the ct state to move forward with cookie_echo and cookie_ack from the opposite dir for the collision scenarios. There are also other Scenarios where it should allow the packet through, addressed by the processing above: Scenario C: new CT is created by INIT_ACK. Scenario D: start INIT on the existing ESTABLISHED ct. Scenario E: start INIT after the old collision on the existing ESTABLISHED ct. 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885] (both side are stopped, then start new connection again in hours) 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 242308742] Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Xin Long Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- include/linux/netfilter/nf_conntrack_sctp.h | 1 + net/netfilter/nf_conntrack_proto_sctp.c | 43 ++++++++++++++++----- 2 files changed, 34 insertions(+), 10 deletions(-) diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 625f491b95de..fb31312825ae 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,7 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 init[IP_CT_DIR_MAX]; u8 last_dir; u8 flags; }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 7247af51bdfc..c94a9971d790 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, /* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, /* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, /* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -426,6 +426,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; + } else if (sch->type == SCTP_CID_COOKIE_ACK) { + ct->proto.sctp.init[dir] = 0; + ct->proto.sctp.init[!dir] = 0; } else if (sch->type == SCTP_CID_HEARTBEAT) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); @@ -474,16 +477,18 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } /* If it is an INIT or an INIT ACK note down the vtag */ - if (sch->type == SCTP_CID_INIT || - sch->type == SCTP_CID_INIT_ACK) { - struct sctp_inithdr _inithdr, *ih; + if (sch->type == SCTP_CID_INIT) { + struct sctp_inithdr _ih, *ih; - ih = skb_header_pointer(skb, offset + sizeof(_sch), - sizeof(_inithdr), &_inithdr); - if (ih == NULL) + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) goto out_unlock; - pr_debug("Setting vtag %x for dir %d\n", - ih->init_tag, !dir); + + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) + ct->proto.sctp.init[!dir] = 0; + ct->proto.sctp.init[dir] = 1; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; /* don't renew timeout on init retransmit so @@ -494,6 +499,24 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, old_state == SCTP_CONNTRACK_CLOSED && nf_ct_is_confirmed(ct)) ignore = true; + } else if (sch->type == SCTP_CID_INIT_ACK) { + struct sctp_inithdr _ih, *ih; + __be32 vtag; + + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) + goto out_unlock; + + vtag = ct->proto.sctp.vtag[!dir]; + if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag) + goto out_unlock; + /* collision */ + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && + vtag != ih->init_tag) + goto out_unlock; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); + ct->proto.sctp.vtag[!dir] = ih->init_tag; } ct->proto.sctp.state = new_state; From 82273f15e3db717a03c07d71481354e38babdc17 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 13 Sep 2023 15:51:37 +0200 Subject: [PATCH 2013/2093] selftests: netfilter: Test nf_tables audit logging [ Upstream commit e8dbde59ca3fe925d0105bfb380e8429928b16dd ] Compare NETFILTER_CFG type audit logs emitted from kernel upon ruleset modifications against expected output. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso Stable-dep-of: 0d880dc6f032 ("netfilter: nf_tables: Deduplicate nft_register_obj audit logs") Signed-off-by: Sasha Levin --- tools/testing/selftests/netfilter/.gitignore | 1 + tools/testing/selftests/netfilter/Makefile | 4 +- .../selftests/netfilter/audit_logread.c | 165 ++++++++++++++++++ tools/testing/selftests/netfilter/config | 1 + .../testing/selftests/netfilter/nft_audit.sh | 108 ++++++++++++ 5 files changed, 277 insertions(+), 2 deletions(-) create mode 100644 tools/testing/selftests/netfilter/audit_logread.c create mode 100755 tools/testing/selftests/netfilter/nft_audit.sh diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore index 4cb887b57413..4b2928e1c19d 100644 --- a/tools/testing/selftests/netfilter/.gitignore +++ b/tools/testing/selftests/netfilter/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only nf-queue connect_close +audit_logread diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 3686bfa6c58d..321db8850da0 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -6,13 +6,13 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ - conntrack_vrf.sh nft_synproxy.sh rpath.sh + conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh HOSTPKG_CONFIG := pkg-config CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) -TEST_GEN_FILES = nf-queue connect_close +TEST_GEN_FILES = nf-queue connect_close audit_logread include ../lib.mk diff --git a/tools/testing/selftests/netfilter/audit_logread.c b/tools/testing/selftests/netfilter/audit_logread.c new file mode 100644 index 000000000000..a0a880fc2d9d --- /dev/null +++ b/tools/testing/selftests/netfilter/audit_logread.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int fd; + +#define MAX_AUDIT_MESSAGE_LENGTH 8970 +struct audit_message { + struct nlmsghdr nlh; + union { + struct audit_status s; + char data[MAX_AUDIT_MESSAGE_LENGTH]; + } u; +}; + +int audit_recv(int fd, struct audit_message *rep) +{ + struct sockaddr_nl addr; + socklen_t addrlen = sizeof(addr); + int ret; + + do { + ret = recvfrom(fd, rep, sizeof(*rep), 0, + (struct sockaddr *)&addr, &addrlen); + } while (ret < 0 && errno == EINTR); + + if (ret < 0 || + addrlen != sizeof(addr) || + addr.nl_pid != 0 || + rep->nlh.nlmsg_type == NLMSG_ERROR) /* short-cut for now */ + return -1; + + return ret; +} + +int audit_send(int fd, uint16_t type, uint32_t key, uint32_t val) +{ + static int seq = 0; + struct audit_message msg = { + .nlh = { + .nlmsg_len = NLMSG_SPACE(sizeof(msg.u.s)), + .nlmsg_type = type, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK, + .nlmsg_seq = ++seq, + }, + .u.s = { + .mask = key, + .enabled = key == AUDIT_STATUS_ENABLED ? val : 0, + .pid = key == AUDIT_STATUS_PID ? val : 0, + } + }; + struct sockaddr_nl addr = { + .nl_family = AF_NETLINK, + }; + int ret; + + do { + ret = sendto(fd, &msg, msg.nlh.nlmsg_len, 0, + (struct sockaddr *)&addr, sizeof(addr)); + } while (ret < 0 && errno == EINTR); + + if (ret != (int)msg.nlh.nlmsg_len) + return -1; + return 0; +} + +int audit_set(int fd, uint32_t key, uint32_t val) +{ + struct audit_message rep = { 0 }; + int ret; + + ret = audit_send(fd, AUDIT_SET, key, val); + if (ret) + return ret; + + ret = audit_recv(fd, &rep); + if (ret < 0) + return ret; + return 0; +} + +int readlog(int fd) +{ + struct audit_message rep = { 0 }; + int ret = audit_recv(fd, &rep); + const char *sep = ""; + char *k, *v; + + if (ret < 0) + return ret; + + if (rep.nlh.nlmsg_type != AUDIT_NETFILTER_CFG) + return 0; + + /* skip the initial "audit(...): " part */ + strtok(rep.u.data, " "); + + while ((k = strtok(NULL, "="))) { + v = strtok(NULL, " "); + + /* these vary and/or are uninteresting, ignore */ + if (!strcmp(k, "pid") || + !strcmp(k, "comm") || + !strcmp(k, "subj")) + continue; + + /* strip the varying sequence number */ + if (!strcmp(k, "table")) + *strchrnul(v, ':') = '\0'; + + printf("%s%s=%s", sep, k, v); + sep = " "; + } + if (*sep) { + printf("\n"); + fflush(stdout); + } + return 0; +} + +void cleanup(int sig) +{ + audit_set(fd, AUDIT_STATUS_ENABLED, 0); + close(fd); + if (sig) + exit(0); +} + +int main(int argc, char **argv) +{ + struct sigaction act = { + .sa_handler = cleanup, + }; + + fd = socket(PF_NETLINK, SOCK_RAW, NETLINK_AUDIT); + if (fd < 0) { + perror("Can't open netlink socket"); + return -1; + } + + if (sigaction(SIGTERM, &act, NULL) < 0 || + sigaction(SIGINT, &act, NULL) < 0) { + perror("Can't set signal handler"); + close(fd); + return -1; + } + + audit_set(fd, AUDIT_STATUS_ENABLED, 1); + audit_set(fd, AUDIT_STATUS_PID, getpid()); + + while (1) + readlog(fd); +} diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config index 4faf2ce021d9..7c42b1b2c69b 100644 --- a/tools/testing/selftests/netfilter/config +++ b/tools/testing/selftests/netfilter/config @@ -6,3 +6,4 @@ CONFIG_NFT_REDIR=m CONFIG_NFT_MASQ=m CONFIG_NFT_FLOW_OFFLOAD=m CONFIG_NF_CT_NETLINK=m +CONFIG_AUDIT=y diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh new file mode 100755 index 000000000000..83c271b1c735 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_audit.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Check that audit logs generated for nft commands are as expected. + +SKIP_RC=4 +RC=0 + +nft --version >/dev/null 2>&1 || { + echo "SKIP: missing nft tool" + exit $SKIP_RC +} + +logfile=$(mktemp) +echo "logging into $logfile" +./audit_logread >"$logfile" & +logread_pid=$! +trap 'kill $logread_pid; rm -f $logfile' EXIT +exec 3<"$logfile" + +do_test() { # (cmd, log) + echo -n "testing for cmd: $1 ... " + cat <&3 >/dev/null + $1 >/dev/null || exit 1 + sleep 0.1 + res=$(diff -a -u <(echo "$2") - <&3) + [ $? -eq 0 ] && { echo "OK"; return; } + echo "FAIL" + echo "$res" + ((RC++)) +} + +nft flush ruleset + +for table in t1 t2; do + do_test "nft add table $table" \ + "table=$table family=2 entries=1 op=nft_register_table" + + do_test "nft add chain $table c1" \ + "table=$table family=2 entries=1 op=nft_register_chain" + + do_test "nft add chain $table c2; add chain $table c3" \ + "table=$table family=2 entries=2 op=nft_register_chain" + + cmd="add rule $table c1 counter" + + do_test "nft $cmd" \ + "table=$table family=2 entries=1 op=nft_register_rule" + + do_test "nft $cmd; $cmd" \ + "table=$table family=2 entries=2 op=nft_register_rule" + + cmd="" + sep="" + for chain in c2 c3; do + for i in {1..3}; do + cmd+="$sep add rule $table $chain counter" + sep=";" + done + done + do_test "nft $cmd" \ + "table=$table family=2 entries=6 op=nft_register_rule" +done + +do_test 'nft reset rules t1 c2' \ +'table=t1 family=2 entries=3 op=nft_reset_rule' + +do_test 'nft reset rules table t1' \ +'table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule' + +do_test 'nft reset rules' \ +'table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule' + +for ((i = 0; i < 500; i++)); do + echo "add rule t2 c3 counter accept comment \"rule $i\"" +done | do_test 'nft -f -' \ +'table=t2 family=2 entries=500 op=nft_register_rule' + +do_test 'nft reset rules t2 c3' \ +'table=t2 family=2 entries=189 op=nft_reset_rule +table=t2 family=2 entries=188 op=nft_reset_rule +table=t2 family=2 entries=126 op=nft_reset_rule' + +do_test 'nft reset rules t2' \ +'table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=186 op=nft_reset_rule +table=t2 family=2 entries=188 op=nft_reset_rule +table=t2 family=2 entries=129 op=nft_reset_rule' + +do_test 'nft reset rules' \ +'table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=180 op=nft_reset_rule +table=t2 family=2 entries=188 op=nft_reset_rule +table=t2 family=2 entries=135 op=nft_reset_rule' + +exit $RC From e1bbe4afe1a38e679d8704ec16c11e542ad9acc4 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Sat, 23 Sep 2023 03:53:49 +0200 Subject: [PATCH 2014/2093] selftests: netfilter: Extend nft_audit.sh [ Upstream commit 203bb9d39866d3c5a8135433ce3742fe4f9d5741 ] Add tests for sets and elements and deletion of all kinds. Also reorder rule reset tests: By moving the bulk rule add command up, the two 'reset rules' tests become identical. While at it, fix for a failing bulk rule add test's error status getting lost due to its use in a pipe. Avoid this by using a temporary file. Headings in diff output for failing tests contain no useful data, strip them. Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal Stable-dep-of: 0d880dc6f032 ("netfilter: nf_tables: Deduplicate nft_register_obj audit logs") Signed-off-by: Sasha Levin --- .../testing/selftests/netfilter/nft_audit.sh | 97 ++++++++++++++++--- 1 file changed, 81 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh index 83c271b1c735..0b3255e7b353 100755 --- a/tools/testing/selftests/netfilter/nft_audit.sh +++ b/tools/testing/selftests/netfilter/nft_audit.sh @@ -12,10 +12,11 @@ nft --version >/dev/null 2>&1 || { } logfile=$(mktemp) +rulefile=$(mktemp) echo "logging into $logfile" ./audit_logread >"$logfile" & logread_pid=$! -trap 'kill $logread_pid; rm -f $logfile' EXIT +trap 'kill $logread_pid; rm -f $logfile $rulefile' EXIT exec 3<"$logfile" do_test() { # (cmd, log) @@ -26,12 +27,14 @@ do_test() { # (cmd, log) res=$(diff -a -u <(echo "$2") - <&3) [ $? -eq 0 ] && { echo "OK"; return; } echo "FAIL" - echo "$res" - ((RC++)) + grep -v '^\(---\|+++\|@@\)' <<< "$res" + ((RC--)) } nft flush ruleset +# adding tables, chains and rules + for table in t1 t2; do do_test "nft add table $table" \ "table=$table family=2 entries=1 op=nft_register_table" @@ -62,6 +65,28 @@ for table in t1 t2; do "table=$table family=2 entries=6 op=nft_register_rule" done +for ((i = 0; i < 500; i++)); do + echo "add rule t2 c3 counter accept comment \"rule $i\"" +done >$rulefile +do_test "nft -f $rulefile" \ +'table=t2 family=2 entries=500 op=nft_register_rule' + +# adding sets and elements + +settype='type inet_service; counter' +setelem='{ 22, 80, 443 }' +setblock="{ $settype; elements = $setelem; }" +do_test "nft add set t1 s $setblock" \ +"table=t1 family=2 entries=4 op=nft_register_set" + +do_test "nft add set t1 s2 $setblock; add set t1 s3 { $settype; }" \ +"table=t1 family=2 entries=5 op=nft_register_set" + +do_test "nft add element t1 s3 $setelem" \ +"table=t1 family=2 entries=3 op=nft_register_setelem" + +# resetting rules + do_test 'nft reset rules t1 c2' \ 'table=t1 family=2 entries=3 op=nft_reset_rule' @@ -70,19 +95,6 @@ do_test 'nft reset rules table t1' \ table=t1 family=2 entries=3 op=nft_reset_rule table=t1 family=2 entries=3 op=nft_reset_rule' -do_test 'nft reset rules' \ -'table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule' - -for ((i = 0; i < 500; i++)); do - echo "add rule t2 c3 counter accept comment \"rule $i\"" -done | do_test 'nft -f -' \ -'table=t2 family=2 entries=500 op=nft_register_rule' - do_test 'nft reset rules t2 c3' \ 'table=t2 family=2 entries=189 op=nft_reset_rule table=t2 family=2 entries=188 op=nft_reset_rule @@ -105,4 +117,57 @@ table=t2 family=2 entries=180 op=nft_reset_rule table=t2 family=2 entries=188 op=nft_reset_rule table=t2 family=2 entries=135 op=nft_reset_rule' +# resetting sets and elements + +elem=(22 ,80 ,443) +relem="" +for i in {1..3}; do + relem+="${elem[((i - 1))]}" + do_test "nft reset element t1 s { $relem }" \ + "table=t1 family=2 entries=$i op=nft_reset_setelem" +done + +do_test 'nft reset set t1 s' \ +'table=t1 family=2 entries=3 op=nft_reset_setelem' + +# deleting rules + +readarray -t handles < <(nft -a list chain t1 c1 | \ + sed -n 's/.*counter.* handle \(.*\)$/\1/p') + +do_test "nft delete rule t1 c1 handle ${handles[0]}" \ +'table=t1 family=2 entries=1 op=nft_unregister_rule' + +cmd='delete rule t1 c1 handle' +do_test "nft $cmd ${handles[1]}; $cmd ${handles[2]}" \ +'table=t1 family=2 entries=2 op=nft_unregister_rule' + +do_test 'nft flush chain t1 c2' \ +'table=t1 family=2 entries=3 op=nft_unregister_rule' + +do_test 'nft flush table t2' \ +'table=t2 family=2 entries=509 op=nft_unregister_rule' + +# deleting chains + +do_test 'nft delete chain t2 c2' \ +'table=t2 family=2 entries=1 op=nft_unregister_chain' + +# deleting sets and elements + +do_test 'nft delete element t1 s { 22 }' \ +'table=t1 family=2 entries=1 op=nft_unregister_setelem' + +do_test 'nft delete element t1 s { 80, 443 }' \ +'table=t1 family=2 entries=2 op=nft_unregister_setelem' + +do_test 'nft flush set t1 s2' \ +'table=t1 family=2 entries=3 op=nft_unregister_setelem' + +do_test 'nft delete set t1 s2' \ +'table=t1 family=2 entries=1 op=nft_unregister_set' + +do_test 'nft delete set t1 s3' \ +'table=t1 family=2 entries=1 op=nft_unregister_set' + exit $RC From 7ff9a9857b8b5197e0ced9bb37256decfc59b95b Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Sat, 23 Sep 2023 03:53:50 +0200 Subject: [PATCH 2015/2093] netfilter: nf_tables: Deduplicate nft_register_obj audit logs [ Upstream commit 0d880dc6f032e0b541520e9926f398a77d3d433c ] When adding/updating an object, the transaction handler emits suitable audit log entries already, the one in nft_obj_notify() is redundant. To fix that (and retain the audit logging from objects' 'update' callback), Introduce an "audit log free" variant for internal use. Fixes: c520292f29b8 ("audit: log nftables configuration change events once per table") Signed-off-by: Phil Sutter Reviewed-by: Richard Guy Briggs Acked-by: Paul Moore (Audit) Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 44 ++++++++++++------- .../testing/selftests/netfilter/nft_audit.sh | 20 +++++++++ 2 files changed, 48 insertions(+), 16 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 52b81dc1fcf5..5e3dbe2652db 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7576,24 +7576,14 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, return nft_delobj(&ctx, obj); } -void nft_obj_notify(struct net *net, const struct nft_table *table, - struct nft_object *obj, u32 portid, u32 seq, int event, - u16 flags, int family, int report, gfp_t gfp) +static void +__nft_obj_notify(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; - char *buf = kasprintf(gfp, "%s:%u", - table->name, nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - obj->handle, - event == NFT_MSG_NEWOBJ ? - AUDIT_NFT_OP_OBJ_REGISTER : - AUDIT_NFT_OP_OBJ_UNREGISTER, - gfp); - kfree(buf); if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -7616,13 +7606,35 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } + +void nft_obj_notify(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + char *buf = kasprintf(gfp, "%s:%u", + table->name, nft_net->base_seq); + + audit_log_nfcfg(buf, + family, + obj->handle, + event == NFT_MSG_NEWOBJ ? + AUDIT_NFT_OP_OBJ_REGISTER : + AUDIT_NFT_OP_OBJ_UNREGISTER, + gfp); + kfree(buf); + + __nft_obj_notify(net, table, obj, portid, seq, event, + flags, family, report, gfp); +} EXPORT_SYMBOL_GPL(nft_obj_notify); static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { - nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->flags, ctx->family, ctx->report, GFP_KERNEL); + __nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, + ctx->seq, event, ctx->flags, ctx->family, + ctx->report, GFP_KERNEL); } /* diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh index 0b3255e7b353..bb34329e02a7 100755 --- a/tools/testing/selftests/netfilter/nft_audit.sh +++ b/tools/testing/selftests/netfilter/nft_audit.sh @@ -85,6 +85,26 @@ do_test "nft add set t1 s2 $setblock; add set t1 s3 { $settype; }" \ do_test "nft add element t1 s3 $setelem" \ "table=t1 family=2 entries=3 op=nft_register_setelem" +# adding counters + +do_test 'nft add counter t1 c1' \ +'table=t1 family=2 entries=1 op=nft_register_obj' + +do_test 'nft add counter t2 c1; add counter t2 c2' \ +'table=t2 family=2 entries=2 op=nft_register_obj' + +# adding/updating quotas + +do_test 'nft add quota t1 q1 { 10 bytes }' \ +'table=t1 family=2 entries=1 op=nft_register_obj' + +do_test 'nft add quota t2 q1 { 10 bytes }; add quota t2 q2 { 10 bytes }' \ +'table=t2 family=2 entries=2 op=nft_register_obj' + +# changing the quota value triggers obj update path +do_test 'nft add quota t1 q1 { 20 bytes }' \ +'table=t1 family=2 entries=1 op=nft_register_obj' + # resetting rules do_test 'nft reset rules t1 c2' \ From 56a6ea76dd9bc370bd406faa77b287656c85eeb9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 28 Sep 2023 15:12:44 +0200 Subject: [PATCH 2016/2093] netfilter: nf_tables: nft_set_rbtree: fix spurious insertion failure [ Upstream commit 087388278e0f301f4c61ddffb1911d3a180f84b8 ] nft_rbtree_gc_elem() walks back and removes the end interval element that comes before the expired element. There is a small chance that we've cached this element as 'rbe_ge'. If this happens, we hold and test a pointer that has been queued for freeing. It also causes spurious insertion failures: $ cat test-testcases-sets-0044interval_overlap_0.1/testout.log Error: Could not process rule: File exists add element t s { 0 - 2 } ^^^^^^ Failed to insert 0 - 2 given: table ip t { set s { type inet_service flags interval,timeout timeout 2s gc-interval 2s } } The set (rbtree) is empty. The 'failure' doesn't happen on next attempt. Reason is that when we try to insert, the tree may hold an expired element that collides with the range we're adding. While we do evict/erase this element, we can trip over this check: if (rbe_ge && nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; rbe_ge was erased by the synchronous gc, we should not have done this check. Next attempt won't find it, so retry results in successful insertion. Restart in-kernel to avoid such spurious errors. Such restart are rare, unless userspace intentionally adds very large numbers of elements with very short timeouts while setting a huge gc interval. Even in this case, this cannot loop forever, on each retry an existing element has been removed. As the caller is holding the transaction mutex, its impossible for a second entity to add more expiring elements to the tree. After this it also becomes feasible to remove the async gc worker and perform all garbage collection from the commit path. Fixes: c9e6978e2725 ("netfilter: nft_set_rbtree: Switch to node list walk for overlap detection") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_set_rbtree.c | 46 +++++++++++++++++++++------------- 1 file changed, 29 insertions(+), 17 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 487572dcd614..2660ceab3759 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -233,10 +233,9 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, rb_erase(&rbe->node, &priv->root); } -static int nft_rbtree_gc_elem(const struct nft_set *__set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, - u8 genmask) +static const struct nft_rbtree_elem * +nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe, u8 genmask) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -246,7 +245,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); if (!gc) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they @@ -261,6 +260,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, prev = rb_prev(prev); } + rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); nft_rbtree_gc_remove(net, set, priv, rbe_prev); @@ -272,7 +272,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, */ gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe_prev); } @@ -280,13 +280,13 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, nft_rbtree_gc_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe); nft_trans_gc_queue_sync_done(gc); - return 0; + return rbe_prev; } static bool nft_rbtree_update_first(const struct nft_set *set, @@ -314,7 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); - int d, err; + int d; /* Descend the tree to search for an existing element greater than the * key value to insert that is greater than the new element. This is the @@ -363,9 +363,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (nft_set_elem_expired(&rbe->ext) && nft_set_elem_active(&rbe->ext, cur_genmask)) { - err = nft_rbtree_gc_elem(set, priv, rbe, genmask); - if (err < 0) - return err; + const struct nft_rbtree_elem *removed_end; + + removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + if (IS_ERR(removed_end)) + return PTR_ERR(removed_end); + + if (removed_end == rbe_le || removed_end == rbe_ge) + return -EAGAIN; continue; } @@ -486,11 +491,18 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *rbe = elem->priv; int err; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); - err = __nft_rbtree_insert(net, set, rbe, ext); - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + do { + if (fatal_signal_pending(current)) + return -EINTR; + + cond_resched(); + + write_lock_bh(&priv->lock); + write_seqcount_begin(&priv->count); + err = __nft_rbtree_insert(net, set, rbe, ext); + write_seqcount_end(&priv->count); + write_unlock_bh(&priv->lock); + } while (err == -EAGAIN); return err; } From da7fa17bd9ac1ce14c1235131d058ed95e6c4765 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Tue, 26 Sep 2023 14:27:30 -0400 Subject: [PATCH 2017/2093] ipv4: Set offload_failed flag in fibmatch results [ Upstream commit 0add5c597f3253a9c6108a0a81d57f44ab0d9d30 ] Due to a small omission, the offload_failed flag is missing from ipv4 fibmatch results. Make sure it is set correctly. The issue can be witnessed using the following commands: echo "1 1" > /sys/bus/netdevsim/new_device ip link add dummy1 up type dummy ip route add 192.0.2.0/24 dev dummy1 echo 1 > /sys/kernel/debug/netdevsim/netdevsim1/fib/fail_route_offload ip route add 198.51.100.0/24 dev dummy1 ip route # 192.168.15.0/24 has rt_trap # 198.51.100.0/24 has rt_offload_failed ip route get 192.168.15.1 fibmatch # Result has rt_trap ip route get 198.51.100.1 fibmatch # Result differs from the route shown by `ip route`, it is missing # rt_offload_failed ip link del dev dummy1 echo 1 > /sys/bus/netdevsim/del_device Fixes: 36c5100e859d ("IPv4: Add "offload failed" indication to routes") Signed-off-by: Benjamin Poirier Reviewed-by: Ido Schimmel Reviewed-by: Simon Horman Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230926182730.231208-1-bpoirier@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/route.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 608bd9f8dbc8..9cbaae4f5ee7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3421,6 +3421,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = + READ_ONCE(fa->offload_failed); break; } } From f2697457ab73aef40fdcbd3cd2b6819e144493a4 Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer Date: Wed, 27 Sep 2023 13:57:49 -0400 Subject: [PATCH 2018/2093] net: stmmac: dwmac-stm32: fix resume on STM32 MCU [ Upstream commit 6f195d6b0da3b689922ba9e302af2f49592fa9fc ] The STM32MP1 keeps clk_rx enabled during suspend, and therefore the driver does not enable the clock in stm32_dwmac_init() if the device was suspended. The problem is that this same code runs on STM32 MCUs, which do disable clk_rx during suspend, causing the clock to never be re-enabled on resume. This patch adds a variant flag to indicate that clk_rx remains enabled during suspend, and uses this to decide whether to enable the clock in stm32_dwmac_init() if the device was suspended. This approach fixes this specific bug with limited opportunity for unintended side-effects, but I have a follow up patch that will refactor the clock configuration and hopefully make it less error prone. Fixes: 6528e02cc9ff ("net: ethernet: stmmac: add adaptation for stm32mp157c.") Signed-off-by: Ben Wolsieffer Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20230927175749.1419774-1-ben.wolsieffer@hefring.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 2b38a499a404..533f5245ad94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -105,6 +105,7 @@ struct stm32_ops { int (*parse_data)(struct stm32_dwmac *dwmac, struct device *dev); u32 syscfg_eth_mask; + bool clk_rx_enable_in_suspend; }; static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat) @@ -122,7 +123,8 @@ static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat) if (ret) return ret; - if (!dwmac->dev->power.is_suspended) { + if (!dwmac->ops->clk_rx_enable_in_suspend || + !dwmac->dev->power.is_suspended) { ret = clk_prepare_enable(dwmac->clk_rx); if (ret) { clk_disable_unprepare(dwmac->clk_tx); @@ -515,7 +517,8 @@ static struct stm32_ops stm32mp1_dwmac_data = { .suspend = stm32mp1_suspend, .resume = stm32mp1_resume, .parse_data = stm32mp1_parse_data, - .syscfg_eth_mask = SYSCFG_MP1_ETH_MASK + .syscfg_eth_mask = SYSCFG_MP1_ETH_MASK, + .clk_rx_enable_in_suspend = true }; static const struct of_device_id stm32_dwmac_match[] = { From 143e72757a902abcecd5f487553f44dc19a56cfc Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Wed, 27 Sep 2023 18:14:14 +0000 Subject: [PATCH 2019/2093] tipc: fix a potential deadlock on &tx->lock [ Upstream commit 08e50cf071847323414df0835109b6f3560d44f5 ] It seems that tipc_crypto_key_revoke() could be be invoked by wokequeue tipc_crypto_work_rx() under process context and timer/rx callback under softirq context, thus the lock acquisition on &tx->lock seems better use spin_lock_bh() to prevent possible deadlock. This flaw was found by an experimental static analysis tool I am developing for irq-related deadlock. tipc_crypto_work_rx() --> tipc_crypto_key_distr() --> tipc_bcast_xmit() --> tipc_bcbase_xmit() --> tipc_bearer_bc_xmit() --> tipc_crypto_xmit() --> tipc_ehdr_build() --> tipc_crypto_key_revoke() --> spin_lock(&tx->lock) --> tipc_disc_timeout() --> tipc_bearer_xmit_skb() --> tipc_crypto_xmit() --> tipc_ehdr_build() --> tipc_crypto_key_revoke() --> spin_lock(&tx->lock) Signed-off-by: Chengfeng Ye Reviewed-by: Jacob Keller Acked-by: Jon Maloy Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication") Link: https://lore.kernel.org/r/20230927181414.59928-1-dg573847474@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/tipc/crypto.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 2b236d95a646..65f59739a041 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1441,14 +1441,14 @@ static int tipc_crypto_key_revoke(struct net *net, u8 tx_key) struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_key key; - spin_lock(&tx->lock); + spin_lock_bh(&tx->lock); key = tx->key; WARN_ON(!key.active || tx_key != key.active); /* Free the active key */ tipc_crypto_key_set_state(tx, key.passive, 0, key.pending); tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); - spin_unlock(&tx->lock); + spin_unlock_bh(&tx->lock); pr_warn("%s: key is revoked\n", tx->name); return -EKEYREVOKED; From 4acf07bafb5812162ab41dc0ef4e8d9f798b5fc0 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sun, 1 Oct 2023 11:12:38 -0400 Subject: [PATCH 2020/2093] tcp: fix quick-ack counting to count actual ACKs of new data [ Upstream commit 059217c18be6757b95bfd77ba53fb50b48b8a816 ] This commit fixes quick-ack counting so that it only considers that a quick-ack has been provided if we are sending an ACK that newly acknowledges data. The code was erroneously using the number of data segments in outgoing skbs when deciding how many quick-ack credits to remove. This logic does not make sense, and could cause poor performance in request-response workloads, like RPC traffic, where requests or responses can be multi-segment skbs. When a TCP connection decides to send N quick-acks, that is to accelerate the cwnd growth of the congestion control module controlling the remote endpoint of the TCP connection. That quick-ack decision is purely about the incoming data and outgoing ACKs. It has nothing to do with the outgoing data or the size of outgoing data. And in particular, an ACK only serves the intended purpose of allowing the remote congestion control to grow the congestion window quickly if the ACK is ACKing or SACKing new data. The fix is simple: only count packets as serving the goal of the quickack mechanism if they are ACKing/SACKing new data. We can tell whether this is the case by checking inet_csk_ack_scheduled(), since we schedule an ACK exactly when we are ACKing/SACKing new data. Fixes: fc6415bcb0f5 ("[TCP]: Fix quick-ack decrementing with TSO.") Signed-off-by: Neal Cardwell Reviewed-by: Yuchung Cheng Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20231001151239.1866845-1-ncardwell.sw@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 6 ++++-- net/ipv4/tcp_output.c | 7 +++---- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 5fd69f2342a4..9ebb54122bb7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -355,12 +355,14 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, bool force_schedule); -static inline void tcp_dec_quickack_mode(struct sock *sk, - const unsigned int pkts) +static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { + /* How many ACKs S/ACKing new data have we sent? */ + const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; + if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index dc3166e56169..5921b0f6f9f4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -177,8 +177,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1373,7 +1372,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); From 419b2c5766fa773db3e36e55f0829ca279bceb86 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sun, 1 Oct 2023 11:12:39 -0400 Subject: [PATCH 2021/2093] tcp: fix delayed ACKs for MSS boundary condition [ Upstream commit 4720852ed9afb1c5ab84e96135cb5b73d5afde6f ] This commit fixes poor delayed ACK behavior that can cause poor TCP latency in a particular boundary condition: when an application makes a TCP socket write that is an exact multiple of the MSS size. The problem is that there is painful boundary discontinuity in the current delayed ACK behavior. With the current delayed ACK behavior, we have: (1) If an app reads data when > 1*MSS is unacknowledged, then tcp_cleanup_rbuf() ACKs immediately because of: tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || (2) If an app reads all received data, and the packets were < 1*MSS, and either (a) the app is not ping-pong or (b) we received two packets < 1*MSS, then tcp_cleanup_rbuf() ACKs immediately beecause of: ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !inet_csk_in_pingpong_mode(sk))) && (3) *However*: if an app reads exactly 1*MSS of data, tcp_cleanup_rbuf() does not send an immediate ACK. This is true even if the app is not ping-pong and the 1*MSS of data had the PSH bit set, suggesting the sending application completed an application write. Thus if the app is not ping-pong, we have this painful case where >1*MSS gets an immediate ACK, and <1*MSS gets an immediate ACK, but a write whose last skb is an exact multiple of 1*MSS can get a 40ms delayed ACK. This means that any app that transfers data in one direction and takes care to align write size or packet size with MSS can suffer this problem. With receive zero copy making 4KB MSS values more common, it is becoming more common to have application writes naturally align with MSS, and more applications are likely to encounter this delayed ACK problem. The fix in this commit is to refine the delayed ACK heuristics with a simple check: immediately ACK a received 1*MSS skb with PSH bit set if the app reads all data. Why? If an skb has a len of exactly 1*MSS and has the PSH bit set then it is likely the end of an application write. So more data may not be arriving soon, and yet the data sender may be waiting for an ACK if cwnd-bound or using TX zero copy. Thus we set ICSK_ACK_PUSHED in this case so that tcp_cleanup_rbuf() will send an ACK immediately if the app reads all of the data and is not ping-pong. Note that this logic is also executed for the case where len > MSS, but in that case this logic does not matter (and does not hurt) because tcp_cleanup_rbuf() will always ACK immediately if the app reads data and there is more than an MSS of unACKed data. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Neal Cardwell Reviewed-by: Yuchung Cheng Reviewed-by: Eric Dumazet Cc: Xin Guo Link: https://lore.kernel.org/r/20231001151239.1866845-2-ncardwell.sw@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_input.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c697836f2b5b..068221e74242 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -243,6 +243,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); + /* If the skb has a len of exactly 1*MSS and has the PSH bit + * set then it is likely the end of an application write. So + * more data may not be arriving soon, and yet the data sender + * may be waiting for an ACK if cwnd-bound or using TX zero + * copy. So we set ICSK_ACK_PUSHED here so that + * tcp_cleanup_rbuf() will send an ACK immediately if the app + * reads all of the data and is not ping-pong. If len > MSS + * then this logic does not matter (and does not hurt) because + * tcp_cleanup_rbuf() will always ACK immediately if the app + * reads data and there is more than an MSS of unACKed data. + */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. From 63cb52e75fd1622e9b186af33f17b87fc2f88e7c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Oct 2023 10:58:45 -0400 Subject: [PATCH 2022/2093] sctp: update transport state when processing a dupcook packet [ Upstream commit 2222a78075f0c19ca18db53fd6623afb4aff602d ] During the 4-way handshake, the transport's state is set to ACTIVE in sctp_process_init() when processing INIT_ACK chunk on client or COOKIE_ECHO chunk on server. In the collision scenario below: 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885] 192.168.1.2 > 192.168.1.1: sctp (1) [INIT ACK] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [COOKIE ECHO] 192.168.1.2 > 192.168.1.1: sctp (1) [COOKIE ACK] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT ACK] [init tag: 3914796021] when processing COOKIE_ECHO on 192.168.1.2, as it's in COOKIE_WAIT state, sctp_sf_do_dupcook_b() is called by sctp_sf_do_5_2_4_dupcook() where it creates a new association and sets its transport to ACTIVE then updates to the old association in sctp_assoc_update(). However, in sctp_assoc_update(), it will skip the transport update if it finds a transport with the same ipaddr already existing in the old asoc, and this causes the old asoc's transport state not to move to ACTIVE after the handshake. This means if DATA retransmission happens at this moment, it won't be able to enter PF state because of the check 'transport->state == SCTP_ACTIVE' in sctp_do_8_2_transport_strike(). This patch fixes it by updating the transport in sctp_assoc_update() with sctp_assoc_add_peer() where it updates the transport state if there is already a transport with the same ipaddr exists in the old asoc. Signed-off-by: Xin Long Reviewed-by: Simon Horman Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/r/fd17356abe49713ded425250cc1ae51e9f5846c6.1696172325.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/associola.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 3460abceba44..2965a12fe8aa 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1161,8 +1161,7 @@ int sctp_assoc_update(struct sctp_association *asoc, /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && - !sctp_assoc_add_peer(asoc, &trans->ipaddr, + if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; From 220f0f866d694b7765e03a70d4457ccd0c1bbe7c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Oct 2023 11:04:20 -0400 Subject: [PATCH 2023/2093] sctp: update hb timer immediately after users change hb_interval [ Upstream commit 1f4e803cd9c9166eb8b6c8b0b8e4124f7499fc07 ] Currently, when hb_interval is changed by users, it won't take effect until the next expiry of hb timer. As the default value is 30s, users have to wait up to 30s to wait its hb_interval update to work. This becomes pretty bad in containers where a much smaller value is usually set on hb_interval. This patch improves it by resetting the hb timer immediately once the value of hb_interval is updated by users. Note that we don't address the already existing 'problem' when sending a heartbeat 'on demand' if one hb has just been sent(from the timer) mentioned in: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg590224.html Signed-off-by: Xin Long Reviewed-by: Simon Horman Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/r/75465785f8ee5df2fb3acdca9b8fafdc18984098.1696172660.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/socket.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 32e3669adf14..e25dc1709131 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2449,6 +2449,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); + sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); From 1a6e2da05f379dd465a6be40ee44567824d2b292 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Oct 2022 14:25:53 -0700 Subject: [PATCH 2024/2093] netlink: split up copies in the ack construction [ Upstream commit 738136a0e3757a8534df3ad97d6ff6d7f429f6c1 ] Clean up the use of unsafe_memcpy() by adding a flexible array at the end of netlink message header and splitting up the header and data copies. Reviewed-by: Kees Cook Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller Stable-dep-of: d0f95894fda7 ("netlink: annotate data-races around sk->sk_err") Signed-off-by: Sasha Levin --- include/net/netlink.h | 21 +++++++++++++++++++++ include/uapi/linux/netlink.h | 2 ++ net/netlink/af_netlink.c | 29 ++++++++++++++++++++--------- 3 files changed, 43 insertions(+), 9 deletions(-) diff --git a/include/net/netlink.h b/include/net/netlink.h index 6bfa972f2fbf..a686c9041ddc 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -937,6 +937,27 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se return __nlmsg_put(skb, portid, seq, type, payload, flags); } +/** + * nlmsg_append - Add more data to a nlmsg in a skb + * @skb: socket buffer to store message in + * @size: length of message payload + * + * Append data to an existing nlmsg, used when constructing a message + * with multiple fixed-format headers (which is rare). + * Returns NULL if the tailroom of the skb is insufficient to store + * the extra payload. + */ +static inline void *nlmsg_append(struct sk_buff *skb, u32 size) +{ + if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size))) + return NULL; + + if (NLMSG_ALIGN(size) - size) + memset(skb_tail_pointer(skb) + size, 0, + NLMSG_ALIGN(size) - size); + return __skb_put(skb, NLMSG_ALIGN(size)); +} + /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index e2ae82e3f9f7..5da0da59bf01 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -48,6 +48,7 @@ struct sockaddr_nl { * @nlmsg_flags: Additional flags * @nlmsg_seq: Sequence number * @nlmsg_pid: Sending process port ID + * @nlmsg_data: Message payload */ struct nlmsghdr { __u32 nlmsg_len; @@ -55,6 +56,7 @@ struct nlmsghdr { __u16 nlmsg_flags; __u32 nlmsg_seq; __u32 nlmsg_pid; + __u8 nlmsg_data[]; }; /* Flags values */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 387e430a35cc..4ddb2ed7706a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2443,19 +2443,24 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); - if (!skb) { - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - sk_error_report(NETLINK_CB(in_skb).sk); - return; - } + if (!skb) + goto err_bad_put; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - NLMSG_ERROR, payload, flags); + NLMSG_ERROR, sizeof(*errmsg), flags); + if (!rep) + goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; - unsafe_memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) - ? nlh->nlmsg_len : sizeof(*nlh), - /* Bounds checked by the skb layer. */); + errmsg->msg = *nlh; + + if (!(flags & NLM_F_CAPPED)) { + if (!nlmsg_append(skb, nlmsg_len(nlh))) + goto err_bad_put; + + memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data, + nlmsg_len(nlh)); + } if (tlvlen) netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack); @@ -2463,6 +2468,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); + + return; + +err_bad_put: + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); From 0915de8c6083e02905095cdb5850255289ebe291 Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Sat, 5 Nov 2022 17:05:04 +0800 Subject: [PATCH 2025/2093] netlink: Fix potential skb memleak in netlink_ack [ Upstream commit e69761483361f3df455bc493c99af0ef1744a14f ] Fix coverity issue 'Resource leak'. We should clean the skb resource if nlmsg_put/append failed. Fixes: 738136a0e375 ("netlink: split up copies in the ack construction") Signed-off-by: Tao Chen Link: https://lore.kernel.org/r/bff442d62c87de6299817fe1897cc5a5694ba9cc.1667638204.git.chentao.kernel@linux.alibaba.com Signed-off-by: Jakub Kicinski Stable-dep-of: d0f95894fda7 ("netlink: annotate data-races around sk->sk_err") Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4ddb2ed7706a..845ac56a3ac2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2444,7 +2444,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) - goto err_bad_put; + goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(*errmsg), flags); @@ -2472,6 +2472,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, return; err_bad_put: + nlmsg_free(skb); +err_skb: NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; sk_error_report(NETLINK_CB(in_skb).sk); } From 40d609b6ad90241150ed4217290857f54affb8ff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 3 Oct 2023 18:34:55 +0000 Subject: [PATCH 2026/2093] netlink: annotate data-races around sk->sk_err [ Upstream commit d0f95894fda7d4f895b29c1097f92d7fee278cb2 ] syzbot caught another data-race in netlink when setting sk->sk_err. Annotate all of them for good measure. BUG: KCSAN: data-race in netlink_recvmsg / netlink_recvmsg write to 0xffff8881613bb220 of 4 bytes by task 28147 on cpu 0: netlink_recvmsg+0x448/0x780 net/netlink/af_netlink.c:1994 sock_recvmsg_nosec net/socket.c:1027 [inline] sock_recvmsg net/socket.c:1049 [inline] __sys_recvfrom+0x1f4/0x2e0 net/socket.c:2229 __do_sys_recvfrom net/socket.c:2247 [inline] __se_sys_recvfrom net/socket.c:2243 [inline] __x64_sys_recvfrom+0x78/0x90 net/socket.c:2243 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881613bb220 of 4 bytes by task 28146 on cpu 1: netlink_recvmsg+0x448/0x780 net/netlink/af_netlink.c:1994 sock_recvmsg_nosec net/socket.c:1027 [inline] sock_recvmsg net/socket.c:1049 [inline] __sys_recvfrom+0x1f4/0x2e0 net/socket.c:2229 __do_sys_recvfrom net/socket.c:2247 [inline] __se_sys_recvfrom net/socket.c:2243 [inline] __x64_sys_recvfrom+0x78/0x90 net/socket.c:2243 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00000000 -> 0x00000016 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 28146 Comm: syz-executor.0 Not tainted 6.6.0-rc3-syzkaller-00055-g9ed22ae6be81 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/06/2023 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20231003183455.3410550-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 845ac56a3ac2..a572a30dfd98 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -352,7 +352,7 @@ static void netlink_overrun(struct sock *sk) if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { - sk->sk_err = ENOBUFS; + WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } @@ -1566,7 +1566,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) goto out; } - sk->sk_err = p->code; + WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; @@ -1955,7 +1955,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { - sk->sk_err = -ret; + WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } @@ -2474,7 +2474,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, err_bad_put: nlmsg_free(skb); err_skb: - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); From 07c6338acb15f78e9e6425eb8ccaa02a548b09d4 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Wed, 4 Oct 2023 21:10:41 +0200 Subject: [PATCH 2027/2093] HID: sony: remove duplicate NULL check before calling usb_free_urb() [ Upstream commit b328dd02e19cb9d3b35de4322f5363516a20ac8c ] usb_free_urb() does the NULL check itself, so there is no need to duplicate it prior to calling. Reported-by: kernel test robot Fixes: e1cd4004cde7c9 ("HID: sony: Fix a potential memory leak in sony_probe()") Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-sony.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 5b3f58e06880..f7f7252d839e 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -3074,8 +3074,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; err: - if (sc->ghl_urb) - usb_free_urb(sc->ghl_urb); + usb_free_urb(sc->ghl_urb); hid_hw_stop(hdev); return ret; From cdcc04e844a2d22d9d25cef1e8e504a174ea9f8f Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 3 Oct 2023 08:53:32 -0700 Subject: [PATCH 2028/2093] HID: intel-ish-hid: ipc: Disable and reenable ACPI GPE bit [ Upstream commit 8f02139ad9a7e6e5c05712f8c1501eebed8eacfd ] The EHL (Elkhart Lake) based platforms provide a OOB (Out of band) service, which allows to wakup device when the system is in S5 (Soft-Off state). This OOB service can be enabled/disabled from BIOS settings. When enabled, the ISH device gets PME wake capability. To enable PME wakeup, driver also needs to enable ACPI GPE bit. On resume, BIOS will clear the wakeup bit. So driver need to re-enable it in resume function to keep the next wakeup capability. But this BIOS clearing of wakeup bit doesn't decrement internal OS GPE reference count, so this reenabling on every resume will cause reference count to overflow. So first disable and reenable ACPI GPE bit using acpi_disable_gpe(). Fixes: 2e23a70edabe ("HID: intel-ish-hid: ipc: finish power flow for EHL OOB") Reported-by: Kai-Heng Feng Closes: https://lore.kernel.org/lkml/CAAd53p4=oLYiH2YbVSmrPNj1zpMcfp=Wxbasb5vhMXOWCArLCg@mail.gmail.com/T/ Tested-by: Kai-Heng Feng Signed-off-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/intel-ish-hid/ipc/pci-ish.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 55cb25038e63..710fda5f19e1 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -133,6 +133,14 @@ static int enable_gpe(struct device *dev) } wakeup = &adev->wakeup; + /* + * Call acpi_disable_gpe(), so that reference count + * gpe_event_info->runtime_count doesn't overflow. + * When gpe_event_info->runtime_count = 0, the call + * to acpi_disable_gpe() simply return. + */ + acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number); + acpi_sts = acpi_enable_gpe(wakeup->gpe_device, wakeup->gpe_number); if (ACPI_FAILURE(acpi_sts)) { dev_err(dev, "enable ose_gpe failed\n"); From ec02b892237de8a3da90182338bde043d23cec98 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Fri, 20 Jan 2023 11:15:28 +0200 Subject: [PATCH 2029/2093] intel_idle: add Emerald Rapids Xeon support [ Upstream commit 74528edfbc664f9d2c927c4e5a44f1285598ed0f ] Emerald Rapids (EMR) is the next Intel Xeon processor after Sapphire Rapids (SPR). EMR C-states are the same as SPR C-states, and we expect that EMR C-state characteristics (latency and target residency) will be the same as in SPR. Therefore, add EMR support by using SPR C-states table. Signed-off-by: Artem Bityutskiy Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/idle/intel_idle.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index cfeb24d40d37..bb3d10099ba4 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1430,6 +1430,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &idle_cpu_adl_l), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &idle_cpu_adl_n), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &idle_cpu_spr), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &idle_cpu_spr), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &idle_cpu_knl), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &idle_cpu_knl), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &idle_cpu_bxt), @@ -1862,6 +1863,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) skx_idle_state_table_update(); break; case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: spr_idle_state_table_update(); break; case INTEL_FAM6_ALDERLAKE: From c9c110ce375422aba7d219ee29046134273ccbd5 Mon Sep 17 00:00:00 2001 From: Jordan Rife Date: Tue, 3 Oct 2023 20:13:03 -0500 Subject: [PATCH 2030/2093] smb: use kernel_connect() and kernel_bind() commit cedc019b9f260facfadd20c6c490e403abf292e3 upstream. Recent changes to kernel_connect() and kernel_bind() ensure that callers are insulated from changes to the address parameter made by BPF SOCK_ADDR hooks. This patch wraps direct calls to ops->connect() and ops->bind() with kernel_connect() and kernel_bind() to ensure that SMB mounts do not see their mount address overwritten in such cases. Link: https://lore.kernel.org/netdev/9944248dba1bce861375fcce9de663934d933ba9.camel@redhat.com/ Cc: # 6.0+ Signed-off-by: Jordan Rife Acked-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/client/connect.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 57da4f23c1e4..acb8951eb757 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2901,9 +2901,9 @@ bind_socket(struct TCP_Server_Info *server) if (server->srcaddr.ss_family != AF_UNSPEC) { /* Bind to the specified local IP address */ struct socket *socket = server->ssocket; - rc = socket->ops->bind(socket, - (struct sockaddr *) &server->srcaddr, - sizeof(server->srcaddr)); + rc = kernel_bind(socket, + (struct sockaddr *) &server->srcaddr, + sizeof(server->srcaddr)); if (rc < 0) { struct sockaddr_in *saddr4; struct sockaddr_in6 *saddr6; @@ -3050,8 +3050,8 @@ generic_ip_connect(struct TCP_Server_Info *server) socket->sk->sk_sndbuf, socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo); - rc = socket->ops->connect(socket, saddr, slen, - server->noblockcnt ? O_NONBLOCK : 0); + rc = kernel_connect(socket, saddr, slen, + server->noblockcnt ? O_NONBLOCK : 0); /* * When mounting SMB root file systems, we do not want to block in * connect. Otherwise bail out and then let cifs_reconnect() perform From 485f0bac83a61878ab1214dc1957dc66956e1e88 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 19 Sep 2023 15:26:35 +0200 Subject: [PATCH 2031/2093] parisc: Fix crash with nr_cpus=1 option commit d3b3c637e4eb8d3bbe53e5692aee66add72f9851 upstream. John David Anglin reported that giving "nr_cpus=1" on the command line causes a crash, while "maxcpus=1" works. Reported-by: John David Anglin Signed-off-by: Helge Deller Cc: stable@vger.kernel.org # v5.18+ Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/smp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 7dbd92cafae3..e37ec0548730 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -443,7 +443,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) if (cpu_online(cpu)) return 0; - if (num_online_cpus() < setup_max_cpus && smp_boot_one_cpu(cpu, tidle)) + if (num_online_cpus() < nr_cpu_ids && + num_online_cpus() < setup_max_cpus && + smp_boot_one_cpu(cpu, tidle)) return -EIO; return cpu_online(cpu) ? 0 : -EIO; From f60287b2d2409b1d2c45f144191ab6ee9bd77421 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Wed, 20 Sep 2023 13:51:16 +0300 Subject: [PATCH 2032/2093] dm zoned: free dmz->ddev array in dmz_put_zoned_devices commit 9850ccd5dd88075b2b7fd28d96299d5535f58cc5 upstream. Commit 4dba12881f88 ("dm zoned: support arbitrary number of devices") made the pointers to additional zoned devices to be stored in a dynamically allocated dmz->ddev array. However, this array is not freed. Rename dmz_put_zoned_device to dmz_put_zoned_devices and fix it to free the dmz->ddev array when cleaning up zoned device information. Remove NULL assignment for all dmz->ddev elements and just free the dmz->ddev array instead. Found by Linux Verification Center (linuxtesting.org). Fixes: 4dba12881f88 ("dm zoned: support arbitrary number of devices") Cc: stable@vger.kernel.org Signed-off-by: Fedor Pchelkin Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-zoned-target.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 95b132b52f33..4abe1e2f8ad8 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -748,17 +748,16 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path, /* * Cleanup zoned device information. */ -static void dmz_put_zoned_device(struct dm_target *ti) +static void dmz_put_zoned_devices(struct dm_target *ti) { struct dmz_target *dmz = ti->private; int i; - for (i = 0; i < dmz->nr_ddevs; i++) { - if (dmz->ddev[i]) { + for (i = 0; i < dmz->nr_ddevs; i++) + if (dmz->ddev[i]) dm_put_device(ti, dmz->ddev[i]); - dmz->ddev[i] = NULL; - } - } + + kfree(dmz->ddev); } static int dmz_fixup_devices(struct dm_target *ti) @@ -948,7 +947,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) err_meta: dmz_dtr_metadata(dmz->metadata); err_dev: - dmz_put_zoned_device(ti); + dmz_put_zoned_devices(ti); err: kfree(dmz->dev); kfree(dmz); @@ -978,7 +977,7 @@ static void dmz_dtr(struct dm_target *ti) bioset_exit(&dmz->bio_set); - dmz_put_zoned_device(ti); + dmz_put_zoned_devices(ti); mutex_destroy(&dmz->chunk_lock); From 9c480fb41aa4c69aa3ba28b57aca92f35884e340 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 4 Oct 2023 21:17:49 +0300 Subject: [PATCH 2033/2093] RDMA/core: Require admin capabilities to set system parameters commit c38d23a54445f9a8aa6831fafc9af0496ba02f9e upstream. Like any other set command, require admin permissions to do it. Cc: stable@vger.kernel.org Fixes: 2b34c5580226 ("RDMA/core: Add command to set ib_core device net namspace sharing mode") Link: https://lore.kernel.org/r/75d329fdd7381b52cbdf87910bef16c9965abb1f.1696443438.git.leon@kernel.org Reviewed-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/nldev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 222733a83ddb..1adf20198afd 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2501,6 +2501,7 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { }, [RDMA_NLDEV_CMD_SYS_SET] = { .doit = nldev_set_sys_set_doit, + .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_STAT_SET] = { .doit = nldev_stat_set_doit, From 315ae630502cf79731aa9c3ac6d499a5da3d5502 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 8 Sep 2023 10:03:50 +0300 Subject: [PATCH 2034/2093] of: dynamic: Fix potential memory leak in of_changeset_action() commit 55e95bfccf6db8d26a66c46e1de50d53c59a6774 upstream. Smatch complains that the error path where "action" is invalid leaks the "ce" allocation: drivers/of/dynamic.c:935 of_changeset_action() warn: possible memory leak of 'ce' Fix this by doing the validation before the allocation. Note that there is not any actual problem with upstream kernels. All callers of of_changeset_action() are static inlines with fixed action values. Fixes: 914d9d831e61 ("of: dynamic: Refactor action prints to not use "%pOF" inside devtree_lock") Reported-by: kernel test robot Closes: https://lore.kernel.org/r/202309011059.EOdr4im9-lkp@intel.com/ Signed-off-by: Dan Carpenter Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/7dfaf999-30ad-491c-9615-fb1138db121c@moroto.mountain Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/dynamic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 95501b77ef31..0fbf331a748f 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -902,13 +902,13 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action, { struct of_changeset_entry *ce; + if (WARN_ON(action >= ARRAY_SIZE(action_names))) + return -EINVAL; + ce = kzalloc(sizeof(*ce), GFP_KERNEL); if (!ce) return -ENOMEM; - if (WARN_ON(action >= ARRAY_SIZE(action_names))) - return -EINVAL; - /* get a reference to the node */ ce->action = action; ce->np = of_node_get(np); From 7e47a8419da69d9071bb3ee399fff73fcc10f301 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 23 Sep 2023 07:55:56 +0200 Subject: [PATCH 2035/2093] IB/mlx4: Fix the size of a buffer in add_port_entries() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit d7f393430a17c2bfcdf805462a5aa80be4285b27 upstream. In order to be sure that 'buff' is never truncated, its size should be 12, not 11. When building with W=1, this fixes the following warnings: drivers/infiniband/hw/mlx4/sysfs.c: In function ‘add_port_entries’: drivers/infiniband/hw/mlx4/sysfs.c:268:34: error: ‘sprintf’ may write a terminating nul past the end of the destination [-Werror=format-overflow=] 268 | sprintf(buff, "%d", i); | ^ drivers/infiniband/hw/mlx4/sysfs.c:268:17: note: ‘sprintf’ output between 2 and 12 bytes into a destination of size 11 268 | sprintf(buff, "%d", i); | ^~~~~~~~~~~~~~~~~~~~~~ drivers/infiniband/hw/mlx4/sysfs.c:286:34: error: ‘sprintf’ may write a terminating nul past the end of the destination [-Werror=format-overflow=] 286 | sprintf(buff, "%d", i); | ^ drivers/infiniband/hw/mlx4/sysfs.c:286:17: note: ‘sprintf’ output between 2 and 12 bytes into a destination of size 11 286 | sprintf(buff, "%d", i); | ^~~~~~~~~~~~~~~~~~~~~~ Fixes: c1e7e466120b ("IB/mlx4: Add iov directory in sysfs under the ib device") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/0bb1443eb47308bc9be30232cc23004c4d4cf43e.1695448530.git.christophe.jaillet@wanadoo.fr Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx4/sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c index 24ee79aa2122..88f534cf690e 100644 --- a/drivers/infiniband/hw/mlx4/sysfs.c +++ b/drivers/infiniband/hw/mlx4/sysfs.c @@ -223,7 +223,7 @@ void del_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num, static int add_port_entries(struct mlx4_ib_dev *device, int port_num) { int i; - char buff[11]; + char buff[12]; struct mlx4_ib_iov_port *port = NULL; int ret = 0 ; struct ib_port_attr attr; From d09e467491b29dfa9736a22458f36c97a6838ba2 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 3 Oct 2023 09:39:26 +0200 Subject: [PATCH 2036/2093] gpio: aspeed: fix the GPIO number passed to pinctrl_gpio_set_config() commit f9315f17bf778cb8079a29639419fcc8a41a3c84 upstream. pinctrl_gpio_set_config() expects the GPIO number from the global GPIO numberspace, not the controller-relative offset, which needs to be added to the chip base. Fixes: 5ae4cb94b313 ("gpio: aspeed: Add debounce support") Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Reviewed-by: Andrew Jeffery Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpio-aspeed.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 318a7d95a1a8..42d3e1cf7352 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -963,7 +963,7 @@ static int aspeed_gpio_set_config(struct gpio_chip *chip, unsigned int offset, else if (param == PIN_CONFIG_BIAS_DISABLE || param == PIN_CONFIG_BIAS_PULL_DOWN || param == PIN_CONFIG_DRIVE_STRENGTH) - return pinctrl_gpio_set_config(offset, config); + return pinctrl_gpio_set_config(chip->base + offset, config); else if (param == PIN_CONFIG_DRIVE_OPEN_DRAIN || param == PIN_CONFIG_DRIVE_OPEN_SOURCE) /* Return -ENOTSUPP to trigger emulation, as per datasheet */ From 52b0bb7139c995296dd6d05ab86d369d81b6cfbc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duje=20Mihanovi=C4=87?= Date: Fri, 29 Sep 2023 17:41:57 +0200 Subject: [PATCH 2037/2093] gpio: pxa: disable pinctrl calls for MMP_GPIO MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f0575116507b981e6a810e78ce3c9040395b958b upstream. Similarly to PXA3xx and MMP2, pinctrl-single isn't capable of setting pin direction on MMP either. Fixes: a770d946371e ("gpio: pxa: add pin control gpio direction and request") Signed-off-by: Duje Mihanović Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpio-pxa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index 1198ab0305d0..b90357774dc0 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -243,6 +243,7 @@ static bool pxa_gpio_has_pinctrl(void) switch (gpio_type) { case PXA3XX_GPIO: case MMP2_GPIO: + case MMP_GPIO: return false; default: From 39f701870114070b60a465141b5df4e5155f29ca Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 27 Sep 2023 12:05:11 +0300 Subject: [PATCH 2038/2093] RDMA/cma: Initialize ib_sa_multicast structure to 0 when join commit e0fe97efdb00f0f32b038a4836406a82886aec9c upstream. Initialize the structure to 0 so that it's fields won't have random values. For example fields like rec.traffic_class (as well as rec.flow_label and rec.sl) is used to generate the user AH through: cma_iboe_join_multicast cma_make_mc_event ib_init_ah_from_mcmember And a random traffic_class causes a random IP DSCP in RoCEv2. Fixes: b5de0c60cc30 ("RDMA/cma: Fix use after free race in roce multicast join") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/20230927090511.603595-1-markzhang@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/cma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 4632b1833381..0773ca7ace24 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4936,7 +4936,7 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; - struct ib_sa_multicast ib; + struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; From 233229fa577a036c7b76c0763d38359531a01b38 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 11 Sep 2023 15:18:06 +0300 Subject: [PATCH 2039/2093] RDMA/cma: Fix truncation compilation warning in make_cma_ports MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 18126c767658ae8a831257c6cb7776c5ba5e7249 upstream. The following compilation error is false alarm as RDMA devices don't have such large amount of ports to actually cause to format truncation. drivers/infiniband/core/cma_configfs.c: In function ‘make_cma_ports’: drivers/infiniband/core/cma_configfs.c:223:57: error: ‘snprintf’ output may be truncated before the last format character [-Werror=format-truncation=] 223 | snprintf(port_str, sizeof(port_str), "%u", i + 1); | ^ drivers/infiniband/core/cma_configfs.c:223:17: note: ‘snprintf’ output between 2 and 11 bytes into a destination of size 10 223 | snprintf(port_str, sizeof(port_str), "%u", i + 1); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors make[5]: *** [scripts/Makefile.build:243: drivers/infiniband/core/cma_configfs.o] Error 1 Fixes: 045959db65c6 ("IB/cma: Add configfs for rdma_cm") Link: https://lore.kernel.org/r/a7e3b347ee134167fa6a3787c56ef231a04bc8c2.1694434639.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/cma_configfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c index 7b68b3ea979f..f2fb2d8a6597 100644 --- a/drivers/infiniband/core/cma_configfs.c +++ b/drivers/infiniband/core/cma_configfs.c @@ -217,7 +217,7 @@ static int make_cma_ports(struct cma_dev_group *cma_dev_group, return -ENOMEM; for (i = 0; i < ports_num; i++) { - char port_str[10]; + char port_str[11]; ports[i].port_num = i + 1; snprintf(port_str, sizeof(port_str), "%u", i + 1); From c54204d7960fab7009f822ca11adc2dd943a212f Mon Sep 17 00:00:00 2001 From: Konstantin Meskhidze Date: Tue, 5 Sep 2023 18:32:58 +0800 Subject: [PATCH 2040/2093] RDMA/uverbs: Fix typo of sizeof argument commit c489800e0d48097fc6afebd862c6afa039110a36 upstream. Since size of 'hdr' pointer and '*hdr' structure is equal on 64-bit machines issue probably didn't cause any wrong behavior. But anyway, fixing of typo is required. Fixes: da0f60df7bd5 ("RDMA/uverbs: Prohibit write() calls with too small buffers") Co-developed-by: Ivanov Mikhail Signed-off-by: Ivanov Mikhail Signed-off-by: Konstantin Meskhidze Link: https://lore.kernel.org/r/20230905103258.1738246-1-konstantin.meskhidze@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/uverbs_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index fa937cd26821..6fe825800494 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -535,7 +535,7 @@ static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr, if (hdr->in_words * 4 != count) return -EINVAL; - if (count < method_elm->req_size + sizeof(hdr)) { + if (count < method_elm->req_size + sizeof(*hdr)) { /* * rdma-core v18 and v19 have a bug where they send DESTROY_CQ * with a 16 byte write instead of 24. Old kernels didn't From 2b298f9181582270d5e95774e5a6c7a7fb5b1206 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 23 Aug 2023 13:57:27 -0700 Subject: [PATCH 2041/2093] RDMA/srp: Do not call scsi_done() from srp_abort() commit e193b7955dfad68035b983a0011f4ef3590c85eb upstream. After scmd_eh_abort_handler() has called the SCSI LLD eh_abort_handler callback, it performs one of the following actions: * Call scsi_queue_insert(). * Call scsi_finish_command(). * Call scsi_eh_scmd_add(). Hence, SCSI abort handlers must not call scsi_done(). Otherwise all the above actions would trigger a use-after-free. Hence remove the scsi_done() call from srp_abort(). Keep the srp_free_req() call before returning SUCCESS because we may not see the command again if SUCCESS is returned. Cc: Bob Pearson Cc: Shinichiro Kawasaki Fixes: d8536670916a ("IB/srp: Avoid having aborted requests hang") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230823205727.505681-1-bvanassche@acm.org Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/ulp/srp/ib_srp.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index a7580c4855fe..c4dcef76e964 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -2789,7 +2789,6 @@ static int srp_abort(struct scsi_cmnd *scmnd) u32 tag; u16 ch_idx; struct srp_rdma_ch *ch; - int ret; shost_printk(KERN_ERR, target->scsi_host, "SRP abort called\n"); @@ -2803,19 +2802,14 @@ static int srp_abort(struct scsi_cmnd *scmnd) shost_printk(KERN_ERR, target->scsi_host, "Sending SRP abort for tag %#x\n", tag); if (srp_send_tsk_mgmt(ch, tag, scmnd->device->lun, - SRP_TSK_ABORT_TASK, NULL) == 0) - ret = SUCCESS; - else if (target->rport->state == SRP_RPORT_LOST) - ret = FAST_IO_FAIL; - else - ret = FAILED; - if (ret == SUCCESS) { + SRP_TSK_ABORT_TASK, NULL) == 0) { srp_free_req(ch, req, scmnd, 0); - scmnd->result = DID_ABORT << 16; - scsi_done(scmnd); + return SUCCESS; } + if (target->rport->state == SRP_RPORT_LOST) + return FAST_IO_FAIL; - return ret; + return FAILED; } static int srp_reset_device(struct scsi_cmnd *scmnd) From 5cf38e638e5d01b68f9133968a85e8b3fd1ecf2f Mon Sep 17 00:00:00 2001 From: Bernard Metzler Date: Tue, 5 Sep 2023 16:58:22 +0200 Subject: [PATCH 2042/2093] RDMA/siw: Fix connection failure handling commit 53a3f777049771496f791504e7dc8ef017cba590 upstream. In case immediate MPA request processing fails, the newly created endpoint unlinks the listening endpoint and is ready to be dropped. This special case was not handled correctly by the code handling the later TCP socket close, causing a NULL dereference crash in siw_cm_work_handler() when dereferencing a NULL listener. We now also cancel the useless MPA timeout, if immediate MPA request processing fails. This patch furthermore simplifies MPA processing in general: Scheduling a useless TCP socket read in sk_data_ready() upcall is now surpressed, if the socket is already moved out of TCP_ESTABLISHED state. Fixes: 6c52fdc244b5 ("rdma/siw: connection management") Signed-off-by: Bernard Metzler Link: https://lore.kernel.org/r/20230905145822.446263-1-bmt@zurich.ibm.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/sw/siw/siw_cm.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 552d8271e423..dc679c34ceef 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -973,6 +973,7 @@ static void siw_accept_newconn(struct siw_cep *cep) siw_cep_put(cep); new_cep->listen_cep = NULL; if (rv) { + siw_cancel_mpatimer(new_cep); siw_cep_set_free(new_cep); goto error; } @@ -1097,9 +1098,12 @@ static void siw_cm_work_handler(struct work_struct *w) /* * Socket close before MPA request received. */ - siw_dbg_cep(cep, "no mpareq: drop listener\n"); - siw_cep_put(cep->listen_cep); - cep->listen_cep = NULL; + if (cep->listen_cep) { + siw_dbg_cep(cep, + "no mpareq: drop listener\n"); + siw_cep_put(cep->listen_cep); + cep->listen_cep = NULL; + } } } release_cep = 1; @@ -1222,7 +1226,11 @@ static void siw_cm_llp_data_ready(struct sock *sk) if (!cep) goto out; - siw_dbg_cep(cep, "state: %d\n", cep->state); + siw_dbg_cep(cep, "cep state: %d, socket state %d\n", + cep->state, sk->sk_state); + + if (sk->sk_state != TCP_ESTABLISHED) + goto out; switch (cep->state) { case SIW_EPSTATE_RDMA_MODE: From 26eb1307c704c56bdd24f5c616fa99812cca085e Mon Sep 17 00:00:00 2001 From: Hamdan Igbaria Date: Wed, 20 Sep 2023 13:01:55 +0300 Subject: [PATCH 2043/2093] RDMA/mlx5: Fix mutex unlocking on error flow for steering anchor creation commit 2fad8f06a582cd431d398a0b3f9be21d069603ab upstream. The mutex was not unlocked on some of the error flows. Moved the unlock location to include all the error flow scenarios. Fixes: e1f4a52ac171 ("RDMA/mlx5: Create an indirect flow table for steering anchor") Reviewed-by: Mark Bloch Signed-off-by: Hamdan Igbaria Link: https://lore.kernel.org/r/1244a69d783da997c0af0b827c622eb00495492e.1695203958.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx5/fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 5a13d902b064..1022cebd0a46 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -2471,8 +2471,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)( mlx5_steering_anchor_destroy_res(ft_prio); put_flow_table: put_flow_table(dev, ft_prio, true); - mutex_unlock(&dev->flow_db->lock); free_obj: + mutex_unlock(&dev->flow_db->lock); kfree(obj); return err; From 76b6a980e85f4aac5c69cec04001504b126c31e0 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 20 Sep 2023 13:01:56 +0300 Subject: [PATCH 2044/2093] RDMA/mlx5: Fix NULL string error commit dab994bcc609a172bfdab15a0d4cb7e50e8b5458 upstream. checkpath is complaining about NULL string, change it to 'Unknown'. Fixes: 37aa5c36aa70 ("IB/mlx5: Add UARs write-combining and non-cached mapping") Signed-off-by: Shay Drory Link: https://lore.kernel.org/r/8638e5c14fadbde5fa9961874feae917073af920.1695203958.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx5/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 3178df55c4d8..0baf3b5518b4 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2074,7 +2074,7 @@ static inline char *mmap_cmd2str(enum mlx5_ib_mmap_cmd cmd) case MLX5_IB_MMAP_DEVICE_MEM: return "Device Memory"; default: - return NULL; + return "Unknown"; } } From 64301a9354626d1afb23a72720a99190d9157358 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 28 Jul 2023 16:09:26 -0500 Subject: [PATCH 2045/2093] x86/sev: Use the GHCB protocol when available for SNP CPUID requests commit 6bc6f7d9d7ac3cdbe9e8b0495538b4a0cc11f032 upstream. SNP retrieves the majority of CPUID information from the SNP CPUID page. But there are times when that information needs to be supplemented by the hypervisor, for example, obtaining the initial APIC ID of the vCPU from leaf 1. The current implementation uses the MSR protocol to retrieve the data from the hypervisor, even when a GHCB exists. The problem arises when an NMI arrives on return from the VMGEXIT. The NMI will be immediately serviced and may generate a #VC requiring communication with the hypervisor. Since a GHCB exists in this case, it will be used. As part of using the GHCB, the #VC handler will write the GHCB physical address into the GHCB MSR and the #VC will be handled. When the NMI completes, processing resumes at the site of the VMGEXIT which is expecting to read the GHCB MSR and find a CPUID MSR protocol response. Since the NMI handling overwrote the GHCB MSR response, the guest will see an invalid reply from the hypervisor and self-terminate. Fix this problem by using the GHCB when it is available. Any NMI received is properly handled because the GHCB contents are copied into a backup page and restored on NMI exit, thus preserving the active GHCB request or result. [ bp: Touchups. ] Fixes: ee0bfa08a345 ("x86/compressed/64: Add support for SEV-SNP CPUID table in #VC handlers") Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/a5856fa1ebe3879de91a8f6298b6bbd901c61881.1690578565.git.thomas.lendacky@amd.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/sev-shared.c | 69 ++++++++++++++++++++++++++++-------- 1 file changed, 55 insertions(+), 14 deletions(-) diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 3a5b0c9c4fcc..7dce812ce253 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -253,7 +253,7 @@ static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg) return 0; } -static int sev_cpuid_hv(struct cpuid_leaf *leaf) +static int __sev_cpuid_hv_msr(struct cpuid_leaf *leaf) { int ret; @@ -276,6 +276,45 @@ static int sev_cpuid_hv(struct cpuid_leaf *leaf) return ret; } +static int __sev_cpuid_hv_ghcb(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +{ + u32 cr4 = native_read_cr4(); + int ret; + + ghcb_set_rax(ghcb, leaf->fn); + ghcb_set_rcx(ghcb, leaf->subfn); + + if (cr4 & X86_CR4_OSXSAVE) + /* Safe to read xcr0 */ + ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK)); + else + /* xgetbv will cause #UD - use reset value for xcr0 */ + ghcb_set_xcr0(ghcb, 1); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && + ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + leaf->eax = ghcb->save.rax; + leaf->ebx = ghcb->save.rbx; + leaf->ecx = ghcb->save.rcx; + leaf->edx = ghcb->save.rdx; + + return ES_OK; +} + +static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +{ + return ghcb ? __sev_cpuid_hv_ghcb(ghcb, ctxt, leaf) + : __sev_cpuid_hv_msr(leaf); +} + /* * This may be called early while still running on the initial identity * mapping. Use RIP-relative addressing to obtain the correct address @@ -385,19 +424,20 @@ snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) return false; } -static void snp_cpuid_hv(struct cpuid_leaf *leaf) +static void snp_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { - if (sev_cpuid_hv(leaf)) + if (sev_cpuid_hv(ghcb, ctxt, leaf)) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); } -static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) +static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + struct cpuid_leaf *leaf) { struct cpuid_leaf leaf_hv = *leaf; switch (leaf->fn) { case 0x1: - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* initial APIC ID */ leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0)); @@ -416,7 +456,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) break; case 0xB: leaf_hv.subfn = 0; - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* extended APIC ID */ leaf->edx = leaf_hv.edx; @@ -464,7 +504,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) } break; case 0x8000001E: - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* extended APIC ID */ leaf->eax = leaf_hv.eax; @@ -485,7 +525,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct cpuid_leaf *leaf) +static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -519,7 +559,7 @@ static int snp_cpuid(struct cpuid_leaf *leaf) return 0; } - return snp_cpuid_postprocess(leaf); + return snp_cpuid_postprocess(ghcb, ctxt, leaf); } /* @@ -541,14 +581,14 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) leaf.fn = fn; leaf.subfn = subfn; - ret = snp_cpuid(&leaf); + ret = snp_cpuid(NULL, NULL, &leaf); if (!ret) goto cpuid_done; if (ret != -EOPNOTSUPP) goto fail; - if (sev_cpuid_hv(&leaf)) + if (__sev_cpuid_hv_msr(&leaf)) goto fail; cpuid_done: @@ -845,14 +885,15 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static int vc_handle_cpuid_snp(struct pt_regs *regs) +static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { + struct pt_regs *regs = ctxt->regs; struct cpuid_leaf leaf; int ret; leaf.fn = regs->ax; leaf.subfn = regs->cx; - ret = snp_cpuid(&leaf); + ret = snp_cpuid(ghcb, ctxt, &leaf); if (!ret) { regs->ax = leaf.eax; regs->bx = leaf.ebx; @@ -871,7 +912,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb, enum es_result ret; int snp_cpuid_ret; - snp_cpuid_ret = vc_handle_cpuid_snp(regs); + snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt); if (!snp_cpuid_ret) return ES_OK; if (snp_cpuid_ret != -EOPNOTSUPP) From a2ca5fd3dbcc665e1169044fa0c9e3eba779202b Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 4 Oct 2023 18:25:01 +0900 Subject: [PATCH 2046/2093] ksmbd: fix race condition between session lookup and expire commit 53ff5cf89142b978b1a5ca8dc4d4425e6a09745f upstream. Thread A + Thread B ksmbd_session_lookup | smb2_sess_setup sess = xa_load | | | xa_erase(&conn->sessions, sess->id); | | ksmbd_session_destroy(sess) --> kfree(sess) | // UAF! | sess->last_active = jiffies | + This patch add rwsem to fix race condition between ksmbd_session_lookup and ksmbd_expire_session. Reported-by: luosili Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/connection.c | 2 ++ fs/smb/server/connection.h | 1 + fs/smb/server/mgmt/user_session.c | 10 +++++++--- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index e1d2be19cddf..ff97cad8d5b4 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -84,6 +84,8 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) spin_lock_init(&conn->llist_lock); INIT_LIST_HEAD(&conn->lock_list); + init_rwsem(&conn->session_lock); + down_write(&conn_list_lock); list_add(&conn->conns_list, &conn_list); up_write(&conn_list_lock); diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index ad8dfaa48ffb..335fdd714d59 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -50,6 +50,7 @@ struct ksmbd_conn { struct nls_table *local_nls; struct unicode_map *um; struct list_head conns_list; + struct rw_semaphore session_lock; /* smb session 1 per user */ struct xarray sessions; unsigned long last_active; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index ea4b56d570fb..cf6621e21ba3 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -183,7 +183,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) unsigned long id; struct ksmbd_session *sess; - down_write(&sessions_table_lock); + down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { if (sess->state != SMB2_SESSION_VALID || time_after(jiffies, @@ -194,7 +194,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) continue; } } - up_write(&sessions_table_lock); + up_write(&conn->session_lock); } int ksmbd_session_register(struct ksmbd_conn *conn, @@ -236,7 +236,9 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) } } } + up_write(&sessions_table_lock); + down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { unsigned long chann_id; struct channel *chann; @@ -253,7 +255,7 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) ksmbd_session_destroy(sess); } } - up_write(&sessions_table_lock); + up_write(&conn->session_lock); } struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, @@ -261,9 +263,11 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, { struct ksmbd_session *sess; + down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); if (sess) sess->last_active = jiffies; + up_read(&conn->session_lock); return sess; } From 8226ffc759ea59f10067b9acdf7f94bae1c69930 Mon Sep 17 00:00:00 2001 From: luosili Date: Wed, 4 Oct 2023 18:29:36 +0900 Subject: [PATCH 2047/2093] ksmbd: fix uaf in smb20_oplock_break_ack commit c69813471a1ec081a0b9bf0c6bd7e8afd818afce upstream. drop reference after use opinfo. Signed-off-by: luosili Signed-off-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/smb/server/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f6fd5cf976a5..683152007566 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8128,10 +8128,10 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) goto err_out; } - opinfo_put(opinfo); - ksmbd_fd_put(work, fp); opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); + opinfo_put(opinfo); + ksmbd_fd_put(work, fp); rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; From edeccce85cbee759d06c25bd3c812799c8a6ef4c Mon Sep 17 00:00:00 2001 From: John David Anglin Date: Tue, 19 Sep 2023 17:51:40 +0000 Subject: [PATCH 2048/2093] parisc: Restore __ldcw_align for PA-RISC 2.0 processors commit 914988e099fc658436fbd7b8f240160c352b6552 upstream. Back in 2005, Kyle McMartin removed the 16-byte alignment for ldcw semaphores on PA 2.0 machines (CONFIG_PA20). This broke spinlocks on pre PA8800 processors. The main symptom was random faults in mmap'd memory (e.g., gcc compilations, etc). Unfortunately, the errata for this ldcw change is lost. The issue is the 16-byte alignment required for ldcw semaphore instructions can only be reduced to natural alignment when the ldcw operation can be handled coherently in cache. Only PA8800 and PA8900 processors actually support doing the operation in cache. Aligning the spinlock dynamically adds two integer instructions to each spinlock. Tested on rp3440, c8000 and a500. Signed-off-by: John David Anglin Link: https://lore.kernel.org/linux-parisc/6b332788-2227-127f-ba6d-55e99ecf4ed8@bell.net/T/#t Link: https://lore.kernel.org/linux-parisc/20050609050702.GB4641@roadwarrior.mcmartin.ca/ Cc: stable@vger.kernel.org Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/asm/ldcw.h | 36 +++++++++++++----------- arch/parisc/include/asm/spinlock_types.h | 5 ---- 2 files changed, 20 insertions(+), 21 deletions(-) diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index 6d28b5514699..10a061d6899c 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -2,14 +2,28 @@ #ifndef __PARISC_LDCW_H #define __PARISC_LDCW_H -#ifndef CONFIG_PA20 /* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data, and GCC only guarantees 8-byte alignment for stack locals, we can't be assured of 16-byte alignment for atomic lock data even if we specify "__attribute ((aligned(16)))" in the type declaration. So, we use a struct containing an array of four ints for the atomic lock type and dynamically select the 16-byte aligned int from the array - for the semaphore. */ + for the semaphore. */ + +/* From: "Jim Hull" + I've attached a summary of the change, but basically, for PA 2.0, as + long as the ",CO" (coherent operation) completer is implemented, then the + 16-byte alignment requirement for ldcw and ldcd is relaxed, and instead + they only require "natural" alignment (4-byte for ldcw, 8-byte for + ldcd). + + Although the cache control hint is accepted by all PA 2.0 processors, + it is only implemented on PA8800/PA8900 CPUs. Prior PA8X00 CPUs still + require 16-byte alignment. If the address is unaligned, the operation + of the instruction is undefined. The ldcw instruction does not generate + unaligned data reference traps so misaligned accesses are not detected. + This hid the problem for years. So, restore the 16-byte alignment dropped + by Kyle McMartin in "Remove __ldcw_align for PA-RISC 2.0 processors". */ #define __PA_LDCW_ALIGNMENT 16 #define __PA_LDCW_ALIGN_ORDER 4 @@ -19,22 +33,12 @@ & ~(__PA_LDCW_ALIGNMENT - 1); \ (volatile unsigned int *) __ret; \ }) -#define __LDCW "ldcw" -#else /*CONFIG_PA20*/ -/* From: "Jim Hull" - I've attached a summary of the change, but basically, for PA 2.0, as - long as the ",CO" (coherent operation) completer is specified, then the - 16-byte alignment requirement for ldcw and ldcd is relaxed, and instead - they only require "natural" alignment (4-byte for ldcw, 8-byte for - ldcd). */ - -#define __PA_LDCW_ALIGNMENT 4 -#define __PA_LDCW_ALIGN_ORDER 2 -#define __ldcw_align(a) (&(a)->slock) +#ifdef CONFIG_PA20 #define __LDCW "ldcw,co" - -#endif /*!CONFIG_PA20*/ +#else +#define __LDCW "ldcw" +#endif /* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. We don't explicitly expose that "*a" may be written as reload diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index ca39ee350c3f..35c5086b74d7 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -3,13 +3,8 @@ #define __ASM_SPINLOCK_TYPES_H typedef struct { -#ifdef CONFIG_PA20 - volatile unsigned int slock; -# define __ARCH_SPIN_LOCK_UNLOCKED { 1 } -#else volatile unsigned int lock[4]; # define __ARCH_SPIN_LOCK_UNLOCKED { { 1, 1, 1, 1 } } -#endif } arch_spinlock_t; From fd32f1eee6c0cdae93533c141cb2e08377e356de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 May 2023 15:46:46 +0000 Subject: [PATCH 2049/2093] ipv6: remove nexthop_fib6_nh_bh() commit ef1148d4487438a3408d6face2a8360d91b4af70 upstream. After blamed commit, nexthop_fib6_nh_bh() and nexthop_fib6_nh() are the same. Delete nexthop_fib6_nh_bh(), and convert /proc/net/ipv6_route to standard rcu to avoid this splat: [ 5723.180080] WARNING: suspicious RCU usage [ 5723.180083] ----------------------------- [ 5723.180084] include/net/nexthop.h:516 suspicious rcu_dereference_check() usage! [ 5723.180086] other info that might help us debug this: [ 5723.180087] rcu_scheduler_active = 2, debug_locks = 1 [ 5723.180089] 2 locks held by cat/55856: [ 5723.180091] #0: ffff9440a582afa8 (&p->lock){+.+.}-{3:3}, at: seq_read_iter (fs/seq_file.c:188) [ 5723.180100] #1: ffffffffaac07040 (rcu_read_lock_bh){....}-{1:2}, at: rcu_lock_acquire (include/linux/rcupdate.h:326) [ 5723.180109] stack backtrace: [ 5723.180111] CPU: 14 PID: 55856 Comm: cat Tainted: G S I 6.3.0-dbx-DEV #528 [ 5723.180115] Call Trace: [ 5723.180117] [ 5723.180119] dump_stack_lvl (lib/dump_stack.c:107) [ 5723.180124] dump_stack (lib/dump_stack.c:114) [ 5723.180126] lockdep_rcu_suspicious (include/linux/context_tracking.h:122) [ 5723.180132] ipv6_route_seq_show (include/net/nexthop.h:?) [ 5723.180135] ? ipv6_route_seq_next (net/ipv6/ip6_fib.c:2605) [ 5723.180140] seq_read_iter (fs/seq_file.c:272) [ 5723.180145] seq_read (fs/seq_file.c:163) [ 5723.180151] proc_reg_read (fs/proc/inode.c:316 fs/proc/inode.c:328) [ 5723.180155] vfs_read (fs/read_write.c:468) [ 5723.180160] ? up_read (kernel/locking/rwsem.c:1617) [ 5723.180164] ksys_read (fs/read_write.c:613) [ 5723.180168] __x64_sys_read (fs/read_write.c:621) [ 5723.180170] do_syscall_64 (arch/x86/entry/common.c:?) [ 5723.180174] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [ 5723.180177] RIP: 0033:0x7fa455677d2a Fixes: 09eed1192cec ("neighbour: switch to standard rcu, instead of rcu_bh") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230510154646.370659-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/nexthop.h | 23 ----------------------- net/ipv6/ip6_fib.c | 16 ++++++++-------- 2 files changed, 8 insertions(+), 31 deletions(-) diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 9fa291a04621..2b12725de9c0 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -497,29 +497,6 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } -/* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock(), or RTNL. - */ -static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) -{ - struct nh_info *nhi; - - if (nh->is_group) { - struct nh_group *nh_grp; - - nh_grp = rcu_dereference_rtnl(nh->nh_grp); - nh = nexthop_mpath_select(nh_grp, 0); - if (!nh) - return NULL; - } - - nhi = rcu_dereference_rtnl(nh->nh_info); - if (nhi->family == AF_INET6) - return &nhi->fib6_nh; - - return NULL; -} - static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 413f66781e50..eb6640f9a792 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2492,7 +2492,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh_bh(rt->nh); + fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); @@ -2557,14 +2557,14 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; - node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { - node = rcu_dereference_bh( + node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); @@ -2594,7 +2594,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); + n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; @@ -2620,12 +2620,12 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU_BH) + __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; - rcu_read_lock_bh(); + rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; @@ -2646,7 +2646,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) - __releases(RCU_BH) + __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; @@ -2654,7 +2654,7 @@ static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); - rcu_read_unlock_bh(); + rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) From 5aaa45025f9f567f00d516ddec0e575e88130737 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 15 Jul 2023 18:36:05 +0300 Subject: [PATCH 2050/2093] vrf: Fix lockdep splat in output path commit 2033ab90380d46e0e9f0520fd6776a73d107fd95 upstream. Cited commit converted the neighbour code to use the standard RCU variant instead of the RCU-bh variant, but the VRF code still uses rcu_read_lock_bh() / rcu_read_unlock_bh() around the neighbour lookup code in its IPv4 and IPv6 output paths, resulting in lockdep splats [1][2]. Can be reproduced using [3]. Fix by switching to rcu_read_lock() / rcu_read_unlock(). [1] ============================= WARNING: suspicious RCU usage 6.5.0-rc1-custom-g9c099e6dbf98 #403 Not tainted ----------------------------- include/net/neighbour.h:302 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by ping/183: #0: ffff888105ea1d80 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0xc6c/0x33c0 #1: ffffffff85b46820 (rcu_read_lock_bh){....}-{1:2}, at: vrf_output+0x2e3/0x2030 stack backtrace: CPU: 0 PID: 183 Comm: ping Not tainted 6.5.0-rc1-custom-g9c099e6dbf98 #403 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc37 04/01/2014 Call Trace: dump_stack_lvl+0xc1/0xf0 lockdep_rcu_suspicious+0x211/0x3b0 vrf_output+0x1380/0x2030 ip_push_pending_frames+0x125/0x2a0 raw_sendmsg+0x200d/0x33c0 inet_sendmsg+0xa2/0xe0 __sys_sendto+0x2aa/0x420 __x64_sys_sendto+0xe5/0x1c0 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [2] ============================= WARNING: suspicious RCU usage 6.5.0-rc1-custom-g9c099e6dbf98 #403 Not tainted ----------------------------- include/net/neighbour.h:302 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 2 locks held by ping6/182: #0: ffff888114b63000 (sk_lock-AF_INET6){+.+.}-{0:0}, at: rawv6_sendmsg+0x1602/0x3e50 #1: ffffffff85b46820 (rcu_read_lock_bh){....}-{1:2}, at: vrf_output6+0xe9/0x1310 stack backtrace: CPU: 0 PID: 182 Comm: ping6 Not tainted 6.5.0-rc1-custom-g9c099e6dbf98 #403 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc37 04/01/2014 Call Trace: dump_stack_lvl+0xc1/0xf0 lockdep_rcu_suspicious+0x211/0x3b0 vrf_output6+0xd32/0x1310 ip6_local_out+0xb4/0x1a0 ip6_send_skb+0xbc/0x340 ip6_push_pending_frames+0xe5/0x110 rawv6_sendmsg+0x2e6e/0x3e50 inet_sendmsg+0xa2/0xe0 __sys_sendto+0x2aa/0x420 __x64_sys_sendto+0xe5/0x1c0 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [3] #!/bin/bash ip link add name vrf-red up numtxqueues 2 type vrf table 10 ip link add name swp1 up master vrf-red type dummy ip address add 192.0.2.1/24 dev swp1 ip address add 2001:db8:1::1/64 dev swp1 ip neigh add 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm dev swp1 ip neigh add 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm dev swp1 ip vrf exec vrf-red ping 192.0.2.2 -c 1 &> /dev/null ip vrf exec vrf-red ping6 2001:db8:1::2 -c 1 &> /dev/null Fixes: 09eed1192cec ("neighbour: switch to standard rcu, instead of rcu_bh") Reported-by: Naresh Kamboju Link: https://lore.kernel.org/netdev/CA+G9fYtEr-=GbcXNDYo3XOkwR+uYgehVoDjsP0pFLUpZ_AZcyg@mail.gmail.com/ Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230715153605.4068066-1-idosch@nvidia.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/vrf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index f6dcec66f0a4..208df4d41939 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -664,7 +664,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - rcu_read_lock_bh(); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) @@ -672,10 +672,10 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -889,7 +889,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s } } - rcu_read_lock_bh(); + rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { @@ -898,11 +898,11 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } From 6d05a1a7a484f1ff1459c4f5b853d94f839b26b0 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 12 Dec 2022 21:14:17 +0100 Subject: [PATCH 2051/2093] btrfs: fix an error handling path in btrfs_rename() commit abe3bf7425fb695a9b37394af18b9ea58a800802 upstream. If new_whiteout_inode() fails, some resources need to be freed. Add the missing goto to the error handling path. Fixes: ab3c5c18e8fa ("btrfs: setup qstr from dentrys using fscrypt helper") Reviewed-by: Sweet Tea Dorminy Signed-off-by: Christophe JAILLET Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/inode.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 47c5be597368..4063447217f9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9400,8 +9400,10 @@ static int btrfs_rename(struct user_namespace *mnt_userns, if (flags & RENAME_WHITEOUT) { whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir); - if (!whiteout_args.inode) - return -ENOMEM; + if (!whiteout_args.inode) { + ret = -ENOMEM; + goto out_fscrypt_names; + } ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items); if (ret) goto out_whiteout_inode; From 6cd57f5c779578c2c41f6ab3dedd71aaddca4d9f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 20 Dec 2022 11:13:33 +0000 Subject: [PATCH 2052/2093] btrfs: fix fscrypt name leak after failure to join log transaction commit fee4c19937439693f2420a916169d08e88576e8e upstream. When logging a new name, we don't expect to fail joining a log transaction since we know at least one of the inodes was logged before in the current transaction. However if we fail for some unexpected reason, we end up not freeing the fscrypt name we previously allocated. So fix that by freeing the name in case we failed to join a log transaction. Fixes: ab3c5c18e8fa ("btrfs: setup qstr from dentrys using fscrypt helper") Reviewed-by: Sweet Tea Dorminy Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/tree-log.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ab7893debf07..c03ff6a5a7f6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7491,8 +7491,11 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, * not fail, but if it does, it's not serious, just bail out and * mark the log for a full commit. */ - if (WARN_ON_ONCE(ret < 0)) + if (WARN_ON_ONCE(ret < 0)) { + fscrypt_free_filename(&fname); goto out; + } + log_pinned = true; path = btrfs_alloc_path(); From ff81d1c77d0890b0cf835378614ba6df02de6cd8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 17 Nov 2022 19:39:03 -0800 Subject: [PATCH 2053/2093] netlink: remove the flex array from struct nlmsghdr commit c73a72f4cbb47672c8cc7f7d7aba52f1cb15baca upstream. I've added a flex array to struct nlmsghdr in commit 738136a0e375 ("netlink: split up copies in the ack construction") to allow accessing the data easily. It leads to warnings with clang, if user space wraps this structure into another struct and the flex array is not at the end of the container. Reviewed-by: Kees Cook Reviewed-by: David Ahern Link: https://lore.kernel.org/all/20221114023927.GA685@u2004-local/ Link: https://lore.kernel.org/r/20221118033903.1651026-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/netlink.h | 2 -- net/netlink/af_netlink.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 5da0da59bf01..e2ae82e3f9f7 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -48,7 +48,6 @@ struct sockaddr_nl { * @nlmsg_flags: Additional flags * @nlmsg_seq: Sequence number * @nlmsg_pid: Sending process port ID - * @nlmsg_data: Message payload */ struct nlmsghdr { __u32 nlmsg_len; @@ -56,7 +55,6 @@ struct nlmsghdr { __u16 nlmsg_flags; __u32 nlmsg_seq; __u32 nlmsg_pid; - __u8 nlmsg_data[]; }; /* Flags values */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a572a30dfd98..cb833302270a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2458,7 +2458,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; - memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data, + memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } From 6e4c40aa270b72673473a3e0e8a8dc36284ad1f8 Mon Sep 17 00:00:00 2001 From: Bernd Schubert Date: Wed, 6 Sep 2023 17:59:03 +0200 Subject: [PATCH 2054/2093] btrfs: file_remove_privs needs an exclusive lock in direct io write commit 9af86694fd5d387992699ec99007ed374966ce9a upstream. This was noticed by Miklos that file_remove_privs might call into notify_change(), which requires to hold an exclusive lock. The problem exists in FUSE and btrfs. We can fix it without any additional helpers from VFS, in case the privileges would need to be dropped, change the lock type to be exclusive and redo the loop. Fixes: e9adabb9712e ("btrfs: use shared lock for direct writes within EOF") CC: Miklos Szeredi CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Christoph Hellwig Signed-off-by: Bernd Schubert Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/file.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 77202addead8..0a46fff3dd06 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1458,8 +1458,13 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; - /* If the write DIO is within EOF, use a shared lock */ - if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode)) + /* + * If the write DIO is within EOF, use a shared lock and also only if + * security bits will likely not be dropped by file_remove_privs() called + * from btrfs_write_check(). Either will need to be rechecked after the + * lock was acquired. + */ + if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode) && IS_NOSEC(inode)) ilock_flags |= BTRFS_ILOCK_SHARED; relock: @@ -1467,6 +1472,13 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) if (err < 0) return err; + /* Shared lock cannot be used with security bits set. */ + if ((ilock_flags & BTRFS_ILOCK_SHARED) && !IS_NOSEC(inode)) { + btrfs_inode_unlock(inode, ilock_flags); + ilock_flags &= ~BTRFS_ILOCK_SHARED; + goto relock; + } + err = generic_write_checks(iocb, from); if (err <= 0) { btrfs_inode_unlock(inode, ilock_flags); From a4fcf8a242c6c89002aa9a406a83d370833f4a58 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Mar 2023 20:17:32 +0000 Subject: [PATCH 2055/2093] ipv6: remove one read_lock()/read_unlock() pair in rt6_check_neigh() commit c486640aa710ddd06c13a7f7162126e1552e8842 upstream. rt6_check_neigh() uses read_lock() to protect n->nud_state reading. This seems overkill and causes false sharing. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Reviewed-by: Martin KaFai Lau Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/route.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0a9f854bfa50..0bcdb675ba2c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -690,16 +690,16 @@ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { - read_lock(&neigh->lock); - if (neigh->nud_state & NUD_VALID) + u8 nud_state = READ_ONCE(neigh->nud_state); + + if (nud_state & NUD_VALID) ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF - else if (!(neigh->nud_state & NUD_FAILED)) + else if (!(nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; else ret = RT6_NUD_FAIL_PROBE; #endif - read_unlock(&neigh->lock); } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; From a4cc925e2e12c3bbffb0860acdb9f9c1abde47dd Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 28 Aug 2023 08:09:47 +0200 Subject: [PATCH 2056/2093] xen/events: replace evtchn_rwlock with RCU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 87797fad6cce28ec9be3c13f031776ff4f104cfc upstream. In unprivileged Xen guests event handling can cause a deadlock with Xen console handling. The evtchn_rwlock and the hvc_lock are taken in opposite sequence in __hvc_poll() and in Xen console IRQ handling. Normally this is no problem, as the evtchn_rwlock is taken as a reader in both paths, but as soon as an event channel is being closed, the lock will be taken as a writer, which will cause read_lock() to block: CPU0 CPU1 CPU2 (IRQ handling) (__hvc_poll()) (closing event channel) read_lock(evtchn_rwlock) spin_lock(hvc_lock) write_lock(evtchn_rwlock) [blocks] spin_lock(hvc_lock) [blocks] read_lock(evtchn_rwlock) [blocks due to writer waiting, and not in_interrupt()] This issue can be avoided by replacing evtchn_rwlock with RCU in xen_free_irq(). Note that RCU is used only to delay freeing of the irq_info memory. There is no RCU based dereferencing or replacement of pointers involved. In order to avoid potential races between removing the irq_info reference and handling of interrupts, set the irq_info pointer to NULL only when freeing its memory. The IRQ itself must be freed at that time, too, as otherwise the same IRQ number could be allocated again before handling of the old instance would have been finished. This is XSA-441 / CVE-2023-34324. Fixes: 54c9de89895e ("xen/events: add a new "late EOI" evtchn framework") Reported-by: Marek Marczykowski-Górecki Signed-off-by: Juergen Gross Reviewed-by: Julien Grall Signed-off-by: Greg Kroah-Hartman --- drivers/xen/events/events_base.c | 87 +++++++++++++++++--------------- 1 file changed, 46 insertions(+), 41 deletions(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index c443f04aaad7..80b46de14f41 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -96,6 +97,7 @@ enum xen_irq_type { struct irq_info { struct list_head list; struct list_head eoi_list; + struct rcu_work rwork; short refcnt; u8 spurious_cnt; u8 is_accounted; @@ -145,23 +147,13 @@ const struct evtchn_ops *evtchn_ops; */ static DEFINE_MUTEX(irq_mapping_update_lock); -/* - * Lock protecting event handling loop against removing event channels. - * Adding of event channels is no issue as the associated IRQ becomes active - * only after everything is setup (before request_[threaded_]irq() the handler - * can't be entered for an event, as the event channel will be unmasked only - * then). - */ -static DEFINE_RWLOCK(evtchn_rwlock); - /* * Lock hierarchy: * * irq_mapping_update_lock - * evtchn_rwlock - * IRQ-desc lock - * percpu eoi_list_lock - * irq_info->lock + * IRQ-desc lock + * percpu eoi_list_lock + * irq_info->lock */ static LIST_HEAD(xen_irq_list_head); @@ -305,6 +297,22 @@ static void channels_on_cpu_inc(struct irq_info *info) info->is_accounted = 1; } +static void delayed_free_irq(struct work_struct *work) +{ + struct irq_info *info = container_of(to_rcu_work(work), struct irq_info, + rwork); + unsigned int irq = info->irq; + + /* Remove the info pointer only now, with no potential users left. */ + set_info_for_irq(irq, NULL); + + kfree(info); + + /* Legacy IRQ descriptors are managed by the arch. */ + if (irq >= nr_legacy_irqs()) + irq_free_desc(irq); +} + /* Constructors for packed IRQ information. */ static int xen_irq_info_common_setup(struct irq_info *info, unsigned irq, @@ -667,33 +675,36 @@ static void xen_irq_lateeoi_worker(struct work_struct *work) eoi = container_of(to_delayed_work(work), struct lateeoi_work, delayed); - read_lock_irqsave(&evtchn_rwlock, flags); + rcu_read_lock(); while (true) { - spin_lock(&eoi->eoi_list_lock); + spin_lock_irqsave(&eoi->eoi_list_lock, flags); info = list_first_entry_or_null(&eoi->eoi_list, struct irq_info, eoi_list); - if (info == NULL || now < info->eoi_time) { - spin_unlock(&eoi->eoi_list_lock); + if (info == NULL) + break; + + if (now < info->eoi_time) { + mod_delayed_work_on(info->eoi_cpu, system_wq, + &eoi->delayed, + info->eoi_time - now); break; } list_del_init(&info->eoi_list); - spin_unlock(&eoi->eoi_list_lock); + spin_unlock_irqrestore(&eoi->eoi_list_lock, flags); info->eoi_time = 0; xen_irq_lateeoi_locked(info, false); } - if (info) - mod_delayed_work_on(info->eoi_cpu, system_wq, - &eoi->delayed, info->eoi_time - now); + spin_unlock_irqrestore(&eoi->eoi_list_lock, flags); - read_unlock_irqrestore(&evtchn_rwlock, flags); + rcu_read_unlock(); } static void xen_cpu_init_eoi(unsigned int cpu) @@ -708,16 +719,15 @@ static void xen_cpu_init_eoi(unsigned int cpu) void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags) { struct irq_info *info; - unsigned long flags; - read_lock_irqsave(&evtchn_rwlock, flags); + rcu_read_lock(); info = info_for_irq(irq); if (info) xen_irq_lateeoi_locked(info, eoi_flags & XEN_EOI_FLAG_SPURIOUS); - read_unlock_irqrestore(&evtchn_rwlock, flags); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xen_irq_lateeoi); @@ -731,6 +741,7 @@ static void xen_irq_init(unsigned irq) info->type = IRQT_UNBOUND; info->refcnt = -1; + INIT_RCU_WORK(&info->rwork, delayed_free_irq); set_info_for_irq(irq, info); /* @@ -788,31 +799,18 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { struct irq_info *info = info_for_irq(irq); - unsigned long flags; if (WARN_ON(!info)) return; - write_lock_irqsave(&evtchn_rwlock, flags); - if (!list_empty(&info->eoi_list)) lateeoi_list_del(info); list_del(&info->list); - set_info_for_irq(irq, NULL); - WARN_ON(info->refcnt > 0); - write_unlock_irqrestore(&evtchn_rwlock, flags); - - kfree(info); - - /* Legacy IRQ descriptors are managed by the arch. */ - if (irq < nr_legacy_irqs()) - return; - - irq_free_desc(irq); + queue_rcu_work(system_wq, &info->rwork); } static void xen_evtchn_close(evtchn_port_t port) @@ -1716,7 +1714,14 @@ static void __xen_evtchn_do_upcall(void) int cpu = smp_processor_id(); struct evtchn_loop_ctrl ctrl = { 0 }; - read_lock(&evtchn_rwlock); + /* + * When closing an event channel the associated IRQ must not be freed + * until all cpus have left the event handling loop. This is ensured + * by taking the rcu_read_lock() while handling events, as freeing of + * the IRQ is handled via queue_rcu_work() _after_ closing the event + * channel. + */ + rcu_read_lock(); do { vcpu_info->evtchn_upcall_pending = 0; @@ -1729,7 +1734,7 @@ static void __xen_evtchn_do_upcall(void) } while (vcpu_info->evtchn_upcall_pending); - read_unlock(&evtchn_rwlock); + rcu_read_unlock(); /* * Increment irq_epoch only now to defer EOIs only for From 082280fe94a09462c727fb6e7b0c982efb36dede Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 10 Oct 2023 22:00:46 +0200 Subject: [PATCH 2057/2093] Linux 6.1.57 Link: https://lore.kernel.org/r/20231009130122.946357448@linuxfoundation.org Tested-by: SeongJae Park Tested-by: Shuah Khan Tested-by: Florian Fainelli Tested-by: Bagas Sanjaya Tested-by: Jon Hunter Tested-by: Takeshi Ogasawara Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9ceda3dad5eb..b435b56594f0 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 56 +SUBLEVEL = 57 EXTRAVERSION = NAME = Curry Ramen From 8f3811172407ebc4835945d18709cd1580ea4977 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 11:57:57 +0000 Subject: [PATCH 2058/2093] Revert "media: uapi: HEVC: Add num_delta_pocs_of_ref_rps_idx field" This reverts commit b608025733579f4e9074a26dc08ea05f0e07ea0f which is upstream commit ae440c5da33cdb90a109f2df2a0360c67b3fab7e. It breaks the UAPI signature (but not the content), and it turns out is not even needed for the 6.1.y tree at all, so revert it for now. Bug: 161946584 Change-Id: I59e0a97dcaf1ee19bdffaf85f0c2a8f93dc82e75 Signed-off-by: Greg Kroah-Hartman --- .../userspace-api/media/v4l/ext-ctrls-codec-stateless.rst | 7 ------- include/uapi/linux/v4l2-controls.h | 6 +----- 2 files changed, 1 insertion(+), 12 deletions(-) diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst index 0ef49647c90b..cd33857d947d 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst @@ -2923,13 +2923,6 @@ This structure contains all loop filter related parameters. See sections - ``poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - PocLtCurr as described in section 8.3.2 "Decoding process for reference picture set": provides the index of the long term references in DPB array. - * - __u8 - - ``num_delta_pocs_of_ref_rps_idx`` - - When the short_term_ref_pic_set_sps_flag in the slice header is equal to 0, - it is the same as the derived value NumDeltaPocs[RefRpsIdx]. It can be used to parse - the RPS data in slice headers instead of skipping it with @short_term_ref_pic_set_size. - When the value of short_term_ref_pic_set_sps_flag in the slice header is - equal to 1, num_delta_pocs_of_ref_rps_idx shall be set to 0. * - struct :c:type:`v4l2_hevc_dpb_entry` - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]`` - The decoded picture buffer, for meta-data about reference frames. diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index d4a4e3cab3c2..b5e7d082b8ad 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -2411,9 +2411,6 @@ struct v4l2_ctrl_hevc_slice_params { * @poc_st_curr_after: provides the index of the short term after references * in DPB array * @poc_lt_curr: provides the index of the long term references in DPB array - * @num_delta_pocs_of_ref_rps_idx: same as the derived value NumDeltaPocs[RefRpsIdx], - * can be used to parse the RPS data in slice headers - * instead of skipping it with @short_term_ref_pic_set_size. * @reserved: padding field. Should be zeroed by applications. * @dpb: the decoded picture buffer, for meta-data about reference frames * @flags: see V4L2_HEVC_DECODE_PARAM_FLAG_{} @@ -2429,8 +2426,7 @@ struct v4l2_ctrl_hevc_decode_params { __u8 poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u8 poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u8 poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; - __u8 num_delta_pocs_of_ref_rps_idx; - __u8 reserved[3]; + __u8 reserved[4]; struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]; __u64 flags; }; From 41aa5528873eb0a41fd6416221829c4cdc5edb16 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 11:59:54 +0000 Subject: [PATCH 2059/2093] Revert "crypto: api - Use work queue in crypto_destroy_instance" This reverts commit c4cb61c5f976183c07d16b0071f0c60bc212ef1f which is commit 9ae4577bc077a7e32c3c7d442c95bc76865c0f17 upstream. It breaks the Android ABI and if it is needed in the future, can be brought back in an abi-safe way. Bug: 161946584 Change-Id: Icc26bcbe08b4d0b48cfae0be695a453531b9db50 Signed-off-by: Greg Kroah-Hartman --- crypto/algapi.c | 16 ++-------------- include/crypto/algapi.h | 3 --- 2 files changed, 2 insertions(+), 17 deletions(-) diff --git a/crypto/algapi.c b/crypto/algapi.c index d1f76b415643..60b98d2c400e 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -17,7 +17,6 @@ #include #include #include -#include #include "internal.h" @@ -75,26 +74,15 @@ static void crypto_free_instance(struct crypto_instance *inst) inst->alg.cra_type->free(inst); } -static void crypto_destroy_instance_workfn(struct work_struct *w) +static void crypto_destroy_instance(struct crypto_alg *alg) { - struct crypto_instance *inst = container_of(w, struct crypto_instance, - free_work); + struct crypto_instance *inst = (void *)alg; struct crypto_template *tmpl = inst->tmpl; crypto_free_instance(inst); crypto_tmpl_put(tmpl); } -static void crypto_destroy_instance(struct crypto_alg *alg) -{ - struct crypto_instance *inst = container_of(alg, - struct crypto_instance, - alg); - - INIT_WORK(&inst->free_work, crypto_destroy_instance_workfn); - schedule_work(&inst->free_work); -} - /* * This function adds a spawn to the list secondary_spawns which * will be used at the end of crypto_remove_spawns to unregister diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 939a3196bf00..224b86064708 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -12,7 +12,6 @@ #include #include #include -#include #include @@ -61,8 +60,6 @@ struct crypto_instance { struct crypto_spawn *spawns; }; - struct work_struct free_work; - void *__ctx[] CRYPTO_MINALIGN_ATTR; }; From 79dd1a60c7055021ae09d1ae47f0d64438e9dc3f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 12:04:03 +0000 Subject: [PATCH 2060/2093] Revert "PCI: Add locking to RMW PCI Express Capability Register accessors" This reverts commit f2d7da8fafed03cf468cd399cec7d80fbe4bab11 which is commit 5e70d0acf0825f439079736080350371f8d6699a upstream. It breaks the Android API and is not needed for any Android-specific platforms, so it can be dropped for now. If it is needed in the future, it can be brought back in an abi-safe way. Bug: 161946584 Change-Id: Ic12bc34085f8c7ecea1899f7e14b6ba2a920beba Signed-off-by: Greg Kroah-Hartman --- drivers/pci/access.c | 20 +++----------------- drivers/pci/probe.c | 1 - include/linux/pci.h | 34 ++-------------------------------- 3 files changed, 5 insertions(+), 50 deletions(-) diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 3d20f9c51efe..708c7529647f 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -491,8 +491,8 @@ int pcie_capability_write_dword(struct pci_dev *dev, int pos, u32 val) } EXPORT_SYMBOL(pcie_capability_write_dword); -int pcie_capability_clear_and_set_word_unlocked(struct pci_dev *dev, int pos, - u16 clear, u16 set) +int pcie_capability_clear_and_set_word(struct pci_dev *dev, int pos, + u16 clear, u16 set) { int ret; u16 val; @@ -506,21 +506,7 @@ int pcie_capability_clear_and_set_word_unlocked(struct pci_dev *dev, int pos, return ret; } -EXPORT_SYMBOL(pcie_capability_clear_and_set_word_unlocked); - -int pcie_capability_clear_and_set_word_locked(struct pci_dev *dev, int pos, - u16 clear, u16 set) -{ - unsigned long flags; - int ret; - - spin_lock_irqsave(&dev->pcie_cap_lock, flags); - ret = pcie_capability_clear_and_set_word_unlocked(dev, pos, clear, set); - spin_unlock_irqrestore(&dev->pcie_cap_lock, flags); - - return ret; -} -EXPORT_SYMBOL(pcie_capability_clear_and_set_word_locked); +EXPORT_SYMBOL(pcie_capability_clear_and_set_word); int pcie_capability_clear_and_set_dword(struct pci_dev *dev, int pos, u32 clear, u32 set) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 0945f50fe94f..7783d381e324 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2313,7 +2313,6 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) .end = -1, }; - spin_lock_init(&dev->pcie_cap_lock); #ifdef CONFIG_PCI_MSI raw_spin_lock_init(&dev->msi_lock); #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 0db9c25c48ea..c9328c7fce40 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -467,7 +467,6 @@ struct pci_dev { pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ - spinlock_t pcie_cap_lock; /* Protects RMW ops in capability accessors */ u32 saved_config_space[16]; /* Config space saved at suspend time */ struct hlist_head saved_cap_space; int rom_attr_enabled; /* Display of ROM attribute enabled? */ @@ -1234,40 +1233,11 @@ int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val); int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val); int pcie_capability_write_word(struct pci_dev *dev, int pos, u16 val); int pcie_capability_write_dword(struct pci_dev *dev, int pos, u32 val); -int pcie_capability_clear_and_set_word_unlocked(struct pci_dev *dev, int pos, - u16 clear, u16 set); -int pcie_capability_clear_and_set_word_locked(struct pci_dev *dev, int pos, - u16 clear, u16 set); +int pcie_capability_clear_and_set_word(struct pci_dev *dev, int pos, + u16 clear, u16 set); int pcie_capability_clear_and_set_dword(struct pci_dev *dev, int pos, u32 clear, u32 set); -/** - * pcie_capability_clear_and_set_word - RMW accessor for PCI Express Capability Registers - * @dev: PCI device structure of the PCI Express device - * @pos: PCI Express Capability Register - * @clear: Clear bitmask - * @set: Set bitmask - * - * Perform a Read-Modify-Write (RMW) operation using @clear and @set - * bitmasks on PCI Express Capability Register at @pos. Certain PCI Express - * Capability Registers are accessed concurrently in RMW fashion, hence - * require locking which is handled transparently to the caller. - */ -static inline int pcie_capability_clear_and_set_word(struct pci_dev *dev, - int pos, - u16 clear, u16 set) -{ - switch (pos) { - case PCI_EXP_LNKCTL: - case PCI_EXP_RTCTL: - return pcie_capability_clear_and_set_word_locked(dev, pos, - clear, set); - default: - return pcie_capability_clear_and_set_word_unlocked(dev, pos, - clear, set); - } -} - static inline int pcie_capability_set_word(struct pci_dev *dev, int pos, u16 set) { From 5c4d483e7c186fb0b6a33e80092a4c4fbf9e89fc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 12:05:14 +0000 Subject: [PATCH 2061/2093] Revert "PCI: Allow drivers to request exclusive config regions" This reverts commit 3108f7c7888401c8afdae2605705fcb3f81ff631 which is commit 278294798ac9118412c9624a801d3f20f2279363 upstream. It breaks the Android API and is not needed for any Android-specific platforms, so it can be dropped for now. If it is needed in the future, it can be brought back in an abi-safe way. Bug: 161946584 Change-Id: Ic1514e1a760e9ac6bb9da232ea895ab4ce42028b Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci-sysfs.c | 7 ------- drivers/pci/probe.c | 6 ------ include/linux/ioport.h | 2 -- include/linux/pci.h | 17 ----------------- kernel/resource.c | 13 +++++-------- 5 files changed, 5 insertions(+), 40 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index dd0d9d9bc509..ba38fc47d35e 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -756,13 +756,6 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj, if (ret) return ret; - if (resource_is_exclusive(&dev->driver_exclusive_resource, off, - count)) { - pci_warn_once(dev, "%s: Unexpected write to kernel-exclusive config offset %llx", - current->comm, off); - add_taint(TAINT_USER, LOCKDEP_STILL_OK); - } - if (off > dev->cfg_size) return 0; if (off + count > dev->cfg_size) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 7783d381e324..5a5429f91539 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2307,12 +2307,6 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) INIT_LIST_HEAD(&dev->bus_list); dev->dev.type = &pci_dev_type; dev->bus = pci_bus_get(bus); - dev->driver_exclusive_resource = (struct resource) { - .name = "PCI Exclusive", - .start = 0, - .end = -1, - }; - #ifdef CONFIG_PCI_MSI raw_spin_lock_init(&dev->msi_lock); #endif diff --git a/include/linux/ioport.h b/include/linux/ioport.h index bb3a325158a7..341bc839cc83 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -324,8 +324,6 @@ extern void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n); extern int iomem_map_sanity_check(resource_size_t addr, unsigned long size); extern bool iomem_is_exclusive(u64 addr); -extern bool resource_is_exclusive(struct resource *resource, u64 addr, - resource_size_t size); extern int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, diff --git a/include/linux/pci.h b/include/linux/pci.h index c9328c7fce40..5c8cabfe404a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -410,7 +410,6 @@ struct pci_dev { */ unsigned int irq; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */ - struct resource driver_exclusive_resource; /* driver exclusive resource ranges */ bool match_driver; /* Skip attaching driver */ @@ -1433,21 +1432,6 @@ int pci_request_selected_regions(struct pci_dev *, int, const char *); int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *); void pci_release_selected_regions(struct pci_dev *, int); -static inline __must_check struct resource * -pci_request_config_region_exclusive(struct pci_dev *pdev, unsigned int offset, - unsigned int len, const char *name) -{ - return __request_region(&pdev->driver_exclusive_resource, offset, len, - name, IORESOURCE_EXCLUSIVE); -} - -static inline void pci_release_config_region(struct pci_dev *pdev, - unsigned int offset, - unsigned int len) -{ - __release_region(&pdev->driver_exclusive_resource, offset, len); -} - /* drivers/pci/bus.c */ void pci_add_resource(struct list_head *resources, struct resource *res); void pci_add_resource_offset(struct list_head *resources, struct resource *res, @@ -2527,7 +2511,6 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #define pci_crit(pdev, fmt, arg...) dev_crit(&(pdev)->dev, fmt, ##arg) #define pci_err(pdev, fmt, arg...) dev_err(&(pdev)->dev, fmt, ##arg) #define pci_warn(pdev, fmt, arg...) dev_warn(&(pdev)->dev, fmt, ##arg) -#define pci_warn_once(pdev, fmt, arg...) dev_warn_once(&(pdev)->dev, fmt, ##arg) #define pci_notice(pdev, fmt, arg...) dev_notice(&(pdev)->dev, fmt, ##arg) #define pci_info(pdev, fmt, arg...) dev_info(&(pdev)->dev, fmt, ##arg) #define pci_dbg(pdev, fmt, arg...) dev_dbg(&(pdev)->dev, fmt, ##arg) diff --git a/kernel/resource.c b/kernel/resource.c index 8f52f8800965..1aeeededdd4c 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1693,15 +1693,18 @@ static int strict_iomem_checks; * * Returns true if exclusive to the kernel, otherwise returns false. */ -bool resource_is_exclusive(struct resource *root, u64 addr, resource_size_t size) +bool iomem_is_exclusive(u64 addr) { const unsigned int exclusive_system_ram = IORESOURCE_SYSTEM_RAM | IORESOURCE_EXCLUSIVE; bool skip_children = false, err = false; + int size = PAGE_SIZE; struct resource *p; + addr = addr & PAGE_MASK; + read_lock(&resource_lock); - for_each_resource(root, p, skip_children) { + for_each_resource(&iomem_resource, p, skip_children) { if (p->start >= addr + size) break; if (p->end < addr) { @@ -1740,12 +1743,6 @@ bool resource_is_exclusive(struct resource *root, u64 addr, resource_size_t size return err; } -bool iomem_is_exclusive(u64 addr) -{ - return resource_is_exclusive(&iomem_resource, addr & PAGE_MASK, - PAGE_SIZE); -} - struct resource_entry *resource_list_create_entry(struct resource *res, size_t extra_size) { From 8d71a1ef6a253353cc0e74d889f399d728704e2f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 14:00:09 +0000 Subject: [PATCH 2062/2093] Revert "tracing: Zero the pipe cpumask on alloc to avoid spurious -EBUSY" This reverts commit 1dd387668d5bd911df0b21716fff6f5180b11e42 which is commit 3d07fa1dd19035eb0b13ae6697efd5caa9033e74 upstream. It fixes a commit that is about to be reverted due to ABI breakage in Android. If needed, it can come back in in an abi-safe way in the future. Bug: 161946584 Change-Id: Ida127a7112c9748ffdccfd6c5498e2a8334ba3dc Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 23a2da26c187..05a1d812ad54 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9396,7 +9396,7 @@ static struct trace_array *trace_array_create(const char *name) if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; - if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) + if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) goto out_free_tr; tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; @@ -10300,7 +10300,7 @@ __init static int tracer_alloc_buffers(void) if (trace_create_savedcmd() < 0) goto out_free_temp_buffer; - if (!zalloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) + if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) goto out_free_savedcmd; /* TODO: make the number of buffers hot pluggable with CPUS */ From cb6717439ca8ad3a4c747b01b952be98949c73e2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 14:01:08 +0000 Subject: [PATCH 2063/2093] Revert "tracing: Introduce pipe_cpumask to avoid race on trace_pipes" This reverts commit 10f358cd4b0e4b43c07c44791d417a87e8a8d61b which is commit c2489bb7e6be2e8cdced12c16c42fa128403ac03 upstream. It breaks the Android ABI and is not needed for Android systems at this point in time. If needed in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: I821cce9935fbf264a40b9c089e5591efdf145bcf Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 55 ++++++-------------------------------------- kernel/trace/trace.h | 2 -- 2 files changed, 7 insertions(+), 50 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 05a1d812ad54..18923133f39c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6617,36 +6617,10 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, #endif -static int open_pipe_on_cpu(struct trace_array *tr, int cpu) -{ - if (cpu == RING_BUFFER_ALL_CPUS) { - if (cpumask_empty(tr->pipe_cpumask)) { - cpumask_setall(tr->pipe_cpumask); - return 0; - } - } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) { - cpumask_set_cpu(cpu, tr->pipe_cpumask); - return 0; - } - return -EBUSY; -} - -static void close_pipe_on_cpu(struct trace_array *tr, int cpu) -{ - if (cpu == RING_BUFFER_ALL_CPUS) { - WARN_ON(!cpumask_full(tr->pipe_cpumask)); - cpumask_clear(tr->pipe_cpumask); - } else { - WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask)); - cpumask_clear_cpu(cpu, tr->pipe_cpumask); - } -} - static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int cpu; int ret; ret = tracing_check_open_get_tr(tr); @@ -6654,16 +6628,13 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) return ret; mutex_lock(&trace_types_lock); - cpu = tracing_get_cpu(inode); - ret = open_pipe_on_cpu(tr, cpu); - if (ret) - goto fail_pipe_on_cpu; /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; - goto fail_alloc_iter; + __trace_array_put(tr); + goto out; } trace_seq_init(&iter->seq); @@ -6686,7 +6657,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->tr = tr; iter->array_buffer = &tr->array_buffer; - iter->cpu_file = cpu; + iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); filp->private_data = iter; @@ -6696,15 +6667,12 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) nonseekable_open(inode, filp); tr->trace_ref++; - +out: mutex_unlock(&trace_types_lock); return ret; fail: kfree(iter); -fail_alloc_iter: - close_pipe_on_cpu(tr, cpu); -fail_pipe_on_cpu: __trace_array_put(tr); mutex_unlock(&trace_types_lock); return ret; @@ -6721,7 +6689,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) if (iter->trace->pipe_close) iter->trace->pipe_close(iter); - close_pipe_on_cpu(tr, iter->cpu_file); + mutex_unlock(&trace_types_lock); free_cpumask_var(iter->started); @@ -9396,9 +9364,6 @@ static struct trace_array *trace_array_create(const char *name) if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; - if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) - goto out_free_tr; - tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); @@ -9440,7 +9405,6 @@ static struct trace_array *trace_array_create(const char *name) out_free_tr: ftrace_free_ftrace_ops(tr); free_trace_buffers(tr); - free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); @@ -9543,7 +9507,6 @@ static int __remove_instance(struct trace_array *tr) } kfree(tr->topts); - free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); @@ -10300,14 +10263,12 @@ __init static int tracer_alloc_buffers(void) if (trace_create_savedcmd() < 0) goto out_free_temp_buffer; - if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) - goto out_free_savedcmd; - /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n"); - goto out_free_pipe_cpumask; + goto out_free_savedcmd; } + if (global_trace.buffer_disabled) tracing_off(); @@ -10360,8 +10321,6 @@ __init static int tracer_alloc_buffers(void) return 0; -out_free_pipe_cpumask: - free_cpumask_var(global_trace.pipe_cpumask); out_free_savedcmd: free_saved_cmdlines_buffer(savedcmd); out_free_temp_buffer: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index dbb86b0dd3b7..3d3505286aa7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -366,8 +366,6 @@ struct trace_array { struct list_head events; struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ - /* one per_cpu trace_pipe can be opened by only one user */ - cpumask_var_t pipe_cpumask; int ref; int trace_ref; #ifdef CONFIG_FUNCTION_TRACER From 045f98748d5f8b0da26136beecbc4d0ee4289818 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 14:06:50 +0000 Subject: [PATCH 2064/2093] Revert "media: cec: core: add adap_unconfigured() callback" This reverts commit 0294e2475092525075e1271d58f6283564a818a3 which is commit 948a77aaecf202f722cf2264025f9987e5bd5c26 upstream. It breaks the Android ABI and is not needed for Android systems at this point in time. If needed in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: I622663df8e9ddfd598285f8af7631f0406351fe0 Signed-off-by: Greg Kroah-Hartman --- drivers/media/cec/core/cec-adap.c | 4 ++-- include/media/cec.h | 5 ++--- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 4bc2a705029e..aed3e51d6d35 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1345,7 +1345,7 @@ static void cec_adap_unconfigure(struct cec_adapter *adap) cec_flush(adap); wake_up_interruptible(&adap->kthread_waitq); cec_post_state_event(adap); - call_void_op(adap, adap_unconfigured); + call_void_op(adap, adap_configured, false); } /* @@ -1536,7 +1536,7 @@ static int cec_config_thread_func(void *arg) adap->kthread_config = NULL; complete(&adap->config_completion); mutex_unlock(&adap->lock); - call_void_op(adap, configured); + call_void_op(adap, adap_configured, true); return 0; unconfigure: diff --git a/include/media/cec.h b/include/media/cec.h index 9c007f83569a..6556cc161dc0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -113,12 +113,12 @@ struct cec_fh { #define CEC_FREE_TIME_TO_USEC(ft) ((ft) * 2400) struct cec_adap_ops { - /* Low-level callbacks, called with adap->lock held */ + /* Low-level callbacks */ int (*adap_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_pin_enable)(struct cec_adapter *adap, bool enable); int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); - void (*adap_unconfigured)(struct cec_adapter *adap); + void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); void (*adap_nb_transmit_canceled)(struct cec_adapter *adap, @@ -131,7 +131,6 @@ struct cec_adap_ops { bool (*error_inj_parse_line)(struct cec_adapter *adap, char *line); /* High-level CEC message callback, called without adap->lock held */ - void (*configured)(struct cec_adapter *adap); int (*received)(struct cec_adapter *adap, struct cec_msg *msg); }; From ecf3d93213c2fa2f453a49d0f11478e891f073d9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 14:06:51 +0000 Subject: [PATCH 2065/2093] Revert "media: cec: core: add adap_nb_transmit_canceled() callback" This reverts commit d6610151ae22954bdec1d154022072b57a9ac487 which is commit da53c36ddd3f118a525a04faa8c47ca471e6c467 upstream. It breaks the Android ABI and is not needed for Android systems at this point in time. If needed in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: I65b4767764af29e74b2e349e7943f4f70f333823 Signed-off-by: Greg Kroah-Hartman --- drivers/media/cec/core/cec-adap.c | 4 ++-- include/media/cec.h | 6 ++---- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index aed3e51d6d35..b1512f9c5895 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -385,8 +385,8 @@ static void cec_data_cancel(struct cec_data *data, u8 tx_status, u8 rx_status) cec_queue_msg_monitor(adap, &data->msg, 1); if (!data->blocking && data->msg.sequence) - /* Allow drivers to react to a canceled transmit */ - call_void_op(adap, adap_nb_transmit_canceled, &data->msg); + /* Allow drivers to process the message first */ + call_op(adap, received, &data->msg); cec_data_completed(data); } diff --git a/include/media/cec.h b/include/media/cec.h index 6556cc161dc0..abee41ae02d0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -121,16 +121,14 @@ struct cec_adap_ops { void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); - void (*adap_nb_transmit_canceled)(struct cec_adapter *adap, - const struct cec_msg *msg); void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); void (*adap_free)(struct cec_adapter *adap); - /* Error injection callbacks, called without adap->lock held */ + /* Error injection callbacks */ int (*error_inj_show)(struct cec_adapter *adap, struct seq_file *sf); bool (*error_inj_parse_line)(struct cec_adapter *adap, char *line); - /* High-level CEC message callback, called without adap->lock held */ + /* High-level CEC message callback */ int (*received)(struct cec_adapter *adap, struct cec_msg *msg); }; From 1592fd4684092fdc43041076f29dcf4a5bc8d05f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 14:10:00 +0000 Subject: [PATCH 2066/2093] Revert "scsi: core: Use 32-bit hostnum in scsi_host_lookup()" This reverts commit f06c7d823ab5e62b8384f69a968664c794eae3f5 which is commit 62ec2092095b678ff89ce4ba51c2938cd1e8e630 upstream. It breaks the Android ABI and is not needed for Android systems at this point in time. If needed in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: I7853972e9f38b29384a23fa3ec9dcf0692a2ede1 Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/hosts.c | 4 ++-- include/scsi/scsi_host.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 8b825364baad..45a2fd6584d1 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -535,7 +535,7 @@ EXPORT_SYMBOL(scsi_host_alloc); static int __scsi_host_match(struct device *dev, const void *data) { struct Scsi_Host *p; - const unsigned int *hostnum = data; + const unsigned short *hostnum = data; p = class_to_shost(dev); return p->host_no == *hostnum; @@ -552,7 +552,7 @@ static int __scsi_host_match(struct device *dev, const void *data) * that scsi_host_get() took. The put_device() below dropped * the reference from class_find_device(). **/ -struct Scsi_Host *scsi_host_lookup(unsigned int hostnum) +struct Scsi_Host *scsi_host_lookup(unsigned short hostnum) { struct device *cdev; struct Scsi_Host *shost = NULL; diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 16c11dd58931..884ee414fdf7 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -777,7 +777,7 @@ extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); extern int scsi_host_busy(struct Scsi_Host *shost); extern void scsi_host_put(struct Scsi_Host *t); -extern struct Scsi_Host *scsi_host_lookup(unsigned int hostnum); +extern struct Scsi_Host *scsi_host_lookup(unsigned short); extern const char *scsi_host_state_name(enum scsi_host_state); extern void scsi_host_complete_all_commands(struct Scsi_Host *shost, enum scsi_host_status status); From acef80535a7a76880bc7351fa7499df4c0963e7e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 14:11:06 +0000 Subject: [PATCH 2067/2093] Revert "usb: typec: bus: verify partner exists in typec_altmode_attention" This reverts commit 0d3b5fe47938e9c451466845304a2bd74e967a80 which is commit f23643306430f86e2f413ee2b986e0773e79da31 upstream. It breaks the Android ABI and is not needed for Android systems at this point in time. If needed in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: Ib271c569a1f86228f86e4c9b164d96f1bf0f0019 Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/bus.c | 12 ++---------- drivers/usb/typec/tcpm/tcpm.c | 3 +-- include/linux/usb/typec_altmode.h | 2 +- 3 files changed, 4 insertions(+), 13 deletions(-) diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 69442a813585..31c2a3130cad 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -154,20 +154,12 @@ EXPORT_SYMBOL_GPL(typec_altmode_exit); * * Notifies the partner of @adev about Attention command. */ -int typec_altmode_attention(struct typec_altmode *adev, u32 vdo) +void typec_altmode_attention(struct typec_altmode *adev, u32 vdo) { - struct altmode *partner = to_altmode(adev)->partner; - struct typec_altmode *pdev; - - if (!partner) - return -ENODEV; - - pdev = &partner->adev; + struct typec_altmode *pdev = &to_altmode(adev)->partner->adev; if (pdev->ops && pdev->ops->attention) pdev->ops->attention(pdev, vdo); - - return 0; } EXPORT_SYMBOL_GPL(typec_altmode_attention); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 7ba5236e06b0..27475f13343b 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1885,8 +1885,7 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port, } break; case ADEV_ATTENTION: - if (typec_altmode_attention(adev, p[1])) - tcpm_log(port, "typec_altmode_attention no port partner altmode"); + typec_altmode_attention(adev, p[1]); break; } } diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 10f70d44c4b7..43f8424e0aad 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -69,7 +69,7 @@ struct typec_altmode_ops { int typec_altmode_enter(struct typec_altmode *altmode, u32 *vdo); int typec_altmode_exit(struct typec_altmode *altmode); -int typec_altmode_attention(struct typec_altmode *altmode, u32 vdo); +void typec_altmode_attention(struct typec_altmode *altmode, u32 vdo); int typec_altmode_vdm(struct typec_altmode *altmode, const u32 header, const u32 *vdo, int count); int typec_altmode_notify(struct typec_altmode *altmode, unsigned long conf, From d78a23145328f8e04f7d99291350227a0ccd341a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 15:00:24 +0000 Subject: [PATCH 2068/2093] Revert "ipv4: fix data-races around inet->inet_id" This reverts commit 417e7ec0d61e2bcb4e264375badbd2e3c879467c which is commit f866fbc842de5976e41ba874b76ce31710b634b5 upstream. It breaks the Android kernel abi. If this is needed in the future, it can come back in an abi-safe way. Bug: 161946584 Cc: Eric Dumazet Change-Id: Ib36deff93f4066ebd3c67ae440da5ac82948b5b3 Signed-off-by: Greg Kroah-Hartman --- .../chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- include/net/inet_sock.h | 2 +- include/net/ip.h | 15 ++------------- net/dccp/ipv4.c | 4 ++-- net/ipv4/af_inet.c | 2 +- net/ipv4/datagram.c | 2 +- net/ipv4/tcp_ipv4.c | 4 ++-- net/sctp/socket.c | 2 +- 8 files changed, 11 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 7750702900fa..c2e7037c7ba1 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1466,7 +1466,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) tp->write_seq = snd_isn; tp->snd_nxt = snd_isn; tp->snd_una = snd_isn; - atomic_set(&inet_sk(sk)->inet_id, get_random_u16()); + inet_sk(sk)->inet_id = get_random_u16(); assign_rxopt(sk, opt); if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index e31d42316b25..eadc37db200d 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -223,8 +223,8 @@ struct inet_sock { __s16 uc_ttl; __u16 cmsg_flags; struct ip_options_rcu __rcu *inet_opt; - atomic_t inet_id; __be16 inet_sport; + __u16 inet_id; __u8 tos; __u8 min_ttl; diff --git a/include/net/ip.h b/include/net/ip.h index cb3c69aaccbd..a6bbf0b79055 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -534,19 +534,8 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, * generator as much as we can. */ if (sk && inet_sk(sk)->inet_daddr) { - int val; - - /* avoid atomic operations for TCP, - * as we hold socket lock at this point. - */ - if (sk_is_tcp(sk)) { - sock_owned_by_me(sk); - val = atomic_read(&inet_sk(sk)->inet_id); - atomic_set(&inet_sk(sk)->inet_id, val + segs); - } else { - val = atomic_add_return(segs, &inet_sk(sk)->inet_id); - } - iph->id = htons(val); + iph->id = htons(inet_sk(sk)->inet_id); + inet_sk(sk)->inet_id += segs; return; } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8f5d3c088111..56ffd06c6cc6 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -130,7 +130,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - atomic_set(&inet->inet_id, get_random_u16()); + inet->inet_id = get_random_u16(); err = dccp_connect(sk); rt = NULL; @@ -435,7 +435,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - atomic_set(&newinet->inet_id, get_random_u16()); + newinet->inet_id = get_random_u16(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 04853c83c85c..ebb737ac9e89 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -340,7 +340,7 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, else inet->pmtudisc = IP_PMTUDISC_WANT; - atomic_set(&inet->inet_id, 0); + inet->inet_id = 0; sock_init_data(sock, sk); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index cb5dbee9e018..4d1af0cd7d99 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - atomic_set(&inet->inet_id, get_random_u16()); + inet->inet_id = get_random_u16(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f9b8a4a1d2ed..08921b96f972 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -312,7 +312,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr)); } - atomic_set(&inet->inet_id, get_random_u16()); + inet->inet_id = get_random_u16(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -1539,7 +1539,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - atomic_set(&newinet->inet_id, get_random_u16()); + newinet->inet_id = get_random_u16(); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a11b0d903514..83656fe03a0e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9472,7 +9472,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - atomic_set(&newinet->inet_id, get_random_u16()); + newinet->inet_id = get_random_u16(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; From 1d14a4d9cef9c8cea3635abf858524f90b50deb6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 15:05:43 +0000 Subject: [PATCH 2069/2093] ANDROID: GKI: sched: put back the cpu_capacity_inverted variable In commit 8517d739923e ("sched/fair: Remove capacity inversion detection"), the cpu_capacity_inverted was removed from struct rq. Add it back to preserve the abi and comment that it's not valid anymore. Note, due to external modules using internal structures like this, it's going to be "tricky" for them to even notice this has changed. Their build systems are going to have "fun" with this... Bug: 161946584 Fixes: 8517d739923e ("sched/fair: Remove capacity inversion detection") Change-Id: I2b41b3ba2eb23fbb33ff872915a5e481640d0cc4 Signed-off-by: Greg Kroah-Hartman --- kernel/sched/sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 8a42a3c36f6d..210032735650 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1061,6 +1061,15 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; + /* + * ANDROID ONLY: + * cpu_capacity_inverted is preserved here to keep the same ABI, + * but it is NOT a field that is used anymore. Be aware of this + * if when attempting to access it in out-of-tree code. It was + * removed in commit 8517d739923e ("sched/fair: Remove capacity + * inversion detection") in the 6.1.47 upstream release. + */ + unsigned long cpu_capacity_inverted; struct balance_callback *balance_callback; From 59ff7fa115e496852bf16936ab5a149345b4556f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 7 Oct 2023 10:51:26 +0000 Subject: [PATCH 2070/2093] ANDROID: GKI: db845c: add pcie_capability_clear_and_set_word to the symbol list In commit 811ec8bc68f3 ("wifi: ath11k: Use RMW accessors for changing LNKCTL"), the ath11k driver adds a call to pcie_capability_clear_and_set_word which is not in the db845c's exported symbol list, so the build breaks. Fix this up by adding the symbol to the correct list (it's already part of the Android preserved KABI list in other targets.) Fixes: 811ec8bc68f3 ("wifi: ath11k: Use RMW accessors for changing LNKCTL") Change-Id: I5ad48ff8edf0fcae6d3e123db4e2ebd875c7ce7e Signed-off-by: Greg Kroah-Hartman --- android/abi_gki_aarch64_db845c | 1 + 1 file changed, 1 insertion(+) diff --git a/android/abi_gki_aarch64_db845c b/android/abi_gki_aarch64_db845c index 2a9e9d583485..09191ef02a16 100644 --- a/android/abi_gki_aarch64_db845c +++ b/android/abi_gki_aarch64_db845c @@ -523,6 +523,7 @@ param_ops_uint pci_clear_master pci_disable_device + pcie_capability_clear_and_set_word pcie_capability_read_word pcie_capability_write_word pci_enable_device From d7156e9445d44216a1299bcc2bcbe3c41eccac0e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 20:47:53 +0000 Subject: [PATCH 2071/2093] ANDROID: GKI: update .stg due to internal zswap and tracing changes There are a number of internal-to-the-kernel changes in the recent set of LTS releases that end up bleeding over into the public .stg file, yet they are really anonymous pointers when it comes to external modules. Update the .stg file with these changes as the tooling is being extra careful, but these are not actual ABI changes so this is safe. Full details are: INFO: ABI DIFFERENCES HAVE BEEN DETECTED! INFO: type 'struct trace_buffer' changed member 'atomic_t resizing' was added type 'struct zs_pool' changed member 'spinlock_t lock' was added member 'atomic_t compaction_in_progress' was added member 'rwlock_t migrate_lock' was removed type 'struct size_class' changed byte size changed from 136 to 128 member 'spinlock_t lock' was removed 6 members ('struct list_head fullness_list[4]' .. 'struct zs_size_stat stats') changed offset changed by -64 Bug: 161946584 Change-Id: Ib5bb4a55ef5463ed49f7cd2c90bf73e278fd51e4 Signed-off-by: Greg Kroah-Hartman --- android/abi_gki_aarch64.stg | 82 +++++++++++++++++++++---------------- 1 file changed, 47 insertions(+), 35 deletions(-) diff --git a/android/abi_gki_aarch64.stg b/android/abi_gki_aarch64.stg index c22a52854e13..1907773740a3 100644 --- a/android/abi_gki_aarch64.stg +++ b/android/abi_gki_aarch64.stg @@ -62522,6 +62522,12 @@ member { type_id: 0x6720d32f offset: 11712 } +member { + id: 0x9ad71760 + name: "compaction_in_progress" + type_id: 0x74d29cf1 + offset: 17568 +} member { id: 0x583d51cc name: "companion_ports" @@ -91948,10 +91954,9 @@ member { offset: 712 } member { - id: 0xf667d80f + id: 0xf667dcee name: "fullness_list" type_id: 0xb8bf135c - offset: 64 } member { id: 0xfeb50ea0 @@ -103779,12 +103784,6 @@ member { type_id: 0x4585663f offset: 320 } -member { - id: 0xad7c8a98 - name: "index" - type_id: 0x4585663f - offset: 672 -} member { id: 0xad7c8ba4 name: "index" @@ -103797,6 +103796,12 @@ member { type_id: 0x4585663f offset: 480 } +member { + id: 0xad7c8d2b + name: "index" + type_id: 0x4585663f + offset: 608 +} member { id: 0xad7c8d72 name: "index" @@ -115578,6 +115583,12 @@ member { type_id: 0xf313e71a offset: 768 } +member { + id: 0x2d1fe43b + name: "lock" + type_id: 0xf313e71a + offset: 17536 +} member { id: 0x2d1fe44c name: "lock" @@ -123438,12 +123449,6 @@ member { type_id: 0x2c8b0a9f offset: 768 } -member { - id: 0xdb33fcdf - name: "migrate_lock" - type_id: 0xf4933b90 - offset: 17536 -} member { id: 0x8edaa968 name: "migrate_page" @@ -136400,10 +136405,10 @@ member { type_id: 0xad7c0a89 } member { - id: 0x7a226550 + id: 0x7a226b7d name: "objs_per_zspage" type_id: 0x6720d32f - offset: 608 + offset: 544 } member { id: 0x33953b25 @@ -141342,10 +141347,10 @@ member { bitsize: 1 } member { - id: 0x338646f2 + id: 0x338649f9 name: "pages_per_zspage" type_id: 0x6720d32f - offset: 640 + offset: 576 } member { id: 0xf9521fd2 @@ -162158,6 +162163,12 @@ member { type_id: 0x03913382 offset: 64 } +member { + id: 0x9a2ccf59 + name: "resizing" + type_id: 0x74d29cf1 + offset: 96 +} member { id: 0x7f319b20 name: "resolution" @@ -173982,18 +173993,18 @@ member { type_id: 0x6720d32f offset: 96 } -member { - id: 0xd91935d3 - name: "size" - type_id: 0x6720d32f - offset: 576 -} member { id: 0xd9193607 name: "size" type_id: 0x6720d32f offset: 896 } +member { + id: 0xd91937b9 + name: "size" + type_id: 0x6720d32f + offset: 512 +} member { id: 0xd9193b66 name: "size" @@ -179931,10 +179942,10 @@ member { offset: 896 } member { - id: 0xb91e0d04 + id: 0xb91e0940 name: "stats" type_id: 0x6b61371d - offset: 704 + offset: 640 } member { id: 0xb920e0d3 @@ -249070,14 +249081,13 @@ struct_union { kind: STRUCT name: "size_class" definition { - bytesize: 136 - member_id: 0x2d1fec85 - member_id: 0xf667d80f - member_id: 0xd91935d3 - member_id: 0x7a226550 - member_id: 0x338646f2 - member_id: 0xad7c8a98 - member_id: 0xb91e0d04 + bytesize: 128 + member_id: 0xf667dcee + member_id: 0xd91937b9 + member_id: 0x7a226b7d + member_id: 0x338649f9 + member_id: 0xad7c8d2b + member_id: 0xb91e0940 } } struct_union { @@ -255002,6 +255012,7 @@ struct_union { member_id: 0x2d2d0138 member_id: 0xe7102ce7 member_id: 0x9fc7d460 + member_id: 0x9a2ccf59 member_id: 0x3dac837e member_id: 0xaa1570ba member_id: 0xad8983a9 @@ -265101,7 +265112,8 @@ struct_union { member_id: 0xb9089225 member_id: 0x868caa9e member_id: 0x8a67a9e5 - member_id: 0xdb33fcdf + member_id: 0x2d1fe43b + member_id: 0x9ad71760 } } struct_union { From 5cdaba14b853ce2240d6d1224565aa765bcb07a7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 18 Oct 2023 14:17:46 +0000 Subject: [PATCH 2072/2093] ANDROID: GKI: add guards for an include file in net/ethtool/ioctl.c In commit 82f9af464e01 ("ipv6: Remove in6addr_any alternatives."), the 6.1.54 release adds a new include file, which changes the crc generation of some of the public symbols in that file. Fix that up by adding a Bug: 161946584 Fixes: 82f9af464e01 ("ipv6: Remove in6addr_any alternatives.") Change-Id: I495d21a761e3724ed1ca605496b2b85acb7a77f5 Signed-off-by: Greg Kroah-Hartman --- net/ethtool/ioctl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index e31d1247b9f0..65ec4826cb9e 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -27,7 +27,9 @@ #include #include #include +#ifndef __GENKSYMS__ #include +#endif #include #include #include From 9f7988e6d7629f8f94ae0e550370f13edf0a5a62 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 12 Oct 2023 10:17:39 +0200 Subject: [PATCH 2073/2093] UPSTREAM: lib/test_meminit: fix off-by-one error in test_pages() commit efb78fa86e95 ("lib/test_meminit: allocate pages up to order MAX_ORDER") works great in kernels 6.4 and newer thanks to commit 23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely"), but for older kernels, the loop is off by one, which causes crashes when the test runs. Fix this up by changing "<= MAX_ORDER" "< MAX_ORDER" to allow the test to work properly for older kernel branches. Fixes: 421855d0d24d ("lib/test_meminit: allocate pages up to order MAX_ORDER") Cc: Andrew Donnellan Cc: Alexander Potapenko Cc: Xiaoke Wang Cc: Cc: Andrew Morton Change-Id: I3c6b6482a276b51273be5fa38ab9d5539d0878fd Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 38fd36728f40d7c83979d9b1443cffcf368790b0) Signed-off-by: Greg Kroah-Hartman --- lib/test_meminit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 0ae35223d773..85d8dd8e01dc 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -93,7 +93,7 @@ static int __init test_pages(int *total_failures) int failures = 0, num_tests = 0; int i; - for (i = 0; i <= MAX_ORDER; i++) + for (i = 0; i < MAX_ORDER; i++) num_tests += do_alloc_pages_order(i, &failures); REPORT_FAILURES_IN_FN(); From 320c8b56ff28f00117b53e2fda5f8e3f33bbb307 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 26 Oct 2023 10:47:11 +0000 Subject: [PATCH 2074/2093] ANDROID: GKI: db845c: add new dma_buf symbols to list In commit 8332311cd02a ("misc: fastrpc: Fix incorrect DMA mapping unmap request"), the symbols dma_buf_map_attachment_unlocked and dma_buf_unmap_attachment_unlocked are now required to be used by the db845c target, so add them to the symbol list to fix up the build. 2 function symbol(s) added 'struct sg_table* dma_buf_map_attachment_unlocked(struct dma_buf_attachment*, enum dma_data_direction)' 'void dma_buf_unmap_attachment_unlocked(struct dma_buf_attachment*, struct sg_table*, enum dma_data_direction)' Fixes: 8332311cd02a ("misc: fastrpc: Fix incorrect DMA mapping unmap request") Change-Id: Ib634cfa9a88a6708893a938a7d48d542db5b7b61 Signed-off-by: Greg Kroah-Hartman --- android/abi_gki_aarch64.stg | 22 ++++++++++++++++++++++ android/abi_gki_aarch64_db845c | 2 ++ 2 files changed, 24 insertions(+) diff --git a/android/abi_gki_aarch64.stg b/android/abi_gki_aarch64.stg index 1907773740a3..b14e8d1a06f5 100644 --- a/android/abi_gki_aarch64.stg +++ b/android/abi_gki_aarch64.stg @@ -343819,6 +343819,16 @@ elf_symbol { type_id: 0x451c3ee7 full_name: "dma_buf_map_attachment" } +elf_symbol { + id: 0x25104c49 + name: "dma_buf_map_attachment_unlocked" + is_defined: true + symbol_type: FUNCTION + crc: 0xedb9c6b4 + namespace: "DMA_BUF" + type_id: 0x451c3ee7 + full_name: "dma_buf_map_attachment_unlocked" +} elf_symbol { id: 0xc99a7edf name: "dma_buf_mmap" @@ -343869,6 +343879,16 @@ elf_symbol { type_id: 0x17ffed59 full_name: "dma_buf_unmap_attachment" } +elf_symbol { + id: 0x68016e57 + name: "dma_buf_unmap_attachment_unlocked" + is_defined: true + symbol_type: FUNCTION + crc: 0xffe8aa2b + namespace: "DMA_BUF" + type_id: 0x17ffed59 + full_name: "dma_buf_unmap_attachment_unlocked" +} elf_symbol { id: 0xe8233473 name: "dma_buf_unpin" @@ -387500,11 +387520,13 @@ interface { symbol_id: 0xe6ad1d16 symbol_id: 0xda3a8347 symbol_id: 0xb3e02cd2 + symbol_id: 0x25104c49 symbol_id: 0xc99a7edf symbol_id: 0xdcb8ed3c symbol_id: 0x4ec1de19 symbol_id: 0xe5cfd7ac symbol_id: 0xd0deb542 + symbol_id: 0x68016e57 symbol_id: 0xe8233473 symbol_id: 0x710f1fc2 symbol_id: 0xaa54a71f diff --git a/android/abi_gki_aarch64_db845c b/android/abi_gki_aarch64_db845c index 09191ef02a16..4fdb4e394771 100644 --- a/android/abi_gki_aarch64_db845c +++ b/android/abi_gki_aarch64_db845c @@ -197,6 +197,8 @@ dma_async_device_register dma_async_tx_descriptor_init dma_buf_export + dma_buf_map_attachment_unlocked + dma_buf_unmap_attachment_unlocked dma_fence_context_alloc dma_fence_init dma_fence_release From 7bcb060a61705c0ca5c3c1d4ce291f1df7c5d3c9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 07:15:44 +0000 Subject: [PATCH 2075/2093] Revert "dm: fix a race condition in retrieve_deps" This reverts commit dbf1a719850577bb51fc7512a3972994b797a17b which is commit f6007dce0cd35d634d9be91ef3515a6385dcee16 upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: Ief37eab88188180ba9884987d9731b10d1527051 Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-core.h | 1 - drivers/md/dm-ioctl.c | 7 +------ drivers/md/dm-table.c | 32 ++++++++------------------------ 3 files changed, 9 insertions(+), 31 deletions(-) diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 71dcd8fd4050..28c641352de9 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -214,7 +214,6 @@ struct dm_table { /* a list of devices used by this table */ struct list_head devices; - struct rw_semaphore devices_lock; /* events get handed up using this callback */ void (*event_fn)(void *); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 206e6ce554dc..2afd2d2a0f40 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1566,8 +1566,6 @@ static void retrieve_deps(struct dm_table *table, struct dm_dev_internal *dd; struct dm_target_deps *deps; - down_read(&table->devices_lock); - deps = get_result_buffer(param, param_size, &len); /* @@ -1582,7 +1580,7 @@ static void retrieve_deps(struct dm_table *table, needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; - goto out; + return; } /* @@ -1594,9 +1592,6 @@ static void retrieve_deps(struct dm_table *table, deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev); param->data_size = param->data_start + needed; - -out: - up_read(&table->devices_lock); } static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 66029bbd9c64..ba2cec22a2b3 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -134,7 +134,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); - init_rwsem(&t->devices_lock); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -363,19 +362,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, return -ENODEV; } - down_write(&t->devices_lock); - dd = find_device(&t->devices, dev); if (!dd) { dd = kmalloc(sizeof(*dd), GFP_KERNEL); - if (!dd) { - r = -ENOMEM; - goto unlock_ret_r; - } + if (!dd) + return -ENOMEM; if ((r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev))) { kfree(dd); - goto unlock_ret_r; + return r; } refcount_set(&dd->count, 1); @@ -385,17 +380,12 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { r = upgrade_mode(dd, mode, t->md); if (r) - goto unlock_ret_r; + return r; } refcount_inc(&dd->count); out: - up_write(&t->devices_lock); *result = dd->dm_dev; return 0; - -unlock_ret_r: - up_write(&t->devices_lock); - return r; } EXPORT_SYMBOL(dm_get_device); @@ -431,12 +421,9 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, void dm_put_device(struct dm_target *ti, struct dm_dev *d) { int found = 0; - struct dm_table *t = ti->table; - struct list_head *devices = &t->devices; + struct list_head *devices = &ti->table->devices; struct dm_dev_internal *dd; - down_write(&t->devices_lock); - list_for_each_entry(dd, devices, list) { if (dd->dm_dev == d) { found = 1; @@ -445,17 +432,14 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } if (!found) { DMERR("%s: device %s not in table devices list", - dm_device_name(t->md), d->name); - goto unlock_ret; + dm_device_name(ti->table->md), d->name); + return; } if (refcount_dec_and_test(&dd->count)) { - dm_put_table_device(t->md, d); + dm_put_table_device(ti->table->md, d); list_del(&dd->list); kfree(dd); } - -unlock_ret: - up_write(&t->devices_lock); } EXPORT_SYMBOL(dm_put_device); From aa5b12e90ab6ca629c1f22368a9d60fbb2df53f7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:32:05 +0000 Subject: [PATCH 2076/2093] Revert "fs/nls: make load_nls() take a const parameter" This reverts commit 952af5cfd5b45ae4a8c9a211c82b66b1ef6c46ca which is commit c1ed39ec116272935528ca9b348b8ee79b0791da upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: I3ecb25cbffc28bc20e7e398ba4b36c71bf54a0bc Signed-off-by: Greg Kroah-Hartman --- fs/nls/nls_base.c | 4 ++-- include/linux/nls.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index a026dbd3593f..52ccd34b1e79 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -272,7 +272,7 @@ int unregister_nls(struct nls_table * nls) return -EINVAL; } -static struct nls_table *find_nls(const char *charset) +static struct nls_table *find_nls(char *charset) { struct nls_table *nls; spin_lock(&nls_lock); @@ -288,7 +288,7 @@ static struct nls_table *find_nls(const char *charset) return nls; } -struct nls_table *load_nls(const char *charset) +struct nls_table *load_nls(char *charset) { return try_then_request_module(find_nls(charset), "nls_%s", charset); } diff --git a/include/linux/nls.h b/include/linux/nls.h index e0bf8367b274..499e486b3722 100644 --- a/include/linux/nls.h +++ b/include/linux/nls.h @@ -47,7 +47,7 @@ enum utf16_endian { /* nls_base.c */ extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); -extern struct nls_table *load_nls(const char *charset); +extern struct nls_table *load_nls(char *); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); #define register_nls(nls) __register_nls((nls), THIS_MODULE) From a81c232edd3c2dad22ce53581a13624a41f695a4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:04 +0000 Subject: [PATCH 2077/2093] Revert "video/aperture: Move vga handling to pci function" This reverts commit 28916927b7626ed3c44d902eafbf9d00691266e1 which is commit f1d599d315fb7b7343cddaf365e671aaa8453aca upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: Iffad2c2b492da2aa7b87dba8d9bd792be74b3b58 Signed-off-by: Greg Kroah-Hartman --- drivers/video/aperture.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 3e4a1f55f51b..7ea18086e659 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -298,6 +298,14 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si aperture_detach_devices(base, size); + /* + * If this is the primary adapter, there could be a VGA device + * that consumes the VGA framebuffer I/O range. Remove this device + * as well. + */ + if (primary) + aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); + return 0; } EXPORT_SYMBOL(aperture_remove_conflicting_devices); @@ -337,13 +345,6 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na } if (primary) { - /* - * If this is the primary adapter, there could be a VGA device - * that consumes the VGA framebuffer I/O range. Remove this - * device as well. - */ - aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); - /* * WARNING: Apparently we must kick fbdev drivers before vgacon, * otherwise the vga fbdev driver falls over. From 33b12f8e4801e8fd96ddf6cb6b56960fd123f62b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:06 +0000 Subject: [PATCH 2078/2093] Revert "video/aperture: Only kick vgacon when the pdev is decoding vga" This reverts commit 4aad3b82b9de7c4ffccb02f87d0c6903569333c9 which is commit 7450cd235b45d43ee6f3c235f89e92623458175d upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: Id7b85df6d6bdffc3f6d2c32a1599d2d9bbc9f062 Signed-off-by: Greg Kroah-Hartman --- drivers/video/aperture.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 7ea18086e659..5c94abdb1ad6 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -344,15 +344,13 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na aperture_detach_devices(base, size); } - if (primary) { - /* - * WARNING: Apparently we must kick fbdev drivers before vgacon, - * otherwise the vga fbdev driver falls over. - */ - ret = vga_remove_vgacon(pdev); - if (ret) - return ret; - } + /* + * WARNING: Apparently we must kick fbdev drivers before vgacon, + * otherwise the vga fbdev driver falls over. + */ + ret = vga_remove_vgacon(pdev); + if (ret) + return ret; return 0; From 6603cc468d4530b51310d3f2f3667f9f705e9765 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:07 +0000 Subject: [PATCH 2079/2093] Revert "drm/aperture: Remove primary argument" This reverts commit 437e99f2a1e933348c4cedb2c7ce6f0ad81b935e which is commit 62aeaeaa1b267c5149abee6b45967a5df3feed58 upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: I04e3476f9417cb019108f2bbb3dd277691ca027d Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/arm/hdlcd_drv.c | 2 +- drivers/gpu/drm/armada/armada_drv.c | 2 +- drivers/gpu/drm/drm_aperture.c | 11 ++++++++--- drivers/gpu/drm/gma500/psb_drv.c | 2 +- drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 1 + drivers/gpu/drm/meson/meson_drv.c | 2 +- drivers/gpu/drm/msm/msm_fbdev.c | 2 +- drivers/gpu/drm/rockchip/rockchip_drm_drv.c | 2 +- drivers/gpu/drm/stm/drv.c | 2 +- drivers/gpu/drm/sun4i/sun4i_drv.c | 2 +- drivers/gpu/drm/tegra/drm.c | 2 +- drivers/gpu/drm/vc4/vc4_drv.c | 2 +- include/drm/drm_aperture.h | 7 ++++--- 13 files changed, 23 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index d6ea47873627..a032003c340c 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -290,7 +290,7 @@ static int hdlcd_drm_bind(struct device *dev) */ if (hdlcd_read(hdlcd, HDLCD_REG_COMMAND)) { hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0); - drm_aperture_remove_framebuffers(&hdlcd_driver); + drm_aperture_remove_framebuffers(false, &hdlcd_driver); } drm_mode_config_reset(drm); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 688ba358f531..142668cd6d7c 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -95,7 +95,7 @@ static int armada_drm_bind(struct device *dev) } /* Remove early framebuffers */ - ret = drm_aperture_remove_framebuffers(&armada_drm_driver); + ret = drm_aperture_remove_framebuffers(false, &armada_drm_driver); if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c index 697cffbfd603..3b8fdeeafd53 100644 --- a/drivers/gpu/drm/drm_aperture.c +++ b/drivers/gpu/drm/drm_aperture.c @@ -32,13 +32,17 @@ * * static int remove_conflicting_framebuffers(struct pci_dev *pdev) * { + * bool primary = false; * resource_size_t base, size; * int ret; * * base = pci_resource_start(pdev, 0); * size = pci_resource_len(pdev, 0); + * #ifdef CONFIG_X86 + * primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; + * #endif * - * return drm_aperture_remove_conflicting_framebuffers(base, size, + * return drm_aperture_remove_conflicting_framebuffers(base, size, primary, * &example_driver); * } * @@ -157,6 +161,7 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * drm_aperture_remove_conflicting_framebuffers - remove existing framebuffers in the given range * @base: the aperture's base address in physical memory * @size: aperture size in bytes + * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes graphics device drivers which use the memory range described by @@ -166,9 +171,9 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); * 0 on success, or a negative errno code otherwise */ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - const struct drm_driver *req_driver) + bool primary, const struct drm_driver *req_driver) { - return aperture_remove_conflicting_devices(base, size, false, req_driver->name); + return aperture_remove_conflicting_devices(base, size, primary, req_driver->name); } EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers); diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 738eb558a97e..000e6704e3c7 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -430,7 +430,7 @@ static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we * might be able to read the framebuffer range from the device. */ - ret = drm_aperture_remove_framebuffers(&driver); + ret = drm_aperture_remove_framebuffers(false, &driver); if (ret) return ret; diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index 68050409dd26..690b90ec82b6 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -75,6 +75,7 @@ static int hyperv_setup_vram(struct hyperv_drm_device *hv, drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, screen_info.lfb_size, + false, &hyperv_driver); hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 119544d88b58..eea433ade79d 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -285,7 +285,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) * Remove early framebuffers (ie. simplefb). The framebuffer can be * located anywhere in RAM */ - ret = drm_aperture_remove_framebuffers(&meson_driver); + ret = drm_aperture_remove_framebuffers(false, &meson_driver); if (ret) goto free_drm; diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index d4a9b501e1bc..46168eccfac4 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -157,7 +157,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev) } /* the fw fb could be anywhere in memory */ - ret = drm_aperture_remove_framebuffers(dev->driver); + ret = drm_aperture_remove_framebuffers(false, dev->driver); if (ret) goto fini; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 8e12053a220b..813f9f8c8698 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -140,7 +140,7 @@ static int rockchip_drm_bind(struct device *dev) int ret; /* Remove existing drivers that may own the framebuffer memory. */ - ret = drm_aperture_remove_framebuffers(&rockchip_drm_driver); + ret = drm_aperture_remove_framebuffers(false, &rockchip_drm_driver); if (ret) { DRM_DEV_ERROR(dev, "Failed to remove existing framebuffers - %d.\n", diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index 0a09a85ac9d6..d7914f5122df 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -185,7 +185,7 @@ static int stm_drm_platform_probe(struct platform_device *pdev) DRM_DEBUG("%s\n", __func__); - ret = drm_aperture_remove_framebuffers(&drv_driver); + ret = drm_aperture_remove_framebuffers(false, &drv_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 5c483bbccbbb..7910c5853f0a 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -98,7 +98,7 @@ static int sun4i_drv_bind(struct device *dev) goto unbind_all; /* Remove early framebuffers (ie. simplefb) */ - ret = drm_aperture_remove_framebuffers(&sun4i_drv_driver); + ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver); if (ret) goto unbind_all; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 5fc55b9777cb..a1f909dac89a 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1252,7 +1252,7 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(&tegra_drm_driver); + err = drm_aperture_remove_framebuffers(false, &tegra_drm_driver); if (err < 0) goto hub; diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index b6384a5dfdbc..8c329c071c62 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -351,7 +351,7 @@ static int vc4_drm_bind(struct device *dev) return -EPROBE_DEFER; } - ret = drm_aperture_remove_framebuffers(driver); + ret = drm_aperture_remove_framebuffers(false, driver); if (ret) return ret; diff --git a/include/drm/drm_aperture.h b/include/drm/drm_aperture.h index cbe33b49fd5d..7096703c3949 100644 --- a/include/drm/drm_aperture.h +++ b/include/drm/drm_aperture.h @@ -13,13 +13,14 @@ int devm_aperture_acquire_from_firmware(struct drm_device *dev, resource_size_t resource_size_t size); int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - const struct drm_driver *req_driver); + bool primary, const struct drm_driver *req_driver); int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const struct drm_driver *req_driver); /** * drm_aperture_remove_framebuffers - remove all existing framebuffers + * @primary: also kick vga16fb if present * @req_driver: requesting DRM driver * * This function removes all graphics device drivers. Use this function on systems @@ -29,9 +30,9 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, * 0 on success, or a negative errno code otherwise */ static inline int -drm_aperture_remove_framebuffers(const struct drm_driver *req_driver) +drm_aperture_remove_framebuffers(bool primary, const struct drm_driver *req_driver) { - return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, + return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary, req_driver); } From 3e052a378b167982340e81af73980294d20d93b4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:09 +0000 Subject: [PATCH 2080/2093] Revert "drm/gma500: Use drm_aperture_remove_conflicting_pci_framebuffers" This reverts commit cccfcbb9e51af026529618e3bdc09b6beacac919 which is commit 80e993988b97fe794f3ec2be6db05fe30f9353c3 upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: I98437f0d8222293d93ad48311e8b719931f68c75 Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/gma500/psb_drv.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 000e6704e3c7..cd9c73f5a64a 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -424,17 +424,12 @@ static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* * We cannot yet easily find the framebuffer's location in memory. So - * remove all framebuffers here. Note that we still want the pci special - * handling to kick out vgacon. + * remove all framebuffers here. * * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we * might be able to read the framebuffer range from the device. */ - ret = drm_aperture_remove_framebuffers(false, &driver); - if (ret) - return ret; - - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); + ret = drm_aperture_remove_framebuffers(true, &driver); if (ret) return ret; From c0584fbc45e041e3bacac3a788a47c77a9b40f48 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:10 +0000 Subject: [PATCH 2081/2093] Revert "fbdev/radeon: use pci aperture helpers" This reverts commit 6db53af15444e7022640d7b8d5e7531d94e27a43 which is commit 9b539c4d1b921bc9c8c578d4d50f0a7e7874d384 upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: If14dd22c006f9d09857175a60c7f684409242515 Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/aty/radeon_base.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 50c384ce2883..8b28c9bddd97 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -2238,6 +2238,14 @@ static const struct bin_attribute edid2_attr = { .read = radeon_show_edid2, }; +static int radeon_kick_out_firmware_fb(struct pci_dev *pdev) +{ + resource_size_t base = pci_resource_start(pdev, 0); + resource_size_t size = pci_resource_len(pdev, 0); + + return aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); +} + static int radeonfb_pci_register(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2288,7 +2296,7 @@ static int radeonfb_pci_register(struct pci_dev *pdev, rinfo->fb_base_phys = pci_resource_start (pdev, 0); rinfo->mmio_base_phys = pci_resource_start (pdev, 2); - ret = aperture_remove_conflicting_pci_devices(pdev, KBUILD_MODNAME); + ret = radeon_kick_out_firmware_fb(pdev); if (ret) goto err_release_fb; From 900112a6dc0f54d9246919d4fff28ddeeaba8b77 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:11 +0000 Subject: [PATCH 2082/2093] Revert "drm/ast: Use drm_aperture_remove_conflicting_pci_framebuffers" This reverts commit cd1f889c99eee5a6fae671962a63bc89e68d7837 which is commit c1ebead36099deb85384f6fb262fe619a04cee73 upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: Id6345a15790f5e3209485004ebe071119684859b Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ast/ast_drv.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 800471f2a203..b9392f31e629 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -89,13 +89,27 @@ static const struct pci_device_id ast_pciidlist[] = { MODULE_DEVICE_TABLE(pci, ast_pciidlist); +static int ast_remove_conflicting_framebuffers(struct pci_dev *pdev) +{ + bool primary = false; + resource_size_t base, size; + + base = pci_resource_start(pdev, 0); + size = pci_resource_len(pdev, 0); +#ifdef CONFIG_X86 + primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; +#endif + + return drm_aperture_remove_conflicting_framebuffers(base, size, primary, &ast_driver); +} + static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct ast_private *ast; struct drm_device *dev; int ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &ast_driver); + ret = ast_remove_conflicting_framebuffers(pdev); if (ret) return ret; From 064668b55e3c7281b7d0c15b8db08fdb444a9cc9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2023 14:36:13 +0000 Subject: [PATCH 2083/2093] Revert "video/aperture: Only remove sysfb on the default vga pci device" This reverts commit 485ec8f8e1d8ae12aa1daa5ad345ba8940ad2db7 which is commit 5ae3716cfdcd286268133867f67d0803847acefc upstream. It breaks the Android ABI and can be brought back later in an abi-safe way if needed. Bug: 161946584 Change-Id: Iec66232fff97b07fd0c57975e8b1785710cfb395 Signed-off-by: Greg Kroah-Hartman --- drivers/video/aperture.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 5c94abdb1ad6..41e77de1ea82 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -332,16 +332,15 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; #endif - if (primary) - sysfb_disable(); - for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; base = pci_resource_start(pdev, bar); size = pci_resource_len(pdev, bar); - aperture_detach_devices(base, size); + ret = aperture_remove_conflicting_devices(base, size, primary, name); + if (ret) + return ret; } /* From 2e4a7791147161e963b341f2d6153f7ff80c7c1a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 28 Oct 2023 06:48:34 +0000 Subject: [PATCH 2084/2093] Revert "arm64: errata: Add Cortex-A520 speculative unprivileged load workaround" This reverts commit 6e3ae2927b432a3b7c8374f14dbc1bd9ebe4372c which is commit 471470bc7052d28ce125901877dd10e4c048e513 upstream. This change breaks the Android ABI, if it is needed in the future, it can be brought back in an abi-safe way. Change-Id: I1f79c77da78e5a0edde2bdebb862e4c9855175a0 Signed-off-by: Greg Kroah-Hartman --- Documentation/arm64/silicon-errata.rst | 2 -- arch/arm64/Kconfig | 13 ------------- arch/arm64/kernel/cpu_errata.c | 8 -------- arch/arm64/kernel/entry.S | 4 ---- arch/arm64/tools/cpucaps | 1 - 5 files changed, 28 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index af6c549ffb1b..e252004fb8b7 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -60,8 +60,6 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #1902691 | ARM64_ERRATUM_1902691 | +----------------+-----------------+-----------------+-----------------------------+ -| ARM | Cortex-A520 | #2966298 | ARM64_ERRATUM_2966298 | -+----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1fecc435e83c..7dafeacab872 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -972,19 +972,6 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. -config ARM64_ERRATUM_2966298 - bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load" - default y - help - This option adds the workaround for ARM Cortex-A520 erratum 2966298. - - On an affected Cortex-A520 core, a speculatively executed unprivileged - load might leak data from a privileged level via a cache side channel. - - Work around this problem by executing a TLBI before returning to EL0. - - If unsure, say Y. - config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 3f917124684c..8dbf3c21ea22 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -723,14 +723,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .cpu_enable = cpu_clear_bf16_from_user_emulation, }, #endif -#ifdef CONFIG_ARM64_ERRATUM_2966298 - { - .desc = "ARM erratum 2966298", - .capability = ARM64_WORKAROUND_2966298, - /* Cortex-A520 r0p0 - r0p1 */ - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1), - }, -#endif #ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38 { .desc = "AmpereOne erratum AC03_CPU_38", diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index de16fa917e1b..beb4db21c89c 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -419,10 +419,6 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] .if \el == 0 -alternative_if ARM64_WORKAROUND_2966298 - tlbi vale1, xzr - dsb nsh -alternative_else_nop_endif alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 ldr lr, [sp, #S_LR] add sp, sp, #PT_REGS_SIZE // restore sp diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index e77c6cd855b8..7b79a8b09504 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -71,7 +71,6 @@ WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 WORKAROUND_2658417 -WORKAROUND_2966298 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE WORKAROUND_TRBE_WRITE_OUT_OF_RANGE From 92a425f8ff658fba32dbb9edab7a71666d14a28f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 24 Oct 2023 12:43:53 +0000 Subject: [PATCH 2085/2093] Revert "netfilter: handle the connecting collision properly in nf_conntrack_proto_sctp" This reverts commit 00d35e6b1672b973a2bf8de1cb8167b287aa5797 which is commit 8e56b063c86569e51eed1c5681ce6361fa97fc7a uptream. It breaks the Android ABI so revert it for now, if it is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: Ia03ea49365e6ce063194738b22f77d2a403ea3a4 Signed-off-by: Greg Kroah-Hartman --- include/linux/netfilter/nf_conntrack_sctp.h | 1 - net/netfilter/nf_conntrack_proto_sctp.c | 43 +++++---------------- 2 files changed, 10 insertions(+), 34 deletions(-) diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index fb31312825ae..625f491b95de 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,7 +9,6 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; - u8 init[IP_CT_DIR_MAX]; u8 last_dir; u8 flags; }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c94a9971d790..7247af51bdfc 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, /* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, /* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, -/* cookie_echo */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, /* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -426,9 +426,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; - } else if (sch->type == SCTP_CID_COOKIE_ACK) { - ct->proto.sctp.init[dir] = 0; - ct->proto.sctp.init[!dir] = 0; } else if (sch->type == SCTP_CID_HEARTBEAT) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); @@ -477,18 +474,16 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } /* If it is an INIT or an INIT ACK note down the vtag */ - if (sch->type == SCTP_CID_INIT) { - struct sctp_inithdr _ih, *ih; + if (sch->type == SCTP_CID_INIT || + sch->type == SCTP_CID_INIT_ACK) { + struct sctp_inithdr _inithdr, *ih; - ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); - if (!ih) + ih = skb_header_pointer(skb, offset + sizeof(_sch), + sizeof(_inithdr), &_inithdr); + if (ih == NULL) goto out_unlock; - - if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) - ct->proto.sctp.init[!dir] = 0; - ct->proto.sctp.init[dir] = 1; - - pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); + pr_debug("Setting vtag %x for dir %d\n", + ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; /* don't renew timeout on init retransmit so @@ -499,24 +494,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, old_state == SCTP_CONNTRACK_CLOSED && nf_ct_is_confirmed(ct)) ignore = true; - } else if (sch->type == SCTP_CID_INIT_ACK) { - struct sctp_inithdr _ih, *ih; - __be32 vtag; - - ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); - if (!ih) - goto out_unlock; - - vtag = ct->proto.sctp.vtag[!dir]; - if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag) - goto out_unlock; - /* collision */ - if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && - vtag != ih->init_tag) - goto out_unlock; - - pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); - ct->proto.sctp.vtag[!dir] = ih->init_tag; } ct->proto.sctp.state = new_state; From 66a17692b1c94b0536d0cf1f8a403e483f96b451 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 28 Oct 2023 10:54:04 +0000 Subject: [PATCH 2086/2093] Revert "wifi: cfg80211: fix cqm_config access race" This reverts commit c797498e860e9a435a651bbf0789433684ce6dd8 which is commit 37c20b2effe987b806c8de6d12978e4ffeff026f upstream. It breaks the Android ABI so revert it for now, if it is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: Ida8b8621fb3099fd1b40aae5ad481139e7d7f173 Signed-off-by: Greg Kroah-Hartman --- include/net/cfg80211.h | 3 +- net/wireless/core.c | 14 +++---- net/wireless/core.h | 7 +--- net/wireless/nl80211.c | 95 +++++++++++++++--------------------------- 4 files changed, 43 insertions(+), 76 deletions(-) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 87783893327a..c57fb8454a7f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5977,8 +5977,7 @@ struct wireless_dev { } wext; #endif - struct wiphy_work cqm_rssi_work; - struct cfg80211_cqm_config __rcu *cqm_config; + struct cfg80211_cqm_config *cqm_config; struct list_head pmsr_list; spinlock_t pmsr_lock; diff --git a/net/wireless/core.c b/net/wireless/core.c index 2c7960467206..8a1f34e95c4f 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1176,11 +1176,16 @@ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state_reason); +void cfg80211_cqm_config_free(struct wireless_dev *wdev) +{ + kfree(wdev->cqm_config); + wdev->cqm_config = NULL; +} + static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, bool unregister_netdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - struct cfg80211_cqm_config *cqm_config; unsigned int link_id; ASSERT_RTNL(); @@ -1219,10 +1224,7 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, kfree_sensitive(wdev->wext.keys); wdev->wext.keys = NULL; #endif - wiphy_work_cancel(wdev->wiphy, &wdev->cqm_rssi_work); - /* deleted from the list, so can't be found from nl80211 any more */ - cqm_config = rcu_access_pointer(wdev->cqm_config); - kfree_rcu(cqm_config, rcu_head); + cfg80211_cqm_config_free(wdev); /* * Ensure that all events have been processed and @@ -1374,8 +1376,6 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; #endif - wiphy_work_init(&wdev->cqm_rssi_work, cfg80211_cqm_rssi_notify_work); - if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) wdev->ps = true; else diff --git a/net/wireless/core.h b/net/wireless/core.h index c85832d28199..6c3d25b7fa6e 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -295,17 +295,12 @@ struct cfg80211_beacon_registration { }; struct cfg80211_cqm_config { - struct rcu_head rcu_head; u32 rssi_hyst; s32 last_rssi_event_value; - enum nl80211_cqm_rssi_threshold_event last_rssi_event_type; int n_rssi_thresholds; s32 rssi_thresholds[]; }; -void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, - struct wiphy_work *work); - void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev); /* free object */ @@ -571,6 +566,8 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, #define CFG80211_DEV_WARN_ON(cond) ({bool __r = (cond); __r; }) #endif +void cfg80211_cqm_config_free(struct wireless_dev *wdev); + void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid); void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev); void cfg80211_pmsr_free_wk(struct work_struct *work); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 96205805da3c..1eb5643b68f5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12636,8 +12636,7 @@ static int nl80211_set_cqm_txe(struct genl_info *info, } static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_cqm_config *cqm_config) + struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; @@ -12646,7 +12645,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, int err; /* RSSI reporting disabled? */ - if (!cqm_config) + if (!wdev->cqm_config) return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); /* @@ -12655,7 +12654,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, * connection is established and enough beacons received to calculate * the average. */ - if (!cqm_config->last_rssi_event_value && + if (!wdev->cqm_config->last_rssi_event_value && wdev->links[0].client.current_bss && rdev->ops->get_station) { struct station_info sinfo = {}; @@ -12669,30 +12668,30 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, cfg80211_sinfo_release_content(&sinfo); if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) - cqm_config->last_rssi_event_value = + wdev->cqm_config->last_rssi_event_value = (s8) sinfo.rx_beacon_signal_avg; } - last = cqm_config->last_rssi_event_value; - hyst = cqm_config->rssi_hyst; - n = cqm_config->n_rssi_thresholds; + last = wdev->cqm_config->last_rssi_event_value; + hyst = wdev->cqm_config->rssi_hyst; + n = wdev->cqm_config->n_rssi_thresholds; for (i = 0; i < n; i++) { i = array_index_nospec(i, n); - if (last < cqm_config->rssi_thresholds[i]) + if (last < wdev->cqm_config->rssi_thresholds[i]) break; } low_index = i - 1; if (low_index >= 0) { low_index = array_index_nospec(low_index, n); - low = cqm_config->rssi_thresholds[low_index] - hyst; + low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; } else { low = S32_MIN; } if (i < n) { i = array_index_nospec(i, n); - high = cqm_config->rssi_thresholds[i] + hyst - 1; + high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; } else { high = S32_MAX; } @@ -12705,7 +12704,6 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, u32 hysteresis) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct cfg80211_cqm_config *cqm_config = NULL, *old; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; int i, err; @@ -12723,6 +12721,10 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; + wdev_lock(wdev); + cfg80211_cqm_config_free(wdev); + wdev_unlock(wdev); + if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) { if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */ return rdev_set_cqm_rssi_config(rdev, dev, 0, 0); @@ -12739,10 +12741,9 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, n_thresholds = 0; wdev_lock(wdev); - old = rcu_dereference_protected(wdev->cqm_config, - lockdep_is_held(&wdev->mtx)); - if (n_thresholds) { + struct cfg80211_cqm_config *cqm_config; + cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, n_thresholds), GFP_KERNEL); @@ -12757,18 +12758,11 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, flex_array_size(cqm_config, rssi_thresholds, n_thresholds)); - rcu_assign_pointer(wdev->cqm_config, cqm_config); - } else { - RCU_INIT_POINTER(wdev->cqm_config, NULL); + wdev->cqm_config = cqm_config; } - err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); - if (err) { - rcu_assign_pointer(wdev->cqm_config, old); - kfree_rcu(cqm_config, rcu_head); - } else { - kfree_rcu(old, rcu_head); - } + err = cfg80211_cqm_rssi_update(rdev, dev); + unlock: wdev_unlock(wdev); @@ -18813,8 +18807,9 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, s32 rssi_level, gfp_t gfp) { + struct sk_buff *msg; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_cqm_config *cqm_config; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); trace_cfg80211_cqm_rssi_notify(dev, rssi_event, rssi_level); @@ -18822,41 +18817,18 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH)) return; - rcu_read_lock(); - cqm_config = rcu_dereference(wdev->cqm_config); - if (cqm_config) { - cqm_config->last_rssi_event_value = rssi_level; - cqm_config->last_rssi_event_type = rssi_event; - wiphy_work_queue(wdev->wiphy, &wdev->cqm_rssi_work); + if (wdev->cqm_config) { + wdev->cqm_config->last_rssi_event_value = rssi_level; + + cfg80211_cqm_rssi_update(rdev, dev); + + if (rssi_level == 0) + rssi_level = wdev->cqm_config->last_rssi_event_value; } - rcu_read_unlock(); -} -EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); -void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) -{ - struct wireless_dev *wdev = container_of(work, struct wireless_dev, - cqm_rssi_work); - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - enum nl80211_cqm_rssi_threshold_event rssi_event; - struct cfg80211_cqm_config *cqm_config; - struct sk_buff *msg; - s32 rssi_level; - - wdev_lock(wdev); - cqm_config = rcu_dereference_protected(wdev->cqm_config, - lockdep_is_held(&wdev->mtx)); - if (!wdev->cqm_config) - goto unlock; - - cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); - - rssi_level = cqm_config->last_rssi_event_value; - rssi_event = cqm_config->last_rssi_event_type; - - msg = cfg80211_prepare_cqm(wdev->netdev, NULL, GFP_KERNEL); + msg = cfg80211_prepare_cqm(dev, NULL, gfp); if (!msg) - goto unlock; + return; if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, rssi_event)) @@ -18866,15 +18838,14 @@ void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) rssi_level)) goto nla_put_failure; - cfg80211_send_cqm(msg, GFP_KERNEL); + cfg80211_send_cqm(msg, gfp); - goto unlock; + return; nla_put_failure: nlmsg_free(msg); - unlock: - wdev_unlock(wdev); } +EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, u32 num_packets, From d2a83cf3764c20a689d69ee3221afb02835f33bd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Oct 2023 10:33:26 +0000 Subject: [PATCH 2087/2093] Revert "scsi: sd: Do not issue commands to suspended disks on shutdown" This reverts commit deacabef6834e7311e901b1924230af502244e02 which is commit 99398d2070ab03d13f90b758ad397e19a65fffb0 upstream. It breaks the Android ABI so revert it for now, if it is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I0134634ac6acd636d23f65d3f1bc4d3b57ff1206 Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/sd.c | 17 ++++------------- drivers/scsi/sd.h | 1 - 2 files changed, 4 insertions(+), 14 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4c02aaf6a72d..e0efeed178d8 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3646,8 +3646,7 @@ static int sd_remove(struct device *dev) device_del(&sdkp->disk_dev); del_gendisk(sdkp->disk); - if (!sdkp->suspended) - sd_shutdown(dev); + sd_shutdown(dev); put_disk(sdkp->disk); return 0; @@ -3778,9 +3777,6 @@ static int sd_suspend_common(struct device *dev, bool runtime) ret = 0; } - if (!ret) - sdkp->suspended = true; - return ret; } @@ -3800,26 +3796,21 @@ static int sd_suspend_runtime(struct device *dev) static int sd_resume(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret = 0; + int ret; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; - if (!sd_do_start_stop(sdkp->device, runtime)) { - sdkp->suspended = false; + if (!sd_do_start_stop(sdkp->device, runtime)) return 0; - } if (!sdkp->device->no_start_on_resume) { sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); } - if (!ret) { + if (!ret) opal_unlock_from_suspend(sdkp->opal_dev); - sdkp->suspended = false; - } - return ret; } diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 1e4238b8f2a5..9795398c83cf 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -131,7 +131,6 @@ struct scsi_disk { u8 provisioning_mode; u8 zeroing_mode; u8 nr_actuators; /* Number of actuators */ - bool suspended; /* Disk is suspended (stopped) */ unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ From 88af92d5d2cfd80f07d84988752db5acbf371390 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Oct 2023 10:33:30 +0000 Subject: [PATCH 2088/2093] Revert "scsi: sd: Differentiate system and runtime start/stop management" This reverts commit 8de6d8449ae959cfea0b20bd7a1cae1041d15a0d which is commit 3cc2ffe5c16dc65dfac354bc5b5bc98d3b397567 upstream. It breaks the Android ABI so revert it for now, if it is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I080e6f1bf683bb4b40e1178835d07284e2578ae5 Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-scsi.c | 3 +- drivers/firewire/sbp2.c | 9 ++-- drivers/scsi/sd.c | 90 ++++++++------------------------------ include/scsi/scsi_device.h | 5 +-- 4 files changed, 23 insertions(+), 84 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 405f9f76bf42..56cf555fd70a 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1092,8 +1092,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) * will be woken up by ata_port_pm_resume() with a port reset * and device revalidation. */ - sdev->manage_system_start_stop = true; - sdev->manage_runtime_start_stop = true; + sdev->manage_start_stop = 1; sdev->no_start_on_resume = 1; } diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index e322a326546b..60051c0cabea 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -81,8 +81,7 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device " * * - power condition * Set the power condition field in the START STOP UNIT commands sent by - * sd_mod on suspend, resume, and shutdown (if manage_system_start_stop or - * manage_runtime_start_stop is on). + * sd_mod on suspend, resume, and shutdown (if manage_start_stop is on). * Some disks need this to spin down or to resume properly. * * - override internal blacklist @@ -1518,10 +1517,8 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->use_10_for_rw = 1; - if (sbp2_param_exclusive_login) { - sdev->manage_system_start_stop = true; - sdev->manage_runtime_start_stop = true; - } + if (sbp2_param_exclusive_login) + sdev->manage_start_stop = 1; if (sdev->type == TYPE_ROM) sdev->use_10_for_ms = 1; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e0efeed178d8..350936860554 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -213,32 +213,18 @@ cache_type_store(struct device *dev, struct device_attribute *attr, } static ssize_t -manage_start_stop_show(struct device *dev, - struct device_attribute *attr, char *buf) +manage_start_stop_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; - return sysfs_emit(buf, "%u\n", - sdp->manage_system_start_stop && - sdp->manage_runtime_start_stop); -} -static DEVICE_ATTR_RO(manage_start_stop); - -static ssize_t -manage_system_start_stop_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct scsi_disk *sdkp = to_scsi_disk(dev); - struct scsi_device *sdp = sdkp->device; - - return sysfs_emit(buf, "%u\n", sdp->manage_system_start_stop); + return sprintf(buf, "%u\n", sdp->manage_start_stop); } static ssize_t -manage_system_start_stop_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +manage_start_stop_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; @@ -250,42 +236,11 @@ manage_system_start_stop_store(struct device *dev, if (kstrtobool(buf, &v)) return -EINVAL; - sdp->manage_system_start_stop = v; + sdp->manage_start_stop = v; return count; } -static DEVICE_ATTR_RW(manage_system_start_stop); - -static ssize_t -manage_runtime_start_stop_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct scsi_disk *sdkp = to_scsi_disk(dev); - struct scsi_device *sdp = sdkp->device; - - return sysfs_emit(buf, "%u\n", sdp->manage_runtime_start_stop); -} - -static ssize_t -manage_runtime_start_stop_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct scsi_disk *sdkp = to_scsi_disk(dev); - struct scsi_device *sdp = sdkp->device; - bool v; - - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - - if (kstrtobool(buf, &v)) - return -EINVAL; - - sdp->manage_runtime_start_stop = v; - - return count; -} -static DEVICE_ATTR_RW(manage_runtime_start_stop); +static DEVICE_ATTR_RW(manage_start_stop); static ssize_t allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -617,8 +572,6 @@ static struct attribute *sd_disk_attrs[] = { &dev_attr_FUA.attr, &dev_attr_allow_restart.attr, &dev_attr_manage_start_stop.attr, - &dev_attr_manage_system_start_stop.attr, - &dev_attr_manage_runtime_start_stop.attr, &dev_attr_protection_type.attr, &dev_attr_protection_mode.attr, &dev_attr_app_tag_own.attr, @@ -3723,20 +3676,13 @@ static void sd_shutdown(struct device *dev) sd_sync_cache(sdkp, NULL); } - if (system_state != SYSTEM_RESTART && - sdkp->device->manage_system_start_stop) { + if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) { sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } } -static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime) -{ - return (sdev->manage_system_start_stop && !runtime) || - (sdev->manage_runtime_start_stop && runtime); -} - -static int sd_suspend_common(struct device *dev, bool runtime) +static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) { struct scsi_disk *sdkp = dev_get_drvdata(dev); struct scsi_sense_hdr sshdr; @@ -3768,12 +3714,12 @@ static int sd_suspend_common(struct device *dev, bool runtime) } } - if (sd_do_start_stop(sdkp->device, runtime)) { + if (sdkp->device->manage_start_stop) { if (!sdkp->device->silence_suspend) sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); /* an error is not worth aborting a system sleep */ ret = sd_start_stop_device(sdkp, 0); - if (!runtime) + if (ignore_stop_errors) ret = 0; } @@ -3785,23 +3731,23 @@ static int sd_suspend_system(struct device *dev) if (pm_runtime_suspended(dev)) return 0; - return sd_suspend_common(dev, false); + return sd_suspend_common(dev, true); } static int sd_suspend_runtime(struct device *dev) { - return sd_suspend_common(dev, true); + return sd_suspend_common(dev, false); } -static int sd_resume(struct device *dev, bool runtime) +static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret; + int ret = 0; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; - if (!sd_do_start_stop(sdkp->device, runtime)) + if (!sdkp->device->manage_start_stop) return 0; if (!sdkp->device->no_start_on_resume) { @@ -3819,7 +3765,7 @@ static int sd_resume_system(struct device *dev) if (pm_runtime_suspended(dev)) return 0; - return sd_resume(dev, false); + return sd_resume(dev); } static int sd_resume_runtime(struct device *dev) @@ -3846,7 +3792,7 @@ static int sd_resume_runtime(struct device *dev) "Failed to clear sense data\n"); } - return sd_resume(dev, true); + return sd_resume(dev); } /** diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index b6610b2b66bd..506af7a1762e 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -162,10 +162,6 @@ struct scsi_device { * pass settings from slave_alloc to scsi * core. */ unsigned int eh_timeout; /* Error handling timeout */ - - bool manage_system_start_stop; /* Let HLD (sd) manage system start/stop */ - bool manage_runtime_start_stop; /* Let HLD (sd) manage runtime start/stop */ - unsigned removable:1; unsigned changed:1; /* Data invalid due to media change */ unsigned busy:1; /* Used to prevent races */ @@ -197,6 +193,7 @@ struct scsi_device { unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */ unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ + unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */ unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */ unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */ unsigned no_uld_attach:1; /* disable connecting to upper level drivers */ From a39cabc3864fb1ee64092569773d12400478b647 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Oct 2023 16:12:16 +0000 Subject: [PATCH 2089/2093] Revert "ata,scsi: do not issue START STOP UNIT on resume" This reverts commit dc3354c961badffc24117390ed2d4d12988d171b which is commit 0a8589055936d8feb56477123a8373ac634018fa upstream. It breaks the Android ABI so revert it for now, if it is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Signed-off-by: Greg Kroah-Hartman Change-Id: I667c8e367971886e847b2240d2c1efcf6a2fe92c --- drivers/ata/libata-scsi.c | 7 ------- drivers/scsi/sd.c | 9 +++------ include/scsi/scsi_device.h | 1 - 3 files changed, 3 insertions(+), 14 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 56cf555fd70a..c73e8a77c157 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1086,14 +1086,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) } } else { sdev->sector_size = ata_id_logical_sector_size(dev->id); - /* - * Stop the drive on suspend but do not issue START STOP UNIT - * on resume as this is not necessary and may fail: the device - * will be woken up by ata_port_pm_resume() with a port reset - * and device revalidation. - */ sdev->manage_start_stop = 1; - sdev->no_start_on_resume = 1; } /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 350936860554..0efc659b8336 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3742,7 +3742,7 @@ static int sd_suspend_runtime(struct device *dev) static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - int ret = 0; + int ret; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; @@ -3750,11 +3750,8 @@ static int sd_resume(struct device *dev) if (!sdkp->device->manage_start_stop) return 0; - if (!sdkp->device->no_start_on_resume) { - sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); - ret = sd_start_stop_device(sdkp, 1); - } - + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + ret = sd_start_stop_device(sdkp, 1); if (!ret) opal_unlock_from_suspend(sdkp->opal_dev); return ret; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 506af7a1762e..26c2ac1ca6a1 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -194,7 +194,6 @@ struct scsi_device { unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */ - unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */ unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */ unsigned no_uld_attach:1; /* disable connecting to upper level drivers */ unsigned select_no_atn:1; From d9fef973fe1c5a1c575832a337764e9a51b174e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Oct 2023 16:27:14 +0000 Subject: [PATCH 2090/2093] Revert "net: release reference to inet6_dev pointer" This reverts commit b6912642746d2c48b80c205b26145839a3a412ed which is commit 5cb249686e67dbef3ffe53887fa725eefc5a7144 upstream. It breaks the Android ABI, and is already merged in the non-LTS branch in an abi-safe way. Bug: 161946584 Change-Id: I563f7eb7ffb01d9681f6a1dbb0252ca32b94f856 Signed-off-by: Greg Kroah-Hartman --- net/ipv6/addrconf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c17764600ad5..91fe6b4c9de4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2756,7 +2756,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) } if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) - goto put; + return; /* * Two things going on here: From ee96408e49390e9ac13841aeb46dba8bbe1c4d51 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Oct 2023 16:27:16 +0000 Subject: [PATCH 2091/2093] Revert "net: change accept_ra_min_rtr_lft to affect all RA lifetimes" This reverts commit bad004c384b7f15fa84a6613868c85e3efcf016e which is commit 5027d54a9c30bc7ec808360378e2b4753f053f25 upstream. It breaks the Android ABI, and is already merged in the non-LTS branch in an abi-safe way. Bug: 161946584 Change-Id: I9f0f611a3ecbae0ae154ae465ff7472d8e98a1d8 Signed-off-by: Greg Kroah-Hartman --- Documentation/networking/ip-sysctl.rst | 8 ++++---- include/linux/ipv6.h | 2 +- include/uapi/linux/ipv6.h | 2 +- net/ipv6/addrconf.c | 13 +++++-------- net/ipv6/ndisc.c | 27 +++++++++++++++----------- 5 files changed, 27 insertions(+), 25 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index f5f7a464605f..b0e9210f7a28 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2148,11 +2148,11 @@ accept_ra_min_hop_limit - INTEGER Default: 1 -accept_ra_min_lft - INTEGER - Minimum acceptable lifetime value in Router Advertisement. +accept_ra_min_rtr_lft - INTEGER + Minimum acceptable router lifetime in Router Advertisement. - RA sections with a lifetime less than this value shall be - ignored. Zero lifetimes stay unaffected. + RAs with a router lifetime less than this value shall be + ignored. RAs with a router lifetime of 0 are unaffected. Default: 0 diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 40365a42fdf8..d03c886ab88a 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -34,7 +34,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; - __s32 accept_ra_min_lft; + __s32 accept_ra_min_rtr_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 4fa8511b1e35..2038eff9b63f 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -198,7 +198,7 @@ enum { DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, - DEVCONF_ACCEPT_RA_MIN_LFT, + DEVCONF_ACCEPT_RA_MIN_RTR_LFT, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 91fe6b4c9de4..ecff66846dd2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -202,7 +202,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_lft = 0, + .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -264,7 +264,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_lft = 0, + .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -2755,9 +2755,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) return; } - if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) - return; - /* * Two things going on here: * 1) Add routes for on-link prefixes @@ -5628,7 +5625,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; - array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft; + array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft; } static inline size_t inet6_ifla6_size(void) @@ -6823,8 +6820,8 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { - .procname = "accept_ra_min_lft", - .data = &ipv6_devconf.accept_ra_min_lft, + .procname = "accept_ra_min_rtr_lft", + .data = &ipv6_devconf.accept_ra_min_rtr_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 8c5a99fe6803..f13d0d2d5da2 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1284,6 +1284,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", @@ -1291,6 +1293,13 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_linkparms; } + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto skip_linkparms; + } + #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { @@ -1331,14 +1340,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_defrtr; } - lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto skip_defrtr; - } - /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ @@ -1501,6 +1502,13 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto out; } + if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { + ND_PRINTK(2, info, + "RA: router lifetime (%ds) is too short: %s\n", + lifetime, skb->dev->name); + goto out; + } + #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, @@ -1525,9 +1533,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (ri->prefix_len == 0 && !in6_dev->cnf.accept_ra_defrtr) continue; - if (ri->lifetime != 0 && - ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft) - continue; if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) From c8da9c614c29cf80749e5eb65d44f2fa7d6a1770 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Oct 2023 16:27:17 +0000 Subject: [PATCH 2092/2093] Revert "net: add sysctl accept_ra_min_rtr_lft" This reverts commit ec4162bb70189648ac39dd5a13d4f16e78b15544 which is commit 1671bcfd76fdc0b9e65153cf759153083755fe4c upstream. It breaks the Android ABI, and is already merged in the non-LTS branch in an abi-safe way. Bug: 161946584 Change-Id: Ie689c535c1f7c1c4a1e6af6805f400da625104c7 Signed-off-by: Greg Kroah-Hartman --- Documentation/networking/ip-sysctl.rst | 8 -------- include/linux/ipv6.h | 1 - include/uapi/linux/ipv6.h | 1 - net/ipv6/addrconf.c | 10 ---------- net/ipv6/ndisc.c | 18 ++---------------- 5 files changed, 2 insertions(+), 36 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b0e9210f7a28..3301288a7c69 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2148,14 +2148,6 @@ accept_ra_min_hop_limit - INTEGER Default: 1 -accept_ra_min_rtr_lft - INTEGER - Minimum acceptable router lifetime in Router Advertisement. - - RAs with a router lifetime less than this value shall be - ignored. RAs with a router lifetime of 0 are unaffected. - - Default: 0 - accept_ra_pinfo - BOOLEAN Learn Prefix Information in Router Advertisement. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index d03c886ab88a..ccd063754c14 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -34,7 +34,6 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; - __s32 accept_ra_min_rtr_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 2038eff9b63f..53326dfc59ec 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -198,7 +198,6 @@ enum { DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, - DEVCONF_ACCEPT_RA_MIN_RTR_LFT, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ecff66846dd2..a7059f6b43ad 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -202,7 +202,6 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -264,7 +263,6 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, - .accept_ra_min_rtr_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -5625,7 +5623,6 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; - array[DEVCONF_ACCEPT_RA_MIN_RTR_LFT] = cnf->accept_ra_min_rtr_lft; } static inline size_t inet6_ifla6_size(void) @@ -6819,13 +6816,6 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "accept_ra_min_rtr_lft", - .data = &ipv6_devconf.accept_ra_min_rtr_lft, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f13d0d2d5da2..16adce999741 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1284,8 +1284,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", @@ -1293,13 +1291,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_linkparms; } - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto skip_linkparms; - } - #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { @@ -1352,6 +1343,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto skip_defrtr; } + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); + #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ @@ -1502,13 +1495,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) goto out; } - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_rtr_lft) { - ND_PRINTK(2, info, - "RA: router lifetime (%ds) is too short: %s\n", - lifetime, skb->dev->name); - goto out; - } - #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, From d0be54afac873c451f9d9baf524aa3191885f7ce Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 31 Oct 2023 08:55:02 +0000 Subject: [PATCH 2093/2093] ANDROID: mm/mempolicy.c fix up conversion to queue_folios_pte_range In commit dc0a8466cd11 ("mm/mempolicy: convert queue_pages_pte_range() to queue_folios_pte_range()"), queue_folios_pte_range was used, but due to other upstream changes backported to the android14-6.1 branch, not all of them were caught. This fixes up the remaining instance, fixing the build. Fixes: dc0a8466cd11 ("mm/mempolicy: convert queue_pages_pte_range() to queue_folios_pte_range()") Change-Id: I007bd7ad6a1e848d715b7a5a06a98d3603238148 Signed-off-by: Greg Kroah-Hartman --- mm/mempolicy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b4011bdecffd..b7fb134c1f22 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -710,7 +710,7 @@ static const struct mm_walk_ops queue_pages_walk_ops = { static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_pages_hugetlb, - .pmd_entry = queue_pages_pte_range, + .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, };